diff options
691 files changed, 59927 insertions, 8061 deletions
diff --git a/.gitignore b/.gitignore index f6050b88e95b..be92dfa89957 100644 --- a/.gitignore +++ b/.gitignore @@ -122,3 +122,6 @@ all.config # Kdevelop4 *.kdev4 + +# fetched Android config fragments +kernel/configs/android-*.cfg diff --git a/Documentation/ABI/testing/procfs-concurrent_time b/Documentation/ABI/testing/procfs-concurrent_time new file mode 100644 index 000000000000..55b414289b40 --- /dev/null +++ b/Documentation/ABI/testing/procfs-concurrent_time @@ -0,0 +1,16 @@ +What: /proc/uid_concurrent_active_time +Date: December 2018 +Contact: Connor O'Brien <connoro@google.com> +Description: + The /proc/uid_concurrent_active_time file displays aggregated cputime + numbers for each uid, broken down by the total number of cores that were + active while the uid's task was running. + +What: /proc/uid_concurrent_policy_time +Date: December 2018 +Contact: Connor O'Brien <connoro@google.com> +Description: + The /proc/uid_concurrent_policy_time file displays aggregated cputime + numbers for each uid, broken down based on the cpufreq policy + of the core used by the uid's task and the number of cores associated + with that policy that were active while the uid's task was running. diff --git a/Documentation/ABI/testing/sysfs-block-zram b/Documentation/ABI/testing/sysfs-block-zram index c1513c756af1..14b2bf2e5105 100644 --- a/Documentation/ABI/testing/sysfs-block-zram +++ b/Documentation/ABI/testing/sysfs-block-zram @@ -98,3 +98,42 @@ Description: The backing_dev file is read-write and set up backing device for zram to write incompressible pages. For using, user should enable CONFIG_ZRAM_WRITEBACK. + +What: /sys/block/zram<id>/idle +Date: November 2018 +Contact: Minchan Kim <minchan@kernel.org> +Description: + idle file is write-only and mark zram slot as idle. + If system has mounted debugfs, user can see which slots + are idle via /sys/kernel/debug/zram/zram<id>/block_state + +What: /sys/block/zram<id>/writeback +Date: November 2018 +Contact: Minchan Kim <minchan@kernel.org> +Description: + The writeback file is write-only and trigger idle and/or + huge page writeback to backing device. + +What: /sys/block/zram<id>/bd_stat +Date: November 2018 +Contact: Minchan Kim <minchan@kernel.org> +Description: + The bd_stat file is read-only and represents backing device's + statistics (bd_count, bd_reads, bd_writes) in a format + similar to block layer statistics file format. + +What: /sys/block/zram<id>/writeback_limit_enable +Date: November 2018 +Contact: Minchan Kim <minchan@kernel.org> +Description: + The writeback_limit_enable file is read-write and specifies + eanbe of writeback_limit feature. "1" means eable the feature. + No limit "0" is the initial state. + +What: /sys/block/zram<id>/writeback_limit +Date: November 2018 +Contact: Minchan Kim <minchan@kernel.org> +Description: + The writeback_limit file is read-write and specifies the maximum + amount of writeback ZRAM can do. The limit could be changed + in run time. diff --git a/Documentation/ABI/testing/sysfs-class-dual-role-usb b/Documentation/ABI/testing/sysfs-class-dual-role-usb new file mode 100644 index 000000000000..a900fd75430c --- /dev/null +++ b/Documentation/ABI/testing/sysfs-class-dual-role-usb @@ -0,0 +1,71 @@ +What: /sys/class/dual_role_usb/.../ +Date: June 2015 +Contact: Badhri Jagan Sridharan<badhri@google.com> +Description: + Provide a generic interface to monitor and change + the state of dual role usb ports. The name here + refers to the name mentioned in the + dual_role_phy_desc that is passed while registering + the dual_role_phy_intstance through + devm_dual_role_instance_register. + +What: /sys/class/dual_role_usb/.../supported_modes +Date: June 2015 +Contact: Badhri Jagan Sridharan<badhri@google.com> +Description: + This is a static node, once initialized this + is not expected to change during runtime. "dfp" + refers to "downstream facing port" i.e. port can + only act as host. "ufp" refers to "upstream + facing port" i.e. port can only act as device. + "dfp ufp" refers to "dual role port" i.e. the port + can either be a host port or a device port. + +What: /sys/class/dual_role_usb/.../mode +Date: June 2015 +Contact: Badhri Jagan Sridharan<badhri@google.com> +Description: + The mode node refers to the current mode in which the + port is operating. "dfp" for host ports. "ufp" for device + ports and "none" when cable is not connected. + + On devices where the USB mode is software-controllable, + userspace can change the mode by writing "dfp" or "ufp". + On devices where the USB mode is fixed in hardware, + this attribute is read-only. + +What: /sys/class/dual_role_usb/.../power_role +Date: June 2015 +Contact: Badhri Jagan Sridharan<badhri@google.com> +Description: + The power_role node mentions whether the port + is "sink"ing or "source"ing power. "none" if + they are not connected. + + On devices implementing USB Power Delivery, + userspace can control the power role by writing "sink" or + "source". On devices without USB-PD, this attribute is + read-only. + +What: /sys/class/dual_role_usb/.../data_role +Date: June 2015 +Contact: Badhri Jagan Sridharan<badhri@google.com> +Description: + The data_role node mentions whether the port + is acting as "host" or "device" for USB data connection. + "none" if there is no active data link. + + On devices implementing USB Power Delivery, userspace + can control the data role by writing "host" or "device". + On devices without USB-PD, this attribute is read-only + +What: /sys/class/dual_role_usb/.../powers_vconn +Date: June 2015 +Contact: Badhri Jagan Sridharan<badhri@google.com> +Description: + The powers_vconn node mentions whether the port + is supplying power for VCONN pin. + + On devices with software control of VCONN, + userspace can disable the power supply to VCONN by writing "n", + or enable the power supply by writing "y". diff --git a/Documentation/ABI/testing/sysfs-fs-f2fs b/Documentation/ABI/testing/sysfs-fs-f2fs index 11b7f4ebea7c..a6fe7368b26c 100644 --- a/Documentation/ABI/testing/sysfs-fs-f2fs +++ b/Documentation/ABI/testing/sysfs-fs-f2fs @@ -51,6 +51,26 @@ Description: Controls the dirty page count condition for the in-place-update policies. +What: /sys/fs/f2fs/<disk>/min_seq_blocks +Date: August 2018 +Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> +Description: + Controls the dirty page count condition for batched sequential + writes in ->writepages. + + +What: /sys/fs/f2fs/<disk>/min_hot_blocks +Date: March 2017 +Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> +Description: + Controls the dirty page count condition for redefining hot data. + +What: /sys/fs/f2fs/<disk>/min_ssr_sections +Date: October 2017 +Contact: "Chao Yu" <yuchao0@huawei.com> +Description: + Controls the fee section threshold to trigger SSR allocation. + What: /sys/fs/f2fs/<disk>/max_small_discards Date: November 2013 Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com> @@ -66,12 +86,28 @@ Description: The unit size is one block, now only support configuring in range of [1, 512]. +What: /sys/fs/f2fs/<disk>/umount_discard_timeout +Date: January 2019 +Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> +Description: + Set timeout to issue discard commands during umount. + Default: 5 secs + What: /sys/fs/f2fs/<disk>/max_victim_search Date: January 2014 Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com> Description: Controls the number of trials to find a victim segment. +What: /sys/fs/f2fs/<disk>/migration_granularity +Date: October 2018 +Contact: "Chao Yu" <yuchao0@huawei.com> +Description: + Controls migration granularity of garbage collection on large + section, it can let GC move partial segment{s} of one section + in one GC cycle, so that dispersing heavy overhead GC to + multiple lightweight one. + What: /sys/fs/f2fs/<disk>/dir_level Date: March 2014 Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com> @@ -89,6 +125,7 @@ Date: February 2015 Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> Description: Controls the trimming rate in batch mode. + <deprecated> What: /sys/fs/f2fs/<disk>/cp_interval Date: October 2015 @@ -100,7 +137,28 @@ What: /sys/fs/f2fs/<disk>/idle_interval Date: January 2016 Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> Description: - Controls the idle timing. + Controls the idle timing for all paths other than + discard and gc path. + +What: /sys/fs/f2fs/<disk>/discard_idle_interval +Date: September 2018 +Contact: "Chao Yu" <yuchao0@huawei.com> +Contact: "Sahitya Tummala" <stummala@codeaurora.org> +Description: + Controls the idle timing for discard path. + +What: /sys/fs/f2fs/<disk>/gc_idle_interval +Date: September 2018 +Contact: "Chao Yu" <yuchao0@huawei.com> +Contact: "Sahitya Tummala" <stummala@codeaurora.org> +Description: + Controls the idle timing for gc path. + +What: /sys/fs/f2fs/<disk>/iostat_enable +Date: August 2017 +Contact: "Chao Yu" <yuchao0@huawei.com> +Description: + Controls to enable/disable IO stat. What: /sys/fs/f2fs/<disk>/ra_nid_pages Date: October 2015 @@ -122,6 +180,12 @@ Contact: "Shuoran Liu" <liushuoran@huawei.com> Description: Shows total written kbytes issued to disk. +What: /sys/fs/f2fs/<disk>/feature +Date: July 2017 +Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> +Description: + Shows all enabled features in current device. + What: /sys/fs/f2fs/<disk>/inject_rate Date: May 2016 Contact: "Sheng Yong" <shengyong1@huawei.com> @@ -138,7 +202,18 @@ What: /sys/fs/f2fs/<disk>/reserved_blocks Date: June 2017 Contact: "Chao Yu" <yuchao0@huawei.com> Description: - Controls current reserved blocks in system. + Controls target reserved blocks in system, the threshold + is soft, it could exceed current available user space. + +What: /sys/fs/f2fs/<disk>/current_reserved_blocks +Date: October 2017 +Contact: "Yunlong Song" <yunlong.song@huawei.com> +Contact: "Chao Yu" <yuchao0@huawei.com> +Description: + Shows current reserved blocks in system, it may be temporarily + smaller than target_reserved_blocks, but will gradually + increase to target_reserved_blocks when more free blocks are + freed by user later. What: /sys/fs/f2fs/<disk>/gc_urgent Date: August 2017 @@ -151,3 +226,20 @@ Date: August 2017 Contact: "Jaegeuk Kim" <jaegeuk@kernel.org> Description: Controls sleep time of GC urgent mode + +What: /sys/fs/f2fs/<disk>/readdir_ra +Date: November 2017 +Contact: "Sheng Yong" <shengyong1@huawei.com> +Description: + Controls readahead inode block in readdir. + +What: /sys/fs/f2fs/<disk>/extension_list +Date: Feburary 2018 +Contact: "Chao Yu" <yuchao0@huawei.com> +Description: + Used to control configure extension list: + - Query: cat /sys/fs/f2fs/<disk>/extension_list + - Add: echo '[h/c]extension' > /sys/fs/f2fs/<disk>/extension_list + - Del: echo '[h/c]!extension' > /sys/fs/f2fs/<disk>/extension_list + - [h] means add/del hot file extension + - [c] means add/del cold file extension diff --git a/Documentation/ABI/testing/sysfs-kernel-wakeup_reasons b/Documentation/ABI/testing/sysfs-kernel-wakeup_reasons new file mode 100644 index 000000000000..acb19b91c192 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-wakeup_reasons @@ -0,0 +1,16 @@ +What: /sys/kernel/wakeup_reasons/last_resume_reason +Date: February 2014 +Contact: Ruchi Kandoi <kandoiruchi@google.com> +Description: + The /sys/kernel/wakeup_reasons/last_resume_reason is + used to report wakeup reasons after system exited suspend. + +What: /sys/kernel/wakeup_reasons/last_suspend_time +Date: March 2015 +Contact: jinqian <jinqian@google.com> +Description: + The /sys/kernel/wakeup_reasons/last_suspend_time is + used to report time spent in last suspend cycle. It contains + two numbers (in seconds) separated by space. First number is + the time spent in suspend and resume processes. Second number + is the time spent in sleep state.
\ No newline at end of file diff --git a/Documentation/accounting/psi.txt b/Documentation/accounting/psi.txt new file mode 100644 index 000000000000..4fb40fe94828 --- /dev/null +++ b/Documentation/accounting/psi.txt @@ -0,0 +1,180 @@ +================================ +PSI - Pressure Stall Information +================================ + +:Date: April, 2018 +:Author: Johannes Weiner <hannes@cmpxchg.org> + +When CPU, memory or IO devices are contended, workloads experience +latency spikes, throughput losses, and run the risk of OOM kills. + +Without an accurate measure of such contention, users are forced to +either play it safe and under-utilize their hardware resources, or +roll the dice and frequently suffer the disruptions resulting from +excessive overcommit. + +The psi feature identifies and quantifies the disruptions caused by +such resource crunches and the time impact it has on complex workloads +or even entire systems. + +Having an accurate measure of productivity losses caused by resource +scarcity aids users in sizing workloads to hardware--or provisioning +hardware according to workload demand. + +As psi aggregates this information in realtime, systems can be managed +dynamically using techniques such as load shedding, migrating jobs to +other systems or data centers, or strategically pausing or killing low +priority or restartable batch jobs. + +This allows maximizing hardware utilization without sacrificing +workload health or risking major disruptions such as OOM kills. + +Pressure interface +================== + +Pressure information for each resource is exported through the +respective file in /proc/pressure/ -- cpu, memory, and io. + +The format for CPU is as such: + +some avg10=0.00 avg60=0.00 avg300=0.00 total=0 + +and for memory and IO: + +some avg10=0.00 avg60=0.00 avg300=0.00 total=0 +full avg10=0.00 avg60=0.00 avg300=0.00 total=0 + +The "some" line indicates the share of time in which at least some +tasks are stalled on a given resource. + +The "full" line indicates the share of time in which all non-idle +tasks are stalled on a given resource simultaneously. In this state +actual CPU cycles are going to waste, and a workload that spends +extended time in this state is considered to be thrashing. This has +severe impact on performance, and it's useful to distinguish this +situation from a state where some tasks are stalled but the CPU is +still doing productive work. As such, time spent in this subset of the +stall state is tracked separately and exported in the "full" averages. + +The ratios are tracked as recent trends over ten, sixty, and three +hundred second windows, which gives insight into short term events as +well as medium and long term trends. The total absolute stall time is +tracked and exported as well, to allow detection of latency spikes +which wouldn't necessarily make a dent in the time averages, or to +average trends over custom time frames. + +Monitoring for pressure thresholds +================================== + +Users can register triggers and use poll() to be woken up when resource +pressure exceeds certain thresholds. + +A trigger describes the maximum cumulative stall time over a specific +time window, e.g. 100ms of total stall time within any 500ms window to +generate a wakeup event. + +To register a trigger user has to open psi interface file under +/proc/pressure/ representing the resource to be monitored and write the +desired threshold and time window. The open file descriptor should be +used to wait for trigger events using select(), poll() or epoll(). +The following format is used: + +<some|full> <stall amount in us> <time window in us> + +For example writing "some 150000 1000000" into /proc/pressure/memory +would add 150ms threshold for partial memory stall measured within +1sec time window. Writing "full 50000 1000000" into /proc/pressure/io +would add 50ms threshold for full io stall measured within 1sec time window. + +Triggers can be set on more than one psi metric and more than one trigger +for the same psi metric can be specified. However for each trigger a separate +file descriptor is required to be able to poll it separately from others, +therefore for each trigger a separate open() syscall should be made even +when opening the same psi interface file. + +Monitors activate only when system enters stall state for the monitored +psi metric and deactivates upon exit from the stall state. While system is +in the stall state psi signal growth is monitored at a rate of 10 times per +tracking window. + +The kernel accepts window sizes ranging from 500ms to 10s, therefore min +monitoring update interval is 50ms and max is 1s. Min limit is set to +prevent overly frequent polling. Max limit is chosen as a high enough number +after which monitors are most likely not needed and psi averages can be used +instead. + +When activated, psi monitor stays active for at least the duration of one +tracking window to avoid repeated activations/deactivations when system is +bouncing in and out of the stall state. + +Notifications to the userspace are rate-limited to one per tracking window. + +The trigger will de-register when the file descriptor used to define the +trigger is closed. + +Userspace monitor usage example +=============================== + +#include <errno.h> +#include <fcntl.h> +#include <stdio.h> +#include <poll.h> +#include <string.h> +#include <unistd.h> + +/* + * Monitor memory partial stall with 1s tracking window size + * and 150ms threshold. + */ +int main() { + const char trig[] = "some 150000 1000000"; + struct pollfd fds; + int n; + + fds.fd = open("/proc/pressure/memory", O_RDWR | O_NONBLOCK); + if (fds.fd < 0) { + printf("/proc/pressure/memory open error: %s\n", + strerror(errno)); + return 1; + } + fds.events = POLLPRI; + + if (write(fds.fd, trig, strlen(trig) + 1) < 0) { + printf("/proc/pressure/memory write error: %s\n", + strerror(errno)); + return 1; + } + + printf("waiting for events...\n"); + while (1) { + n = poll(&fds, 1, -1); + if (n < 0) { + printf("poll error: %s\n", strerror(errno)); + return 1; + } + if (fds.revents & POLLERR) { + printf("got POLLERR, event source is gone\n"); + return 0; + } + if (fds.revents & POLLPRI) { + printf("event triggered!\n"); + } else { + printf("unknown event received: 0x%x\n", fds.revents); + return 1; + } + } + + return 0; +} + +Cgroup2 interface +================= + +In a system with a CONFIG_CGROUP=y kernel and the cgroup2 filesystem +mounted, pressure stall information is also tracked for tasks grouped +into cgroups. Each subdirectory in the cgroupfs mountpoint contains +cpu.pressure, memory.pressure, and io.pressure files; the format is +the same as the /proc/pressure/ files. + +Per-cgroup psi monitors can be specified and used the same way as +system-wide ones. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index dc96e7f10ebc..9cc43c8bb225 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3432,6 +3432,10 @@ before loading. See Documentation/blockdev/ramdisk.txt. + psi= [KNL] Enable or disable pressure stall information + tracking. + Format: <bool> + psmouse.proto= [HW,MOUSE] Highest PS2 mouse protocol extension to probe for; one of (bare|imps|exps|lifebook|any). psmouse.rate= [HW,MOUSE] Set desired mouse report rate, in reports diff --git a/Documentation/arm64/cpu-feature-registers.txt b/Documentation/arm64/cpu-feature-registers.txt index 7964f03846b1..6aa3558163c5 100644 --- a/Documentation/arm64/cpu-feature-registers.txt +++ b/Documentation/arm64/cpu-feature-registers.txt @@ -110,6 +110,7 @@ infrastructure: x--------------------------------------------------x | Name | bits | visible | |--------------------------------------------------| + | RES0 | [63-48] | n | | TS | [55-52] | y | |--------------------------------------------------| | FHM | [51-48] | y | @@ -124,6 +125,8 @@ infrastructure: |--------------------------------------------------| | RDM | [31-28] | y | |--------------------------------------------------| + | RES0 | [27-24] | n | + |--------------------------------------------------| | ATOMICS | [23-20] | y | |--------------------------------------------------| | CRC32 | [19-16] | y | diff --git a/Documentation/blockdev/zram.txt b/Documentation/blockdev/zram.txt index 257e65714c6a..6e5c2bb222c3 100644 --- a/Documentation/blockdev/zram.txt +++ b/Documentation/blockdev/zram.txt @@ -156,19 +156,23 @@ Per-device statistics are exported as various nodes under /sys/block/zram<id>/ A brief description of exported device attributes. For more details please read Documentation/ABI/testing/sysfs-block-zram. -Name access description ----- ------ ----------- -disksize RW show and set the device's disk size -initstate RO shows the initialization state of the device -reset WO trigger device reset -mem_used_max WO reset the `mem_used_max' counter (see later) -mem_limit WO specifies the maximum amount of memory ZRAM can use - to store the compressed data -max_comp_streams RW the number of possible concurrent compress operations -comp_algorithm RW show and change the compression algorithm -compact WO trigger memory compaction -debug_stat RO this file is used for zram debugging purposes -backing_dev RW set up backend storage for zram to write out +Name access description +---- ------ ----------- +disksize RW show and set the device's disk size +initstate RO shows the initialization state of the device +reset WO trigger device reset +mem_used_max WO reset the `mem_used_max' counter (see later) +mem_limit WO specifies the maximum amount of memory ZRAM can use + to store the compressed data +writeback_limit WO specifies the maximum amount of write IO zram can + write out to backing device as 4KB unit +writeback_limit_enable RW show and set writeback_limit feature +max_comp_streams RW the number of possible concurrent compress operations +comp_algorithm RW show and change the compression algorithm +compact WO trigger memory compaction +debug_stat RO this file is used for zram debugging purposes +backing_dev RW set up backend storage for zram to write out +idle WO mark allocated slot as idle User space is advised to use the following files to read the device statistics. @@ -218,6 +222,18 @@ line of text and contains the following stats separated by whitespace: same_pages the number of same element filled pages written to this disk. No memory is allocated for such pages. pages_compacted the number of pages freed during compaction + huge_pages the number of incompressible pages + +File /sys/block/zram<id>/bd_stat + +The stat file represents device's backing device statistics. It consists of +a single line of text and contains the following stats separated by whitespace: + bd_count size of data written in backing device. + Unit: 4K bytes + bd_reads the number of reads from backing device + Unit: 4K bytes + bd_writes the number of writes to backing device + Unit: 4K bytes 9) Deactivate: swapoff /dev/zram0 @@ -236,11 +252,104 @@ line of text and contains the following stats separated by whitespace: = writeback -With incompressible pages, there is no memory saving with zram. -Instead, with CONFIG_ZRAM_WRITEBACK, zram can write incompressible page +With CONFIG_ZRAM_WRITEBACK, zram can write idle/incompressible page to backing storage rather than keeping it in memory. -User should set up backing device via /sys/block/zramX/backing_dev -before disksize setting. +To use the feature, admin should set up backing device via + + "echo /dev/sda5 > /sys/block/zramX/backing_dev" + +before disksize setting. It supports only partition at this moment. +If admin want to use incompressible page writeback, they could do via + + "echo huge > /sys/block/zramX/write" + +To use idle page writeback, first, user need to declare zram pages +as idle. + + "echo all > /sys/block/zramX/idle" + +From now on, any pages on zram are idle pages. The idle mark +will be removed until someone request access of the block. +IOW, unless there is access request, those pages are still idle pages. + +Admin can request writeback of those idle pages at right timing via + + "echo idle > /sys/block/zramX/writeback" + +With the command, zram writeback idle pages from memory to the storage. + +If there are lots of write IO with flash device, potentially, it has +flash wearout problem so that admin needs to design write limitation +to guarantee storage health for entire product life. + +To overcome the concern, zram supports "writeback_limit" feature. +The "writeback_limit_enable"'s default value is 0 so that it doesn't limit +any writeback. IOW, if admin want to apply writeback budget, he should +enable writeback_limit_enable via + + $ echo 1 > /sys/block/zramX/writeback_limit_enable + +Once writeback_limit_enable is set, zram doesn't allow any writeback +until admin set the budget via /sys/block/zramX/writeback_limit. + +(If admin doesn't enable writeback_limit_enable, writeback_limit's value +assigned via /sys/block/zramX/writeback_limit is meaninless.) + +If admin want to limit writeback as per-day 400M, he could do it +like below. + + $ MB_SHIFT=20 + $ 4K_SHIFT=12 + $ echo $((400<<MB_SHIFT>>4K_SHIFT)) > \ + /sys/block/zram0/writeback_limit. + $ echo 1 > /sys/block/zram0/writeback_limit_enable + +If admin want to allow further write again once the bugdet is exausted, +he could do it like below + + $ echo $((400<<MB_SHIFT>>4K_SHIFT)) > \ + /sys/block/zram0/writeback_limit + +If admin want to see remaining writeback budget since he set, + + $ cat /sys/block/zramX/writeback_limit + +If admin want to disable writeback limit, he could do + + $ echo 0 > /sys/block/zramX/writeback_limit_enable + +The writeback_limit count will reset whenever you reset zram(e.g., +system reboot, echo 1 > /sys/block/zramX/reset) so keeping how many of +writeback happened until you reset the zram to allocate extra writeback +budget in next setting is user's job. + +If admin want to measure writeback count in a certain period, he could +know it via /sys/block/zram0/bd_stat's 3rd column. + += memory tracking + +With CONFIG_ZRAM_MEMORY_TRACKING, user can know information of the +zram block. It could be useful to catch cold or incompressible +pages of the process with*pagemap. +If you enable the feature, you could see block state via +/sys/kernel/debug/zram/zram0/block_state". The output is as follows, + + 300 75.033841 .wh. + 301 63.806904 s... + 302 63.806919 ..hi + +First column is zram's block index. +Second column is access time since the system was booted +Third column is state of the block. +(s: same page +w: written page to backing store +h: huge page +i: idle page) + +First line of above example says 300th block is accessed at 75.033841sec +and the block's state is huge so it is written back to the backing +storage. It's a debugging feature so anyone shouldn't rely on it to work +properly. Nitin Gupta ngupta@vflare.org diff --git a/Documentation/cgroup-v2.txt b/Documentation/cgroup-v2.txt index dc44785dc0fa..7e3672812510 100644 --- a/Documentation/cgroup-v2.txt +++ b/Documentation/cgroup-v2.txt @@ -958,6 +958,12 @@ All time durations are in microseconds. $PERIOD duration. If only one number is written, $MAX is updated. + cpu.pressure + A read-only nested-key file which exists on non-root cgroups. + + Shows pressure stall information for CPU. See + Documentation/accounting/psi.txt for details. + Memory ------ @@ -1194,6 +1200,12 @@ PAGE_SIZE multiple when read back. Swap usage hard limit. If a cgroup's swap usage reaches this limit, anonymous meomry of the cgroup will not be swapped out. + memory.pressure + A read-only nested-key file which exists on non-root cgroups. + + Shows pressure stall information for memory. See + Documentation/accounting/psi.txt for details. + Usage Guidelines ~~~~~~~~~~~~~~~~ @@ -1329,6 +1341,12 @@ IO Interface Files 8:16 rbps=2097152 wbps=max riops=max wiops=max + io.pressure + A read-only nested-key file which exists on non-root cgroups. + + Shows pressure stall information for IO. See + Documentation/accounting/psi.txt for details. + Writeback ~~~~~~~~~ diff --git a/Documentation/device-mapper/dm-bow.txt b/Documentation/device-mapper/dm-bow.txt new file mode 100644 index 000000000000..e3fc4d22e0f4 --- /dev/null +++ b/Documentation/device-mapper/dm-bow.txt @@ -0,0 +1,99 @@ +dm_bow (backup on write) +======================== + +dm_bow is a device mapper driver that uses the free space on a device to back up +data that is overwritten. The changes can then be committed by a simple state +change, or rolled back by removing the dm_bow device and running a command line +utility over the underlying device. + +dm_bow has three states, set by writing ‘1’ or ‘2’ to /sys/block/dm-?/bow/state. +It is only possible to go from state 0 (initial state) to state 1, and then from +state 1 to state 2. + +State 0: dm_bow collects all trims to the device and assumes that these mark +free space on the overlying file system that can be safely used. Typically the +mount code would create the dm_bow device, mount the file system, call the +FITRIM ioctl on the file system then switch to state 1. These trims are not +propagated to the underlying device. + +State 1: All writes to the device cause the underlying data to be backed up to +the free (trimmed) area as needed in such a way as they can be restored. +However, the writes, with one exception, then happen exactly as they would +without dm_bow, so the device is always in a good final state. The exception is +that sector 0 is used to keep a log of the latest changes, both to indicate that +we are in this state and to allow rollback. See below for all details. If there +isn't enough free space, writes are failed with -ENOSPC. + +State 2: The transition to state 2 triggers replacing the special sector 0 with +the normal sector 0, and the freeing of all state information. dm_bow then +becomes a pass-through driver, allowing the device to continue to be used with +minimal performance impact. + +Usage +===== +dm-bow takes one command line parameter, the name of the underlying device. + +dm-bow will typically be used in the following way. dm-bow will be loaded with a +suitable underlying device and the resultant device will be mounted. A file +system trim will be issued via the FITRIM ioctl, then the device will be +switched to state 1. The file system will now be used as normal. At some point, +the changes can either be committed by switching to state 2, or rolled back by +unmounting the file system, removing the dm-bow device and running the command +line utility. Note that rebooting the device will be equivalent to unmounting +and removing, but the command line utility must still be run + +Details of operation in state 1 +=============================== + +dm_bow maintains a type for all sectors. A sector can be any of: + +SECTOR0 +SECTOR0_CURRENT +UNCHANGED +FREE +CHANGED +BACKUP + +SECTOR0 is the first sector on the device, and is used to hold the log of +changes. This is the one exception. + +SECTOR0_CURRENT is a sector picked from the FREE sectors, and is where reads and +writes from the true sector zero are redirected to. Note that like any backup +sector, if the sector is written to directly, it must be moved again. + +UNCHANGED means that the sector has not been changed since we entered state 1. +Thus if it is written to or trimmed, the contents must first be backed up. + +FREE means that the sector was trimmed in state 0 and has not yet been written +to or used for backup. On being written to, a FREE sector is changed to CHANGED. + +CHANGED means that the sector has been modified, and can be further modified +without further backup. + +BACKUP means that this is a free sector being used as a backup. On being written +to, the contents must first be backed up again. + +All backup operations are logged to the first sector. The log sector has the +format: +-------------------------------------------------------- +| Magic | Count | Sequence | Log entry | Log entry | … +-------------------------------------------------------- + +Magic is a magic number. Count is the number of log entries. Sequence is 0 +initially. A log entry is + +----------------------------------- +| Source | Dest | Size | Checksum | +----------------------------------- + +When SECTOR0 is full, the log sector is backed up and another empty log sector +created with sequence number one higher. The first entry in any log entry with +sequence > 0 therefore must be the log of the backing up of the previous log +sector. Note that sequence is not strictly needed, but is a useful sanity check +and potentially limits the time spent trying to restore a corrupted snapshot. + +On entering state 1, dm_bow has a list of free sectors. All other sectors are +unchanged. Sector0_current is selected from the free sectors and the contents of +sector 0 are copied there. The sector 0 is backed up, which triggers the first +log entry to be written. + diff --git a/Documentation/device-mapper/verity.txt b/Documentation/device-mapper/verity.txt index 89fd8f9a259f..b3d2e4a42255 100644 --- a/Documentation/device-mapper/verity.txt +++ b/Documentation/device-mapper/verity.txt @@ -109,6 +109,17 @@ fec_start <offset> This is the offset, in <data_block_size> blocks, from the start of the FEC device to the beginning of the encoding data. +check_at_most_once + Verify data blocks only the first time they are read from the data device, + rather than every time. This reduces the overhead of dm-verity so that it + can be used on systems that are memory and/or CPU constrained. However, it + provides a reduced level of security because only offline tampering of the + data device's content will be detected, not online tampering. + + Hash blocks are still verified each time they are read from the hash device, + since verification of hash blocks is less performance critical than data + blocks, and a hash block will not be verified any more after all the data + blocks it covers have been verified anyway. Theory of operation =================== diff --git a/Documentation/devicetree/bindings/misc/memory-state-time.txt b/Documentation/devicetree/bindings/misc/memory-state-time.txt new file mode 100644 index 000000000000..c99a506c030d --- /dev/null +++ b/Documentation/devicetree/bindings/misc/memory-state-time.txt @@ -0,0 +1,8 @@ +Memory bandwidth and frequency state tracking + +Required properties: +- compatible : should be: + "memory-state-time" +- freq-tbl: Should contain entries with each frequency in Hz. +- bw-buckets: Should contain upper-bound limits for each bandwidth bucket in Mbps. + Must match the framework power_profile.xml for the device. diff --git a/Documentation/devicetree/bindings/scheduler/sched-energy-costs.txt b/Documentation/devicetree/bindings/scheduler/sched-energy-costs.txt new file mode 100644 index 000000000000..447cc32b3f21 --- /dev/null +++ b/Documentation/devicetree/bindings/scheduler/sched-energy-costs.txt @@ -0,0 +1,383 @@ +=========================================================== +Energy cost bindings for Energy Aware Scheduling +=========================================================== + +=========================================================== +1 - Introduction +=========================================================== + +This note specifies bindings required for energy-aware scheduling +(EAS)[1]. Historically, the scheduler's primary objective has been +performance. EAS aims to provide an alternative objective - energy +efficiency. EAS relies on a simple platform energy cost model to +guide scheduling decisions. The model only considers the CPU +subsystem. + +This note is aligned with the definition of the layout of physical +CPUs in the system as described in the ARM topology binding +description [2]. The concept is applicable to any system so long as +the cost model data is provided for those processing elements in +that system's topology that EAS is required to service. + +Processing elements refer to hardware threads, CPUs and clusters of +related CPUs in increasing order of hierarchy. + +EAS requires two key cost metrics - busy costs and idle costs. Busy +costs comprise of a list of compute capacities for the processing +element in question and the corresponding power consumption at that +capacity. Idle costs comprise of a list of power consumption values +for each idle state [C-state] that the processing element supports. +For a detailed description of these metrics, their derivation and +their use see [3]. + +These cost metrics are required for processing elements in all +scheduling domain levels that EAS is required to service. + +=========================================================== +2 - energy-costs node +=========================================================== + +Energy costs for the processing elements in scheduling domains that +EAS is required to service are defined in the energy-costs node +which acts as a container for the actual per processing element cost +nodes. A single energy-costs node is required for a given system. + +- energy-costs node + + Usage: Required + + Description: The energy-costs node is a container node and + it's sub-nodes describe costs for each processing element at + all scheduling domain levels that EAS is required to + service. + + Node name must be "energy-costs". + + The energy-costs node's parent node must be the cpus node. + + The energy-costs node's child nodes can be: + + - one or more cost nodes. + + Any other configuration is considered invalid. + +The energy-costs node can only contain a single type of child node +whose bindings are described in paragraph 4. + +=========================================================== +3 - energy-costs node child nodes naming convention +=========================================================== + +energy-costs child nodes must follow a naming convention where the +node name must be "thread-costN", "core-costN", "cluster-costN" +depending on whether the costs in the node are for a thread, core or +cluster. N (where N = {0, 1, ...}) is the node number and has no +bearing to the OS' logical thread, core or cluster index. + +=========================================================== +4 - cost node bindings +=========================================================== + +Bindings for cost nodes are defined as follows: + +- system-cost node + + Description: Optional. Must be declared within an energy-costs + node. A system should contain no more than one system-cost node. + + Systems with no modelled system cost should not provide this + node. + + The system-cost node name must be "system-costN" as + described in 3 above. + + A system-cost node must be a leaf node with no children. + + Properties for system-cost nodes are described in paragraph + 5 below. + + Any other configuration is considered invalid. + +- cluster-cost node + + Description: must be declared within an energy-costs node. A + system can contain multiple clusters and each cluster + serviced by EAS must have a corresponding cluster-costs + node. + + The cluster-cost node name must be "cluster-costN" as + described in 3 above. + + A cluster-cost node must be a leaf node with no children. + + Properties for cluster-cost nodes are described in paragraph + 5 below. + + Any other configuration is considered invalid. + +- core-cost node + + Description: must be declared within an energy-costs node. A + system can contain multiple cores and each core serviced by + EAS must have a corresponding core-cost node. + + The core-cost node name must be "core-costN" as described in + 3 above. + + A core-cost node must be a leaf node with no children. + + Properties for core-cost nodes are described in paragraph + 5 below. + + Any other configuration is considered invalid. + +- thread-cost node + + Description: must be declared within an energy-costs node. A + system can contain cores with multiple hardware threads and + each thread serviced by EAS must have a corresponding + thread-cost node. + + The core-cost node name must be "core-costN" as described in + 3 above. + + A core-cost node must be a leaf node with no children. + + Properties for thread-cost nodes are described in paragraph + 5 below. + + Any other configuration is considered invalid. + +=========================================================== +5 - Cost node properties +========================================================== + +All cost node types must have only the following properties: + +- busy-cost-data + + Usage: required + Value type: An array of 2-item tuples. Each item is of type + u32. + Definition: The first item in the tuple is the capacity + value as described in [3]. The second item in the tuple is + the energy cost value as described in [3]. + +- idle-cost-data + + Usage: required + Value type: An array of 1-item tuples. The item is of type + u32. + Definition: The item in the tuple is the energy cost value + as described in [3]. + +=========================================================== +4 - Extensions to the cpu node +=========================================================== + +The cpu node is extended with a property that establishes the +connection between the processing element represented by the cpu +node and the cost-nodes associated with this processing element. + +The connection is expressed in line with the topological hierarchy +that this processing element belongs to starting with the level in +the hierarchy that this processing element itself belongs to through +to the highest level that EAS is required to service. The +connection cannot be sparse and must be contiguous from the +processing element's level through to the highest desired level. The +highest desired level must be the same for all processing elements. + +Example: Given that a cpu node may represent a thread that is a part +of a core, this property may contain multiple elements which +associate the thread with cost nodes describing the costs for the +thread itself, the core the thread belongs to, the cluster the core +belongs to and so on. The elements must be ordered from the lowest +level nodes to the highest desired level that EAS must service. The +highest desired level must be the same for all cpu nodes. The +elements must not be sparse: there must be elements for the current +thread, the next level of hierarchy (core) and so on without any +'holes'. + +Example: Given that a cpu node may represent a core that is a part +of a cluster of related cpus this property may contain multiple +elements which associate the core with cost nodes describing the +costs for the core itself, the cluster the core belongs to and so +on. The elements must be ordered from the lowest level nodes to the +highest desired level that EAS must service. The highest desired +level must be the same for all cpu nodes. The elements must not be +sparse: there must be elements for the current thread, the next +level of hierarchy (core) and so on without any 'holes'. + +If the system comprises of hierarchical clusters of clusters, this +property will contain multiple associations with the relevant number +of cluster elements in hierarchical order. + +Property added to the cpu node: + +- sched-energy-costs + + Usage: required + Value type: List of phandles + Definition: a list of phandles to specific cost nodes in the + energy-costs parent node that correspond to the processing + element represented by this cpu node in hierarchical order + of topology. + + The order of phandles in the list is significant. The first + phandle is to the current processing element's own cost + node. Subsequent phandles are to higher hierarchical level + cost nodes up until the maximum level that EAS is to + service. + + All cpu nodes must have the same highest level cost node. + + The phandle list must not be sparsely populated with handles + to non-contiguous hierarchical levels. See commentary above + for clarity. + + Any other configuration is invalid. + +- freq-energy-model + Description: Optional. Must be declared if the energy model + represents frequency/power values. If absent, energy model is + by default considered as capacity/power. + +=========================================================== +5 - Example dts +=========================================================== + +Example 1 (ARM 64-bit, 6-cpu system, two clusters of cpus, one +cluster of 2 Cortex-A57 cpus, one cluster of 4 Cortex-A53 cpus): + +cpus { + #address-cells = <2>; + #size-cells = <0>; + . + . + . + A57_0: cpu@0 { + compatible = "arm,cortex-a57","arm,armv8"; + reg = <0x0 0x0>; + device_type = "cpu"; + enable-method = "psci"; + next-level-cache = <&A57_L2>; + clocks = <&scpi_dvfs 0>; + cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; + sched-energy-costs = <&CPU_COST_0 &CLUSTER_COST_0>; + }; + + A57_1: cpu@1 { + compatible = "arm,cortex-a57","arm,armv8"; + reg = <0x0 0x1>; + device_type = "cpu"; + enable-method = "psci"; + next-level-cache = <&A57_L2>; + clocks = <&scpi_dvfs 0>; + cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; + sched-energy-costs = <&CPU_COST_0 &CLUSTER_COST_0>; + }; + + A53_0: cpu@100 { + compatible = "arm,cortex-a53","arm,armv8"; + reg = <0x0 0x100>; + device_type = "cpu"; + enable-method = "psci"; + next-level-cache = <&A53_L2>; + clocks = <&scpi_dvfs 1>; + cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; + sched-energy-costs = <&CPU_COST_1 &CLUSTER_COST_1>; + }; + + A53_1: cpu@101 { + compatible = "arm,cortex-a53","arm,armv8"; + reg = <0x0 0x101>; + device_type = "cpu"; + enable-method = "psci"; + next-level-cache = <&A53_L2>; + clocks = <&scpi_dvfs 1>; + cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; + sched-energy-costs = <&CPU_COST_1 &CLUSTER_COST_1>; + }; + + A53_2: cpu@102 { + compatible = "arm,cortex-a53","arm,armv8"; + reg = <0x0 0x102>; + device_type = "cpu"; + enable-method = "psci"; + next-level-cache = <&A53_L2>; + clocks = <&scpi_dvfs 1>; + cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; + sched-energy-costs = <&CPU_COST_1 &CLUSTER_COST_1>; + }; + + A53_3: cpu@103 { + compatible = "arm,cortex-a53","arm,armv8"; + reg = <0x0 0x103>; + device_type = "cpu"; + enable-method = "psci"; + next-level-cache = <&A53_L2>; + clocks = <&scpi_dvfs 1>; + cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; + sched-energy-costs = <&CPU_COST_1 &CLUSTER_COST_1>; + }; + + energy-costs { + CPU_COST_0: core-cost0 { + busy-cost-data = < + 417 168 + 579 251 + 744 359 + 883 479 + 1024 616 + >; + idle-cost-data = < + 15 + 0 + >; + }; + CPU_COST_1: core-cost1 { + busy-cost-data = < + 235 33 + 302 46 + 368 61 + 406 76 + 447 93 + >; + idle-cost-data = < + 6 + 0 + >; + }; + CLUSTER_COST_0: cluster-cost0 { + busy-cost-data = < + 417 24 + 579 32 + 744 43 + 883 49 + 1024 64 + >; + idle-cost-data = < + 65 + 24 + >; + }; + CLUSTER_COST_1: cluster-cost1 { + busy-cost-data = < + 235 26 + 303 30 + 368 39 + 406 47 + 447 57 + >; + idle-cost-data = < + 56 + 17 + >; + }; + }; +}; + +=============================================================================== +[1] https://lkml.org/lkml/2015/5/12/728 +[2] Documentation/devicetree/bindings/topology.txt +[3] Documentation/scheduler/sched-energy.txt diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt index 13c2ff034348..35c777b6e69b 100644 --- a/Documentation/filesystems/f2fs.txt +++ b/Documentation/filesystems/f2fs.txt @@ -126,6 +126,8 @@ disable_ext_identify Disable the extension list configured by mkfs, so f2fs does not aware of cold files such as media files. inline_xattr Enable the inline xattrs feature. noinline_xattr Disable the inline xattrs feature. +inline_xattr_size=%u Support configuring inline xattr size, it depends on + flexible inline xattr feature. inline_data Enable the inline data feature: New created small(<~3.4k) files can be written into inode block. inline_dentry Enable the inline dir feature: data in new created @@ -157,6 +159,25 @@ data_flush Enable data flushing before checkpoint in order to persist data of regular and symlink. fault_injection=%d Enable fault injection in all supported types with specified injection rate. +fault_type=%d Support configuring fault injection type, should be + enabled with fault_injection option, fault type value + is shown below, it supports single or combined type. + Type_Name Type_Value + FAULT_KMALLOC 0x000000001 + FAULT_KVMALLOC 0x000000002 + FAULT_PAGE_ALLOC 0x000000004 + FAULT_PAGE_GET 0x000000008 + FAULT_ALLOC_BIO 0x000000010 + FAULT_ALLOC_NID 0x000000020 + FAULT_ORPHAN 0x000000040 + FAULT_BLOCK 0x000000080 + FAULT_DIR_DEPTH 0x000000100 + FAULT_EVICT_INODE 0x000000200 + FAULT_TRUNCATE 0x000000400 + FAULT_READ_IO 0x000000800 + FAULT_CHECKPOINT 0x000001000 + FAULT_DISCARD 0x000002000 + FAULT_WRITE_IO 0x000004000 mode=%s Control block allocation mode which supports "adaptive" and "lfs". In "lfs" mode, there should be no random writes towards main area. @@ -174,6 +195,30 @@ offgrpjquota Turn off group journelled quota. offprjjquota Turn off project journelled quota. quota Enable plain user disk quota accounting. noquota Disable all plain disk quota option. +whint_mode=%s Control which write hints are passed down to block + layer. This supports "off", "user-based", and + "fs-based". In "off" mode (default), f2fs does not pass + down hints. In "user-based" mode, f2fs tries to pass + down hints given by users. And in "fs-based" mode, f2fs + passes down hints with its policy. +alloc_mode=%s Adjust block allocation policy, which supports "reuse" + and "default". +fsync_mode=%s Control the policy of fsync. Currently supports "posix", + "strict", and "nobarrier". In "posix" mode, which is + default, fsync will follow POSIX semantics and does a + light operation to improve the filesystem performance. + In "strict" mode, fsync will be heavy and behaves in line + with xfs, ext4 and btrfs, where xfstest generic/342 will + pass, but the performance will regress. "nobarrier" is + based on "posix", but doesn't issue flush command for + non-atomic files likewise "nobarrier" mount option. +test_dummy_encryption Enable dummy encryption, which provides a fake fscrypt + context. The fake fscrypt context is used by xfstests. +checkpoint=%s Set to "disable" to turn off checkpointing. Set to "enable" + to reenable checkpointing. Is enabled by default. While + disabled, any unmounting or unexpected shutdowns will cause + the filesystem contents to appear as they did when the + filesystem was mounted with that option. ================================================================================ DEBUGFS ENTRIES diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst new file mode 100644 index 000000000000..3a7b60521b94 --- /dev/null +++ b/Documentation/filesystems/fscrypt.rst @@ -0,0 +1,641 @@ +===================================== +Filesystem-level encryption (fscrypt) +===================================== + +Introduction +============ + +fscrypt is a library which filesystems can hook into to support +transparent encryption of files and directories. + +Note: "fscrypt" in this document refers to the kernel-level portion, +implemented in ``fs/crypto/``, as opposed to the userspace tool +`fscrypt <https://github.com/google/fscrypt>`_. This document only +covers the kernel-level portion. For command-line examples of how to +use encryption, see the documentation for the userspace tool `fscrypt +<https://github.com/google/fscrypt>`_. Also, it is recommended to use +the fscrypt userspace tool, or other existing userspace tools such as +`fscryptctl <https://github.com/google/fscryptctl>`_ or `Android's key +management system +<https://source.android.com/security/encryption/file-based>`_, over +using the kernel's API directly. Using existing tools reduces the +chance of introducing your own security bugs. (Nevertheless, for +completeness this documentation covers the kernel's API anyway.) + +Unlike dm-crypt, fscrypt operates at the filesystem level rather than +at the block device level. This allows it to encrypt different files +with different keys and to have unencrypted files on the same +filesystem. This is useful for multi-user systems where each user's +data-at-rest needs to be cryptographically isolated from the others. +However, except for filenames, fscrypt does not encrypt filesystem +metadata. + +Unlike eCryptfs, which is a stacked filesystem, fscrypt is integrated +directly into supported filesystems --- currently ext4, F2FS, and +UBIFS. This allows encrypted files to be read and written without +caching both the decrypted and encrypted pages in the pagecache, +thereby nearly halving the memory used and bringing it in line with +unencrypted files. Similarly, half as many dentries and inodes are +needed. eCryptfs also limits encrypted filenames to 143 bytes, +causing application compatibility issues; fscrypt allows the full 255 +bytes (NAME_MAX). Finally, unlike eCryptfs, the fscrypt API can be +used by unprivileged users, with no need to mount anything. + +fscrypt does not support encrypting files in-place. Instead, it +supports marking an empty directory as encrypted. Then, after +userspace provides the key, all regular files, directories, and +symbolic links created in that directory tree are transparently +encrypted. + +Threat model +============ + +Offline attacks +--------------- + +Provided that userspace chooses a strong encryption key, fscrypt +protects the confidentiality of file contents and filenames in the +event of a single point-in-time permanent offline compromise of the +block device content. fscrypt does not protect the confidentiality of +non-filename metadata, e.g. file sizes, file permissions, file +timestamps, and extended attributes. Also, the existence and location +of holes (unallocated blocks which logically contain all zeroes) in +files is not protected. + +fscrypt is not guaranteed to protect confidentiality or authenticity +if an attacker is able to manipulate the filesystem offline prior to +an authorized user later accessing the filesystem. + +Online attacks +-------------- + +fscrypt (and storage encryption in general) can only provide limited +protection, if any at all, against online attacks. In detail: + +fscrypt is only resistant to side-channel attacks, such as timing or +electromagnetic attacks, to the extent that the underlying Linux +Cryptographic API algorithms are. If a vulnerable algorithm is used, +such as a table-based implementation of AES, it may be possible for an +attacker to mount a side channel attack against the online system. +Side channel attacks may also be mounted against applications +consuming decrypted data. + +After an encryption key has been provided, fscrypt is not designed to +hide the plaintext file contents or filenames from other users on the +same system, regardless of the visibility of the keyring key. +Instead, existing access control mechanisms such as file mode bits, +POSIX ACLs, LSMs, or mount namespaces should be used for this purpose. +Also note that as long as the encryption keys are *anywhere* in +memory, an online attacker can necessarily compromise them by mounting +a physical attack or by exploiting any kernel security vulnerability +which provides an arbitrary memory read primitive. + +While it is ostensibly possible to "evict" keys from the system, +recently accessed encrypted files will remain accessible at least +until the filesystem is unmounted or the VFS caches are dropped, e.g. +using ``echo 2 > /proc/sys/vm/drop_caches``. Even after that, if the +RAM is compromised before being powered off, it will likely still be +possible to recover portions of the plaintext file contents, if not +some of the encryption keys as well. (Since Linux v4.12, all +in-kernel keys related to fscrypt are sanitized before being freed. +However, userspace would need to do its part as well.) + +Currently, fscrypt does not prevent a user from maliciously providing +an incorrect key for another user's existing encrypted files. A +protection against this is planned. + +Key hierarchy +============= + +Master Keys +----------- + +Each encrypted directory tree is protected by a *master key*. Master +keys can be up to 64 bytes long, and must be at least as long as the +greater of the key length needed by the contents and filenames +encryption modes being used. For example, if AES-256-XTS is used for +contents encryption, the master key must be 64 bytes (512 bits). Note +that the XTS mode is defined to require a key twice as long as that +required by the underlying block cipher. + +To "unlock" an encrypted directory tree, userspace must provide the +appropriate master key. There can be any number of master keys, each +of which protects any number of directory trees on any number of +filesystems. + +Userspace should generate master keys either using a cryptographically +secure random number generator, or by using a KDF (Key Derivation +Function). Note that whenever a KDF is used to "stretch" a +lower-entropy secret such as a passphrase, it is critical that a KDF +designed for this purpose be used, such as scrypt, PBKDF2, or Argon2. + +Per-file keys +------------- + +Since each master key can protect many files, it is necessary to +"tweak" the encryption of each file so that the same plaintext in two +files doesn't map to the same ciphertext, or vice versa. In most +cases, fscrypt does this by deriving per-file keys. When a new +encrypted inode (regular file, directory, or symlink) is created, +fscrypt randomly generates a 16-byte nonce and stores it in the +inode's encryption xattr. Then, it uses a KDF (Key Derivation +Function) to derive the file's key from the master key and nonce. + +The Adiantum encryption mode (see `Encryption modes and usage`_) is +special, since it accepts longer IVs and is suitable for both contents +and filenames encryption. For it, a "direct key" option is offered +where the file's nonce is included in the IVs and the master key is +used for encryption directly. This improves performance; however, +users must not use the same master key for any other encryption mode. + +Below, the KDF and design considerations are described in more detail. + +The current KDF works by encrypting the master key with AES-128-ECB, +using the file's nonce as the AES key. The output is used as the +derived key. If the output is longer than needed, then it is +truncated to the needed length. + +Note: this KDF meets the primary security requirement, which is to +produce unique derived keys that preserve the entropy of the master +key, assuming that the master key is already a good pseudorandom key. +However, it is nonstandard and has some problems such as being +reversible, so it is generally considered to be a mistake! It may be +replaced with HKDF or another more standard KDF in the future. + +Key derivation was chosen over key wrapping because wrapped keys would +require larger xattrs which would be less likely to fit in-line in the +filesystem's inode table, and there didn't appear to be any +significant advantages to key wrapping. In particular, currently +there is no requirement to support unlocking a file with multiple +alternative master keys or to support rotating master keys. Instead, +the master keys may be wrapped in userspace, e.g. as is done by the +`fscrypt <https://github.com/google/fscrypt>`_ tool. + +Including the inode number in the IVs was considered. However, it was +rejected as it would have prevented ext4 filesystems from being +resized, and by itself still wouldn't have been sufficient to prevent +the same key from being directly reused for both XTS and CTS-CBC. + +Encryption modes and usage +========================== + +fscrypt allows one encryption mode to be specified for file contents +and one encryption mode to be specified for filenames. Different +directory trees are permitted to use different encryption modes. +Currently, the following pairs of encryption modes are supported: + +- AES-256-XTS for contents and AES-256-CTS-CBC for filenames +- AES-128-CBC for contents and AES-128-CTS-CBC for filenames +- Adiantum for both contents and filenames + +If unsure, you should use the (AES-256-XTS, AES-256-CTS-CBC) pair. + +AES-128-CBC was added only for low-powered embedded devices with +crypto accelerators such as CAAM or CESA that do not support XTS. + +Adiantum is a (primarily) stream cipher-based mode that is fast even +on CPUs without dedicated crypto instructions. It's also a true +wide-block mode, unlike XTS. It can also eliminate the need to derive +per-file keys. However, it depends on the security of two primitives, +XChaCha12 and AES-256, rather than just one. See the paper +"Adiantum: length-preserving encryption for entry-level processors" +(https://eprint.iacr.org/2018/720.pdf) for more details. To use +Adiantum, CONFIG_CRYPTO_ADIANTUM must be enabled. Also, fast +implementations of ChaCha and NHPoly1305 should be enabled, e.g. +CONFIG_CRYPTO_CHACHA20_NEON and CONFIG_CRYPTO_NHPOLY1305_NEON for ARM. + +New encryption modes can be added relatively easily, without changes +to individual filesystems. However, authenticated encryption (AE) +modes are not currently supported because of the difficulty of dealing +with ciphertext expansion. + +Contents encryption +------------------- + +For file contents, each filesystem block is encrypted independently. +Currently, only the case where the filesystem block size is equal to +the system's page size (usually 4096 bytes) is supported. + +Each block's IV is set to the logical block number within the file as +a little endian number, except that: + +- With CBC mode encryption, ESSIV is also used. Specifically, each IV + is encrypted with AES-256 where the AES-256 key is the SHA-256 hash + of the file's data encryption key. + +- In the "direct key" configuration (FS_POLICY_FLAG_DIRECT_KEY set in + the fscrypt_policy), the file's nonce is also appended to the IV. + Currently this is only allowed with the Adiantum encryption mode. + +Filenames encryption +-------------------- + +For filenames, each full filename is encrypted at once. Because of +the requirements to retain support for efficient directory lookups and +filenames of up to 255 bytes, the same IV is used for every filename +in a directory. + +However, each encrypted directory still uses a unique key; or +alternatively (for the "direct key" configuration) has the file's +nonce included in the IVs. Thus, IV reuse is limited to within a +single directory. + +With CTS-CBC, the IV reuse means that when the plaintext filenames +share a common prefix at least as long as the cipher block size (16 +bytes for AES), the corresponding encrypted filenames will also share +a common prefix. This is undesirable. Adiantum does not have this +weakness, as it is a wide-block encryption mode. + +All supported filenames encryption modes accept any plaintext length +>= 16 bytes; cipher block alignment is not required. However, +filenames shorter than 16 bytes are NUL-padded to 16 bytes before +being encrypted. In addition, to reduce leakage of filename lengths +via their ciphertexts, all filenames are NUL-padded to the next 4, 8, +16, or 32-byte boundary (configurable). 32 is recommended since this +provides the best confidentiality, at the cost of making directory +entries consume slightly more space. Note that since NUL (``\0``) is +not otherwise a valid character in filenames, the padding will never +produce duplicate plaintexts. + +Symbolic link targets are considered a type of filename and are +encrypted in the same way as filenames in directory entries, except +that IV reuse is not a problem as each symlink has its own inode. + +User API +======== + +Setting an encryption policy +---------------------------- + +The FS_IOC_SET_ENCRYPTION_POLICY ioctl sets an encryption policy on an +empty directory or verifies that a directory or regular file already +has the specified encryption policy. It takes in a pointer to a +:c:type:`struct fscrypt_policy`, defined as follows:: + + #define FS_KEY_DESCRIPTOR_SIZE 8 + + struct fscrypt_policy { + __u8 version; + __u8 contents_encryption_mode; + __u8 filenames_encryption_mode; + __u8 flags; + __u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE]; + }; + +This structure must be initialized as follows: + +- ``version`` must be 0. + +- ``contents_encryption_mode`` and ``filenames_encryption_mode`` must + be set to constants from ``<linux/fs.h>`` which identify the + encryption modes to use. If unsure, use + FS_ENCRYPTION_MODE_AES_256_XTS (1) for ``contents_encryption_mode`` + and FS_ENCRYPTION_MODE_AES_256_CTS (4) for + ``filenames_encryption_mode``. + +- ``flags`` must contain a value from ``<linux/fs.h>`` which + identifies the amount of NUL-padding to use when encrypting + filenames. If unsure, use FS_POLICY_FLAGS_PAD_32 (0x3). + In addition, if the chosen encryption modes are both + FS_ENCRYPTION_MODE_ADIANTUM, this can contain + FS_POLICY_FLAG_DIRECT_KEY to specify that the master key should be + used directly, without key derivation. + +- ``master_key_descriptor`` specifies how to find the master key in + the keyring; see `Adding keys`_. It is up to userspace to choose a + unique ``master_key_descriptor`` for each master key. The e4crypt + and fscrypt tools use the first 8 bytes of + ``SHA-512(SHA-512(master_key))``, but this particular scheme is not + required. Also, the master key need not be in the keyring yet when + FS_IOC_SET_ENCRYPTION_POLICY is executed. However, it must be added + before any files can be created in the encrypted directory. + +If the file is not yet encrypted, then FS_IOC_SET_ENCRYPTION_POLICY +verifies that the file is an empty directory. If so, the specified +encryption policy is assigned to the directory, turning it into an +encrypted directory. After that, and after providing the +corresponding master key as described in `Adding keys`_, all regular +files, directories (recursively), and symlinks created in the +directory will be encrypted, inheriting the same encryption policy. +The filenames in the directory's entries will be encrypted as well. + +Alternatively, if the file is already encrypted, then +FS_IOC_SET_ENCRYPTION_POLICY validates that the specified encryption +policy exactly matches the actual one. If they match, then the ioctl +returns 0. Otherwise, it fails with EEXIST. This works on both +regular files and directories, including nonempty directories. + +Note that the ext4 filesystem does not allow the root directory to be +encrypted, even if it is empty. Users who want to encrypt an entire +filesystem with one key should consider using dm-crypt instead. + +FS_IOC_SET_ENCRYPTION_POLICY can fail with the following errors: + +- ``EACCES``: the file is not owned by the process's uid, nor does the + process have the CAP_FOWNER capability in a namespace with the file + owner's uid mapped +- ``EEXIST``: the file is already encrypted with an encryption policy + different from the one specified +- ``EINVAL``: an invalid encryption policy was specified (invalid + version, mode(s), or flags) +- ``ENOTDIR``: the file is unencrypted and is a regular file, not a + directory +- ``ENOTEMPTY``: the file is unencrypted and is a nonempty directory +- ``ENOTTY``: this type of filesystem does not implement encryption +- ``EOPNOTSUPP``: the kernel was not configured with encryption + support for this filesystem, or the filesystem superblock has not + had encryption enabled on it. (For example, to use encryption on an + ext4 filesystem, CONFIG_EXT4_ENCRYPTION must be enabled in the + kernel config, and the superblock must have had the "encrypt" + feature flag enabled using ``tune2fs -O encrypt`` or ``mkfs.ext4 -O + encrypt``.) +- ``EPERM``: this directory may not be encrypted, e.g. because it is + the root directory of an ext4 filesystem +- ``EROFS``: the filesystem is readonly + +Getting an encryption policy +---------------------------- + +The FS_IOC_GET_ENCRYPTION_POLICY ioctl retrieves the :c:type:`struct +fscrypt_policy`, if any, for a directory or regular file. See above +for the struct definition. No additional permissions are required +beyond the ability to open the file. + +FS_IOC_GET_ENCRYPTION_POLICY can fail with the following errors: + +- ``EINVAL``: the file is encrypted, but it uses an unrecognized + encryption context format +- ``ENODATA``: the file is not encrypted +- ``ENOTTY``: this type of filesystem does not implement encryption +- ``EOPNOTSUPP``: the kernel was not configured with encryption + support for this filesystem + +Note: if you only need to know whether a file is encrypted or not, on +most filesystems it is also possible to use the FS_IOC_GETFLAGS ioctl +and check for FS_ENCRYPT_FL, or to use the statx() system call and +check for STATX_ATTR_ENCRYPTED in stx_attributes. + +Getting the per-filesystem salt +------------------------------- + +Some filesystems, such as ext4 and F2FS, also support the deprecated +ioctl FS_IOC_GET_ENCRYPTION_PWSALT. This ioctl retrieves a randomly +generated 16-byte value stored in the filesystem superblock. This +value is intended to used as a salt when deriving an encryption key +from a passphrase or other low-entropy user credential. + +FS_IOC_GET_ENCRYPTION_PWSALT is deprecated. Instead, prefer to +generate and manage any needed salt(s) in userspace. + +Adding keys +----------- + +To provide a master key, userspace must add it to an appropriate +keyring using the add_key() system call (see: +``Documentation/security/keys/core.rst``). The key type must be +"logon"; keys of this type are kept in kernel memory and cannot be +read back by userspace. The key description must be "fscrypt:" +followed by the 16-character lower case hex representation of the +``master_key_descriptor`` that was set in the encryption policy. The +key payload must conform to the following structure:: + + #define FS_MAX_KEY_SIZE 64 + + struct fscrypt_key { + u32 mode; + u8 raw[FS_MAX_KEY_SIZE]; + u32 size; + }; + +``mode`` is ignored; just set it to 0. The actual key is provided in +``raw`` with ``size`` indicating its size in bytes. That is, the +bytes ``raw[0..size-1]`` (inclusive) are the actual key. + +The key description prefix "fscrypt:" may alternatively be replaced +with a filesystem-specific prefix such as "ext4:". However, the +filesystem-specific prefixes are deprecated and should not be used in +new programs. + +There are several different types of keyrings in which encryption keys +may be placed, such as a session keyring, a user session keyring, or a +user keyring. Each key must be placed in a keyring that is "attached" +to all processes that might need to access files encrypted with it, in +the sense that request_key() will find the key. Generally, if only +processes belonging to a specific user need to access a given +encrypted directory and no session keyring has been installed, then +that directory's key should be placed in that user's user session +keyring or user keyring. Otherwise, a session keyring should be +installed if needed, and the key should be linked into that session +keyring, or in a keyring linked into that session keyring. + +Note: introducing the complex visibility semantics of keyrings here +was arguably a mistake --- especially given that by design, after any +process successfully opens an encrypted file (thereby setting up the +per-file key), possessing the keyring key is not actually required for +any process to read/write the file until its in-memory inode is +evicted. In the future there probably should be a way to provide keys +directly to the filesystem instead, which would make the intended +semantics clearer. + +Access semantics +================ + +With the key +------------ + +With the encryption key, encrypted regular files, directories, and +symlinks behave very similarly to their unencrypted counterparts --- +after all, the encryption is intended to be transparent. However, +astute users may notice some differences in behavior: + +- Unencrypted files, or files encrypted with a different encryption + policy (i.e. different key, modes, or flags), cannot be renamed or + linked into an encrypted directory; see `Encryption policy + enforcement`_. Attempts to do so will fail with EPERM. However, + encrypted files can be renamed within an encrypted directory, or + into an unencrypted directory. + +- Direct I/O is not supported on encrypted files. Attempts to use + direct I/O on such files will fall back to buffered I/O. + +- The fallocate operations FALLOC_FL_COLLAPSE_RANGE, + FALLOC_FL_INSERT_RANGE, and FALLOC_FL_ZERO_RANGE are not supported + on encrypted files and will fail with EOPNOTSUPP. + +- Online defragmentation of encrypted files is not supported. The + EXT4_IOC_MOVE_EXT and F2FS_IOC_MOVE_RANGE ioctls will fail with + EOPNOTSUPP. + +- The ext4 filesystem does not support data journaling with encrypted + regular files. It will fall back to ordered data mode instead. + +- DAX (Direct Access) is not supported on encrypted files. + +- The st_size of an encrypted symlink will not necessarily give the + length of the symlink target as required by POSIX. It will actually + give the length of the ciphertext, which will be slightly longer + than the plaintext due to NUL-padding and an extra 2-byte overhead. + +- The maximum length of an encrypted symlink is 2 bytes shorter than + the maximum length of an unencrypted symlink. For example, on an + EXT4 filesystem with a 4K block size, unencrypted symlinks can be up + to 4095 bytes long, while encrypted symlinks can only be up to 4093 + bytes long (both lengths excluding the terminating null). + +Note that mmap *is* supported. This is possible because the pagecache +for an encrypted file contains the plaintext, not the ciphertext. + +Without the key +--------------- + +Some filesystem operations may be performed on encrypted regular +files, directories, and symlinks even before their encryption key has +been provided: + +- File metadata may be read, e.g. using stat(). + +- Directories may be listed, in which case the filenames will be + listed in an encoded form derived from their ciphertext. The + current encoding algorithm is described in `Filename hashing and + encoding`_. The algorithm is subject to change, but it is + guaranteed that the presented filenames will be no longer than + NAME_MAX bytes, will not contain the ``/`` or ``\0`` characters, and + will uniquely identify directory entries. + + The ``.`` and ``..`` directory entries are special. They are always + present and are not encrypted or encoded. + +- Files may be deleted. That is, nondirectory files may be deleted + with unlink() as usual, and empty directories may be deleted with + rmdir() as usual. Therefore, ``rm`` and ``rm -r`` will work as + expected. + +- Symlink targets may be read and followed, but they will be presented + in encrypted form, similar to filenames in directories. Hence, they + are unlikely to point to anywhere useful. + +Without the key, regular files cannot be opened or truncated. +Attempts to do so will fail with ENOKEY. This implies that any +regular file operations that require a file descriptor, such as +read(), write(), mmap(), fallocate(), and ioctl(), are also forbidden. + +Also without the key, files of any type (including directories) cannot +be created or linked into an encrypted directory, nor can a name in an +encrypted directory be the source or target of a rename, nor can an +O_TMPFILE temporary file be created in an encrypted directory. All +such operations will fail with ENOKEY. + +It is not currently possible to backup and restore encrypted files +without the encryption key. This would require special APIs which +have not yet been implemented. + +Encryption policy enforcement +============================= + +After an encryption policy has been set on a directory, all regular +files, directories, and symbolic links created in that directory +(recursively) will inherit that encryption policy. Special files --- +that is, named pipes, device nodes, and UNIX domain sockets --- will +not be encrypted. + +Except for those special files, it is forbidden to have unencrypted +files, or files encrypted with a different encryption policy, in an +encrypted directory tree. Attempts to link or rename such a file into +an encrypted directory will fail with EPERM. This is also enforced +during ->lookup() to provide limited protection against offline +attacks that try to disable or downgrade encryption in known locations +where applications may later write sensitive data. It is recommended +that systems implementing a form of "verified boot" take advantage of +this by validating all top-level encryption policies prior to access. + +Implementation details +====================== + +Encryption context +------------------ + +An encryption policy is represented on-disk by a :c:type:`struct +fscrypt_context`. It is up to individual filesystems to decide where +to store it, but normally it would be stored in a hidden extended +attribute. It should *not* be exposed by the xattr-related system +calls such as getxattr() and setxattr() because of the special +semantics of the encryption xattr. (In particular, there would be +much confusion if an encryption policy were to be added to or removed +from anything other than an empty directory.) The struct is defined +as follows:: + + #define FS_KEY_DESCRIPTOR_SIZE 8 + #define FS_KEY_DERIVATION_NONCE_SIZE 16 + + struct fscrypt_context { + u8 format; + u8 contents_encryption_mode; + u8 filenames_encryption_mode; + u8 flags; + u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE]; + u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE]; + }; + +Note that :c:type:`struct fscrypt_context` contains the same +information as :c:type:`struct fscrypt_policy` (see `Setting an +encryption policy`_), except that :c:type:`struct fscrypt_context` +also contains a nonce. The nonce is randomly generated by the kernel +and is used to derive the inode's encryption key as described in +`Per-file keys`_. + +Data path changes +----------------- + +For the read path (->readpage()) of regular files, filesystems can +read the ciphertext into the page cache and decrypt it in-place. The +page lock must be held until decryption has finished, to prevent the +page from becoming visible to userspace prematurely. + +For the write path (->writepage()) of regular files, filesystems +cannot encrypt data in-place in the page cache, since the cached +plaintext must be preserved. Instead, filesystems must encrypt into a +temporary buffer or "bounce page", then write out the temporary +buffer. Some filesystems, such as UBIFS, already use temporary +buffers regardless of encryption. Other filesystems, such as ext4 and +F2FS, have to allocate bounce pages specially for encryption. + +Filename hashing and encoding +----------------------------- + +Modern filesystems accelerate directory lookups by using indexed +directories. An indexed directory is organized as a tree keyed by +filename hashes. When a ->lookup() is requested, the filesystem +normally hashes the filename being looked up so that it can quickly +find the corresponding directory entry, if any. + +With encryption, lookups must be supported and efficient both with and +without the encryption key. Clearly, it would not work to hash the +plaintext filenames, since the plaintext filenames are unavailable +without the key. (Hashing the plaintext filenames would also make it +impossible for the filesystem's fsck tool to optimize encrypted +directories.) Instead, filesystems hash the ciphertext filenames, +i.e. the bytes actually stored on-disk in the directory entries. When +asked to do a ->lookup() with the key, the filesystem just encrypts +the user-supplied name to get the ciphertext. + +Lookups without the key are more complicated. The raw ciphertext may +contain the ``\0`` and ``/`` characters, which are illegal in +filenames. Therefore, readdir() must base64-encode the ciphertext for +presentation. For most filenames, this works fine; on ->lookup(), the +filesystem just base64-decodes the user-supplied name to get back to +the raw ciphertext. + +However, for very long filenames, base64 encoding would cause the +filename length to exceed NAME_MAX. To prevent this, readdir() +actually presents long filenames in an abbreviated form which encodes +a strong "hash" of the ciphertext filename, along with the optional +filesystem-specific hash(es) needed for directory lookups. This +allows the filesystem to still, with a high degree of confidence, map +the filename given in ->lookup() back to a particular directory entry +that was previously listed by readdir(). See :c:type:`struct +fscrypt_digested_name` in the source for more details. + +Note that the precise way that filenames are presented to userspace +without the key is subject to change in the future. It is only meant +as a way to temporarily present valid filenames so that commands like +``rm -r`` work as expected on encrypted directories. diff --git a/Documentation/filesystems/overlayfs.txt b/Documentation/filesystems/overlayfs.txt index 8caa60734647..8d3792cce7a3 100644 --- a/Documentation/filesystems/overlayfs.txt +++ b/Documentation/filesystems/overlayfs.txt @@ -89,6 +89,29 @@ Only the lists of names from directories are merged. Other content such as metadata and extended attributes are reported for the upper directory only. These attributes of the lower directory are hidden. +credentials +----------- + +By default, all access to the upper, lower and work directories is the +recorded mounter's MAC and DAC credentials. The incoming accesses are +checked against the caller's credentials. + +In the case where caller MAC or DAC credentials do not overlap, a +use case available in older versions of the driver, the +override_creds mount flag can be turned off and help when the use +pattern has caller with legitimate credentials where the mounter +does not. Several unintended side effects will occur though. The +caller without certain key capabilities or lower privilege will not +always be able to delete files or directories, create nodes, or +search some restricted directories. The ability to search and read +a directory entry is spotty as a result of the cache mechanism not +retesting the credentials because of the assumption, a privileged +caller can fill cache, then a lower privilege can read the directory +cache. The uneven security model where cache, upperdir and workdir +are opened at privilege, but accessed without creating a form of +privilege escalation, should only be used with strict understanding +of the side effects and of the security policies. + whiteouts and opaque directories -------------------------------- diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index 4cee34ce496e..09bc35fbe66b 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -396,6 +396,8 @@ is not associated with a file: [stack] = the stack of the main process [vdso] = the "virtual dynamic shared object", the kernel system call handler + [anon:<name>] = an anonymous mapping that has been + named by userspace or if empty, the mapping is anonymous. @@ -424,6 +426,7 @@ KernelPageSize: 4 kB MMUPageSize: 4 kB Locked: 0 kB VmFlags: rd ex mr mw me dw +Name: name from userspace the first of these lines shows the same information as is displayed for the mapping in /proc/PID/maps. The remaining lines show the size of the mapping @@ -498,6 +501,9 @@ be vanished or the reverse -- new added. Interpretation of their meaning might change in future as well. So each consumer of these flags has to follow each specific kernel version for the exact semantic. +The "Name" field will only be present on a mapping that has been named by +userspace, and will show the name passed in by userspace. + This file is only present if the CONFIG_MMU kernel configuration option is enabled. diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 3bbe6fb2b086..4606682423cf 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -614,6 +614,16 @@ tcp_fastopen_blackhole_timeout_sec - INTEGER initial value when the blackhole issue goes away. By default, it is set to 1hr. +tcp_fwmark_accept - BOOLEAN + If set, incoming connections to listening sockets that do not have a + socket mark will set the mark of the accepting socket to the fwmark of + the incoming SYN packet. This will cause all packets on that connection + (starting from the first SYNACK) to be sent with that fwmark. The + listening socket's mark is unchanged. Listening sockets that already + have a fwmark set via setsockopt(SOL_SOCKET, SO_MARK, ...) are + unaffected. + Default: 0 + tcp_syn_retries - INTEGER Number of times initial SYNs for an active TCP connection attempt will be retransmitted. Should not be higher than 127. Default value diff --git a/Documentation/printk-formats.txt b/Documentation/printk-formats.txt index d1aecf53badb..bbfeeb0813d3 100644 --- a/Documentation/printk-formats.txt +++ b/Documentation/printk-formats.txt @@ -5,7 +5,6 @@ How to get printk format specifiers right :Author: Randy Dunlap <rdunlap@infradead.org> :Author: Andrew Murray <amurray@mpc-data.co.uk> - Integer types ============= @@ -45,6 +44,18 @@ return from vsnprintf. Raw pointer value SHOULD be printed with %p. The kernel supports the following extended format specifiers for pointer types: +Pointer Types +============= + +Pointers printed without a specifier extension (i.e unadorned %p) are +hashed to give a unique identifier without leaking kernel addresses to user +space. On 64 bit machines the first 32 bits are zeroed. If you _really_ +want the address see %px below. + +:: + + %p abcdef12 or 00000000abcdef12 + Symbols/Function Pointers ========================= @@ -85,18 +96,32 @@ Examples:: printk("Faulted at %pS\n", (void *)regs->ip); printk(" %s%pB\n", (reliable ? "" : "? "), (void *)*stack); - Kernel Pointers =============== :: - %pK 0x01234567 or 0x0123456789abcdef + %pK 01234567 or 0123456789abcdef For printing kernel pointers which should be hidden from unprivileged users. The behaviour of ``%pK`` depends on the ``kptr_restrict sysctl`` - see Documentation/sysctl/kernel.txt for more details. +Unmodified Addresses +==================== + +:: + + %px 01234567 or 0123456789abcdef + +For printing pointers when you _really_ want to print the address. Please +consider whether or not you are leaking sensitive information about the +Kernel layout in memory before printing pointers with %px. %px is +functionally equivalent to %lx. %px is preferred to %lx because it is more +uniquely grep'able. If, in the future, we need to modify the way the Kernel +handles printing pointers it will be nice to be able to find the call +sites. + Struct Resources ================ diff --git a/Documentation/scheduler/sched-energy.txt b/Documentation/scheduler/sched-energy.txt new file mode 100644 index 000000000000..dab2f9088b33 --- /dev/null +++ b/Documentation/scheduler/sched-energy.txt @@ -0,0 +1,362 @@ +Energy cost model for energy-aware scheduling (EXPERIMENTAL) + +Introduction +============= + +The basic energy model uses platform energy data stored in sched_group_energy +data structures attached to the sched_groups in the sched_domain hierarchy. The +energy cost model offers two functions that can be used to guide scheduling +decisions: + +1. static unsigned int sched_group_energy(struct energy_env *eenv) +2. static int energy_diff(struct energy_env *eenv) + +sched_group_energy() estimates the energy consumed by all cpus in a specific +sched_group including any shared resources owned exclusively by this group of +cpus. Resources shared with other cpus are excluded (e.g. later level caches). + +energy_diff() estimates the total energy impact of a utilization change. That +is, adding, removing, or migrating utilization (tasks). + +Both functions use a struct energy_env to specify the scenario to be evaluated: + + struct energy_env { + struct sched_group *sg_top; + struct sched_group *sg_cap; + int cap_idx; + int util_delta; + int src_cpu; + int dst_cpu; + int energy; + }; + +sg_top: sched_group to be evaluated. Not used by energy_diff(). + +sg_cap: sched_group covering the cpus in the same frequency domain. Set by +sched_group_energy(). + +cap_idx: Capacity state to be used for energy calculations. Set by +find_new_capacity(). + +util_delta: Amount of utilization to be added, removed, or migrated. + +src_cpu: Source cpu from where 'util_delta' utilization is removed. Should be +-1 if no source (e.g. task wake-up). + +dst_cpu: Destination cpu where 'util_delta' utilization is added. Should be -1 +if utilization is removed (e.g. terminating tasks). + +energy: Result of sched_group_energy(). + +The metric used to represent utilization is the actual per-entity running time +averaged over time using a geometric series. Very similar to the existing +per-entity load-tracking, but _not_ scaled by task priority and capped by the +capacity of the cpu. The latter property does mean that utilization may +underestimate the compute requirements for task on fully/over utilized cpus. +The greatest potential for energy savings without affecting performance too much +is scenarios where the system isn't fully utilized. If the system is deemed +fully utilized load-balancing should be done with task load (includes task +priority) instead in the interest of fairness and performance. + + +Background and Terminology +=========================== + +To make it clear from the start: + +energy = [joule] (resource like a battery on powered devices) +power = energy/time = [joule/second] = [watt] + +The goal of energy-aware scheduling is to minimize energy, while still getting +the job done. That is, we want to maximize: + + performance [inst/s] + -------------------- + power [W] + +which is equivalent to minimizing: + + energy [J] + ----------- + instruction + +while still getting 'good' performance. It is essentially an alternative +optimization objective to the current performance-only objective for the +scheduler. This alternative considers two objectives: energy-efficiency and +performance. Hence, there needs to be a user controllable knob to switch the +objective. Since it is early days, this is currently a sched_feature +(ENERGY_AWARE). + +The idea behind introducing an energy cost model is to allow the scheduler to +evaluate the implications of its decisions rather than applying energy-saving +techniques blindly that may only have positive effects on some platforms. At +the same time, the energy cost model must be as simple as possible to minimize +the scheduler latency impact. + +Platform topology +------------------ + +The system topology (cpus, caches, and NUMA information, not peripherals) is +represented in the scheduler by the sched_domain hierarchy which has +sched_groups attached at each level that covers one or more cpus (see +sched-domains.txt for more details). To add energy awareness to the scheduler +we need to consider power and frequency domains. + +Power domain: + +A power domain is a part of the system that can be powered on/off +independently. Power domains are typically organized in a hierarchy where you +may be able to power down just a cpu or a group of cpus along with any +associated resources (e.g. shared caches). Powering up a cpu means that all +power domains it is a part of in the hierarchy must be powered up. Hence, it is +more expensive to power up the first cpu that belongs to a higher level power +domain than powering up additional cpus in the same high level domain. Two +level power domain hierarchy example: + + Power source + +-------------------------------+----... +per group PD G G + | +----------+ | + +--------+-------| Shared | (other groups) +per-cpu PD G G | resource | + | | +----------+ + +-------+ +-------+ + | CPU 0 | | CPU 1 | + +-------+ +-------+ + +Frequency domain: + +Frequency domains (P-states) typically cover the same group of cpus as one of +the power domain levels. That is, there might be several smaller power domains +sharing the same frequency (P-state) or there might be a power domain spanning +multiple frequency domains. + +From a scheduling point of view there is no need to know the actual frequencies +[Hz]. All the scheduler cares about is the compute capacity available at the +current state (P-state) the cpu is in and any other available states. For that +reason, and to also factor in any cpu micro-architecture differences, compute +capacity scaling states are called 'capacity states' in this document. For SMP +systems this is equivalent to P-states. For mixed micro-architecture systems +(like ARM big.LITTLE) it is P-states scaled according to the micro-architecture +performance relative to the other cpus in the system. + +Energy modelling: +------------------ + +Due to the hierarchical nature of the power domains, the most obvious way to +model energy costs is therefore to associate power and energy costs with +domains (groups of cpus). Energy costs of shared resources are associated with +the group of cpus that share the resources, only the cost of powering the +cpu itself and any private resources (e.g. private L1 caches) is associated +with the per-cpu groups (lowest level). + +For example, for an SMP system with per-cpu power domains and a cluster level +(group of cpus) power domain we get the overall energy costs to be: + + energy = energy_cluster + n * energy_cpu + +where 'n' is the number of cpus powered up and energy_cluster is the cost paid +as soon as any cpu in the cluster is powered up. + +The power and frequency domains can naturally be mapped onto the existing +sched_domain hierarchy and sched_groups by adding the necessary data to the +existing data structures. + +The energy model considers energy consumption from two contributors (shown in +the illustration below): + +1. Busy energy: Energy consumed while a cpu and the higher level groups that it +belongs to are busy running tasks. Busy energy is associated with the state of +the cpu, not an event. The time the cpu spends in this state varies. Thus, the +most obvious platform parameter for this contribution is busy power +(energy/time). + +2. Idle energy: Energy consumed while a cpu and higher level groups that it +belongs to are idle (in a C-state). Like busy energy, idle energy is associated +with the state of the cpu. Thus, the platform parameter for this contribution +is idle power (energy/time). + +Energy consumed during transitions from an idle-state (C-state) to a busy state +(P-state) or going the other way is ignored by the model to simplify the energy +model calculations. + + + Power + ^ + | busy->idle idle->busy + | transition transition + | + | _ __ + | / \ / \__________________ + |______________/ \ / + | \ / + | Busy \ Idle / Busy + | low P-state \____________/ high P-state + | + +------------------------------------------------------------> time + +Busy |--------------| |-----------------| + +Wakeup |------| |------| + +Idle |------------| + + +The basic algorithm +==================== + +The basic idea is to determine the total energy impact when utilization is +added or removed by estimating the impact at each level in the sched_domain +hierarchy starting from the bottom (sched_group contains just a single cpu). +The energy cost comes from busy time (sched_group is awake because one or more +cpus are busy) and idle time (in an idle-state). Energy model numbers account +for energy costs associated with all cpus in the sched_group as a group. + + for_each_domain(cpu, sd) { + sg = sched_group_of(cpu) + energy_before = curr_util(sg) * busy_power(sg) + + (1-curr_util(sg)) * idle_power(sg) + energy_after = new_util(sg) * busy_power(sg) + + (1-new_util(sg)) * idle_power(sg) + energy_diff += energy_before - energy_after + + } + + return energy_diff + +{curr, new}_util: The cpu utilization at the lowest level and the overall +non-idle time for the entire group for higher levels. Utilization is in the +range 0.0 to 1.0 in the pseudo-code. + +busy_power: The power consumption of the sched_group. + +idle_power: The power consumption of the sched_group when idle. + +Note: It is a fundamental assumption that the utilization is (roughly) scale +invariant. Task utilization tracking factors in any frequency scaling and +performance scaling differences due to difference cpu microarchitectures such +that task utilization can be used across the entire system. + + +Platform energy data +===================== + +struct sched_group_energy can be attached to sched_groups in the sched_domain +hierarchy and has the following members: + +cap_states: + List of struct capacity_state representing the supported capacity states + (P-states). struct capacity_state has two members: cap and power, which + represents the compute capacity and the busy_power of the state. The + list must be ordered by capacity low->high. + +nr_cap_states: + Number of capacity states in cap_states list. + +idle_states: + List of struct idle_state containing idle_state power cost for each + idle-state supported by the system orderd by shallowest state first. + All states must be included at all level in the hierarchy, i.e. a + sched_group spanning just a single cpu must also include coupled + idle-states (cluster states). In addition to the cpuidle idle-states, + the list must also contain an entry for the idling using the arch + default idle (arch_idle_cpu()). Despite this state may not be a true + hardware idle-state it is considered the shallowest idle-state in the + energy model and must be the first entry. cpus may enter this state + (possibly 'active idling') if cpuidle decides not enter a cpuidle + idle-state. Default idle may not be used when cpuidle is enabled. + In this case, it should just be a copy of the first cpuidle idle-state. + +nr_idle_states: + Number of idle states in idle_states list. + +There are no unit requirements for the energy cost data. Data can be normalized +with any reference, however, the normalization must be consistent across all +energy cost data. That is, one bogo-joule/watt must be the same quantity for +data, but we don't care what it is. + +A recipe for platform characterization +======================================= + +Obtaining the actual model data for a particular platform requires some way of +measuring power/energy. There isn't a tool to help with this (yet). This +section provides a recipe for use as reference. It covers the steps used to +characterize the ARM TC2 development platform. This sort of measurements is +expected to be done anyway when tuning cpuidle and cpufreq for a given +platform. + +The energy model needs two types of data (struct sched_group_energy holds +these) for each sched_group where energy costs should be taken into account: + +1. Capacity state information + +A list containing the compute capacity and power consumption when fully +utilized attributed to the group as a whole for each available capacity state. +At the lowest level (group contains just a single cpu) this is the power of the +cpu alone without including power consumed by resources shared with other cpus. +It basically needs to fit the basic modelling approach described in "Background +and Terminology" section: + + energy_system = energy_shared + n * energy_cpu + +for a system containing 'n' busy cpus. Only 'energy_cpu' should be included at +the lowest level. 'energy_shared' is included at the next level which +represents the group of cpus among which the resources are shared. + +This model is, of course, a simplification of reality. Thus, power/energy +attributions might not always exactly represent how the hardware is designed. +Also, busy power is likely to depend on the workload. It is therefore +recommended to use a representative mix of workloads when characterizing the +capacity states. + +If the group has no capacity scaling support, the list will contain a single +state where power is the busy power attributed to the group. The capacity +should be set to a default value (1024). + +When frequency domains include multiple power domains, the group representing +the frequency domain and all child groups share capacity states. This must be +indicated by setting the SD_SHARE_CAP_STATES sched_domain flag. All groups at +all levels that share the capacity state must have the list of capacity states +with the power set to the contribution of the individual group. + +2. Idle power information + +Stored in the idle_states list. The power number is the group idle power +consumption in each idle state as well when the group is idle but has not +entered an idle-state ('active idle' as mentioned earlier). Due to the way the +energy model is defined, the idle power of the deepest group idle state can +alternatively be accounted for in the parent group busy power. In that case the +group idle state power values are offset such that the idle power of the +deepest state is zero. It is less intuitive, but it is easier to measure as +idle power consumed by the group and the busy/idle power of the parent group +cannot be distinguished without per group measurement points. + +Measuring capacity states and idle power: + +The capacity states' capacity and power can be estimated by running a benchmark +workload at each available capacity state. By restricting the benchmark to run +on subsets of cpus it is possible to extrapolate the power consumption of +shared resources. + +ARM TC2 has two clusters of two and three cpus respectively. Each cluster has a +shared L2 cache. TC2 has on-chip energy counters per cluster. Running a +benchmark workload on just one cpu in a cluster means that power is consumed in +the cluster (higher level group) and a single cpu (lowest level group). Adding +another benchmark task to another cpu increases the power consumption by the +amount consumed by the additional cpu. Hence, it is possible to extrapolate the +cluster busy power. + +For platforms that don't have energy counters or equivalent instrumentation +built-in, it may be possible to use an external DAQ to acquire similar data. + +If the benchmark includes some performance score (for example sysbench cpu +benchmark), this can be used to record the compute capacity. + +Measuring idle power requires insight into the idle state implementation on the +particular platform. Specifically, if the platform has coupled idle-states (or +package states). To measure non-coupled per-cpu idle-states it is necessary to +keep one cpu busy to keep any shared resources alive to isolate the idle power +of the cpu from idle/busy power of the shared resources. The cpu can be tricked +into different per-cpu idle states by disabling the other states. Based on +various combinations of measurements with specific cpus busy and disabling +idle-states it is possible to extrapolate the idle-state power. diff --git a/Documentation/scheduler/sched-pelt.c b/Documentation/scheduler/sched-pelt.c index e4219139386a..20ebf049aa09 100644 --- a/Documentation/scheduler/sched-pelt.c +++ b/Documentation/scheduler/sched-pelt.c @@ -10,34 +10,34 @@ #include <math.h> #include <stdio.h> -#define HALFLIFE 32 +#define HALFLIFE { 32, 16, 8 } #define SHIFT 32 double y; -void calc_runnable_avg_yN_inv(void) +void calc_runnable_avg_yN_inv(const int halflife) { int i; unsigned int x; printf("static const u32 runnable_avg_yN_inv[] = {"); - for (i = 0; i < HALFLIFE; i++) { + for (i = 0; i < halflife; i++) { x = ((1UL<<32)-1)*pow(y, i); - if (i % 6 == 0) printf("\n\t"); - printf("0x%8x, ", x); + if (i % 4 == 0) printf("\n\t"); + printf("0x%8x,", x); } printf("\n};\n\n"); } -int sum = 1024; +int sum; -void calc_runnable_avg_yN_sum(void) +void calc_runnable_avg_yN_sum(const int halflife) { int i; printf("static const u32 runnable_avg_yN_sum[] = {\n\t 0,"); - for (i = 1; i <= HALFLIFE; i++) { + for (i = 1; i <= halflife; i++) { if (i == 1) sum *= y; else @@ -51,11 +51,10 @@ void calc_runnable_avg_yN_sum(void) printf("\n};\n\n"); } -int n = -1; -/* first period */ -long max = 1024; +int n; +long max; -void calc_converged_max(void) +void calc_converged_max(const int halflife) { long last = 0, y_inv = ((1UL<<32)-1)*y; @@ -73,17 +72,17 @@ void calc_converged_max(void) last = max; } n--; - printf("#define LOAD_AVG_PERIOD %d\n", HALFLIFE); + printf("#define LOAD_AVG_PERIOD %d\n", halflife); printf("#define LOAD_AVG_MAX %ld\n", max); -// printf("#define LOAD_AVG_MAX_N %d\n\n", n); + printf("#define LOAD_AVG_MAX_N %d\n\n", n); } -void calc_accumulated_sum_32(void) +void calc_accumulated_sum_32(const int halflife) { int i, x = sum; printf("static const u32 __accumulated_sum_N32[] = {\n\t 0,"); - for (i = 1; i <= n/HALFLIFE+1; i++) { + for (i = 1; i <= n/halflife+1; i++) { if (i > 1) x = x/2 + sum; @@ -97,12 +96,30 @@ void calc_accumulated_sum_32(void) void main(void) { - printf("/* Generated by Documentation/scheduler/sched-pelt; do not modify. */\n\n"); - - y = pow(0.5, 1/(double)HALFLIFE); - - calc_runnable_avg_yN_inv(); -// calc_runnable_avg_yN_sum(); - calc_converged_max(); -// calc_accumulated_sum_32(); + int hl_value[] = HALFLIFE; + int hl_count = sizeof(hl_value) / sizeof(int); + int hl_idx, halflife; + + printf("/* SPDX-License-Identifier: GPL-2.0 */\n"); + printf("/* Generated by Documentation/scheduler/sched-pelt; do not modify. */\n"); + + for (hl_idx = 0; hl_idx < hl_count; ++hl_idx) { + halflife = hl_value[hl_idx]; + + y = pow(0.5, 1/(double)halflife); + sum = 1024; + /* first period */ + max = 1024; + n = -1; + + printf("\n#ifdef CONFIG_PELT_UTIL_HALFLIFE_%d\n", halflife); + calc_runnable_avg_yN_inv(halflife); + calc_runnable_avg_yN_sum(halflife); + calc_converged_max(halflife); + /* + * calc_accumulated_sum_32(halflife) precomputed load sum table of half-life, + * not used yet. + */ + printf("#endif\n"); + } } diff --git a/Documentation/scheduler/sched-tune.txt b/Documentation/scheduler/sched-tune.txt new file mode 100644 index 000000000000..1a103715f7bd --- /dev/null +++ b/Documentation/scheduler/sched-tune.txt @@ -0,0 +1,388 @@ + Central, scheduler-driven, power-performance control + (EXPERIMENTAL) + +Abstract +======== + +The topic of a single simple power-performance tunable, that is wholly +scheduler centric, and has well defined and predictable properties has come up +on several occasions in the past [1,2]. With techniques such as a scheduler +driven DVFS [3], we now have a good framework for implementing such a tunable. +This document describes the overall ideas behind its design and implementation. + + +Table of Contents +================= + +1. Motivation +2. Introduction +3. Signal Boosting Strategy +4. OPP selection using boosted CPU utilization +5. Per task group boosting +6. Per-task wakeup-placement-strategy Selection +7. Question and Answers + - What about "auto" mode? + - What about boosting on a congested system? + - How CPUs are boosted when we have tasks with multiple boost values? +8. References + + +1. Motivation +============= + +Schedutil [3] is a utilization-driven cpufreq governor which allows the +scheduler to select the optimal DVFS operating point (OPP) for running a task +allocated to a CPU. + +However, sometimes it may be desired to intentionally boost the performance of +a workload even if that could imply a reasonable increase in energy +consumption. For example, in order to reduce the response time of a task, we +may want to run the task at a higher OPP than the one that is actually required +by it's CPU bandwidth demand. + +This last requirement is especially important if we consider that one of the +main goals of the utilization-driven governor component is to replace all +currently available CPUFreq policies. Since schedutil is event-based, as +opposed to the sampling driven governors we currently have, they are already +more responsive at selecting the optimal OPP to run tasks allocated to a CPU. +However, just tracking the actual task utilization may not be enough from a +performance standpoint. For example, it is not possible to get behaviors +similar to those provided by the "performance" and "interactive" CPUFreq +governors. + +This document describes an implementation of a tunable, stacked on top of the +utilization-driven governor which extends its functionality to support task +performance boosting. + +By "performance boosting" we mean the reduction of the time required to +complete a task activation, i.e. the time elapsed from a task wakeup to its +next deactivation (e.g. because it goes back to sleep or it terminates). For +example, if we consider a simple periodic task which executes the same workload +for 5[s] every 20[s] while running at a certain OPP, a boosted execution of +that task must complete each of its activations in less than 5[s]. + +The rest of this document introduces in more details the proposed solution +which has been named SchedTune. + + +2. Introduction +=============== + +SchedTune exposes a simple user-space interface provided through a new +CGroup controller 'stune' which provides two power-performance tunables +per group: + + /<stune cgroup mount point>/schedtune.prefer_idle + /<stune cgroup mount point>/schedtune.boost + +The CGroup implementation permits arbitrary user-space defined task +classification to tune the scheduler for different goals depending on the +specific nature of the task, e.g. background vs interactive vs low-priority. + +More details are given in section 5. + +2.1 Boosting +============ + +The boost value is expressed as an integer in the range [0..100]. + +A value of 0 (default) configures the CFS scheduler for maximum energy +efficiency. This means that schedutil runs the tasks at the minimum OPP +required to satisfy their workload demand. + +A value of 100 configures scheduler for maximum performance, which translates +to the selection of the maximum OPP on that CPU. + +The range between 0 and 100 can be set to satisfy other scenarios suitably. For +example to satisfy interactive response or depending on other system events +(battery level etc). + +The overall design of the SchedTune module is built on top of "Per-Entity Load +Tracking" (PELT) signals and schedutil by introducing a bias on the OPP +selection. + +Each time a task is allocated on a CPU, cpufreq is given the opportunity to tune +the operating frequency of that CPU to better match the workload demand. The +selection of the actual OPP being activated is influenced by the boost value +for the task CGroup. + +This simple biasing approach leverages existing frameworks, which means minimal +modifications to the scheduler, and yet it allows to achieve a range of +different behaviours all from a single simple tunable knob. + +In EAS schedulers, we use boosted task and CPU utilization for energy +calculation and energy-aware task placement. + +2.2 prefer_idle +=============== + +This is a flag which indicates to the scheduler that userspace would like +the scheduler to focus on energy or to focus on performance. + +A value of 0 (default) signals to the CFS scheduler that tasks in this group +can be placed according to the energy-aware wakeup strategy. + +A value of 1 signals to the CFS scheduler that tasks in this group should be +placed to minimise wakeup latency. + +Android platforms typically use this flag for application tasks which the +user is currently interacting with. + + +3. Signal Boosting Strategy +=========================== + +The whole PELT machinery works based on the value of a few load tracking signals +which basically track the CPU bandwidth requirements for tasks and the capacity +of CPUs. The basic idea behind the SchedTune knob is to artificially inflate +some of these load tracking signals to make a task or RQ appears more demanding +that it actually is. + +Which signals have to be inflated depends on the specific "consumer". However, +independently from the specific (signal, consumer) pair, it is important to +define a simple and possibly consistent strategy for the concept of boosting a +signal. + +A boosting strategy defines how the "abstract" user-space defined +sched_cfs_boost value is translated into an internal "margin" value to be added +to a signal to get its inflated value: + + margin := boosting_strategy(sched_cfs_boost, signal) + boosted_signal := signal + margin + +The boosting strategy currently implemented in SchedTune is called 'Signal +Proportional Compensation' (SPC). With SPC, the sched_cfs_boost value is used to +compute a margin which is proportional to the complement of the original signal. +When a signal has a maximum possible value, its complement is defined as +the delta from the actual value and its possible maximum. + +Since the tunable implementation uses signals which have SCHED_CAPACITY_SCALE as +the maximum possible value, the margin becomes: + + margin := sched_cfs_boost * (SCHED_CAPACITY_SCALE - signal) + +Using this boosting strategy: +- a 100% sched_cfs_boost means that the signal is scaled to the maximum value +- each value in the range of sched_cfs_boost effectively inflates the signal in + question by a quantity which is proportional to the maximum value. + +For example, by applying the SPC boosting strategy to the selection of the OPP +to run a task it is possible to achieve these behaviors: + +- 0% boosting: run the task at the minimum OPP required by its workload +- 100% boosting: run the task at the maximum OPP available for the CPU +- 50% boosting: run at the half-way OPP between minimum and maximum + +Which means that, at 50% boosting, a task will be scheduled to run at half of +the maximum theoretically achievable performance on the specific target +platform. + +A graphical representation of an SPC boosted signal is represented in the +following figure where: + a) "-" represents the original signal + b) "b" represents a 50% boosted signal + c) "p" represents a 100% boosted signal + + + ^ + | SCHED_CAPACITY_SCALE + +-----------------------------------------------------------------+ + |pppppppppppppppppppppppppppppppppppppppppppppppppppppppppppppppppp + | + | boosted_signal + | bbbbbbbbbbbbbbbbbbbbbbbb + | + | original signal + | bbbbbbbbbbbbbbbbbbbbbbbb+----------------------+ + | | + |bbbbbbbbbbbbbbbbbb | + | | + | | + | | + | +-----------------------+ + | | + | | + | | + |------------------+ + | + | + +-----------------------------------------------------------------------> + +The plot above shows a ramped load signal (titled 'original_signal') and it's +boosted equivalent. For each step of the original signal the boosted signal +corresponding to a 50% boost is midway from the original signal and the upper +bound. Boosting by 100% generates a boosted signal which is always saturated to +the upper bound. + + +4. OPP selection using boosted CPU utilization +============================================== + +It is worth calling out that the implementation does not introduce any new load +signals. Instead, it provides an API to tune existing signals. This tuning is +done on demand and only in scheduler code paths where it is sensible to do so. +The new API calls are defined to return either the default signal or a boosted +one, depending on the value of sched_cfs_boost. This is a clean an non invasive +modification of the existing existing code paths. + +The signal representing a CPU's utilization is boosted according to the +previously described SPC boosting strategy. To schedutil, this allows a CPU +(ie CFS run-queue) to appear more used then it actually is. + +Thus, with the sched_cfs_boost enabled we have the following main functions to +get the current utilization of a CPU: + + cpu_util() + boosted_cpu_util() + +The new boosted_cpu_util() is similar to the first but returns a boosted +utilization signal which is a function of the sched_cfs_boost value. + +This function is used in the CFS scheduler code paths where schedutil needs to +decide the OPP to run a CPU at. For example, this allows selecting the highest +OPP for a CPU which has the boost value set to 100%. + + +5. Per task group boosting +========================== + +On battery powered devices there usually are many background services which are +long running and need energy efficient scheduling. On the other hand, some +applications are more performance sensitive and require an interactive +response and/or maximum performance, regardless of the energy cost. + +To better service such scenarios, the SchedTune implementation has an extension +that provides a more fine grained boosting interface. + +A new CGroup controller, namely "schedtune", can be enabled which allows to +defined and configure task groups with different boosting values. +Tasks that require special performance can be put into separate CGroups. +The value of the boost associated with the tasks in this group can be specified +using a single knob exposed by the CGroup controller: + + schedtune.boost + +This knob allows the definition of a boost value that is to be used for +SPC boosting of all tasks attached to this group. + +The current schedtune controller implementation is really simple and has these +main characteristics: + + 1) It is only possible to create 1 level depth hierarchies + + The root control groups define the system-wide boost value to be applied + by default to all tasks. Its direct subgroups are named "boost groups" and + they define the boost value for specific set of tasks. + Further nested subgroups are not allowed since they do not have a sensible + meaning from a user-space standpoint. + + 2) It is possible to define only a limited number of "boost groups" + + This number is defined at compile time and by default configured to 16. + This is a design decision motivated by two main reasons: + a) In a real system we do not expect utilization scenarios with more than + a few boost groups. For example, a reasonable collection of groups could + be just "background", "interactive" and "performance". + b) It simplifies the implementation considerably, especially for the code + which has to compute the per CPU boosting once there are multiple + RUNNABLE tasks with different boost values. + +Such a simple design should allow servicing the main utilization scenarios +identified so far. It provides a simple interface which can be used to manage +the power-performance of all tasks or only selected tasks. +Moreover, this interface can be easily integrated by user-space run-times (e.g. +Android, ChromeOS) to implement a QoS solution for task boosting based on tasks +classification, which has been a long standing requirement. + +Setup and usage +--------------- + +0. Use a kernel with CONFIG_SCHED_TUNE support enabled + +1. Check that the "schedtune" CGroup controller is available: + + root@linaro-nano:~# cat /proc/cgroups + #subsys_name hierarchy num_cgroups enabled + cpuset 0 1 1 + cpu 0 1 1 + schedtune 0 1 1 + +2. Mount a tmpfs to create the CGroups mount point (Optional) + + root@linaro-nano:~# sudo mount -t tmpfs cgroups /sys/fs/cgroup + +3. Mount the "schedtune" controller + + root@linaro-nano:~# mkdir /sys/fs/cgroup/stune + root@linaro-nano:~# sudo mount -t cgroup -o schedtune stune /sys/fs/cgroup/stune + +4. Create task groups and configure their specific boost value (Optional) + + For example here we create a "performance" boost group configure to boost + all its tasks to 100% + + root@linaro-nano:~# mkdir /sys/fs/cgroup/stune/performance + root@linaro-nano:~# echo 100 > /sys/fs/cgroup/stune/performance/schedtune.boost + +5. Move tasks into the boost group + + For example, the following moves the tasks with PID $TASKPID (and all its + threads) into the "performance" boost group. + + root@linaro-nano:~# echo "TASKPID > /sys/fs/cgroup/stune/performance/cgroup.procs + +This simple configuration allows only the threads of the $TASKPID task to run, +when needed, at the highest OPP in the most capable CPU of the system. + + +6. Per-task wakeup-placement-strategy Selection +=============================================== + +Many devices have a number of CFS tasks in use which require an absolute +minimum wakeup latency, and many tasks for which wakeup latency is not +important. + +For touch-driven environments, removing additional wakeup latency can be +critical. + +When you use the Schedtume CGroup controller, you have access to a second +parameter which allows a group to be marked such that energy_aware task +placement is bypassed for tasks belonging to that group. + +prefer_idle=0 (default - use energy-aware task placement if available) +prefer_idle=1 (never use energy-aware task placement for these tasks) + +Since the regular wakeup task placement algorithm in CFS is biased for +performance, this has the effect of restoring minimum wakeup latency +for the desired tasks whilst still allowing energy-aware wakeup placement +to save energy for other tasks. + + +7. Question and Answers +======================= + +What about "auto" mode? +----------------------- + +The 'auto' mode as described in [5] can be implemented by interfacing SchedTune +with some suitable user-space element. This element could use the exposed +system-wide or cgroup based interface. + +How are multiple groups of tasks with different boost values managed? +--------------------------------------------------------------------- + +The current SchedTune implementation keeps track of the boosted RUNNABLE tasks +on a CPU. The CPU utilization seen by schedutil (and used to select an +appropriate OPP) is boosted with a value which is the maximum of the boost +values of the currently RUNNABLE tasks in its RQ. + +This allows cpufreq to boost a CPU only while there are boosted tasks ready +to run and switch back to the energy efficient mode as soon as the last boosted +task is dequeued. + + +8. References +============= +[1] http://lwn.net/Articles/552889 +[2] http://lkml.org/lkml/2012/5/18/91 +[3] https://lkml.org/lkml/2016/3/29/1041 diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index 694968c7523c..b757d6eb365b 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -653,7 +653,8 @@ allowed to execute. perf_event_paranoid: Controls use of the performance events system by unprivileged -users (without CAP_SYS_ADMIN). The default value is 2. +users (without CAP_SYS_ADMIN). The default value is 3 if +CONFIG_SECURITY_PERF_EVENTS_RESTRICT is set, or 2 otherwise. -1: Allow use of (almost) all events by all users Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK @@ -661,6 +662,7 @@ users (without CAP_SYS_ADMIN). The default value is 2. Disallow raw tracepoint access by users without CAP_SYS_ADMIN >=1: Disallow CPU event access by users without CAP_SYS_ADMIN >=2: Disallow kernel profiling by users without CAP_SYS_ADMIN +>=3: Disallow all event access by users without CAP_SYS_ADMIN ============================================================== diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index 9baf66a9ef4e..1d1f2cb5abc8 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -30,6 +30,7 @@ Currently, these files are in /proc/sys/vm: - dirty_writeback_centisecs - drop_caches - extfrag_threshold +- extra_free_kbytes - hugepages_treat_as_movable - hugetlb_shm_group - laptop_mode @@ -260,6 +261,21 @@ any throttling. ============================================================== +extra_free_kbytes + +This parameter tells the VM to keep extra free memory between the threshold +where background reclaim (kswapd) kicks in, and the threshold where direct +reclaim (by allocating processes) kicks in. + +This is useful for workloads that require low latency memory allocations +and have a bounded burstiness in memory allocations, for example a +realtime application that receives and transmits network traffic +(causing in-kernel memory allocations) with a maximum total message burst +size of 200MB may need 200MB of extra free memory to avoid direct reclaim +related latencies. + +============================================================== + hugepages_treat_as_movable This parameter controls whether we can allocate hugepages from ZONE_MOVABLE diff --git a/Documentation/trace/events-power.txt b/Documentation/trace/events-power.txt index 21d514ced212..4d817d5acc40 100644 --- a/Documentation/trace/events-power.txt +++ b/Documentation/trace/events-power.txt @@ -25,6 +25,7 @@ cpufreq. cpu_idle "state=%lu cpu_id=%lu" cpu_frequency "state=%lu cpu_id=%lu" +cpu_frequency_limits "min=%lu max=%lu cpu_id=%lu" A suspend event is used to indicate the system going in and out of the suspend mode: diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt index d4601df6e72e..f2fcbb7a70c6 100644 --- a/Documentation/trace/ftrace.txt +++ b/Documentation/trace/ftrace.txt @@ -2407,6 +2407,35 @@ will produce: 1) 1.449 us | } +You can disable the hierarchical function call formatting and instead print a +flat list of function entry and return events. This uses the format described +in the Output Formatting section and respects all the trace options that +control that formatting. Hierarchical formatting is the default. + + hierachical: echo nofuncgraph-flat > trace_options + flat: echo funcgraph-flat > trace_options + + ie: + + # tracer: function_graph + # + # entries-in-buffer/entries-written: 68355/68355 #P:2 + # + # _-----=> irqs-off + # / _----=> need-resched + # | / _---=> hardirq/softirq + # || / _--=> preempt-depth + # ||| / delay + # TASK-PID CPU# |||| TIMESTAMP FUNCTION + # | | | |||| | | + sh-1806 [001] d... 198.843443: graph_ent: func=_raw_spin_lock + sh-1806 [001] d... 198.843445: graph_ent: func=__raw_spin_lock + sh-1806 [001] d..1 198.843447: graph_ret: func=__raw_spin_lock + sh-1806 [001] d..1 198.843449: graph_ret: func=_raw_spin_lock + sh-1806 [001] d..1 198.843451: graph_ent: func=_raw_spin_unlock_irqrestore + sh-1806 [001] d... 198.843453: graph_ret: func=_raw_spin_unlock_irqrestore + + You might find other useful features for this tracer in the following "dynamic ftrace" section such as tracing only specific functions or tasks. @@ -372,6 +372,7 @@ HOST_LOADLIBES := $(HOST_LFS_LIBS) # Make variables (CC, etc...) AS = $(CROSS_COMPILE)as LD = $(CROSS_COMPILE)ld +LDGOLD = $(CROSS_COMPILE)ld.gold CC = $(CROSS_COMPILE)gcc CPP = $(CC) -E AR = $(CROSS_COMPILE)ar @@ -480,7 +481,11 @@ endif ifeq ($(cc-name),clang) ifneq ($(CROSS_COMPILE),) -CLANG_FLAGS += --target=$(notdir $(CROSS_COMPILE:%-=%)) +CLANG_TRIPLE ?= $(CROSS_COMPILE) +CLANG_FLAGS += --target=$(notdir $(CLANG_TRIPLE:%-=%)) +ifeq ($(shell $(srctree)/scripts/clang-android.sh $(CC) $(CLANG_FLAGS)), y) +$(error "Clang with Android --target detected. Did you specify CLANG_TRIPLE?") +endif GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)elfedit)) CLANG_FLAGS += --prefix=$(GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE)) GCC_TOOLCHAIN := $(realpath $(GCC_TOOLCHAIN_DIR)/..) @@ -636,6 +641,20 @@ CFLAGS_GCOV := -fprofile-arcs -ftest-coverage -fno-tree-loop-im $(call cc-disabl CFLAGS_KCOV := $(call cc-option,-fsanitize-coverage=trace-pc,) export CFLAGS_GCOV CFLAGS_KCOV +# Make toolchain changes before including arch/$(SRCARCH)/Makefile to ensure +# ar/cc/ld-* macros return correct values. +ifdef CONFIG_LTO_CLANG +# use GNU gold with LLVMgold for LTO linking, and LD for vmlinux_link +LDFINAL_vmlinux := $(LD) +LD := $(LDGOLD) +LDFLAGS += -plugin LLVMgold.so +# use llvm-ar for building symbol tables from IR files, and llvm-dis instead +# of objdump for processing symbol versions and exports +LLVM_AR := llvm-ar +LLVM_DIS := llvm-dis +export LLVM_AR LLVM_DIS +endif + # The arch Makefile can set ARCH_{CPP,A,C}FLAGS to override the default # values of the respective KBUILD_* variables ARCH_CPPFLAGS := @@ -709,6 +728,7 @@ ifeq ($(cc-name),clang) KBUILD_CPPFLAGS += $(call cc-option,-Qunused-arguments,) KBUILD_CFLAGS += $(call cc-disable-warning, format-invalid-specifier) KBUILD_CFLAGS += $(call cc-disable-warning, gnu) +KBUILD_CFLAGS += $(call cc-disable-warning, duplicate-decl-specifier) # Quiet clang warning: comparison of unsigned expression < 0 is always false KBUILD_CFLAGS += $(call cc-disable-warning, tautological-compare) # CLANG uses a _MergedGlobals as optimization, but this breaks modpost, as the @@ -737,6 +757,11 @@ KBUILD_CFLAGS += -fomit-frame-pointer endif endif +# Initialize all stack variables with a pattern, if desired. +ifdef CONFIG_INIT_STACK_ALL +KBUILD_CFLAGS += -ftrivial-auto-var-init=pattern +endif + KBUILD_CFLAGS += $(call cc-option, -fno-var-tracking-assignments) ifdef CONFIG_DEBUG_INFO @@ -784,6 +809,53 @@ KBUILD_CFLAGS += $(call cc-option,-ffunction-sections,) KBUILD_CFLAGS += $(call cc-option,-fdata-sections,) endif +ifdef CONFIG_LTO_CLANG +lto-clang-flags := -flto -fvisibility=hidden + +# allow disabling only clang LTO where needed +DISABLE_LTO_CLANG := -fno-lto -fvisibility=default +export DISABLE_LTO_CLANG +endif + +ifdef CONFIG_LTO +lto-flags := $(lto-clang-flags) +KBUILD_CFLAGS += $(lto-flags) + +DISABLE_LTO := $(DISABLE_LTO_CLANG) +export DISABLE_LTO + +# LDFINAL_vmlinux and LDFLAGS_FINAL_vmlinux can be set to override +# the linker and flags for vmlinux_link. +export LDFINAL_vmlinux LDFLAGS_FINAL_vmlinux +endif + +ifdef CONFIG_CFI_CLANG +cfi-clang-flags += -fsanitize=cfi +DISABLE_CFI_CLANG := -fno-sanitize=cfi +ifdef CONFIG_MODULES +cfi-clang-flags += -fsanitize-cfi-cross-dso +DISABLE_CFI_CLANG += -fno-sanitize-cfi-cross-dso +endif +ifdef CONFIG_CFI_PERMISSIVE +cfi-clang-flags += -fsanitize-recover=cfi -fno-sanitize-trap=cfi +endif + +# also disable CFI when LTO is disabled +DISABLE_LTO_CLANG += $(DISABLE_CFI_CLANG) +# allow disabling only clang CFI where needed +export DISABLE_CFI_CLANG +endif + +ifdef CONFIG_CFI +# cfi-flags are re-tested in prepare-compiler-check +cfi-flags := $(cfi-clang-flags) +KBUILD_CFLAGS += $(cfi-flags) + +DISABLE_CFI := $(DISABLE_CFI_CLANG) +DISABLE_LTO += $(DISABLE_CFI) +export DISABLE_CFI +endif + # arch Makefile may override CC so keep this after arch Makefile is included NOSTDINC_FLAGS += -nostdinc -isystem $(shell $(CC) -print-file-name=include) CHECKFLAGS += $(NOSTDINC_FLAGS) @@ -1129,6 +1201,22 @@ endif # CC_STACKPROTECTOR_STRONG! Why did it build with _REGULAR?!") PHONY += prepare-compiler-check prepare-compiler-check: FORCE +# Make sure we're using a supported toolchain with LTO_CLANG +ifdef CONFIG_LTO_CLANG + ifneq ($(call clang-ifversion, -ge, 0500, y), y) + @echo Cannot use CONFIG_LTO_CLANG: requires clang 5.0 or later >&2 && exit 1 + endif + ifneq ($(call gold-ifversion, -ge, 112000000, y), y) + @echo Cannot use CONFIG_LTO_CLANG: requires GNU gold 1.12 or later >&2 && exit 1 + endif +endif +# Make sure compiler supports LTO flags +ifdef lto-flags + ifeq ($(call cc-option, $(lto-flags)),) + @echo Cannot use CONFIG_LTO: $(lto-flags) not supported by compiler \ + >&2 && exit 1 + endif +endif # Make sure compiler supports requested stack protector flag. ifdef stackp-name ifeq ($(call cc-option, $(stackp-flag)),) @@ -1143,6 +1231,11 @@ ifdef stackp-check $(stackp-flag) available but compiler is broken >&2 && exit 1 endif endif +ifdef cfi-flags + ifeq ($(call cc-option, $(cfi-flags)),) + @echo Cannot use CONFIG_CFI: $(cfi-flags) not supported by compiler >&2 && exit 1 + endif +endif @: # Generate some files @@ -1607,7 +1700,8 @@ clean: $(clean-dirs) -o -name modules.builtin -o -name '.tmp_*.o.*' \ -o -name '*.c.[012]*.*' \ -o -name '*.ll' \ - -o -name '*.gcno' \) -type f -print | xargs rm -f + -o -name '*.gcno' \ + -o -name '*.*.symversions' \) -type f -print | xargs rm -f # Generate tags for editors # --------------------------------------------------------------------------- diff --git a/arch/Kconfig b/arch/Kconfig index 77b3e21c4844..0f2363604193 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -611,6 +611,75 @@ config LD_DEAD_CODE_DATA_ELIMINATION sections (e.g., '.text.init'). Typically '.' in section names is used to distinguish them from label names / C identifiers. +config LTO + def_bool n + +config ARCH_SUPPORTS_LTO_CLANG + bool + help + An architecture should select this option it supports: + - compiling with clang, + - compiling inline assembly with clang's integrated assembler, + - and linking with either lld or GNU gold w/ LLVMgold. + +choice + prompt "Link-Time Optimization (LTO) (EXPERIMENTAL)" + default LTO_NONE + help + This option turns on Link-Time Optimization (LTO). + +config LTO_NONE + bool "None" + +config LTO_CLANG + bool "Use clang Link Time Optimization (LTO) (EXPERIMENTAL)" + depends on ARCH_SUPPORTS_LTO_CLANG + depends on !FTRACE_MCOUNT_RECORD || HAVE_C_RECORDMCOUNT + depends on !KASAN + select LTO + select THIN_ARCHIVES + select LD_DEAD_CODE_DATA_ELIMINATION + help + This option enables clang's Link Time Optimization (LTO), which allows + the compiler to optimize the kernel globally at link time. If you + enable this option, the compiler generates LLVM IR instead of object + files, and the actual compilation from IR occurs at the LTO link step, + which may take several minutes. + + If you select this option, you must compile the kernel with clang >= + 5.0 (make CC=clang) and GNU gold from binutils >= 2.27, and have the + LLVMgold plug-in in LD_LIBRARY_PATH. + +endchoice + +config CFI + bool + +config CFI_PERMISSIVE + bool "Use CFI in permissive mode" + depends on CFI + help + When selected, Control Flow Integrity (CFI) violations result in a + warning instead of a kernel panic. This option is useful for finding + CFI violations in drivers during development. + +config CFI_CLANG + bool "Use clang Control Flow Integrity (CFI) (EXPERIMENTAL)" + depends on LTO_CLANG + depends on KALLSYMS + select CFI + help + This option enables clang Control Flow Integrity (CFI), which adds + runtime checking for indirect function calls. + +config CFI_CLANG_SHADOW + bool "Use CFI shadow to speed up cross-module checks" + default y + depends on CFI_CLANG + help + If you select this option, the kernel builds a fast look-up table of + CFI check functions in loaded modules to reduce overhead. + config HAVE_ARCH_WITHIN_STACK_FRAMES bool help diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 7a8fbe9a077b..a8ba03171f5f 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1822,6 +1822,15 @@ config XEN help Say Y if you want to run Linux in a Virtual Machine on Xen on ARM. +config ARM_FLUSH_CONSOLE_ON_RESTART + bool "Force flush the console on restart" + help + If the console is locked while the system is rebooted, the messages + in the temporary logbuffer would not have propogated to all the + console drivers. This option forces the console lock to be + released if it failed to be acquired, which will cause all the + pending messages to be flushed. + endmenu menu "Boot options" @@ -1850,6 +1859,21 @@ config DEPRECATED_PARAM_STRUCT This was deprecated in 2001 and announced to live on for 5 years. Some old boot loaders still use this way. +config BUILD_ARM_APPENDED_DTB_IMAGE + bool "Build a concatenated zImage/dtb by default" + depends on OF + help + Enabling this option will cause a concatenated zImage and list of + DTBs to be built by default (instead of a standalone zImage.) + The image will built in arch/arm/boot/zImage-dtb + +config BUILD_ARM_APPENDED_DTB_IMAGE_NAMES + string "Default dtb names" + depends on BUILD_ARM_APPENDED_DTB_IMAGE + help + Space separated list of names of dtbs to append when + building a concatenated zImage-dtb. + # Compressed boot loader in ROM. Yes, we really want to ask about # TEXT and BSS so we preserve their values in the config files. config ZBOOT_ROM_TEXT diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 234ee43b4438..ffc188d36dda 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -305,6 +305,8 @@ libs-y := arch/arm/lib/ $(libs-y) boot := arch/arm/boot ifeq ($(CONFIG_XIP_KERNEL),y) KBUILD_IMAGE := $(boot)/xipImage +else ifeq ($(CONFIG_BUILD_ARM_APPENDED_DTB_IMAGE),y) +KBUILD_IMAGE := $(boot)/zImage-dtb else KBUILD_IMAGE := $(boot)/zImage endif @@ -358,6 +360,9 @@ ifeq ($(CONFIG_VDSO),y) $(Q)$(MAKE) $(build)=arch/arm/vdso $@ endif +zImage-dtb: vmlinux scripts dtbs + $(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@ + # We use MRPROPER_FILES and CLEAN_FILES now archclean: $(Q)$(MAKE) $(clean)=$(boot) diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile index 50f8d1be7fcb..da75630c440d 100644 --- a/arch/arm/boot/Makefile +++ b/arch/arm/boot/Makefile @@ -16,6 +16,7 @@ OBJCOPYFLAGS :=-O binary -R .comment -S ifneq ($(MACHINE),) include $(MACHINE)/Makefile.boot endif +include $(srctree)/arch/arm/boot/dts/Makefile # Note: the following conditions must always be true: # ZRELADDR == virt_to_phys(PAGE_OFFSET + TEXT_OFFSET) @@ -29,6 +30,14 @@ export ZRELADDR INITRD_PHYS PARAMS_PHYS targets := Image zImage xipImage bootpImage uImage +DTB_NAMES := $(subst $\",,$(CONFIG_BUILD_ARM_APPENDED_DTB_IMAGE_NAMES)) +ifneq ($(DTB_NAMES),) +DTB_LIST := $(addsuffix .dtb,$(DTB_NAMES)) +else +DTB_LIST := $(dtb-y) +endif +DTB_OBJS := $(addprefix $(obj)/dts/,$(DTB_LIST)) + ifeq ($(CONFIG_XIP_KERNEL),y) $(obj)/xipImage: vmlinux FORCE @@ -55,6 +64,10 @@ $(obj)/compressed/vmlinux: $(obj)/Image FORCE $(obj)/zImage: $(obj)/compressed/vmlinux FORCE $(call if_changed,objcopy) +$(obj)/zImage-dtb: $(obj)/zImage $(DTB_OBJS) FORCE + $(call if_changed,cat) + @echo ' Kernel: $@ is ready' + endif ifneq ($(LOADADDR),) diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 8ca539bdac35..f0de0b356cd4 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -792,6 +792,8 @@ __armv7_mmu_cache_on: bic r6, r6, #1 << 31 @ 32-bit translation system bic r6, r6, #(7 << 0) | (1 << 4) @ use only ttbr0 mcrne p15, 0, r3, c2, c0, 0 @ load page table pointer + mcrne p15, 0, r0, c8, c7, 0 @ flush I,D TLBs + mcr p15, 0, r0, c7, c5, 4 @ ISB mcrne p15, 0, r1, c3, c0, 0 @ load domain access control mcrne p15, 0, r6, c2, c0, 2 @ load ttb control #endif diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile index eff87a344566..86e591cc2567 100644 --- a/arch/arm/boot/dts/Makefile +++ b/arch/arm/boot/dts/Makefile @@ -1074,5 +1074,15 @@ endif dtstree := $(srctree)/$(src) dtb-$(CONFIG_OF_ALL_DTBS) := $(patsubst $(dtstree)/%.dts,%.dtb, $(wildcard $(dtstree)/*.dts)) -always := $(dtb-y) +DTB_NAMES := $(subst $\",,$(CONFIG_BUILD_ARM_APPENDED_DTB_IMAGE_NAMES)) +ifneq ($(DTB_NAMES),) +DTB_LIST := $(addsuffix .dtb,$(DTB_NAMES)) +else +DTB_LIST := $(dtb-y) +endif + +targets += dtbs dtbs_install +targets += $(DTB_LIST) + +always := $(DTB_LIST) clean-files := *.dtb diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts index a4c7713edfcd..c5c365f35baa 100644 --- a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts +++ b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts @@ -41,6 +41,7 @@ cci-control-port = <&cci_control1>; cpu-idle-states = <&CLUSTER_SLEEP_BIG>; capacity-dmips-mhz = <1024>; + sched-energy-costs = <&CPU_COST_A15 &CLUSTER_COST_A15>; }; cpu1: cpu@1 { @@ -50,6 +51,7 @@ cci-control-port = <&cci_control1>; cpu-idle-states = <&CLUSTER_SLEEP_BIG>; capacity-dmips-mhz = <1024>; + sched-energy-costs = <&CPU_COST_A15 &CLUSTER_COST_A15>; }; cpu2: cpu@2 { @@ -59,6 +61,7 @@ cci-control-port = <&cci_control2>; cpu-idle-states = <&CLUSTER_SLEEP_LITTLE>; capacity-dmips-mhz = <516>; + sched-energy-costs = <&CPU_COST_A7 &CLUSTER_COST_A7>; }; cpu3: cpu@3 { @@ -68,6 +71,7 @@ cci-control-port = <&cci_control2>; cpu-idle-states = <&CLUSTER_SLEEP_LITTLE>; capacity-dmips-mhz = <516>; + sched-energy-costs = <&CPU_COST_A7 &CLUSTER_COST_A7>; }; cpu4: cpu@4 { @@ -77,6 +81,7 @@ cci-control-port = <&cci_control2>; cpu-idle-states = <&CLUSTER_SLEEP_LITTLE>; capacity-dmips-mhz = <516>; + sched-energy-costs = <&CPU_COST_A7 &CLUSTER_COST_A7>; }; idle-states { @@ -96,6 +101,77 @@ min-residency-us = <2500>; }; }; + + energy-costs { + CPU_COST_A15: core-cost0 { + busy-cost-data = < + 426 2021 + 512 2312 + 597 2756 + 682 3125 + 768 3524 + 853 3846 + 938 5177 + 1024 6997 + >; + idle-cost-data = < + 0 + 0 + 0 + >; + }; + CPU_COST_A7: core-cost1 { + busy-cost-data = < + 150 187 + 172 275 + 215 334 + 258 407 + 301 447 + 344 549 + 387 761 + 430 1024 + >; + idle-cost-data = < + 0 + 0 + 0 + >; + }; + CLUSTER_COST_A15: cluster-cost0 { + busy-cost-data = < + 426 7920 + 512 8165 + 597 8172 + 682 8195 + 768 8265 + 853 8446 + 938 11426 + 1024 15200 + >; + idle-cost-data = < + 70 + 70 + 25 + >; + }; + CLUSTER_COST_A7: cluster-cost1 { + busy-cost-data = < + 150 2967 + 172 2792 + 215 2810 + 258 2815 + 301 2919 + 344 2847 + 387 3917 + 430 4905 + >; + idle-cost-data = < + 25 + 25 + 10 + >; + }; + }; }; memory@80000000 { diff --git a/arch/arm/configs/ranchu_defconfig b/arch/arm/configs/ranchu_defconfig new file mode 100644 index 000000000000..83a3c0d82662 --- /dev/null +++ b/arch/arm/configs/ranchu_defconfig @@ -0,0 +1,313 @@ +# CONFIG_LOCALVERSION_AUTO is not set +CONFIG_AUDIT=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_TASKSTATS=y +CONFIG_TASK_DELAY_ACCT=y +CONFIG_TASK_XACCT=y +CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_LOG_BUF_SHIFT=14 +CONFIG_CGROUPS=y +CONFIG_CGROUP_DEBUG=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CPUSETS=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_CGROUP_SCHED=y +CONFIG_RT_GROUP_SCHED=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_KALLSYMS_ALL=y +CONFIG_EMBEDDED=y +CONFIG_PROFILING=y +CONFIG_OPROFILE=y +CONFIG_ARCH_MMAP_RND_BITS=16 +# CONFIG_BLK_DEV_BSG is not set +# CONFIG_IOSCHED_DEADLINE is not set +# CONFIG_IOSCHED_CFQ is not set +CONFIG_ARCH_VIRT=y +CONFIG_ARM_KERNMEM_PERMS=y +CONFIG_SMP=y +CONFIG_PREEMPT=y +CONFIG_AEABI=y +CONFIG_HIGHMEM=y +CONFIG_KSM=y +CONFIG_SECCOMP=y +CONFIG_CMDLINE="console=ttyAMA0" +CONFIG_VFP=y +CONFIG_NEON=y +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +CONFIG_PM_AUTOSLEEP=y +CONFIG_PM_WAKELOCKS=y +CONFIG_PM_WAKELOCKS_LIMIT=0 +# CONFIG_PM_WAKELOCKS_GC is not set +CONFIG_PM_DEBUG=y +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_XFRM_USER=y +CONFIG_NET_KEY=y +CONFIG_INET=y +CONFIG_INET_DIAG_DESTROY=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +CONFIG_INET_ESP=y +# CONFIG_INET_LRO is not set +CONFIG_IPV6_ROUTER_PREF=y +CONFIG_IPV6_ROUTE_INFO=y +CONFIG_IPV6_OPTIMISTIC_DAD=y +CONFIG_INET6_AH=y +CONFIG_INET6_ESP=y +CONFIG_INET6_IPCOMP=y +CONFIG_IPV6_MIP6=y +CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_NETFILTER=y +CONFIG_NF_CONNTRACK=y +CONFIG_NF_CONNTRACK_SECMARK=y +CONFIG_NF_CONNTRACK_EVENTS=y +CONFIG_NF_CT_PROTO_DCCP=y +CONFIG_NF_CT_PROTO_SCTP=y +CONFIG_NF_CT_PROTO_UDPLITE=y +CONFIG_NF_CONNTRACK_AMANDA=y +CONFIG_NF_CONNTRACK_FTP=y +CONFIG_NF_CONNTRACK_H323=y +CONFIG_NF_CONNTRACK_IRC=y +CONFIG_NF_CONNTRACK_NETBIOS_NS=y +CONFIG_NF_CONNTRACK_PPTP=y +CONFIG_NF_CONNTRACK_SANE=y +CONFIG_NF_CONNTRACK_TFTP=y +CONFIG_NF_CT_NETLINK=y +CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y +CONFIG_NETFILTER_XT_TARGET_CONNMARK=y +CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y +CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y +CONFIG_NETFILTER_XT_TARGET_MARK=y +CONFIG_NETFILTER_XT_TARGET_NFLOG=y +CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y +CONFIG_NETFILTER_XT_TARGET_TPROXY=y +CONFIG_NETFILTER_XT_TARGET_TRACE=y +CONFIG_NETFILTER_XT_TARGET_SECMARK=y +CONFIG_NETFILTER_XT_TARGET_TCPMSS=y +CONFIG_NETFILTER_XT_MATCH_COMMENT=y +CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y +CONFIG_NETFILTER_XT_MATCH_CONNMARK=y +CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y +CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y +CONFIG_NETFILTER_XT_MATCH_HELPER=y +CONFIG_NETFILTER_XT_MATCH_IPRANGE=y +CONFIG_NETFILTER_XT_MATCH_LENGTH=y +CONFIG_NETFILTER_XT_MATCH_LIMIT=y +CONFIG_NETFILTER_XT_MATCH_MAC=y +CONFIG_NETFILTER_XT_MATCH_MARK=y +CONFIG_NETFILTER_XT_MATCH_OWNER=y +CONFIG_NETFILTER_XT_MATCH_POLICY=y +CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y +CONFIG_NETFILTER_XT_MATCH_QUOTA=y +CONFIG_NETFILTER_XT_MATCH_QUOTA2=y +CONFIG_NETFILTER_XT_MATCH_SOCKET=y +CONFIG_NETFILTER_XT_MATCH_STATE=y +CONFIG_NETFILTER_XT_MATCH_STATISTIC=y +CONFIG_NETFILTER_XT_MATCH_STRING=y +CONFIG_NETFILTER_XT_MATCH_TIME=y +CONFIG_NETFILTER_XT_MATCH_U32=y +CONFIG_NF_CONNTRACK_IPV4=y +CONFIG_IP_NF_IPTABLES=y +CONFIG_IP_NF_MATCH_AH=y +CONFIG_IP_NF_MATCH_ECN=y +CONFIG_IP_NF_MATCH_TTL=y +CONFIG_IP_NF_FILTER=y +CONFIG_IP_NF_TARGET_REJECT=y +CONFIG_IP_NF_MANGLE=y +CONFIG_IP_NF_RAW=y +CONFIG_IP_NF_SECURITY=y +CONFIG_IP_NF_ARPTABLES=y +CONFIG_IP_NF_ARPFILTER=y +CONFIG_IP_NF_ARP_MANGLE=y +CONFIG_NF_CONNTRACK_IPV6=y +CONFIG_IP6_NF_IPTABLES=y +CONFIG_IP6_NF_FILTER=y +CONFIG_IP6_NF_TARGET_REJECT=y +CONFIG_IP6_NF_MANGLE=y +CONFIG_IP6_NF_RAW=y +CONFIG_BRIDGE=y +CONFIG_NET_SCHED=y +CONFIG_NET_SCH_HTB=y +CONFIG_NET_CLS_U32=y +CONFIG_NET_EMATCH=y +CONFIG_NET_EMATCH_U32=y +CONFIG_NET_CLS_ACT=y +# CONFIG_WIRELESS is not set +CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_MTD=y +CONFIG_MTD_CMDLINE_PARTS=y +CONFIG_MTD_BLOCK=y +CONFIG_MTD_CFI=y +CONFIG_MTD_CFI_INTELEXT=y +CONFIG_MTD_CFI_AMDSTD=y +CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_SIZE=8192 +CONFIG_VIRTIO_BLK=y +CONFIG_MD=y +CONFIG_BLK_DEV_DM=y +CONFIG_DM_CRYPT=y +CONFIG_DM_UEVENT=y +CONFIG_DM_VERITY=y +CONFIG_DM_VERITY_FEC=y +CONFIG_NETDEVICES=y +CONFIG_TUN=y +CONFIG_VIRTIO_NET=y +CONFIG_SMSC911X=y +CONFIG_PPP=y +CONFIG_PPP_BSDCOMP=y +CONFIG_PPP_DEFLATE=y +CONFIG_PPP_MPPE=y +CONFIG_USB_USBNET=y +# CONFIG_WLAN is not set +CONFIG_INPUT_EVDEV=y +CONFIG_INPUT_KEYRESET=y +CONFIG_KEYBOARD_GOLDFISH_EVENTS=y +# CONFIG_INPUT_MOUSE is not set +CONFIG_INPUT_JOYSTICK=y +CONFIG_JOYSTICK_XPAD=y +CONFIG_JOYSTICK_XPAD_FF=y +CONFIG_JOYSTICK_XPAD_LEDS=y +CONFIG_INPUT_TABLET=y +CONFIG_TABLET_USB_ACECAD=y +CONFIG_TABLET_USB_AIPTEK=y +CONFIG_TABLET_USB_GTCO=y +CONFIG_TABLET_USB_HANWANG=y +CONFIG_TABLET_USB_KBTAB=y +CONFIG_INPUT_MISC=y +CONFIG_INPUT_UINPUT=y +CONFIG_INPUT_GPIO=y +# CONFIG_SERIO_SERPORT is not set +CONFIG_SERIO_AMBAKMI=y +# CONFIG_VT is not set +# CONFIG_LEGACY_PTYS is not set +# CONFIG_DEVMEM is not set +# CONFIG_DEVKMEM is not set +CONFIG_SERIAL_AMBA_PL011=y +CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +CONFIG_VIRTIO_CONSOLE=y +# CONFIG_HW_RANDOM is not set +# CONFIG_HWMON is not set +CONFIG_MEDIA_SUPPORT=y +CONFIG_FB=y +CONFIG_FB_GOLDFISH=y +CONFIG_FB_SIMPLE=y +CONFIG_BACKLIGHT_LCD_SUPPORT=y +CONFIG_LOGO=y +# CONFIG_LOGO_LINUX_MONO is not set +# CONFIG_LOGO_LINUX_VGA16 is not set +CONFIG_SOUND=y +CONFIG_SND=y +CONFIG_HIDRAW=y +CONFIG_UHID=y +CONFIG_HID_A4TECH=y +CONFIG_HID_ACRUX=y +CONFIG_HID_ACRUX_FF=y +CONFIG_HID_APPLE=y +CONFIG_HID_BELKIN=y +CONFIG_HID_CHERRY=y +CONFIG_HID_CHICONY=y +CONFIG_HID_PRODIKEYS=y +CONFIG_HID_CYPRESS=y +CONFIG_HID_DRAGONRISE=y +CONFIG_DRAGONRISE_FF=y +CONFIG_HID_EMS_FF=y +CONFIG_HID_ELECOM=y +CONFIG_HID_EZKEY=y +CONFIG_HID_HOLTEK=y +CONFIG_HID_KEYTOUCH=y +CONFIG_HID_KYE=y +CONFIG_HID_UCLOGIC=y +CONFIG_HID_WALTOP=y +CONFIG_HID_GYRATION=y +CONFIG_HID_TWINHAN=y +CONFIG_HID_KENSINGTON=y +CONFIG_HID_LCPOWER=y +CONFIG_HID_LOGITECH=y +CONFIG_HID_LOGITECH_DJ=y +CONFIG_LOGITECH_FF=y +CONFIG_LOGIRUMBLEPAD2_FF=y +CONFIG_LOGIG940_FF=y +CONFIG_HID_MAGICMOUSE=y +CONFIG_HID_MICROSOFT=y +CONFIG_HID_MONTEREY=y +CONFIG_HID_MULTITOUCH=y +CONFIG_HID_NTRIG=y +CONFIG_HID_ORTEK=y +CONFIG_HID_PANTHERLORD=y +CONFIG_PANTHERLORD_FF=y +CONFIG_HID_PETALYNX=y +CONFIG_HID_PICOLCD=y +CONFIG_HID_PRIMAX=y +CONFIG_HID_ROCCAT=y +CONFIG_HID_SAITEK=y +CONFIG_HID_SAMSUNG=y +CONFIG_HID_SONY=y +CONFIG_HID_SPEEDLINK=y +CONFIG_HID_SUNPLUS=y +CONFIG_HID_GREENASIA=y +CONFIG_GREENASIA_FF=y +CONFIG_HID_SMARTJOYPLUS=y +CONFIG_SMARTJOYPLUS_FF=y +CONFIG_HID_TIVO=y +CONFIG_HID_TOPSEED=y +CONFIG_HID_THRUSTMASTER=y +CONFIG_HID_WACOM=y +CONFIG_HID_WIIMOTE=y +CONFIG_HID_ZEROPLUS=y +CONFIG_HID_ZYDACRON=y +CONFIG_USB_HIDDEV=y +CONFIG_USB_ANNOUNCE_NEW_DEVICES=y +CONFIG_USB_EHCI_HCD=y +CONFIG_USB_OTG_WAKELOCK=y +CONFIG_RTC_CLASS=y +CONFIG_RTC_DRV_PL031=y +CONFIG_VIRTIO_MMIO=y +CONFIG_STAGING=y +CONFIG_ASHMEM=y +CONFIG_ANDROID_LOW_MEMORY_KILLER=y +CONFIG_SYNC=y +CONFIG_SW_SYNC=y +CONFIG_SW_SYNC_USER=y +CONFIG_ION=y +CONFIG_GOLDFISH_AUDIO=y +CONFIG_GOLDFISH=y +CONFIG_GOLDFISH_PIPE=y +CONFIG_ANDROID=y +CONFIG_ANDROID_BINDER_IPC=y +CONFIG_EXT4_FS=y +CONFIG_EXT4_FS_SECURITY=y +CONFIG_QUOTA=y +CONFIG_FUSE_FS=y +CONFIG_CUSE=y +CONFIG_MSDOS_FS=y +CONFIG_VFAT_FS=y +CONFIG_TMPFS=y +CONFIG_TMPFS_POSIX_ACL=y +CONFIG_PSTORE=y +CONFIG_PSTORE_CONSOLE=y +CONFIG_PSTORE_RAM=y +CONFIG_NFS_FS=y +CONFIG_ROOT_NFS=y +CONFIG_NLS_CODEPAGE_437=y +CONFIG_NLS_ISO8859_1=y +CONFIG_DEBUG_INFO=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_DETECT_HUNG_TASK=y +CONFIG_PANIC_TIMEOUT=5 +# CONFIG_SCHED_DEBUG is not set +CONFIG_SCHEDSTATS=y +CONFIG_TIMER_STATS=y +CONFIG_ENABLE_DEFAULT_TRACERS=y +CONFIG_SECURITY=y +CONFIG_SECURITY_NETWORK=y +CONFIG_SECURITY_SELINUX=y +CONFIG_VIRTUALIZATION=y diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig index b8e69fe282b8..5c278a8cce68 100644 --- a/arch/arm/crypto/Kconfig +++ b/arch/arm/crypto/Kconfig @@ -69,6 +69,15 @@ config CRYPTO_AES_ARM help Use optimized AES assembler routines for ARM platforms. + On ARM processors without the Crypto Extensions, this is the + fastest AES implementation for single blocks. For multiple + blocks, the NEON bit-sliced implementation is usually faster. + + This implementation may be vulnerable to cache timing attacks, + since it uses lookup tables. However, as countermeasures it + disables IRQs and preloads the tables; it is hoped this makes + such attacks very difficult. + config CRYPTO_AES_ARM_BS tristate "Bit sliced AES using NEON instructions" depends on KERNEL_MODE_NEON @@ -116,9 +125,14 @@ config CRYPTO_CRC32_ARM_CE select CRYPTO_HASH config CRYPTO_CHACHA20_NEON - tristate "NEON accelerated ChaCha20 symmetric cipher" + tristate "NEON accelerated ChaCha stream cipher algorithms" depends on KERNEL_MODE_NEON select CRYPTO_BLKCIPHER select CRYPTO_CHACHA20 +config CRYPTO_NHPOLY1305_NEON + tristate "NEON accelerated NHPoly1305 hash function (for Adiantum)" + depends on KERNEL_MODE_NEON + select CRYPTO_NHPOLY1305 + endif diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile index c9919c2b7ad1..5668d910fb15 100644 --- a/arch/arm/crypto/Makefile +++ b/arch/arm/crypto/Makefile @@ -9,7 +9,8 @@ obj-$(CONFIG_CRYPTO_SHA1_ARM) += sha1-arm.o obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sha1-arm-neon.o obj-$(CONFIG_CRYPTO_SHA256_ARM) += sha256-arm.o obj-$(CONFIG_CRYPTO_SHA512_ARM) += sha512-arm.o -obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha20-neon.o +obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha-neon.o +obj-$(CONFIG_CRYPTO_NHPOLY1305_NEON) += nhpoly1305-neon.o ce-obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o ce-obj-$(CONFIG_CRYPTO_SHA1_ARM_CE) += sha1-arm-ce.o @@ -52,7 +53,8 @@ aes-arm-ce-y := aes-ce-core.o aes-ce-glue.o ghash-arm-ce-y := ghash-ce-core.o ghash-ce-glue.o crct10dif-arm-ce-y := crct10dif-ce-core.o crct10dif-ce-glue.o crc32-arm-ce-y:= crc32-ce-core.o crc32-ce-glue.o -chacha20-neon-y := chacha20-neon-core.o chacha20-neon-glue.o +chacha-neon-y := chacha-neon-core.o chacha-neon-glue.o +nhpoly1305-neon-y := nh-neon-core.o nhpoly1305-neon-glue.o ifdef REGENERATE_ARM_CRYPTO quiet_cmd_perl = PERL $@ diff --git a/arch/arm/crypto/aes-cipher-core.S b/arch/arm/crypto/aes-cipher-core.S index 54b384084637..f2d67c095e59 100644 --- a/arch/arm/crypto/aes-cipher-core.S +++ b/arch/arm/crypto/aes-cipher-core.S @@ -10,6 +10,7 @@ */ #include <linux/linkage.h> +#include <asm/assembler.h> #include <asm/cache.h> .text @@ -41,7 +42,7 @@ .endif .endm - .macro __hround, out0, out1, in0, in1, in2, in3, t3, t4, enc, sz, op + .macro __hround, out0, out1, in0, in1, in2, in3, t3, t4, enc, sz, op, oldcpsr __select \out0, \in0, 0 __select t0, \in1, 1 __load \out0, \out0, 0, \sz, \op @@ -73,6 +74,14 @@ __load t0, t0, 3, \sz, \op __load \t4, \t4, 3, \sz, \op + .ifnb \oldcpsr + /* + * This is the final round and we're done with all data-dependent table + * lookups, so we can safely re-enable interrupts. + */ + restore_irqs \oldcpsr + .endif + eor \out1, \out1, t1, ror #24 eor \out0, \out0, t2, ror #16 ldm rk!, {t1, t2} @@ -83,14 +92,14 @@ eor \out1, \out1, t2 .endm - .macro fround, out0, out1, out2, out3, in0, in1, in2, in3, sz=2, op + .macro fround, out0, out1, out2, out3, in0, in1, in2, in3, sz=2, op, oldcpsr __hround \out0, \out1, \in0, \in1, \in2, \in3, \out2, \out3, 1, \sz, \op - __hround \out2, \out3, \in2, \in3, \in0, \in1, \in1, \in2, 1, \sz, \op + __hround \out2, \out3, \in2, \in3, \in0, \in1, \in1, \in2, 1, \sz, \op, \oldcpsr .endm - .macro iround, out0, out1, out2, out3, in0, in1, in2, in3, sz=2, op + .macro iround, out0, out1, out2, out3, in0, in1, in2, in3, sz=2, op, oldcpsr __hround \out0, \out1, \in0, \in3, \in2, \in1, \out2, \out3, 0, \sz, \op - __hround \out2, \out3, \in2, \in1, \in0, \in3, \in1, \in0, 0, \sz, \op + __hround \out2, \out3, \in2, \in1, \in0, \in3, \in1, \in0, 0, \sz, \op, \oldcpsr .endm .macro __rev, out, in @@ -118,13 +127,14 @@ .macro do_crypt, round, ttab, ltab, bsz push {r3-r11, lr} + // Load keys first, to reduce latency in case they're not cached yet. + ldm rk!, {r8-r11} + ldr r4, [in] ldr r5, [in, #4] ldr r6, [in, #8] ldr r7, [in, #12] - ldm rk!, {r8-r11} - #ifdef CONFIG_CPU_BIG_ENDIAN __rev r4, r4 __rev r5, r5 @@ -138,6 +148,25 @@ eor r7, r7, r11 __adrl ttab, \ttab + /* + * Disable interrupts and prefetch the 1024-byte 'ft' or 'it' table into + * L1 cache, assuming cacheline size >= 32. This is a hardening measure + * intended to make cache-timing attacks more difficult. They may not + * be fully prevented, however; see the paper + * https://cr.yp.to/antiforgery/cachetiming-20050414.pdf + * ("Cache-timing attacks on AES") for a discussion of the many + * difficulties involved in writing truly constant-time AES software. + */ + save_and_disable_irqs t0 + .set i, 0 + .rept 1024 / 128 + ldr r8, [ttab, #i + 0] + ldr r9, [ttab, #i + 32] + ldr r10, [ttab, #i + 64] + ldr r11, [ttab, #i + 96] + .set i, i + 128 + .endr + push {t0} // oldcpsr tst rounds, #2 bne 1f @@ -151,8 +180,21 @@ \round r4, r5, r6, r7, r8, r9, r10, r11 b 0b -2: __adrl ttab, \ltab - \round r4, r5, r6, r7, r8, r9, r10, r11, \bsz, b +2: .ifb \ltab + add ttab, ttab, #1 + .else + __adrl ttab, \ltab + // Prefetch inverse S-box for final round; see explanation above + .set i, 0 + .rept 256 / 64 + ldr t0, [ttab, #i + 0] + ldr t1, [ttab, #i + 32] + .set i, i + 64 + .endr + .endif + + pop {rounds} // oldcpsr + \round r4, r5, r6, r7, r8, r9, r10, r11, \bsz, b, rounds #ifdef CONFIG_CPU_BIG_ENDIAN __rev r4, r4 @@ -174,6 +216,16 @@ .ltorg .endm +ENTRY(__aes_arm_encrypt) + do_crypt fround, crypto_ft_tab,, 2 +ENDPROC(__aes_arm_encrypt) + + .align 5 +ENTRY(__aes_arm_decrypt) + do_crypt iround, crypto_it_tab, __aes_arm_inverse_sbox, 0 +ENDPROC(__aes_arm_decrypt) + + .section ".rodata", "a" .align L1_CACHE_SHIFT .type __aes_arm_inverse_sbox, %object __aes_arm_inverse_sbox: @@ -210,12 +262,3 @@ __aes_arm_inverse_sbox: .byte 0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26 .byte 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d .size __aes_arm_inverse_sbox, . - __aes_arm_inverse_sbox - -ENTRY(__aes_arm_encrypt) - do_crypt fround, crypto_ft_tab, crypto_ft_tab + 1, 2 -ENDPROC(__aes_arm_encrypt) - - .align 5 -ENTRY(__aes_arm_decrypt) - do_crypt iround, crypto_it_tab, __aes_arm_inverse_sbox, 0 -ENDPROC(__aes_arm_decrypt) diff --git a/arch/arm/crypto/chacha20-neon-core.S b/arch/arm/crypto/chacha-neon-core.S index 3fecb2124c35..eb22926d4912 100644 --- a/arch/arm/crypto/chacha20-neon-core.S +++ b/arch/arm/crypto/chacha-neon-core.S @@ -1,5 +1,5 @@ /* - * ChaCha20 256-bit cipher algorithm, RFC7539, ARM NEON functions + * ChaCha/XChaCha NEON helper functions * * Copyright (C) 2016 Linaro, Ltd. <ard.biesheuvel@linaro.org> * @@ -18,42 +18,61 @@ * (at your option) any later version. */ + /* + * NEON doesn't have a rotate instruction. The alternatives are, more or less: + * + * (a) vshl.u32 + vsri.u32 (needs temporary register) + * (b) vshl.u32 + vshr.u32 + vorr (needs temporary register) + * (c) vrev32.16 (16-bit rotations only) + * (d) vtbl.8 + vtbl.8 (multiple of 8 bits rotations only, + * needs index vector) + * + * ChaCha has 16, 12, 8, and 7-bit rotations. For the 12 and 7-bit rotations, + * the only choices are (a) and (b). We use (a) since it takes two-thirds the + * cycles of (b) on both Cortex-A7 and Cortex-A53. + * + * For the 16-bit rotation, we use vrev32.16 since it's consistently fastest + * and doesn't need a temporary register. + * + * For the 8-bit rotation, we use vtbl.8 + vtbl.8. On Cortex-A7, this sequence + * is twice as fast as (a), even when doing (a) on multiple registers + * simultaneously to eliminate the stall between vshl and vsri. Also, it + * parallelizes better when temporary registers are scarce. + * + * A disadvantage is that on Cortex-A53, the vtbl sequence is the same speed as + * (a), so the need to load the rotation table actually makes the vtbl method + * slightly slower overall on that CPU (~1.3% slower ChaCha20). Still, it + * seems to be a good compromise to get a more significant speed boost on some + * CPUs, e.g. ~4.8% faster ChaCha20 on Cortex-A7. + */ + #include <linux/linkage.h> .text .fpu neon .align 5 -ENTRY(chacha20_block_xor_neon) - // r0: Input state matrix, s - // r1: 1 data block output, o - // r2: 1 data block input, i - - // - // This function encrypts one ChaCha20 block by loading the state matrix - // in four NEON registers. It performs matrix operation on four words in - // parallel, but requireds shuffling to rearrange the words after each - // round. - // - - // x0..3 = s0..3 - add ip, r0, #0x20 - vld1.32 {q0-q1}, [r0] - vld1.32 {q2-q3}, [ip] - - vmov q8, q0 - vmov q9, q1 - vmov q10, q2 - vmov q11, q3 +/* + * chacha_permute - permute one block + * + * Permute one 64-byte block where the state matrix is stored in the four NEON + * registers q0-q3. It performs matrix operations on four words in parallel, + * but requires shuffling to rearrange the words after each round. + * + * The round count is given in r3. + * + * Clobbers: r3, ip, q4-q5 + */ +chacha_permute: - mov r3, #10 + adr ip, .Lrol8_table + vld1.8 {d10}, [ip, :64] .Ldoubleround: // x0 += x1, x3 = rotl32(x3 ^ x0, 16) vadd.i32 q0, q0, q1 - veor q4, q3, q0 - vshl.u32 q3, q4, #16 - vsri.u32 q3, q4, #16 + veor q3, q3, q0 + vrev32.16 q3, q3 // x2 += x3, x1 = rotl32(x1 ^ x2, 12) vadd.i32 q2, q2, q3 @@ -63,9 +82,9 @@ ENTRY(chacha20_block_xor_neon) // x0 += x1, x3 = rotl32(x3 ^ x0, 8) vadd.i32 q0, q0, q1 - veor q4, q3, q0 - vshl.u32 q3, q4, #8 - vsri.u32 q3, q4, #24 + veor q3, q3, q0 + vtbl.8 d6, {d6}, d10 + vtbl.8 d7, {d7}, d10 // x2 += x3, x1 = rotl32(x1 ^ x2, 7) vadd.i32 q2, q2, q3 @@ -82,9 +101,8 @@ ENTRY(chacha20_block_xor_neon) // x0 += x1, x3 = rotl32(x3 ^ x0, 16) vadd.i32 q0, q0, q1 - veor q4, q3, q0 - vshl.u32 q3, q4, #16 - vsri.u32 q3, q4, #16 + veor q3, q3, q0 + vrev32.16 q3, q3 // x2 += x3, x1 = rotl32(x1 ^ x2, 12) vadd.i32 q2, q2, q3 @@ -94,9 +112,9 @@ ENTRY(chacha20_block_xor_neon) // x0 += x1, x3 = rotl32(x3 ^ x0, 8) vadd.i32 q0, q0, q1 - veor q4, q3, q0 - vshl.u32 q3, q4, #8 - vsri.u32 q3, q4, #24 + veor q3, q3, q0 + vtbl.8 d6, {d6}, d10 + vtbl.8 d7, {d7}, d10 // x2 += x3, x1 = rotl32(x1 ^ x2, 7) vadd.i32 q2, q2, q3 @@ -111,9 +129,31 @@ ENTRY(chacha20_block_xor_neon) // x3 = shuffle32(x3, MASK(0, 3, 2, 1)) vext.8 q3, q3, q3, #4 - subs r3, r3, #1 + subs r3, r3, #2 bne .Ldoubleround + bx lr +ENDPROC(chacha_permute) + +ENTRY(chacha_block_xor_neon) + // r0: Input state matrix, s + // r1: 1 data block output, o + // r2: 1 data block input, i + // r3: nrounds + push {lr} + + // x0..3 = s0..3 + add ip, r0, #0x20 + vld1.32 {q0-q1}, [r0] + vld1.32 {q2-q3}, [ip] + + vmov q8, q0 + vmov q9, q1 + vmov q10, q2 + vmov q11, q3 + + bl chacha_permute + add ip, r2, #0x20 vld1.8 {q4-q5}, [r2] vld1.8 {q6-q7}, [ip] @@ -138,44 +178,66 @@ ENTRY(chacha20_block_xor_neon) vst1.8 {q0-q1}, [r1] vst1.8 {q2-q3}, [ip] - bx lr -ENDPROC(chacha20_block_xor_neon) + pop {pc} +ENDPROC(chacha_block_xor_neon) + +ENTRY(hchacha_block_neon) + // r0: Input state matrix, s + // r1: output (8 32-bit words) + // r2: nrounds + push {lr} + + vld1.32 {q0-q1}, [r0]! + vld1.32 {q2-q3}, [r0] + + mov r3, r2 + bl chacha_permute + + vst1.32 {q0}, [r1]! + vst1.32 {q3}, [r1] + + pop {pc} +ENDPROC(hchacha_block_neon) + + .align 4 +.Lctrinc: .word 0, 1, 2, 3 +.Lrol8_table: .byte 3, 0, 1, 2, 7, 4, 5, 6 .align 5 -ENTRY(chacha20_4block_xor_neon) - push {r4-r6, lr} - mov ip, sp // preserve the stack pointer - sub r3, sp, #0x20 // allocate a 32 byte buffer - bic r3, r3, #0x1f // aligned to 32 bytes - mov sp, r3 +ENTRY(chacha_4block_xor_neon) + push {r4-r5} + mov r4, sp // preserve the stack pointer + sub ip, sp, #0x20 // allocate a 32 byte buffer + bic ip, ip, #0x1f // aligned to 32 bytes + mov sp, ip // r0: Input state matrix, s // r1: 4 data blocks output, o // r2: 4 data blocks input, i + // r3: nrounds // - // This function encrypts four consecutive ChaCha20 blocks by loading + // This function encrypts four consecutive ChaCha blocks by loading // the state matrix in NEON registers four times. The algorithm performs // each operation on the corresponding word of each state matrix, hence - // requires no word shuffling. For final XORing step we transpose the - // matrix by interleaving 32- and then 64-bit words, which allows us to - // do XOR in NEON registers. + // requires no word shuffling. The words are re-interleaved before the + // final addition of the original state and the XORing step. // - // x0..15[0-3] = s0..3[0..3] - add r3, r0, #0x20 + // x0..15[0-3] = s0..15[0-3] + add ip, r0, #0x20 vld1.32 {q0-q1}, [r0] - vld1.32 {q2-q3}, [r3] + vld1.32 {q2-q3}, [ip] - adr r3, CTRINC + adr r5, .Lctrinc vdup.32 q15, d7[1] vdup.32 q14, d7[0] - vld1.32 {q11}, [r3, :128] + vld1.32 {q4}, [r5, :128] vdup.32 q13, d6[1] vdup.32 q12, d6[0] - vadd.i32 q12, q12, q11 // x12 += counter values 0-3 vdup.32 q11, d5[1] vdup.32 q10, d5[0] + vadd.u32 q12, q12, q4 // x12 += counter values 0-3 vdup.32 q9, d4[1] vdup.32 q8, d4[0] vdup.32 q7, d3[1] @@ -187,9 +249,12 @@ ENTRY(chacha20_4block_xor_neon) vdup.32 q1, d0[1] vdup.32 q0, d0[0] - mov r3, #10 + adr ip, .Lrol8_table + b 1f .Ldoubleround4: + vld1.32 {q8-q9}, [sp, :256] +1: // x0 += x4, x12 = rotl32(x12 ^ x0, 16) // x1 += x5, x13 = rotl32(x13 ^ x1, 16) // x2 += x6, x14 = rotl32(x14 ^ x2, 16) @@ -238,24 +303,25 @@ ENTRY(chacha20_4block_xor_neon) // x1 += x5, x13 = rotl32(x13 ^ x1, 8) // x2 += x6, x14 = rotl32(x14 ^ x2, 8) // x3 += x7, x15 = rotl32(x15 ^ x3, 8) + vld1.8 {d16}, [ip, :64] vadd.i32 q0, q0, q4 vadd.i32 q1, q1, q5 vadd.i32 q2, q2, q6 vadd.i32 q3, q3, q7 - veor q8, q12, q0 - veor q9, q13, q1 - vshl.u32 q12, q8, #8 - vshl.u32 q13, q9, #8 - vsri.u32 q12, q8, #24 - vsri.u32 q13, q9, #24 + veor q12, q12, q0 + veor q13, q13, q1 + veor q14, q14, q2 + veor q15, q15, q3 - veor q8, q14, q2 - veor q9, q15, q3 - vshl.u32 q14, q8, #8 - vshl.u32 q15, q9, #8 - vsri.u32 q14, q8, #24 - vsri.u32 q15, q9, #24 + vtbl.8 d24, {d24}, d16 + vtbl.8 d25, {d25}, d16 + vtbl.8 d26, {d26}, d16 + vtbl.8 d27, {d27}, d16 + vtbl.8 d28, {d28}, d16 + vtbl.8 d29, {d29}, d16 + vtbl.8 d30, {d30}, d16 + vtbl.8 d31, {d31}, d16 vld1.32 {q8-q9}, [sp, :256] @@ -334,24 +400,25 @@ ENTRY(chacha20_4block_xor_neon) // x1 += x6, x12 = rotl32(x12 ^ x1, 8) // x2 += x7, x13 = rotl32(x13 ^ x2, 8) // x3 += x4, x14 = rotl32(x14 ^ x3, 8) + vld1.8 {d16}, [ip, :64] vadd.i32 q0, q0, q5 vadd.i32 q1, q1, q6 vadd.i32 q2, q2, q7 vadd.i32 q3, q3, q4 - veor q8, q15, q0 - veor q9, q12, q1 - vshl.u32 q15, q8, #8 - vshl.u32 q12, q9, #8 - vsri.u32 q15, q8, #24 - vsri.u32 q12, q9, #24 + veor q15, q15, q0 + veor q12, q12, q1 + veor q13, q13, q2 + veor q14, q14, q3 - veor q8, q13, q2 - veor q9, q14, q3 - vshl.u32 q13, q8, #8 - vshl.u32 q14, q9, #8 - vsri.u32 q13, q8, #24 - vsri.u32 q14, q9, #24 + vtbl.8 d30, {d30}, d16 + vtbl.8 d31, {d31}, d16 + vtbl.8 d24, {d24}, d16 + vtbl.8 d25, {d25}, d16 + vtbl.8 d26, {d26}, d16 + vtbl.8 d27, {d27}, d16 + vtbl.8 d28, {d28}, d16 + vtbl.8 d29, {d29}, d16 vld1.32 {q8-q9}, [sp, :256] @@ -380,105 +447,77 @@ ENTRY(chacha20_4block_xor_neon) vsri.u32 q5, q8, #25 vsri.u32 q6, q9, #25 - subs r3, r3, #1 - beq 0f + subs r3, r3, #2 + bne .Ldoubleround4 - vld1.32 {q8-q9}, [sp, :256] - b .Ldoubleround4 - - // x0[0-3] += s0[0] - // x1[0-3] += s0[1] - // x2[0-3] += s0[2] - // x3[0-3] += s0[3] -0: ldmia r0!, {r3-r6} - vdup.32 q8, r3 - vdup.32 q9, r4 - vadd.i32 q0, q0, q8 - vadd.i32 q1, q1, q9 - vdup.32 q8, r5 - vdup.32 q9, r6 - vadd.i32 q2, q2, q8 - vadd.i32 q3, q3, q9 - - // x4[0-3] += s1[0] - // x5[0-3] += s1[1] - // x6[0-3] += s1[2] - // x7[0-3] += s1[3] - ldmia r0!, {r3-r6} - vdup.32 q8, r3 - vdup.32 q9, r4 - vadd.i32 q4, q4, q8 - vadd.i32 q5, q5, q9 - vdup.32 q8, r5 - vdup.32 q9, r6 - vadd.i32 q6, q6, q8 - vadd.i32 q7, q7, q9 - - // interleave 32-bit words in state n, n+1 - vzip.32 q0, q1 - vzip.32 q2, q3 - vzip.32 q4, q5 - vzip.32 q6, q7 - - // interleave 64-bit words in state n, n+2 + // x0..7[0-3] are in q0-q7, x10..15[0-3] are in q10-q15. + // x8..9[0-3] are on the stack. + + // Re-interleave the words in the first two rows of each block (x0..7). + // Also add the counter values 0-3 to x12[0-3]. + vld1.32 {q8}, [r5, :128] // load counter values 0-3 + vzip.32 q0, q1 // => (0 1 0 1) (0 1 0 1) + vzip.32 q2, q3 // => (2 3 2 3) (2 3 2 3) + vzip.32 q4, q5 // => (4 5 4 5) (4 5 4 5) + vzip.32 q6, q7 // => (6 7 6 7) (6 7 6 7) + vadd.u32 q12, q8 // x12 += counter values 0-3 vswp d1, d4 vswp d3, d6 + vld1.32 {q8-q9}, [r0]! // load s0..7 vswp d9, d12 vswp d11, d14 - // xor with corresponding input, write to output + // Swap q1 and q4 so that we'll free up consecutive registers (q0-q1) + // after XORing the first 32 bytes. + vswp q1, q4 + + // First two rows of each block are (q0 q1) (q2 q6) (q4 q5) (q3 q7) + + // x0..3[0-3] += s0..3[0-3] (add orig state to 1st row of each block) + vadd.u32 q0, q0, q8 + vadd.u32 q2, q2, q8 + vadd.u32 q4, q4, q8 + vadd.u32 q3, q3, q8 + + // x4..7[0-3] += s4..7[0-3] (add orig state to 2nd row of each block) + vadd.u32 q1, q1, q9 + vadd.u32 q6, q6, q9 + vadd.u32 q5, q5, q9 + vadd.u32 q7, q7, q9 + + // XOR first 32 bytes using keystream from first two rows of first block vld1.8 {q8-q9}, [r2]! veor q8, q8, q0 - veor q9, q9, q4 + veor q9, q9, q1 vst1.8 {q8-q9}, [r1]! + // Re-interleave the words in the last two rows of each block (x8..15). vld1.32 {q8-q9}, [sp, :256] - - // x8[0-3] += s2[0] - // x9[0-3] += s2[1] - // x10[0-3] += s2[2] - // x11[0-3] += s2[3] - ldmia r0!, {r3-r6} - vdup.32 q0, r3 - vdup.32 q4, r4 - vadd.i32 q8, q8, q0 - vadd.i32 q9, q9, q4 - vdup.32 q0, r5 - vdup.32 q4, r6 - vadd.i32 q10, q10, q0 - vadd.i32 q11, q11, q4 - - // x12[0-3] += s3[0] - // x13[0-3] += s3[1] - // x14[0-3] += s3[2] - // x15[0-3] += s3[3] - ldmia r0!, {r3-r6} - vdup.32 q0, r3 - vdup.32 q4, r4 - adr r3, CTRINC - vadd.i32 q12, q12, q0 - vld1.32 {q0}, [r3, :128] - vadd.i32 q13, q13, q4 - vadd.i32 q12, q12, q0 // x12 += counter values 0-3 - - vdup.32 q0, r5 - vdup.32 q4, r6 - vadd.i32 q14, q14, q0 - vadd.i32 q15, q15, q4 - - // interleave 32-bit words in state n, n+1 - vzip.32 q8, q9 - vzip.32 q10, q11 - vzip.32 q12, q13 - vzip.32 q14, q15 - - // interleave 64-bit words in state n, n+2 - vswp d17, d20 - vswp d19, d22 + vzip.32 q12, q13 // => (12 13 12 13) (12 13 12 13) + vzip.32 q14, q15 // => (14 15 14 15) (14 15 14 15) + vzip.32 q8, q9 // => (8 9 8 9) (8 9 8 9) + vzip.32 q10, q11 // => (10 11 10 11) (10 11 10 11) + vld1.32 {q0-q1}, [r0] // load s8..15 vswp d25, d28 vswp d27, d30 + vswp d17, d20 + vswp d19, d22 + + // Last two rows of each block are (q8 q12) (q10 q14) (q9 q13) (q11 q15) + + // x8..11[0-3] += s8..11[0-3] (add orig state to 3rd row of each block) + vadd.u32 q8, q8, q0 + vadd.u32 q10, q10, q0 + vadd.u32 q9, q9, q0 + vadd.u32 q11, q11, q0 - vmov q4, q1 + // x12..15[0-3] += s12..15[0-3] (add orig state to 4th row of each block) + vadd.u32 q12, q12, q1 + vadd.u32 q14, q14, q1 + vadd.u32 q13, q13, q1 + vadd.u32 q15, q15, q1 + + // XOR the rest of the data with the keystream vld1.8 {q0-q1}, [r2]! veor q0, q0, q8 @@ -511,13 +550,11 @@ ENTRY(chacha20_4block_xor_neon) vst1.8 {q0-q1}, [r1]! vld1.8 {q0-q1}, [r2] + mov sp, r4 // restore original stack pointer veor q0, q0, q11 veor q1, q1, q15 vst1.8 {q0-q1}, [r1] - mov sp, ip - pop {r4-r6, pc} -ENDPROC(chacha20_4block_xor_neon) - - .align 4 -CTRINC: .word 0, 1, 2, 3 + pop {r4-r5} + bx lr +ENDPROC(chacha_4block_xor_neon) diff --git a/arch/arm/crypto/chacha-neon-glue.c b/arch/arm/crypto/chacha-neon-glue.c new file mode 100644 index 000000000000..9d6fda81986d --- /dev/null +++ b/arch/arm/crypto/chacha-neon-glue.c @@ -0,0 +1,201 @@ +/* + * ARM NEON accelerated ChaCha and XChaCha stream ciphers, + * including ChaCha20 (RFC7539) + * + * Copyright (C) 2016 Linaro, Ltd. <ard.biesheuvel@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Based on: + * ChaCha20 256-bit cipher algorithm, RFC7539, SIMD glue code + * + * Copyright (C) 2015 Martin Willi + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <crypto/algapi.h> +#include <crypto/chacha.h> +#include <crypto/internal/skcipher.h> +#include <linux/kernel.h> +#include <linux/module.h> + +#include <asm/hwcap.h> +#include <asm/neon.h> +#include <asm/simd.h> + +asmlinkage void chacha_block_xor_neon(const u32 *state, u8 *dst, const u8 *src, + int nrounds); +asmlinkage void chacha_4block_xor_neon(const u32 *state, u8 *dst, const u8 *src, + int nrounds); +asmlinkage void hchacha_block_neon(const u32 *state, u32 *out, int nrounds); + +static void chacha_doneon(u32 *state, u8 *dst, const u8 *src, + unsigned int bytes, int nrounds) +{ + u8 buf[CHACHA_BLOCK_SIZE]; + + while (bytes >= CHACHA_BLOCK_SIZE * 4) { + chacha_4block_xor_neon(state, dst, src, nrounds); + bytes -= CHACHA_BLOCK_SIZE * 4; + src += CHACHA_BLOCK_SIZE * 4; + dst += CHACHA_BLOCK_SIZE * 4; + state[12] += 4; + } + while (bytes >= CHACHA_BLOCK_SIZE) { + chacha_block_xor_neon(state, dst, src, nrounds); + bytes -= CHACHA_BLOCK_SIZE; + src += CHACHA_BLOCK_SIZE; + dst += CHACHA_BLOCK_SIZE; + state[12]++; + } + if (bytes) { + memcpy(buf, src, bytes); + chacha_block_xor_neon(state, buf, buf, nrounds); + memcpy(dst, buf, bytes); + } +} + +static int chacha_neon_stream_xor(struct skcipher_request *req, + struct chacha_ctx *ctx, u8 *iv) +{ + struct skcipher_walk walk; + u32 state[16]; + int err; + + err = skcipher_walk_virt(&walk, req, false); + + crypto_chacha_init(state, ctx, iv); + + while (walk.nbytes > 0) { + unsigned int nbytes = walk.nbytes; + + if (nbytes < walk.total) + nbytes = round_down(nbytes, walk.stride); + + kernel_neon_begin(); + chacha_doneon(state, walk.dst.virt.addr, walk.src.virt.addr, + nbytes, ctx->nrounds); + kernel_neon_end(); + err = skcipher_walk_done(&walk, walk.nbytes - nbytes); + } + + return err; +} + +static int chacha_neon(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); + + if (req->cryptlen <= CHACHA_BLOCK_SIZE || !may_use_simd()) + return crypto_chacha_crypt(req); + + return chacha_neon_stream_xor(req, ctx, req->iv); +} + +static int xchacha_neon(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); + struct chacha_ctx subctx; + u32 state[16]; + u8 real_iv[16]; + + if (req->cryptlen <= CHACHA_BLOCK_SIZE || !may_use_simd()) + return crypto_xchacha_crypt(req); + + crypto_chacha_init(state, ctx, req->iv); + + kernel_neon_begin(); + hchacha_block_neon(state, subctx.key, ctx->nrounds); + kernel_neon_end(); + subctx.nrounds = ctx->nrounds; + + memcpy(&real_iv[0], req->iv + 24, 8); + memcpy(&real_iv[8], req->iv + 16, 8); + return chacha_neon_stream_xor(req, &subctx, real_iv); +} + +static struct skcipher_alg algs[] = { + { + .base.cra_name = "chacha20", + .base.cra_driver_name = "chacha20-neon", + .base.cra_priority = 300, + .base.cra_blocksize = 1, + .base.cra_ctxsize = sizeof(struct chacha_ctx), + .base.cra_module = THIS_MODULE, + + .min_keysize = CHACHA_KEY_SIZE, + .max_keysize = CHACHA_KEY_SIZE, + .ivsize = CHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, + .walksize = 4 * CHACHA_BLOCK_SIZE, + .setkey = crypto_chacha20_setkey, + .encrypt = chacha_neon, + .decrypt = chacha_neon, + }, { + .base.cra_name = "xchacha20", + .base.cra_driver_name = "xchacha20-neon", + .base.cra_priority = 300, + .base.cra_blocksize = 1, + .base.cra_ctxsize = sizeof(struct chacha_ctx), + .base.cra_module = THIS_MODULE, + + .min_keysize = CHACHA_KEY_SIZE, + .max_keysize = CHACHA_KEY_SIZE, + .ivsize = XCHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, + .walksize = 4 * CHACHA_BLOCK_SIZE, + .setkey = crypto_chacha20_setkey, + .encrypt = xchacha_neon, + .decrypt = xchacha_neon, + }, { + .base.cra_name = "xchacha12", + .base.cra_driver_name = "xchacha12-neon", + .base.cra_priority = 300, + .base.cra_blocksize = 1, + .base.cra_ctxsize = sizeof(struct chacha_ctx), + .base.cra_module = THIS_MODULE, + + .min_keysize = CHACHA_KEY_SIZE, + .max_keysize = CHACHA_KEY_SIZE, + .ivsize = XCHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, + .walksize = 4 * CHACHA_BLOCK_SIZE, + .setkey = crypto_chacha12_setkey, + .encrypt = xchacha_neon, + .decrypt = xchacha_neon, + } +}; + +static int __init chacha_simd_mod_init(void) +{ + if (!(elf_hwcap & HWCAP_NEON)) + return -ENODEV; + + return crypto_register_skciphers(algs, ARRAY_SIZE(algs)); +} + +static void __exit chacha_simd_mod_fini(void) +{ + crypto_unregister_skciphers(algs, ARRAY_SIZE(algs)); +} + +module_init(chacha_simd_mod_init); +module_exit(chacha_simd_mod_fini); + +MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (NEON accelerated)"); +MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>"); +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_CRYPTO("chacha20"); +MODULE_ALIAS_CRYPTO("chacha20-neon"); +MODULE_ALIAS_CRYPTO("xchacha20"); +MODULE_ALIAS_CRYPTO("xchacha20-neon"); +MODULE_ALIAS_CRYPTO("xchacha12"); +MODULE_ALIAS_CRYPTO("xchacha12-neon"); diff --git a/arch/arm/crypto/chacha20-neon-glue.c b/arch/arm/crypto/chacha20-neon-glue.c deleted file mode 100644 index 59a7be08e80c..000000000000 --- a/arch/arm/crypto/chacha20-neon-glue.c +++ /dev/null @@ -1,127 +0,0 @@ -/* - * ChaCha20 256-bit cipher algorithm, RFC7539, ARM NEON functions - * - * Copyright (C) 2016 Linaro, Ltd. <ard.biesheuvel@linaro.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * Based on: - * ChaCha20 256-bit cipher algorithm, RFC7539, SIMD glue code - * - * Copyright (C) 2015 Martin Willi - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ - -#include <crypto/algapi.h> -#include <crypto/chacha20.h> -#include <crypto/internal/skcipher.h> -#include <linux/kernel.h> -#include <linux/module.h> - -#include <asm/hwcap.h> -#include <asm/neon.h> -#include <asm/simd.h> - -asmlinkage void chacha20_block_xor_neon(u32 *state, u8 *dst, const u8 *src); -asmlinkage void chacha20_4block_xor_neon(u32 *state, u8 *dst, const u8 *src); - -static void chacha20_doneon(u32 *state, u8 *dst, const u8 *src, - unsigned int bytes) -{ - u8 buf[CHACHA20_BLOCK_SIZE]; - - while (bytes >= CHACHA20_BLOCK_SIZE * 4) { - chacha20_4block_xor_neon(state, dst, src); - bytes -= CHACHA20_BLOCK_SIZE * 4; - src += CHACHA20_BLOCK_SIZE * 4; - dst += CHACHA20_BLOCK_SIZE * 4; - state[12] += 4; - } - while (bytes >= CHACHA20_BLOCK_SIZE) { - chacha20_block_xor_neon(state, dst, src); - bytes -= CHACHA20_BLOCK_SIZE; - src += CHACHA20_BLOCK_SIZE; - dst += CHACHA20_BLOCK_SIZE; - state[12]++; - } - if (bytes) { - memcpy(buf, src, bytes); - chacha20_block_xor_neon(state, buf, buf); - memcpy(dst, buf, bytes); - } -} - -static int chacha20_neon(struct skcipher_request *req) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct chacha20_ctx *ctx = crypto_skcipher_ctx(tfm); - struct skcipher_walk walk; - u32 state[16]; - int err; - - if (req->cryptlen <= CHACHA20_BLOCK_SIZE || !may_use_simd()) - return crypto_chacha20_crypt(req); - - err = skcipher_walk_virt(&walk, req, true); - - crypto_chacha20_init(state, ctx, walk.iv); - - kernel_neon_begin(); - while (walk.nbytes > 0) { - unsigned int nbytes = walk.nbytes; - - if (nbytes < walk.total) - nbytes = round_down(nbytes, walk.stride); - - chacha20_doneon(state, walk.dst.virt.addr, walk.src.virt.addr, - nbytes); - err = skcipher_walk_done(&walk, walk.nbytes - nbytes); - } - kernel_neon_end(); - - return err; -} - -static struct skcipher_alg alg = { - .base.cra_name = "chacha20", - .base.cra_driver_name = "chacha20-neon", - .base.cra_priority = 300, - .base.cra_blocksize = 1, - .base.cra_ctxsize = sizeof(struct chacha20_ctx), - .base.cra_module = THIS_MODULE, - - .min_keysize = CHACHA20_KEY_SIZE, - .max_keysize = CHACHA20_KEY_SIZE, - .ivsize = CHACHA20_IV_SIZE, - .chunksize = CHACHA20_BLOCK_SIZE, - .walksize = 4 * CHACHA20_BLOCK_SIZE, - .setkey = crypto_chacha20_setkey, - .encrypt = chacha20_neon, - .decrypt = chacha20_neon, -}; - -static int __init chacha20_simd_mod_init(void) -{ - if (!(elf_hwcap & HWCAP_NEON)) - return -ENODEV; - - return crypto_register_skcipher(&alg); -} - -static void __exit chacha20_simd_mod_fini(void) -{ - crypto_unregister_skcipher(&alg); -} - -module_init(chacha20_simd_mod_init); -module_exit(chacha20_simd_mod_fini); - -MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>"); -MODULE_LICENSE("GPL v2"); -MODULE_ALIAS_CRYPTO("chacha20"); diff --git a/arch/arm/crypto/nh-neon-core.S b/arch/arm/crypto/nh-neon-core.S new file mode 100644 index 000000000000..434d80ab531c --- /dev/null +++ b/arch/arm/crypto/nh-neon-core.S @@ -0,0 +1,116 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * NH - ε-almost-universal hash function, NEON accelerated version + * + * Copyright 2018 Google LLC + * + * Author: Eric Biggers <ebiggers@google.com> + */ + +#include <linux/linkage.h> + + .text + .fpu neon + + KEY .req r0 + MESSAGE .req r1 + MESSAGE_LEN .req r2 + HASH .req r3 + + PASS0_SUMS .req q0 + PASS0_SUM_A .req d0 + PASS0_SUM_B .req d1 + PASS1_SUMS .req q1 + PASS1_SUM_A .req d2 + PASS1_SUM_B .req d3 + PASS2_SUMS .req q2 + PASS2_SUM_A .req d4 + PASS2_SUM_B .req d5 + PASS3_SUMS .req q3 + PASS3_SUM_A .req d6 + PASS3_SUM_B .req d7 + K0 .req q4 + K1 .req q5 + K2 .req q6 + K3 .req q7 + T0 .req q8 + T0_L .req d16 + T0_H .req d17 + T1 .req q9 + T1_L .req d18 + T1_H .req d19 + T2 .req q10 + T2_L .req d20 + T2_H .req d21 + T3 .req q11 + T3_L .req d22 + T3_H .req d23 + +.macro _nh_stride k0, k1, k2, k3 + + // Load next message stride + vld1.8 {T3}, [MESSAGE]! + + // Load next key stride + vld1.32 {\k3}, [KEY]! + + // Add message words to key words + vadd.u32 T0, T3, \k0 + vadd.u32 T1, T3, \k1 + vadd.u32 T2, T3, \k2 + vadd.u32 T3, T3, \k3 + + // Multiply 32x32 => 64 and accumulate + vmlal.u32 PASS0_SUMS, T0_L, T0_H + vmlal.u32 PASS1_SUMS, T1_L, T1_H + vmlal.u32 PASS2_SUMS, T2_L, T2_H + vmlal.u32 PASS3_SUMS, T3_L, T3_H +.endm + +/* + * void nh_neon(const u32 *key, const u8 *message, size_t message_len, + * u8 hash[NH_HASH_BYTES]) + * + * It's guaranteed that message_len % 16 == 0. + */ +ENTRY(nh_neon) + + vld1.32 {K0,K1}, [KEY]! + vmov.u64 PASS0_SUMS, #0 + vmov.u64 PASS1_SUMS, #0 + vld1.32 {K2}, [KEY]! + vmov.u64 PASS2_SUMS, #0 + vmov.u64 PASS3_SUMS, #0 + + subs MESSAGE_LEN, MESSAGE_LEN, #64 + blt .Lloop4_done +.Lloop4: + _nh_stride K0, K1, K2, K3 + _nh_stride K1, K2, K3, K0 + _nh_stride K2, K3, K0, K1 + _nh_stride K3, K0, K1, K2 + subs MESSAGE_LEN, MESSAGE_LEN, #64 + bge .Lloop4 + +.Lloop4_done: + ands MESSAGE_LEN, MESSAGE_LEN, #63 + beq .Ldone + _nh_stride K0, K1, K2, K3 + + subs MESSAGE_LEN, MESSAGE_LEN, #16 + beq .Ldone + _nh_stride K1, K2, K3, K0 + + subs MESSAGE_LEN, MESSAGE_LEN, #16 + beq .Ldone + _nh_stride K2, K3, K0, K1 + +.Ldone: + // Sum the accumulators for each pass, then store the sums to 'hash' + vadd.u64 T0_L, PASS0_SUM_A, PASS0_SUM_B + vadd.u64 T0_H, PASS1_SUM_A, PASS1_SUM_B + vadd.u64 T1_L, PASS2_SUM_A, PASS2_SUM_B + vadd.u64 T1_H, PASS3_SUM_A, PASS3_SUM_B + vst1.8 {T0-T1}, [HASH] + bx lr +ENDPROC(nh_neon) diff --git a/arch/arm/crypto/nhpoly1305-neon-glue.c b/arch/arm/crypto/nhpoly1305-neon-glue.c new file mode 100644 index 000000000000..49aae87cb2bc --- /dev/null +++ b/arch/arm/crypto/nhpoly1305-neon-glue.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * NHPoly1305 - ε-almost-∆-universal hash function for Adiantum + * (NEON accelerated version) + * + * Copyright 2018 Google LLC + */ + +#include <asm/neon.h> +#include <asm/simd.h> +#include <crypto/internal/hash.h> +#include <crypto/nhpoly1305.h> +#include <linux/module.h> + +asmlinkage void nh_neon(const u32 *key, const u8 *message, size_t message_len, + u8 hash[NH_HASH_BYTES]); + +/* wrapper to avoid indirect call to assembly, which doesn't work with CFI */ +static void _nh_neon(const u32 *key, const u8 *message, size_t message_len, + __le64 hash[NH_NUM_PASSES]) +{ + nh_neon(key, message, message_len, (u8 *)hash); +} + +static int nhpoly1305_neon_update(struct shash_desc *desc, + const u8 *src, unsigned int srclen) +{ + if (srclen < 64 || !may_use_simd()) + return crypto_nhpoly1305_update(desc, src, srclen); + + do { + unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE); + + kernel_neon_begin(); + crypto_nhpoly1305_update_helper(desc, src, n, _nh_neon); + kernel_neon_end(); + src += n; + srclen -= n; + } while (srclen); + return 0; +} + +static struct shash_alg nhpoly1305_alg = { + .base.cra_name = "nhpoly1305", + .base.cra_driver_name = "nhpoly1305-neon", + .base.cra_priority = 200, + .base.cra_ctxsize = sizeof(struct nhpoly1305_key), + .base.cra_module = THIS_MODULE, + .digestsize = POLY1305_DIGEST_SIZE, + .init = crypto_nhpoly1305_init, + .update = nhpoly1305_neon_update, + .final = crypto_nhpoly1305_final, + .setkey = crypto_nhpoly1305_setkey, + .descsize = sizeof(struct nhpoly1305_state), +}; + +static int __init nhpoly1305_mod_init(void) +{ + if (!(elf_hwcap & HWCAP_NEON)) + return -ENODEV; + + return crypto_register_shash(&nhpoly1305_alg); +} + +static void __exit nhpoly1305_mod_exit(void) +{ + crypto_unregister_shash(&nhpoly1305_alg); +} + +module_init(nhpoly1305_mod_init); +module_exit(nhpoly1305_mod_exit); + +MODULE_DESCRIPTION("NHPoly1305 ε-almost-∆-universal hash function (NEON-accelerated)"); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>"); +MODULE_ALIAS_CRYPTO("nhpoly1305"); +MODULE_ALIAS_CRYPTO("nhpoly1305-neon"); diff --git a/arch/arm/include/asm/fiq_glue.h b/arch/arm/include/asm/fiq_glue.h new file mode 100644 index 000000000000..a9e244f9f197 --- /dev/null +++ b/arch/arm/include/asm/fiq_glue.h @@ -0,0 +1,33 @@ +/* + * Copyright (C) 2010 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __ASM_FIQ_GLUE_H +#define __ASM_FIQ_GLUE_H + +struct fiq_glue_handler { + void (*fiq)(struct fiq_glue_handler *h, void *regs, void *svc_sp); + void (*resume)(struct fiq_glue_handler *h); +}; +typedef void (*fiq_return_handler_t)(void); + +int fiq_glue_register_handler(struct fiq_glue_handler *handler); +int fiq_glue_set_return_handler(fiq_return_handler_t fiq_return); +int fiq_glue_clear_return_handler(fiq_return_handler_t fiq_return); + +#ifdef CONFIG_FIQ_GLUE +void fiq_glue_resume(void); +#else +static inline void fiq_glue_resume(void) {} +#endif + +#endif diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h index f59ab9bcbaf9..201dc2011c16 100644 --- a/arch/arm/include/asm/topology.h +++ b/arch/arm/include/asm/topology.h @@ -25,6 +25,20 @@ void init_cpu_topology(void); void store_cpu_topology(unsigned int cpuid); const struct cpumask *cpu_coregroup_mask(int cpu); +#include <linux/arch_topology.h> + +/* Replace task scheduler's default frequency-invariant accounting */ +#define arch_scale_freq_capacity topology_get_freq_scale + +/* Replace task scheduler's default max-frequency-invariant accounting */ +#define arch_scale_max_freq_capacity topology_get_max_freq_scale + +/* Replace task scheduler's default cpu-invariant accounting */ +#define arch_scale_cpu_capacity topology_get_cpu_scale + +/* Enable topology flag updates */ +#define arch_update_cpu_topology topology_update_cpu_topology + #else static inline void init_cpu_topology(void) { } diff --git a/arch/arm/kernel/kgdb.c b/arch/arm/kernel/kgdb.c index caa0dbe3dc61..923a725ab9b5 100644 --- a/arch/arm/kernel/kgdb.c +++ b/arch/arm/kernel/kgdb.c @@ -141,6 +141,8 @@ int kgdb_arch_handle_exception(int exception_vector, int signo, static int kgdb_brk_fn(struct pt_regs *regs, unsigned int instr) { + if (user_mode(regs)) + return -1; kgdb_handle_exception(1, SIGTRAP, 0, regs); return 0; @@ -148,6 +150,8 @@ static int kgdb_brk_fn(struct pt_regs *regs, unsigned int instr) static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int instr) { + if (user_mode(regs)) + return -1; compiled_break = 1; kgdb_handle_exception(1, SIGTRAP, 0, regs); diff --git a/arch/arm/kernel/reboot.c b/arch/arm/kernel/reboot.c index 3b2aa9a9fe26..c74249136f18 100644 --- a/arch/arm/kernel/reboot.c +++ b/arch/arm/kernel/reboot.c @@ -6,6 +6,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ +#include <linux/console.h> #include <linux/cpu.h> #include <linux/delay.h> #include <linux/reboot.h> @@ -125,6 +126,31 @@ void machine_power_off(void) pm_power_off(); } +#ifdef CONFIG_ARM_FLUSH_CONSOLE_ON_RESTART +void arm_machine_flush_console(void) +{ + printk("\n"); + pr_emerg("Restarting %s\n", linux_banner); + if (console_trylock()) { + console_unlock(); + return; + } + + mdelay(50); + + local_irq_disable(); + if (!console_trylock()) + pr_emerg("arm_restart: Console was locked! Busting\n"); + else + pr_emerg("arm_restart: Console was locked!\n"); + console_unlock(); +} +#else +void arm_machine_flush_console(void) +{ +} +#endif + /* * Restart requires that the secondary CPUs stop performing any activity * while the primary CPU resets the system. Systems with a single CPU can @@ -141,6 +167,10 @@ void machine_restart(char *cmd) local_irq_disable(); smp_send_stop(); + /* Flush the console to make sure all the relevant messages make it + * out to the console drivers */ + arm_machine_flush_console(); + if (arm_pm_restart) arm_pm_restart(reboot_mode, cmd); else diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c index 24ac3cab411d..28ca1646a38a 100644 --- a/arch/arm/kernel/topology.c +++ b/arch/arm/kernel/topology.c @@ -23,6 +23,7 @@ #include <linux/of.h> #include <linux/sched.h> #include <linux/sched/topology.h> +#include <linux/sched/energy.h> #include <linux/slab.h> #include <linux/string.h> @@ -30,6 +31,18 @@ #include <asm/cputype.h> #include <asm/topology.h> +static inline +const struct sched_group_energy * const cpu_core_energy(int cpu) +{ + return sge_array[cpu][SD_LEVEL0]; +} + +static inline +const struct sched_group_energy * const cpu_cluster_energy(int cpu) +{ + return sge_array[cpu][SD_LEVEL1]; +} + /* * cpu capacity scale management */ @@ -278,23 +291,37 @@ void store_cpu_topology(unsigned int cpuid) update_cpu_capacity(cpuid); + topology_detect_flags(); + pr_info("CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n", cpuid, cpu_topology[cpuid].thread_id, cpu_topology[cpuid].core_id, cpu_topology[cpuid].socket_id, mpidr); } +#ifdef CONFIG_SCHED_MC +static int core_flags(void) +{ + return cpu_core_flags() | topology_core_flags(); +} + static inline int cpu_corepower_flags(void) { - return SD_SHARE_PKG_RESOURCES | SD_SHARE_POWERDOMAIN; + return topology_core_flags() + | SD_SHARE_PKG_RESOURCES | SD_SHARE_POWERDOMAIN; +} +#endif + +static int cpu_flags(void) +{ + return topology_cpu_flags(); } static struct sched_domain_topology_level arm_topology[] = { #ifdef CONFIG_SCHED_MC - { cpu_corepower_mask, cpu_corepower_flags, SD_INIT_NAME(GMC) }, - { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, + { cpu_coregroup_mask, core_flags, cpu_core_energy, SD_INIT_NAME(MC) }, #endif - { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { cpu_cpu_mask, cpu_flags, cpu_cluster_energy, SD_INIT_NAME(DIE) }, { NULL, }, }; diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S index 24659952c278..11da0f50a1fe 100644 --- a/arch/arm/mm/cache-v6.S +++ b/arch/arm/mm/cache-v6.S @@ -270,6 +270,11 @@ v6_dma_clean_range: * - end - virtual end address of region */ ENTRY(v6_dma_flush_range) +#ifdef CONFIG_CACHE_FLUSH_RANGE_LIMIT + sub r2, r1, r0 + cmp r2, #CONFIG_CACHE_FLUSH_RANGE_LIMIT + bhi v6_dma_flush_dcache_all +#endif #ifdef CONFIG_DMA_CACHE_RWFO ldrb r2, [r0] @ read for ownership strb r2, [r0] @ write for ownership @@ -292,6 +297,18 @@ ENTRY(v6_dma_flush_range) mcr p15, 0, r0, c7, c10, 4 @ drain write buffer ret lr +#ifdef CONFIG_CACHE_FLUSH_RANGE_LIMIT +v6_dma_flush_dcache_all: + mov r0, #0 +#ifdef HARVARD_CACHE + mcr p15, 0, r0, c7, c14, 0 @ D cache clean+invalidate +#else + mcr p15, 0, r0, c7, c15, 0 @ Cache clean+invalidate +#endif + mcr p15, 0, r0, c7, c10, 4 @ drain write buffer + mov pc, lr +#endif + /* * dma_map_area(start, size, dir) * - start - kernel virtual start address diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 9bb446cc135d..54f8e6f83788 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -277,10 +277,10 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) local_irq_enable(); /* - * If we're in an interrupt or have no user + * If we're in an interrupt, or have no irqs, or have no user * context, we must not take the fault.. */ - if (faulthandler_disabled() || !mm) + if (faulthandler_disabled() || irqs_disabled() || !mm) goto no_context; if (user_mode(regs)) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index e296ae3e20f4..a1ed5985232c 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -24,6 +24,7 @@ config ARM64 select ARCH_HAVE_NMI_SAFE_CMPXCHG if ACPI_APEI_SEA select ARCH_USE_CMPXCHG_LOCKREF select ARCH_SUPPORTS_MEMORY_FAILURE + select ARCH_SUPPORTS_LTO_CLANG select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_NUMA_BALANCING select ARCH_WANT_COMPAT_IPC_PARSE_VERSION @@ -434,7 +435,7 @@ config ARM64_ERRATUM_845719 config ARM64_ERRATUM_843419 bool "Cortex-A53: 843419: A load or store might access an incorrect address" - default y + default y if !LTO_CLANG select ARM64_MODULE_CMODEL_LARGE if MODULES help This option links the kernel with '--fix-cortex-a53-843419' and @@ -1070,7 +1071,7 @@ config RANDOMIZE_BASE config RANDOMIZE_MODULE_REGION_FULL bool "Randomize the module region independently from the core kernel" - depends on RANDOMIZE_BASE + depends on RANDOMIZE_BASE && !LTO_CLANG default y help Randomizes the location of the module region without considering the @@ -1104,6 +1105,23 @@ config CMDLINE entering them here. As a minimum, you should specify the the root device (e.g. root=/dev/nfs). +choice + prompt "Kernel command line type" if CMDLINE != "" + default CMDLINE_FROM_BOOTLOADER + +config CMDLINE_FROM_BOOTLOADER + bool "Use bootloader kernel arguments if available" + help + Uses the command-line options passed by the boot loader. If + the boot loader doesn't provide any, the default kernel command + string provided in CMDLINE will be used. + +config CMDLINE_EXTEND + bool "Extend bootloader kernel arguments" + help + The command-line arguments provided by the boot loader will be + appended to the default kernel command string. + config CMDLINE_FORCE bool "Always use the default kernel command string" help @@ -1111,6 +1129,7 @@ config CMDLINE_FORCE loader passes other arguments to the kernel. This is useful if you cannot or don't want to change the command-line options your boot loader passes to the kernel. +endchoice config EFI_STUB bool @@ -1143,6 +1162,41 @@ config DMI However, even with this option, the resultant kernel should continue to boot on existing non-UEFI platforms. +config BUILD_ARM64_APPENDED_DTB_IMAGE + bool "Build a concatenated Image.gz/dtb by default" + depends on OF + help + Enabling this option will cause a concatenated Image.gz and list of + DTBs to be built by default (instead of a standalone Image.gz.) + The image will built in arch/arm64/boot/Image.gz-dtb + +choice + prompt "Appended DTB Kernel Image name" + depends on BUILD_ARM64_APPENDED_DTB_IMAGE + help + Enabling this option will cause a specific kernel image Image or + Image.gz to be used for final image creation. + The image will built in arch/arm64/boot/IMAGE-NAME-dtb + + config IMG_GZ_DTB + bool "Image.gz-dtb" + config IMG_DTB + bool "Image-dtb" +endchoice + +config BUILD_ARM64_APPENDED_KERNEL_IMAGE_NAME + string + depends on BUILD_ARM64_APPENDED_DTB_IMAGE + default "Image.gz-dtb" if IMG_GZ_DTB + default "Image-dtb" if IMG_DTB + +config BUILD_ARM64_APPENDED_DTB_IMAGE_NAMES + string "Default dtb names" + depends on BUILD_ARM64_APPENDED_DTB_IMAGE + help + Space separated list of names of dtbs to append when + building a concatenated Image.gz-dtb. + endmenu menu "Userspace binary formats" diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 8c4bc5a2c61f..da33748bc418 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -26,8 +26,17 @@ ifeq ($(CONFIG_ARM64_ERRATUM_843419),y) ifeq ($(call ld-option, --fix-cortex-a53-843419),) $(warning ld does not support --fix-cortex-a53-843419; kernel may be susceptible to erratum) else + ifeq ($(call gold-ifversion, -lt, 114000000, y), y) +$(warning This version of GNU gold may generate incorrect code with --fix-cortex-a53-843419;\ + see https://sourceware.org/bugzilla/show_bug.cgi?id=21491) + endif LDFLAGS_vmlinux += --fix-cortex-a53-843419 endif +else + ifeq ($(ld-name),gold) +# Pass --no-fix-cortex-a53-843419 to ensure the erratum fix is disabled +LDFLAGS += --no-fix-cortex-a53-843419 + endif endif KBUILD_DEFCONFIG := defconfig @@ -49,9 +58,17 @@ $(warning Detected assembler with broken .inst; disassembly will be unreliable) endif endif -KBUILD_CFLAGS += -mgeneral-regs-only $(lseinstr) $(brokengasinst) +ifeq ($(cc-name),clang) +# This is a workaround for https://bugs.llvm.org/show_bug.cgi?id=30792. +# TODO: revert when this is fixed in LLVM. +KBUILD_CFLAGS += -mno-implicit-float +else +KBUILD_CFLAGS += -mgeneral-regs-only +endif +KBUILD_CFLAGS += $(lseinstr) $(brokengasinst) KBUILD_CFLAGS += -fno-asynchronous-unwind-tables KBUILD_CFLAGS += $(call cc-option, -mpc-relative-literal-loads) +KBUILD_CFLAGS += -fno-pic KBUILD_AFLAGS += $(lseinstr) $(brokengasinst) KBUILD_CFLAGS += $(call cc-option,-mabi=lp64) @@ -62,14 +79,22 @@ KBUILD_CPPFLAGS += -mbig-endian CHECKFLAGS += -D__AARCH64EB__ AS += -EB LD += -EB +ifeq ($(ld-name),gold) +LDFLAGS += -maarch64_elf64_be_vec +else LDFLAGS += -maarch64linuxb +endif UTS_MACHINE := aarch64_be else KBUILD_CPPFLAGS += -mlittle-endian CHECKFLAGS += -D__AARCH64EL__ AS += -EL LD += -EL +ifeq ($(ld-name),gold) +LDFLAGS += -maarch64_elf64_le_vec +else LDFLAGS += -maarch64linux +endif UTS_MACHINE := aarch64 endif @@ -77,6 +102,10 @@ CHECKFLAGS += -D__aarch64__ -m64 ifeq ($(CONFIG_ARM64_MODULE_CMODEL_LARGE), y) KBUILD_CFLAGS_MODULE += -mcmodel=large +ifeq ($(CONFIG_LTO_CLANG), y) +# Code model is not stored in LLVM IR, so we need to pass it also to LLVMgold +KBUILD_LDFLAGS_MODULE += -plugin-opt=-code-model=large +endif endif ifeq ($(CONFIG_ARM64_MODULE_PLTS),y) @@ -95,6 +124,10 @@ else TEXT_OFFSET := 0x00080000 endif +ifeq ($(cc-name),clang) +KBUILD_CFLAGS += $(call cc-disable-warning, asm-operand-widths) +endif + # KASAN_SHADOW_OFFSET = VA_START + (1 << (VA_BITS - 3)) - (1 << 61) # in 32-bit arithmetic KASAN_SHADOW_OFFSET := $(shell printf "0x%08x00000000\n" $$(( \ @@ -114,10 +147,15 @@ core-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a # Default target when executing plain make boot := arch/arm64/boot +ifeq ($(CONFIG_BUILD_ARM64_APPENDED_DTB_IMAGE),y) +KBUILD_IMAGE := $(boot)/$(subst $\",,$(CONFIG_BUILD_ARM64_APPENDED_KERNEL_IMAGE_NAME)) +else KBUILD_IMAGE := $(boot)/Image.gz +endif + KBUILD_DTBS := dtbs -all: Image.gz $(KBUILD_DTBS) +all: Image.gz $(KBUILD_DTBS) $(subst $\",,$(CONFIG_BUILD_ARM64_APPENDED_KERNEL_IMAGE_NAME)) Image: vmlinux @@ -140,6 +178,12 @@ dtbs: prepare scripts dtbs_install: $(Q)$(MAKE) $(dtbinst)=$(boot)/dts +Image-dtb: vmlinux scripts dtbs + $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ + +Image.gz-dtb: vmlinux scripts dtbs Image.gz + $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ + PHONY += vdso_install vdso_install: $(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso $@ diff --git a/arch/arm64/boot/.gitignore b/arch/arm64/boot/.gitignore index 8dab0bb6ae66..34e35209fc2e 100644 --- a/arch/arm64/boot/.gitignore +++ b/arch/arm64/boot/.gitignore @@ -1,2 +1,4 @@ Image +Image-dtb Image.gz +Image.gz-dtb diff --git a/arch/arm64/boot/Makefile b/arch/arm64/boot/Makefile index cd3414898d10..0921d5e5d192 100644 --- a/arch/arm64/boot/Makefile +++ b/arch/arm64/boot/Makefile @@ -14,16 +14,29 @@ # Based on the ia64 boot/Makefile. # +include $(srctree)/arch/arm64/boot/dts/Makefile + OBJCOPYFLAGS_Image :=-O binary -R .note -R .note.gnu.build-id -R .comment -S targets := Image Image.bz2 Image.gz Image.lz4 Image.lzma Image.lzo +DTB_NAMES := $(subst $\",,$(CONFIG_BUILD_ARM64_APPENDED_DTB_IMAGE_NAMES)) +ifneq ($(DTB_NAMES),) +DTB_LIST := $(addsuffix .dtb,$(DTB_NAMES)) +else +DTB_LIST := $(dtb-y) +endif +DTB_OBJS := $(addprefix $(obj)/dts/,$(DTB_LIST)) + $(obj)/Image: vmlinux FORCE $(call if_changed,objcopy) $(obj)/Image.bz2: $(obj)/Image FORCE $(call if_changed,bzip2) +$(obj)/Image-dtb: $(obj)/Image $(DTB_OBJS) FORCE + $(call if_changed,cat) + $(obj)/Image.gz: $(obj)/Image FORCE $(call if_changed,gzip) @@ -36,6 +49,9 @@ $(obj)/Image.lzma: $(obj)/Image FORCE $(obj)/Image.lzo: $(obj)/Image FORCE $(call if_changed,lzo) +$(obj)/Image.gz-dtb: $(obj)/Image.gz $(DTB_OBJS) FORCE + $(call if_changed,cat) + install: $(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \ $(obj)/Image System.map "$(INSTALL_PATH)" diff --git a/arch/arm64/boot/dts/Makefile b/arch/arm64/boot/dts/Makefile index c6684ab8e201..db5a70876487 100644 --- a/arch/arm64/boot/dts/Makefile +++ b/arch/arm64/boot/dts/Makefile @@ -32,3 +32,17 @@ dtstree := $(srctree)/$(src) dtb-$(CONFIG_OF_ALL_DTBS) := $(patsubst $(dtstree)/%.dts,%.dtb, $(foreach d,$(dts-dirs), $(wildcard $(dtstree)/$(d)/*.dts))) always := $(dtb-y) + +targets += dtbs + +DTB_NAMES := $(subst $\",,$(CONFIG_BUILD_ARM64_APPENDED_DTB_IMAGE_NAMES)) +ifneq ($(DTB_NAMES),) +DTB_LIST := $(addsuffix .dtb,$(DTB_NAMES)) +else +DTB_LIST := $(dtb-y) +endif +targets += $(DTB_LIST) + +dtbs: $(addprefix $(obj)/, $(DTB_LIST)) + +clean-files := dts/*.dtb *.dtb diff --git a/arch/arm64/boot/dts/arm/juno-r2.dts b/arch/arm64/boot/dts/arm/juno-r2.dts index b39b6d6ec5aa..d2467e478ec3 100644 --- a/arch/arm64/boot/dts/arm/juno-r2.dts +++ b/arch/arm64/boot/dts/arm/juno-r2.dts @@ -98,6 +98,7 @@ next-level-cache = <&A72_L2>; clocks = <&scpi_dvfs 0>; cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; + sched-energy-costs = <&CPU_COST_A72 &CLUSTER_COST_A72>; capacity-dmips-mhz = <1024>; }; @@ -115,6 +116,7 @@ next-level-cache = <&A72_L2>; clocks = <&scpi_dvfs 0>; cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; + sched-energy-costs = <&CPU_COST_A72 &CLUSTER_COST_A72>; capacity-dmips-mhz = <1024>; }; @@ -132,6 +134,7 @@ next-level-cache = <&A53_L2>; clocks = <&scpi_dvfs 1>; cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; + sched-energy-costs = <&CPU_COST_A53R2 &CLUSTER_COST_A53R2>; capacity-dmips-mhz = <485>; }; @@ -149,6 +152,7 @@ next-level-cache = <&A53_L2>; clocks = <&scpi_dvfs 1>; cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; + sched-energy-costs = <&CPU_COST_A53R2 &CLUSTER_COST_A53R2>; capacity-dmips-mhz = <485>; }; @@ -166,6 +170,7 @@ next-level-cache = <&A53_L2>; clocks = <&scpi_dvfs 1>; cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; + sched-energy-costs = <&CPU_COST_A53R2 &CLUSTER_COST_A53R2>; capacity-dmips-mhz = <485>; }; @@ -183,6 +188,7 @@ next-level-cache = <&A53_L2>; clocks = <&scpi_dvfs 1>; cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; + sched-energy-costs = <&CPU_COST_A53R2 &CLUSTER_COST_A53R2>; capacity-dmips-mhz = <485>; }; @@ -199,6 +205,7 @@ cache-line-size = <64>; cache-sets = <1024>; }; + /include/ "juno-sched-energy.dtsi" }; pmu_a72 { diff --git a/arch/arm64/boot/dts/arm/juno-sched-energy.dtsi b/arch/arm64/boot/dts/arm/juno-sched-energy.dtsi new file mode 100644 index 000000000000..221196ea2091 --- /dev/null +++ b/arch/arm64/boot/dts/arm/juno-sched-energy.dtsi @@ -0,0 +1,123 @@ +/* + * ARM JUNO specific energy cost model data. There are no unit requirements for + * the data. Data can be normalized to any reference point, but the + * normalization must be consistent. That is, one bogo-joule/watt must be the + * same quantity for all data, but we don't care what it is. + */ + +energy-costs { + /* Juno r0 Energy */ + CPU_COST_A57: core-cost0 { + busy-cost-data = < + 417 168 + 579 251 + 744 359 + 883 479 + 1024 616 + >; + idle-cost-data = < + 15 + 15 + 0 + 0 + >; + }; + CPU_COST_A53: core-cost1 { + busy-cost-data = < + 235 33 + 302 46 + 368 61 + 406 76 + 446 93 + >; + idle-cost-data = < + 6 + 6 + 0 + 0 + >; + }; + CLUSTER_COST_A57: cluster-cost0 { + busy-cost-data = < + 417 24 + 579 32 + 744 43 + 883 49 + 1024 64 + >; + idle-cost-data = < + 65 + 65 + 65 + 24 + >; + }; + CLUSTER_COST_A53: cluster-cost1 { + busy-cost-data = < + 235 26 + 302 30 + 368 39 + 406 47 + 446 57 + >; + idle-cost-data = < + 56 + 56 + 56 + 17 + >; + }; + /* Juno r2 Energy */ + CPU_COST_A72: core-cost2 { + busy-cost-data = < + 501 174 + 849 344 + 1024 526 + >; + idle-cost-data = < + 48 + 48 + 0 + 0 + >; + }; + CPU_COST_A53R2: core-cost3 { + busy-cost-data = < + 276 37 + 501 59 + 593 117 + >; + idle-cost-data = < + 33 + 33 + 0 + 0 + >; + }; + CLUSTER_COST_A72: cluster-cost2 { + busy-cost-data = < + 501 48 + 849 73 + 1024 107 + >; + idle-cost-data = < + 48 + 48 + 48 + 18 + >; + }; + CLUSTER_COST_A53R2: cluster-cost3 { + busy-cost-data = < + 276 41 + 501 86 + 593 107 + >; + idle-cost-data = < + 41 + 41 + 41 + 14 + >; + }; +}; diff --git a/arch/arm64/boot/dts/arm/juno.dts b/arch/arm64/boot/dts/arm/juno.dts index c9236c4b967d..ae5306a0ca26 100644 --- a/arch/arm64/boot/dts/arm/juno.dts +++ b/arch/arm64/boot/dts/arm/juno.dts @@ -97,6 +97,7 @@ next-level-cache = <&A57_L2>; clocks = <&scpi_dvfs 0>; cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; + sched-energy-costs = <&CPU_COST_A57 &CLUSTER_COST_A57>; capacity-dmips-mhz = <1024>; }; @@ -114,6 +115,7 @@ next-level-cache = <&A57_L2>; clocks = <&scpi_dvfs 0>; cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; + sched-energy-costs = <&CPU_COST_A57 &CLUSTER_COST_A57>; capacity-dmips-mhz = <1024>; }; @@ -131,6 +133,7 @@ next-level-cache = <&A53_L2>; clocks = <&scpi_dvfs 1>; cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; + sched-energy-costs = <&CPU_COST_A53 &CLUSTER_COST_A53>; capacity-dmips-mhz = <578>; }; @@ -148,6 +151,7 @@ next-level-cache = <&A53_L2>; clocks = <&scpi_dvfs 1>; cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; + sched-energy-costs = <&CPU_COST_A53 &CLUSTER_COST_A53>; capacity-dmips-mhz = <578>; }; @@ -165,6 +169,7 @@ next-level-cache = <&A53_L2>; clocks = <&scpi_dvfs 1>; cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; + sched-energy-costs = <&CPU_COST_A53 &CLUSTER_COST_A53>; capacity-dmips-mhz = <578>; }; @@ -182,6 +187,7 @@ next-level-cache = <&A53_L2>; clocks = <&scpi_dvfs 1>; cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>; + sched-energy-costs = <&CPU_COST_A53 &CLUSTER_COST_A53>; capacity-dmips-mhz = <578>; }; @@ -198,6 +204,7 @@ cache-line-size = <64>; cache-sets = <1024>; }; + /include/ "juno-sched-energy.dtsi" }; pmu_a57 { diff --git a/arch/arm64/boot/dts/hisilicon/hi6220.dtsi b/arch/arm64/boot/dts/hisilicon/hi6220.dtsi index ff1dc89f599e..66d48e35d66d 100644 --- a/arch/arm64/boot/dts/hisilicon/hi6220.dtsi +++ b/arch/arm64/boot/dts/hisilicon/hi6220.dtsi @@ -92,7 +92,9 @@ cooling-max-level = <0>; #cooling-cells = <2>; /* min followed by max */ cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP>; + sched-energy-costs = <&CPU_COST &CLUSTER_COST &SYSTEM_COST>; dynamic-power-coefficient = <311>; + capacity-dmips-mhz = <1024>; }; cpu1: cpu@1 { @@ -103,6 +105,8 @@ next-level-cache = <&CLUSTER0_L2>; operating-points-v2 = <&cpu_opp_table>; cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP>; + sched-energy-costs = <&CPU_COST &CLUSTER_COST &SYSTEM_COST>; + capacity-dmips-mhz = <1024>; }; cpu2: cpu@2 { @@ -113,6 +117,7 @@ next-level-cache = <&CLUSTER0_L2>; operating-points-v2 = <&cpu_opp_table>; cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP>; + capacity-dmips-mhz = <1024>; }; cpu3: cpu@3 { @@ -123,6 +128,8 @@ next-level-cache = <&CLUSTER0_L2>; operating-points-v2 = <&cpu_opp_table>; cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP>; + sched-energy-costs = <&CPU_COST &CLUSTER_COST &SYSTEM_COST>; + capacity-dmips-mhz = <1024>; }; cpu4: cpu@100 { @@ -133,6 +140,7 @@ next-level-cache = <&CLUSTER1_L2>; operating-points-v2 = <&cpu_opp_table>; cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP>; + capacity-dmips-mhz = <1024>; }; cpu5: cpu@101 { @@ -143,6 +151,8 @@ next-level-cache = <&CLUSTER1_L2>; operating-points-v2 = <&cpu_opp_table>; cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP>; + sched-energy-costs = <&CPU_COST &CLUSTER_COST &SYSTEM_COST>; + capacity-dmips-mhz = <1024>; }; cpu6: cpu@102 { @@ -153,6 +163,8 @@ next-level-cache = <&CLUSTER1_L2>; operating-points-v2 = <&cpu_opp_table>; cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP>; + sched-energy-costs = <&CPU_COST &CLUSTER_COST &SYSTEM_COST>; + capacity-dmips-mhz = <1024>; }; cpu7: cpu@103 { @@ -163,6 +175,8 @@ next-level-cache = <&CLUSTER1_L2>; operating-points-v2 = <&cpu_opp_table>; cpu-idle-states = <&CPU_SLEEP &CLUSTER_SLEEP>; + sched-energy-costs = <&CPU_COST &CLUSTER_COST &SYSTEM_COST>; + capacity-dmips-mhz = <1024>; }; CLUSTER0_L2: l2-cache0 { @@ -172,6 +186,50 @@ CLUSTER1_L2: l2-cache1 { compatible = "cache"; }; + + energy-costs { + SYSTEM_COST: system-cost0 { + busy-cost-data = < + 1024 0 + >; + idle-cost-data = < + 0 + 0 + 0 + 0 + >; + }; + CLUSTER_COST: cluster-cost0 { + busy-cost-data = < + 178 16 + 369 29 + 622 47 + 819 75 + 1024 112 + >; + idle-cost-data = < + 107 + 107 + 47 + 0 + >; + }; + CPU_COST: core-cost0 { + busy-cost-data = < + 178 69 + 369 125 + 622 224 + 819 367 + 1024 670 + >; + idle-cost-data = < + 15 + 15 + 0 + 0 + >; + }; + }; }; cpu_opp_table: cpu_opp_table { diff --git a/arch/arm64/configs/cuttlefish_defconfig b/arch/arm64/configs/cuttlefish_defconfig new file mode 100644 index 000000000000..4f6591ec4bc6 --- /dev/null +++ b/arch/arm64/configs/cuttlefish_defconfig @@ -0,0 +1,457 @@ +# CONFIG_FHANDLE is not set +CONFIG_AUDIT=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_TASKSTATS=y +CONFIG_TASK_DELAY_ACCT=y +CONFIG_TASK_XACCT=y +CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_PSI=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_MEMCG=y +CONFIG_MEMCG_SWAP=y +CONFIG_RT_GROUP_SCHED=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CPUSETS=y +# CONFIG_PROC_PID_CPUSET is not set +CONFIG_CGROUP_CPUACCT=y +CONFIG_CGROUP_BPF=y +CONFIG_NAMESPACES=y +CONFIG_SCHED_AUTOGROUP=y +CONFIG_SCHED_TUNE=y +CONFIG_DEFAULT_USE_ENERGY_AWARE=y +CONFIG_BLK_DEV_INITRD=y +# CONFIG_RD_BZIP2 is not set +# CONFIG_RD_LZMA is not set +# CONFIG_RD_XZ is not set +# CONFIG_RD_LZO is not set +# CONFIG_RD_LZ4 is not set +CONFIG_SGETMASK_SYSCALL=y +# CONFIG_SYSFS_SYSCALL is not set +CONFIG_KALLSYMS_ALL=y +CONFIG_BPF_SYSCALL=y +CONFIG_BPF_JIT_ALWAYS_ON=y +CONFIG_EMBEDDED=y +# CONFIG_VM_EVENT_COUNTERS is not set +# CONFIG_COMPAT_BRK is not set +# CONFIG_SLAB_MERGE_DEFAULT is not set +CONFIG_PROFILING=y +CONFIG_KPROBES=y +CONFIG_JUMP_LABEL=y +CONFIG_CC_STACKPROTECTOR_STRONG=y +CONFIG_REFCOUNT_FULL=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODVERSIONS=y +CONFIG_PCI=y +CONFIG_PCI_HOST_GENERIC=y +CONFIG_PREEMPT=y +CONFIG_HZ_100=y +# CONFIG_SPARSEMEM_VMEMMAP is not set +CONFIG_KSM=y +CONFIG_ZSMALLOC=y +CONFIG_SECCOMP=y +CONFIG_PARAVIRT=y +CONFIG_ARMV8_DEPRECATED=y +CONFIG_SWP_EMULATION=y +CONFIG_CP15_BARRIER_EMULATION=y +CONFIG_SETEND_EMULATION=y +CONFIG_ARM64_SW_TTBR0_PAN=y +CONFIG_ARM64_LSE_ATOMICS=y +CONFIG_RANDOMIZE_BASE=y +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +CONFIG_COMPAT=y +CONFIG_PM_WAKELOCKS=y +CONFIG_PM_WAKELOCKS_LIMIT=0 +# CONFIG_PM_WAKELOCKS_GC is not set +CONFIG_PM_DEBUG=y +CONFIG_CPU_IDLE=y +CONFIG_ARM_CPUIDLE=y +CONFIG_CPU_FREQ=y +CONFIG_CPU_FREQ_TIMES=y +CONFIG_CPU_FREQ_DEFAULT_GOV_SCHEDUTIL=y +CONFIG_CPU_FREQ_GOV_POWERSAVE=y +CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y +CONFIG_CPUFREQ_DT=y +CONFIG_ARM_BIG_LITTLE_CPUFREQ=y +CONFIG_ARM_DT_BL_CPUFREQ=y +CONFIG_ARM_SCPI_CPUFREQ=y +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_XFRM_USER=y +CONFIG_XFRM_INTERFACE=y +CONFIG_XFRM_STATISTICS=y +CONFIG_NET_KEY=y +CONFIG_INET=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_NET_IPGRE_DEMUX=y +CONFIG_NET_IPVTI=y +CONFIG_INET_ESP=y +# CONFIG_INET_XFRM_MODE_BEET is not set +CONFIG_INET_UDP_DIAG=y +CONFIG_INET_DIAG_DESTROY=y +CONFIG_TCP_CONG_ADVANCED=y +# CONFIG_TCP_CONG_BIC is not set +# CONFIG_TCP_CONG_WESTWOOD is not set +# CONFIG_TCP_CONG_HTCP is not set +CONFIG_IPV6_ROUTER_PREF=y +CONFIG_IPV6_ROUTE_INFO=y +CONFIG_IPV6_OPTIMISTIC_DAD=y +CONFIG_INET6_ESP=y +CONFIG_INET6_IPCOMP=y +CONFIG_IPV6_MIP6=y +CONFIG_IPV6_VTI=y +CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_NETFILTER=y +CONFIG_NF_CONNTRACK=y +CONFIG_NF_CONNTRACK_SECMARK=y +CONFIG_NF_CONNTRACK_EVENTS=y +CONFIG_NF_CONNTRACK_AMANDA=y +CONFIG_NF_CONNTRACK_FTP=y +CONFIG_NF_CONNTRACK_H323=y +CONFIG_NF_CONNTRACK_IRC=y +CONFIG_NF_CONNTRACK_NETBIOS_NS=y +CONFIG_NF_CONNTRACK_PPTP=y +CONFIG_NF_CONNTRACK_SANE=y +CONFIG_NF_CONNTRACK_TFTP=y +CONFIG_NF_CT_NETLINK=y +CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y +CONFIG_NETFILTER_XT_TARGET_CONNMARK=y +CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y +CONFIG_NETFILTER_XT_TARGET_CT=y +CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y +CONFIG_NETFILTER_XT_TARGET_MARK=y +CONFIG_NETFILTER_XT_TARGET_NFLOG=y +CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y +CONFIG_NETFILTER_XT_TARGET_TPROXY=y +CONFIG_NETFILTER_XT_TARGET_TRACE=y +CONFIG_NETFILTER_XT_TARGET_SECMARK=y +CONFIG_NETFILTER_XT_TARGET_TCPMSS=y +CONFIG_NETFILTER_XT_MATCH_BPF=y +CONFIG_NETFILTER_XT_MATCH_COMMENT=y +CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y +CONFIG_NETFILTER_XT_MATCH_CONNMARK=y +CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y +CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y +CONFIG_NETFILTER_XT_MATCH_HELPER=y +CONFIG_NETFILTER_XT_MATCH_IPRANGE=y +CONFIG_NETFILTER_XT_MATCH_LENGTH=y +CONFIG_NETFILTER_XT_MATCH_LIMIT=y +CONFIG_NETFILTER_XT_MATCH_MAC=y +CONFIG_NETFILTER_XT_MATCH_MARK=y +CONFIG_NETFILTER_XT_MATCH_OWNER=y +CONFIG_NETFILTER_XT_MATCH_POLICY=y +CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y +CONFIG_NETFILTER_XT_MATCH_QUOTA=y +CONFIG_NETFILTER_XT_MATCH_QUOTA2=y +CONFIG_NETFILTER_XT_MATCH_SOCKET=y +CONFIG_NETFILTER_XT_MATCH_STATE=y +CONFIG_NETFILTER_XT_MATCH_STATISTIC=y +CONFIG_NETFILTER_XT_MATCH_STRING=y +CONFIG_NETFILTER_XT_MATCH_TIME=y +CONFIG_NETFILTER_XT_MATCH_U32=y +CONFIG_NF_CONNTRACK_IPV4=y +CONFIG_NF_SOCKET_IPV4=y +CONFIG_IP_NF_IPTABLES=y +CONFIG_IP_NF_MATCH_ECN=y +CONFIG_IP_NF_MATCH_TTL=y +CONFIG_IP_NF_FILTER=y +CONFIG_IP_NF_TARGET_REJECT=y +CONFIG_IP_NF_NAT=y +CONFIG_IP_NF_TARGET_MASQUERADE=y +CONFIG_IP_NF_TARGET_NETMAP=y +CONFIG_IP_NF_TARGET_REDIRECT=y +CONFIG_IP_NF_MANGLE=y +CONFIG_IP_NF_RAW=y +CONFIG_IP_NF_SECURITY=y +CONFIG_IP_NF_ARPTABLES=y +CONFIG_IP_NF_ARPFILTER=y +CONFIG_IP_NF_ARP_MANGLE=y +CONFIG_NF_CONNTRACK_IPV6=y +CONFIG_NF_SOCKET_IPV6=y +CONFIG_IP6_NF_IPTABLES=y +CONFIG_IP6_NF_MATCH_RPFILTER=y +CONFIG_IP6_NF_FILTER=y +CONFIG_IP6_NF_TARGET_REJECT=y +CONFIG_IP6_NF_MANGLE=y +CONFIG_IP6_NF_RAW=y +CONFIG_L2TP=y +CONFIG_NET_SCHED=y +CONFIG_NET_SCH_HTB=y +CONFIG_NET_SCH_NETEM=y +CONFIG_NET_SCH_INGRESS=y +CONFIG_NET_CLS_U32=y +CONFIG_NET_CLS_BPF=y +CONFIG_NET_EMATCH=y +CONFIG_NET_EMATCH_U32=y +CONFIG_NET_CLS_ACT=y +CONFIG_VSOCKETS=y +CONFIG_VIRTIO_VSOCKETS=y +CONFIG_BPF_JIT=y +CONFIG_CFG80211=y +# CONFIG_CFG80211_DEFAULT_PS is not set +CONFIG_MAC80211=y +# CONFIG_MAC80211_RC_MINSTREL is not set +CONFIG_RFKILL=y +# CONFIG_UEVENT_HELPER is not set +# CONFIG_ALLOW_DEV_COREDUMP is not set +CONFIG_DEBUG_DEVRES=y +CONFIG_OF_UNITTEST=y +CONFIG_ZRAM=y +CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_LOOP_MIN_COUNT=16 +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_SIZE=8192 +CONFIG_VIRTIO_BLK=y +CONFIG_UID_SYS_STATS=y +CONFIG_SCSI=y +# CONFIG_SCSI_PROC_FS is not set +CONFIG_BLK_DEV_SD=y +CONFIG_SCSI_VIRTIO=y +CONFIG_MD=y +CONFIG_BLK_DEV_DM=y +CONFIG_DM_CRYPT=y +CONFIG_DM_UEVENT=y +CONFIG_DM_VERITY=y +CONFIG_DM_VERITY_FEC=y +CONFIG_DM_VERITY_AVB=y +CONFIG_DM_BOW=y +CONFIG_NETDEVICES=y +CONFIG_NETCONSOLE=y +CONFIG_NETCONSOLE_DYNAMIC=y +CONFIG_TUN=y +CONFIG_VIRTIO_NET=y +# CONFIG_ETHERNET is not set +CONFIG_PHYLIB=y +CONFIG_PPP=y +CONFIG_PPP_BSDCOMP=y +CONFIG_PPP_DEFLATE=y +CONFIG_PPP_MPPE=y +CONFIG_PPTP=y +CONFIG_PPPOL2TP=y +CONFIG_USB_RTL8152=y +CONFIG_USB_USBNET=y +# CONFIG_USB_NET_AX8817X is not set +# CONFIG_USB_NET_AX88179_178A is not set +# CONFIG_USB_NET_CDCETHER is not set +# CONFIG_USB_NET_CDC_NCM is not set +# CONFIG_USB_NET_NET1080 is not set +# CONFIG_USB_NET_CDC_SUBSET is not set +# CONFIG_USB_NET_ZAURUS is not set +# CONFIG_WLAN_VENDOR_ADMTEK is not set +# CONFIG_WLAN_VENDOR_ATH is not set +# CONFIG_WLAN_VENDOR_ATMEL is not set +# CONFIG_WLAN_VENDOR_BROADCOM is not set +# CONFIG_WLAN_VENDOR_CISCO is not set +# CONFIG_WLAN_VENDOR_INTEL is not set +# CONFIG_WLAN_VENDOR_INTERSIL is not set +# CONFIG_WLAN_VENDOR_MARVELL is not set +# CONFIG_WLAN_VENDOR_MEDIATEK is not set +# CONFIG_WLAN_VENDOR_RALINK is not set +# CONFIG_WLAN_VENDOR_REALTEK is not set +# CONFIG_WLAN_VENDOR_RSI is not set +# CONFIG_WLAN_VENDOR_ST is not set +# CONFIG_WLAN_VENDOR_TI is not set +# CONFIG_WLAN_VENDOR_ZYDAS is not set +# CONFIG_WLAN_VENDOR_QUANTENNA is not set +CONFIG_VIRT_WIFI=y +CONFIG_INPUT_EVDEV=y +CONFIG_INPUT_KEYRESET=y +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +CONFIG_INPUT_JOYSTICK=y +CONFIG_JOYSTICK_XPAD=y +CONFIG_JOYSTICK_XPAD_FF=y +CONFIG_JOYSTICK_XPAD_LEDS=y +CONFIG_INPUT_TABLET=y +CONFIG_TABLET_USB_ACECAD=y +CONFIG_TABLET_USB_AIPTEK=y +CONFIG_TABLET_USB_GTCO=y +CONFIG_TABLET_USB_HANWANG=y +CONFIG_TABLET_USB_KBTAB=y +CONFIG_INPUT_MISC=y +CONFIG_INPUT_UINPUT=y +CONFIG_INPUT_GPIO=y +# CONFIG_VT is not set +# CONFIG_LEGACY_PTYS is not set +# CONFIG_DEVMEM is not set +CONFIG_SERIAL_8250=y +# CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set +CONFIG_SERIAL_8250_CONSOLE=y +# CONFIG_SERIAL_8250_EXAR is not set +CONFIG_SERIAL_8250_NR_UARTS=48 +CONFIG_SERIAL_8250_EXTENDED=y +CONFIG_SERIAL_8250_MANY_PORTS=y +CONFIG_SERIAL_8250_SHARE_IRQ=y +CONFIG_SERIAL_OF_PLATFORM=y +CONFIG_SERIAL_AMBA_PL011=y +CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +CONFIG_VIRTIO_CONSOLE=y +CONFIG_HW_RANDOM=y +CONFIG_HW_RANDOM_VIRTIO=y +# CONFIG_HW_RANDOM_CAVIUM is not set +# CONFIG_DEVPORT is not set +# CONFIG_I2C_COMPAT is not set +# CONFIG_I2C_HELPER_AUTO is not set +# CONFIG_HWMON is not set +CONFIG_THERMAL=y +CONFIG_CPU_THERMAL=y +CONFIG_MEDIA_SUPPORT=y +# CONFIG_VGA_ARB is not set +CONFIG_DRM=y +# CONFIG_DRM_FBDEV_EMULATION is not set +CONFIG_DRM_VIRTIO_GPU=y +CONFIG_SOUND=y +CONFIG_SND=y +CONFIG_SND_HRTIMER=y +# CONFIG_SND_SUPPORT_OLD_API is not set +# CONFIG_SND_VERBOSE_PROCFS is not set +# CONFIG_SND_DRIVERS is not set +CONFIG_SND_INTEL8X0=y +# CONFIG_SND_USB is not set +CONFIG_HIDRAW=y +CONFIG_UHID=y +CONFIG_HID_A4TECH=y +CONFIG_HID_ACRUX=y +CONFIG_HID_ACRUX_FF=y +CONFIG_HID_APPLE=y +CONFIG_HID_BELKIN=y +CONFIG_HID_CHERRY=y +CONFIG_HID_CHICONY=y +CONFIG_HID_PRODIKEYS=y +CONFIG_HID_CYPRESS=y +CONFIG_HID_DRAGONRISE=y +CONFIG_DRAGONRISE_FF=y +CONFIG_HID_EMS_FF=y +CONFIG_HID_ELECOM=y +CONFIG_HID_EZKEY=y +CONFIG_HID_HOLTEK=y +CONFIG_HID_KEYTOUCH=y +CONFIG_HID_KYE=y +CONFIG_HID_UCLOGIC=y +CONFIG_HID_WALTOP=y +CONFIG_HID_GYRATION=y +CONFIG_HID_TWINHAN=y +CONFIG_HID_KENSINGTON=y +CONFIG_HID_LCPOWER=y +CONFIG_HID_LOGITECH=y +CONFIG_HID_LOGITECH_DJ=y +CONFIG_LOGITECH_FF=y +CONFIG_LOGIRUMBLEPAD2_FF=y +CONFIG_LOGIG940_FF=y +CONFIG_HID_MAGICMOUSE=y +CONFIG_HID_MICROSOFT=y +CONFIG_HID_MONTEREY=y +CONFIG_HID_MULTITOUCH=y +CONFIG_HID_NTRIG=y +CONFIG_HID_ORTEK=y +CONFIG_HID_PANTHERLORD=y +CONFIG_PANTHERLORD_FF=y +CONFIG_HID_PETALYNX=y +CONFIG_HID_PICOLCD=y +CONFIG_HID_PRIMAX=y +CONFIG_HID_ROCCAT=y +CONFIG_HID_SAITEK=y +CONFIG_HID_SAMSUNG=y +CONFIG_HID_SONY=y +CONFIG_HID_SPEEDLINK=y +CONFIG_HID_SUNPLUS=y +CONFIG_HID_GREENASIA=y +CONFIG_GREENASIA_FF=y +CONFIG_HID_SMARTJOYPLUS=y +CONFIG_SMARTJOYPLUS_FF=y +CONFIG_HID_TIVO=y +CONFIG_HID_TOPSEED=y +CONFIG_HID_THRUSTMASTER=y +CONFIG_HID_WACOM=y +CONFIG_HID_WIIMOTE=y +CONFIG_HID_ZEROPLUS=y +CONFIG_HID_ZYDACRON=y +CONFIG_USB_HIDDEV=y +CONFIG_USB_ANNOUNCE_NEW_DEVICES=y +CONFIG_USB_EHCI_HCD=y +CONFIG_USB_GADGET=y +CONFIG_USB_CONFIGFS=y +CONFIG_USB_CONFIGFS_F_FS=y +CONFIG_USB_CONFIGFS_F_ACC=y +CONFIG_USB_CONFIGFS_F_AUDIO_SRC=y +CONFIG_USB_CONFIGFS_UEVENT=y +CONFIG_USB_CONFIGFS_F_MIDI=y +CONFIG_MMC=y +# CONFIG_PWRSEQ_EMMC is not set +# CONFIG_PWRSEQ_SIMPLE is not set +# CONFIG_MMC_BLOCK is not set +CONFIG_RTC_CLASS=y +# CONFIG_RTC_SYSTOHC is not set +CONFIG_RTC_DRV_PL030=y +CONFIG_RTC_DRV_PL031=y +CONFIG_VIRTIO_PCI=y +# CONFIG_VIRTIO_PCI_LEGACY is not set +CONFIG_VIRTIO_BALLOON=y +CONFIG_VIRTIO_INPUT=y +CONFIG_VIRTIO_MMIO=y +CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y +CONFIG_STAGING=y +CONFIG_ASHMEM=y +CONFIG_ANDROID_VSOC=y +CONFIG_ION=y +CONFIG_ION_SYSTEM_HEAP=y +CONFIG_COMMON_CLK_SCPI=y +# CONFIG_COMMON_CLK_XGENE is not set +CONFIG_MAILBOX=y +# CONFIG_IOMMU_SUPPORT is not set +CONFIG_ANDROID=y +CONFIG_ANDROID_BINDER_IPC=y +CONFIG_ARM_SCPI_PROTOCOL=y +# CONFIG_ARM_SCPI_POWER_DOMAIN is not set +CONFIG_EXT4_FS=y +CONFIG_EXT4_FS_SECURITY=y +CONFIG_EXT4_ENCRYPTION=y +CONFIG_F2FS_FS=y +CONFIG_F2FS_FS_SECURITY=y +CONFIG_F2FS_FS_ENCRYPTION=y +# CONFIG_DNOTIFY is not set +CONFIG_QUOTA=y +CONFIG_QFMT_V2=y +CONFIG_FUSE_FS=y +CONFIG_OVERLAY_FS=y +CONFIG_MSDOS_FS=y +CONFIG_VFAT_FS=y +CONFIG_TMPFS=y +CONFIG_TMPFS_POSIX_ACL=y +# CONFIG_EFIVAR_FS is not set +CONFIG_SDCARD_FS=y +CONFIG_PSTORE=y +CONFIG_PSTORE_CONSOLE=y +CONFIG_PSTORE_RAM=y +CONFIG_PRINTK_TIME=y +CONFIG_DEBUG_INFO=y +# CONFIG_ENABLE_MUST_CHECK is not set +CONFIG_FRAME_WARN=1024 +# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set +CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_STACK_USAGE=y +CONFIG_DEBUG_MEMORY_INIT=y +CONFIG_SOFTLOCKUP_DETECTOR=y +# CONFIG_DETECT_HUNG_TASK is not set +CONFIG_PANIC_TIMEOUT=5 +CONFIG_SCHEDSTATS=y +CONFIG_RCU_CPU_STALL_TIMEOUT=60 +CONFIG_ENABLE_DEFAULT_TRACERS=y +CONFIG_SECURITY_PERF_EVENTS_RESTRICT=y +CONFIG_SECURITY=y +CONFIG_SECURITY_NETWORK=y +CONFIG_LSM_MMAP_MIN_ADDR=65536 +CONFIG_HARDENED_USERCOPY=y +CONFIG_SECURITY_SELINUX=y +CONFIG_CRYPTO_ADIANTUM=y +CONFIG_CRYPTO_SHA512=y +CONFIG_CRYPTO_LZ4=y +CONFIG_CRYPTO_ZSTD=y +CONFIG_CRYPTO_ANSI_CPRNG=y +CONFIG_CRYPTO_DEV_VIRTIO=y +CONFIG_XZ_DEC=y diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index b05796578e7a..14f170fa433c 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -4,6 +4,7 @@ CONFIG_AUDIT=y CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y CONFIG_IRQ_TIME_ACCOUNTING=y +CONFIG_SCHED_WALT=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_BSD_PROCESS_ACCT_V3=y CONFIG_TASKSTATS=y @@ -24,8 +25,9 @@ CONFIG_CGROUP_CPUACCT=y CONFIG_CGROUP_PERF=y CONFIG_USER_NS=y CONFIG_SCHED_AUTOGROUP=y +CONFIG_SCHED_TUNE=y +CONFIG_DEFAULT_USE_ENERGY_AWARE=y CONFIG_BLK_DEV_INITRD=y -CONFIG_KALLSYMS_ALL=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y CONFIG_JUMP_LABEL=y @@ -69,13 +71,13 @@ CONFIG_HOTPLUG_PCI_ACPI=y CONFIG_PCI_LAYERSCAPE=y CONFIG_PCI_HISI=y CONFIG_PCIE_QCOM=y -CONFIG_PCIE_KIRIN=y CONFIG_PCIE_ARMADA_8K=y +CONFIG_PCIE_KIRIN=y CONFIG_PCI_AARDVARK=y CONFIG_PCIE_RCAR=y -CONFIG_PCIE_ROCKCHIP=m CONFIG_PCI_HOST_GENERIC=y CONFIG_PCI_XGENE=y +CONFIG_PCIE_ROCKCHIP=m CONFIG_ARM64_VA_BITS_48=y CONFIG_SCHED_MC=y CONFIG_NUMA=y @@ -93,6 +95,12 @@ CONFIG_HIBERNATION=y CONFIG_WQ_POWER_EFFICIENT_DEFAULT=y CONFIG_ARM_CPUIDLE=y CONFIG_CPU_FREQ=y +CONFIG_CPU_FREQ_STAT=y +CONFIG_CPU_FREQ_DEFAULT_GOV_SCHEDUTIL=y +CONFIG_CPU_FREQ_GOV_POWERSAVE=y +CONFIG_CPU_FREQ_GOV_USERSPACE=y +CONFIG_CPU_FREQ_GOV_ONDEMAND=y +CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y CONFIG_CPUFREQ_DT=y CONFIG_ARM_BIG_LITTLE_CPUFREQ=y CONFIG_ARM_SCPI_CPUFREQ=y @@ -140,11 +148,10 @@ CONFIG_BT_HIDP=m CONFIG_BT_LEDS=y # CONFIG_BT_DEBUGFS is not set CONFIG_BT_HCIUART=m -CONFIG_BT_HCIUART_LL=y -CONFIG_CFG80211=m -CONFIG_MAC80211=m +CONFIG_CFG80211=y +CONFIG_MAC80211=y CONFIG_MAC80211_LEDS=y -CONFIG_RFKILL=m +CONFIG_RFKILL=y CONFIG_NET_9P=y CONFIG_NET_9P_VIRTIO=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" @@ -210,21 +217,16 @@ CONFIG_REALTEK_PHY=m CONFIG_ROCKCHIP_PHY=y CONFIG_USB_PEGASUS=m CONFIG_USB_RTL8150=m -CONFIG_USB_RTL8152=m -CONFIG_USB_USBNET=m -CONFIG_USB_NET_DM9601=m -CONFIG_USB_NET_SR9800=m -CONFIG_USB_NET_SMSC75XX=m -CONFIG_USB_NET_SMSC95XX=m -CONFIG_USB_NET_PLUSB=m -CONFIG_USB_NET_MCS7830=m +CONFIG_USB_RTL8152=y CONFIG_BRCMFMAC=m +CONFIG_RTL_CARDS=m CONFIG_WL18XX=m CONFIG_WLCORE_SDIO=m +CONFIG_USB_NET_RNDIS_WLAN=y CONFIG_INPUT_EVDEV=y CONFIG_KEYBOARD_ADC=m -CONFIG_KEYBOARD_CROS_EC=y CONFIG_KEYBOARD_GPIO=y +CONFIG_KEYBOARD_CROS_EC=y CONFIG_INPUT_MISC=y CONFIG_INPUT_PM8941_PWRKEY=y CONFIG_INPUT_HISI_POWERKEY=y @@ -275,20 +277,20 @@ CONFIG_I2C_UNIPHIER_F=y CONFIG_I2C_RCAR=y CONFIG_I2C_CROS_EC_TUNNEL=y CONFIG_SPI=y -CONFIG_SPI_MESON_SPICC=m -CONFIG_SPI_MESON_SPIFC=m CONFIG_SPI_BCM2835=m CONFIG_SPI_BCM2835AUX=m +CONFIG_SPI_MESON_SPICC=m +CONFIG_SPI_MESON_SPIFC=m CONFIG_SPI_ORION=y CONFIG_SPI_PL022=y -CONFIG_SPI_QUP=y CONFIG_SPI_ROCKCHIP=y +CONFIG_SPI_QUP=y CONFIG_SPI_S3C64XX=y CONFIG_SPI_SPIDEV=m CONFIG_SPMI=y -CONFIG_PINCTRL_IPQ8074=y CONFIG_PINCTRL_SINGLE=y CONFIG_PINCTRL_MAX77620=y +CONFIG_PINCTRL_IPQ8074=y CONFIG_PINCTRL_MSM8916=y CONFIG_PINCTRL_MSM8994=y CONFIG_PINCTRL_MSM8996=y @@ -315,9 +317,8 @@ CONFIG_SENSORS_INA2XX=m CONFIG_THERMAL_GOV_POWER_ALLOCATOR=y CONFIG_CPU_THERMAL=y CONFIG_THERMAL_EMULATION=y -CONFIG_BRCMSTB_THERMAL=m -CONFIG_EXYNOS_THERMAL=y CONFIG_ROCKCHIP_THERMAL=m +CONFIG_EXYNOS_THERMAL=y CONFIG_WATCHDOG=y CONFIG_S3C2410_WATCHDOG=y CONFIG_MESON_GXBB_WATCHDOG=m @@ -336,9 +337,9 @@ CONFIG_MFD_MAX77620=y CONFIG_MFD_SPMI_PMIC=y CONFIG_MFD_RK808=y CONFIG_MFD_SEC_CORE=y +CONFIG_REGULATOR_FIXED_VOLTAGE=y CONFIG_REGULATOR_AXP20X=y CONFIG_REGULATOR_FAN53555=y -CONFIG_REGULATOR_FIXED_VOLTAGE=y CONFIG_REGULATOR_GPIO=y CONFIG_REGULATOR_HI6421V530=y CONFIG_REGULATOR_HI655X=y @@ -348,16 +349,13 @@ CONFIG_REGULATOR_QCOM_SMD_RPM=y CONFIG_REGULATOR_QCOM_SPMI=y CONFIG_REGULATOR_RK808=y CONFIG_REGULATOR_S2MPS11=y +CONFIG_RC_DEVICES=y +CONFIG_IR_MESON=m CONFIG_MEDIA_SUPPORT=m CONFIG_MEDIA_CAMERA_SUPPORT=y CONFIG_MEDIA_ANALOG_TV_SUPPORT=y CONFIG_MEDIA_DIGITAL_TV_SUPPORT=y CONFIG_MEDIA_CONTROLLER=y -CONFIG_MEDIA_RC_SUPPORT=y -CONFIG_RC_CORE=m -CONFIG_RC_DEVICES=y -CONFIG_RC_DECODERS=y -CONFIG_IR_MESON=m CONFIG_VIDEO_V4L2_SUBDEV_API=y # CONFIG_DVB_NET is not set CONFIG_V4L_MEM2MEM_DRIVERS=y @@ -395,7 +393,6 @@ CONFIG_FB_ARMCLCD=y CONFIG_BACKLIGHT_GENERIC=m CONFIG_BACKLIGHT_PWM=m CONFIG_BACKLIGHT_LP855X=m -CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y # CONFIG_LOGO_LINUX_MONO is not set # CONFIG_LOGO_LINUX_VGA16 is not set @@ -494,7 +491,6 @@ CONFIG_XEN_GRANT_DEV_ALLOC=y CONFIG_COMMON_CLK_RK808=y CONFIG_COMMON_CLK_SCPI=y CONFIG_COMMON_CLK_CS2000_CP=y -CONFIG_COMMON_CLK_S2MPS11=y CONFIG_CLK_QORIQ=y CONFIG_COMMON_CLK_PWM=y CONFIG_COMMON_CLK_QCOM=y @@ -533,13 +529,13 @@ CONFIG_PWM_MESON=m CONFIG_PWM_ROCKCHIP=y CONFIG_PWM_SAMSUNG=y CONFIG_PWM_TEGRA=m -CONFIG_PHY_RCAR_GEN3_USB2=y -CONFIG_PHY_HI6220_USB=y +CONFIG_PHY_XGENE=y CONFIG_PHY_SUN4I_USB=y -CONFIG_PHY_ROCKCHIP_INNO_USB2=y +CONFIG_PHY_HI6220_USB=y +CONFIG_PHY_RCAR_GEN3_USB2=y CONFIG_PHY_ROCKCHIP_EMMC=y +CONFIG_PHY_ROCKCHIP_INNO_USB2=y CONFIG_PHY_ROCKCHIP_PCIE=m -CONFIG_PHY_XGENE=y CONFIG_PHY_TEGRA_XUSB=y CONFIG_QCOM_L2_PMU=y CONFIG_QCOM_L3_PMU=y @@ -581,29 +577,27 @@ CONFIG_VIRTUALIZATION=y CONFIG_KVM=y CONFIG_PRINTK_TIME=y CONFIG_DEBUG_INFO=y -CONFIG_DEBUG_FS=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y -CONFIG_LOCKUP_DETECTOR=y -# CONFIG_SCHED_DEBUG is not set +CONFIG_SCHEDSTATS=y # CONFIG_DEBUG_PREEMPT is not set -# CONFIG_FTRACE is not set +CONFIG_PROVE_LOCKING=y +CONFIG_FUNCTION_TRACER=y +CONFIG_IRQSOFF_TRACER=y +CONFIG_PREEMPT_TRACER=y +CONFIG_SCHED_TRACER=y CONFIG_MEMTEST=y CONFIG_SECURITY=y CONFIG_CRYPTO_ECHAINIV=y CONFIG_CRYPTO_ANSI_CPRNG=y CONFIG_ARM64_CRYPTO=y -CONFIG_CRYPTO_SHA256_ARM64=m CONFIG_CRYPTO_SHA512_ARM64=m CONFIG_CRYPTO_SHA1_ARM64_CE=y CONFIG_CRYPTO_SHA2_ARM64_CE=y CONFIG_CRYPTO_GHASH_ARM64_CE=y CONFIG_CRYPTO_CRCT10DIF_ARM64_CE=m CONFIG_CRYPTO_CRC32_ARM64_CE=m -CONFIG_CRYPTO_AES_ARM64=m -CONFIG_CRYPTO_AES_ARM64_CE=m CONFIG_CRYPTO_AES_ARM64_CE_CCM=y CONFIG_CRYPTO_AES_ARM64_CE_BLK=y -CONFIG_CRYPTO_AES_ARM64_NEON_BLK=m CONFIG_CRYPTO_CHACHA20_NEON=m CONFIG_CRYPTO_AES_ARM64_BS=m diff --git a/arch/arm64/configs/ranchu64_defconfig b/arch/arm64/configs/ranchu64_defconfig new file mode 100644 index 000000000000..71e8102dc40c --- /dev/null +++ b/arch/arm64/configs/ranchu64_defconfig @@ -0,0 +1,309 @@ +# CONFIG_LOCALVERSION_AUTO is not set +# CONFIG_SWAP is not set +CONFIG_POSIX_MQUEUE=y +CONFIG_AUDIT=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_BSD_PROCESS_ACCT=y +CONFIG_BSD_PROCESS_ACCT_V3=y +CONFIG_TASKSTATS=y +CONFIG_TASK_DELAY_ACCT=y +CONFIG_TASK_XACCT=y +CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_LOG_BUF_SHIFT=14 +CONFIG_CGROUP_DEBUG=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_RT_GROUP_SCHED=y +CONFIG_SCHED_AUTOGROUP=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_KALLSYMS_ALL=y +CONFIG_EMBEDDED=y +# CONFIG_COMPAT_BRK is not set +CONFIG_PROFILING=y +CONFIG_ARCH_MMAP_RND_BITS=24 +CONFIG_ARCH_MMAP_RND_COMPAT_BITS=16 +# CONFIG_BLK_DEV_BSG is not set +# CONFIG_IOSCHED_DEADLINE is not set +CONFIG_ARCH_VEXPRESS=y +CONFIG_NR_CPUS=4 +CONFIG_PREEMPT=y +CONFIG_KSM=y +CONFIG_SECCOMP=y +CONFIG_ARMV8_DEPRECATED=y +CONFIG_SWP_EMULATION=y +CONFIG_CP15_BARRIER_EMULATION=y +CONFIG_SETEND_EMULATION=y +CONFIG_CMDLINE="console=ttyAMA0" +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +CONFIG_COMPAT=y +CONFIG_PM_AUTOSLEEP=y +CONFIG_PM_WAKELOCKS=y +CONFIG_PM_WAKELOCKS_LIMIT=0 +# CONFIG_PM_WAKELOCKS_GC is not set +CONFIG_PM_DEBUG=y +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_XFRM_USER=y +CONFIG_NET_KEY=y +CONFIG_INET=y +CONFIG_INET_DIAG_DESTROY=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +CONFIG_INET_ESP=y +# CONFIG_INET_LRO is not set +CONFIG_IPV6_ROUTER_PREF=y +CONFIG_IPV6_ROUTE_INFO=y +CONFIG_IPV6_OPTIMISTIC_DAD=y +CONFIG_INET6_AH=y +CONFIG_INET6_ESP=y +CONFIG_INET6_IPCOMP=y +CONFIG_IPV6_MIP6=y +CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_NETFILTER=y +CONFIG_NF_CONNTRACK=y +CONFIG_NF_CONNTRACK_SECMARK=y +CONFIG_NF_CONNTRACK_EVENTS=y +CONFIG_NF_CT_PROTO_DCCP=y +CONFIG_NF_CT_PROTO_SCTP=y +CONFIG_NF_CT_PROTO_UDPLITE=y +CONFIG_NF_CONNTRACK_AMANDA=y +CONFIG_NF_CONNTRACK_FTP=y +CONFIG_NF_CONNTRACK_H323=y +CONFIG_NF_CONNTRACK_IRC=y +CONFIG_NF_CONNTRACK_NETBIOS_NS=y +CONFIG_NF_CONNTRACK_PPTP=y +CONFIG_NF_CONNTRACK_SANE=y +CONFIG_NF_CONNTRACK_TFTP=y +CONFIG_NF_CT_NETLINK=y +CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y +CONFIG_NETFILTER_XT_TARGET_CONNMARK=y +CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y +CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y +CONFIG_NETFILTER_XT_TARGET_MARK=y +CONFIG_NETFILTER_XT_TARGET_NFLOG=y +CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y +CONFIG_NETFILTER_XT_TARGET_TPROXY=y +CONFIG_NETFILTER_XT_TARGET_TRACE=y +CONFIG_NETFILTER_XT_TARGET_SECMARK=y +CONFIG_NETFILTER_XT_TARGET_TCPMSS=y +CONFIG_NETFILTER_XT_MATCH_COMMENT=y +CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y +CONFIG_NETFILTER_XT_MATCH_CONNMARK=y +CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y +CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y +CONFIG_NETFILTER_XT_MATCH_HELPER=y +CONFIG_NETFILTER_XT_MATCH_IPRANGE=y +CONFIG_NETFILTER_XT_MATCH_LENGTH=y +CONFIG_NETFILTER_XT_MATCH_LIMIT=y +CONFIG_NETFILTER_XT_MATCH_MAC=y +CONFIG_NETFILTER_XT_MATCH_MARK=y +CONFIG_NETFILTER_XT_MATCH_OWNER=y +CONFIG_NETFILTER_XT_MATCH_POLICY=y +CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y +CONFIG_NETFILTER_XT_MATCH_QUOTA=y +CONFIG_NETFILTER_XT_MATCH_QUOTA2=y +CONFIG_NETFILTER_XT_MATCH_SOCKET=y +CONFIG_NETFILTER_XT_MATCH_STATE=y +CONFIG_NETFILTER_XT_MATCH_STATISTIC=y +CONFIG_NETFILTER_XT_MATCH_STRING=y +CONFIG_NETFILTER_XT_MATCH_TIME=y +CONFIG_NETFILTER_XT_MATCH_U32=y +CONFIG_NF_CONNTRACK_IPV4=y +CONFIG_IP_NF_IPTABLES=y +CONFIG_IP_NF_MATCH_AH=y +CONFIG_IP_NF_MATCH_ECN=y +CONFIG_IP_NF_MATCH_RPFILTER=y +CONFIG_IP_NF_MATCH_TTL=y +CONFIG_IP_NF_FILTER=y +CONFIG_IP_NF_TARGET_REJECT=y +CONFIG_IP_NF_MANGLE=y +CONFIG_IP_NF_TARGET_ECN=y +CONFIG_IP_NF_TARGET_TTL=y +CONFIG_IP_NF_RAW=y +CONFIG_IP_NF_SECURITY=y +CONFIG_IP_NF_ARPTABLES=y +CONFIG_IP_NF_ARPFILTER=y +CONFIG_IP_NF_ARP_MANGLE=y +CONFIG_NF_CONNTRACK_IPV6=y +CONFIG_IP6_NF_IPTABLES=y +CONFIG_IP6_NF_MATCH_AH=y +CONFIG_IP6_NF_MATCH_EUI64=y +CONFIG_IP6_NF_MATCH_FRAG=y +CONFIG_IP6_NF_MATCH_OPTS=y +CONFIG_IP6_NF_MATCH_HL=y +CONFIG_IP6_NF_MATCH_IPV6HEADER=y +CONFIG_IP6_NF_MATCH_MH=y +CONFIG_IP6_NF_MATCH_RT=y +CONFIG_IP6_NF_TARGET_HL=y +CONFIG_IP6_NF_FILTER=y +CONFIG_IP6_NF_TARGET_REJECT=y +CONFIG_IP6_NF_MANGLE=y +CONFIG_IP6_NF_RAW=y +CONFIG_BRIDGE=y +CONFIG_NET_SCHED=y +CONFIG_NET_SCH_HTB=y +CONFIG_NET_CLS_U32=y +CONFIG_NET_EMATCH=y +CONFIG_NET_EMATCH_U32=y +CONFIG_NET_CLS_ACT=y +# CONFIG_WIRELESS is not set +CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_SIZE=8192 +CONFIG_VIRTIO_BLK=y +CONFIG_SCSI=y +# CONFIG_SCSI_PROC_FS is not set +CONFIG_BLK_DEV_SD=y +# CONFIG_SCSI_LOWLEVEL is not set +CONFIG_MD=y +CONFIG_BLK_DEV_DM=y +CONFIG_DM_CRYPT=y +CONFIG_DM_UEVENT=y +CONFIG_DM_VERITY=y +CONFIG_DM_VERITY_FEC=y +CONFIG_NETDEVICES=y +CONFIG_TUN=y +CONFIG_VIRTIO_NET=y +CONFIG_SMC91X=y +CONFIG_PPP=y +CONFIG_PPP_BSDCOMP=y +CONFIG_PPP_DEFLATE=y +CONFIG_PPP_MPPE=y +# CONFIG_WLAN is not set +CONFIG_INPUT_EVDEV=y +CONFIG_INPUT_KEYRESET=y +CONFIG_KEYBOARD_GOLDFISH_EVENTS=y +# CONFIG_INPUT_MOUSE is not set +CONFIG_INPUT_JOYSTICK=y +CONFIG_INPUT_TABLET=y +CONFIG_INPUT_MISC=y +CONFIG_INPUT_UINPUT=y +CONFIG_INPUT_GPIO=y +# CONFIG_SERIO_SERPORT is not set +# CONFIG_VT is not set +# CONFIG_LEGACY_PTYS is not set +# CONFIG_DEVMEM is not set +# CONFIG_DEVKMEM is not set +CONFIG_SERIAL_AMBA_PL011=y +CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +CONFIG_VIRTIO_CONSOLE=y +# CONFIG_HW_RANDOM is not set +CONFIG_BATTERY_GOLDFISH=y +# CONFIG_HWMON is not set +CONFIG_MEDIA_SUPPORT=y +CONFIG_FB=y +CONFIG_FB_GOLDFISH=y +CONFIG_FB_SIMPLE=y +CONFIG_BACKLIGHT_LCD_SUPPORT=y +CONFIG_LOGO=y +# CONFIG_LOGO_LINUX_MONO is not set +# CONFIG_LOGO_LINUX_VGA16 is not set +CONFIG_SOUND=y +CONFIG_SND=y +CONFIG_HIDRAW=y +CONFIG_UHID=y +CONFIG_HID_A4TECH=y +CONFIG_HID_ACRUX=y +CONFIG_HID_ACRUX_FF=y +CONFIG_HID_APPLE=y +CONFIG_HID_BELKIN=y +CONFIG_HID_CHERRY=y +CONFIG_HID_CHICONY=y +CONFIG_HID_PRODIKEYS=y +CONFIG_HID_CYPRESS=y +CONFIG_HID_DRAGONRISE=y +CONFIG_DRAGONRISE_FF=y +CONFIG_HID_EMS_FF=y +CONFIG_HID_ELECOM=y +CONFIG_HID_EZKEY=y +CONFIG_HID_KEYTOUCH=y +CONFIG_HID_KYE=y +CONFIG_HID_WALTOP=y +CONFIG_HID_GYRATION=y +CONFIG_HID_TWINHAN=y +CONFIG_HID_KENSINGTON=y +CONFIG_HID_LCPOWER=y +CONFIG_HID_LOGITECH=y +CONFIG_HID_LOGITECH_DJ=y +CONFIG_LOGITECH_FF=y +CONFIG_LOGIRUMBLEPAD2_FF=y +CONFIG_LOGIG940_FF=y +CONFIG_HID_MAGICMOUSE=y +CONFIG_HID_MICROSOFT=y +CONFIG_HID_MONTEREY=y +CONFIG_HID_MULTITOUCH=y +CONFIG_HID_ORTEK=y +CONFIG_HID_PANTHERLORD=y +CONFIG_PANTHERLORD_FF=y +CONFIG_HID_PETALYNX=y +CONFIG_HID_PICOLCD=y +CONFIG_HID_PRIMAX=y +CONFIG_HID_SAITEK=y +CONFIG_HID_SAMSUNG=y +CONFIG_HID_SPEEDLINK=y +CONFIG_HID_SUNPLUS=y +CONFIG_HID_GREENASIA=y +CONFIG_GREENASIA_FF=y +CONFIG_HID_SMARTJOYPLUS=y +CONFIG_SMARTJOYPLUS_FF=y +CONFIG_HID_TIVO=y +CONFIG_HID_TOPSEED=y +CONFIG_HID_THRUSTMASTER=y +CONFIG_HID_WACOM=y +CONFIG_HID_WIIMOTE=y +CONFIG_HID_ZEROPLUS=y +CONFIG_HID_ZYDACRON=y +# CONFIG_USB_SUPPORT is not set +CONFIG_RTC_CLASS=y +CONFIG_VIRTIO_MMIO=y +CONFIG_STAGING=y +CONFIG_ASHMEM=y +CONFIG_ANDROID_TIMED_GPIO=y +CONFIG_ANDROID_LOW_MEMORY_KILLER=y +CONFIG_SYNC=y +CONFIG_SW_SYNC=y +CONFIG_SW_SYNC_USER=y +CONFIG_ION=y +CONFIG_GOLDFISH_AUDIO=y +CONFIG_GOLDFISH=y +CONFIG_GOLDFISH_PIPE=y +# CONFIG_IOMMU_SUPPORT is not set +CONFIG_ANDROID=y +CONFIG_ANDROID_BINDER_IPC=y +CONFIG_EXT2_FS=y +CONFIG_EXT4_FS=y +CONFIG_EXT4_FS_SECURITY=y +CONFIG_QUOTA=y +CONFIG_FUSE_FS=y +CONFIG_CUSE=y +CONFIG_MSDOS_FS=y +CONFIG_VFAT_FS=y +CONFIG_TMPFS=y +CONFIG_TMPFS_POSIX_ACL=y +# CONFIG_MISC_FILESYSTEMS is not set +CONFIG_NFS_FS=y +CONFIG_ROOT_NFS=y +CONFIG_NLS_CODEPAGE_437=y +CONFIG_NLS_ISO8859_1=y +CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_FS=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_PANIC_TIMEOUT=5 +# CONFIG_SCHED_DEBUG is not set +CONFIG_SCHEDSTATS=y +CONFIG_TIMER_STATS=y +# CONFIG_FTRACE is not set +CONFIG_ATOMIC64_SELFTEST=y +CONFIG_DEBUG_RODATA=y +CONFIG_SECURITY=y +CONFIG_SECURITY_NETWORK=y +CONFIG_SECURITY_SELINUX=y diff --git a/arch/arm64/crypto/chacha20-neon-glue.c b/arch/arm64/crypto/chacha20-neon-glue.c index cbdb75d15cd0..f6cfab1bc0e2 100644 --- a/arch/arm64/crypto/chacha20-neon-glue.c +++ b/arch/arm64/crypto/chacha20-neon-glue.c @@ -19,7 +19,7 @@ */ #include <crypto/algapi.h> -#include <crypto/chacha20.h> +#include <crypto/chacha.h> #include <crypto/internal/skcipher.h> #include <linux/kernel.h> #include <linux/module.h> @@ -34,20 +34,20 @@ asmlinkage void chacha20_4block_xor_neon(u32 *state, u8 *dst, const u8 *src); static void chacha20_doneon(u32 *state, u8 *dst, const u8 *src, unsigned int bytes) { - u8 buf[CHACHA20_BLOCK_SIZE]; + u8 buf[CHACHA_BLOCK_SIZE]; - while (bytes >= CHACHA20_BLOCK_SIZE * 4) { + while (bytes >= CHACHA_BLOCK_SIZE * 4) { chacha20_4block_xor_neon(state, dst, src); - bytes -= CHACHA20_BLOCK_SIZE * 4; - src += CHACHA20_BLOCK_SIZE * 4; - dst += CHACHA20_BLOCK_SIZE * 4; + bytes -= CHACHA_BLOCK_SIZE * 4; + src += CHACHA_BLOCK_SIZE * 4; + dst += CHACHA_BLOCK_SIZE * 4; state[12] += 4; } - while (bytes >= CHACHA20_BLOCK_SIZE) { + while (bytes >= CHACHA_BLOCK_SIZE) { chacha20_block_xor_neon(state, dst, src); - bytes -= CHACHA20_BLOCK_SIZE; - src += CHACHA20_BLOCK_SIZE; - dst += CHACHA20_BLOCK_SIZE; + bytes -= CHACHA_BLOCK_SIZE; + src += CHACHA_BLOCK_SIZE; + dst += CHACHA_BLOCK_SIZE; state[12]++; } if (bytes) { @@ -60,17 +60,17 @@ static void chacha20_doneon(u32 *state, u8 *dst, const u8 *src, static int chacha20_neon(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct chacha20_ctx *ctx = crypto_skcipher_ctx(tfm); + struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); struct skcipher_walk walk; u32 state[16]; int err; - if (!may_use_simd() || req->cryptlen <= CHACHA20_BLOCK_SIZE) - return crypto_chacha20_crypt(req); + if (!may_use_simd() || req->cryptlen <= CHACHA_BLOCK_SIZE) + return crypto_chacha_crypt(req); err = skcipher_walk_virt(&walk, req, true); - crypto_chacha20_init(state, ctx, walk.iv); + crypto_chacha_init(state, ctx, walk.iv); kernel_neon_begin(); while (walk.nbytes > 0) { @@ -93,14 +93,14 @@ static struct skcipher_alg alg = { .base.cra_driver_name = "chacha20-neon", .base.cra_priority = 300, .base.cra_blocksize = 1, - .base.cra_ctxsize = sizeof(struct chacha20_ctx), + .base.cra_ctxsize = sizeof(struct chacha_ctx), .base.cra_module = THIS_MODULE, - .min_keysize = CHACHA20_KEY_SIZE, - .max_keysize = CHACHA20_KEY_SIZE, - .ivsize = CHACHA20_IV_SIZE, - .chunksize = CHACHA20_BLOCK_SIZE, - .walksize = 4 * CHACHA20_BLOCK_SIZE, + .min_keysize = CHACHA_KEY_SIZE, + .max_keysize = CHACHA_KEY_SIZE, + .ivsize = CHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, + .walksize = 4 * CHACHA_BLOCK_SIZE, .setkey = crypto_chacha20_setkey, .encrypt = chacha20_neon, .decrypt = chacha20_neon, diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c index 70568e6db77b..fb7a9caf51c8 100644 --- a/arch/arm64/crypto/sha1-ce-glue.c +++ b/arch/arm64/crypto/sha1-ce-glue.c @@ -29,6 +29,14 @@ struct sha1_ce_state { asmlinkage void sha1_ce_transform(struct sha1_ce_state *sst, u8 const *src, int blocks); +#ifdef CONFIG_CFI_CLANG +static inline void __cfi_sha1_ce_transform(struct sha1_state *sst, + u8 const *src, int blocks) +{ + sha1_ce_transform((struct sha1_ce_state *)sst, src, blocks); +} +#define sha1_ce_transform __cfi_sha1_ce_transform +#endif const u32 sha1_ce_offsetof_count = offsetof(struct sha1_ce_state, sst.count); const u32 sha1_ce_offsetof_finalize = offsetof(struct sha1_ce_state, finalize); diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c index af8472aded42..9141184d89e4 100644 --- a/arch/arm64/crypto/sha2-ce-glue.c +++ b/arch/arm64/crypto/sha2-ce-glue.c @@ -29,6 +29,14 @@ struct sha256_ce_state { asmlinkage void sha2_ce_transform(struct sha256_ce_state *sst, u8 const *src, int blocks); +#ifdef CONFIG_CFI_CLANG +static inline void __cfi_sha2_ce_transform(struct sha256_state *sst, + u8 const *src, int blocks) +{ + sha2_ce_transform((struct sha256_ce_state *)sst, src, blocks); +} +#define sha2_ce_transform __cfi_sha2_ce_transform +#endif const u32 sha256_ce_offsetof_count = offsetof(struct sha256_ce_state, sst.count); diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index 4572a9b560fa..20bfb8e676e0 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -29,7 +29,9 @@ ({ \ u64 reg; \ asm volatile(ALTERNATIVE("mrs %0, " __stringify(r##nvh),\ - "mrs_s %0, " __stringify(r##vh),\ + DEFINE_MRS_S \ + "mrs_s %0, " __stringify(r##vh) "\n"\ + UNDEFINE_MRS_S, \ ARM64_HAS_VIRT_HOST_EXTN) \ : "=r" (reg)); \ reg; \ @@ -39,7 +41,9 @@ do { \ u64 __val = (u64)(v); \ asm volatile(ALTERNATIVE("msr " __stringify(r##nvh) ", %x0",\ - "msr_s " __stringify(r##vh) ", %x0",\ + DEFINE_MSR_S \ + "msr_s " __stringify(r##vh) ", %x0\n"\ + UNDEFINE_MSR_S, \ ARM64_HAS_VIRT_HOST_EXTN) \ : : "rZ" (__val)); \ } while (0) diff --git a/arch/arm64/include/asm/lse.h b/arch/arm64/include/asm/lse.h index eec95768eaad..7bf78372da69 100644 --- a/arch/arm64/include/asm/lse.h +++ b/arch/arm64/include/asm/lse.h @@ -17,7 +17,12 @@ #else /* __ASSEMBLER__ */ +#ifdef CONFIG_LTO_CLANG +#define __LSE_PREAMBLE ".arch armv8-a+lse\n" +#else __asm__(".arch_extension lse"); +#define __LSE_PREAMBLE +#endif /* Move the ll/sc atomics out-of-line */ #define __LL_SC_INLINE notrace @@ -30,7 +35,7 @@ __asm__(".arch_extension lse"); /* In-line patching at runtime */ #define ARM64_LSE_ATOMIC_INSN(llsc, lse) \ - ALTERNATIVE(llsc, lse, ARM64_HAS_LSE_ATOMICS) + ALTERNATIVE(llsc, __LSE_PREAMBLE lse, ARM64_HAS_LSE_ATOMICS) #endif /* __ASSEMBLER__ */ #else /* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */ diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index 779d7a2ec5ec..f7ff06580721 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -132,7 +132,7 @@ static inline void cpu_install_idmap(void) * Atomically replaces the active TTBR1_EL1 PGD with a new VA-compatible PGD, * avoiding the possibility of conflicting TLB entries being allocated. */ -static inline void cpu_replace_ttbr1(pgd_t *pgd) +static inline void __nocfi cpu_replace_ttbr1(pgd_t *pgd) { typedef void (ttbr_replace_func)(phys_addr_t); extern ttbr_replace_func idmap_cpu_replace_ttbr1; diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 2564dd429ab6..c1612da556c8 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -547,20 +547,39 @@ #include <linux/build_bug.h> #include <linux/types.h> -asm( -" .irp num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30\n" -" .equ .L__reg_num_x\\num, \\num\n" -" .endr\n" +#define __DEFINE_MRS_MSR_S_REGNUM \ +" .irp num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30\n" \ +" .equ .L__reg_num_x\\num, \\num\n" \ +" .endr\n" \ " .equ .L__reg_num_xzr, 31\n" -"\n" -" .macro mrs_s, rt, sreg\n" - __emit_inst(0xd5200000|(\\sreg)|(.L__reg_num_\\rt)) + +#define DEFINE_MRS_S \ + __DEFINE_MRS_MSR_S_REGNUM \ +" .macro mrs_s, rt, sreg\n" \ +" .inst 0xd5200000|(\\sreg)|(.L__reg_num_\\rt)\n" \ " .endm\n" -"\n" -" .macro msr_s, sreg, rt\n" - __emit_inst(0xd5000000|(\\sreg)|(.L__reg_num_\\rt)) + +#define DEFINE_MSR_S \ + __DEFINE_MRS_MSR_S_REGNUM \ +" .macro msr_s, sreg, rt\n" \ +" .inst 0xd5000000|(\\sreg)|(.L__reg_num_\\rt)\n" \ " .endm\n" -); + +#define UNDEFINE_MRS_S \ +" .purgem mrs_s\n" + +#define UNDEFINE_MSR_S \ +" .purgem msr_s\n" + +#define __mrs_s(r, v) \ + DEFINE_MRS_S \ +" mrs_s %0, " __stringify(r) "\n" \ + UNDEFINE_MRS_S : "=r" (v) + +#define __msr_s(r, v) \ + DEFINE_MSR_S \ +" msr_s " __stringify(r) ", %x0\n" \ + UNDEFINE_MSR_S : : "rZ" (v) /* * Unlike read_cpuid, calls to read_sysreg are never expected to be @@ -586,15 +605,15 @@ asm( * For registers without architectural names, or simply unsupported by * GAS. */ -#define read_sysreg_s(r) ({ \ - u64 __val; \ - asm volatile("mrs_s %0, " __stringify(r) : "=r" (__val)); \ - __val; \ +#define read_sysreg_s(r) ({ \ + u64 __val; \ + asm volatile(__mrs_s(r, __val)); \ + __val; \ }) -#define write_sysreg_s(v, r) do { \ - u64 __val = (u64)(v); \ - asm volatile("msr_s " __stringify(r) ", %x0" : : "rZ" (__val)); \ +#define write_sysreg_s(v, r) do { \ + u64 __val = (u64)(v); \ + asm volatile(__msr_s(r, __val)); \ } while (0) /* diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h index b3202284568b..b7bd70520a77 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -33,6 +33,20 @@ int pcibus_to_node(struct pci_bus *bus); #endif /* CONFIG_NUMA */ +#include <linux/arch_topology.h> + +/* Replace task scheduler's default frequency-invariant accounting */ +#define arch_scale_freq_capacity topology_get_freq_scale + +/* Replace task scheduler's default max-frequency-invariant accounting */ +#define arch_scale_max_freq_capacity topology_get_max_freq_scale + +/* Replace task scheduler's default cpu-invariant accounting */ +#define arch_scale_cpu_capacity topology_get_cpu_scale + +/* Enable topology flag updates */ +#define arch_update_cpu_topology topology_update_cpu_topology + #include <asm-generic/topology.h> #endif /* _ASM_ARM_TOPOLOGY_H */ diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 6b3bb67596ae..b35bfc49b5e3 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -106,6 +106,11 @@ cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused) * sync with the documentation of the CPU feature register ABI. */ static const struct arm64_ftr_bits ftr_id_aa64isar0[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64ISAR0_DP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64ISAR0_SM4_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64ISAR0_SM3_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64ISAR0_SHA3_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64ISAR0_RDM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_TS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_FHM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_DP_SHIFT, 4, 0), @@ -887,7 +892,7 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, } #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 -static void +static void __nocfi kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused) { typedef void (kpti_remap_fn)(int, int, phys_addr_t); diff --git a/arch/arm64/kernel/io.c b/arch/arm64/kernel/io.c index 354be2a872ae..79b17384effa 100644 --- a/arch/arm64/kernel/io.c +++ b/arch/arm64/kernel/io.c @@ -25,8 +25,7 @@ */ void __memcpy_fromio(void *to, const volatile void __iomem *from, size_t count) { - while (count && (!IS_ALIGNED((unsigned long)from, 8) || - !IS_ALIGNED((unsigned long)to, 8))) { + while (count && !IS_ALIGNED((unsigned long)from, 8)) { *(u8 *)to = __raw_readb(from); from++; to++; @@ -54,23 +53,22 @@ EXPORT_SYMBOL(__memcpy_fromio); */ void __memcpy_toio(volatile void __iomem *to, const void *from, size_t count) { - while (count && (!IS_ALIGNED((unsigned long)to, 8) || - !IS_ALIGNED((unsigned long)from, 8))) { - __raw_writeb(*(volatile u8 *)from, to); + while (count && !IS_ALIGNED((unsigned long)to, 8)) { + __raw_writeb(*(u8 *)from, to); from++; to++; count--; } while (count >= 8) { - __raw_writeq(*(volatile u64 *)from, to); + __raw_writeq(*(u64 *)from, to); from += 8; to += 8; count -= 8; } while (count) { - __raw_writeb(*(volatile u8 *)from, to); + __raw_writeb(*(u8 *)from, to); from++; to++; count--; diff --git a/arch/arm64/kernel/module.lds b/arch/arm64/kernel/module.lds index 22e36a21c113..99eb7c292494 100644 --- a/arch/arm64/kernel/module.lds +++ b/arch/arm64/kernel/module.lds @@ -1,5 +1,5 @@ SECTIONS { - .plt (NOLOAD) : { BYTE(0) } - .init.plt (NOLOAD) : { BYTE(0) } - .text.ftrace_trampoline (NOLOAD) : { BYTE(0) } + .plt : { BYTE(0) } + .init.plt : { BYTE(0) } + .text.ftrace_trampoline : { BYTE(0) } } diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 2ff327651ebe..fef9f2f70252 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -170,6 +170,70 @@ void machine_restart(char *cmd) while (1); } +/* + * dump a block of kernel memory from around the given address + */ +static void show_data(unsigned long addr, int nbytes, const char *name) +{ + int i, j; + int nlines; + u32 *p; + + /* + * don't attempt to dump non-kernel addresses or + * values that are probably just small negative numbers + */ + if (addr < PAGE_OFFSET || addr > -256UL) + return; + + printk("\n%s: %#lx:\n", name, addr); + + /* + * round address down to a 32 bit boundary + * and always dump a multiple of 32 bytes + */ + p = (u32 *)(addr & ~(sizeof(u32) - 1)); + nbytes += (addr & (sizeof(u32) - 1)); + nlines = (nbytes + 31) / 32; + + + for (i = 0; i < nlines; i++) { + /* + * just display low 16 bits of address to keep + * each line of the dump < 80 characters + */ + printk("%04lx ", (unsigned long)p & 0xffff); + for (j = 0; j < 8; j++) { + u32 data; + if (probe_kernel_address(p, data)) { + pr_cont(" ********"); + } else { + pr_cont(" %08x", data); + } + ++p; + } + pr_cont("\n"); + } +} + +static void show_extra_register_data(struct pt_regs *regs, int nbytes) +{ + mm_segment_t fs; + unsigned int i; + + fs = get_fs(); + set_fs(KERNEL_DS); + show_data(regs->pc - nbytes, nbytes * 2, "PC"); + show_data(regs->regs[30] - nbytes, nbytes * 2, "LR"); + show_data(regs->sp - nbytes, nbytes * 2, "SP"); + for (i = 0; i < 30; i++) { + char name[4]; + snprintf(name, sizeof(name), "X%u", i); + show_data(regs->regs[i] - nbytes, nbytes * 2, name); + } + set_fs(fs); +} + void __show_regs(struct pt_regs *regs) { int i, top_reg; @@ -203,6 +267,9 @@ void __show_regs(struct pt_regs *regs) pr_cont("\n"); } + if (!user_mode(regs)) + show_extra_register_data(regs, 128); + printk("\n"); } void show_regs(struct pt_regs * regs) diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 8d48b233e6ce..6eb9350be46f 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -21,6 +21,7 @@ #include <linux/of.h> #include <linux/sched.h> #include <linux/sched/topology.h> +#include <linux/sched/energy.h> #include <linux/slab.h> #include <linux/string.h> @@ -280,8 +281,58 @@ void store_cpu_topology(unsigned int cpuid) topology_populated: update_siblings_masks(cpuid); + topology_detect_flags(); } +#ifdef CONFIG_SCHED_SMT +static int smt_flags(void) +{ + return cpu_smt_flags() | topology_smt_flags(); +} +#endif + +#ifdef CONFIG_SCHED_MC +static int core_flags(void) +{ + return cpu_core_flags() | topology_core_flags(); +} +#endif + +static int cpu_flags(void) +{ + return topology_cpu_flags(); +} + +static inline +const struct sched_group_energy * const cpu_core_energy(int cpu) +{ + return sge_array[cpu][SD_LEVEL0]; +} + +static inline +const struct sched_group_energy * const cpu_cluster_energy(int cpu) +{ + return sge_array[cpu][SD_LEVEL1]; +} + +static inline +const struct sched_group_energy * const cpu_system_energy(int cpu) +{ + return sge_array[cpu][SD_LEVEL2]; +} + +static struct sched_domain_topology_level arm64_topology[] = { +#ifdef CONFIG_SCHED_SMT + { cpu_smt_mask, smt_flags, SD_INIT_NAME(SMT) }, +#endif +#ifdef CONFIG_SCHED_MC + { cpu_coregroup_mask, core_flags, cpu_core_energy, SD_INIT_NAME(MC) }, +#endif + { cpu_cpu_mask, cpu_flags, cpu_cluster_energy, SD_INIT_NAME(DIE) }, + { cpu_cpu_mask, NULL, cpu_system_energy, SD_INIT_NAME(SYS) }, + { NULL, } +}; + static void __init reset_cpu_topology(void) { unsigned int cpu; @@ -310,4 +361,6 @@ void __init init_cpu_topology(void) */ if (of_have_populated_dt() && parse_dt_topology()) reset_cpu_topology(); + else + set_sched_topology(arm64_topology); } diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index b215c712d897..b2c1695c4d4c 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -12,17 +12,13 @@ obj-vdso := gettimeofday.o note.o sigreturn.o targets := $(obj-vdso) vdso.so vdso.so.dbg obj-vdso := $(addprefix $(obj)/, $(obj-vdso)) -ccflags-y := -shared -fno-common -fno-builtin -ccflags-y += -nostdlib -Wl,-soname=linux-vdso.so.1 \ - $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) +ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv \ + --build-id $(call ld-option,-n) -T +ccflags-y += $(DISABLE_LTO) # Disable gcov profiling for VDSO code GCOV_PROFILE := n -# Workaround for bare-metal (ELF) toolchains that neglect to pass -shared -# down to collect2, resulting in silent corruption of the vDSO image. -ccflags-y += -Wl,-shared - obj-y += vdso.o extra-y += vdso.lds CPPFLAGS_vdso.lds += -P -C -U$(ARCH) @@ -32,7 +28,7 @@ $(obj)/vdso.o : $(obj)/vdso.so # Link rule for the .so file, .lds has to be first $(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso) - $(call if_changed,vdsold) + $(call if_changed,ld) # Strip rule for the .so file $(obj)/%.so: OBJCOPYFLAGS := -S @@ -54,8 +50,6 @@ $(obj-vdso): %.o: %.S FORCE $(call if_changed_dep,vdsoas) # Actual build commands -quiet_cmd_vdsold = VDSOL $@ - cmd_vdsold = $(CC) $(c_flags) -Wl,-n -Wl,-T $^ -o $@ quiet_cmd_vdsoas = VDSOA $@ cmd_vdsoas = $(CC) $(a_flags) -c -o $@ $< diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S index df829c4346fa..21805e416483 100644 --- a/arch/arm64/kernel/vdso/gettimeofday.S +++ b/arch/arm64/kernel/vdso/gettimeofday.S @@ -310,7 +310,7 @@ ENTRY(__kernel_clock_getres) b.ne 4f ldr x2, 5f 2: - cbz w1, 3f + cbz x1, 3f stp xzr, x2, [x1] 3: /* res == NULL. */ diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index c4e55176f4b6..9c0543066b08 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -61,7 +61,7 @@ jiffies = jiffies_64; #define TRAMP_TEXT \ . = ALIGN(PAGE_SIZE); \ VMLINUX_SYMBOL(__entry_tramp_text_start) = .; \ - *(.entry.tramp.text) \ + KEEP(*(.entry.tramp.text)) \ . = ALIGN(PAGE_SIZE); \ VMLINUX_SYMBOL(__entry_tramp_text_end) = .; #else @@ -151,7 +151,7 @@ SECTIONS . = ALIGN(4); .altinstructions : { __alt_instructions = .; - *(.altinstructions) + KEEP(*(.altinstructions)) __alt_instructions_end = .; } diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile index f04400d494b7..bfa00a9e161d 100644 --- a/arch/arm64/kvm/hyp/Makefile +++ b/arch/arm64/kvm/hyp/Makefile @@ -3,7 +3,11 @@ # Makefile for Kernel-based Virtual Machine module, HYP part # -ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING +ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING $(DISABLE_CFI) + +ifeq ($(cc-name),clang) +ccflags-y += -fno-jump-tables +endif KVM=../../../../virt/kvm diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 56c110844c01..2c2eee348e9e 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -166,7 +166,7 @@ static void *__dma_alloc(struct device *dev, size_t size, /* create a coherent mapping */ page = virt_to_page(ptr); coherent_ptr = dma_common_contiguous_remap(page, size, VM_USERMAP, - prot, NULL); + prot, __builtin_return_address(0)); if (!coherent_ptr) goto no_map; diff --git a/arch/powerpc/platforms/cell/cpufreq_spudemand.c b/arch/powerpc/platforms/cell/cpufreq_spudemand.c index 882944c36ef5..5d8e8b6bb1cc 100644 --- a/arch/powerpc/platforms/cell/cpufreq_spudemand.c +++ b/arch/powerpc/platforms/cell/cpufreq_spudemand.c @@ -49,7 +49,7 @@ static int calc_freq(struct spu_gov_info_struct *info) cpu = info->policy->cpu; busy_spus = atomic_read(&cbe_spu_info[cpu_to_node(cpu)].busy_spus); - CALC_LOAD(info->busy_spus, EXP, busy_spus * FIXED_1); + info->busy_spus = calc_load(info->busy_spus, EXP, busy_spus * FIXED_1); pr_debug("cpu %d: busy_spus=%d, info->busy_spus=%ld\n", cpu, busy_spus, info->busy_spus); diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c index 1fbb5da17dd2..509cf6709131 100644 --- a/arch/powerpc/platforms/cell/spufs/sched.c +++ b/arch/powerpc/platforms/cell/spufs/sched.c @@ -987,9 +987,9 @@ static void spu_calc_load(void) unsigned long active_tasks; /* fixed-point */ active_tasks = count_active_contexts() * FIXED_1; - CALC_LOAD(spu_avenrun[0], EXP_1, active_tasks); - CALC_LOAD(spu_avenrun[1], EXP_5, active_tasks); - CALC_LOAD(spu_avenrun[2], EXP_15, active_tasks); + spu_avenrun[0] = calc_load(spu_avenrun[0], EXP_1, active_tasks); + spu_avenrun[1] = calc_load(spu_avenrun[1], EXP_5, active_tasks); + spu_avenrun[2] = calc_load(spu_avenrun[2], EXP_15, active_tasks); } static void spusched_wake(unsigned long data) @@ -1071,9 +1071,6 @@ void spuctx_switch_state(struct spu_context *ctx, } } -#define LOAD_INT(x) ((x) >> FSHIFT) -#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) - static int show_spu_loadavg(struct seq_file *s, void *private) { int a, b, c; diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c index 25224c9e1dc0..5a8e4caac369 100644 --- a/arch/powerpc/platforms/pseries/cmm.c +++ b/arch/powerpc/platforms/pseries/cmm.c @@ -747,7 +747,7 @@ static void cmm_exit(void) * Return value: * 0 on success / other on failure **/ -static int cmm_set_disable(const char *val, struct kernel_param *kp) +static int cmm_set_disable(const char *val, const struct kernel_param *kp) { int disable = simple_strtoul(val, NULL, 10); diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c index 45b3178200ab..a8aac17e1e82 100644 --- a/arch/s390/appldata/appldata_os.c +++ b/arch/s390/appldata/appldata_os.c @@ -24,10 +24,6 @@ #include "appldata.h" - -#define LOAD_INT(x) ((x) >> FSHIFT) -#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) - /* * OS data * diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index be3136f142a9..a8103a84b4ac 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -113,7 +113,7 @@ show_signal_msg(struct pt_regs *regs, int sig, int code, if (!printk_ratelimit()) return; - printk("%s%s[%d]: segfault at %lx ip %p (rpc %p) sp %p error %x", + printk("%s%s[%d]: segfault at %lx ip %px (rpc %px) sp %px error %x", task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG, tsk->comm, task_pid_nr(tsk), address, (void *)regs->pc, (void *)regs->u_regs[UREG_I7], diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 815c03d7a765..41363f46797b 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -154,7 +154,7 @@ show_signal_msg(struct pt_regs *regs, int sig, int code, if (!printk_ratelimit()) return; - printk("%s%s[%d]: segfault at %lx ip %p (rpc %p) sp %p error %x", + printk("%s%s[%d]: segfault at %lx ip %px (rpc %px) sp %px error %x", task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG, tsk->comm, task_pid_nr(tsk), address, (void *)regs->tpc, (void *)regs->u_regs[UREG_I7], diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 4e6fcb32620f..428644175956 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -150,7 +150,7 @@ static void show_segv_info(struct uml_pt_regs *regs) if (!printk_ratelimit()) return; - printk("%s%s[%d]: segfault at %lx ip %p sp %p error %x", + printk("%s%s[%d]: segfault at %lx ip %px sp %px error %x", task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG, tsk->comm, task_pid_nr(tsk), FAULT_ADDRESS(*fi), (void *)UPT_IP(regs), (void *)UPT_SP(regs), diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 3dc54d2f79c4..62ec0e709e8a 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -112,6 +112,8 @@ else KBUILD_CFLAGS += $(call cc-option,-mno-80387) KBUILD_CFLAGS += $(call cc-option,-mno-fp-ret-in-387) + KBUILD_CFLAGS += -fno-pic + # By default gcc and clang use a stack alignment of 16 bytes for x86. # However the standard kernel entry on x86-64 leaves the stack on an # 8-byte boundary. If the compiler isn't informed about the actual diff --git a/arch/x86/configs/i386_ranchu_defconfig b/arch/x86/configs/i386_ranchu_defconfig new file mode 100644 index 000000000000..864841204edb --- /dev/null +++ b/arch/x86/configs/i386_ranchu_defconfig @@ -0,0 +1,421 @@ +# CONFIG_64BIT is not set +# CONFIG_LOCALVERSION_AUTO is not set +CONFIG_POSIX_MQUEUE=y +CONFIG_AUDIT=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_BSD_PROCESS_ACCT=y +CONFIG_TASKSTATS=y +CONFIG_TASK_DELAY_ACCT=y +CONFIG_TASK_XACCT=y +CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_CGROUPS=y +CONFIG_CGROUP_DEBUG=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_CGROUP_SCHED=y +CONFIG_RT_GROUP_SCHED=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y +CONFIG_SYSCTL_SYSCALL=y +CONFIG_KALLSYMS_ALL=y +CONFIG_EMBEDDED=y +# CONFIG_COMPAT_BRK is not set +CONFIG_ARCH_MMAP_RND_BITS=16 +CONFIG_PARTITION_ADVANCED=y +CONFIG_OSF_PARTITION=y +CONFIG_AMIGA_PARTITION=y +CONFIG_MAC_PARTITION=y +CONFIG_BSD_DISKLABEL=y +CONFIG_MINIX_SUBPARTITION=y +CONFIG_SOLARIS_X86_PARTITION=y +CONFIG_UNIXWARE_DISKLABEL=y +CONFIG_SGI_PARTITION=y +CONFIG_SUN_PARTITION=y +CONFIG_KARMA_PARTITION=y +CONFIG_SMP=y +CONFIG_X86_BIGSMP=y +CONFIG_MCORE2=y +CONFIG_X86_GENERIC=y +CONFIG_HPET_TIMER=y +CONFIG_NR_CPUS=512 +CONFIG_PREEMPT=y +# CONFIG_X86_MCE is not set +CONFIG_X86_REBOOTFIXUPS=y +CONFIG_X86_MSR=y +CONFIG_X86_CPUID=y +CONFIG_KSM=y +CONFIG_CMA=y +# CONFIG_MTRR_SANITIZER is not set +CONFIG_EFI=y +CONFIG_EFI_STUB=y +CONFIG_HZ_100=y +CONFIG_PHYSICAL_START=0x100000 +CONFIG_PM_AUTOSLEEP=y +CONFIG_PM_WAKELOCKS=y +CONFIG_PM_WAKELOCKS_LIMIT=0 +# CONFIG_PM_WAKELOCKS_GC is not set +CONFIG_PM_DEBUG=y +CONFIG_CPU_FREQ=y +# CONFIG_CPU_FREQ_STAT is not set +CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y +CONFIG_CPU_FREQ_GOV_USERSPACE=y +CONFIG_PCIEPORTBUS=y +# CONFIG_PCIEASPM is not set +CONFIG_PCCARD=y +CONFIG_YENTA=y +CONFIG_HOTPLUG_PCI=y +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +CONFIG_BINFMT_MISC=y +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_XFRM_USER=y +CONFIG_NET_KEY=y +CONFIG_INET=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IP_ROUTE_MULTIPATH=y +CONFIG_IP_ROUTE_VERBOSE=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +CONFIG_IP_PNP_RARP=y +CONFIG_IP_MROUTE=y +CONFIG_IP_PIMSM_V1=y +CONFIG_IP_PIMSM_V2=y +CONFIG_SYN_COOKIES=y +CONFIG_INET_ESP=y +# CONFIG_INET_XFRM_MODE_BEET is not set +# CONFIG_INET_LRO is not set +CONFIG_INET_DIAG_DESTROY=y +CONFIG_IPV6_ROUTER_PREF=y +CONFIG_IPV6_ROUTE_INFO=y +CONFIG_IPV6_OPTIMISTIC_DAD=y +CONFIG_INET6_AH=y +CONFIG_INET6_ESP=y +CONFIG_INET6_IPCOMP=y +CONFIG_IPV6_MIP6=y +CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_NETLABEL=y +CONFIG_NETFILTER=y +CONFIG_NF_CONNTRACK=y +CONFIG_NF_CONNTRACK_SECMARK=y +CONFIG_NF_CONNTRACK_EVENTS=y +CONFIG_NF_CT_PROTO_DCCP=y +CONFIG_NF_CT_PROTO_SCTP=y +CONFIG_NF_CT_PROTO_UDPLITE=y +CONFIG_NF_CONNTRACK_AMANDA=y +CONFIG_NF_CONNTRACK_FTP=y +CONFIG_NF_CONNTRACK_H323=y +CONFIG_NF_CONNTRACK_IRC=y +CONFIG_NF_CONNTRACK_NETBIOS_NS=y +CONFIG_NF_CONNTRACK_PPTP=y +CONFIG_NF_CONNTRACK_SANE=y +CONFIG_NF_CONNTRACK_TFTP=y +CONFIG_NF_CT_NETLINK=y +CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y +CONFIG_NETFILTER_XT_TARGET_CONNMARK=y +CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y +CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y +CONFIG_NETFILTER_XT_TARGET_MARK=y +CONFIG_NETFILTER_XT_TARGET_NFLOG=y +CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y +CONFIG_NETFILTER_XT_TARGET_TPROXY=y +CONFIG_NETFILTER_XT_TARGET_TRACE=y +CONFIG_NETFILTER_XT_TARGET_SECMARK=y +CONFIG_NETFILTER_XT_TARGET_TCPMSS=y +CONFIG_NETFILTER_XT_MATCH_COMMENT=y +CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y +CONFIG_NETFILTER_XT_MATCH_CONNMARK=y +CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y +CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y +CONFIG_NETFILTER_XT_MATCH_HELPER=y +CONFIG_NETFILTER_XT_MATCH_IPRANGE=y +CONFIG_NETFILTER_XT_MATCH_LENGTH=y +CONFIG_NETFILTER_XT_MATCH_LIMIT=y +CONFIG_NETFILTER_XT_MATCH_MAC=y +CONFIG_NETFILTER_XT_MATCH_MARK=y +CONFIG_NETFILTER_XT_MATCH_OWNER=y +CONFIG_NETFILTER_XT_MATCH_POLICY=y +CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y +CONFIG_NETFILTER_XT_MATCH_QUOTA=y +CONFIG_NETFILTER_XT_MATCH_QUOTA2=y +CONFIG_NETFILTER_XT_MATCH_SOCKET=y +CONFIG_NETFILTER_XT_MATCH_STATE=y +CONFIG_NETFILTER_XT_MATCH_STATISTIC=y +CONFIG_NETFILTER_XT_MATCH_STRING=y +CONFIG_NETFILTER_XT_MATCH_TIME=y +CONFIG_NETFILTER_XT_MATCH_U32=y +CONFIG_NF_CONNTRACK_IPV4=y +CONFIG_IP_NF_IPTABLES=y +CONFIG_IP_NF_MATCH_AH=y +CONFIG_IP_NF_MATCH_ECN=y +CONFIG_IP_NF_MATCH_TTL=y +CONFIG_IP_NF_FILTER=y +CONFIG_IP_NF_TARGET_REJECT=y +CONFIG_IP_NF_MANGLE=y +CONFIG_IP_NF_RAW=y +CONFIG_IP_NF_SECURITY=y +CONFIG_IP_NF_ARPTABLES=y +CONFIG_IP_NF_ARPFILTER=y +CONFIG_IP_NF_ARP_MANGLE=y +CONFIG_NF_CONNTRACK_IPV6=y +CONFIG_IP6_NF_IPTABLES=y +CONFIG_IP6_NF_FILTER=y +CONFIG_IP6_NF_TARGET_REJECT=y +CONFIG_IP6_NF_MANGLE=y +CONFIG_IP6_NF_RAW=y +CONFIG_NET_SCHED=y +CONFIG_NET_SCH_HTB=y +CONFIG_NET_CLS_U32=y +CONFIG_NET_EMATCH=y +CONFIG_NET_EMATCH_U32=y +CONFIG_NET_CLS_ACT=y +CONFIG_CFG80211=y +CONFIG_MAC80211=y +CONFIG_MAC80211_LEDS=y +CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_DMA_CMA=y +CONFIG_CMA_SIZE_MBYTES=16 +CONFIG_CONNECTOR=y +CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_SIZE=8192 +CONFIG_VIRTIO_BLK=y +CONFIG_BLK_DEV_SD=y +CONFIG_BLK_DEV_SR=y +CONFIG_BLK_DEV_SR_VENDOR=y +CONFIG_CHR_DEV_SG=y +CONFIG_SCSI_CONSTANTS=y +CONFIG_SCSI_SPI_ATTRS=y +CONFIG_SCSI_ISCSI_ATTRS=y +# CONFIG_SCSI_LOWLEVEL is not set +CONFIG_ATA=y +CONFIG_SATA_AHCI=y +CONFIG_ATA_PIIX=y +CONFIG_PATA_AMD=y +CONFIG_PATA_OLDPIIX=y +CONFIG_PATA_SCH=y +CONFIG_PATA_MPIIX=y +CONFIG_ATA_GENERIC=y +CONFIG_MD=y +CONFIG_BLK_DEV_MD=y +CONFIG_BLK_DEV_DM=y +CONFIG_DM_DEBUG=y +CONFIG_DM_CRYPT=y +CONFIG_DM_MIRROR=y +CONFIG_DM_ZERO=y +CONFIG_DM_UEVENT=y +CONFIG_DM_VERITY=y +CONFIG_DM_VERITY_FEC=y +CONFIG_NETDEVICES=y +CONFIG_NETCONSOLE=y +CONFIG_TUN=y +CONFIG_VIRTIO_NET=y +CONFIG_BNX2=y +CONFIG_TIGON3=y +CONFIG_NET_TULIP=y +CONFIG_E100=y +CONFIG_E1000=y +CONFIG_E1000E=y +CONFIG_SKY2=y +CONFIG_NE2K_PCI=y +CONFIG_FORCEDETH=y +CONFIG_8139TOO=y +# CONFIG_8139TOO_PIO is not set +CONFIG_R8169=y +CONFIG_FDDI=y +CONFIG_PPP=y +CONFIG_PPP_BSDCOMP=y +CONFIG_PPP_DEFLATE=y +CONFIG_PPP_MPPE=y +CONFIG_USB_USBNET=y +CONFIG_INPUT_POLLDEV=y +# CONFIG_INPUT_MOUSEDEV_PSAUX is not set +CONFIG_INPUT_EVDEV=y +CONFIG_INPUT_KEYRESET=y +# CONFIG_KEYBOARD_ATKBD is not set +CONFIG_KEYBOARD_GOLDFISH_EVENTS=y +# CONFIG_INPUT_MOUSE is not set +CONFIG_INPUT_JOYSTICK=y +CONFIG_JOYSTICK_XPAD=y +CONFIG_JOYSTICK_XPAD_FF=y +CONFIG_JOYSTICK_XPAD_LEDS=y +CONFIG_INPUT_TABLET=y +CONFIG_TABLET_USB_ACECAD=y +CONFIG_TABLET_USB_AIPTEK=y +CONFIG_TABLET_USB_GTCO=y +CONFIG_TABLET_USB_HANWANG=y +CONFIG_TABLET_USB_KBTAB=y +CONFIG_INPUT_TOUCHSCREEN=y +CONFIG_INPUT_MISC=y +CONFIG_INPUT_UINPUT=y +CONFIG_INPUT_GPIO=y +# CONFIG_SERIO is not set +# CONFIG_VT is not set +# CONFIG_LEGACY_PTYS is not set +CONFIG_SERIAL_NONSTANDARD=y +# CONFIG_DEVMEM is not set +# CONFIG_DEVKMEM is not set +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_VIRTIO_CONSOLE=y +CONFIG_NVRAM=y +CONFIG_I2C_I801=y +CONFIG_BATTERY_GOLDFISH=y +CONFIG_WATCHDOG=y +CONFIG_MEDIA_SUPPORT=y +CONFIG_AGP=y +CONFIG_AGP_AMD64=y +CONFIG_AGP_INTEL=y +CONFIG_DRM=y +CONFIG_FB_MODE_HELPERS=y +CONFIG_FB_TILEBLITTING=y +CONFIG_FB_EFI=y +CONFIG_FB_GOLDFISH=y +CONFIG_BACKLIGHT_LCD_SUPPORT=y +# CONFIG_LCD_CLASS_DEVICE is not set +CONFIG_SOUND=y +CONFIG_SND=y +CONFIG_HIDRAW=y +CONFIG_UHID=y +CONFIG_HID_A4TECH=y +CONFIG_HID_ACRUX=y +CONFIG_HID_ACRUX_FF=y +CONFIG_HID_APPLE=y +CONFIG_HID_BELKIN=y +CONFIG_HID_CHERRY=y +CONFIG_HID_CHICONY=y +CONFIG_HID_PRODIKEYS=y +CONFIG_HID_CYPRESS=y +CONFIG_HID_DRAGONRISE=y +CONFIG_DRAGONRISE_FF=y +CONFIG_HID_EMS_FF=y +CONFIG_HID_ELECOM=y +CONFIG_HID_EZKEY=y +CONFIG_HID_HOLTEK=y +CONFIG_HID_KEYTOUCH=y +CONFIG_HID_KYE=y +CONFIG_HID_UCLOGIC=y +CONFIG_HID_WALTOP=y +CONFIG_HID_GYRATION=y +CONFIG_HID_TWINHAN=y +CONFIG_HID_KENSINGTON=y +CONFIG_HID_LCPOWER=y +CONFIG_HID_LOGITECH=y +CONFIG_HID_LOGITECH_DJ=y +CONFIG_LOGITECH_FF=y +CONFIG_LOGIRUMBLEPAD2_FF=y +CONFIG_LOGIG940_FF=y +CONFIG_HID_MAGICMOUSE=y +CONFIG_HID_MICROSOFT=y +CONFIG_HID_MONTEREY=y +CONFIG_HID_MULTITOUCH=y +CONFIG_HID_NTRIG=y +CONFIG_HID_ORTEK=y +CONFIG_HID_PANTHERLORD=y +CONFIG_PANTHERLORD_FF=y +CONFIG_HID_PETALYNX=y +CONFIG_HID_PICOLCD=y +CONFIG_HID_PRIMAX=y +CONFIG_HID_ROCCAT=y +CONFIG_HID_SAITEK=y +CONFIG_HID_SAMSUNG=y +CONFIG_HID_SONY=y +CONFIG_HID_SPEEDLINK=y +CONFIG_HID_SUNPLUS=y +CONFIG_HID_GREENASIA=y +CONFIG_GREENASIA_FF=y +CONFIG_HID_SMARTJOYPLUS=y +CONFIG_SMARTJOYPLUS_FF=y +CONFIG_HID_TIVO=y +CONFIG_HID_TOPSEED=y +CONFIG_HID_THRUSTMASTER=y +CONFIG_HID_WACOM=y +CONFIG_HID_WIIMOTE=y +CONFIG_HID_ZEROPLUS=y +CONFIG_HID_ZYDACRON=y +CONFIG_HID_PID=y +CONFIG_USB_HIDDEV=y +CONFIG_USB_ANNOUNCE_NEW_DEVICES=y +CONFIG_USB_MON=y +CONFIG_USB_EHCI_HCD=y +# CONFIG_USB_EHCI_TT_NEWSCHED is not set +CONFIG_USB_OHCI_HCD=y +CONFIG_USB_UHCI_HCD=y +CONFIG_USB_PRINTER=y +CONFIG_USB_STORAGE=y +CONFIG_USB_OTG_WAKELOCK=y +CONFIG_EDAC=y +CONFIG_RTC_CLASS=y +# CONFIG_RTC_HCTOSYS is not set +CONFIG_DMADEVICES=y +CONFIG_VIRTIO_PCI=y +CONFIG_STAGING=y +CONFIG_ASHMEM=y +CONFIG_ANDROID_LOW_MEMORY_KILLER=y +CONFIG_SYNC=y +CONFIG_SW_SYNC=y +CONFIG_SYNC_FILE=y +CONFIG_ION=y +CONFIG_GOLDFISH_AUDIO=y +CONFIG_SND_HDA_INTEL=y +CONFIG_GOLDFISH=y +CONFIG_GOLDFISH_PIPE=y +CONFIG_GOLDFISH_SYNC=y +CONFIG_ANDROID=y +CONFIG_ANDROID_BINDER_IPC=y +CONFIG_ISCSI_IBFT_FIND=y +CONFIG_EXT4_FS=y +CONFIG_EXT4_FS_SECURITY=y +CONFIG_QUOTA=y +CONFIG_QUOTA_NETLINK_INTERFACE=y +# CONFIG_PRINT_QUOTA_WARNING is not set +CONFIG_FUSE_FS=y +CONFIG_ISO9660_FS=y +CONFIG_JOLIET=y +CONFIG_ZISOFS=y +CONFIG_MSDOS_FS=y +CONFIG_VFAT_FS=y +CONFIG_PROC_KCORE=y +CONFIG_TMPFS=y +CONFIG_TMPFS_POSIX_ACL=y +CONFIG_HUGETLBFS=y +CONFIG_PSTORE=y +CONFIG_PSTORE_CONSOLE=y +CONFIG_PSTORE_RAM=y +# CONFIG_NETWORK_FILESYSTEMS is not set +CONFIG_NLS_DEFAULT="utf8" +CONFIG_NLS_CODEPAGE_437=y +CONFIG_NLS_ASCII=y +CONFIG_NLS_ISO8859_1=y +CONFIG_NLS_UTF8=y +CONFIG_PRINTK_TIME=y +CONFIG_DEBUG_INFO=y +# CONFIG_ENABLE_WARN_DEPRECATED is not set +# CONFIG_ENABLE_MUST_CHECK is not set +CONFIG_FRAME_WARN=2048 +# CONFIG_UNUSED_SYMBOLS is not set +CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_MEMORY_INIT=y +CONFIG_PANIC_TIMEOUT=5 +CONFIG_SCHEDSTATS=y +CONFIG_TIMER_STATS=y +CONFIG_SCHED_TRACER=y +CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_PROVIDE_OHCI1394_DMA_INIT=y +CONFIG_KEYS=y +CONFIG_SECURITY=y +CONFIG_SECURITY_NETWORK=y +CONFIG_SECURITY_SELINUX=y +CONFIG_CRYPTO_AES_586=y +CONFIG_CRYPTO_TWOFISH=y +CONFIG_ASYMMETRIC_KEY_TYPE=y +CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=y +CONFIG_X509_CERTIFICATE_PARSER=y +CONFIG_PKCS7_MESSAGE_PARSER=y +CONFIG_PKCS7_TEST_KEY=y +# CONFIG_VIRTUALIZATION is not set +CONFIG_CRC_T10DIF=y diff --git a/arch/x86/configs/x86_64_cuttlefish_defconfig b/arch/x86/configs/x86_64_cuttlefish_defconfig new file mode 100644 index 000000000000..9bcef659c79e --- /dev/null +++ b/arch/x86/configs/x86_64_cuttlefish_defconfig @@ -0,0 +1,497 @@ +CONFIG_POSIX_MQUEUE=y +# CONFIG_FHANDLE is not set +# CONFIG_USELIB is not set +CONFIG_AUDIT=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_BSD_PROCESS_ACCT=y +CONFIG_TASKSTATS=y +CONFIG_TASK_DELAY_ACCT=y +CONFIG_TASK_XACCT=y +CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_PSI=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_CGROUPS=y +CONFIG_MEMCG=y +CONFIG_MEMCG_SWAP=y +CONFIG_CGROUP_SCHED=y +CONFIG_RT_GROUP_SCHED=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CPUSETS=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_CGROUP_BPF=y +CONFIG_NAMESPACES=y +CONFIG_SCHED_TUNE=y +CONFIG_BLK_DEV_INITRD=y +# CONFIG_RD_LZ4 is not set +CONFIG_KALLSYMS_ALL=y +# CONFIG_PCSPKR_PLATFORM is not set +CONFIG_BPF_SYSCALL=y +CONFIG_BPF_JIT_ALWAYS_ON=y +CONFIG_EMBEDDED=y +# CONFIG_COMPAT_BRK is not set +CONFIG_PROFILING=y +CONFIG_OPROFILE=y +CONFIG_KPROBES=y +CONFIG_JUMP_LABEL=y +CONFIG_CC_STACKPROTECTOR_STRONG=y +CONFIG_REFCOUNT_FULL=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODVERSIONS=y +CONFIG_PARTITION_ADVANCED=y +CONFIG_SMP=y +CONFIG_HYPERVISOR_GUEST=y +CONFIG_PARAVIRT=y +CONFIG_PARAVIRT_SPINLOCKS=y +CONFIG_MCORE2=y +CONFIG_PROCESSOR_SELECT=y +# CONFIG_CPU_SUP_CENTAUR is not set +CONFIG_NR_CPUS=8 +CONFIG_PREEMPT=y +# CONFIG_MICROCODE is not set +CONFIG_X86_MSR=y +CONFIG_X86_CPUID=y +CONFIG_KSM=y +CONFIG_DEFAULT_MMAP_MIN_ADDR=65536 +CONFIG_ZSMALLOC=y +# CONFIG_MTRR is not set +CONFIG_EFI=y +CONFIG_HZ_100=y +CONFIG_KEXEC=y +CONFIG_CRASH_DUMP=y +CONFIG_PHYSICAL_START=0x200000 +CONFIG_PHYSICAL_ALIGN=0x1000000 +CONFIG_CMDLINE_BOOL=y +CONFIG_PM_WAKELOCKS=y +CONFIG_PM_WAKELOCKS_LIMIT=0 +# CONFIG_PM_WAKELOCKS_GC is not set +CONFIG_PM_DEBUG=y +CONFIG_ACPI_PROCFS_POWER=y +# CONFIG_ACPI_FAN is not set +# CONFIG_ACPI_THERMAL is not set +# CONFIG_X86_PM_TIMER is not set +CONFIG_CPU_FREQ_TIMES=y +CONFIG_CPU_FREQ_GOV_ONDEMAND=y +CONFIG_X86_ACPI_CPUFREQ=y +CONFIG_PCI_MMCONFIG=y +CONFIG_PCI_MSI=y +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +CONFIG_BINFMT_MISC=y +CONFIG_IA32_EMULATION=y +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_XFRM_USER=y +CONFIG_XFRM_INTERFACE=y +CONFIG_XFRM_STATISTICS=y +CONFIG_NET_KEY=y +CONFIG_INET=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IP_ROUTE_MULTIPATH=y +CONFIG_IP_ROUTE_VERBOSE=y +CONFIG_NET_IPGRE_DEMUX=y +CONFIG_IP_MROUTE=y +CONFIG_IP_PIMSM_V1=y +CONFIG_IP_PIMSM_V2=y +CONFIG_SYN_COOKIES=y +CONFIG_NET_IPVTI=y +CONFIG_INET_ESP=y +# CONFIG_INET_XFRM_MODE_BEET is not set +CONFIG_INET_UDP_DIAG=y +CONFIG_INET_DIAG_DESTROY=y +CONFIG_TCP_CONG_ADVANCED=y +# CONFIG_TCP_CONG_BIC is not set +# CONFIG_TCP_CONG_WESTWOOD is not set +# CONFIG_TCP_CONG_HTCP is not set +CONFIG_TCP_MD5SIG=y +CONFIG_IPV6_ROUTER_PREF=y +CONFIG_IPV6_ROUTE_INFO=y +CONFIG_IPV6_OPTIMISTIC_DAD=y +CONFIG_INET6_AH=y +CONFIG_INET6_ESP=y +CONFIG_INET6_IPCOMP=y +CONFIG_IPV6_MIP6=y +CONFIG_IPV6_VTI=y +CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_NETLABEL=y +CONFIG_NETFILTER=y +CONFIG_NF_CONNTRACK=y +CONFIG_NF_CONNTRACK_SECMARK=y +CONFIG_NF_CONNTRACK_EVENTS=y +CONFIG_NF_CONNTRACK_AMANDA=y +CONFIG_NF_CONNTRACK_FTP=y +CONFIG_NF_CONNTRACK_H323=y +CONFIG_NF_CONNTRACK_IRC=y +CONFIG_NF_CONNTRACK_NETBIOS_NS=y +CONFIG_NF_CONNTRACK_PPTP=y +CONFIG_NF_CONNTRACK_SANE=y +CONFIG_NF_CONNTRACK_TFTP=y +CONFIG_NF_CT_NETLINK=y +CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y +CONFIG_NETFILTER_XT_TARGET_CONNMARK=y +CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y +CONFIG_NETFILTER_XT_TARGET_CT=y +CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y +CONFIG_NETFILTER_XT_TARGET_MARK=y +CONFIG_NETFILTER_XT_TARGET_NFLOG=y +CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y +CONFIG_NETFILTER_XT_TARGET_TPROXY=y +CONFIG_NETFILTER_XT_TARGET_TRACE=y +CONFIG_NETFILTER_XT_TARGET_SECMARK=y +CONFIG_NETFILTER_XT_TARGET_TCPMSS=y +CONFIG_NETFILTER_XT_MATCH_BPF=y +CONFIG_NETFILTER_XT_MATCH_COMMENT=y +CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y +CONFIG_NETFILTER_XT_MATCH_CONNMARK=y +CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y +CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y +CONFIG_NETFILTER_XT_MATCH_HELPER=y +CONFIG_NETFILTER_XT_MATCH_IPRANGE=y +# CONFIG_NETFILTER_XT_MATCH_L2TP is not set +CONFIG_NETFILTER_XT_MATCH_LENGTH=y +CONFIG_NETFILTER_XT_MATCH_LIMIT=y +CONFIG_NETFILTER_XT_MATCH_MAC=y +CONFIG_NETFILTER_XT_MATCH_MARK=y +CONFIG_NETFILTER_XT_MATCH_OWNER=y +CONFIG_NETFILTER_XT_MATCH_POLICY=y +CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y +CONFIG_NETFILTER_XT_MATCH_QUOTA=y +CONFIG_NETFILTER_XT_MATCH_QUOTA2=y +CONFIG_NETFILTER_XT_MATCH_SOCKET=y +CONFIG_NETFILTER_XT_MATCH_STATE=y +CONFIG_NETFILTER_XT_MATCH_STATISTIC=y +CONFIG_NETFILTER_XT_MATCH_STRING=y +CONFIG_NETFILTER_XT_MATCH_TIME=y +CONFIG_NETFILTER_XT_MATCH_U32=y +CONFIG_NF_CONNTRACK_IPV4=y +CONFIG_NF_SOCKET_IPV4=y +CONFIG_IP_NF_IPTABLES=y +CONFIG_IP_NF_MATCH_AH=y +CONFIG_IP_NF_MATCH_ECN=y +CONFIG_IP_NF_MATCH_TTL=y +CONFIG_IP_NF_FILTER=y +CONFIG_IP_NF_TARGET_REJECT=y +CONFIG_IP_NF_NAT=y +CONFIG_IP_NF_TARGET_MASQUERADE=y +CONFIG_IP_NF_TARGET_NETMAP=y +CONFIG_IP_NF_TARGET_REDIRECT=y +CONFIG_IP_NF_MANGLE=y +CONFIG_IP_NF_RAW=y +CONFIG_IP_NF_SECURITY=y +CONFIG_IP_NF_ARPTABLES=y +CONFIG_IP_NF_ARPFILTER=y +CONFIG_IP_NF_ARP_MANGLE=y +CONFIG_NF_CONNTRACK_IPV6=y +CONFIG_NF_SOCKET_IPV6=y +CONFIG_IP6_NF_IPTABLES=y +CONFIG_IP6_NF_MATCH_IPV6HEADER=y +CONFIG_IP6_NF_MATCH_RPFILTER=y +CONFIG_IP6_NF_FILTER=y +CONFIG_IP6_NF_TARGET_REJECT=y +CONFIG_IP6_NF_MANGLE=y +CONFIG_IP6_NF_RAW=y +CONFIG_L2TP=y +CONFIG_NET_SCHED=y +CONFIG_NET_SCH_HTB=y +CONFIG_NET_SCH_NETEM=y +CONFIG_NET_SCH_INGRESS=y +CONFIG_NET_CLS_U32=y +CONFIG_NET_CLS_BPF=y +CONFIG_NET_EMATCH=y +CONFIG_NET_EMATCH_U32=y +CONFIG_NET_CLS_ACT=y +CONFIG_VSOCKETS=y +CONFIG_VIRTIO_VSOCKETS=y +CONFIG_BPF_JIT=y +CONFIG_CFG80211=y +CONFIG_MAC80211=y +CONFIG_RFKILL=y +CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_DEBUG_DEVRES=y +CONFIG_OF=y +CONFIG_OF_UNITTEST=y +# CONFIG_PNP_DEBUG_MESSAGES is not set +CONFIG_ZRAM=y +CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_LOOP_MIN_COUNT=16 +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_SIZE=8192 +CONFIG_VIRTIO_BLK=y +CONFIG_UID_SYS_STATS=y +CONFIG_SCSI=y +CONFIG_BLK_DEV_SD=y +CONFIG_BLK_DEV_SR=y +CONFIG_BLK_DEV_SR_VENDOR=y +CONFIG_CHR_DEV_SG=y +CONFIG_SCSI_CONSTANTS=y +CONFIG_SCSI_SPI_ATTRS=y +CONFIG_SCSI_VIRTIO=y +CONFIG_MD=y +CONFIG_BLK_DEV_DM=y +CONFIG_DM_CRYPT=y +CONFIG_DM_MIRROR=y +CONFIG_DM_ZERO=y +CONFIG_DM_UEVENT=y +CONFIG_DM_VERITY=y +CONFIG_DM_VERITY_FEC=y +CONFIG_DM_VERITY_AVB=y +CONFIG_DM_BOW=y +CONFIG_NETDEVICES=y +CONFIG_NETCONSOLE=y +CONFIG_NETCONSOLE_DYNAMIC=y +CONFIG_TUN=y +CONFIG_VIRTIO_NET=y +# CONFIG_ETHERNET is not set +CONFIG_PPP=y +CONFIG_PPP_BSDCOMP=y +CONFIG_PPP_DEFLATE=y +CONFIG_PPP_MPPE=y +CONFIG_PPTP=y +CONFIG_PPPOL2TP=y +CONFIG_USB_RTL8152=y +CONFIG_USB_USBNET=y +# CONFIG_USB_NET_AX8817X is not set +# CONFIG_USB_NET_AX88179_178A is not set +# CONFIG_USB_NET_CDCETHER is not set +# CONFIG_USB_NET_CDC_NCM is not set +# CONFIG_USB_NET_NET1080 is not set +# CONFIG_USB_NET_CDC_SUBSET is not set +# CONFIG_USB_NET_ZAURUS is not set +# CONFIG_WLAN_VENDOR_ADMTEK is not set +# CONFIG_WLAN_VENDOR_ATH is not set +# CONFIG_WLAN_VENDOR_ATMEL is not set +# CONFIG_WLAN_VENDOR_BROADCOM is not set +# CONFIG_WLAN_VENDOR_CISCO is not set +# CONFIG_WLAN_VENDOR_INTEL is not set +# CONFIG_WLAN_VENDOR_INTERSIL is not set +# CONFIG_WLAN_VENDOR_MARVELL is not set +# CONFIG_WLAN_VENDOR_MEDIATEK is not set +# CONFIG_WLAN_VENDOR_RALINK is not set +# CONFIG_WLAN_VENDOR_REALTEK is not set +# CONFIG_WLAN_VENDOR_RSI is not set +# CONFIG_WLAN_VENDOR_ST is not set +# CONFIG_WLAN_VENDOR_TI is not set +# CONFIG_WLAN_VENDOR_ZYDAS is not set +# CONFIG_WLAN_VENDOR_QUANTENNA is not set +CONFIG_MAC80211_HWSIM=y +CONFIG_VIRT_WIFI=y +CONFIG_INPUT_MOUSEDEV=y +CONFIG_INPUT_EVDEV=y +CONFIG_INPUT_KEYRESET=y +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +CONFIG_INPUT_JOYSTICK=y +CONFIG_JOYSTICK_XPAD=y +CONFIG_JOYSTICK_XPAD_FF=y +CONFIG_JOYSTICK_XPAD_LEDS=y +CONFIG_INPUT_TABLET=y +CONFIG_TABLET_USB_ACECAD=y +CONFIG_TABLET_USB_AIPTEK=y +CONFIG_TABLET_USB_GTCO=y +CONFIG_TABLET_USB_HANWANG=y +CONFIG_TABLET_USB_KBTAB=y +CONFIG_INPUT_MISC=y +CONFIG_INPUT_UINPUT=y +CONFIG_INPUT_GPIO=y +# CONFIG_SERIO_I8042 is not set +# CONFIG_VT is not set +# CONFIG_LEGACY_PTYS is not set +# CONFIG_DEVMEM is not set +CONFIG_SERIAL_8250=y +# CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set +CONFIG_SERIAL_8250_CONSOLE=y +# CONFIG_SERIAL_8250_EXAR is not set +CONFIG_SERIAL_8250_NR_UARTS=48 +CONFIG_SERIAL_8250_EXTENDED=y +CONFIG_SERIAL_8250_MANY_PORTS=y +CONFIG_SERIAL_8250_SHARE_IRQ=y +CONFIG_VIRTIO_CONSOLE=y +CONFIG_HW_RANDOM=y +# CONFIG_HW_RANDOM_INTEL is not set +# CONFIG_HW_RANDOM_AMD is not set +# CONFIG_HW_RANDOM_VIA is not set +CONFIG_HW_RANDOM_VIRTIO=y +CONFIG_HPET=y +# CONFIG_HPET_MMAP_DEFAULT is not set +# CONFIG_DEVPORT is not set +# CONFIG_ACPI_I2C_OPREGION is not set +# CONFIG_I2C_COMPAT is not set +# CONFIG_I2C_HELPER_AUTO is not set +CONFIG_PTP_1588_CLOCK=y +# CONFIG_HWMON is not set +# CONFIG_X86_PKG_TEMP_THERMAL is not set +CONFIG_WATCHDOG=y +CONFIG_SOFT_WATCHDOG=y +CONFIG_MEDIA_SUPPORT=y +# CONFIG_VGA_ARB is not set +CONFIG_DRM=y +# CONFIG_DRM_FBDEV_EMULATION is not set +CONFIG_DRM_VIRTIO_GPU=y +CONFIG_SOUND=y +CONFIG_SND=y +CONFIG_SND_HRTIMER=y +# CONFIG_SND_SUPPORT_OLD_API is not set +# CONFIG_SND_VERBOSE_PROCFS is not set +# CONFIG_SND_DRIVERS is not set +CONFIG_SND_INTEL8X0=y +# CONFIG_SND_USB is not set +CONFIG_HIDRAW=y +CONFIG_UHID=y +CONFIG_HID_A4TECH=y +CONFIG_HID_ACRUX=y +CONFIG_HID_ACRUX_FF=y +CONFIG_HID_APPLE=y +CONFIG_HID_BELKIN=y +CONFIG_HID_CHERRY=y +CONFIG_HID_CHICONY=y +CONFIG_HID_PRODIKEYS=y +CONFIG_HID_CYPRESS=y +CONFIG_HID_DRAGONRISE=y +CONFIG_DRAGONRISE_FF=y +CONFIG_HID_EMS_FF=y +CONFIG_HID_ELECOM=y +CONFIG_HID_EZKEY=y +CONFIG_HID_HOLTEK=y +CONFIG_HID_KEYTOUCH=y +CONFIG_HID_KYE=y +CONFIG_HID_UCLOGIC=y +CONFIG_HID_WALTOP=y +CONFIG_HID_GYRATION=y +CONFIG_HID_TWINHAN=y +CONFIG_HID_KENSINGTON=y +CONFIG_HID_LCPOWER=y +CONFIG_HID_LOGITECH=y +CONFIG_HID_LOGITECH_DJ=y +CONFIG_LOGITECH_FF=y +CONFIG_LOGIRUMBLEPAD2_FF=y +CONFIG_LOGIG940_FF=y +CONFIG_HID_MAGICMOUSE=y +CONFIG_HID_MICROSOFT=y +CONFIG_HID_MONTEREY=y +CONFIG_HID_MULTITOUCH=y +CONFIG_HID_NTRIG=y +CONFIG_HID_ORTEK=y +CONFIG_HID_PANTHERLORD=y +CONFIG_PANTHERLORD_FF=y +CONFIG_HID_PETALYNX=y +CONFIG_HID_PICOLCD=y +CONFIG_HID_PRIMAX=y +CONFIG_HID_ROCCAT=y +CONFIG_HID_SAITEK=y +CONFIG_HID_SAMSUNG=y +CONFIG_HID_SONY=y +CONFIG_HID_SPEEDLINK=y +CONFIG_HID_SUNPLUS=y +CONFIG_HID_GREENASIA=y +CONFIG_GREENASIA_FF=y +CONFIG_HID_SMARTJOYPLUS=y +CONFIG_SMARTJOYPLUS_FF=y +CONFIG_HID_TIVO=y +CONFIG_HID_TOPSEED=y +CONFIG_HID_THRUSTMASTER=y +CONFIG_HID_WACOM=y +CONFIG_HID_WIIMOTE=y +CONFIG_HID_ZEROPLUS=y +CONFIG_HID_ZYDACRON=y +CONFIG_USB_HIDDEV=y +CONFIG_USB_ANNOUNCE_NEW_DEVICES=y +CONFIG_USB_EHCI_HCD=y +CONFIG_USB_GADGET=y +CONFIG_USB_DUMMY_HCD=y +CONFIG_USB_CONFIGFS=y +CONFIG_USB_CONFIGFS_F_FS=y +CONFIG_USB_CONFIGFS_F_ACC=y +CONFIG_USB_CONFIGFS_F_AUDIO_SRC=y +CONFIG_USB_CONFIGFS_UEVENT=y +CONFIG_USB_CONFIGFS_F_MIDI=y +CONFIG_RTC_CLASS=y +CONFIG_RTC_DRV_TEST=y +CONFIG_SW_SYNC=y +CONFIG_VIRTIO_PCI=y +CONFIG_VIRTIO_BALLOON=y +CONFIG_VIRTIO_INPUT=y +CONFIG_VIRTIO_MMIO=y +CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y +CONFIG_STAGING=y +CONFIG_ASHMEM=y +CONFIG_ANDROID_VSOC=y +CONFIG_ION=y +CONFIG_ION_SYSTEM_HEAP=y +# CONFIG_X86_PLATFORM_DEVICES is not set +# CONFIG_IOMMU_SUPPORT is not set +CONFIG_ANDROID=y +CONFIG_ANDROID_BINDER_IPC=y +# CONFIG_FIRMWARE_MEMMAP is not set +CONFIG_EXT4_FS=y +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_EXT4_FS_SECURITY=y +CONFIG_EXT4_ENCRYPTION=y +CONFIG_F2FS_FS=y +CONFIG_F2FS_FS_SECURITY=y +CONFIG_F2FS_FS_ENCRYPTION=y +CONFIG_QUOTA=y +CONFIG_QUOTA_NETLINK_INTERFACE=y +# CONFIG_PRINT_QUOTA_WARNING is not set +CONFIG_QFMT_V2=y +CONFIG_AUTOFS4_FS=y +CONFIG_FUSE_FS=y +CONFIG_OVERLAY_FS=y +CONFIG_MSDOS_FS=y +CONFIG_VFAT_FS=y +CONFIG_PROC_KCORE=y +CONFIG_TMPFS=y +CONFIG_TMPFS_POSIX_ACL=y +CONFIG_HUGETLBFS=y +# CONFIG_EFIVAR_FS is not set +CONFIG_SDCARD_FS=y +CONFIG_PSTORE=y +CONFIG_PSTORE_CONSOLE=y +CONFIG_PSTORE_RAM=y +CONFIG_NLS_DEFAULT="utf8" +CONFIG_NLS_CODEPAGE_437=y +CONFIG_NLS_ASCII=y +CONFIG_NLS_ISO8859_1=y +CONFIG_NLS_UTF8=y +CONFIG_PRINTK_TIME=y +CONFIG_DEBUG_INFO=y +# CONFIG_ENABLE_WARN_DEPRECATED is not set +# CONFIG_ENABLE_MUST_CHECK is not set +CONFIG_FRAME_WARN=1024 +# CONFIG_UNUSED_SYMBOLS is not set +CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_STACK_USAGE=y +CONFIG_DEBUG_MEMORY_INIT=y +CONFIG_DEBUG_STACKOVERFLOW=y +CONFIG_HARDLOCKUP_DETECTOR=y +CONFIG_PANIC_TIMEOUT=5 +CONFIG_SCHEDSTATS=y +CONFIG_RCU_CPU_STALL_TIMEOUT=60 +CONFIG_ENABLE_DEFAULT_TRACERS=y +CONFIG_IO_DELAY_NONE=y +CONFIG_DEBUG_BOOT_PARAMS=y +CONFIG_OPTIMIZE_INLINING=y +CONFIG_UNWINDER_FRAME_POINTER=y +CONFIG_SECURITY_PERF_EVENTS_RESTRICT=y +CONFIG_SECURITY=y +CONFIG_SECURITY_NETWORK=y +CONFIG_SECURITY_PATH=y +CONFIG_HARDENED_USERCOPY=y +CONFIG_SECURITY_SELINUX=y +CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE=1 +CONFIG_CRYPTO_RSA=y +# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set +CONFIG_CRYPTO_ADIANTUM=y +CONFIG_CRYPTO_SHA512=y +CONFIG_CRYPTO_AES_NI_INTEL=y +CONFIG_CRYPTO_LZ4=y +CONFIG_CRYPTO_ZSTD=y +CONFIG_CRYPTO_DEV_VIRTIO=y +CONFIG_ASYMMETRIC_KEY_TYPE=y +CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=y +CONFIG_X509_CERTIFICATE_PARSER=y +CONFIG_SYSTEM_TRUSTED_KEYRING=y +CONFIG_SYSTEM_TRUSTED_KEYS="verity_dev_keys.x509" diff --git a/arch/x86/configs/x86_64_ranchu_defconfig b/arch/x86/configs/x86_64_ranchu_defconfig new file mode 100644 index 000000000000..964b93d9ee18 --- /dev/null +++ b/arch/x86/configs/x86_64_ranchu_defconfig @@ -0,0 +1,416 @@ +# CONFIG_LOCALVERSION_AUTO is not set +CONFIG_POSIX_MQUEUE=y +CONFIG_AUDIT=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_BSD_PROCESS_ACCT=y +CONFIG_TASKSTATS=y +CONFIG_TASK_DELAY_ACCT=y +CONFIG_TASK_XACCT=y +CONFIG_TASK_IO_ACCOUNTING=y +CONFIG_CGROUPS=y +CONFIG_CGROUP_DEBUG=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_CGROUP_SCHED=y +CONFIG_RT_GROUP_SCHED=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y +CONFIG_SYSCTL_SYSCALL=y +CONFIG_KALLSYMS_ALL=y +CONFIG_EMBEDDED=y +# CONFIG_COMPAT_BRK is not set +CONFIG_ARCH_MMAP_RND_BITS=32 +CONFIG_ARCH_MMAP_RND_COMPAT_BITS=16 +CONFIG_PARTITION_ADVANCED=y +CONFIG_OSF_PARTITION=y +CONFIG_AMIGA_PARTITION=y +CONFIG_MAC_PARTITION=y +CONFIG_BSD_DISKLABEL=y +CONFIG_MINIX_SUBPARTITION=y +CONFIG_SOLARIS_X86_PARTITION=y +CONFIG_UNIXWARE_DISKLABEL=y +CONFIG_SGI_PARTITION=y +CONFIG_SUN_PARTITION=y +CONFIG_KARMA_PARTITION=y +CONFIG_SMP=y +CONFIG_MCORE2=y +CONFIG_MAXSMP=y +CONFIG_PREEMPT=y +# CONFIG_X86_MCE is not set +CONFIG_X86_MSR=y +CONFIG_X86_CPUID=y +CONFIG_KSM=y +CONFIG_CMA=y +# CONFIG_MTRR_SANITIZER is not set +CONFIG_EFI=y +CONFIG_EFI_STUB=y +CONFIG_HZ_100=y +CONFIG_PHYSICAL_START=0x100000 +CONFIG_PM_AUTOSLEEP=y +CONFIG_PM_WAKELOCKS=y +CONFIG_PM_WAKELOCKS_LIMIT=0 +# CONFIG_PM_WAKELOCKS_GC is not set +CONFIG_PM_DEBUG=y +CONFIG_CPU_FREQ=y +# CONFIG_CPU_FREQ_STAT is not set +CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y +CONFIG_CPU_FREQ_GOV_USERSPACE=y +CONFIG_PCI_MMCONFIG=y +CONFIG_PCIEPORTBUS=y +# CONFIG_PCIEASPM is not set +CONFIG_PCCARD=y +CONFIG_YENTA=y +CONFIG_HOTPLUG_PCI=y +# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set +CONFIG_BINFMT_MISC=y +CONFIG_IA32_EMULATION=y +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_UNIX=y +CONFIG_XFRM_USER=y +CONFIG_NET_KEY=y +CONFIG_INET=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IP_ROUTE_MULTIPATH=y +CONFIG_IP_ROUTE_VERBOSE=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +CONFIG_IP_PNP_RARP=y +CONFIG_IP_MROUTE=y +CONFIG_IP_PIMSM_V1=y +CONFIG_IP_PIMSM_V2=y +CONFIG_SYN_COOKIES=y +CONFIG_INET_ESP=y +# CONFIG_INET_XFRM_MODE_BEET is not set +# CONFIG_INET_LRO is not set +CONFIG_INET_DIAG_DESTROY=y +CONFIG_IPV6_ROUTER_PREF=y +CONFIG_IPV6_ROUTE_INFO=y +CONFIG_IPV6_OPTIMISTIC_DAD=y +CONFIG_INET6_AH=y +CONFIG_INET6_ESP=y +CONFIG_INET6_IPCOMP=y +CONFIG_IPV6_MIP6=y +CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_NETLABEL=y +CONFIG_NETFILTER=y +CONFIG_NF_CONNTRACK=y +CONFIG_NF_CONNTRACK_SECMARK=y +CONFIG_NF_CONNTRACK_EVENTS=y +CONFIG_NF_CT_PROTO_DCCP=y +CONFIG_NF_CT_PROTO_SCTP=y +CONFIG_NF_CT_PROTO_UDPLITE=y +CONFIG_NF_CONNTRACK_AMANDA=y +CONFIG_NF_CONNTRACK_FTP=y +CONFIG_NF_CONNTRACK_H323=y +CONFIG_NF_CONNTRACK_IRC=y +CONFIG_NF_CONNTRACK_NETBIOS_NS=y +CONFIG_NF_CONNTRACK_PPTP=y +CONFIG_NF_CONNTRACK_SANE=y +CONFIG_NF_CONNTRACK_TFTP=y +CONFIG_NF_CT_NETLINK=y +CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y +CONFIG_NETFILTER_XT_TARGET_CONNMARK=y +CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y +CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y +CONFIG_NETFILTER_XT_TARGET_MARK=y +CONFIG_NETFILTER_XT_TARGET_NFLOG=y +CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y +CONFIG_NETFILTER_XT_TARGET_TPROXY=y +CONFIG_NETFILTER_XT_TARGET_TRACE=y +CONFIG_NETFILTER_XT_TARGET_SECMARK=y +CONFIG_NETFILTER_XT_TARGET_TCPMSS=y +CONFIG_NETFILTER_XT_MATCH_COMMENT=y +CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y +CONFIG_NETFILTER_XT_MATCH_CONNMARK=y +CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y +CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y +CONFIG_NETFILTER_XT_MATCH_HELPER=y +CONFIG_NETFILTER_XT_MATCH_IPRANGE=y +CONFIG_NETFILTER_XT_MATCH_LENGTH=y +CONFIG_NETFILTER_XT_MATCH_LIMIT=y +CONFIG_NETFILTER_XT_MATCH_MAC=y +CONFIG_NETFILTER_XT_MATCH_MARK=y +CONFIG_NETFILTER_XT_MATCH_OWNER=y +CONFIG_NETFILTER_XT_MATCH_POLICY=y +CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y +CONFIG_NETFILTER_XT_MATCH_QUOTA=y +CONFIG_NETFILTER_XT_MATCH_QUOTA2=y +CONFIG_NETFILTER_XT_MATCH_SOCKET=y +CONFIG_NETFILTER_XT_MATCH_STATE=y +CONFIG_NETFILTER_XT_MATCH_STATISTIC=y +CONFIG_NETFILTER_XT_MATCH_STRING=y +CONFIG_NETFILTER_XT_MATCH_TIME=y +CONFIG_NETFILTER_XT_MATCH_U32=y +CONFIG_NF_CONNTRACK_IPV4=y +CONFIG_IP_NF_IPTABLES=y +CONFIG_IP_NF_MATCH_AH=y +CONFIG_IP_NF_MATCH_ECN=y +CONFIG_IP_NF_MATCH_TTL=y +CONFIG_IP_NF_FILTER=y +CONFIG_IP_NF_TARGET_REJECT=y +CONFIG_IP_NF_MANGLE=y +CONFIG_IP_NF_RAW=y +CONFIG_IP_NF_SECURITY=y +CONFIG_IP_NF_ARPTABLES=y +CONFIG_IP_NF_ARPFILTER=y +CONFIG_IP_NF_ARP_MANGLE=y +CONFIG_NF_CONNTRACK_IPV6=y +CONFIG_IP6_NF_IPTABLES=y +CONFIG_IP6_NF_FILTER=y +CONFIG_IP6_NF_TARGET_REJECT=y +CONFIG_IP6_NF_MANGLE=y +CONFIG_IP6_NF_RAW=y +CONFIG_NET_SCHED=y +CONFIG_NET_SCH_HTB=y +CONFIG_NET_CLS_U32=y +CONFIG_NET_EMATCH=y +CONFIG_NET_EMATCH_U32=y +CONFIG_NET_CLS_ACT=y +CONFIG_CFG80211=y +CONFIG_MAC80211=y +CONFIG_MAC80211_LEDS=y +CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_DMA_CMA=y +CONFIG_CONNECTOR=y +CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_SIZE=8192 +CONFIG_VIRTIO_BLK=y +CONFIG_BLK_DEV_SD=y +CONFIG_BLK_DEV_SR=y +CONFIG_BLK_DEV_SR_VENDOR=y +CONFIG_CHR_DEV_SG=y +CONFIG_SCSI_CONSTANTS=y +CONFIG_SCSI_SPI_ATTRS=y +CONFIG_SCSI_ISCSI_ATTRS=y +# CONFIG_SCSI_LOWLEVEL is not set +CONFIG_ATA=y +CONFIG_SATA_AHCI=y +CONFIG_ATA_PIIX=y +CONFIG_PATA_AMD=y +CONFIG_PATA_OLDPIIX=y +CONFIG_PATA_SCH=y +CONFIG_PATA_MPIIX=y +CONFIG_ATA_GENERIC=y +CONFIG_MD=y +CONFIG_BLK_DEV_MD=y +CONFIG_BLK_DEV_DM=y +CONFIG_DM_DEBUG=y +CONFIG_DM_CRYPT=y +CONFIG_DM_MIRROR=y +CONFIG_DM_ZERO=y +CONFIG_DM_UEVENT=y +CONFIG_DM_VERITY=y +CONFIG_DM_VERITY_FEC=y +CONFIG_NETDEVICES=y +CONFIG_NETCONSOLE=y +CONFIG_TUN=y +CONFIG_VIRTIO_NET=y +CONFIG_BNX2=y +CONFIG_TIGON3=y +CONFIG_NET_TULIP=y +CONFIG_E100=y +CONFIG_E1000=y +CONFIG_E1000E=y +CONFIG_SKY2=y +CONFIG_NE2K_PCI=y +CONFIG_FORCEDETH=y +CONFIG_8139TOO=y +# CONFIG_8139TOO_PIO is not set +CONFIG_R8169=y +CONFIG_FDDI=y +CONFIG_PPP=y +CONFIG_PPP_BSDCOMP=y +CONFIG_PPP_DEFLATE=y +CONFIG_PPP_MPPE=y +CONFIG_USB_USBNET=y +CONFIG_INPUT_POLLDEV=y +# CONFIG_INPUT_MOUSEDEV_PSAUX is not set +CONFIG_INPUT_EVDEV=y +CONFIG_INPUT_KEYRESET=y +# CONFIG_KEYBOARD_ATKBD is not set +CONFIG_KEYBOARD_GOLDFISH_EVENTS=y +# CONFIG_INPUT_MOUSE is not set +CONFIG_INPUT_JOYSTICK=y +CONFIG_JOYSTICK_XPAD=y +CONFIG_JOYSTICK_XPAD_FF=y +CONFIG_JOYSTICK_XPAD_LEDS=y +CONFIG_INPUT_TABLET=y +CONFIG_TABLET_USB_ACECAD=y +CONFIG_TABLET_USB_AIPTEK=y +CONFIG_TABLET_USB_GTCO=y +CONFIG_TABLET_USB_HANWANG=y +CONFIG_TABLET_USB_KBTAB=y +CONFIG_INPUT_TOUCHSCREEN=y +CONFIG_INPUT_MISC=y +CONFIG_INPUT_UINPUT=y +CONFIG_INPUT_GPIO=y +# CONFIG_SERIO is not set +# CONFIG_VT is not set +# CONFIG_LEGACY_PTYS is not set +CONFIG_SERIAL_NONSTANDARD=y +# CONFIG_DEVMEM is not set +# CONFIG_DEVKMEM is not set +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_VIRTIO_CONSOLE=y +CONFIG_NVRAM=y +CONFIG_I2C_I801=y +CONFIG_BATTERY_GOLDFISH=y +CONFIG_WATCHDOG=y +CONFIG_MEDIA_SUPPORT=y +CONFIG_AGP=y +CONFIG_AGP_AMD64=y +CONFIG_AGP_INTEL=y +CONFIG_DRM=y +CONFIG_FB_MODE_HELPERS=y +CONFIG_FB_TILEBLITTING=y +CONFIG_FB_EFI=y +CONFIG_FB_GOLDFISH=y +CONFIG_BACKLIGHT_LCD_SUPPORT=y +# CONFIG_LCD_CLASS_DEVICE is not set +CONFIG_SOUND=y +CONFIG_SND=y +CONFIG_HIDRAW=y +CONFIG_UHID=y +CONFIG_HID_A4TECH=y +CONFIG_HID_ACRUX=y +CONFIG_HID_ACRUX_FF=y +CONFIG_HID_APPLE=y +CONFIG_HID_BELKIN=y +CONFIG_HID_CHERRY=y +CONFIG_HID_CHICONY=y +CONFIG_HID_PRODIKEYS=y +CONFIG_HID_CYPRESS=y +CONFIG_HID_DRAGONRISE=y +CONFIG_DRAGONRISE_FF=y +CONFIG_HID_EMS_FF=y +CONFIG_HID_ELECOM=y +CONFIG_HID_EZKEY=y +CONFIG_HID_HOLTEK=y +CONFIG_HID_KEYTOUCH=y +CONFIG_HID_KYE=y +CONFIG_HID_UCLOGIC=y +CONFIG_HID_WALTOP=y +CONFIG_HID_GYRATION=y +CONFIG_HID_TWINHAN=y +CONFIG_HID_KENSINGTON=y +CONFIG_HID_LCPOWER=y +CONFIG_HID_LOGITECH=y +CONFIG_HID_LOGITECH_DJ=y +CONFIG_LOGITECH_FF=y +CONFIG_LOGIRUMBLEPAD2_FF=y +CONFIG_LOGIG940_FF=y +CONFIG_HID_MAGICMOUSE=y +CONFIG_HID_MICROSOFT=y +CONFIG_HID_MONTEREY=y +CONFIG_HID_MULTITOUCH=y +CONFIG_HID_NTRIG=y +CONFIG_HID_ORTEK=y +CONFIG_HID_PANTHERLORD=y +CONFIG_PANTHERLORD_FF=y +CONFIG_HID_PETALYNX=y +CONFIG_HID_PICOLCD=y +CONFIG_HID_PRIMAX=y +CONFIG_HID_ROCCAT=y +CONFIG_HID_SAITEK=y +CONFIG_HID_SAMSUNG=y +CONFIG_HID_SONY=y +CONFIG_HID_SPEEDLINK=y +CONFIG_HID_SUNPLUS=y +CONFIG_HID_GREENASIA=y +CONFIG_GREENASIA_FF=y +CONFIG_HID_SMARTJOYPLUS=y +CONFIG_SMARTJOYPLUS_FF=y +CONFIG_HID_TIVO=y +CONFIG_HID_TOPSEED=y +CONFIG_HID_THRUSTMASTER=y +CONFIG_HID_WACOM=y +CONFIG_HID_WIIMOTE=y +CONFIG_HID_ZEROPLUS=y +CONFIG_HID_ZYDACRON=y +CONFIG_HID_PID=y +CONFIG_USB_HIDDEV=y +CONFIG_USB_ANNOUNCE_NEW_DEVICES=y +CONFIG_USB_MON=y +CONFIG_USB_EHCI_HCD=y +# CONFIG_USB_EHCI_TT_NEWSCHED is not set +CONFIG_USB_OHCI_HCD=y +CONFIG_USB_UHCI_HCD=y +CONFIG_USB_PRINTER=y +CONFIG_USB_STORAGE=y +CONFIG_USB_OTG_WAKELOCK=y +CONFIG_EDAC=y +CONFIG_RTC_CLASS=y +# CONFIG_RTC_HCTOSYS is not set +CONFIG_DMADEVICES=y +CONFIG_VIRTIO_PCI=y +CONFIG_STAGING=y +CONFIG_ASHMEM=y +CONFIG_ANDROID_LOW_MEMORY_KILLER=y +CONFIG_SYNC=y +CONFIG_SW_SYNC=y +CONFIG_SYNC_FILE=y +CONFIG_ION=y +CONFIG_GOLDFISH_AUDIO=y +CONFIG_SND_HDA_INTEL=y +CONFIG_GOLDFISH=y +CONFIG_GOLDFISH_PIPE=y +CONFIG_GOLDFISH_SYNC=y +CONFIG_ANDROID=y +CONFIG_ANDROID_BINDER_IPC=y +CONFIG_ISCSI_IBFT_FIND=y +CONFIG_EXT4_FS=y +CONFIG_EXT4_FS_SECURITY=y +CONFIG_QUOTA=y +CONFIG_QUOTA_NETLINK_INTERFACE=y +# CONFIG_PRINT_QUOTA_WARNING is not set +CONFIG_FUSE_FS=y +CONFIG_ISO9660_FS=y +CONFIG_JOLIET=y +CONFIG_ZISOFS=y +CONFIG_MSDOS_FS=y +CONFIG_VFAT_FS=y +CONFIG_PROC_KCORE=y +CONFIG_TMPFS=y +CONFIG_TMPFS_POSIX_ACL=y +CONFIG_HUGETLBFS=y +CONFIG_PSTORE=y +CONFIG_PSTORE_CONSOLE=y +CONFIG_PSTORE_RAM=y +# CONFIG_NETWORK_FILESYSTEMS is not set +CONFIG_NLS_DEFAULT="utf8" +CONFIG_NLS_CODEPAGE_437=y +CONFIG_NLS_ASCII=y +CONFIG_NLS_ISO8859_1=y +CONFIG_NLS_UTF8=y +CONFIG_PRINTK_TIME=y +CONFIG_DEBUG_INFO=y +# CONFIG_ENABLE_WARN_DEPRECATED is not set +# CONFIG_ENABLE_MUST_CHECK is not set +# CONFIG_UNUSED_SYMBOLS is not set +CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_MEMORY_INIT=y +CONFIG_PANIC_TIMEOUT=5 +CONFIG_SCHEDSTATS=y +CONFIG_TIMER_STATS=y +CONFIG_SCHED_TRACER=y +CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_PROVIDE_OHCI1394_DMA_INIT=y +CONFIG_KEYS=y +CONFIG_SECURITY=y +CONFIG_SECURITY_NETWORK=y +CONFIG_SECURITY_SELINUX=y +CONFIG_CRYPTO_TWOFISH=y +CONFIG_ASYMMETRIC_KEY_TYPE=y +CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=y +CONFIG_X509_CERTIFICATE_PARSER=y +CONFIG_PKCS7_MESSAGE_PARSER=y +CONFIG_PKCS7_TEST_KEY=y +# CONFIG_VIRTUALIZATION is not set +CONFIG_CRC_T10DIF=y diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha20_glue.c index 1e6af1b35f7b..dfc91b938323 100644 --- a/arch/x86/crypto/chacha20_glue.c +++ b/arch/x86/crypto/chacha20_glue.c @@ -10,7 +10,7 @@ */ #include <crypto/algapi.h> -#include <crypto/chacha20.h> +#include <crypto/chacha.h> #include <crypto/internal/skcipher.h> #include <linux/kernel.h> #include <linux/module.h> @@ -29,31 +29,31 @@ static bool chacha20_use_avx2; static void chacha20_dosimd(u32 *state, u8 *dst, const u8 *src, unsigned int bytes) { - u8 buf[CHACHA20_BLOCK_SIZE]; + u8 buf[CHACHA_BLOCK_SIZE]; #ifdef CONFIG_AS_AVX2 if (chacha20_use_avx2) { - while (bytes >= CHACHA20_BLOCK_SIZE * 8) { + while (bytes >= CHACHA_BLOCK_SIZE * 8) { chacha20_8block_xor_avx2(state, dst, src); - bytes -= CHACHA20_BLOCK_SIZE * 8; - src += CHACHA20_BLOCK_SIZE * 8; - dst += CHACHA20_BLOCK_SIZE * 8; + bytes -= CHACHA_BLOCK_SIZE * 8; + src += CHACHA_BLOCK_SIZE * 8; + dst += CHACHA_BLOCK_SIZE * 8; state[12] += 8; } } #endif - while (bytes >= CHACHA20_BLOCK_SIZE * 4) { + while (bytes >= CHACHA_BLOCK_SIZE * 4) { chacha20_4block_xor_ssse3(state, dst, src); - bytes -= CHACHA20_BLOCK_SIZE * 4; - src += CHACHA20_BLOCK_SIZE * 4; - dst += CHACHA20_BLOCK_SIZE * 4; + bytes -= CHACHA_BLOCK_SIZE * 4; + src += CHACHA_BLOCK_SIZE * 4; + dst += CHACHA_BLOCK_SIZE * 4; state[12] += 4; } - while (bytes >= CHACHA20_BLOCK_SIZE) { + while (bytes >= CHACHA_BLOCK_SIZE) { chacha20_block_xor_ssse3(state, dst, src); - bytes -= CHACHA20_BLOCK_SIZE; - src += CHACHA20_BLOCK_SIZE; - dst += CHACHA20_BLOCK_SIZE; + bytes -= CHACHA_BLOCK_SIZE; + src += CHACHA_BLOCK_SIZE; + dst += CHACHA_BLOCK_SIZE; state[12]++; } if (bytes) { @@ -66,7 +66,7 @@ static void chacha20_dosimd(u32 *state, u8 *dst, const u8 *src, static int chacha20_simd(struct skcipher_request *req) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct chacha20_ctx *ctx = crypto_skcipher_ctx(tfm); + struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); u32 *state, state_buf[16 + 2] __aligned(8); struct skcipher_walk walk; int err; @@ -74,20 +74,20 @@ static int chacha20_simd(struct skcipher_request *req) BUILD_BUG_ON(CHACHA20_STATE_ALIGN != 16); state = PTR_ALIGN(state_buf + 0, CHACHA20_STATE_ALIGN); - if (req->cryptlen <= CHACHA20_BLOCK_SIZE || !may_use_simd()) - return crypto_chacha20_crypt(req); + if (req->cryptlen <= CHACHA_BLOCK_SIZE || !may_use_simd()) + return crypto_chacha_crypt(req); err = skcipher_walk_virt(&walk, req, true); - crypto_chacha20_init(state, ctx, walk.iv); + crypto_chacha_init(state, ctx, walk.iv); kernel_fpu_begin(); - while (walk.nbytes >= CHACHA20_BLOCK_SIZE) { + while (walk.nbytes >= CHACHA_BLOCK_SIZE) { chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr, - rounddown(walk.nbytes, CHACHA20_BLOCK_SIZE)); + rounddown(walk.nbytes, CHACHA_BLOCK_SIZE)); err = skcipher_walk_done(&walk, - walk.nbytes % CHACHA20_BLOCK_SIZE); + walk.nbytes % CHACHA_BLOCK_SIZE); } if (walk.nbytes) { @@ -106,14 +106,14 @@ static struct skcipher_alg alg = { .base.cra_driver_name = "chacha20-simd", .base.cra_priority = 300, .base.cra_blocksize = 1, - .base.cra_ctxsize = sizeof(struct chacha20_ctx), + .base.cra_ctxsize = sizeof(struct chacha_ctx), .base.cra_alignmask = sizeof(u32) - 1, .base.cra_module = THIS_MODULE, - .min_keysize = CHACHA20_KEY_SIZE, - .max_keysize = CHACHA20_KEY_SIZE, - .ivsize = CHACHA20_IV_SIZE, - .chunksize = CHACHA20_BLOCK_SIZE, + .min_keysize = CHACHA_KEY_SIZE, + .max_keysize = CHACHA_KEY_SIZE, + .ivsize = CHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, .setkey = crypto_chacha20_setkey, .encrypt = chacha20_simd, .decrypt = chacha20_simd, diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c index 28c372003e44..a69670b5b849 100644 --- a/arch/x86/crypto/poly1305_glue.c +++ b/arch/x86/crypto/poly1305_glue.c @@ -83,35 +83,37 @@ static unsigned int poly1305_simd_blocks(struct poly1305_desc_ctx *dctx, if (poly1305_use_avx2 && srclen >= POLY1305_BLOCK_SIZE * 4) { if (unlikely(!sctx->wset)) { if (!sctx->uset) { - memcpy(sctx->u, dctx->r, sizeof(sctx->u)); - poly1305_simd_mult(sctx->u, dctx->r); + memcpy(sctx->u, dctx->r.r, sizeof(sctx->u)); + poly1305_simd_mult(sctx->u, dctx->r.r); sctx->uset = true; } memcpy(sctx->u + 5, sctx->u, sizeof(sctx->u)); - poly1305_simd_mult(sctx->u + 5, dctx->r); + poly1305_simd_mult(sctx->u + 5, dctx->r.r); memcpy(sctx->u + 10, sctx->u + 5, sizeof(sctx->u)); - poly1305_simd_mult(sctx->u + 10, dctx->r); + poly1305_simd_mult(sctx->u + 10, dctx->r.r); sctx->wset = true; } blocks = srclen / (POLY1305_BLOCK_SIZE * 4); - poly1305_4block_avx2(dctx->h, src, dctx->r, blocks, sctx->u); + poly1305_4block_avx2(dctx->h.h, src, dctx->r.r, blocks, + sctx->u); src += POLY1305_BLOCK_SIZE * 4 * blocks; srclen -= POLY1305_BLOCK_SIZE * 4 * blocks; } #endif if (likely(srclen >= POLY1305_BLOCK_SIZE * 2)) { if (unlikely(!sctx->uset)) { - memcpy(sctx->u, dctx->r, sizeof(sctx->u)); - poly1305_simd_mult(sctx->u, dctx->r); + memcpy(sctx->u, dctx->r.r, sizeof(sctx->u)); + poly1305_simd_mult(sctx->u, dctx->r.r); sctx->uset = true; } blocks = srclen / (POLY1305_BLOCK_SIZE * 2); - poly1305_2block_sse2(dctx->h, src, dctx->r, blocks, sctx->u); + poly1305_2block_sse2(dctx->h.h, src, dctx->r.r, blocks, + sctx->u); src += POLY1305_BLOCK_SIZE * 2 * blocks; srclen -= POLY1305_BLOCK_SIZE * 2 * blocks; } if (srclen >= POLY1305_BLOCK_SIZE) { - poly1305_block_sse2(dctx->h, src, dctx->r, 1); + poly1305_block_sse2(dctx->h.h, src, dctx->r.r, 1); srclen -= POLY1305_BLOCK_SIZE; } return srclen; diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index b034826a0b3b..21be0193d9dc 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -287,7 +287,7 @@ recompute_jump(struct alt_instr *a, u8 *orig_insn, u8 *repl_insn, u8 *insnbuf) tgt_rip = next_rip + o_dspl; n_dspl = tgt_rip - orig_insn; - DPRINTK("target RIP: %p, new_displ: 0x%x", tgt_rip, n_dspl); + DPRINTK("target RIP: %px, new_displ: 0x%x", tgt_rip, n_dspl); if (tgt_rip - orig_insn >= 0) { if (n_dspl - 2 <= 127) @@ -344,7 +344,7 @@ static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *ins add_nops(instr + (a->instrlen - a->padlen), a->padlen); local_irq_restore(flags); - DUMP_BYTES(instr, a->instrlen, "%p: [%d:%d) optimized NOPs: ", + DUMP_BYTES(instr, a->instrlen, "%px: [%d:%d) optimized NOPs: ", instr, a->instrlen - a->padlen, a->padlen); } @@ -365,7 +365,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, u8 *instr, *replacement; u8 insnbuf[MAX_PATCH_LEN]; - DPRINTK("alt table %p -> %p", start, end); + DPRINTK("alt table %px, -> %px", start, end); /* * The scan order should be from start to end. A later scanned * alternative code can overwrite previously scanned alternative code. @@ -389,14 +389,14 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, continue; } - DPRINTK("feat: %d*32+%d, old: (%p, len: %d), repl: (%p, len: %d), pad: %d", + DPRINTK("feat: %d*32+%d, old: (%px len: %d), repl: (%px, len: %d), pad: %d", a->cpuid >> 5, a->cpuid & 0x1f, instr, a->instrlen, replacement, a->replacementlen, a->padlen); - DUMP_BYTES(instr, a->instrlen, "%p: old_insn: ", instr); - DUMP_BYTES(replacement, a->replacementlen, "%p: rpl_insn: ", replacement); + DUMP_BYTES(instr, a->instrlen, "%px: old_insn: ", instr); + DUMP_BYTES(replacement, a->replacementlen, "%px: rpl_insn: ", replacement); memcpy(insnbuf, replacement, a->replacementlen); insnbuf_sz = a->replacementlen; @@ -422,7 +422,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, a->instrlen - a->replacementlen); insnbuf_sz += a->instrlen - a->replacementlen; } - DUMP_BYTES(insnbuf, insnbuf_sz, "%p: final_insn: ", instr); + DUMP_BYTES(insnbuf, insnbuf_sz, "%px: final_insn: ", instr); text_poke_early(instr, insnbuf, insnbuf_sz); } diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 1789626cf95e..d3df6fa5dc63 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -877,7 +877,7 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code, if (!printk_ratelimit()) return; - printk("%s%s[%d]: segfault at %lx ip %p sp %p error %lx", + printk("%s%s[%d]: segfault at %lx ip %px sp %px error %lx", task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG, tsk->comm, task_pid_nr(tsk), address, (void *)regs->ip, (void *)regs->sp, error_code); diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index abff76bda9e6..a7a7677265b6 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -592,7 +592,7 @@ enum __force_cpu_type { static int force_cpu_type; -static int set_cpu_type(const char *str, struct kernel_param *kp) +static int set_cpu_type(const char *str, const struct kernel_param *kp) { if (!strcmp(str, "timer")) { force_cpu_type = timer; diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index f779d2a5b04c..41fd4c123165 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -431,6 +431,7 @@ static void xen_pv_play_dead(void) /* used only with HOTPLUG_CPU */ * data back is to call: */ tick_nohz_idle_enter(); + tick_nohz_idle_stop_tick_protected(); cpuhp_online_idle(CPUHP_AP_ONLINE_IDLE); } diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 9c4f1c496c90..8df0fecac3a8 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -225,6 +225,7 @@ struct cfq_group_data { unsigned int weight; unsigned int leaf_weight; + u64 group_idle; }; /* This is per cgroup per device grouping structure */ @@ -310,6 +311,7 @@ struct cfq_group { struct cfq_queue *async_cfqq[2][IOPRIO_BE_NR]; struct cfq_queue *async_idle_cfqq; + u64 group_idle; }; struct cfq_io_cq { @@ -802,6 +804,17 @@ static inline void cfqg_stats_update_completion(struct cfq_group *cfqg, #endif /* CONFIG_CFQ_GROUP_IOSCHED */ +static inline u64 get_group_idle(struct cfq_data *cfqd) +{ +#ifdef CONFIG_CFQ_GROUP_IOSCHED + struct cfq_queue *cfqq = cfqd->active_queue; + + if (cfqq && cfqq->cfqg) + return cfqq->cfqg->group_idle; +#endif + return cfqd->cfq_group_idle; +} + #define cfq_log(cfqd, fmt, args...) \ blk_add_trace_msg((cfqd)->queue, "cfq " fmt, ##args) @@ -822,7 +835,7 @@ static inline bool cfq_io_thinktime_big(struct cfq_data *cfqd, if (!sample_valid(ttime->ttime_samples)) return false; if (group_idle) - slice = cfqd->cfq_group_idle; + slice = get_group_idle(cfqd); else slice = cfqd->cfq_slice_idle; return ttime->ttime_mean > slice; @@ -1589,6 +1602,7 @@ static void cfq_cpd_init(struct blkcg_policy_data *cpd) cgd->weight = weight; cgd->leaf_weight = weight; + cgd->group_idle = cfq_group_idle; } static void cfq_cpd_free(struct blkcg_policy_data *cpd) @@ -1633,6 +1647,7 @@ static void cfq_pd_init(struct blkg_policy_data *pd) cfqg->weight = cgd->weight; cfqg->leaf_weight = cgd->leaf_weight; + cfqg->group_idle = cgd->group_idle; } static void cfq_pd_offline(struct blkg_policy_data *pd) @@ -1754,6 +1769,19 @@ static int cfq_print_leaf_weight(struct seq_file *sf, void *v) return 0; } +static int cfq_print_group_idle(struct seq_file *sf, void *v) +{ + struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); + struct cfq_group_data *cgd = blkcg_to_cfqgd(blkcg); + u64 val = 0; + + if (cgd) + val = cgd->group_idle; + + seq_printf(sf, "%llu\n", div_u64(val, NSEC_PER_USEC)); + return 0; +} + static ssize_t __cfqg_set_weight_device(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off, bool on_dfl, bool is_leaf_weight) @@ -1875,6 +1903,37 @@ static int cfq_set_leaf_weight(struct cgroup_subsys_state *css, return __cfq_set_weight(css, val, false, false, true); } +static int cfq_set_group_idle(struct cgroup_subsys_state *css, + struct cftype *cft, u64 val) +{ + struct blkcg *blkcg = css_to_blkcg(css); + struct cfq_group_data *cfqgd; + struct blkcg_gq *blkg; + int ret = 0; + + spin_lock_irq(&blkcg->lock); + cfqgd = blkcg_to_cfqgd(blkcg); + if (!cfqgd) { + ret = -EINVAL; + goto out; + } + + cfqgd->group_idle = val * NSEC_PER_USEC; + + hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { + struct cfq_group *cfqg = blkg_to_cfqg(blkg); + + if (!cfqg) + continue; + + cfqg->group_idle = cfqgd->group_idle; + } + +out: + spin_unlock_irq(&blkcg->lock); + return ret; +} + static int cfqg_print_stat(struct seq_file *sf, void *v) { blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat, @@ -2020,6 +2079,11 @@ static struct cftype cfq_blkcg_legacy_files[] = { .seq_show = cfq_print_leaf_weight, .write_u64 = cfq_set_leaf_weight, }, + { + .name = "group_idle", + .seq_show = cfq_print_group_idle, + .write_u64 = cfq_set_group_idle, + }, /* statistics, covers only the tasks in the cfqg */ { @@ -2914,7 +2978,7 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd) * with sync vs async workloads. */ if (blk_queue_nonrot(cfqd->queue) && cfqd->hw_tag && - !cfqd->cfq_group_idle) + !get_group_idle(cfqd)) return; WARN_ON(!RB_EMPTY_ROOT(&cfqq->sort_list)); @@ -2925,9 +2989,8 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd) */ if (!cfq_should_idle(cfqd, cfqq)) { /* no queue idling. Check for group idling */ - if (cfqd->cfq_group_idle) - group_idle = cfqd->cfq_group_idle; - else + group_idle = get_group_idle(cfqd); + if (!group_idle) return; } @@ -2968,7 +3031,7 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd) cfq_mark_cfqq_wait_request(cfqq); if (group_idle) - sl = cfqd->cfq_group_idle; + sl = group_idle; else sl = cfqd->cfq_slice_idle; @@ -3317,7 +3380,7 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd) * this group, wait for requests to complete. */ check_group_idle: - if (cfqd->cfq_group_idle && cfqq->cfqg->nr_cfqq == 1 && + if (get_group_idle(cfqd) && cfqq->cfqg->nr_cfqq == 1 && cfqq->cfqg->dispatched && !cfq_io_thinktime_big(cfqd, &cfqq->cfqg->ttime, true)) { cfqq = NULL; @@ -3880,7 +3943,7 @@ cfq_update_io_thinktime(struct cfq_data *cfqd, struct cfq_queue *cfqq, cfqd->cfq_slice_idle); } #ifdef CONFIG_CFQ_GROUP_IOSCHED - __cfq_update_io_thinktime(&cfqq->cfqg->ttime, cfqd->cfq_group_idle); + __cfq_update_io_thinktime(&cfqq->cfqg->ttime, get_group_idle(cfqd)); #endif } @@ -4278,7 +4341,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq) if (cfq_should_wait_busy(cfqd, cfqq)) { u64 extend_sl = cfqd->cfq_slice_idle; if (!cfqd->cfq_slice_idle) - extend_sl = cfqd->cfq_group_idle; + extend_sl = get_group_idle(cfqd); cfqq->slice_end = now + extend_sl; cfq_mark_cfqq_wait_busy(cfqq); cfq_log_cfqq(cfqd, cfqq, "will busy wait"); diff --git a/build.config.aarch64 b/build.config.aarch64 new file mode 100644 index 000000000000..523bbc0449f7 --- /dev/null +++ b/build.config.aarch64 @@ -0,0 +1,11 @@ +ARCH=arm64 + +CLANG_TRIPLE=aarch64-linux-gnu- +CROSS_COMPILE=aarch64-linux-androidkernel- +LINUX_GCC_CROSS_COMPILE_PREBUILTS_BIN=prebuilts/gcc/linux-x86/aarch64/aarch64-linux-android-4.9/bin + +FILES=" +arch/arm64/boot/Image.gz +vmlinux +System.map +" diff --git a/build.config.common b/build.config.common new file mode 100644 index 000000000000..2024f6312f01 --- /dev/null +++ b/build.config.common @@ -0,0 +1,9 @@ +BRANCH=android-4.14-q +KERNEL_DIR=common + +CC=clang +CLANG_PREBUILT_BIN=prebuilts-master/clang/host/linux-x86/clang-r365631c/bin +BUILDTOOLS_PREBUILT_BIN=build/build-tools/path/linux-x86 + +EXTRA_CMDS='' +STOP_SHIP_TRACEPRINTK=1 diff --git a/build.config.cuttlefish.aarch64 b/build.config.cuttlefish.aarch64 new file mode 100644 index 000000000000..0cb601958972 --- /dev/null +++ b/build.config.cuttlefish.aarch64 @@ -0,0 +1,5 @@ +. ${ROOT_DIR}/common/build.config.common +. ${ROOT_DIR}/common/build.config.aarch64 + +DEFCONFIG=cuttlefish_defconfig +POST_DEFCONFIG_CMDS="check_defconfig" diff --git a/build.config.cuttlefish.x86_64 b/build.config.cuttlefish.x86_64 new file mode 100644 index 000000000000..fed773ccc64a --- /dev/null +++ b/build.config.cuttlefish.x86_64 @@ -0,0 +1,5 @@ +. ${ROOT_DIR}/common/build.config.common +. ${ROOT_DIR}/common/build.config.x86_64 + +DEFCONFIG=x86_64_cuttlefish_defconfig +POST_DEFCONFIG_CMDS="check_defconfig" diff --git a/build.config.goldfish.arm b/build.config.goldfish.arm new file mode 100644 index 000000000000..ff5646ab4f40 --- /dev/null +++ b/build.config.goldfish.arm @@ -0,0 +1,13 @@ +ARCH=arm +BRANCH=android-4.4 +CROSS_COMPILE=arm-linux-androidkernel- +DEFCONFIG=ranchu_defconfig +EXTRA_CMDS='' +KERNEL_DIR=common +LINUX_GCC_CROSS_COMPILE_PREBUILTS_BIN=prebuilts/gcc/linux-x86/arm/arm-linux-androideabi-4.9/bin +FILES=" +arch/arm/boot/zImage +vmlinux +System.map +" +STOP_SHIP_TRACEPRINTK=1 diff --git a/build.config.goldfish.arm64 b/build.config.goldfish.arm64 new file mode 100644 index 000000000000..4c896a679ab9 --- /dev/null +++ b/build.config.goldfish.arm64 @@ -0,0 +1,13 @@ +ARCH=arm64 +BRANCH=android-4.4 +CROSS_COMPILE=aarch64-linux-android- +DEFCONFIG=ranchu64_defconfig +EXTRA_CMDS='' +KERNEL_DIR=common +LINUX_GCC_CROSS_COMPILE_PREBUILTS_BIN=prebuilts/gcc/linux-x86/aarch64/aarch64-linux-android-4.9/bin +FILES=" +arch/arm64/boot/Image +vmlinux +System.map +" +STOP_SHIP_TRACEPRINTK=1 diff --git a/build.config.goldfish.mips b/build.config.goldfish.mips new file mode 100644 index 000000000000..9a14a444ac14 --- /dev/null +++ b/build.config.goldfish.mips @@ -0,0 +1,12 @@ +ARCH=mips +BRANCH=android-4.4 +CROSS_COMPILE=mips64el-linux-android- +DEFCONFIG=ranchu_defconfig +EXTRA_CMDS='' +KERNEL_DIR=common +LINUX_GCC_CROSS_COMPILE_PREBUILTS_BIN=prebuilts/gcc/linux-x86/mips/mips64el-linux-android-4.9/bin +FILES=" +vmlinux +System.map +" +STOP_SHIP_TRACEPRINTK=1 diff --git a/build.config.goldfish.mips64 b/build.config.goldfish.mips64 new file mode 100644 index 000000000000..6ad9759f5f4a --- /dev/null +++ b/build.config.goldfish.mips64 @@ -0,0 +1,12 @@ +ARCH=mips +BRANCH=android-4.4 +CROSS_COMPILE=mips64el-linux-android- +DEFCONFIG=ranchu64_defconfig +EXTRA_CMDS='' +KERNEL_DIR=common +LINUX_GCC_CROSS_COMPILE_PREBUILTS_BIN=prebuilts/gcc/linux-x86/mips/mips64el-linux-android-4.9/bin +FILES=" +vmlinux +System.map +" +STOP_SHIP_TRACEPRINTK=1 diff --git a/build.config.goldfish.x86 b/build.config.goldfish.x86 new file mode 100644 index 000000000000..2266c621835e --- /dev/null +++ b/build.config.goldfish.x86 @@ -0,0 +1,13 @@ +ARCH=x86 +BRANCH=android-4.4 +CROSS_COMPILE=x86_64-linux-android- +DEFCONFIG=i386_ranchu_defconfig +EXTRA_CMDS='' +KERNEL_DIR=common +LINUX_GCC_CROSS_COMPILE_PREBUILTS_BIN=prebuilts/gcc/linux-x86/x86/x86_64-linux-android-4.9/bin +FILES=" +arch/x86/boot/bzImage +vmlinux +System.map +" +STOP_SHIP_TRACEPRINTK=1 diff --git a/build.config.goldfish.x86_64 b/build.config.goldfish.x86_64 new file mode 100644 index 000000000000..08c42c2eba03 --- /dev/null +++ b/build.config.goldfish.x86_64 @@ -0,0 +1,13 @@ +ARCH=x86_64 +BRANCH=android-4.4 +CROSS_COMPILE=x86_64-linux-android- +DEFCONFIG=x86_64_ranchu_defconfig +EXTRA_CMDS='' +KERNEL_DIR=common +LINUX_GCC_CROSS_COMPILE_PREBUILTS_BIN=prebuilts/gcc/linux-x86/x86/x86_64-linux-android-4.9/bin +FILES=" +arch/x86/boot/bzImage +vmlinux +System.map +" +STOP_SHIP_TRACEPRINTK=1 diff --git a/build.config.x86_64 b/build.config.x86_64 new file mode 100644 index 000000000000..df73a47e7220 --- /dev/null +++ b/build.config.x86_64 @@ -0,0 +1,11 @@ +ARCH=x86_64 + +CLANG_TRIPLE=x86_64-linux-gnu- +CROSS_COMPILE=x86_64-linux-androidkernel- +LINUX_GCC_CROSS_COMPILE_PREBUILTS_BIN=prebuilts/gcc/linux-x86/x86/x86_64-linux-android-4.9/bin + +FILES=" +arch/x86/boot/bzImage +vmlinux +System.map +" diff --git a/certs/system_keyring.c b/certs/system_keyring.c index 81728717523d..4ba922ff3db6 100644 --- a/certs/system_keyring.c +++ b/certs/system_keyring.c @@ -264,5 +264,46 @@ error: return ret; } EXPORT_SYMBOL_GPL(verify_pkcs7_signature); - #endif /* CONFIG_SYSTEM_DATA_VERIFICATION */ + +/** + * verify_signature_one - Verify a signature with keys from given keyring + * @sig: The signature to be verified + * @trusted_keys: Trusted keys to use (NULL for builtin trusted keys only, + * (void *)1UL for all trusted keys). + * @keyid: key description (not partial) + */ +int verify_signature_one(const struct public_key_signature *sig, + struct key *trusted_keys, const char *keyid) +{ + key_ref_t ref; + struct key *key; + int ret; + + if (!sig) + return -EBADMSG; + if (!trusted_keys) { + trusted_keys = builtin_trusted_keys; + } else if (trusted_keys == (void *)1UL) { +#ifdef CONFIG_SECONDARY_TRUSTED_KEYRING + trusted_keys = secondary_trusted_keys; +#else + trusted_keys = builtin_trusted_keys; +#endif + } + + ref = keyring_search(make_key_ref(trusted_keys, 1), + &key_type_asymmetric, keyid); + if (IS_ERR(ref)) { + pr_err("Asymmetric key (%s) not found in keyring(%s)\n", + keyid, trusted_keys->description); + return -ENOKEY; + } + + key = key_ref_to_ptr(ref); + ret = verify_signature(key, sig); + key_put(key); + return ret; +} +EXPORT_SYMBOL_GPL(verify_signature_one); + diff --git a/crypto/Kconfig b/crypto/Kconfig index 84f99f8eca4b..edee90887ef6 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -389,6 +389,34 @@ config CRYPTO_KEYWRAP Support for key wrapping (NIST SP800-38F / RFC3394) without padding. +config CRYPTO_NHPOLY1305 + tristate + select CRYPTO_HASH + select CRYPTO_POLY1305 + +config CRYPTO_ADIANTUM + tristate "Adiantum support" + select CRYPTO_CHACHA20 + select CRYPTO_POLY1305 + select CRYPTO_NHPOLY1305 + help + Adiantum is a tweakable, length-preserving encryption mode + designed for fast and secure disk encryption, especially on + CPUs without dedicated crypto instructions. It encrypts + each sector using the XChaCha12 stream cipher, two passes of + an ε-almost-∆-universal hash function, and an invocation of + the AES-256 block cipher on a single 16-byte block. On CPUs + without AES instructions, Adiantum is much faster than + AES-XTS. + + Adiantum's security is provably reducible to that of its + underlying stream and block ciphers, subject to a security + bound. Unlike XTS, Adiantum is a true wide-block encryption + mode, so it actually provides an even stronger notion of + security than XTS, subject to the security bound. + + If unsure, say N. + comment "Hash modes" config CRYPTO_CMAC @@ -1326,18 +1354,26 @@ config CRYPTO_SALSA20 Bernstein <djb@cr.yp.to>. See <http://cr.yp.to/snuffle.html> config CRYPTO_CHACHA20 - tristate "ChaCha20 cipher algorithm" + tristate "ChaCha stream cipher algorithms" select CRYPTO_BLKCIPHER help - ChaCha20 cipher algorithm, RFC7539. + The ChaCha20, XChaCha20, and XChaCha12 stream cipher algorithms. ChaCha20 is a 256-bit high-speed stream cipher designed by Daniel J. Bernstein and further specified in RFC7539 for use in IETF protocols. - This is the portable C implementation of ChaCha20. - - See also: + This is the portable C implementation of ChaCha20. See also: <http://cr.yp.to/chacha/chacha-20080128.pdf> + XChaCha20 is the application of the XSalsa20 construction to ChaCha20 + rather than to Salsa20. XChaCha20 extends ChaCha20's nonce length + from 64 bits (or 96 bits using the RFC7539 convention) to 192 bits, + while provably retaining ChaCha20's security. See also: + <https://cr.yp.to/snuffle/xsalsa-20081128.pdf> + + XChaCha12 is XChaCha20 reduced to 12 rounds, with correspondingly + reduced security margin but increased performance. It can be needed + in some performance-sensitive scenarios. + config CRYPTO_CHACHA20_X86_64 tristate "ChaCha20 cipher algorithm (x86_64/SSSE3/AVX2)" depends on X86 && 64BIT @@ -1638,6 +1674,15 @@ config CRYPTO_LZ4HC help This is the LZ4 high compression mode algorithm. +config CRYPTO_ZSTD + tristate "Zstd compression algorithm" + select CRYPTO_ALGAPI + select CRYPTO_ACOMP2 + select ZSTD_COMPRESS + select ZSTD_DECOMPRESS + help + This is the zstd algorithm. + comment "Random Number Generation" config CRYPTO_ANSI_CPRNG diff --git a/crypto/Makefile b/crypto/Makefile index 56282e2d75ad..3bbd4103accb 100644 --- a/crypto/Makefile +++ b/crypto/Makefile @@ -83,6 +83,8 @@ obj-$(CONFIG_CRYPTO_LRW) += lrw.o obj-$(CONFIG_CRYPTO_XTS) += xts.o obj-$(CONFIG_CRYPTO_CTR) += ctr.o obj-$(CONFIG_CRYPTO_KEYWRAP) += keywrap.o +obj-$(CONFIG_CRYPTO_ADIANTUM) += adiantum.o +obj-$(CONFIG_CRYPTO_NHPOLY1305) += nhpoly1305.o obj-$(CONFIG_CRYPTO_GCM) += gcm.o obj-$(CONFIG_CRYPTO_CCM) += ccm.o obj-$(CONFIG_CRYPTO_CHACHA20POLY1305) += chacha20poly1305.o @@ -110,7 +112,7 @@ obj-$(CONFIG_CRYPTO_KHAZAD) += khazad.o obj-$(CONFIG_CRYPTO_ANUBIS) += anubis.o obj-$(CONFIG_CRYPTO_SEED) += seed.o obj-$(CONFIG_CRYPTO_SALSA20) += salsa20_generic.o -obj-$(CONFIG_CRYPTO_CHACHA20) += chacha20_generic.o +obj-$(CONFIG_CRYPTO_CHACHA20) += chacha_generic.o obj-$(CONFIG_CRYPTO_POLY1305) += poly1305_generic.o obj-$(CONFIG_CRYPTO_DEFLATE) += deflate.o obj-$(CONFIG_CRYPTO_MICHAEL_MIC) += michael_mic.o @@ -135,6 +137,7 @@ obj-$(CONFIG_CRYPTO_USER_API_HASH) += algif_hash.o obj-$(CONFIG_CRYPTO_USER_API_SKCIPHER) += algif_skcipher.o obj-$(CONFIG_CRYPTO_USER_API_RNG) += algif_rng.o obj-$(CONFIG_CRYPTO_USER_API_AEAD) += algif_aead.o +obj-$(CONFIG_CRYPTO_ZSTD) += zstd.o ecdh_generic-y := ecc.o ecdh_generic-y += ecdh.o diff --git a/crypto/adiantum.c b/crypto/adiantum.c new file mode 100644 index 000000000000..5564e73266a6 --- /dev/null +++ b/crypto/adiantum.c @@ -0,0 +1,668 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Adiantum length-preserving encryption mode + * + * Copyright 2018 Google LLC + */ + +/* + * Adiantum is a tweakable, length-preserving encryption mode designed for fast + * and secure disk encryption, especially on CPUs without dedicated crypto + * instructions. Adiantum encrypts each sector using the XChaCha12 stream + * cipher, two passes of an ε-almost-∆-universal (ε-∆U) hash function based on + * NH and Poly1305, and an invocation of the AES-256 block cipher on a single + * 16-byte block. See the paper for details: + * + * Adiantum: length-preserving encryption for entry-level processors + * (https://eprint.iacr.org/2018/720.pdf) + * + * For flexibility, this implementation also allows other ciphers: + * + * - Stream cipher: XChaCha12 or XChaCha20 + * - Block cipher: any with a 128-bit block size and 256-bit key + * + * This implementation doesn't currently allow other ε-∆U hash functions, i.e. + * HPolyC is not supported. This is because Adiantum is ~20% faster than HPolyC + * but still provably as secure, and also the ε-∆U hash function of HBSH is + * formally defined to take two inputs (tweak, message) which makes it difficult + * to wrap with the crypto_shash API. Rather, some details need to be handled + * here. Nevertheless, if needed in the future, support for other ε-∆U hash + * functions could be added here. + */ + +#include <crypto/b128ops.h> +#include <crypto/chacha.h> +#include <crypto/internal/hash.h> +#include <crypto/internal/skcipher.h> +#include <crypto/nhpoly1305.h> +#include <crypto/scatterwalk.h> +#include <linux/module.h> + +#include "internal.h" + +/* + * Size of right-hand part of input data, in bytes; also the size of the block + * cipher's block size and the hash function's output. + */ +#define BLOCKCIPHER_BLOCK_SIZE 16 + +/* Size of the block cipher key (K_E) in bytes */ +#define BLOCKCIPHER_KEY_SIZE 32 + +/* Size of the hash key (K_H) in bytes */ +#define HASH_KEY_SIZE (POLY1305_BLOCK_SIZE + NHPOLY1305_KEY_SIZE) + +/* + * The specification allows variable-length tweaks, but Linux's crypto API + * currently only allows algorithms to support a single length. The "natural" + * tweak length for Adiantum is 16, since that fits into one Poly1305 block for + * the best performance. But longer tweaks are useful for fscrypt, to avoid + * needing to derive per-file keys. So instead we use two blocks, or 32 bytes. + */ +#define TWEAK_SIZE 32 + +struct adiantum_instance_ctx { + struct crypto_skcipher_spawn streamcipher_spawn; + struct crypto_spawn blockcipher_spawn; + struct crypto_shash_spawn hash_spawn; +}; + +struct adiantum_tfm_ctx { + struct crypto_skcipher *streamcipher; + struct crypto_cipher *blockcipher; + struct crypto_shash *hash; + struct poly1305_key header_hash_key; +}; + +struct adiantum_request_ctx { + + /* + * Buffer for right-hand part of data, i.e. + * + * P_L => P_M => C_M => C_R when encrypting, or + * C_R => C_M => P_M => P_L when decrypting. + * + * Also used to build the IV for the stream cipher. + */ + union { + u8 bytes[XCHACHA_IV_SIZE]; + __le32 words[XCHACHA_IV_SIZE / sizeof(__le32)]; + le128 bignum; /* interpret as element of Z/(2^{128}Z) */ + } rbuf; + + bool enc; /* true if encrypting, false if decrypting */ + + /* + * The result of the Poly1305 ε-∆U hash function applied to + * (bulk length, tweak) + */ + le128 header_hash; + + /* Sub-requests, must be last */ + union { + struct shash_desc hash_desc; + struct skcipher_request streamcipher_req; + } u; +}; + +/* + * Given the XChaCha stream key K_S, derive the block cipher key K_E and the + * hash key K_H as follows: + * + * K_E || K_H || ... = XChaCha(key=K_S, nonce=1||0^191) + * + * Note that this denotes using bits from the XChaCha keystream, which here we + * get indirectly by encrypting a buffer containing all 0's. + */ +static int adiantum_setkey(struct crypto_skcipher *tfm, const u8 *key, + unsigned int keylen) +{ + struct adiantum_tfm_ctx *tctx = crypto_skcipher_ctx(tfm); + struct { + u8 iv[XCHACHA_IV_SIZE]; + u8 derived_keys[BLOCKCIPHER_KEY_SIZE + HASH_KEY_SIZE]; + struct scatterlist sg; + struct crypto_wait wait; + struct skcipher_request req; /* must be last */ + } *data; + u8 *keyp; + int err; + + /* Set the stream cipher key (K_S) */ + crypto_skcipher_clear_flags(tctx->streamcipher, CRYPTO_TFM_REQ_MASK); + crypto_skcipher_set_flags(tctx->streamcipher, + crypto_skcipher_get_flags(tfm) & + CRYPTO_TFM_REQ_MASK); + err = crypto_skcipher_setkey(tctx->streamcipher, key, keylen); + crypto_skcipher_set_flags(tfm, + crypto_skcipher_get_flags(tctx->streamcipher) & + CRYPTO_TFM_RES_MASK); + if (err) + return err; + + /* Derive the subkeys */ + data = kzalloc(sizeof(*data) + + crypto_skcipher_reqsize(tctx->streamcipher), GFP_KERNEL); + if (!data) + return -ENOMEM; + data->iv[0] = 1; + sg_init_one(&data->sg, data->derived_keys, sizeof(data->derived_keys)); + crypto_init_wait(&data->wait); + skcipher_request_set_tfm(&data->req, tctx->streamcipher); + skcipher_request_set_callback(&data->req, CRYPTO_TFM_REQ_MAY_SLEEP | + CRYPTO_TFM_REQ_MAY_BACKLOG, + crypto_req_done, &data->wait); + skcipher_request_set_crypt(&data->req, &data->sg, &data->sg, + sizeof(data->derived_keys), data->iv); + err = crypto_wait_req(crypto_skcipher_encrypt(&data->req), &data->wait); + if (err) + goto out; + keyp = data->derived_keys; + + /* Set the block cipher key (K_E) */ + crypto_cipher_clear_flags(tctx->blockcipher, CRYPTO_TFM_REQ_MASK); + crypto_cipher_set_flags(tctx->blockcipher, + crypto_skcipher_get_flags(tfm) & + CRYPTO_TFM_REQ_MASK); + err = crypto_cipher_setkey(tctx->blockcipher, keyp, + BLOCKCIPHER_KEY_SIZE); + crypto_skcipher_set_flags(tfm, + crypto_cipher_get_flags(tctx->blockcipher) & + CRYPTO_TFM_RES_MASK); + if (err) + goto out; + keyp += BLOCKCIPHER_KEY_SIZE; + + /* Set the hash key (K_H) */ + poly1305_core_setkey(&tctx->header_hash_key, keyp); + keyp += POLY1305_BLOCK_SIZE; + + crypto_shash_clear_flags(tctx->hash, CRYPTO_TFM_REQ_MASK); + crypto_shash_set_flags(tctx->hash, crypto_skcipher_get_flags(tfm) & + CRYPTO_TFM_REQ_MASK); + err = crypto_shash_setkey(tctx->hash, keyp, NHPOLY1305_KEY_SIZE); + crypto_skcipher_set_flags(tfm, crypto_shash_get_flags(tctx->hash) & + CRYPTO_TFM_RES_MASK); + keyp += NHPOLY1305_KEY_SIZE; + WARN_ON(keyp != &data->derived_keys[ARRAY_SIZE(data->derived_keys)]); +out: + kzfree(data); + return err; +} + +/* Addition in Z/(2^{128}Z) */ +static inline void le128_add(le128 *r, const le128 *v1, const le128 *v2) +{ + u64 x = le64_to_cpu(v1->b); + u64 y = le64_to_cpu(v2->b); + + r->b = cpu_to_le64(x + y); + r->a = cpu_to_le64(le64_to_cpu(v1->a) + le64_to_cpu(v2->a) + + (x + y < x)); +} + +/* Subtraction in Z/(2^{128}Z) */ +static inline void le128_sub(le128 *r, const le128 *v1, const le128 *v2) +{ + u64 x = le64_to_cpu(v1->b); + u64 y = le64_to_cpu(v2->b); + + r->b = cpu_to_le64(x - y); + r->a = cpu_to_le64(le64_to_cpu(v1->a) - le64_to_cpu(v2->a) - + (x - y > x)); +} + +/* + * Apply the Poly1305 ε-∆U hash function to (bulk length, tweak) and save the + * result to rctx->header_hash. This is the calculation + * + * H_T ← Poly1305_{K_T}(bin_{128}(|L|) || T) + * + * from the procedure in section 6.4 of the Adiantum paper. The resulting value + * is reused in both the first and second hash steps. Specifically, it's added + * to the result of an independently keyed ε-∆U hash function (for equal length + * inputs only) taken over the left-hand part (the "bulk") of the message, to + * give the overall Adiantum hash of the (tweak, left-hand part) pair. + */ +static void adiantum_hash_header(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + const struct adiantum_tfm_ctx *tctx = crypto_skcipher_ctx(tfm); + struct adiantum_request_ctx *rctx = skcipher_request_ctx(req); + const unsigned int bulk_len = req->cryptlen - BLOCKCIPHER_BLOCK_SIZE; + struct { + __le64 message_bits; + __le64 padding; + } header = { + .message_bits = cpu_to_le64((u64)bulk_len * 8) + }; + struct poly1305_state state; + + poly1305_core_init(&state); + + BUILD_BUG_ON(sizeof(header) % POLY1305_BLOCK_SIZE != 0); + poly1305_core_blocks(&state, &tctx->header_hash_key, + &header, sizeof(header) / POLY1305_BLOCK_SIZE); + + BUILD_BUG_ON(TWEAK_SIZE % POLY1305_BLOCK_SIZE != 0); + poly1305_core_blocks(&state, &tctx->header_hash_key, req->iv, + TWEAK_SIZE / POLY1305_BLOCK_SIZE); + + poly1305_core_emit(&state, &rctx->header_hash); +} + +/* Hash the left-hand part (the "bulk") of the message using NHPoly1305 */ +static int adiantum_hash_message(struct skcipher_request *req, + struct scatterlist *sgl, le128 *digest) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + const struct adiantum_tfm_ctx *tctx = crypto_skcipher_ctx(tfm); + struct adiantum_request_ctx *rctx = skcipher_request_ctx(req); + const unsigned int bulk_len = req->cryptlen - BLOCKCIPHER_BLOCK_SIZE; + struct shash_desc *hash_desc = &rctx->u.hash_desc; + struct sg_mapping_iter miter; + unsigned int i, n; + int err; + + hash_desc->tfm = tctx->hash; + hash_desc->flags = 0; + + err = crypto_shash_init(hash_desc); + if (err) + return err; + + sg_miter_start(&miter, sgl, sg_nents(sgl), + SG_MITER_FROM_SG | SG_MITER_ATOMIC); + for (i = 0; i < bulk_len; i += n) { + sg_miter_next(&miter); + n = min_t(unsigned int, miter.length, bulk_len - i); + err = crypto_shash_update(hash_desc, miter.addr, n); + if (err) + break; + } + sg_miter_stop(&miter); + if (err) + return err; + + return crypto_shash_final(hash_desc, (u8 *)digest); +} + +/* Continue Adiantum encryption/decryption after the stream cipher step */ +static int adiantum_finish(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + const struct adiantum_tfm_ctx *tctx = crypto_skcipher_ctx(tfm); + struct adiantum_request_ctx *rctx = skcipher_request_ctx(req); + const unsigned int bulk_len = req->cryptlen - BLOCKCIPHER_BLOCK_SIZE; + le128 digest; + int err; + + /* If decrypting, decrypt C_M with the block cipher to get P_M */ + if (!rctx->enc) + crypto_cipher_decrypt_one(tctx->blockcipher, rctx->rbuf.bytes, + rctx->rbuf.bytes); + + /* + * Second hash step + * enc: C_R = C_M - H_{K_H}(T, C_L) + * dec: P_R = P_M - H_{K_H}(T, P_L) + */ + err = adiantum_hash_message(req, req->dst, &digest); + if (err) + return err; + le128_add(&digest, &digest, &rctx->header_hash); + le128_sub(&rctx->rbuf.bignum, &rctx->rbuf.bignum, &digest); + scatterwalk_map_and_copy(&rctx->rbuf.bignum, req->dst, + bulk_len, BLOCKCIPHER_BLOCK_SIZE, 1); + return 0; +} + +static void adiantum_streamcipher_done(struct crypto_async_request *areq, + int err) +{ + struct skcipher_request *req = areq->data; + + if (!err) + err = adiantum_finish(req); + + skcipher_request_complete(req, err); +} + +static int adiantum_crypt(struct skcipher_request *req, bool enc) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + const struct adiantum_tfm_ctx *tctx = crypto_skcipher_ctx(tfm); + struct adiantum_request_ctx *rctx = skcipher_request_ctx(req); + const unsigned int bulk_len = req->cryptlen - BLOCKCIPHER_BLOCK_SIZE; + unsigned int stream_len; + le128 digest; + int err; + + if (req->cryptlen < BLOCKCIPHER_BLOCK_SIZE) + return -EINVAL; + + rctx->enc = enc; + + /* + * First hash step + * enc: P_M = P_R + H_{K_H}(T, P_L) + * dec: C_M = C_R + H_{K_H}(T, C_L) + */ + adiantum_hash_header(req); + err = adiantum_hash_message(req, req->src, &digest); + if (err) + return err; + le128_add(&digest, &digest, &rctx->header_hash); + scatterwalk_map_and_copy(&rctx->rbuf.bignum, req->src, + bulk_len, BLOCKCIPHER_BLOCK_SIZE, 0); + le128_add(&rctx->rbuf.bignum, &rctx->rbuf.bignum, &digest); + + /* If encrypting, encrypt P_M with the block cipher to get C_M */ + if (enc) + crypto_cipher_encrypt_one(tctx->blockcipher, rctx->rbuf.bytes, + rctx->rbuf.bytes); + + /* Initialize the rest of the XChaCha IV (first part is C_M) */ + BUILD_BUG_ON(BLOCKCIPHER_BLOCK_SIZE != 16); + BUILD_BUG_ON(XCHACHA_IV_SIZE != 32); /* nonce || stream position */ + rctx->rbuf.words[4] = cpu_to_le32(1); + rctx->rbuf.words[5] = 0; + rctx->rbuf.words[6] = 0; + rctx->rbuf.words[7] = 0; + + /* + * XChaCha needs to be done on all the data except the last 16 bytes; + * for disk encryption that usually means 4080 or 496 bytes. But ChaCha + * implementations tend to be most efficient when passed a whole number + * of 64-byte ChaCha blocks, or sometimes even a multiple of 256 bytes. + * And here it doesn't matter whether the last 16 bytes are written to, + * as the second hash step will overwrite them. Thus, round the XChaCha + * length up to the next 64-byte boundary if possible. + */ + stream_len = bulk_len; + if (round_up(stream_len, CHACHA_BLOCK_SIZE) <= req->cryptlen) + stream_len = round_up(stream_len, CHACHA_BLOCK_SIZE); + + skcipher_request_set_tfm(&rctx->u.streamcipher_req, tctx->streamcipher); + skcipher_request_set_crypt(&rctx->u.streamcipher_req, req->src, + req->dst, stream_len, &rctx->rbuf); + skcipher_request_set_callback(&rctx->u.streamcipher_req, + req->base.flags, + adiantum_streamcipher_done, req); + return crypto_skcipher_encrypt(&rctx->u.streamcipher_req) ?: + adiantum_finish(req); +} + +static int adiantum_encrypt(struct skcipher_request *req) +{ + return adiantum_crypt(req, true); +} + +static int adiantum_decrypt(struct skcipher_request *req) +{ + return adiantum_crypt(req, false); +} + +static int adiantum_init_tfm(struct crypto_skcipher *tfm) +{ + struct skcipher_instance *inst = skcipher_alg_instance(tfm); + struct adiantum_instance_ctx *ictx = skcipher_instance_ctx(inst); + struct adiantum_tfm_ctx *tctx = crypto_skcipher_ctx(tfm); + struct crypto_skcipher *streamcipher; + struct crypto_cipher *blockcipher; + struct crypto_shash *hash; + unsigned int subreq_size; + int err; + + streamcipher = crypto_spawn_skcipher(&ictx->streamcipher_spawn); + if (IS_ERR(streamcipher)) + return PTR_ERR(streamcipher); + + blockcipher = crypto_spawn_cipher(&ictx->blockcipher_spawn); + if (IS_ERR(blockcipher)) { + err = PTR_ERR(blockcipher); + goto err_free_streamcipher; + } + + hash = crypto_spawn_shash(&ictx->hash_spawn); + if (IS_ERR(hash)) { + err = PTR_ERR(hash); + goto err_free_blockcipher; + } + + tctx->streamcipher = streamcipher; + tctx->blockcipher = blockcipher; + tctx->hash = hash; + + BUILD_BUG_ON(offsetofend(struct adiantum_request_ctx, u) != + sizeof(struct adiantum_request_ctx)); + subreq_size = max(FIELD_SIZEOF(struct adiantum_request_ctx, + u.hash_desc) + + crypto_shash_descsize(hash), + FIELD_SIZEOF(struct adiantum_request_ctx, + u.streamcipher_req) + + crypto_skcipher_reqsize(streamcipher)); + + crypto_skcipher_set_reqsize(tfm, + offsetof(struct adiantum_request_ctx, u) + + subreq_size); + return 0; + +err_free_blockcipher: + crypto_free_cipher(blockcipher); +err_free_streamcipher: + crypto_free_skcipher(streamcipher); + return err; +} + +static void adiantum_exit_tfm(struct crypto_skcipher *tfm) +{ + struct adiantum_tfm_ctx *tctx = crypto_skcipher_ctx(tfm); + + crypto_free_skcipher(tctx->streamcipher); + crypto_free_cipher(tctx->blockcipher); + crypto_free_shash(tctx->hash); +} + +static void adiantum_free_instance(struct skcipher_instance *inst) +{ + struct adiantum_instance_ctx *ictx = skcipher_instance_ctx(inst); + + crypto_drop_skcipher(&ictx->streamcipher_spawn); + crypto_drop_spawn(&ictx->blockcipher_spawn); + crypto_drop_shash(&ictx->hash_spawn); + kfree(inst); +} + +/* + * Check for a supported set of inner algorithms. + * See the comment at the beginning of this file. + */ +static bool adiantum_supported_algorithms(struct skcipher_alg *streamcipher_alg, + struct crypto_alg *blockcipher_alg, + struct shash_alg *hash_alg) +{ + if (strcmp(streamcipher_alg->base.cra_name, "xchacha12") != 0 && + strcmp(streamcipher_alg->base.cra_name, "xchacha20") != 0) + return false; + + if (blockcipher_alg->cra_cipher.cia_min_keysize > BLOCKCIPHER_KEY_SIZE || + blockcipher_alg->cra_cipher.cia_max_keysize < BLOCKCIPHER_KEY_SIZE) + return false; + if (blockcipher_alg->cra_blocksize != BLOCKCIPHER_BLOCK_SIZE) + return false; + + if (strcmp(hash_alg->base.cra_name, "nhpoly1305") != 0) + return false; + + return true; +} + +static int adiantum_create(struct crypto_template *tmpl, struct rtattr **tb) +{ + struct crypto_attr_type *algt; + const char *streamcipher_name; + const char *blockcipher_name; + const char *nhpoly1305_name; + struct skcipher_instance *inst; + struct adiantum_instance_ctx *ictx; + struct skcipher_alg *streamcipher_alg; + struct crypto_alg *blockcipher_alg; + struct crypto_alg *_hash_alg; + struct shash_alg *hash_alg; + int err; + + algt = crypto_get_attr_type(tb); + if (IS_ERR(algt)) + return PTR_ERR(algt); + + if ((algt->type ^ CRYPTO_ALG_TYPE_SKCIPHER) & algt->mask) + return -EINVAL; + + streamcipher_name = crypto_attr_alg_name(tb[1]); + if (IS_ERR(streamcipher_name)) + return PTR_ERR(streamcipher_name); + + blockcipher_name = crypto_attr_alg_name(tb[2]); + if (IS_ERR(blockcipher_name)) + return PTR_ERR(blockcipher_name); + + nhpoly1305_name = crypto_attr_alg_name(tb[3]); + if (nhpoly1305_name == ERR_PTR(-ENOENT)) + nhpoly1305_name = "nhpoly1305"; + if (IS_ERR(nhpoly1305_name)) + return PTR_ERR(nhpoly1305_name); + + inst = kzalloc(sizeof(*inst) + sizeof(*ictx), GFP_KERNEL); + if (!inst) + return -ENOMEM; + ictx = skcipher_instance_ctx(inst); + + /* Stream cipher, e.g. "xchacha12" */ + crypto_set_skcipher_spawn(&ictx->streamcipher_spawn, + skcipher_crypto_instance(inst)); + err = crypto_grab_skcipher(&ictx->streamcipher_spawn, streamcipher_name, + 0, crypto_requires_sync(algt->type, + algt->mask)); + if (err) + goto out_free_inst; + streamcipher_alg = crypto_spawn_skcipher_alg(&ictx->streamcipher_spawn); + + /* Block cipher, e.g. "aes" */ + crypto_set_spawn(&ictx->blockcipher_spawn, + skcipher_crypto_instance(inst)); + err = crypto_grab_spawn(&ictx->blockcipher_spawn, blockcipher_name, + CRYPTO_ALG_TYPE_CIPHER, CRYPTO_ALG_TYPE_MASK); + if (err) + goto out_drop_streamcipher; + blockcipher_alg = ictx->blockcipher_spawn.alg; + + /* NHPoly1305 ε-∆U hash function */ + _hash_alg = crypto_alg_mod_lookup(nhpoly1305_name, + CRYPTO_ALG_TYPE_SHASH, + CRYPTO_ALG_TYPE_MASK); + if (IS_ERR(_hash_alg)) { + err = PTR_ERR(_hash_alg); + goto out_drop_blockcipher; + } + hash_alg = __crypto_shash_alg(_hash_alg); + err = crypto_init_shash_spawn(&ictx->hash_spawn, hash_alg, + skcipher_crypto_instance(inst)); + if (err) + goto out_put_hash; + + /* Check the set of algorithms */ + if (!adiantum_supported_algorithms(streamcipher_alg, blockcipher_alg, + hash_alg)) { + pr_warn("Unsupported Adiantum instantiation: (%s,%s,%s)\n", + streamcipher_alg->base.cra_name, + blockcipher_alg->cra_name, hash_alg->base.cra_name); + err = -EINVAL; + goto out_drop_hash; + } + + /* Instance fields */ + + err = -ENAMETOOLONG; + if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME, + "adiantum(%s,%s)", streamcipher_alg->base.cra_name, + blockcipher_alg->cra_name) >= CRYPTO_MAX_ALG_NAME) + goto out_drop_hash; + if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME, + "adiantum(%s,%s,%s)", + streamcipher_alg->base.cra_driver_name, + blockcipher_alg->cra_driver_name, + hash_alg->base.cra_driver_name) >= CRYPTO_MAX_ALG_NAME) + goto out_drop_hash; + + inst->alg.base.cra_flags = streamcipher_alg->base.cra_flags & + CRYPTO_ALG_ASYNC; + inst->alg.base.cra_blocksize = BLOCKCIPHER_BLOCK_SIZE; + inst->alg.base.cra_ctxsize = sizeof(struct adiantum_tfm_ctx); + inst->alg.base.cra_alignmask = streamcipher_alg->base.cra_alignmask | + hash_alg->base.cra_alignmask; + /* + * The block cipher is only invoked once per message, so for long + * messages (e.g. sectors for disk encryption) its performance doesn't + * matter as much as that of the stream cipher and hash function. Thus, + * weigh the block cipher's ->cra_priority less. + */ + inst->alg.base.cra_priority = (4 * streamcipher_alg->base.cra_priority + + 2 * hash_alg->base.cra_priority + + blockcipher_alg->cra_priority) / 7; + + inst->alg.setkey = adiantum_setkey; + inst->alg.encrypt = adiantum_encrypt; + inst->alg.decrypt = adiantum_decrypt; + inst->alg.init = adiantum_init_tfm; + inst->alg.exit = adiantum_exit_tfm; + inst->alg.min_keysize = crypto_skcipher_alg_min_keysize(streamcipher_alg); + inst->alg.max_keysize = crypto_skcipher_alg_max_keysize(streamcipher_alg); + inst->alg.ivsize = TWEAK_SIZE; + + inst->free = adiantum_free_instance; + + err = skcipher_register_instance(tmpl, inst); + if (err) + goto out_drop_hash; + + crypto_mod_put(_hash_alg); + return 0; + +out_drop_hash: + crypto_drop_shash(&ictx->hash_spawn); +out_put_hash: + crypto_mod_put(_hash_alg); +out_drop_blockcipher: + crypto_drop_spawn(&ictx->blockcipher_spawn); +out_drop_streamcipher: + crypto_drop_skcipher(&ictx->streamcipher_spawn); +out_free_inst: + kfree(inst); + return err; +} + +/* adiantum(streamcipher_name, blockcipher_name [, nhpoly1305_name]) */ +static struct crypto_template adiantum_tmpl = { + .name = "adiantum", + .create = adiantum_create, + .module = THIS_MODULE, +}; + +static int __init adiantum_module_init(void) +{ + return crypto_register_template(&adiantum_tmpl); +} + +static void __exit adiantum_module_exit(void) +{ + crypto_unregister_template(&adiantum_tmpl); +} + +module_init(adiantum_module_init); +module_exit(adiantum_module_exit); + +MODULE_DESCRIPTION("Adiantum length-preserving encryption mode"); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>"); +MODULE_ALIAS_CRYPTO("adiantum"); diff --git a/crypto/aes_generic.c b/crypto/aes_generic.c index ca554d57d01e..13df33aca463 100644 --- a/crypto/aes_generic.c +++ b/crypto/aes_generic.c @@ -63,7 +63,8 @@ static inline u8 byte(const u32 x, const unsigned n) static const u32 rco_tab[10] = { 1, 2, 4, 8, 16, 32, 64, 128, 27, 54 }; -__visible const u32 crypto_ft_tab[4][256] = { +/* cacheline-aligned to facilitate prefetching into cache */ +__visible const u32 crypto_ft_tab[4][256] __cacheline_aligned = { { 0xa56363c6, 0x847c7cf8, 0x997777ee, 0x8d7b7bf6, 0x0df2f2ff, 0xbd6b6bd6, 0xb16f6fde, 0x54c5c591, @@ -327,7 +328,7 @@ __visible const u32 crypto_ft_tab[4][256] = { } }; -__visible const u32 crypto_fl_tab[4][256] = { +__visible const u32 crypto_fl_tab[4][256] __cacheline_aligned = { { 0x00000063, 0x0000007c, 0x00000077, 0x0000007b, 0x000000f2, 0x0000006b, 0x0000006f, 0x000000c5, @@ -591,7 +592,7 @@ __visible const u32 crypto_fl_tab[4][256] = { } }; -__visible const u32 crypto_it_tab[4][256] = { +__visible const u32 crypto_it_tab[4][256] __cacheline_aligned = { { 0x50a7f451, 0x5365417e, 0xc3a4171a, 0x965e273a, 0xcb6bab3b, 0xf1459d1f, 0xab58faac, 0x9303e34b, @@ -855,7 +856,7 @@ __visible const u32 crypto_it_tab[4][256] = { } }; -__visible const u32 crypto_il_tab[4][256] = { +__visible const u32 crypto_il_tab[4][256] __cacheline_aligned = { { 0x00000052, 0x00000009, 0x0000006a, 0x000000d5, 0x00000030, 0x00000036, 0x000000a5, 0x00000038, diff --git a/crypto/api.c b/crypto/api.c index 187795a6687d..6832b599ec4c 100644 --- a/crypto/api.c +++ b/crypto/api.c @@ -24,6 +24,7 @@ #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/string.h> +#include <linux/completion.h> #include "internal.h" LIST_HEAD(crypto_alg_list); @@ -594,5 +595,17 @@ int crypto_has_alg(const char *name, u32 type, u32 mask) } EXPORT_SYMBOL_GPL(crypto_has_alg); +void crypto_req_done(struct crypto_async_request *req, int err) +{ + struct crypto_wait *wait = req->data; + + if (err == -EINPROGRESS) + return; + + wait->err = err; + complete(&wait->completion); +} +EXPORT_SYMBOL_GPL(crypto_req_done); + MODULE_DESCRIPTION("Cryptographic core API"); MODULE_LICENSE("GPL"); diff --git a/crypto/chacha20_generic.c b/crypto/chacha20_generic.c deleted file mode 100644 index 4a45fa4890c0..000000000000 --- a/crypto/chacha20_generic.c +++ /dev/null @@ -1,143 +0,0 @@ -/* - * ChaCha20 256-bit cipher algorithm, RFC7539 - * - * Copyright (C) 2015 Martin Willi - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ - -#include <crypto/algapi.h> -#include <crypto/chacha20.h> -#include <crypto/internal/skcipher.h> -#include <linux/module.h> - -static inline u32 le32_to_cpuvp(const void *p) -{ - return le32_to_cpup(p); -} - -static void chacha20_docrypt(u32 *state, u8 *dst, const u8 *src, - unsigned int bytes) -{ - u8 stream[CHACHA20_BLOCK_SIZE]; - - if (dst != src) - memcpy(dst, src, bytes); - - while (bytes >= CHACHA20_BLOCK_SIZE) { - chacha20_block(state, stream); - crypto_xor(dst, stream, CHACHA20_BLOCK_SIZE); - bytes -= CHACHA20_BLOCK_SIZE; - dst += CHACHA20_BLOCK_SIZE; - } - if (bytes) { - chacha20_block(state, stream); - crypto_xor(dst, stream, bytes); - } -} - -void crypto_chacha20_init(u32 *state, struct chacha20_ctx *ctx, u8 *iv) -{ - static const char constant[16] = "expand 32-byte k"; - - state[0] = le32_to_cpuvp(constant + 0); - state[1] = le32_to_cpuvp(constant + 4); - state[2] = le32_to_cpuvp(constant + 8); - state[3] = le32_to_cpuvp(constant + 12); - state[4] = ctx->key[0]; - state[5] = ctx->key[1]; - state[6] = ctx->key[2]; - state[7] = ctx->key[3]; - state[8] = ctx->key[4]; - state[9] = ctx->key[5]; - state[10] = ctx->key[6]; - state[11] = ctx->key[7]; - state[12] = le32_to_cpuvp(iv + 0); - state[13] = le32_to_cpuvp(iv + 4); - state[14] = le32_to_cpuvp(iv + 8); - state[15] = le32_to_cpuvp(iv + 12); -} -EXPORT_SYMBOL_GPL(crypto_chacha20_init); - -int crypto_chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key, - unsigned int keysize) -{ - struct chacha20_ctx *ctx = crypto_skcipher_ctx(tfm); - int i; - - if (keysize != CHACHA20_KEY_SIZE) - return -EINVAL; - - for (i = 0; i < ARRAY_SIZE(ctx->key); i++) - ctx->key[i] = le32_to_cpuvp(key + i * sizeof(u32)); - - return 0; -} -EXPORT_SYMBOL_GPL(crypto_chacha20_setkey); - -int crypto_chacha20_crypt(struct skcipher_request *req) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct chacha20_ctx *ctx = crypto_skcipher_ctx(tfm); - struct skcipher_walk walk; - u32 state[16]; - int err; - - err = skcipher_walk_virt(&walk, req, true); - - crypto_chacha20_init(state, ctx, walk.iv); - - while (walk.nbytes > 0) { - unsigned int nbytes = walk.nbytes; - - if (nbytes < walk.total) - nbytes = round_down(nbytes, walk.stride); - - chacha20_docrypt(state, walk.dst.virt.addr, walk.src.virt.addr, - nbytes); - err = skcipher_walk_done(&walk, walk.nbytes - nbytes); - } - - return err; -} -EXPORT_SYMBOL_GPL(crypto_chacha20_crypt); - -static struct skcipher_alg alg = { - .base.cra_name = "chacha20", - .base.cra_driver_name = "chacha20-generic", - .base.cra_priority = 100, - .base.cra_blocksize = 1, - .base.cra_ctxsize = sizeof(struct chacha20_ctx), - .base.cra_alignmask = sizeof(u32) - 1, - .base.cra_module = THIS_MODULE, - - .min_keysize = CHACHA20_KEY_SIZE, - .max_keysize = CHACHA20_KEY_SIZE, - .ivsize = CHACHA20_IV_SIZE, - .chunksize = CHACHA20_BLOCK_SIZE, - .setkey = crypto_chacha20_setkey, - .encrypt = crypto_chacha20_crypt, - .decrypt = crypto_chacha20_crypt, -}; - -static int __init chacha20_generic_mod_init(void) -{ - return crypto_register_skcipher(&alg); -} - -static void __exit chacha20_generic_mod_fini(void) -{ - crypto_unregister_skcipher(&alg); -} - -module_init(chacha20_generic_mod_init); -module_exit(chacha20_generic_mod_fini); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Martin Willi <martin@strongswan.org>"); -MODULE_DESCRIPTION("chacha20 cipher algorithm"); -MODULE_ALIAS_CRYPTO("chacha20"); -MODULE_ALIAS_CRYPTO("chacha20-generic"); diff --git a/crypto/chacha20poly1305.c b/crypto/chacha20poly1305.c index af8afe5c06ea..dce194c8a3d7 100644 --- a/crypto/chacha20poly1305.c +++ b/crypto/chacha20poly1305.c @@ -13,7 +13,7 @@ #include <crypto/internal/hash.h> #include <crypto/internal/skcipher.h> #include <crypto/scatterwalk.h> -#include <crypto/chacha20.h> +#include <crypto/chacha.h> #include <crypto/poly1305.h> #include <linux/err.h> #include <linux/init.h> @@ -51,7 +51,7 @@ struct poly_req { }; struct chacha_req { - u8 iv[CHACHA20_IV_SIZE]; + u8 iv[CHACHA_IV_SIZE]; struct scatterlist src[1]; struct skcipher_request req; /* must be last member */ }; @@ -97,7 +97,7 @@ static void chacha_iv(u8 *iv, struct aead_request *req, u32 icb) memcpy(iv, &leicb, sizeof(leicb)); memcpy(iv + sizeof(leicb), ctx->salt, ctx->saltlen); memcpy(iv + sizeof(leicb) + ctx->saltlen, req->iv, - CHACHA20_IV_SIZE - sizeof(leicb) - ctx->saltlen); + CHACHA_IV_SIZE - sizeof(leicb) - ctx->saltlen); } static int poly_verify_tag(struct aead_request *req) @@ -502,7 +502,7 @@ static int chachapoly_setkey(struct crypto_aead *aead, const u8 *key, struct chachapoly_ctx *ctx = crypto_aead_ctx(aead); int err; - if (keylen != ctx->saltlen + CHACHA20_KEY_SIZE) + if (keylen != ctx->saltlen + CHACHA_KEY_SIZE) return -EINVAL; keylen -= ctx->saltlen; @@ -647,7 +647,7 @@ static int chachapoly_create(struct crypto_template *tmpl, struct rtattr **tb, err = -EINVAL; /* Need 16-byte IV size, including Initial Block Counter value */ - if (crypto_skcipher_alg_ivsize(chacha) != CHACHA20_IV_SIZE) + if (crypto_skcipher_alg_ivsize(chacha) != CHACHA_IV_SIZE) goto out_drop_chacha; /* Not a stream cipher? */ if (chacha->base.cra_blocksize != 1) diff --git a/crypto/chacha_generic.c b/crypto/chacha_generic.c new file mode 100644 index 000000000000..35b583101f4f --- /dev/null +++ b/crypto/chacha_generic.c @@ -0,0 +1,217 @@ +/* + * ChaCha and XChaCha stream ciphers, including ChaCha20 (RFC7539) + * + * Copyright (C) 2015 Martin Willi + * Copyright (C) 2018 Google LLC + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <asm/unaligned.h> +#include <crypto/algapi.h> +#include <crypto/chacha.h> +#include <crypto/internal/skcipher.h> +#include <linux/module.h> + +static void chacha_docrypt(u32 *state, u8 *dst, const u8 *src, + unsigned int bytes, int nrounds) +{ + /* aligned to potentially speed up crypto_xor() */ + u8 stream[CHACHA_BLOCK_SIZE] __aligned(sizeof(long)); + + if (dst != src) + memcpy(dst, src, bytes); + + while (bytes >= CHACHA_BLOCK_SIZE) { + chacha_block(state, stream, nrounds); + crypto_xor(dst, stream, CHACHA_BLOCK_SIZE); + bytes -= CHACHA_BLOCK_SIZE; + dst += CHACHA_BLOCK_SIZE; + } + if (bytes) { + chacha_block(state, stream, nrounds); + crypto_xor(dst, stream, bytes); + } +} + +static int chacha_stream_xor(struct skcipher_request *req, + struct chacha_ctx *ctx, u8 *iv) +{ + struct skcipher_walk walk; + u32 state[16]; + int err; + + err = skcipher_walk_virt(&walk, req, false); + + crypto_chacha_init(state, ctx, iv); + + while (walk.nbytes > 0) { + unsigned int nbytes = walk.nbytes; + + if (nbytes < walk.total) + nbytes = round_down(nbytes, walk.stride); + + chacha_docrypt(state, walk.dst.virt.addr, walk.src.virt.addr, + nbytes, ctx->nrounds); + err = skcipher_walk_done(&walk, walk.nbytes - nbytes); + } + + return err; +} + +void crypto_chacha_init(u32 *state, struct chacha_ctx *ctx, u8 *iv) +{ + state[0] = 0x61707865; /* "expa" */ + state[1] = 0x3320646e; /* "nd 3" */ + state[2] = 0x79622d32; /* "2-by" */ + state[3] = 0x6b206574; /* "te k" */ + state[4] = ctx->key[0]; + state[5] = ctx->key[1]; + state[6] = ctx->key[2]; + state[7] = ctx->key[3]; + state[8] = ctx->key[4]; + state[9] = ctx->key[5]; + state[10] = ctx->key[6]; + state[11] = ctx->key[7]; + state[12] = get_unaligned_le32(iv + 0); + state[13] = get_unaligned_le32(iv + 4); + state[14] = get_unaligned_le32(iv + 8); + state[15] = get_unaligned_le32(iv + 12); +} +EXPORT_SYMBOL_GPL(crypto_chacha_init); + +static int chacha_setkey(struct crypto_skcipher *tfm, const u8 *key, + unsigned int keysize, int nrounds) +{ + struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); + int i; + + if (keysize != CHACHA_KEY_SIZE) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(ctx->key); i++) + ctx->key[i] = get_unaligned_le32(key + i * sizeof(u32)); + + ctx->nrounds = nrounds; + return 0; +} + +int crypto_chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key, + unsigned int keysize) +{ + return chacha_setkey(tfm, key, keysize, 20); +} +EXPORT_SYMBOL_GPL(crypto_chacha20_setkey); + +int crypto_chacha12_setkey(struct crypto_skcipher *tfm, const u8 *key, + unsigned int keysize) +{ + return chacha_setkey(tfm, key, keysize, 12); +} +EXPORT_SYMBOL_GPL(crypto_chacha12_setkey); + +int crypto_chacha_crypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); + + return chacha_stream_xor(req, ctx, req->iv); +} +EXPORT_SYMBOL_GPL(crypto_chacha_crypt); + +int crypto_xchacha_crypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); + struct chacha_ctx subctx; + u32 state[16]; + u8 real_iv[16]; + + /* Compute the subkey given the original key and first 128 nonce bits */ + crypto_chacha_init(state, ctx, req->iv); + hchacha_block(state, subctx.key, ctx->nrounds); + subctx.nrounds = ctx->nrounds; + + /* Build the real IV */ + memcpy(&real_iv[0], req->iv + 24, 8); /* stream position */ + memcpy(&real_iv[8], req->iv + 16, 8); /* remaining 64 nonce bits */ + + /* Generate the stream and XOR it with the data */ + return chacha_stream_xor(req, &subctx, real_iv); +} +EXPORT_SYMBOL_GPL(crypto_xchacha_crypt); + +static struct skcipher_alg algs[] = { + { + .base.cra_name = "chacha20", + .base.cra_driver_name = "chacha20-generic", + .base.cra_priority = 100, + .base.cra_blocksize = 1, + .base.cra_ctxsize = sizeof(struct chacha_ctx), + .base.cra_module = THIS_MODULE, + + .min_keysize = CHACHA_KEY_SIZE, + .max_keysize = CHACHA_KEY_SIZE, + .ivsize = CHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, + .setkey = crypto_chacha20_setkey, + .encrypt = crypto_chacha_crypt, + .decrypt = crypto_chacha_crypt, + }, { + .base.cra_name = "xchacha20", + .base.cra_driver_name = "xchacha20-generic", + .base.cra_priority = 100, + .base.cra_blocksize = 1, + .base.cra_ctxsize = sizeof(struct chacha_ctx), + .base.cra_module = THIS_MODULE, + + .min_keysize = CHACHA_KEY_SIZE, + .max_keysize = CHACHA_KEY_SIZE, + .ivsize = XCHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, + .setkey = crypto_chacha20_setkey, + .encrypt = crypto_xchacha_crypt, + .decrypt = crypto_xchacha_crypt, + }, { + .base.cra_name = "xchacha12", + .base.cra_driver_name = "xchacha12-generic", + .base.cra_priority = 100, + .base.cra_blocksize = 1, + .base.cra_ctxsize = sizeof(struct chacha_ctx), + .base.cra_module = THIS_MODULE, + + .min_keysize = CHACHA_KEY_SIZE, + .max_keysize = CHACHA_KEY_SIZE, + .ivsize = XCHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, + .setkey = crypto_chacha12_setkey, + .encrypt = crypto_xchacha_crypt, + .decrypt = crypto_xchacha_crypt, + } +}; + +static int __init chacha_generic_mod_init(void) +{ + return crypto_register_skciphers(algs, ARRAY_SIZE(algs)); +} + +static void __exit chacha_generic_mod_fini(void) +{ + crypto_unregister_skciphers(algs, ARRAY_SIZE(algs)); +} + +module_init(chacha_generic_mod_init); +module_exit(chacha_generic_mod_fini); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Martin Willi <martin@strongswan.org>"); +MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (generic)"); +MODULE_ALIAS_CRYPTO("chacha20"); +MODULE_ALIAS_CRYPTO("chacha20-generic"); +MODULE_ALIAS_CRYPTO("xchacha20"); +MODULE_ALIAS_CRYPTO("xchacha20-generic"); +MODULE_ALIAS_CRYPTO("xchacha12"); +MODULE_ALIAS_CRYPTO("xchacha12-generic"); diff --git a/crypto/nhpoly1305.c b/crypto/nhpoly1305.c new file mode 100644 index 000000000000..ec831a5594d8 --- /dev/null +++ b/crypto/nhpoly1305.c @@ -0,0 +1,254 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * NHPoly1305 - ε-almost-∆-universal hash function for Adiantum + * + * Copyright 2018 Google LLC + */ + +/* + * "NHPoly1305" is the main component of Adiantum hashing. + * Specifically, it is the calculation + * + * H_L ← Poly1305_{K_L}(NH_{K_N}(pad_{128}(L))) + * + * from the procedure in section 6.4 of the Adiantum paper [1]. It is an + * ε-almost-∆-universal (ε-∆U) hash function for equal-length inputs over + * Z/(2^{128}Z), where the "∆" operation is addition. It hashes 1024-byte + * chunks of the input with the NH hash function [2], reducing the input length + * by 32x. The resulting NH digests are evaluated as a polynomial in + * GF(2^{130}-5), like in the Poly1305 MAC [3]. Note that the polynomial + * evaluation by itself would suffice to achieve the ε-∆U property; NH is used + * for performance since it's over twice as fast as Poly1305. + * + * This is *not* a cryptographic hash function; do not use it as such! + * + * [1] Adiantum: length-preserving encryption for entry-level processors + * (https://eprint.iacr.org/2018/720.pdf) + * [2] UMAC: Fast and Secure Message Authentication + * (https://fastcrypto.org/umac/umac_proc.pdf) + * [3] The Poly1305-AES message-authentication code + * (https://cr.yp.to/mac/poly1305-20050329.pdf) + */ + +#include <asm/unaligned.h> +#include <crypto/algapi.h> +#include <crypto/internal/hash.h> +#include <crypto/nhpoly1305.h> +#include <linux/crypto.h> +#include <linux/kernel.h> +#include <linux/module.h> + +static void nh_generic(const u32 *key, const u8 *message, size_t message_len, + __le64 hash[NH_NUM_PASSES]) +{ + u64 sums[4] = { 0, 0, 0, 0 }; + + BUILD_BUG_ON(NH_PAIR_STRIDE != 2); + BUILD_BUG_ON(NH_NUM_PASSES != 4); + + while (message_len) { + u32 m0 = get_unaligned_le32(message + 0); + u32 m1 = get_unaligned_le32(message + 4); + u32 m2 = get_unaligned_le32(message + 8); + u32 m3 = get_unaligned_le32(message + 12); + + sums[0] += (u64)(u32)(m0 + key[ 0]) * (u32)(m2 + key[ 2]); + sums[1] += (u64)(u32)(m0 + key[ 4]) * (u32)(m2 + key[ 6]); + sums[2] += (u64)(u32)(m0 + key[ 8]) * (u32)(m2 + key[10]); + sums[3] += (u64)(u32)(m0 + key[12]) * (u32)(m2 + key[14]); + sums[0] += (u64)(u32)(m1 + key[ 1]) * (u32)(m3 + key[ 3]); + sums[1] += (u64)(u32)(m1 + key[ 5]) * (u32)(m3 + key[ 7]); + sums[2] += (u64)(u32)(m1 + key[ 9]) * (u32)(m3 + key[11]); + sums[3] += (u64)(u32)(m1 + key[13]) * (u32)(m3 + key[15]); + key += NH_MESSAGE_UNIT / sizeof(key[0]); + message += NH_MESSAGE_UNIT; + message_len -= NH_MESSAGE_UNIT; + } + + hash[0] = cpu_to_le64(sums[0]); + hash[1] = cpu_to_le64(sums[1]); + hash[2] = cpu_to_le64(sums[2]); + hash[3] = cpu_to_le64(sums[3]); +} + +/* Pass the next NH hash value through Poly1305 */ +static void process_nh_hash_value(struct nhpoly1305_state *state, + const struct nhpoly1305_key *key) +{ + BUILD_BUG_ON(NH_HASH_BYTES % POLY1305_BLOCK_SIZE != 0); + + poly1305_core_blocks(&state->poly_state, &key->poly_key, state->nh_hash, + NH_HASH_BYTES / POLY1305_BLOCK_SIZE); +} + +/* + * Feed the next portion of the source data, as a whole number of 16-byte + * "NH message units", through NH and Poly1305. Each NH hash is taken over + * 1024 bytes, except possibly the final one which is taken over a multiple of + * 16 bytes up to 1024. Also, in the case where data is passed in misaligned + * chunks, we combine partial hashes; the end result is the same either way. + */ +static void nhpoly1305_units(struct nhpoly1305_state *state, + const struct nhpoly1305_key *key, + const u8 *src, unsigned int srclen, nh_t nh_fn) +{ + do { + unsigned int bytes; + + if (state->nh_remaining == 0) { + /* Starting a new NH message */ + bytes = min_t(unsigned int, srclen, NH_MESSAGE_BYTES); + nh_fn(key->nh_key, src, bytes, state->nh_hash); + state->nh_remaining = NH_MESSAGE_BYTES - bytes; + } else { + /* Continuing a previous NH message */ + __le64 tmp_hash[NH_NUM_PASSES]; + unsigned int pos; + int i; + + pos = NH_MESSAGE_BYTES - state->nh_remaining; + bytes = min(srclen, state->nh_remaining); + nh_fn(&key->nh_key[pos / 4], src, bytes, tmp_hash); + for (i = 0; i < NH_NUM_PASSES; i++) + le64_add_cpu(&state->nh_hash[i], + le64_to_cpu(tmp_hash[i])); + state->nh_remaining -= bytes; + } + if (state->nh_remaining == 0) + process_nh_hash_value(state, key); + src += bytes; + srclen -= bytes; + } while (srclen); +} + +int crypto_nhpoly1305_setkey(struct crypto_shash *tfm, + const u8 *key, unsigned int keylen) +{ + struct nhpoly1305_key *ctx = crypto_shash_ctx(tfm); + int i; + + if (keylen != NHPOLY1305_KEY_SIZE) + return -EINVAL; + + poly1305_core_setkey(&ctx->poly_key, key); + key += POLY1305_BLOCK_SIZE; + + for (i = 0; i < NH_KEY_WORDS; i++) + ctx->nh_key[i] = get_unaligned_le32(key + i * sizeof(u32)); + + return 0; +} +EXPORT_SYMBOL(crypto_nhpoly1305_setkey); + +int crypto_nhpoly1305_init(struct shash_desc *desc) +{ + struct nhpoly1305_state *state = shash_desc_ctx(desc); + + poly1305_core_init(&state->poly_state); + state->buflen = 0; + state->nh_remaining = 0; + return 0; +} +EXPORT_SYMBOL(crypto_nhpoly1305_init); + +int crypto_nhpoly1305_update_helper(struct shash_desc *desc, + const u8 *src, unsigned int srclen, + nh_t nh_fn) +{ + struct nhpoly1305_state *state = shash_desc_ctx(desc); + const struct nhpoly1305_key *key = crypto_shash_ctx(desc->tfm); + unsigned int bytes; + + if (state->buflen) { + bytes = min(srclen, (int)NH_MESSAGE_UNIT - state->buflen); + memcpy(&state->buffer[state->buflen], src, bytes); + state->buflen += bytes; + if (state->buflen < NH_MESSAGE_UNIT) + return 0; + nhpoly1305_units(state, key, state->buffer, NH_MESSAGE_UNIT, + nh_fn); + state->buflen = 0; + src += bytes; + srclen -= bytes; + } + + if (srclen >= NH_MESSAGE_UNIT) { + bytes = round_down(srclen, NH_MESSAGE_UNIT); + nhpoly1305_units(state, key, src, bytes, nh_fn); + src += bytes; + srclen -= bytes; + } + + if (srclen) { + memcpy(state->buffer, src, srclen); + state->buflen = srclen; + } + return 0; +} +EXPORT_SYMBOL(crypto_nhpoly1305_update_helper); + +int crypto_nhpoly1305_update(struct shash_desc *desc, + const u8 *src, unsigned int srclen) +{ + return crypto_nhpoly1305_update_helper(desc, src, srclen, nh_generic); +} +EXPORT_SYMBOL(crypto_nhpoly1305_update); + +int crypto_nhpoly1305_final_helper(struct shash_desc *desc, u8 *dst, nh_t nh_fn) +{ + struct nhpoly1305_state *state = shash_desc_ctx(desc); + const struct nhpoly1305_key *key = crypto_shash_ctx(desc->tfm); + + if (state->buflen) { + memset(&state->buffer[state->buflen], 0, + NH_MESSAGE_UNIT - state->buflen); + nhpoly1305_units(state, key, state->buffer, NH_MESSAGE_UNIT, + nh_fn); + } + + if (state->nh_remaining) + process_nh_hash_value(state, key); + + poly1305_core_emit(&state->poly_state, dst); + return 0; +} +EXPORT_SYMBOL(crypto_nhpoly1305_final_helper); + +int crypto_nhpoly1305_final(struct shash_desc *desc, u8 *dst) +{ + return crypto_nhpoly1305_final_helper(desc, dst, nh_generic); +} +EXPORT_SYMBOL(crypto_nhpoly1305_final); + +static struct shash_alg nhpoly1305_alg = { + .base.cra_name = "nhpoly1305", + .base.cra_driver_name = "nhpoly1305-generic", + .base.cra_priority = 100, + .base.cra_ctxsize = sizeof(struct nhpoly1305_key), + .base.cra_module = THIS_MODULE, + .digestsize = POLY1305_DIGEST_SIZE, + .init = crypto_nhpoly1305_init, + .update = crypto_nhpoly1305_update, + .final = crypto_nhpoly1305_final, + .setkey = crypto_nhpoly1305_setkey, + .descsize = sizeof(struct nhpoly1305_state), +}; + +static int __init nhpoly1305_mod_init(void) +{ + return crypto_register_shash(&nhpoly1305_alg); +} + +static void __exit nhpoly1305_mod_exit(void) +{ + crypto_unregister_shash(&nhpoly1305_alg); +} + +module_init(nhpoly1305_mod_init); +module_exit(nhpoly1305_mod_exit); + +MODULE_DESCRIPTION("NHPoly1305 ε-almost-∆-universal hash function"); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>"); +MODULE_ALIAS_CRYPTO("nhpoly1305"); +MODULE_ALIAS_CRYPTO("nhpoly1305-generic"); diff --git a/crypto/poly1305_generic.c b/crypto/poly1305_generic.c index ba39eb308c79..b60c1eee9839 100644 --- a/crypto/poly1305_generic.c +++ b/crypto/poly1305_generic.c @@ -38,7 +38,7 @@ int crypto_poly1305_init(struct shash_desc *desc) { struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); - memset(dctx->h, 0, sizeof(dctx->h)); + poly1305_core_init(&dctx->h); dctx->buflen = 0; dctx->rset = false; dctx->sset = false; @@ -47,23 +47,16 @@ int crypto_poly1305_init(struct shash_desc *desc) } EXPORT_SYMBOL_GPL(crypto_poly1305_init); -static void poly1305_setrkey(struct poly1305_desc_ctx *dctx, const u8 *key) +void poly1305_core_setkey(struct poly1305_key *key, const u8 *raw_key) { /* r &= 0xffffffc0ffffffc0ffffffc0fffffff */ - dctx->r[0] = (get_unaligned_le32(key + 0) >> 0) & 0x3ffffff; - dctx->r[1] = (get_unaligned_le32(key + 3) >> 2) & 0x3ffff03; - dctx->r[2] = (get_unaligned_le32(key + 6) >> 4) & 0x3ffc0ff; - dctx->r[3] = (get_unaligned_le32(key + 9) >> 6) & 0x3f03fff; - dctx->r[4] = (get_unaligned_le32(key + 12) >> 8) & 0x00fffff; -} - -static void poly1305_setskey(struct poly1305_desc_ctx *dctx, const u8 *key) -{ - dctx->s[0] = get_unaligned_le32(key + 0); - dctx->s[1] = get_unaligned_le32(key + 4); - dctx->s[2] = get_unaligned_le32(key + 8); - dctx->s[3] = get_unaligned_le32(key + 12); + key->r[0] = (get_unaligned_le32(raw_key + 0) >> 0) & 0x3ffffff; + key->r[1] = (get_unaligned_le32(raw_key + 3) >> 2) & 0x3ffff03; + key->r[2] = (get_unaligned_le32(raw_key + 6) >> 4) & 0x3ffc0ff; + key->r[3] = (get_unaligned_le32(raw_key + 9) >> 6) & 0x3f03fff; + key->r[4] = (get_unaligned_le32(raw_key + 12) >> 8) & 0x00fffff; } +EXPORT_SYMBOL_GPL(poly1305_core_setkey); /* * Poly1305 requires a unique key for each tag, which implies that we can't set @@ -75,13 +68,16 @@ unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx, { if (!dctx->sset) { if (!dctx->rset && srclen >= POLY1305_BLOCK_SIZE) { - poly1305_setrkey(dctx, src); + poly1305_core_setkey(&dctx->r, src); src += POLY1305_BLOCK_SIZE; srclen -= POLY1305_BLOCK_SIZE; dctx->rset = true; } if (srclen >= POLY1305_BLOCK_SIZE) { - poly1305_setskey(dctx, src); + dctx->s[0] = get_unaligned_le32(src + 0); + dctx->s[1] = get_unaligned_le32(src + 4); + dctx->s[2] = get_unaligned_le32(src + 8); + dctx->s[3] = get_unaligned_le32(src + 12); src += POLY1305_BLOCK_SIZE; srclen -= POLY1305_BLOCK_SIZE; dctx->sset = true; @@ -91,41 +87,37 @@ unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx, } EXPORT_SYMBOL_GPL(crypto_poly1305_setdesckey); -static unsigned int poly1305_blocks(struct poly1305_desc_ctx *dctx, - const u8 *src, unsigned int srclen, - u32 hibit) +static void poly1305_blocks_internal(struct poly1305_state *state, + const struct poly1305_key *key, + const void *src, unsigned int nblocks, + u32 hibit) { u32 r0, r1, r2, r3, r4; u32 s1, s2, s3, s4; u32 h0, h1, h2, h3, h4; u64 d0, d1, d2, d3, d4; - unsigned int datalen; - if (unlikely(!dctx->sset)) { - datalen = crypto_poly1305_setdesckey(dctx, src, srclen); - src += srclen - datalen; - srclen = datalen; - } + if (!nblocks) + return; - r0 = dctx->r[0]; - r1 = dctx->r[1]; - r2 = dctx->r[2]; - r3 = dctx->r[3]; - r4 = dctx->r[4]; + r0 = key->r[0]; + r1 = key->r[1]; + r2 = key->r[2]; + r3 = key->r[3]; + r4 = key->r[4]; s1 = r1 * 5; s2 = r2 * 5; s3 = r3 * 5; s4 = r4 * 5; - h0 = dctx->h[0]; - h1 = dctx->h[1]; - h2 = dctx->h[2]; - h3 = dctx->h[3]; - h4 = dctx->h[4]; - - while (likely(srclen >= POLY1305_BLOCK_SIZE)) { + h0 = state->h[0]; + h1 = state->h[1]; + h2 = state->h[2]; + h3 = state->h[3]; + h4 = state->h[4]; + do { /* h += m[i] */ h0 += (get_unaligned_le32(src + 0) >> 0) & 0x3ffffff; h1 += (get_unaligned_le32(src + 3) >> 2) & 0x3ffffff; @@ -154,16 +146,36 @@ static unsigned int poly1305_blocks(struct poly1305_desc_ctx *dctx, h1 += h0 >> 26; h0 = h0 & 0x3ffffff; src += POLY1305_BLOCK_SIZE; - srclen -= POLY1305_BLOCK_SIZE; - } + } while (--nblocks); - dctx->h[0] = h0; - dctx->h[1] = h1; - dctx->h[2] = h2; - dctx->h[3] = h3; - dctx->h[4] = h4; + state->h[0] = h0; + state->h[1] = h1; + state->h[2] = h2; + state->h[3] = h3; + state->h[4] = h4; +} - return srclen; +void poly1305_core_blocks(struct poly1305_state *state, + const struct poly1305_key *key, + const void *src, unsigned int nblocks) +{ + poly1305_blocks_internal(state, key, src, nblocks, 1 << 24); +} +EXPORT_SYMBOL_GPL(poly1305_core_blocks); + +static void poly1305_blocks(struct poly1305_desc_ctx *dctx, + const u8 *src, unsigned int srclen, u32 hibit) +{ + unsigned int datalen; + + if (unlikely(!dctx->sset)) { + datalen = crypto_poly1305_setdesckey(dctx, src, srclen); + src += srclen - datalen; + srclen = datalen; + } + + poly1305_blocks_internal(&dctx->h, &dctx->r, + src, srclen / POLY1305_BLOCK_SIZE, hibit); } int crypto_poly1305_update(struct shash_desc *desc, @@ -187,9 +199,9 @@ int crypto_poly1305_update(struct shash_desc *desc, } if (likely(srclen >= POLY1305_BLOCK_SIZE)) { - bytes = poly1305_blocks(dctx, src, srclen, 1 << 24); - src += srclen - bytes; - srclen = bytes; + poly1305_blocks(dctx, src, srclen, 1 << 24); + src += srclen - (srclen % POLY1305_BLOCK_SIZE); + srclen %= POLY1305_BLOCK_SIZE; } if (unlikely(srclen)) { @@ -201,31 +213,18 @@ int crypto_poly1305_update(struct shash_desc *desc, } EXPORT_SYMBOL_GPL(crypto_poly1305_update); -int crypto_poly1305_final(struct shash_desc *desc, u8 *dst) +void poly1305_core_emit(const struct poly1305_state *state, void *dst) { - struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); - __le32 *mac = (__le32 *)dst; u32 h0, h1, h2, h3, h4; u32 g0, g1, g2, g3, g4; u32 mask; - u64 f = 0; - - if (unlikely(!dctx->sset)) - return -ENOKEY; - - if (unlikely(dctx->buflen)) { - dctx->buf[dctx->buflen++] = 1; - memset(dctx->buf + dctx->buflen, 0, - POLY1305_BLOCK_SIZE - dctx->buflen); - poly1305_blocks(dctx, dctx->buf, POLY1305_BLOCK_SIZE, 0); - } /* fully carry h */ - h0 = dctx->h[0]; - h1 = dctx->h[1]; - h2 = dctx->h[2]; - h3 = dctx->h[3]; - h4 = dctx->h[4]; + h0 = state->h[0]; + h1 = state->h[1]; + h2 = state->h[2]; + h3 = state->h[3]; + h4 = state->h[4]; h2 += (h1 >> 26); h1 = h1 & 0x3ffffff; h3 += (h2 >> 26); h2 = h2 & 0x3ffffff; @@ -255,16 +254,40 @@ int crypto_poly1305_final(struct shash_desc *desc, u8 *dst) h4 = (h4 & mask) | g4; /* h = h % (2^128) */ - h0 = (h0 >> 0) | (h1 << 26); - h1 = (h1 >> 6) | (h2 << 20); - h2 = (h2 >> 12) | (h3 << 14); - h3 = (h3 >> 18) | (h4 << 8); + put_unaligned_le32((h0 >> 0) | (h1 << 26), dst + 0); + put_unaligned_le32((h1 >> 6) | (h2 << 20), dst + 4); + put_unaligned_le32((h2 >> 12) | (h3 << 14), dst + 8); + put_unaligned_le32((h3 >> 18) | (h4 << 8), dst + 12); +} +EXPORT_SYMBOL_GPL(poly1305_core_emit); + +int crypto_poly1305_final(struct shash_desc *desc, u8 *dst) +{ + struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); + __le32 digest[4]; + u64 f = 0; + + if (unlikely(!dctx->sset)) + return -ENOKEY; + + if (unlikely(dctx->buflen)) { + dctx->buf[dctx->buflen++] = 1; + memset(dctx->buf + dctx->buflen, 0, + POLY1305_BLOCK_SIZE - dctx->buflen); + poly1305_blocks(dctx, dctx->buf, POLY1305_BLOCK_SIZE, 0); + } + + poly1305_core_emit(&dctx->h, digest); /* mac = (h + s) % (2^128) */ - f = (f >> 32) + h0 + dctx->s[0]; mac[0] = cpu_to_le32(f); - f = (f >> 32) + h1 + dctx->s[1]; mac[1] = cpu_to_le32(f); - f = (f >> 32) + h2 + dctx->s[2]; mac[2] = cpu_to_le32(f); - f = (f >> 32) + h3 + dctx->s[3]; mac[3] = cpu_to_le32(f); + f = (f >> 32) + le32_to_cpu(digest[0]) + dctx->s[0]; + put_unaligned_le32(f, dst + 0); + f = (f >> 32) + le32_to_cpu(digest[1]) + dctx->s[1]; + put_unaligned_le32(f, dst + 4); + f = (f >> 32) + le32_to_cpu(digest[2]) + dctx->s[2]; + put_unaligned_le32(f, dst + 8); + f = (f >> 32) + le32_to_cpu(digest[3]) + dctx->s[3]; + put_unaligned_le32(f, dst + 12); return 0; } diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c index f7affe7cf0b4..99f2432c96fb 100644 --- a/crypto/tcrypt.c +++ b/crypto/tcrypt.c @@ -1610,6 +1610,16 @@ static int do_test(const char *alg, u32 type, u32 mask, int m) speed_template_32); break; + case 219: + test_cipher_speed("adiantum(xchacha12,aes)", ENCRYPT, sec, NULL, + 0, speed_template_32); + test_cipher_speed("adiantum(xchacha12,aes)", DECRYPT, sec, NULL, + 0, speed_template_32); + test_cipher_speed("adiantum(xchacha20,aes)", ENCRYPT, sec, NULL, + 0, speed_template_32); + test_cipher_speed("adiantum(xchacha20,aes)", DECRYPT, sec, NULL, + 0, speed_template_32); + break; case 300: if (alg) { diff --git a/crypto/testmgr.c b/crypto/testmgr.c index d91278c01ea8..db88375bb40a 100644 --- a/crypto/testmgr.c +++ b/crypto/testmgr.c @@ -2355,6 +2355,24 @@ static int alg_test_null(const struct alg_test_desc *desc, /* Please keep this list sorted by algorithm name. */ static const struct alg_test_desc alg_test_descs[] = { { + .alg = "adiantum(xchacha12,aes)", + .test = alg_test_skcipher, + .suite = { + .cipher = { + .enc = __VECS(adiantum_xchacha12_aes_enc_tv_template), + .dec = __VECS(adiantum_xchacha12_aes_dec_tv_template) + } + }, + }, { + .alg = "adiantum(xchacha20,aes)", + .test = alg_test_skcipher, + .suite = { + .cipher = { + .enc = __VECS(adiantum_xchacha20_aes_enc_tv_template), + .dec = __VECS(adiantum_xchacha20_aes_dec_tv_template) + } + }, + }, { .alg = "ansi_cprng", .test = alg_test_cprng, .suite = { @@ -3303,6 +3321,12 @@ static const struct alg_test_desc alg_test_descs[] = { .hash = __VECS(michael_mic_tv_template) } }, { + .alg = "nhpoly1305", + .test = alg_test_hash, + .suite = { + .hash = __VECS(nhpoly1305_tv_template) + } + }, { .alg = "ofb(aes)", .test = alg_test_skcipher, .fips_allowed = 1, @@ -3554,6 +3578,24 @@ static const struct alg_test_desc alg_test_descs[] = { .hash = __VECS(aes_xcbc128_tv_template) } }, { + .alg = "xchacha12", + .test = alg_test_skcipher, + .suite = { + .cipher = { + .enc = __VECS(xchacha12_tv_template), + .dec = __VECS(xchacha12_tv_template) + } + }, + }, { + .alg = "xchacha20", + .test = alg_test_skcipher, + .suite = { + .cipher = { + .enc = __VECS(xchacha20_tv_template), + .dec = __VECS(xchacha20_tv_template) + } + }, + }, { .alg = "xts(aes)", .test = alg_test_skcipher, .fips_allowed = 1, @@ -3609,6 +3651,16 @@ static const struct alg_test_desc alg_test_descs[] = { .decomp = __VECS(zlib_deflate_decomp_tv_template) } } + }, { + .alg = "zstd", + .test = alg_test_comp, + .fips_allowed = 1, + .suite = { + .comp = { + .comp = __VECS(zstd_comp_tv_template), + .decomp = __VECS(zstd_decomp_tv_template) + } + } } }; diff --git a/crypto/testmgr.h b/crypto/testmgr.h index 12835f072614..7519eb5345ed 100644 --- a/crypto/testmgr.h +++ b/crypto/testmgr.h @@ -29,7 +29,7 @@ #define MAX_DIGEST_SIZE 64 #define MAX_TAP 8 -#define MAX_KEYLEN 160 +#define MAX_KEYLEN 1088 #define MAX_IVLEN 32 struct hash_testvec { @@ -37,10 +37,10 @@ struct hash_testvec { const char *key; const char *plaintext; const char *digest; - unsigned char tap[MAX_TAP]; + unsigned short tap[MAX_TAP]; + unsigned short np; unsigned short psize; - unsigned char np; - unsigned char ksize; + unsigned short ksize; }; /* @@ -4705,6 +4705,1237 @@ static const struct hash_testvec poly1305_tv_template[] = { } }; +/* NHPoly1305 test vectors from https://github.com/google/adiantum */ +static const struct hash_testvec nhpoly1305_tv_template[] = { + { + .key = "\xd2\x5d\x4c\xdd\x8d\x2b\x7f\x7a" + "\xd9\xbe\x71\xec\xd1\x83\x52\xe3" + "\xe1\xad\xd7\x5c\x0a\x75\x9d\xec" + "\x1d\x13\x7e\x5d\x71\x07\xc9\xe4" + "\x57\x2d\x44\x68\xcf\xd8\xd6\xc5" + "\x39\x69\x7d\x32\x75\x51\x4f\x7e" + "\xb2\x4c\xc6\x90\x51\x6e\xd9\xd6" + "\xa5\x8b\x2d\xf1\x94\xf9\xf7\x5e" + "\x2c\x84\x7b\x41\x0f\x88\x50\x89" + "\x30\xd9\xa1\x38\x46\x6c\xc0\x4f" + "\xe8\xdf\xdc\x66\xab\x24\x43\x41" + "\x91\x55\x29\x65\x86\x28\x5e\x45" + "\xd5\x2d\xb7\x80\x08\x9a\xc3\xd4" + "\x9a\x77\x0a\xd4\xef\x3e\xe6\x3f" + "\x6f\x2f\x9b\x3a\x7d\x12\x1e\x80" + "\x6c\x44\xa2\x25\xe1\xf6\x60\xe9" + "\x0d\xaf\xc5\x3c\xa5\x79\xae\x64" + "\xbc\xa0\x39\xa3\x4d\x10\xe5\x4d" + "\xd5\xe7\x89\x7a\x13\xee\x06\x78" + "\xdc\xa4\xdc\x14\x27\xe6\x49\x38" + "\xd0\xe0\x45\x25\x36\xc5\xf4\x79" + "\x2e\x9a\x98\x04\xe4\x2b\x46\x52" + "\x7c\x33\xca\xe2\x56\x51\x50\xe2" + "\xa5\x9a\xae\x18\x6a\x13\xf8\xd2" + "\x21\x31\x66\x02\xe2\xda\x8d\x7e" + "\x41\x19\xb2\x61\xee\x48\x8f\xf1" + "\x65\x24\x2e\x1e\x68\xce\x05\xd9" + "\x2a\xcf\xa5\x3a\x57\xdd\x35\x91" + "\x93\x01\xca\x95\xfc\x2b\x36\x04" + "\xe6\x96\x97\x28\xf6\x31\xfe\xa3" + "\x9d\xf6\x6a\x1e\x80\x8d\xdc\xec" + "\xaf\x66\x11\x13\x02\x88\xd5\x27" + "\x33\xb4\x1a\xcd\xa3\xf6\xde\x31" + "\x8e\xc0\x0e\x6c\xd8\x5a\x97\x5e" + "\xdd\xfd\x60\x69\x38\x46\x3f\x90" + "\x5e\x97\xd3\x32\x76\xc7\x82\x49" + "\xfe\xba\x06\x5f\x2f\xa2\xfd\xff" + "\x80\x05\x40\xe4\x33\x03\xfb\x10" + "\xc0\xde\x65\x8c\xc9\x8d\x3a\x9d" + "\xb5\x7b\x36\x4b\xb5\x0c\xcf\x00" + "\x9c\x87\xe4\x49\xad\x90\xda\x4a" + "\xdd\xbd\xff\xe2\x32\x57\xd6\x78" + "\x36\x39\x6c\xd3\x5b\x9b\x88\x59" + "\x2d\xf0\x46\xe4\x13\x0e\x2b\x35" + "\x0d\x0f\x73\x8a\x4f\x26\x84\x75" + "\x88\x3c\xc5\x58\x66\x18\x1a\xb4" + "\x64\x51\x34\x27\x1b\xa4\x11\xc9" + "\x6d\x91\x8a\xfa\x32\x60\x9d\xd7" + "\x87\xe5\xaa\x43\x72\xf8\xda\xd1" + "\x48\x44\x13\x61\xdc\x8c\x76\x17" + "\x0c\x85\x4e\xf3\xdd\xa2\x42\xd2" + "\x74\xc1\x30\x1b\xeb\x35\x31\x29" + "\x5b\xd7\x4c\x94\x46\x35\xa1\x23" + "\x50\xf2\xa2\x8e\x7e\x4f\x23\x4f" + "\x51\xff\xe2\xc9\xa3\x7d\x56\x8b" + "\x41\xf2\xd0\xc5\x57\x7e\x59\xac" + "\xbb\x65\xf3\xfe\xf7\x17\xef\x63" + "\x7c\x6f\x23\xdd\x22\x8e\xed\x84" + "\x0e\x3b\x09\xb3\xf3\xf4\x8f\xcd" + "\x37\xa8\xe1\xa7\x30\xdb\xb1\xa2" + "\x9c\xa2\xdf\x34\x17\x3e\x68\x44" + "\xd0\xde\x03\x50\xd1\x48\x6b\x20" + "\xe2\x63\x45\xa5\xea\x87\xc2\x42" + "\x95\x03\x49\x05\xed\xe0\x90\x29" + "\x1a\xb8\xcf\x9b\x43\xcf\x29\x7a" + "\x63\x17\x41\x9f\xe0\xc9\x10\xfd" + "\x2c\x56\x8c\x08\x55\xb4\xa9\x27" + "\x0f\x23\xb1\x05\x6a\x12\x46\xc7" + "\xe1\xfe\x28\x93\x93\xd7\x2f\xdc" + "\x98\x30\xdb\x75\x8a\xbe\x97\x7a" + "\x02\xfb\x8c\xba\xbe\x25\x09\xbe" + "\xce\xcb\xa2\xef\x79\x4d\x0e\x9d" + "\x1b\x9d\xb6\x39\x34\x38\xfa\x07" + "\xec\xe8\xfc\x32\x85\x1d\xf7\x85" + "\x63\xc3\x3c\xc0\x02\x75\xd7\x3f" + "\xb2\x68\x60\x66\x65\x81\xc6\xb1" + "\x42\x65\x4b\x4b\x28\xd7\xc7\xaa" + "\x9b\xd2\xdc\x1b\x01\xe0\x26\x39" + "\x01\xc1\x52\x14\xd1\x3f\xb7\xe6" + "\x61\x41\xc7\x93\xd2\xa2\x67\xc6" + "\xf7\x11\xb5\xf5\xea\xdd\x19\xfb" + "\x4d\x21\x12\xd6\x7d\xf1\x10\xb0" + "\x89\x07\xc7\x5a\x52\x73\x70\x2f" + "\x32\xef\x65\x2b\x12\xb2\xf0\xf5" + "\x20\xe0\x90\x59\x7e\x64\xf1\x4c" + "\x41\xb3\xa5\x91\x08\xe6\x5e\x5f" + "\x05\x56\x76\xb4\xb0\xcd\x70\x53" + "\x10\x48\x9c\xff\xc2\x69\x55\x24" + "\x87\xef\x84\xea\xfb\xa7\xbf\xa0" + "\x91\x04\xad\x4f\x8b\x57\x54\x4b" + "\xb6\xe9\xd1\xac\x37\x2f\x1d\x2e" + "\xab\xa5\xa4\xe8\xff\xfb\xd9\x39" + "\x2f\xb7\xac\xd1\xfe\x0b\x9a\x80" + "\x0f\xb6\xf4\x36\x39\x90\x51\xe3" + "\x0a\x2f\xb6\x45\x76\x89\xcd\x61" + "\xfe\x48\x5f\x75\x1d\x13\x00\x62" + "\x80\x24\x47\xe7\xbc\x37\xd7\xe3" + "\x15\xe8\x68\x22\xaf\x80\x6f\x4b" + "\xa8\x9f\x01\x10\x48\x14\xc3\x02" + "\x52\xd2\xc7\x75\x9b\x52\x6d\x30" + "\xac\x13\x85\xc8\xf7\xa3\x58\x4b" + "\x49\xf7\x1c\x45\x55\x8c\x39\x9a" + "\x99\x6d\x97\x27\x27\xe6\xab\xdd" + "\x2c\x42\x1b\x35\xdd\x9d\x73\xbb" + "\x6c\xf3\x64\xf1\xfb\xb9\xf7\xe6" + "\x4a\x3c\xc0\x92\xc0\x2e\xb7\x1a" + "\xbe\xab\xb3\x5a\xe5\xea\xb1\x48" + "\x58\x13\x53\x90\xfd\xc3\x8e\x54" + "\xf9\x18\x16\x73\xe8\xcb\x6d\x39" + "\x0e\xd7\xe0\xfe\xb6\x9f\x43\x97" + "\xe8\xd0\x85\x56\x83\x3e\x98\x68" + "\x7f\xbd\x95\xa8\x9a\x61\x21\x8f" + "\x06\x98\x34\xa6\xc8\xd6\x1d\xf3" + "\x3d\x43\xa4\x9a\x8c\xe5\xd3\x5a" + "\x32\xa2\x04\x22\xa4\x19\x1a\x46" + "\x42\x7e\x4d\xe5\xe0\xe6\x0e\xca" + "\xd5\x58\x9d\x2c\xaf\xda\x33\x5c" + "\xb0\x79\x9e\xc9\xfc\xca\xf0\x2f" + "\xa8\xb2\x77\xeb\x7a\xa2\xdd\x37" + "\x35\x83\x07\xd6\x02\x1a\xb6\x6c" + "\x24\xe2\x59\x08\x0e\xfd\x3e\x46" + "\xec\x40\x93\xf4\x00\x26\x4f\x2a" + "\xff\x47\x2f\xeb\x02\x92\x26\x5b" + "\x53\x17\xc2\x8d\x2a\xc7\xa3\x1b" + "\xcd\xbc\xa7\xe8\xd1\x76\xe3\x80" + "\x21\xca\x5d\x3b\xe4\x9c\x8f\xa9" + "\x5b\x7f\x29\x7f\x7c\xd8\xed\x6d" + "\x8c\xb2\x86\x85\xe7\x77\xf2\x85" + "\xab\x38\xa9\x9d\xc1\x4e\xc5\x64" + "\x33\x73\x8b\x59\x03\xad\x05\xdf" + "\x25\x98\x31\xde\xef\x13\xf1\x9b" + "\x3c\x91\x9d\x7b\xb1\xfa\xe6\xbf" + "\x5b\xed\xa5\x55\xe6\xea\x6c\x74" + "\xf4\xb9\xe4\x45\x64\x72\x81\xc2" + "\x4c\x28\xd4\xcd\xac\xe2\xde\xf9" + "\xeb\x5c\xeb\x61\x60\x5a\xe5\x28", + .ksize = 1088, + .plaintext = "", + .psize = 0, + .digest = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00", + }, { + .key = "\x29\x21\x43\xcb\xcb\x13\x07\xde" + "\xbf\x48\xdf\x8a\x7f\xa2\x84\xde" + "\x72\x23\x9d\xf5\xf0\x07\xf2\x4c" + "\x20\x3a\x93\xb9\xcd\x5d\xfe\xcb" + "\x99\x2c\x2b\x58\xc6\x50\x5f\x94" + "\x56\xc3\x7c\x0d\x02\x3f\xb8\x5e" + "\x7b\xc0\x6c\x51\x34\x76\xc0\x0e" + "\xc6\x22\xc8\x9e\x92\xa0\x21\xc9" + "\x85\x5c\x7c\xf8\xe2\x64\x47\xc9" + "\xe4\xa2\x57\x93\xf8\xa2\x69\xcd" + "\x62\x98\x99\xf4\xd7\x7b\x14\xb1" + "\xd8\x05\xff\x04\x15\xc9\xe1\x6e" + "\x9b\xe6\x50\x6b\x0b\x3f\x22\x1f" + "\x08\xde\x0c\x5b\x08\x7e\xc6\x2f" + "\x6c\xed\xd6\xb2\x15\xa4\xb3\xf9" + "\xa7\x46\x38\x2a\xea\x69\xa5\xde" + "\x02\xc3\x96\x89\x4d\x55\x3b\xed" + "\x3d\x3a\x85\x77\xbf\x97\x45\x5c" + "\x9e\x02\x69\xe2\x1b\x68\xbe\x96" + "\xfb\x64\x6f\x0f\xf6\x06\x40\x67" + "\xfa\x04\xe3\x55\xfa\xbe\xa4\x60" + "\xef\x21\x66\x97\xe6\x9d\x5c\x1f" + "\x62\x37\xaa\x31\xde\xe4\x9c\x28" + "\x95\xe0\x22\x86\xf4\x4d\xf3\x07" + "\xfd\x5f\x3a\x54\x2c\x51\x80\x71" + "\xba\x78\x69\x5b\x65\xab\x1f\x81" + "\xed\x3b\xff\x34\xa3\xfb\xbc\x73" + "\x66\x7d\x13\x7f\xdf\x6e\xe2\xe2" + "\xeb\x4f\x6c\xda\x7d\x33\x57\xd0" + "\xd3\x7c\x95\x4f\x33\x58\x21\xc7" + "\xc0\xe5\x6f\x42\x26\xc6\x1f\x5e" + "\x85\x1b\x98\x9a\xa2\x1e\x55\x77" + "\x23\xdf\x81\x5e\x79\x55\x05\xfc" + "\xfb\xda\xee\xba\x5a\xba\xf7\x77" + "\x7f\x0e\xd3\xe1\x37\xfe\x8d\x2b" + "\xd5\x3f\xfb\xd0\xc0\x3c\x0b\x3f" + "\xcf\x3c\x14\xcf\xfb\x46\x72\x4c" + "\x1f\x39\xe2\xda\x03\x71\x6d\x23" + "\xef\x93\xcd\x39\xd9\x37\x80\x4d" + "\x65\x61\xd1\x2c\x03\xa9\x47\x72" + "\x4d\x1e\x0e\x16\x33\x0f\x21\x17" + "\xec\x92\xea\x6f\x37\x22\xa4\xd8" + "\x03\x33\x9e\xd8\x03\x69\x9a\xe8" + "\xb2\x57\xaf\x78\x99\x05\x12\xab" + "\x48\x90\x80\xf0\x12\x9b\x20\x64" + "\x7a\x1d\x47\x5f\xba\x3c\xf9\xc3" + "\x0a\x0d\x8d\xa1\xf9\x1b\x82\x13" + "\x3e\x0d\xec\x0a\x83\xc0\x65\xe1" + "\xe9\x95\xff\x97\xd6\xf2\xe4\xd5" + "\x86\xc0\x1f\x29\x27\x63\xd7\xde" + "\xb7\x0a\x07\x99\x04\x2d\xa3\x89" + "\xa2\x43\xcf\xf3\xe1\x43\xac\x4a" + "\x06\x97\xd0\x05\x4f\x87\xfa\xf9" + "\x9b\xbf\x52\x70\xbd\xbc\x6c\xf3" + "\x03\x13\x60\x41\x28\x09\xec\xcc" + "\xb1\x1a\xec\xd6\xfb\x6f\x2a\x89" + "\x5d\x0b\x53\x9c\x59\xc1\x84\x21" + "\x33\x51\x47\x19\x31\x9c\xd4\x0a" + "\x4d\x04\xec\x50\x90\x61\xbd\xbc" + "\x7e\xc8\xd9\x6c\x98\x1d\x45\x41" + "\x17\x5e\x97\x1c\xc5\xa8\xe8\xea" + "\x46\x58\x53\xf7\x17\xd5\xad\x11" + "\xc8\x54\xf5\x7a\x33\x90\xf5\x19" + "\xba\x36\xb4\xfc\x52\xa5\x72\x3d" + "\x14\xbb\x55\xa7\xe9\xe3\x12\xf7" + "\x1c\x30\xa2\x82\x03\xbf\x53\x91" + "\x2e\x60\x41\x9f\x5b\x69\x39\xf6" + "\x4d\xc8\xf8\x46\x7a\x7f\xa4\x98" + "\x36\xff\x06\xcb\xca\xe7\x33\xf2" + "\xc0\x4a\xf4\x3c\x14\x44\x5f\x6b" + "\x75\xef\x02\x36\x75\x08\x14\xfd" + "\x10\x8e\xa5\x58\xd0\x30\x46\x49" + "\xaf\x3a\xf8\x40\x3d\x35\xdb\x84" + "\x11\x2e\x97\x6a\xb7\x87\x7f\xad" + "\xf1\xfa\xa5\x63\x60\xd8\x5e\xbf" + "\x41\x78\x49\xcf\x77\xbb\x56\xbb" + "\x7d\x01\x67\x05\x22\xc8\x8f\x41" + "\xba\x81\xd2\xca\x2c\x38\xac\x76" + "\x06\xc1\x1a\xc2\xce\xac\x90\x67" + "\x57\x3e\x20\x12\x5b\xd9\x97\x58" + "\x65\x05\xb7\x04\x61\x7e\xd8\x3a" + "\xbf\x55\x3b\x13\xe9\x34\x5a\x37" + "\x36\xcb\x94\x45\xc5\x32\xb3\xa0" + "\x0c\x3e\x49\xc5\xd3\xed\xa7\xf0" + "\x1c\x69\xcc\xea\xcc\x83\xc9\x16" + "\x95\x72\x4b\xf4\x89\xd5\xb9\x10" + "\xf6\x2d\x60\x15\xea\x3c\x06\x66" + "\x9f\x82\xad\x17\xce\xd2\xa4\x48" + "\x7c\x65\xd9\xf8\x02\x4d\x9b\x4c" + "\x89\x06\x3a\x34\x85\x48\x89\x86" + "\xf9\x24\xa9\x54\x72\xdb\x44\x95" + "\xc7\x44\x1c\x19\x11\x4c\x04\xdc" + "\x13\xb9\x67\xc8\xc3\x3a\x6a\x50" + "\xfa\xd1\xfb\xe1\x88\xb6\xf1\xa3" + "\xc5\x3b\xdc\x38\x45\x16\x26\x02" + "\x3b\xb8\x8f\x8b\x58\x7d\x23\x04" + "\x50\x6b\x81\x9f\xae\x66\xac\x6f" + "\xcf\x2a\x9d\xf1\xfd\x1d\x57\x07" + "\xbe\x58\xeb\x77\x0c\xe3\xc2\x19" + "\x14\x74\x1b\x51\x1c\x4f\x41\xf3" + "\x32\x89\xb3\xe7\xde\x62\xf6\x5f" + "\xc7\x6a\x4a\x2a\x5b\x0f\x5f\x87" + "\x9c\x08\xb9\x02\x88\xc8\x29\xb7" + "\x94\x52\xfa\x52\xfe\xaa\x50\x10" + "\xba\x48\x75\x5e\x11\x1b\xe6\x39" + "\xd7\x82\x2c\x87\xf1\x1e\xa4\x38" + "\x72\x3e\x51\xe7\xd8\x3e\x5b\x7b" + "\x31\x16\x89\xba\xd6\xad\x18\x5e" + "\xba\xf8\x12\xb3\xf4\x6c\x47\x30" + "\xc0\x38\x58\xb3\x10\x8d\x58\x5d" + "\xb4\xfb\x19\x7e\x41\xc3\x66\xb8" + "\xd6\x72\x84\xe1\x1a\xc2\x71\x4c" + "\x0d\x4a\x21\x7a\xab\xa2\xc0\x36" + "\x15\xc5\xe9\x46\xd7\x29\x17\x76" + "\x5e\x47\x36\x7f\x72\x05\xa7\xcc" + "\x36\x63\xf9\x47\x7d\xe6\x07\x3c" + "\x8b\x79\x1d\x96\x61\x8d\x90\x65" + "\x7c\xf5\xeb\x4e\x6e\x09\x59\x6d" + "\x62\x50\x1b\x0f\xe0\xdc\x78\xf2" + "\x5b\x83\x1a\xa1\x11\x75\xfd\x18" + "\xd7\xe2\x8d\x65\x14\x21\xce\xbe" + "\xb5\x87\xe3\x0a\xda\x24\x0a\x64" + "\xa9\x9f\x03\x8d\x46\x5d\x24\x1a" + "\x8a\x0c\x42\x01\xca\xb1\x5f\x7c" + "\xa5\xac\x32\x4a\xb8\x07\x91\x18" + "\x6f\xb0\x71\x3c\xc9\xb1\xa8\xf8" + "\x5f\x69\xa5\xa1\xca\x9e\x7a\xaa" + "\xac\xe9\xc7\x47\x41\x75\x25\xc3" + "\x73\xe2\x0b\xdd\x6d\x52\x71\xbe" + "\xc5\xdc\xb4\xe7\x01\x26\x53\x77" + "\x86\x90\x85\x68\x6b\x7b\x03\x53" + "\xda\x52\x52\x51\x68\xc8\xf3\xec" + "\x6c\xd5\x03\x7a\xa3\x0e\xb4\x02" + "\x5f\x1a\xab\xee\xca\x67\x29\x7b" + "\xbd\x96\x59\xb3\x8b\x32\x7a\x92" + "\x9f\xd8\x25\x2b\xdf\xc0\x4c\xda", + .ksize = 1088, + .plaintext = "\xbc\xda\x81\xa8\x78\x79\x1c\xbf" + "\x77\x53\xba\x4c\x30\x5b\xb8\x33", + .psize = 16, + .digest = "\x04\xbf\x7f\x6a\xce\x72\xea\x6a" + "\x79\xdb\xb0\xc9\x60\xf6\x12\xcc", + .np = 6, + .tap = { 4, 4, 1, 1, 1, 5 }, + }, { + .key = "\x65\x4d\xe3\xf8\xd2\x4c\xac\x28" + "\x68\xf5\xb3\x81\x71\x4b\xa1\xfa" + "\x04\x0e\xd3\x81\x36\xbe\x0c\x81" + "\x5e\xaf\xbc\x3a\xa4\xc0\x8e\x8b" + "\x55\x63\xd3\x52\x97\x88\xd6\x19" + "\xbc\x96\xdf\x49\xff\x04\x63\xf5" + "\x0c\x11\x13\xaa\x9e\x1f\x5a\xf7" + "\xdd\xbd\x37\x80\xc3\xd0\xbe\xa7" + "\x05\xc8\x3c\x98\x1e\x05\x3c\x84" + "\x39\x61\xc4\xed\xed\x71\x1b\xc4" + "\x74\x45\x2c\xa1\x56\x70\x97\xfd" + "\x44\x18\x07\x7d\xca\x60\x1f\x73" + "\x3b\x6d\x21\xcb\x61\x87\x70\x25" + "\x46\x21\xf1\x1f\x21\x91\x31\x2d" + "\x5d\xcc\xb7\xd1\x84\x3e\x3d\xdb" + "\x03\x53\x2a\x82\xa6\x9a\x95\xbc" + "\x1a\x1e\x0a\x5e\x07\x43\xab\x43" + "\xaf\x92\x82\x06\x91\x04\x09\xf4" + "\x17\x0a\x9a\x2c\x54\xdb\xb8\xf4" + "\xd0\xf0\x10\x66\x24\x8d\xcd\xda" + "\xfe\x0e\x45\x9d\x6f\xc4\x4e\xf4" + "\x96\xaf\x13\xdc\xa9\xd4\x8c\xc4" + "\xc8\x57\x39\x3c\xc2\xd3\x0a\x76" + "\x4a\x1f\x75\x83\x44\xc7\xd1\x39" + "\xd8\xb5\x41\xba\x73\x87\xfa\x96" + "\xc7\x18\x53\xfb\x9b\xda\xa0\x97" + "\x1d\xee\x60\x85\x9e\x14\xc3\xce" + "\xc4\x05\x29\x3b\x95\x30\xa3\xd1" + "\x9f\x82\x6a\x04\xf5\xa7\x75\x57" + "\x82\x04\xfe\x71\x51\x71\xb1\x49" + "\x50\xf8\xe0\x96\xf1\xfa\xa8\x88" + "\x3f\xa0\x86\x20\xd4\x60\x79\x59" + "\x17\x2d\xd1\x09\xf4\xec\x05\x57" + "\xcf\x62\x7e\x0e\x7e\x60\x78\xe6" + "\x08\x60\x29\xd8\xd5\x08\x1a\x24" + "\xc4\x6c\x24\xe7\x92\x08\x3d\x8a" + "\x98\x7a\xcf\x99\x0a\x65\x0e\xdc" + "\x8c\x8a\xbe\x92\x82\x91\xcc\x62" + "\x30\xb6\xf4\x3f\xc6\x8a\x7f\x12" + "\x4a\x8a\x49\xfa\x3f\x5c\xd4\x5a" + "\xa6\x82\xa3\xe6\xaa\x34\x76\xb2" + "\xab\x0a\x30\xef\x6c\x77\x58\x3f" + "\x05\x6b\xcc\x5c\xae\xdc\xd7\xb9" + "\x51\x7e\x8d\x32\x5b\x24\x25\xbe" + "\x2b\x24\x01\xcf\x80\xda\x16\xd8" + "\x90\x72\x2c\xad\x34\x8d\x0c\x74" + "\x02\xcb\xfd\xcf\x6e\xef\x97\xb5" + "\x4c\xf2\x68\xca\xde\x43\x9e\x8a" + "\xc5\x5f\x31\x7f\x14\x71\x38\xec" + "\xbd\x98\xe5\x71\xc4\xb5\xdb\xef" + "\x59\xd2\xca\xc0\xc1\x86\x75\x01" + "\xd4\x15\x0d\x6f\xa4\xf7\x7b\x37" + "\x47\xda\x18\x93\x63\xda\xbe\x9e" + "\x07\xfb\xb2\x83\xd5\xc4\x34\x55" + "\xee\x73\xa1\x42\x96\xf9\x66\x41" + "\xa4\xcc\xd2\x93\x6e\xe1\x0a\xbb" + "\xd2\xdd\x18\x23\xe6\x6b\x98\x0b" + "\x8a\x83\x59\x2c\xc3\xa6\x59\x5b" + "\x01\x22\x59\xf7\xdc\xb0\x87\x7e" + "\xdb\x7d\xf4\x71\x41\xab\xbd\xee" + "\x79\xbe\x3c\x01\x76\x0b\x2d\x0a" + "\x42\xc9\x77\x8c\xbb\x54\x95\x60" + "\x43\x2e\xe0\x17\x52\xbd\x90\xc9" + "\xc2\x2c\xdd\x90\x24\x22\x76\x40" + "\x5c\xb9\x41\xc9\xa1\xd5\xbd\xe3" + "\x44\xe0\xa4\xab\xcc\xb8\xe2\x32" + "\x02\x15\x04\x1f\x8c\xec\x5d\x14" + "\xac\x18\xaa\xef\x6e\x33\x19\x6e" + "\xde\xfe\x19\xdb\xeb\x61\xca\x18" + "\xad\xd8\x3d\xbf\x09\x11\xc7\xa5" + "\x86\x0b\x0f\xe5\x3e\xde\xe8\xd9" + "\x0a\x69\x9e\x4c\x20\xff\xf9\xc5" + "\xfa\xf8\xf3\x7f\xa5\x01\x4b\x5e" + "\x0f\xf0\x3b\x68\xf0\x46\x8c\x2a" + "\x7a\xc1\x8f\xa0\xfe\x6a\x5b\x44" + "\x70\x5c\xcc\x92\x2c\x6f\x0f\xbd" + "\x25\x3e\xb7\x8e\x73\x58\xda\xc9" + "\xa5\xaa\x9e\xf3\x9b\xfd\x37\x3e" + "\xe2\x88\xa4\x7b\xc8\x5c\xa8\x93" + "\x0e\xe7\x9a\x9c\x2e\x95\x18\x9f" + "\xc8\x45\x0c\x88\x9e\x53\x4f\x3a" + "\x76\xc1\x35\xfa\x17\xd8\xac\xa0" + "\x0c\x2d\x47\x2e\x4f\x69\x9b\xf7" + "\xd0\xb6\x96\x0c\x19\xb3\x08\x01" + "\x65\x7a\x1f\xc7\x31\x86\xdb\xc8" + "\xc1\x99\x8f\xf8\x08\x4a\x9d\x23" + "\x22\xa8\xcf\x27\x01\x01\x88\x93" + "\x9c\x86\x45\xbd\xe0\x51\xca\x52" + "\x84\xba\xfe\x03\xf7\xda\xc5\xce" + "\x3e\x77\x75\x86\xaf\x84\xc8\x05" + "\x44\x01\x0f\x02\xf3\x58\xb0\x06" + "\x5a\xd7\x12\x30\x8d\xdf\x1f\x1f" + "\x0a\xe6\xd2\xea\xf6\x3a\x7a\x99" + "\x63\xe8\xd2\xc1\x4a\x45\x8b\x40" + "\x4d\x0a\xa9\x76\x92\xb3\xda\x87" + "\x36\x33\xf0\x78\xc3\x2f\x5f\x02" + "\x1a\x6a\x2c\x32\xcd\x76\xbf\xbd" + "\x5a\x26\x20\x28\x8c\x8c\xbc\x52" + "\x3d\x0a\xc9\xcb\xab\xa4\x21\xb0" + "\x54\x40\x81\x44\xc7\xd6\x1c\x11" + "\x44\xc6\x02\x92\x14\x5a\xbf\x1a" + "\x09\x8a\x18\xad\xcd\x64\x3d\x53" + "\x4a\xb6\xa5\x1b\x57\x0e\xef\xe0" + "\x8c\x44\x5f\x7d\xbd\x6c\xfd\x60" + "\xae\x02\x24\xb6\x99\xdd\x8c\xaf" + "\x59\x39\x75\x3c\xd1\x54\x7b\x86" + "\xcc\x99\xd9\x28\x0c\xb0\x94\x62" + "\xf9\x51\xd1\x19\x96\x2d\x66\xf5" + "\x55\xcf\x9e\x59\xe2\x6b\x2c\x08" + "\xc0\x54\x48\x24\x45\xc3\x8c\x73" + "\xea\x27\x6e\x66\x7d\x1d\x0e\x6e" + "\x13\xe8\x56\x65\x3a\xb0\x81\x5c" + "\xf0\xe8\xd8\x00\x6b\xcd\x8f\xad" + "\xdd\x53\xf3\xa4\x6c\x43\xd6\x31" + "\xaf\xd2\x76\x1e\x91\x12\xdb\x3c" + "\x8c\xc2\x81\xf0\x49\xdb\xe2\x6b" + "\x76\x62\x0a\x04\xe4\xaa\x8a\x7c" + "\x08\x0b\x5d\xd0\xee\x1d\xfb\xc4" + "\x02\x75\x42\xd6\xba\xa7\x22\xa8" + "\x47\x29\xb7\x85\x6d\x93\x3a\xdb" + "\x00\x53\x0b\xa2\xeb\xf8\xfe\x01" + "\x6f\x8a\x31\xd6\x17\x05\x6f\x67" + "\x88\x95\x32\xfe\x4f\xa6\x4b\xf8" + "\x03\xe4\xcd\x9a\x18\xe8\x4e\x2d" + "\xf7\x97\x9a\x0c\x7d\x9f\x7e\x44" + "\x69\x51\xe0\x32\x6b\x62\x86\x8f" + "\xa6\x8e\x0b\x21\x96\xe5\xaf\x77" + "\xc0\x83\xdf\xa5\x0e\xd0\xa1\x04" + "\xaf\xc1\x10\xcb\x5a\x40\xe4\xe3" + "\x38\x7e\x07\xe8\x4d\xfa\xed\xc5" + "\xf0\x37\xdf\xbb\x8a\xcf\x3d\xdc" + "\x61\xd2\xc6\x2b\xff\x07\xc9\x2f" + "\x0c\x2d\x5c\x07\xa8\x35\x6a\xfc" + "\xae\x09\x03\x45\x74\x51\x4d\xc4" + "\xb8\x23\x87\x4a\x99\x27\x20\x87" + "\x62\x44\x0a\x4a\xce\x78\x47\x22", + .ksize = 1088, + .plaintext = "\x8e\xb0\x4c\xde\x9c\x4a\x04\x5a" + "\xf6\xa9\x7f\x45\x25\xa5\x7b\x3a" + "\xbc\x4d\x73\x39\x81\xb5\xbd\x3d" + "\x21\x6f\xd7\x37\x50\x3c\x7b\x28" + "\xd1\x03\x3a\x17\xed\x7b\x7c\x2a" + "\x16\xbc\xdf\x19\x89\x52\x71\x31" + "\xb6\xc0\xfd\xb5\xd3\xba\x96\x99" + "\xb6\x34\x0b\xd0\x99\x93\xfc\x1a" + "\x01\x3c\x85\xc6\x9b\x78\x5c\x8b" + "\xfe\xae\xd2\xbf\xb2\x6f\xf9\xed" + "\xc8\x25\x17\xfe\x10\x3b\x7d\xda" + "\xf4\x8d\x35\x4b\x7c\x7b\x82\xe7" + "\xc2\xb3\xee\x60\x4a\x03\x86\xc9" + "\x4e\xb5\xc4\xbe\xd2\xbd\x66\xf1" + "\x13\xf1\x09\xab\x5d\xca\x63\x1f" + "\xfc\xfb\x57\x2a\xfc\xca\x66\xd8" + "\x77\x84\x38\x23\x1d\xac\xd3\xb3" + "\x7a\xad\x4c\x70\xfa\x9c\xc9\x61" + "\xa6\x1b\xba\x33\x4b\x4e\x33\xec" + "\xa0\xa1\x64\x39\x40\x05\x1c\xc2" + "\x3f\x49\x9d\xae\xf2\xc5\xf2\xc5" + "\xfe\xe8\xf4\xc2\xf9\x96\x2d\x28" + "\x92\x30\x44\xbc\xd2\x7f\xe1\x6e" + "\x62\x02\x8f\x3d\x1c\x80\xda\x0e" + "\x6a\x90\x7e\x75\xff\xec\x3e\xc4" + "\xcd\x16\x34\x3b\x05\x6d\x4d\x20" + "\x1c\x7b\xf5\x57\x4f\xfa\x3d\xac" + "\xd0\x13\x55\xe8\xb3\xe1\x1b\x78" + "\x30\xe6\x9f\x84\xd4\x69\xd1\x08" + "\x12\x77\xa7\x4a\xbd\xc0\xf2\xd2" + "\x78\xdd\xa3\x81\x12\xcb\x6c\x14" + "\x90\x61\xe2\x84\xc6\x2b\x16\xcc" + "\x40\x99\x50\x88\x01\x09\x64\x4f" + "\x0a\x80\xbe\x61\xae\x46\xc9\x0a" + "\x5d\xe0\xfb\x72\x7a\x1a\xdd\x61" + "\x63\x20\x05\xa0\x4a\xf0\x60\x69" + "\x7f\x92\xbc\xbf\x4e\x39\x4d\xdd" + "\x74\xd1\xb7\xc0\x5a\x34\xb7\xae" + "\x76\x65\x2e\xbc\x36\xb9\x04\x95" + "\x42\xe9\x6f\xca\x78\xb3\x72\x07" + "\xa3\xba\x02\x94\x67\x4c\xb1\xd7" + "\xe9\x30\x0d\xf0\x3b\xb8\x10\x6d" + "\xea\x2b\x21\xbf\x74\x59\x82\x97" + "\x85\xaa\xf1\xd7\x54\x39\xeb\x05" + "\xbd\xf3\x40\xa0\x97\xe6\x74\xfe" + "\xb4\x82\x5b\xb1\x36\xcb\xe8\x0d" + "\xce\x14\xd9\xdf\xf1\x94\x22\xcd" + "\xd6\x00\xba\x04\x4c\x05\x0c\xc0" + "\xd1\x5a\xeb\x52\xd5\xa8\x8e\xc8" + "\x97\xa1\xaa\xc1\xea\xc1\xbe\x7c" + "\x36\xb3\x36\xa0\xc6\x76\x66\xc5" + "\xe2\xaf\xd6\x5c\xe2\xdb\x2c\xb3" + "\x6c\xb9\x99\x7f\xff\x9f\x03\x24" + "\xe1\x51\x44\x66\xd8\x0c\x5d\x7f" + "\x5c\x85\x22\x2a\xcf\x6d\x79\x28" + "\xab\x98\x01\x72\xfe\x80\x87\x5f" + "\x46\xba\xef\x81\x24\xee\xbf\xb0" + "\x24\x74\xa3\x65\x97\x12\xc4\xaf" + "\x8b\xa0\x39\xda\x8a\x7e\x74\x6e" + "\x1b\x42\xb4\x44\x37\xfc\x59\xfd" + "\x86\xed\xfb\x8c\x66\x33\xda\x63" + "\x75\xeb\xe1\xa4\x85\x4f\x50\x8f" + "\x83\x66\x0d\xd3\x37\xfa\xe6\x9c" + "\x4f\x30\x87\x35\x18\xe3\x0b\xb7" + "\x6e\x64\x54\xcd\x70\xb3\xde\x54" + "\xb7\x1d\xe6\x4c\x4d\x55\x12\x12" + "\xaf\x5f\x7f\x5e\xee\x9d\xe8\x8e" + "\x32\x9d\x4e\x75\xeb\xc6\xdd\xaa" + "\x48\x82\xa4\x3f\x3c\xd7\xd3\xa8" + "\x63\x9e\x64\xfe\xe3\x97\x00\x62" + "\xe5\x40\x5d\xc3\xad\x72\xe1\x28" + "\x18\x50\xb7\x75\xef\xcd\x23\xbf" + "\x3f\xc0\x51\x36\xf8\x41\xc3\x08" + "\xcb\xf1\x8d\x38\x34\xbd\x48\x45" + "\x75\xed\xbc\x65\x7b\xb5\x0c\x9b" + "\xd7\x67\x7d\x27\xb4\xc4\x80\xd7" + "\xa9\xb9\xc7\x4a\x97\xaa\xda\xc8" + "\x3c\x74\xcf\x36\x8f\xe4\x41\xe3" + "\xd4\xd3\x26\xa7\xf3\x23\x9d\x8f" + "\x6c\x20\x05\x32\x3e\xe0\xc3\xc8" + "\x56\x3f\xa7\x09\xb7\xfb\xc7\xf7" + "\xbe\x2a\xdd\x0f\x06\x7b\x0d\xdd" + "\xb0\xb4\x86\x17\xfd\xb9\x04\xe5" + "\xc0\x64\x5d\xad\x2a\x36\x38\xdb" + "\x24\xaf\x5b\xff\xca\xf9\x41\xe8" + "\xf9\x2f\x1e\x5e\xf9\xf5\xd5\xf2" + "\xb2\x88\xca\xc9\xa1\x31\xe2\xe8" + "\x10\x95\x65\xbf\xf1\x11\x61\x7a" + "\x30\x1a\x54\x90\xea\xd2\x30\xf6" + "\xa5\xad\x60\xf9\x4d\x84\x21\x1b" + "\xe4\x42\x22\xc8\x12\x4b\xb0\x58" + "\x3e\x9c\x2d\x32\x95\x0a\x8e\xb0" + "\x0a\x7e\x77\x2f\xe8\x97\x31\x6a" + "\xf5\x59\xb4\x26\xe6\x37\x12\xc9" + "\xcb\xa0\x58\x33\x6f\xd5\x55\x55" + "\x3c\xa1\x33\xb1\x0b\x7e\x2e\xb4" + "\x43\x2a\x84\x39\xf0\x9c\xf4\x69" + "\x4f\x1e\x79\xa6\x15\x1b\x87\xbb" + "\xdb\x9b\xe0\xf1\x0b\xba\xe3\x6e" + "\xcc\x2f\x49\x19\x22\x29\xfc\x71" + "\xbb\x77\x38\x18\x61\xaf\x85\x76" + "\xeb\xd1\x09\xcc\x86\x04\x20\x9a" + "\x66\x53\x2f\x44\x8b\xc6\xa3\xd2" + "\x5f\xc7\x79\x82\x66\xa8\x6e\x75" + "\x7d\x94\xd1\x86\x75\x0f\xa5\x4f" + "\x3c\x7a\x33\xce\xd1\x6e\x9d\x7b" + "\x1f\x91\x37\xb8\x37\x80\xfb\xe0" + "\x52\x26\xd0\x9a\xd4\x48\x02\x41" + "\x05\xe3\x5a\x94\xf1\x65\x61\x19" + "\xb8\x88\x4e\x2b\xea\xba\x8b\x58" + "\x8b\x42\x01\x00\xa8\xfe\x00\x5c" + "\xfe\x1c\xee\x31\x15\x69\xfa\xb3" + "\x9b\x5f\x22\x8e\x0d\x2c\xe3\xa5" + "\x21\xb9\x99\x8a\x8e\x94\x5a\xef" + "\x13\x3e\x99\x96\x79\x6e\xd5\x42" + "\x36\x03\xa9\xe2\xca\x65\x4e\x8a" + "\x8a\x30\xd2\x7d\x74\xe7\xf0\xaa" + "\x23\x26\xdd\xcb\x82\x39\xfc\x9d" + "\x51\x76\x21\x80\xa2\xbe\x93\x03" + "\x47\xb0\xc1\xb6\xdc\x63\xfd\x9f" + "\xca\x9d\xa5\xca\x27\x85\xe2\xd8" + "\x15\x5b\x7e\x14\x7a\xc4\x89\xcc" + "\x74\x14\x4b\x46\xd2\xce\xac\x39" + "\x6b\x6a\x5a\xa4\x0e\xe3\x7b\x15" + "\x94\x4b\x0f\x74\xcb\x0c\x7f\xa9" + "\xbe\x09\x39\xa3\xdd\x56\x5c\xc7" + "\x99\x56\x65\x39\xf4\x0b\x7d\x87" + "\xec\xaa\xe3\x4d\x22\x65\x39\x4e", + .psize = 1024, + .digest = "\x64\x3a\xbc\xc3\x3f\x74\x40\x51" + "\x6e\x56\x01\x1a\x51\xec\x36\xde", + .np = 8, + .tap = { 64, 203, 267, 28, 263, 62, 54, 83 }, + }, { + .key = "\x1b\x82\x2e\x1b\x17\x23\xb9\x6d" + "\xdc\x9c\xda\x99\x07\xe3\x5f\xd8" + "\xd2\xf8\x43\x80\x8d\x86\x7d\x80" + "\x1a\xd0\xcc\x13\xb9\x11\x05\x3f" + "\x7e\xcf\x7e\x80\x0e\xd8\x25\x48" + "\x8b\xaa\x63\x83\x92\xd0\x72\xf5" + "\x4f\x67\x7e\x50\x18\x25\xa4\xd1" + "\xe0\x7e\x1e\xba\xd8\xa7\x6e\xdb" + "\x1a\xcc\x0d\xfe\x9f\x6d\x22\x35" + "\xe1\xe6\xe0\xa8\x7b\x9c\xb1\x66" + "\xa3\xf8\xff\x4d\x90\x84\x28\xbc" + "\xdc\x19\xc7\x91\x49\xfc\xf6\x33" + "\xc9\x6e\x65\x7f\x28\x6f\x68\x2e" + "\xdf\x1a\x75\xe9\xc2\x0c\x96\xb9" + "\x31\x22\xc4\x07\xc6\x0a\x2f\xfd" + "\x36\x06\x5f\x5c\xc5\xb1\x3a\xf4" + "\x5e\x48\xa4\x45\x2b\x88\xa7\xee" + "\xa9\x8b\x52\xcc\x99\xd9\x2f\xb8" + "\xa4\x58\x0a\x13\xeb\x71\x5a\xfa" + "\xe5\x5e\xbe\xf2\x64\xad\x75\xbc" + "\x0b\x5b\x34\x13\x3b\x23\x13\x9a" + "\x69\x30\x1e\x9a\xb8\x03\xb8\x8b" + "\x3e\x46\x18\x6d\x38\xd9\xb3\xd8" + "\xbf\xf1\xd0\x28\xe6\x51\x57\x80" + "\x5e\x99\xfb\xd0\xce\x1e\x83\xf7" + "\xe9\x07\x5a\x63\xa9\xef\xce\xa5" + "\xfb\x3f\x37\x17\xfc\x0b\x37\x0e" + "\xbb\x4b\x21\x62\xb7\x83\x0e\xa9" + "\x9e\xb0\xc4\xad\x47\xbe\x35\xe7" + "\x51\xb2\xf2\xac\x2b\x65\x7b\x48" + "\xe3\x3f\x5f\xb6\x09\x04\x0c\x58" + "\xce\x99\xa9\x15\x2f\x4e\xc1\xf2" + "\x24\x48\xc0\xd8\x6c\xd3\x76\x17" + "\x83\x5d\xe6\xe3\xfd\x01\x8e\xf7" + "\x42\xa5\x04\x29\x30\xdf\xf9\x00" + "\x4a\xdc\x71\x22\x1a\x33\x15\xb6" + "\xd7\x72\xfb\x9a\xb8\xeb\x2b\x38" + "\xea\xa8\x61\xa8\x90\x11\x9d\x73" + "\x2e\x6c\xce\x81\x54\x5a\x9f\xcd" + "\xcf\xd5\xbd\x26\x5d\x66\xdb\xfb" + "\xdc\x1e\x7c\x10\xfe\x58\x82\x10" + "\x16\x24\x01\xce\x67\x55\x51\xd1" + "\xdd\x6b\x44\xa3\x20\x8e\xa9\xa6" + "\x06\xa8\x29\x77\x6e\x00\x38\x5b" + "\xde\x4d\x58\xd8\x1f\x34\xdf\xf9" + "\x2c\xac\x3e\xad\xfb\x92\x0d\x72" + "\x39\xa4\xac\x44\x10\xc0\x43\xc4" + "\xa4\x77\x3b\xfc\xc4\x0d\x37\xd3" + "\x05\x84\xda\x53\x71\xf8\x80\xd3" + "\x34\x44\xdb\x09\xb4\x2b\x8e\xe3" + "\x00\x75\x50\x9e\x43\x22\x00\x0b" + "\x7c\x70\xab\xd4\x41\xf1\x93\xcd" + "\x25\x2d\x84\x74\xb5\xf2\x92\xcd" + "\x0a\x28\xea\x9a\x49\x02\x96\xcb" + "\x85\x9e\x2f\x33\x03\x86\x1d\xdc" + "\x1d\x31\xd5\xfc\x9d\xaa\xc5\xe9" + "\x9a\xc4\x57\xf5\x35\xed\xf4\x4b" + "\x3d\x34\xc2\x29\x13\x86\x36\x42" + "\x5d\xbf\x90\x86\x13\x77\xe5\xc3" + "\x62\xb4\xfe\x0b\x70\x39\x35\x65" + "\x02\xea\xf6\xce\x57\x0c\xbb\x74" + "\x29\xe3\xfd\x60\x90\xfd\x10\x38" + "\xd5\x4e\x86\xbd\x37\x70\xf0\x97" + "\xa6\xab\x3b\x83\x64\x52\xca\x66" + "\x2f\xf9\xa4\xca\x3a\x55\x6b\xb0" + "\xe8\x3a\x34\xdb\x9e\x48\x50\x2f" + "\x3b\xef\xfd\x08\x2d\x5f\xc1\x37" + "\x5d\xbe\x73\xe4\xd8\xe9\xac\xca" + "\x8a\xaa\x48\x7c\x5c\xf4\xa6\x96" + "\x5f\xfa\x70\xa6\xb7\x8b\x50\xcb" + "\xa6\xf5\xa9\xbd\x7b\x75\x4c\x22" + "\x0b\x19\x40\x2e\xc9\x39\x39\x32" + "\x83\x03\xa8\xa4\x98\xe6\x8e\x16" + "\xb9\xde\x08\xc5\xfc\xbf\xad\x39" + "\xa8\xc7\x93\x6c\x6f\x23\xaf\xc1" + "\xab\xe1\xdf\xbb\x39\xae\x93\x29" + "\x0e\x7d\x80\x8d\x3e\x65\xf3\xfd" + "\x96\x06\x65\x90\xa1\x28\x64\x4b" + "\x69\xf9\xa8\x84\x27\x50\xfc\x87" + "\xf7\xbf\x55\x8e\x56\x13\x58\x7b" + "\x85\xb4\x6a\x72\x0f\x40\xf1\x4f" + "\x83\x81\x1f\x76\xde\x15\x64\x7a" + "\x7a\x80\xe4\xc7\x5e\x63\x01\x91" + "\xd7\x6b\xea\x0b\x9b\xa2\x99\x3b" + "\x6c\x88\xd8\xfd\x59\x3c\x8d\x22" + "\x86\x56\xbe\xab\xa1\x37\x08\x01" + "\x50\x85\x69\x29\xee\x9f\xdf\x21" + "\x3e\x20\x20\xf5\xb0\xbb\x6b\xd0" + "\x9c\x41\x38\xec\x54\x6f\x2d\xbd" + "\x0f\xe1\xbd\xf1\x2b\x6e\x60\x56" + "\x29\xe5\x7a\x70\x1c\xe2\xfc\x97" + "\x82\x68\x67\xd9\x3d\x1f\xfb\xd8" + "\x07\x9f\xbf\x96\x74\xba\x6a\x0e" + "\x10\x48\x20\xd8\x13\x1e\xb5\x44" + "\xf2\xcc\xb1\x8b\xfb\xbb\xec\xd7" + "\x37\x70\x1f\x7c\x55\xd2\x4b\xb9" + "\xfd\x70\x5e\xa3\x91\x73\x63\x52" + "\x13\x47\x5a\x06\xfb\x01\x67\xa5" + "\xc0\xd0\x49\x19\x56\x66\x9a\x77" + "\x64\xaf\x8c\x25\x91\x52\x87\x0e" + "\x18\xf3\x5f\x97\xfd\x71\x13\xf8" + "\x05\xa5\x39\xcc\x65\xd3\xcc\x63" + "\x5b\xdb\x5f\x7e\x5f\x6e\xad\xc4" + "\xf4\xa0\xc5\xc2\x2b\x4d\x97\x38" + "\x4f\xbc\xfa\x33\x17\xb4\x47\xb9" + "\x43\x24\x15\x8d\xd2\xed\x80\x68" + "\x84\xdb\x04\x80\xca\x5e\x6a\x35" + "\x2c\x2c\xe7\xc5\x03\x5f\x54\xb0" + "\x5e\x4f\x1d\x40\x54\x3d\x78\x9a" + "\xac\xda\x80\x27\x4d\x15\x4c\x1a" + "\x6e\x80\xc9\xc4\x3b\x84\x0e\xd9" + "\x2e\x93\x01\x8c\xc3\xc8\x91\x4b" + "\xb3\xaa\x07\x04\x68\x5b\x93\xa5" + "\xe7\xc4\x9d\xe7\x07\xee\xf5\x3b" + "\x40\x89\xcc\x60\x34\x9d\xb4\x06" + "\x1b\xef\x92\xe6\xc1\x2a\x7d\x0f" + "\x81\xaa\x56\xe3\xd7\xed\xa7\xd4" + "\xa7\x3a\x49\xc4\xad\x81\x5c\x83" + "\x55\x8e\x91\x54\xb7\x7d\x65\xa5" + "\x06\x16\xd5\x9a\x16\xc1\xb0\xa2" + "\x06\xd8\x98\x47\x73\x7e\x73\xa0" + "\xb8\x23\xb1\x52\xbf\x68\x74\x5d" + "\x0b\xcb\xfa\x8c\x46\xe3\x24\xe6" + "\xab\xd4\x69\x8d\x8c\xf2\x8a\x59" + "\xbe\x48\x46\x50\x8c\x9a\xe8\xe3" + "\x31\x55\x0a\x06\xed\x4f\xf8\xb7" + "\x4f\xe3\x85\x17\x30\xbd\xd5\x20" + "\xe7\x5b\xb2\x32\xcf\x6b\x16\x44" + "\xd2\xf5\x7e\xd7\xd1\x2f\xee\x64" + "\x3e\x9d\x10\xef\x27\x35\x43\x64" + "\x67\xfb\x7a\x7b\xe0\x62\x31\x9a" + "\x4d\xdf\xa5\xab\xc0\x20\xbb\x01" + "\xe9\x7b\x54\xf1\xde\xb2\x79\x50" + "\x6c\x4b\x91\xdb\x7f\xbb\x50\xc1" + "\x55\x44\x38\x9a\xe0\x9f\xe8\x29" + "\x6f\x15\xf8\x4e\xa6\xec\xa0\x60", + .ksize = 1088, + .plaintext = "\x15\x68\x9e\x2f\xad\x15\x52\xdf" + "\xf0\x42\x62\x24\x2a\x2d\xea\xbf" + "\xc7\xf3\xb4\x1a\xf5\xed\xb2\x08" + "\x15\x60\x1c\x00\x77\xbf\x0b\x0e" + "\xb7\x2c\xcf\x32\x3a\xc7\x01\x77" + "\xef\xa6\x75\xd0\x29\xc7\x68\x20" + "\xb2\x92\x25\xbf\x12\x34\xe9\xa4" + "\xfd\x32\x7b\x3f\x7c\xbd\xa5\x02" + "\x38\x41\xde\xc9\xc1\x09\xd9\xfc" + "\x6e\x78\x22\x83\x18\xf7\x50\x8d" + "\x8f\x9c\x2d\x02\xa5\x30\xac\xff" + "\xea\x63\x2e\x80\x37\x83\xb0\x58" + "\xda\x2f\xef\x21\x55\xba\x7b\xb1" + "\xb6\xed\xf5\xd2\x4d\xaa\x8c\xa9" + "\xdd\xdb\x0f\xb4\xce\xc1\x9a\xb1" + "\xc1\xdc\xbd\xab\x86\xc2\xdf\x0b" + "\xe1\x2c\xf9\xbe\xf6\xd8\xda\x62" + "\x72\xdd\x98\x09\x52\xc0\xc4\xb6" + "\x7b\x17\x5c\xf5\xd8\x4b\x88\xd6" + "\x6b\xbf\x84\x4a\x3f\xf5\x4d\xd2" + "\x94\xe2\x9c\xff\xc7\x3c\xd9\xc8" + "\x37\x38\xbc\x8c\xf3\xe7\xb7\xd0" + "\x1d\x78\xc4\x39\x07\xc8\x5e\x79" + "\xb6\x5a\x90\x5b\x6e\x97\xc9\xd4" + "\x82\x9c\xf3\x83\x7a\xe7\x97\xfc" + "\x1d\xbb\xef\xdb\xce\xe0\x82\xad" + "\xca\x07\x6c\x54\x62\x6f\x81\xe6" + "\x7a\x5a\x96\x6e\x80\x3a\xa2\x37" + "\x6f\xc6\xa4\x29\xc3\x9e\x19\x94" + "\x9f\xb0\x3e\x38\xfb\x3c\x2b\x7d" + "\xaa\xb8\x74\xda\x54\x23\x51\x12" + "\x4b\x96\x36\x8f\x91\x4f\x19\x37" + "\x83\xc9\xdd\xc7\x1a\x32\x2d\xab" + "\xc7\x89\xe2\x07\x47\x6c\xe8\xa6" + "\x70\x6b\x8e\x0c\xda\x5c\x6a\x59" + "\x27\x33\x0e\xe1\xe1\x20\xe8\xc8" + "\xae\xdc\xd0\xe3\x6d\xa8\xa6\x06" + "\x41\xb4\xd4\xd4\xcf\x91\x3e\x06" + "\xb0\x9a\xf7\xf1\xaa\xa6\x23\x92" + "\x10\x86\xf0\x94\xd1\x7c\x2e\x07" + "\x30\xfb\xc5\xd8\xf3\x12\xa9\xe8" + "\x22\x1c\x97\x1a\xad\x96\xb0\xa1" + "\x72\x6a\x6b\xb4\xfd\xf7\xe8\xfa" + "\xe2\x74\xd8\x65\x8d\x35\x17\x4b" + "\x00\x23\x5c\x8c\x70\xad\x71\xa2" + "\xca\xc5\x6c\x59\xbf\xb4\xc0\x6d" + "\x86\x98\x3e\x19\x5a\x90\x92\xb1" + "\x66\x57\x6a\x91\x68\x7c\xbc\xf3" + "\xf1\xdb\x94\xf8\x48\xf1\x36\xd8" + "\x78\xac\x1c\xa9\xcc\xd6\x27\xba" + "\x91\x54\x22\xf5\xe6\x05\x3f\xcc" + "\xc2\x8f\x2c\x3b\x2b\xc3\x2b\x2b" + "\x3b\xb8\xb6\x29\xb7\x2f\x94\xb6" + "\x7b\xfc\x94\x3e\xd0\x7a\x41\x59" + "\x7b\x1f\x9a\x09\xa6\xed\x4a\x82" + "\x9d\x34\x1c\xbd\x4e\x1c\x3a\x66" + "\x80\x74\x0e\x9a\x4f\x55\x54\x47" + "\x16\xba\x2a\x0a\x03\x35\x99\xa3" + "\x5c\x63\x8d\xa2\x72\x8b\x17\x15" + "\x68\x39\x73\xeb\xec\xf2\xe8\xf5" + "\x95\x32\x27\xd6\xc4\xfe\xb0\x51" + "\xd5\x0c\x50\xc5\xcd\x6d\x16\xb3" + "\xa3\x1e\x95\x69\xad\x78\x95\x06" + "\xb9\x46\xf2\x6d\x24\x5a\x99\x76" + "\x73\x6a\x91\xa6\xac\x12\xe1\x28" + "\x79\xbc\x08\x4e\x97\x00\x98\x63" + "\x07\x1c\x4e\xd1\x68\xf3\xb3\x81" + "\xa8\xa6\x5f\xf1\x01\xc9\xc1\xaf" + "\x3a\x96\xf9\x9d\xb5\x5a\x5f\x8f" + "\x7e\xc1\x7e\x77\x0a\x40\xc8\x8e" + "\xfc\x0e\xed\xe1\x0d\xb0\xe5\x5e" + "\x5e\x6f\xf5\x7f\xab\x33\x7d\xcd" + "\xf0\x09\x4b\xb2\x11\x37\xdc\x65" + "\x97\x32\x62\x71\x3a\x29\x54\xb9" + "\xc7\xa4\xbf\x75\x0f\xf9\x40\xa9" + "\x8d\xd7\x8b\xa7\xe0\x9a\xbe\x15" + "\xc6\xda\xd8\x00\x14\x69\x1a\xaf" + "\x5f\x79\xc3\xf5\xbb\x6c\x2a\x9d" + "\xdd\x3c\x5f\x97\x21\xe1\x3a\x03" + "\x84\x6a\xe9\x76\x11\x1f\xd3\xd5" + "\xf0\x54\x20\x4d\xc2\x91\xc3\xa4" + "\x36\x25\xbe\x1b\x2a\x06\xb7\xf3" + "\xd1\xd0\x55\x29\x81\x4c\x83\xa3" + "\xa6\x84\x1e\x5c\xd1\xd0\x6c\x90" + "\xa4\x11\xf0\xd7\x63\x6a\x48\x05" + "\xbc\x48\x18\x53\xcd\xb0\x8d\xdb" + "\xdc\xfe\x55\x11\x5c\x51\xb3\xab" + "\xab\x63\x3e\x31\x5a\x8b\x93\x63" + "\x34\xa9\xba\x2b\x69\x1a\xc0\xe3" + "\xcb\x41\xbc\xd7\xf5\x7f\x82\x3e" + "\x01\xa3\x3c\x72\xf4\xfe\xdf\xbe" + "\xb1\x67\x17\x2b\x37\x60\x0d\xca" + "\x6f\xc3\x94\x2c\xd2\x92\x6d\x9d" + "\x75\x18\x77\xaa\x29\x38\x96\xed" + "\x0e\x20\x70\x92\xd5\xd0\xb4\x00" + "\xc0\x31\xf2\xc9\x43\x0e\x75\x1d" + "\x4b\x64\xf2\x1f\xf2\x29\x6c\x7b" + "\x7f\xec\x59\x7d\x8c\x0d\xd4\xd3" + "\xac\x53\x4c\xa3\xde\x42\x92\x95" + "\x6d\xa3\x4f\xd0\xe6\x3d\xe7\xec" + "\x7a\x4d\x68\xf1\xfe\x67\x66\x09" + "\x83\x22\xb1\x98\x43\x8c\xab\xb8" + "\x45\xe6\x6d\xdf\x5e\x50\x71\xce" + "\xf5\x4e\x40\x93\x2b\xfa\x86\x0e" + "\xe8\x30\xbd\x82\xcc\x1c\x9c\x5f" + "\xad\xfd\x08\x31\xbe\x52\xe7\xe6" + "\xf2\x06\x01\x62\x25\x15\x99\x74" + "\x33\x51\x52\x57\x3f\x57\x87\x61" + "\xb9\x7f\x29\x3d\xcd\x92\x5e\xa6" + "\x5c\x3b\xf1\xed\x5f\xeb\x82\xed" + "\x56\x7b\x61\xe7\xfd\x02\x47\x0e" + "\x2a\x15\xa4\xce\x43\x86\x9b\xe1" + "\x2b\x4c\x2a\xd9\x42\x97\xf7\x9a" + "\xe5\x47\x46\x48\xd3\x55\x6f\x4d" + "\xd9\xeb\x4b\xdd\x7b\x21\x2f\xb3" + "\xa8\x36\x28\xdf\xca\xf1\xf6\xd9" + "\x10\xf6\x1c\xfd\x2e\x0c\x27\xe0" + "\x01\xb3\xff\x6d\x47\x08\x4d\xd4" + "\x00\x25\xee\x55\x4a\xe9\xe8\x5b" + "\xd8\xf7\x56\x12\xd4\x50\xb2\xe5" + "\x51\x6f\x34\x63\x69\xd2\x4e\x96" + "\x4e\xbc\x79\xbf\x18\xae\xc6\x13" + "\x80\x92\x77\xb0\xb4\x0f\x29\x94" + "\x6f\x4c\xbb\x53\x11\x36\xc3\x9f" + "\x42\x8e\x96\x8a\x91\xc8\xe9\xfc" + "\xfe\xbf\x7c\x2d\x6f\xf9\xb8\x44" + "\x89\x1b\x09\x53\x0a\x2a\x92\xc3" + "\x54\x7a\x3a\xf9\xe2\xe4\x75\x87" + "\xa0\x5e\x4b\x03\x7a\x0d\x8a\xf4" + "\x55\x59\x94\x2b\x63\x96\x0e\xf5", + .psize = 1040, + .digest = "\xb5\xb9\x08\xb3\x24\x3e\x03\xf0" + "\xd6\x0b\x57\xbc\x0a\x6d\x89\x59", + }, { + .key = "\xf6\x34\x42\x71\x35\x52\x8b\x58" + "\x02\x3a\x8e\x4a\x8d\x41\x13\xe9" + "\x7f\xba\xb9\x55\x9d\x73\x4d\xf8" + "\x3f\x5d\x73\x15\xff\xd3\x9e\x7f" + "\x20\x2a\x6a\xa8\xd1\xf0\x8f\x12" + "\x6b\x02\xd8\x6c\xde\xba\x80\x22" + "\x19\x37\xc8\xd0\x4e\x89\x17\x7c" + "\x7c\xdd\x88\xfd\x41\xc0\x04\xb7" + "\x1d\xac\x19\xe3\x20\xc7\x16\xcf" + "\x58\xee\x1d\x7a\x61\x69\xa9\x12" + "\x4b\xef\x4f\xb6\x38\xdd\x78\xf8" + "\x28\xee\x70\x08\xc7\x7c\xcc\xc8" + "\x1e\x41\xf5\x80\x86\x70\xd0\xf0" + "\xa3\x87\x6b\x0a\x00\xd2\x41\x28" + "\x74\x26\xf1\x24\xf3\xd0\x28\x77" + "\xd7\xcd\xf6\x2d\x61\xf4\xa2\x13" + "\x77\xb4\x6f\xa0\xf4\xfb\xd6\xb5" + "\x38\x9d\x5a\x0c\x51\xaf\xad\x63" + "\x27\x67\x8c\x01\xea\x42\x1a\x66" + "\xda\x16\x7c\x3c\x30\x0c\x66\x53" + "\x1c\x88\xa4\x5c\xb2\xe3\x78\x0a" + "\x13\x05\x6d\xe2\xaf\xb3\xe4\x75" + "\x00\x99\x58\xee\x76\x09\x64\xaa" + "\xbb\x2e\xb1\x81\xec\xd8\x0e\xd3" + "\x0c\x33\x5d\xb7\x98\xef\x36\xb6" + "\xd2\x65\x69\x41\x70\x12\xdc\x25" + "\x41\x03\x99\x81\x41\x19\x62\x13" + "\xd1\x0a\x29\xc5\x8c\xe0\x4c\xf3" + "\xd6\xef\x4c\xf4\x1d\x83\x2e\x6d" + "\x8e\x14\x87\xed\x80\xe0\xaa\xd3" + "\x08\x04\x73\x1a\x84\x40\xf5\x64" + "\xbd\x61\x32\x65\x40\x42\xfb\xb0" + "\x40\xf6\x40\x8d\xc7\x7f\x14\xd0" + "\x83\x99\xaa\x36\x7e\x60\xc6\xbf" + "\x13\x8a\xf9\x21\xe4\x7e\x68\x87" + "\xf3\x33\x86\xb4\xe0\x23\x7e\x0a" + "\x21\xb1\xf5\xad\x67\x3c\x9c\x9d" + "\x09\xab\xaf\x5f\xba\xe0\xd0\x82" + "\x48\x22\x70\xb5\x6d\x53\xd6\x0e" + "\xde\x64\x92\x41\xb0\xd3\xfb\xda" + "\x21\xfe\xab\xea\x20\xc4\x03\x58" + "\x18\x2e\x7d\x2f\x03\xa9\x47\x66" + "\xdf\x7b\xa4\x6b\x34\x6b\x55\x9c" + "\x4f\xd7\x9c\x47\xfb\xa9\x42\xec" + "\x5a\x12\xfd\xfe\x76\xa0\x92\x9d" + "\xfe\x1e\x16\xdd\x24\x2a\xe4\x27" + "\xd5\xa9\xf2\x05\x4f\x83\xa2\xaf" + "\xfe\xee\x83\x7a\xad\xde\xdf\x9a" + "\x80\xd5\x81\x14\x93\x16\x7e\x46" + "\x47\xc2\x14\xef\x49\x6e\xb9\xdb" + "\x40\xe8\x06\x6f\x9c\x2a\xfd\x62" + "\x06\x46\xfd\x15\x1d\x36\x61\x6f" + "\x77\x77\x5e\x64\xce\x78\x1b\x85" + "\xbf\x50\x9a\xfd\x67\xa6\x1a\x65" + "\xad\x5b\x33\x30\xf1\x71\xaa\xd9" + "\x23\x0d\x92\x24\x5f\xae\x57\xb0" + "\x24\x37\x0a\x94\x12\xfb\xb5\xb1" + "\xd3\xb8\x1d\x12\x29\xb0\x80\x24" + "\x2d\x47\x9f\x96\x1f\x95\xf1\xb1" + "\xda\x35\xf6\x29\xe0\xe1\x23\x96" + "\xc7\xe8\x22\x9b\x7c\xac\xf9\x41" + "\x39\x01\xe5\x73\x15\x5e\x99\xec" + "\xb4\xc1\xf4\xe7\xa7\x97\x6a\xd5" + "\x90\x9a\xa0\x1d\xf3\x5a\x8b\x5f" + "\xdf\x01\x52\xa4\x93\x31\x97\xb0" + "\x93\x24\xb5\xbc\xb2\x14\x24\x98" + "\x4a\x8f\x19\x85\xc3\x2d\x0f\x74" + "\x9d\x16\x13\x80\x5e\x59\x62\x62" + "\x25\xe0\xd1\x2f\x64\xef\xba\xac" + "\xcd\x09\x07\x15\x8a\xcf\x73\xb5" + "\x8b\xc9\xd8\x24\xb0\x53\xd5\x6f" + "\xe1\x2b\x77\xb1\xc5\xe4\xa7\x0e" + "\x18\x45\xab\x36\x03\x59\xa8\xbd" + "\x43\xf0\xd8\x2c\x1a\x69\x96\xbb" + "\x13\xdf\x6c\x33\x77\xdf\x25\x34" + "\x5b\xa5\x5b\x8c\xf9\x51\x05\xd4" + "\x8b\x8b\x44\x87\x49\xfc\xa0\x8f" + "\x45\x15\x5b\x40\x42\xc4\x09\x92" + "\x98\x0c\x4d\xf4\x26\x37\x1b\x13" + "\x76\x01\x93\x8d\x4f\xe6\xed\x18" + "\xd0\x79\x7b\x3f\x44\x50\xcb\xee" + "\xf7\x4a\xc9\x9e\xe0\x96\x74\xa7" + "\xe6\x93\xb2\x53\xca\x55\xa8\xdc" + "\x1e\x68\x07\x87\xb7\x2e\xc1\x08" + "\xb2\xa4\x5b\xaf\xc6\xdb\x5c\x66" + "\x41\x1c\x51\xd9\xb0\x07\x00\x0d" + "\xf0\x4c\xdc\x93\xde\xa9\x1e\x8e" + "\xd3\x22\x62\xd8\x8b\x88\x2c\xea" + "\x5e\xf1\x6e\x14\x40\xc7\xbe\xaa" + "\x42\x28\xd0\x26\x30\x78\x01\x9b" + "\x83\x07\xbc\x94\xc7\x57\xa2\x9f" + "\x03\x07\xff\x16\xff\x3c\x6e\x48" + "\x0a\xd0\xdd\x4c\xf6\x64\x9a\xf1" + "\xcd\x30\x12\x82\x2c\x38\xd3\x26" + "\x83\xdb\xab\x3e\xc6\xf8\xe6\xfa" + "\x77\x0a\x78\x82\x75\xf8\x63\x51" + "\x59\xd0\x8d\x24\x9f\x25\xe6\xa3" + "\x4c\xbc\x34\xfc\xe3\x10\xc7\x62" + "\xd4\x23\xc8\x3d\xa7\xc6\xa6\x0a" + "\x4f\x7e\x29\x9d\x6d\xbe\xb5\xf1" + "\xdf\xa4\x53\xfa\xc0\x23\x0f\x37" + "\x84\x68\xd0\xb5\xc8\xc6\xae\xf8" + "\xb7\x8d\xb3\x16\xfe\x8f\x87\xad" + "\xd0\xc1\x08\xee\x12\x1c\x9b\x1d" + "\x90\xf8\xd1\x63\xa4\x92\x3c\xf0" + "\xc7\x34\xd8\xf1\x14\xed\xa3\xbc" + "\x17\x7e\xd4\x62\x42\x54\x57\x2c" + "\x3e\x7a\x35\x35\x17\x0f\x0b\x7f" + "\x81\xa1\x3f\xd0\xcd\xc8\x3b\x96" + "\xe9\xe0\x4a\x04\xe1\xb6\x3c\xa1" + "\xd6\xca\xc4\xbd\xb6\xb5\x95\x34" + "\x12\x9d\xc5\x96\xf2\xdf\xba\x54" + "\x76\xd1\xb2\x6b\x3b\x39\xe0\xb9" + "\x18\x62\xfb\xf7\xfc\x12\xf1\x5f" + "\x7e\xc7\xe3\x59\x4c\xa6\xc2\x3d" + "\x40\x15\xf9\xa3\x95\x64\x4c\x74" + "\x8b\x73\x77\x33\x07\xa7\x04\x1d" + "\x33\x5a\x7e\x8f\xbd\x86\x01\x4f" + "\x3e\xb9\x27\x6f\xe2\x41\xf7\x09" + "\x67\xfd\x29\x28\xc5\xe4\xf6\x18" + "\x4c\x1b\x49\xb2\x9c\x5b\xf6\x81" + "\x4f\xbb\x5c\xcc\x0b\xdf\x84\x23" + "\x58\xd6\x28\x34\x93\x3a\x25\x97" + "\xdf\xb2\xc3\x9e\x97\x38\x0b\x7d" + "\x10\xb3\x54\x35\x23\x8c\x64\xee" + "\xf0\xd8\x66\xff\x8b\x22\xd2\x5b" + "\x05\x16\x3c\x89\xf7\xb1\x75\xaf" + "\xc0\xae\x6a\x4f\x3f\xaf\x9a\xf4" + "\xf4\x9a\x24\xd9\x80\x82\xc0\x12" + "\xde\x96\xd1\xbe\x15\x0b\x8d\x6a" + "\xd7\x12\xe4\x85\x9f\x83\xc9\xc3" + "\xff\x0b\xb5\xaf\x3b\xd8\x6d\x67" + "\x81\x45\xe6\xac\xec\xc1\x7b\x16" + "\x18\x0a\xce\x4b\xc0\x2e\x76\xbc" + "\x1b\xfa\xb4\x34\xb8\xfc\x3e\xc8" + "\x5d\x90\x71\x6d\x7a\x79\xef\x06", + .ksize = 1088, + .plaintext = "\xaa\x5d\x54\xcb\xea\x1e\x46\x0f" + "\x45\x87\x70\x51\x8a\x66\x7a\x33" + "\xb4\x18\xff\xa9\x82\xf9\x45\x4b" + "\x93\xae\x2e\x7f\xab\x98\xfe\xbf" + "\x01\xee\xe5\xa0\x37\x8f\x57\xa6" + "\xb0\x76\x0d\xa4\xd6\x28\x2b\x5d" + "\xe1\x03\xd6\x1c\x6f\x34\x0d\xe7" + "\x61\x2d\x2e\xe5\xae\x5d\x47\xc7" + "\x80\x4b\x18\x8f\xa8\x99\xbc\x28" + "\xed\x1d\x9d\x86\x7d\xd7\x41\xd1" + "\xe0\x2b\xe1\x8c\x93\x2a\xa7\x80" + "\xe1\x07\xa0\xa9\x9f\x8c\x8d\x1a" + "\x55\xfc\x6b\x24\x7a\xbd\x3e\x51" + "\x68\x4b\x26\x59\xc8\xa7\x16\xd9" + "\xb9\x61\x13\xde\x8b\x63\x1c\xf6" + "\x60\x01\xfb\x08\xb3\x5b\x0a\xbf" + "\x34\x73\xda\x87\x87\x3d\x6f\x97" + "\x4a\x0c\xa3\x58\x20\xa2\xc0\x81" + "\x5b\x8c\xef\xa9\xc2\x01\x1e\x64" + "\x83\x8c\xbc\x03\xb6\xd0\x29\x9f" + "\x54\xe2\xce\x8b\xc2\x07\x85\x78" + "\x25\x38\x96\x4c\xb4\xbe\x17\x4a" + "\x65\xa6\xfa\x52\x9d\x66\x9d\x65" + "\x4a\xd1\x01\x01\xf0\xcb\x13\xcc" + "\xa5\x82\xf3\xf2\x66\xcd\x3f\x9d" + "\xd1\xaa\xe4\x67\xea\xf2\xad\x88" + "\x56\x76\xa7\x9b\x59\x3c\xb1\x5d" + "\x78\xfd\x69\x79\x74\x78\x43\x26" + "\x7b\xde\x3f\xf1\xf5\x4e\x14\xd9" + "\x15\xf5\x75\xb5\x2e\x19\xf3\x0c" + "\x48\x72\xd6\x71\x6d\x03\x6e\xaa" + "\xa7\x08\xf9\xaa\x70\xa3\x0f\x4d" + "\x12\x8a\xdd\xe3\x39\x73\x7e\xa7" + "\xea\x1f\x6d\x06\x26\x2a\xf2\xc5" + "\x52\xb4\xbf\xfd\x52\x0c\x06\x60" + "\x90\xd1\xb2\x7b\x56\xae\xac\x58" + "\x5a\x6b\x50\x2a\xf5\xe0\x30\x3c" + "\x2a\x98\x0f\x1b\x5b\x0a\x84\x6c" + "\x31\xae\x92\xe2\xd4\xbb\x7f\x59" + "\x26\x10\xb9\x89\x37\x68\x26\xbf" + "\x41\xc8\x49\xc4\x70\x35\x7d\xff" + "\x2d\x7f\xf6\x8a\x93\x68\x8c\x78" + "\x0d\x53\xce\x7d\xff\x7d\xfb\xae" + "\x13\x1b\x75\xc4\x78\xd7\x71\xd8" + "\xea\xd3\xf4\x9d\x95\x64\x8e\xb4" + "\xde\xb8\xe4\xa6\x68\xc8\xae\x73" + "\x58\xaf\xa8\xb0\x5a\x20\xde\x87" + "\x43\xb9\x0f\xe3\xad\x41\x4b\xd5" + "\xb7\xad\x16\x00\xa6\xff\xf6\x74" + "\xbf\x8c\x9f\xb3\x58\x1b\xb6\x55" + "\xa9\x90\x56\x28\xf0\xb5\x13\x4e" + "\x9e\xf7\x25\x86\xe0\x07\x7b\x98" + "\xd8\x60\x5d\x38\x95\x3c\xe4\x22" + "\x16\x2f\xb2\xa2\xaf\xe8\x90\x17" + "\xec\x11\x83\x1a\xf4\xa9\x26\xda" + "\x39\x72\xf5\x94\x61\x05\x51\xec" + "\xa8\x30\x8b\x2c\x13\xd0\x72\xac" + "\xb9\xd2\xa0\x4c\x4b\x78\xe8\x6e" + "\x04\x85\xe9\x04\x49\x82\x91\xff" + "\x89\xe5\xab\x4c\xaa\x37\x03\x12" + "\xca\x8b\x74\x10\xfd\x9e\xd9\x7b" + "\xcb\xdb\x82\x6e\xce\x2e\x33\x39" + "\xce\xd2\x84\x6e\x34\x71\x51\x6e" + "\x0d\xd6\x01\x87\xc7\xfa\x0a\xd3" + "\xad\x36\xf3\x4c\x9f\x96\x5e\x62" + "\x62\x54\xc3\x03\x78\xd6\xab\xdd" + "\x89\x73\x55\x25\x30\xf8\xa7\xe6" + "\x4f\x11\x0c\x7c\x0a\xa1\x2b\x7b" + "\x3d\x0d\xde\x81\xd4\x9d\x0b\xae" + "\xdf\x00\xf9\x4c\xb6\x90\x8e\x16" + "\xcb\x11\xc8\xd1\x2e\x73\x13\x75" + "\x75\x3e\xaa\xf5\xee\x02\xb3\x18" + "\xa6\x2d\xf5\x3b\x51\xd1\x1f\x47" + "\x6b\x2c\xdb\xc4\x10\xe0\xc8\xba" + "\x9d\xac\xb1\x9d\x75\xd5\x41\x0e" + "\x7e\xbe\x18\x5b\xa4\x1f\xf8\x22" + "\x4c\xc1\x68\xda\x6d\x51\x34\x6c" + "\x19\x59\xec\xb5\xb1\xec\xa7\x03" + "\xca\x54\x99\x63\x05\x6c\xb1\xac" + "\x9c\x31\xd6\xdb\xba\x7b\x14\x12" + "\x7a\xc3\x2f\xbf\x8d\xdc\x37\x46" + "\xdb\xd2\xbc\xd4\x2f\xab\x30\xd5" + "\xed\x34\x99\x8e\x83\x3e\xbe\x4c" + "\x86\x79\x58\xe0\x33\x8d\x9a\xb8" + "\xa9\xa6\x90\x46\xa2\x02\xb8\xdd" + "\xf5\xf9\x1a\x5c\x8c\x01\xaa\x6e" + "\xb4\x22\x12\xf5\x0c\x1b\x9b\x7a" + "\xc3\x80\xf3\x06\x00\x5f\x30\xd5" + "\x06\xdb\x7d\x82\xc2\xd4\x0b\x4c" + "\x5f\xe9\xc5\xf5\xdf\x97\x12\xbf" + "\x56\xaf\x9b\x69\xcd\xee\x30\xb4" + "\xa8\x71\xff\x3e\x7d\x73\x7a\xb4" + "\x0d\xa5\x46\x7a\xf3\xf4\x15\x87" + "\x5d\x93\x2b\x8c\x37\x64\xb5\xdd" + "\x48\xd1\xe5\x8c\xae\xd4\xf1\x76" + "\xda\xf4\xba\x9e\x25\x0e\xad\xa3" + "\x0d\x08\x7c\xa8\x82\x16\x8d\x90" + "\x56\x40\x16\x84\xe7\x22\x53\x3a" + "\x58\xbc\xb9\x8f\x33\xc8\xc2\x84" + "\x22\xe6\x0d\xe7\xb3\xdc\x5d\xdf" + "\xd7\x2a\x36\xe4\x16\x06\x07\xd2" + "\x97\x60\xb2\xf5\x5e\x14\xc9\xfd" + "\x8b\x05\xd1\xce\xee\x9a\x65\x99" + "\xb7\xae\x19\xb7\xc8\xbc\xd5\xa2" + "\x7b\x95\xe1\xcc\xba\x0d\xdc\x8a" + "\x1d\x59\x52\x50\xaa\x16\x02\x82" + "\xdf\x61\x33\x2e\x44\xce\x49\xc7" + "\xe5\xc6\x2e\x76\xcf\x80\x52\xf0" + "\x3d\x17\x34\x47\x3f\xd3\x80\x48" + "\xa2\xba\xd5\xc7\x7b\x02\x28\xdb" + "\xac\x44\xc7\x6e\x05\x5c\xc2\x79" + "\xb3\x7d\x6a\x47\x77\x66\xf1\x38" + "\xf0\xf5\x4f\x27\x1a\x31\xca\x6c" + "\x72\x95\x92\x8e\x3f\xb0\xec\x1d" + "\xc7\x2a\xff\x73\xee\xdf\x55\x80" + "\x93\xd2\xbd\x34\xd3\x9f\x00\x51" + "\xfb\x2e\x41\xba\x6c\x5a\x7c\x17" + "\x7f\xe6\x70\xac\x8d\x39\x3f\x77" + "\xe2\x23\xac\x8f\x72\x4e\xe4\x53" + "\xcc\xf1\x1b\xf1\x35\xfe\x52\xa4" + "\xd6\xb8\x40\x6b\xc1\xfd\xa0\xa1" + "\xf5\x46\x65\xc2\x50\xbb\x43\xe2" + "\xd1\x43\x28\x34\x74\xf5\x87\xa0" + "\xf2\x5e\x27\x3b\x59\x2b\x3e\x49" + "\xdf\x46\xee\xaf\x71\xd7\x32\x36" + "\xc7\x14\x0b\x58\x6e\x3e\x2d\x41" + "\xfa\x75\x66\x3a\x54\xe0\xb2\xb9" + "\xaf\xdd\x04\x80\x15\x19\x3f\x6f" + "\xce\x12\xb4\xd8\xe8\x89\x3c\x05" + "\x30\xeb\xf3\x3d\xcd\x27\xec\xdc" + "\x56\x70\x12\xcf\x78\x2b\x77\xbf" + "\x22\xf0\x1b\x17\x9c\xcc\xd6\x1b" + "\x2d\x3d\xa0\x3b\xd8\xc9\x70\xa4" + "\x7a\x3e\x07\xb9\x06\xc3\xfa\xb0" + "\x33\xee\xc1\xd8\xf6\xe0\xf0\xb2" + "\x61\x12\x69\xb0\x5f\x28\x99\xda" + "\xc3\x61\x48\xfa\x07\x16\x03\xc4" + "\xa8\xe1\x3c\xe8\x0e\x64\x15\x30" + "\xc1\x9d\x84\x2f\x73\x98\x0e\x3a" + "\xf2\x86\x21\xa4\x9e\x1d\xb5\x86" + "\x16\xdb\x2b\x9a\x06\x64\x8e\x79" + "\x8d\x76\x3e\xc3\xc2\x64\x44\xe3" + "\xda\xbc\x1a\x52\xd7\x61\x03\x65" + "\x54\x32\x77\x01\xed\x9d\x8a\x43" + "\x25\x24\xe3\xc1\xbe\xb8\x2f\xcb" + "\x89\x14\x64\xab\xf6\xa0\x6e\x02" + "\x57\xe4\x7d\xa9\x4e\x9a\x03\x36" + "\xad\xf1\xb1\xfc\x0b\xe6\x79\x51" + "\x9f\x81\x77\xc4\x14\x78\x9d\xbf" + "\xb6\xd6\xa3\x8c\xba\x0b\x26\xe7" + "\xc8\xb9\x5c\xcc\xe1\x5f\xd5\xc6" + "\xc4\xca\xc2\xa3\x45\xba\x94\x13" + "\xb2\x8f\xc3\x54\x01\x09\xe7\x8b" + "\xda\x2a\x0a\x11\x02\x43\xcb\x57" + "\xc9\xcc\xb5\x5c\xab\xc4\xec\x54" + "\x00\x06\x34\xe1\x6e\x03\x89\x7c" + "\xc6\xfb\x6a\xc7\x60\x43\xd6\xc5" + "\xb5\x68\x72\x89\x8f\x42\xc3\x74" + "\xbd\x25\xaa\x9f\x67\xb5\xdf\x26" + "\x20\xe8\xb7\x01\x3c\xe4\x77\xce" + "\xc4\x65\xa7\x23\x79\xea\x33\xc7" + "\x82\x14\x5c\x82\xf2\x4e\x3d\xf6" + "\xc6\x4a\x0e\x29\xbb\xec\x44\xcd" + "\x2f\xd1\x4f\x21\x71\xa9\xce\x0f" + "\x5c\xf2\x72\x5c\x08\x2e\x21\xd2" + "\xc3\x29\x13\xd8\xac\xc3\xda\x13" + "\x1a\x9d\xa7\x71\x1d\x27\x1d\x27" + "\x1d\xea\xab\x44\x79\xad\xe5\xeb" + "\xef\x1f\x22\x0a\x44\x4f\xcb\x87" + "\xa7\x58\x71\x0e\x66\xf8\x60\xbf" + "\x60\x74\x4a\xb4\xec\x2e\xfe\xd3" + "\xf5\xb8\xfe\x46\x08\x50\x99\x6c" + "\x66\xa5\xa8\x34\x44\xb5\xe5\xf0" + "\xdd\x2c\x67\x4e\x35\x96\x8e\x67" + "\x48\x3f\x5f\x37\x44\x60\x51\x2e" + "\x14\x91\x5e\x57\xc3\x0e\x79\x77" + "\x2f\x03\xf4\xe2\x1c\x72\xbf\x85" + "\x5d\xd3\x17\xdf\x6c\xc5\x70\x24" + "\x42\xdf\x51\x4e\x2a\xb2\xd2\x5b" + "\x9e\x69\x83\x41\x11\xfe\x73\x22" + "\xde\x8a\x9e\xd8\x8a\xfb\x20\x38" + "\xd8\x47\x6f\xd5\xed\x8f\x41\xfd" + "\x13\x7a\x18\x03\x7d\x0f\xcd\x7d" + "\xa6\x7d\x31\x9e\xf1\x8f\x30\xa3" + "\x8b\x4c\x24\xb7\xf5\x48\xd7\xd9" + "\x12\xe7\x84\x97\x5c\x31\x6d\xfb" + "\xdf\xf3\xd3\xd1\xd5\x0c\x30\x06" + "\x01\x6a\xbc\x6c\x78\x7b\xa6\x50" + "\xfa\x0f\x3c\x42\x2d\xa5\xa3\x3b" + "\xcf\x62\x50\xff\x71\x6d\xe7\xda" + "\x27\xab\xc6\x67\x16\x65\x68\x64" + "\xc7\xd5\x5f\x81\xa9\xf6\x65\xb3" + "\x5e\x43\x91\x16\xcd\x3d\x55\x37" + "\x55\xb3\xf0\x28\xc5\x54\x19\xc0" + "\xe0\xd6\x2a\x61\xd4\xc8\x72\x51" + "\xe9\xa1\x7b\x48\x21\xad\x44\x09" + "\xe4\x01\x61\x3c\x8a\x5b\xf9\xa1" + "\x6e\x1b\xdf\xc0\x04\xa8\x8b\xf2" + "\x21\xbe\x34\x7b\xfc\xa1\xcd\xc9" + "\xa9\x96\xf4\xa4\x4c\xf7\x4e\x8f" + "\x84\xcc\xd3\xa8\x92\x77\x8f\x36" + "\xe2\x2e\x8c\x33\xe8\x84\xa6\x0c" + "\x6c\x8a\xda\x14\x32\xc2\x96\xff" + "\xc6\x4a\xc2\x9b\x30\x7f\xd1\x29" + "\xc0\xd5\x78\x41\x00\x80\x80\x03" + "\x2a\xb1\xde\x26\x03\x48\x49\xee" + "\x57\x14\x76\x51\x3c\x36\x5d\x0a" + "\x5c\x9f\xe8\xd8\x53\xdb\x4f\xd4" + "\x38\xbf\x66\xc9\x75\x12\x18\x75" + "\x34\x2d\x93\x22\x96\x51\x24\x6e" + "\x4e\xd9\x30\xea\x67\xff\x92\x1c" + "\x16\x26\xe9\xb5\x33\xab\x8c\x22" + "\x47\xdb\xa0\x2c\x08\xf0\x12\x69" + "\x7e\x93\x52\xda\xa5\xe5\xca\xc1" + "\x0f\x55\x2a\xbd\x09\x30\x88\x1b" + "\x9c\xc6\x9f\xe6\xdb\xa6\x92\xeb" + "\xf4\xbd\x5c\xc4\xdb\xc6\x71\x09" + "\xab\x5e\x48\x0c\xed\x6f\xda\x8e" + "\x8d\x0c\x98\x71\x7d\x10\xd0\x9c" + "\x20\x9b\x79\x53\x26\x5d\xb9\x85" + "\x8a\x31\xb8\xc5\x1c\x97\xde\x88" + "\x61\x55\x7f\x7c\x21\x06\xea\xc4" + "\x5f\xaf\xf2\xf0\xd5\x5e\x7d\xb4" + "\x6e\xcf\xe9\xae\x1b\x0e\x11\x80" + "\xc1\x9a\x74\x7e\x52\x6f\xa0\xb7" + "\x24\xcd\x8d\x0a\x11\x40\x63\x72" + "\xfa\xe2\xc5\xb3\x94\xef\x29\xa2" + "\x1a\x23\x43\x04\x37\x55\x0d\xe9" + "\x83\xb2\x29\x51\x49\x64\xa0\xbd" + "\xde\x73\xfd\xa5\x7c\x95\x70\x62" + "\x58\xdc\xe2\xd0\xbf\x98\xf5\x8a" + "\x6a\xfd\xce\xa8\x0e\x42\x2a\xeb" + "\xd2\xff\x83\x27\x53\x5c\xa0\x6e" + "\x93\xef\xe2\xb9\x5d\x35\xd6\x98" + "\xf6\x71\x19\x7a\x54\xa1\xa7\xe8" + "\x09\xfe\xf6\x9e\xc7\xbd\x3e\x29" + "\xbd\x6b\x17\xf4\xe7\x3e\x10\x5c" + "\xc1\xd2\x59\x4f\x4b\x12\x1a\x5b" + "\x50\x80\x59\xb9\xec\x13\x66\xa8" + "\xd2\x31\x7b\x6a\x61\x22\xdd\x7d" + "\x61\xee\x87\x16\x46\x9f\xf9\xc7" + "\x41\xee\x74\xf8\xd0\x96\x2c\x76" + "\x2a\xac\x7d\x6e\x9f\x0e\x7f\x95" + "\xfe\x50\x16\xb2\x23\xca\x62\xd5" + "\x68\xcf\x07\x3f\x3f\x97\x85\x2a" + "\x0c\x25\x45\xba\xdb\x32\xcb\x83" + "\x8c\x4f\xe0\x6d\x9a\x99\xf9\xc9" + "\xda\xd4\x19\x31\xc1\x7c\x6d\xd9" + "\x9c\x56\xd3\xec\xc1\x81\x4c\xed" + "\x28\x9d\x87\xeb\x19\xd7\x1a\x4f" + "\x04\x6a\xcb\x1f\xcf\x1f\xa2\x16" + "\xfc\x2a\x0d\xa1\x14\x2d\xfa\xc5" + "\x5a\xd2\xc5\xf9\x19\x7c\x20\x1f" + "\x2d\x10\xc0\x66\x7c\xd9\x2d\xe5" + "\x88\x70\x59\xa7\x85\xd5\x2e\x7c" + "\x5c\xe3\xb7\x12\xd6\x97\x3f\x29", + .psize = 2048, + .digest = "\x37\x90\x92\xc2\xeb\x01\x87\xd9" + "\x95\xc7\x91\xc3\x17\x8b\x38\x52", + } +}; + /* * DES test vectors. */ @@ -33101,6 +34332,2108 @@ static const struct cipher_testvec chacha20_enc_tv_template[] = { }, }; +static const struct cipher_testvec xchacha20_tv_template[] = { + { /* from libsodium test/default/xchacha20.c */ + .key = "\x79\xc9\x97\x98\xac\x67\x30\x0b" + "\xbb\x27\x04\xc9\x5c\x34\x1e\x32" + "\x45\xf3\xdc\xb2\x17\x61\xb9\x8e" + "\x52\xff\x45\xb2\x4f\x30\x4f\xc4", + .klen = 32, + .iv = "\xb3\x3f\xfd\x30\x96\x47\x9b\xcf" + "\xbc\x9a\xee\x49\x41\x76\x88\xa0" + "\xa2\x55\x4f\x8d\x95\x38\x94\x19" + "\x00\x00\x00\x00\x00\x00\x00\x00", + .input = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00", + .result = "\xc6\xe9\x75\x81\x60\x08\x3a\xc6" + "\x04\xef\x90\xe7\x12\xce\x6e\x75" + "\xd7\x79\x75\x90\x74\x4e\x0c\xf0" + "\x60\xf0\x13\x73\x9c", + .ilen = 29, + .rlen = 29, + }, { /* from libsodium test/default/xchacha20.c */ + .key = "\x9d\x23\xbd\x41\x49\xcb\x97\x9c" + "\xcf\x3c\x5c\x94\xdd\x21\x7e\x98" + "\x08\xcb\x0e\x50\xcd\x0f\x67\x81" + "\x22\x35\xea\xaf\x60\x1d\x62\x32", + .klen = 32, + .iv = "\xc0\x47\x54\x82\x66\xb7\xc3\x70" + "\xd3\x35\x66\xa2\x42\x5c\xbf\x30" + "\xd8\x2d\x1e\xaf\x52\x94\x10\x9e" + "\x00\x00\x00\x00\x00\x00\x00\x00", + .input = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00", + .result = "\xa2\x12\x09\x09\x65\x94\xde\x8c" + "\x56\x67\xb1\xd1\x3a\xd9\x3f\x74" + "\x41\x06\xd0\x54\xdf\x21\x0e\x47" + "\x82\xcd\x39\x6f\xec\x69\x2d\x35" + "\x15\xa2\x0b\xf3\x51\xee\xc0\x11" + "\xa9\x2c\x36\x78\x88\xbc\x46\x4c" + "\x32\xf0\x80\x7a\xcd\x6c\x20\x3a" + "\x24\x7e\x0d\xb8\x54\x14\x84\x68" + "\xe9\xf9\x6b\xee\x4c\xf7\x18\xd6" + "\x8d\x5f\x63\x7c\xbd\x5a\x37\x64" + "\x57\x78\x8e\x6f\xae\x90\xfc\x31" + "\x09\x7c\xfc", + .ilen = 91, + .rlen = 91, + }, { /* Taken from the ChaCha20 test vectors, appended 16 random bytes + to nonce, and recomputed the ciphertext with libsodium */ + .key = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00", + .klen = 32, + .iv = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x67\xc6\x69\x73" + "\x51\xff\x4a\xec\x29\xcd\xba\xab" + "\x00\x00\x00\x00\x00\x00\x00\x00", + .input = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00", + .result = "\x9c\x49\x2a\xe7\x8a\x2f\x93\xc7" + "\xb3\x33\x6f\x82\x17\xd8\xc4\x1e" + "\xad\x80\x11\x11\x1d\x4c\x16\x18" + "\x07\x73\x9b\x4f\xdb\x7c\xcb\x47" + "\xfd\xef\x59\x74\xfa\x3f\xe5\x4c" + "\x9b\xd0\xea\xbc\xba\x56\xad\x32" + "\x03\xdc\xf8\x2b\xc1\xe1\x75\x67" + "\x23\x7b\xe6\xfc\xd4\x03\x86\x54", + .ilen = 64, + .rlen = 64, + }, { /* Taken from the ChaCha20 test vectors, appended 16 random bytes + to nonce, and recomputed the ciphertext with libsodium */ + .key = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x01", + .klen = 32, + .iv = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x02\xf2\xfb\xe3\x46" + "\x7c\xc2\x54\xf8\x1b\xe8\xe7\x8d" + "\x01\x00\x00\x00\x00\x00\x00\x00", + .input = "\x41\x6e\x79\x20\x73\x75\x62\x6d" + "\x69\x73\x73\x69\x6f\x6e\x20\x74" + "\x6f\x20\x74\x68\x65\x20\x49\x45" + "\x54\x46\x20\x69\x6e\x74\x65\x6e" + "\x64\x65\x64\x20\x62\x79\x20\x74" + "\x68\x65\x20\x43\x6f\x6e\x74\x72" + "\x69\x62\x75\x74\x6f\x72\x20\x66" + "\x6f\x72\x20\x70\x75\x62\x6c\x69" + "\x63\x61\x74\x69\x6f\x6e\x20\x61" + "\x73\x20\x61\x6c\x6c\x20\x6f\x72" + "\x20\x70\x61\x72\x74\x20\x6f\x66" + "\x20\x61\x6e\x20\x49\x45\x54\x46" + "\x20\x49\x6e\x74\x65\x72\x6e\x65" + "\x74\x2d\x44\x72\x61\x66\x74\x20" + "\x6f\x72\x20\x52\x46\x43\x20\x61" + "\x6e\x64\x20\x61\x6e\x79\x20\x73" + "\x74\x61\x74\x65\x6d\x65\x6e\x74" + "\x20\x6d\x61\x64\x65\x20\x77\x69" + "\x74\x68\x69\x6e\x20\x74\x68\x65" + "\x20\x63\x6f\x6e\x74\x65\x78\x74" + "\x20\x6f\x66\x20\x61\x6e\x20\x49" + "\x45\x54\x46\x20\x61\x63\x74\x69" + "\x76\x69\x74\x79\x20\x69\x73\x20" + "\x63\x6f\x6e\x73\x69\x64\x65\x72" + "\x65\x64\x20\x61\x6e\x20\x22\x49" + "\x45\x54\x46\x20\x43\x6f\x6e\x74" + "\x72\x69\x62\x75\x74\x69\x6f\x6e" + "\x22\x2e\x20\x53\x75\x63\x68\x20" + "\x73\x74\x61\x74\x65\x6d\x65\x6e" + "\x74\x73\x20\x69\x6e\x63\x6c\x75" + "\x64\x65\x20\x6f\x72\x61\x6c\x20" + "\x73\x74\x61\x74\x65\x6d\x65\x6e" + "\x74\x73\x20\x69\x6e\x20\x49\x45" + "\x54\x46\x20\x73\x65\x73\x73\x69" + "\x6f\x6e\x73\x2c\x20\x61\x73\x20" + "\x77\x65\x6c\x6c\x20\x61\x73\x20" + "\x77\x72\x69\x74\x74\x65\x6e\x20" + "\x61\x6e\x64\x20\x65\x6c\x65\x63" + "\x74\x72\x6f\x6e\x69\x63\x20\x63" + "\x6f\x6d\x6d\x75\x6e\x69\x63\x61" + "\x74\x69\x6f\x6e\x73\x20\x6d\x61" + "\x64\x65\x20\x61\x74\x20\x61\x6e" + "\x79\x20\x74\x69\x6d\x65\x20\x6f" + "\x72\x20\x70\x6c\x61\x63\x65\x2c" + "\x20\x77\x68\x69\x63\x68\x20\x61" + "\x72\x65\x20\x61\x64\x64\x72\x65" + "\x73\x73\x65\x64\x20\x74\x6f", + .result = "\xf9\xab\x7a\x4a\x60\xb8\x5f\xa0" + "\x50\xbb\x57\xce\xef\x8c\xc1\xd9" + "\x24\x15\xb3\x67\x5e\x7f\x01\xf6" + "\x1c\x22\xf6\xe5\x71\xb1\x43\x64" + "\x63\x05\xd5\xfc\x5c\x3d\xc0\x0e" + "\x23\xef\xd3\x3b\xd9\xdc\x7f\xa8" + "\x58\x26\xb3\xd0\xc2\xd5\x04\x3f" + "\x0a\x0e\x8f\x17\xe4\xcd\xf7\x2a" + "\xb4\x2c\x09\xe4\x47\xec\x8b\xfb" + "\x59\x37\x7a\xa1\xd0\x04\x7e\xaa" + "\xf1\x98\x5f\x24\x3d\x72\x9a\x43" + "\xa4\x36\x51\x92\x22\x87\xff\x26" + "\xce\x9d\xeb\x59\x78\x84\x5e\x74" + "\x97\x2e\x63\xc0\xef\x29\xf7\x8a" + "\xb9\xee\x35\x08\x77\x6a\x35\x9a" + "\x3e\xe6\x4f\x06\x03\x74\x1b\xc1" + "\x5b\xb3\x0b\x89\x11\x07\xd3\xb7" + "\x53\xd6\x25\x04\xd9\x35\xb4\x5d" + "\x4c\x33\x5a\xc2\x42\x4c\xe6\xa4" + "\x97\x6e\x0e\xd2\xb2\x8b\x2f\x7f" + "\x28\xe5\x9f\xac\x4b\x2e\x02\xab" + "\x85\xfa\xa9\x0d\x7c\x2d\x10\xe6" + "\x91\xab\x55\x63\xf0\xde\x3a\x94" + "\x25\x08\x10\x03\xc2\x68\xd1\xf4" + "\xaf\x7d\x9c\x99\xf7\x86\x96\x30" + "\x60\xfc\x0b\xe6\xa8\x80\x15\xb0" + "\x81\xb1\x0c\xbe\xb9\x12\x18\x25" + "\xe9\x0e\xb1\xe7\x23\xb2\xef\x4a" + "\x22\x8f\xc5\x61\x89\xd4\xe7\x0c" + "\x64\x36\x35\x61\xb6\x34\x60\xf7" + "\x7b\x61\x37\x37\x12\x10\xa2\xf6" + "\x7e\xdb\x7f\x39\x3f\xb6\x8e\x89" + "\x9e\xf3\xfe\x13\x98\xbb\x66\x5a" + "\xec\xea\xab\x3f\x9c\x87\xc4\x8c" + "\x8a\x04\x18\x49\xfc\x77\x11\x50" + "\x16\xe6\x71\x2b\xee\xc0\x9c\xb6" + "\x87\xfd\x80\xff\x0b\x1d\x73\x38" + "\xa4\x1d\x6f\xae\xe4\x12\xd7\x93" + "\x9d\xcd\x38\x26\x09\x40\x52\xcd" + "\x67\x01\x67\x26\xe0\x3e\x98\xa8" + "\xe8\x1a\x13\x41\xbb\x90\x4d\x87" + "\xbb\x42\x82\x39\xce\x3a\xd0\x18" + "\x6d\x7b\x71\x8f\xbb\x2c\x6a\xd1" + "\xbd\xf5\xc7\x8a\x7e\xe1\x1e\x0f" + "\x0d\x0d\x13\x7c\xd9\xd8\x3c\x91" + "\xab\xff\x1f\x12\xc3\xee\xe5\x65" + "\x12\x8d\x7b\x61\xe5\x1f\x98", + .ilen = 375, + .rlen = 375, + .also_non_np = 1, + .np = 3, + .tap = { 375 - 20, 4, 16 }, + + }, { /* Taken from the ChaCha20 test vectors, appended 16 random bytes + to nonce, and recomputed the ciphertext with libsodium */ + .key = "\x1c\x92\x40\xa5\xeb\x55\xd3\x8a" + "\xf3\x33\x88\x86\x04\xf6\xb5\xf0" + "\x47\x39\x17\xc1\x40\x2b\x80\x09" + "\x9d\xca\x5c\xbc\x20\x70\x75\xc0", + .klen = 32, + .iv = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x02\x76\x5a\x2e\x63" + "\x33\x9f\xc9\x9a\x66\x32\x0d\xb7" + "\x2a\x00\x00\x00\x00\x00\x00\x00", + .input = "\x27\x54\x77\x61\x73\x20\x62\x72" + "\x69\x6c\x6c\x69\x67\x2c\x20\x61" + "\x6e\x64\x20\x74\x68\x65\x20\x73" + "\x6c\x69\x74\x68\x79\x20\x74\x6f" + "\x76\x65\x73\x0a\x44\x69\x64\x20" + "\x67\x79\x72\x65\x20\x61\x6e\x64" + "\x20\x67\x69\x6d\x62\x6c\x65\x20" + "\x69\x6e\x20\x74\x68\x65\x20\x77" + "\x61\x62\x65\x3a\x0a\x41\x6c\x6c" + "\x20\x6d\x69\x6d\x73\x79\x20\x77" + "\x65\x72\x65\x20\x74\x68\x65\x20" + "\x62\x6f\x72\x6f\x67\x6f\x76\x65" + "\x73\x2c\x0a\x41\x6e\x64\x20\x74" + "\x68\x65\x20\x6d\x6f\x6d\x65\x20" + "\x72\x61\x74\x68\x73\x20\x6f\x75" + "\x74\x67\x72\x61\x62\x65\x2e", + .result = "\x95\xb9\x51\xe7\x8f\xb4\xa4\x03" + "\xca\x37\xcc\xde\x60\x1d\x8c\xe2" + "\xf1\xbb\x8a\x13\x7f\x61\x85\xcc" + "\xad\xf4\xf0\xdc\x86\xa6\x1e\x10" + "\xbc\x8e\xcb\x38\x2b\xa5\xc8\x8f" + "\xaa\x03\x3d\x53\x4a\x42\xb1\x33" + "\xfc\xd3\xef\xf0\x8e\x7e\x10\x9c" + "\x6f\x12\x5e\xd4\x96\xfe\x5b\x08" + "\xb6\x48\xf0\x14\x74\x51\x18\x7c" + "\x07\x92\xfc\xac\x9d\xf1\x94\xc0" + "\xc1\x9d\xc5\x19\x43\x1f\x1d\xbb" + "\x07\xf0\x1b\x14\x25\x45\xbb\xcb" + "\x5c\xe2\x8b\x28\xf3\xcf\x47\x29" + "\x27\x79\x67\x24\xa6\x87\xc2\x11" + "\x65\x03\xfa\x45\xf7\x9e\x53\x7a" + "\x99\xf1\x82\x25\x4f\x8d\x07", + .ilen = 127, + .rlen = 127, + }, { /* Taken from the ChaCha20 test vectors, appended 16 random bytes + to nonce, and recomputed the ciphertext with libsodium */ + .key = "\x1c\x92\x40\xa5\xeb\x55\xd3\x8a" + "\xf3\x33\x88\x86\x04\xf6\xb5\xf0" + "\x47\x39\x17\xc1\x40\x2b\x80\x09" + "\x9d\xca\x5c\xbc\x20\x70\x75\xc0", + .klen = 32, + .iv = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x01\x31\x58\xa3\x5a" + "\x25\x5d\x05\x17\x58\xe9\x5e\xd4" + "\x1c\x00\x00\x00\x00\x00\x00\x00", + .input = "\x49\xee\xe0\xdc\x24\x90\x40\xcd" + "\xc5\x40\x8f\x47\x05\xbc\xdd\x81" + "\x47\xc6\x8d\xe6\xb1\x8f\xd7\xcb" + "\x09\x0e\x6e\x22\x48\x1f\xbf\xb8" + "\x5c\xf7\x1e\x8a\xc1\x23\xf2\xd4" + "\x19\x4b\x01\x0f\x4e\xa4\x43\xce" + "\x01\xc6\x67\xda\x03\x91\x18\x90" + "\xa5\xa4\x8e\x45\x03\xb3\x2d\xac" + "\x74\x92\xd3\x53\x47\xc8\xdd\x25" + "\x53\x6c\x02\x03\x87\x0d\x11\x0c" + "\x58\xe3\x12\x18\xfd\x2a\x5b\x40" + "\x0c\x30\xf0\xb8\x3f\x43\xce\xae" + "\x65\x3a\x7d\x7c\xf4\x54\xaa\xcc" + "\x33\x97\xc3\x77\xba\xc5\x70\xde" + "\xd7\xd5\x13\xa5\x65\xc4\x5f\x0f" + "\x46\x1a\x0d\x97\xb5\xf3\xbb\x3c" + "\x84\x0f\x2b\xc5\xaa\xea\xf2\x6c" + "\xc9\xb5\x0c\xee\x15\xf3\x7d\xbe" + "\x9f\x7b\x5a\xa6\xae\x4f\x83\xb6" + "\x79\x49\x41\xf4\x58\x18\xcb\x86" + "\x7f\x30\x0e\xf8\x7d\x44\x36\xea" + "\x75\xeb\x88\x84\x40\x3c\xad\x4f" + "\x6f\x31\x6b\xaa\x5d\xe5\xa5\xc5" + "\x21\x66\xe9\xa7\xe3\xb2\x15\x88" + "\x78\xf6\x79\xa1\x59\x47\x12\x4e" + "\x9f\x9f\x64\x1a\xa0\x22\x5b\x08" + "\xbe\x7c\x36\xc2\x2b\x66\x33\x1b" + "\xdd\x60\x71\xf7\x47\x8c\x61\xc3" + "\xda\x8a\x78\x1e\x16\xfa\x1e\x86" + "\x81\xa6\x17\x2a\xa7\xb5\xc2\xe7" + "\xa4\xc7\x42\xf1\xcf\x6a\xca\xb4" + "\x45\xcf\xf3\x93\xf0\xe7\xea\xf6" + "\xf4\xe6\x33\x43\x84\x93\xa5\x67" + "\x9b\x16\x58\x58\x80\x0f\x2b\x5c" + "\x24\x74\x75\x7f\x95\x81\xb7\x30" + "\x7a\x33\xa7\xf7\x94\x87\x32\x27" + "\x10\x5d\x14\x4c\x43\x29\xdd\x26" + "\xbd\x3e\x3c\x0e\xfe\x0e\xa5\x10" + "\xea\x6b\x64\xfd\x73\xc6\xed\xec" + "\xa8\xc9\xbf\xb3\xba\x0b\x4d\x07" + "\x70\xfc\x16\xfd\x79\x1e\xd7\xc5" + "\x49\x4e\x1c\x8b\x8d\x79\x1b\xb1" + "\xec\xca\x60\x09\x4c\x6a\xd5\x09" + "\x49\x46\x00\x88\x22\x8d\xce\xea" + "\xb1\x17\x11\xde\x42\xd2\x23\xc1" + "\x72\x11\xf5\x50\x73\x04\x40\x47" + "\xf9\x5d\xe7\xa7\x26\xb1\x7e\xb0" + "\x3f\x58\xc1\x52\xab\x12\x67\x9d" + "\x3f\x43\x4b\x68\xd4\x9c\x68\x38" + "\x07\x8a\x2d\x3e\xf3\xaf\x6a\x4b" + "\xf9\xe5\x31\x69\x22\xf9\xa6\x69" + "\xc6\x9c\x96\x9a\x12\x35\x95\x1d" + "\x95\xd5\xdd\xbe\xbf\x93\x53\x24" + "\xfd\xeb\xc2\x0a\x64\xb0\x77\x00" + "\x6f\x88\xc4\x37\x18\x69\x7c\xd7" + "\x41\x92\x55\x4c\x03\xa1\x9a\x4b" + "\x15\xe5\xdf\x7f\x37\x33\x72\xc1" + "\x8b\x10\x67\xa3\x01\x57\x94\x25" + "\x7b\x38\x71\x7e\xdd\x1e\xcc\x73" + "\x55\xd2\x8e\xeb\x07\xdd\xf1\xda" + "\x58\xb1\x47\x90\xfe\x42\x21\x72" + "\xa3\x54\x7a\xa0\x40\xec\x9f\xdd" + "\xc6\x84\x6e\xca\xae\xe3\x68\xb4" + "\x9d\xe4\x78\xff\x57\xf2\xf8\x1b" + "\x03\xa1\x31\xd9\xde\x8d\xf5\x22" + "\x9c\xdd\x20\xa4\x1e\x27\xb1\x76" + "\x4f\x44\x55\xe2\x9b\xa1\x9c\xfe" + "\x54\xf7\x27\x1b\xf4\xde\x02\xf5" + "\x1b\x55\x48\x5c\xdc\x21\x4b\x9e" + "\x4b\x6e\xed\x46\x23\xdc\x65\xb2" + "\xcf\x79\x5f\x28\xe0\x9e\x8b\xe7" + "\x4c\x9d\x8a\xff\xc1\xa6\x28\xb8" + "\x65\x69\x8a\x45\x29\xef\x74\x85" + "\xde\x79\xc7\x08\xae\x30\xb0\xf4" + "\xa3\x1d\x51\x41\xab\xce\xcb\xf6" + "\xb5\xd8\x6d\xe0\x85\xe1\x98\xb3" + "\x43\xbb\x86\x83\x0a\xa0\xf5\xb7" + "\x04\x0b\xfa\x71\x1f\xb0\xf6\xd9" + "\x13\x00\x15\xf0\xc7\xeb\x0d\x5a" + "\x9f\xd7\xb9\x6c\x65\x14\x22\x45" + "\x6e\x45\x32\x3e\x7e\x60\x1a\x12" + "\x97\x82\x14\xfb\xaa\x04\x22\xfa" + "\xa0\xe5\x7e\x8c\x78\x02\x48\x5d" + "\x78\x33\x5a\x7c\xad\xdb\x29\xce" + "\xbb\x8b\x61\xa4\xb7\x42\xe2\xac" + "\x8b\x1a\xd9\x2f\x0b\x8b\x62\x21" + "\x83\x35\x7e\xad\x73\xc2\xb5\x6c" + "\x10\x26\x38\x07\xe5\xc7\x36\x80" + "\xe2\x23\x12\x61\xf5\x48\x4b\x2b" + "\xc5\xdf\x15\xd9\x87\x01\xaa\xac" + "\x1e\x7c\xad\x73\x78\x18\x63\xe0" + "\x8b\x9f\x81\xd8\x12\x6a\x28\x10" + "\xbe\x04\x68\x8a\x09\x7c\x1b\x1c" + "\x83\x66\x80\x47\x80\xe8\xfd\x35" + "\x1c\x97\x6f\xae\x49\x10\x66\xcc" + "\xc6\xd8\xcc\x3a\x84\x91\x20\x77" + "\x72\xe4\x24\xd2\x37\x9f\xc5\xc9" + "\x25\x94\x10\x5f\x40\x00\x64\x99" + "\xdc\xae\xd7\x21\x09\x78\x50\x15" + "\xac\x5f\xc6\x2c\xa2\x0b\xa9\x39" + "\x87\x6e\x6d\xab\xde\x08\x51\x16" + "\xc7\x13\xe9\xea\xed\x06\x8e\x2c" + "\xf8\x37\x8c\xf0\xa6\x96\x8d\x43" + "\xb6\x98\x37\xb2\x43\xed\xde\xdf" + "\x89\x1a\xe7\xeb\x9d\xa1\x7b\x0b" + "\x77\xb0\xe2\x75\xc0\xf1\x98\xd9" + "\x80\x55\xc9\x34\x91\xd1\x59\xe8" + "\x4b\x0f\xc1\xa9\x4b\x7a\x84\x06" + "\x20\xa8\x5d\xfa\xd1\xde\x70\x56" + "\x2f\x9e\x91\x9c\x20\xb3\x24\xd8" + "\x84\x3d\xe1\x8c\x7e\x62\x52\xe5" + "\x44\x4b\x9f\xc2\x93\x03\xea\x2b" + "\x59\xc5\xfa\x3f\x91\x2b\xbb\x23" + "\xf5\xb2\x7b\xf5\x38\xaf\xb3\xee" + "\x63\xdc\x7b\xd1\xff\xaa\x8b\xab" + "\x82\x6b\x37\x04\xeb\x74\xbe\x79" + "\xb9\x83\x90\xef\x20\x59\x46\xff" + "\xe9\x97\x3e\x2f\xee\xb6\x64\x18" + "\x38\x4c\x7a\x4a\xf9\x61\xe8\x9a" + "\xa1\xb5\x01\xa6\x47\xd3\x11\xd4" + "\xce\xd3\x91\x49\x88\xc7\xb8\x4d" + "\xb1\xb9\x07\x6d\x16\x72\xae\x46" + "\x5e\x03\xa1\x4b\xb6\x02\x30\xa8" + "\x3d\xa9\x07\x2a\x7c\x19\xe7\x62" + "\x87\xe3\x82\x2f\x6f\xe1\x09\xd9" + "\x94\x97\xea\xdd\x58\x9e\xae\x76" + "\x7e\x35\xe5\xb4\xda\x7e\xf4\xde" + "\xf7\x32\x87\xcd\x93\xbf\x11\x56" + "\x11\xbe\x08\x74\xe1\x69\xad\xe2" + "\xd7\xf8\x86\x75\x8a\x3c\xa4\xbe" + "\x70\xa7\x1b\xfc\x0b\x44\x2a\x76" + "\x35\xea\x5d\x85\x81\xaf\x85\xeb" + "\xa0\x1c\x61\xc2\xf7\x4f\xa5\xdc" + "\x02\x7f\xf6\x95\x40\x6e\x8a\x9a" + "\xf3\x5d\x25\x6e\x14\x3a\x22\xc9" + "\x37\x1c\xeb\x46\x54\x3f\xa5\x91" + "\xc2\xb5\x8c\xfe\x53\x08\x97\x32" + "\x1b\xb2\x30\x27\xfe\x25\x5d\xdc" + "\x08\x87\xd0\xe5\x94\x1a\xd4\xf1" + "\xfe\xd6\xb4\xa3\xe6\x74\x81\x3c" + "\x1b\xb7\x31\xa7\x22\xfd\xd4\xdd" + "\x20\x4e\x7c\x51\xb0\x60\x73\xb8" + "\x9c\xac\x91\x90\x7e\x01\xb0\xe1" + "\x8a\x2f\x75\x1c\x53\x2a\x98\x2a" + "\x06\x52\x95\x52\xb2\xe9\x25\x2e" + "\x4c\xe2\x5a\x00\xb2\x13\x81\x03" + "\x77\x66\x0d\xa5\x99\xda\x4e\x8c" + "\xac\xf3\x13\x53\x27\x45\xaf\x64" + "\x46\xdc\xea\x23\xda\x97\xd1\xab" + "\x7d\x6c\x30\x96\x1f\xbc\x06\x34" + "\x18\x0b\x5e\x21\x35\x11\x8d\x4c" + "\xe0\x2d\xe9\x50\x16\x74\x81\xa8" + "\xb4\x34\xb9\x72\x42\xa6\xcc\xbc" + "\xca\x34\x83\x27\x10\x5b\x68\x45" + "\x8f\x52\x22\x0c\x55\x3d\x29\x7c" + "\xe3\xc0\x66\x05\x42\x91\x5f\x58" + "\xfe\x4a\x62\xd9\x8c\xa9\x04\x19" + "\x04\xa9\x08\x4b\x57\xfc\x67\x53" + "\x08\x7c\xbc\x66\x8a\xb0\xb6\x9f" + "\x92\xd6\x41\x7c\x5b\x2a\x00\x79" + "\x72", + .result = "\x3a\x92\xee\x53\x31\xaf\x2b\x60" + "\x5f\x55\x8d\x00\x5d\xfc\x74\x97" + "\x28\x54\xf4\xa5\x75\xf1\x9b\x25" + "\x62\x1c\xc0\xe0\x13\xc8\x87\x53" + "\xd0\xf3\xa7\x97\x1f\x3b\x1e\xea" + "\xe0\xe5\x2a\xd1\xdd\xa4\x3b\x50" + "\x45\xa3\x0d\x7e\x1b\xc9\xa0\xad" + "\xb9\x2c\x54\xa6\xc7\x55\x16\xd0" + "\xc5\x2e\x02\x44\x35\xd0\x7e\x67" + "\xf2\xc4\x9b\xcd\x95\x10\xcc\x29" + "\x4b\xfa\x86\x87\xbe\x40\x36\xbe" + "\xe1\xa3\x52\x89\x55\x20\x9b\xc2" + "\xab\xf2\x31\x34\x16\xad\xc8\x17" + "\x65\x24\xc0\xff\x12\x37\xfe\x5a" + "\x62\x3b\x59\x47\x6c\x5f\x3a\x8e" + "\x3b\xd9\x30\xc8\x7f\x2f\x88\xda" + "\x80\xfd\x02\xda\x7f\x9a\x7a\x73" + "\x59\xc5\x34\x09\x9a\x11\xcb\xa7" + "\xfc\xf6\xa1\xa0\x60\xfb\x43\xbb" + "\xf1\xe9\xd7\xc6\x79\x27\x4e\xff" + "\x22\xb4\x24\xbf\x76\xee\x47\xb9" + "\x6d\x3f\x8b\xb0\x9c\x3c\x43\xdd" + "\xff\x25\x2e\x6d\xa4\x2b\xfb\x5d" + "\x1b\x97\x6c\x55\x0a\x82\x7a\x7b" + "\x94\x34\xc2\xdb\x2f\x1f\xc1\xea" + "\xd4\x4d\x17\x46\x3b\x51\x69\x09" + "\xe4\x99\x32\x25\xfd\x94\xaf\xfb" + "\x10\xf7\x4f\xdd\x0b\x3c\x8b\x41" + "\xb3\x6a\xb7\xd1\x33\xa8\x0c\x2f" + "\x62\x4c\x72\x11\xd7\x74\xe1\x3b" + "\x38\x43\x66\x7b\x6c\x36\x48\xe7" + "\xe3\xe7\x9d\xb9\x42\x73\x7a\x2a" + "\x89\x20\x1a\x41\x80\x03\xf7\x8f" + "\x61\x78\x13\xbf\xfe\x50\xf5\x04" + "\x52\xf9\xac\x47\xf8\x62\x4b\xb2" + "\x24\xa9\xbf\x64\xb0\x18\x69\xd2" + "\xf5\xe4\xce\xc8\xb1\x87\x75\xd6" + "\x2c\x24\x79\x00\x7d\x26\xfb\x44" + "\xe7\x45\x7a\xee\x58\xa5\x83\xc1" + "\xb4\x24\xab\x23\x2f\x4d\xd7\x4f" + "\x1c\xc7\xaa\xa9\x50\xf4\xa3\x07" + "\x12\x13\x89\x74\xdc\x31\x6a\xb2" + "\xf5\x0f\x13\x8b\xb9\xdb\x85\x1f" + "\xf5\xbc\x88\xd9\x95\xea\x31\x6c" + "\x36\x60\xb6\x49\xdc\xc4\xf7\x55" + "\x3f\x21\xc1\xb5\x92\x18\x5e\xbc" + "\x9f\x87\x7f\xe7\x79\x25\x40\x33" + "\xd6\xb9\x33\xd5\x50\xb3\xc7\x89" + "\x1b\x12\xa0\x46\xdd\xa7\xd8\x3e" + "\x71\xeb\x6f\x66\xa1\x26\x0c\x67" + "\xab\xb2\x38\x58\x17\xd8\x44\x3b" + "\x16\xf0\x8e\x62\x8d\x16\x10\x00" + "\x32\x8b\xef\xb9\x28\xd3\xc5\xad" + "\x0a\x19\xa2\xe4\x03\x27\x7d\x94" + "\x06\x18\xcd\xd6\x27\x00\xf9\x1f" + "\xb6\xb3\xfe\x96\x35\x5f\xc4\x1c" + "\x07\x62\x10\x79\x68\x50\xf1\x7e" + "\x29\xe7\xc4\xc4\xe7\xee\x54\xd6" + "\x58\x76\x84\x6d\x8d\xe4\x59\x31" + "\xe9\xf4\xdc\xa1\x1f\xe5\x1a\xd6" + "\xe6\x64\x46\xf5\x77\x9c\x60\x7a" + "\x5e\x62\xe3\x0a\xd4\x9f\x7a\x2d" + "\x7a\xa5\x0a\x7b\x29\x86\x7a\x74" + "\x74\x71\x6b\xca\x7d\x1d\xaa\xba" + "\x39\x84\x43\x76\x35\xfe\x4f\x9b" + "\xbb\xbb\xb5\x6a\x32\xb5\x5d\x41" + "\x51\xf0\x5b\x68\x03\x47\x4b\x8a" + "\xca\x88\xf6\x37\xbd\x73\x51\x70" + "\x66\xfe\x9e\x5f\x21\x9c\xf3\xdd" + "\xc3\xea\x27\xf9\x64\x94\xe1\x19" + "\xa0\xa9\xab\x60\xe0\x0e\xf7\x78" + "\x70\x86\xeb\xe0\xd1\x5c\x05\xd3" + "\xd7\xca\xe0\xc0\x47\x47\x34\xee" + "\x11\xa3\xa3\x54\x98\xb7\x49\x8e" + "\x84\x28\x70\x2c\x9e\xfb\x55\x54" + "\x4d\xf8\x86\xf7\x85\x7c\xbd\xf3" + "\x17\xd8\x47\xcb\xac\xf4\x20\x85" + "\x34\x66\xad\x37\x2d\x5e\x52\xda" + "\x8a\xfe\x98\x55\x30\xe7\x2d\x2b" + "\x19\x10\x8e\x7b\x66\x5e\xdc\xe0" + "\x45\x1f\x7b\xb4\x08\xfb\x8f\xf6" + "\x8c\x89\x21\x34\x55\x27\xb2\x76" + "\xb2\x07\xd9\xd6\x68\x9b\xea\x6b" + "\x2d\xb4\xc4\x35\xdd\xd2\x79\xae" + "\xc7\xd6\x26\x7f\x12\x01\x8c\xa7" + "\xe3\xdb\xa8\xf4\xf7\x2b\xec\x99" + "\x11\x00\xf1\x35\x8c\xcf\xd5\xc9" + "\xbd\x91\x36\x39\x70\xcf\x7d\x70" + "\x47\x1a\xfc\x6b\x56\xe0\x3f\x9c" + "\x60\x49\x01\x72\xa9\xaf\x2c\x9c" + "\xe8\xab\xda\x8c\x14\x19\xf3\x75" + "\x07\x17\x9d\x44\x67\x7a\x2e\xef" + "\xb7\x83\x35\x4a\xd1\x3d\x1c\x84" + "\x32\xdd\xaa\xea\xca\x1d\xdc\x72" + "\x2c\xcc\x43\xcd\x5d\xe3\x21\xa4" + "\xd0\x8a\x4b\x20\x12\xa3\xd5\x86" + "\x76\x96\xff\x5f\x04\x57\x0f\xe6" + "\xba\xe8\x76\x50\x0c\x64\x1d\x83" + "\x9c\x9b\x9a\x9a\x58\x97\x9c\x5c" + "\xb4\xa4\xa6\x3e\x19\xeb\x8f\x5a" + "\x61\xb2\x03\x7b\x35\x19\xbe\xa7" + "\x63\x0c\xfd\xdd\xf9\x90\x6c\x08" + "\x19\x11\xd3\x65\x4a\xf5\x96\x92" + "\x59\xaa\x9c\x61\x0c\x29\xa7\xf8" + "\x14\x39\x37\xbf\x3c\xf2\x16\x72" + "\x02\xfa\xa2\xf3\x18\x67\x5d\xcb" + "\xdc\x4d\xbb\x96\xff\x70\x08\x2d" + "\xc2\xa8\x52\xe1\x34\x5f\x72\xfe" + "\x64\xbf\xca\xa7\x74\x38\xfb\x74" + "\x55\x9c\xfa\x8a\xed\xfb\x98\xeb" + "\x58\x2e\x6c\xe1\x52\x76\x86\xd7" + "\xcf\xa1\xa4\xfc\xb2\x47\x41\x28" + "\xa3\xc1\xe5\xfd\x53\x19\x28\x2b" + "\x37\x04\x65\x96\x99\x7a\x28\x0f" + "\x07\x68\x4b\xc7\x52\x0a\x55\x35" + "\x40\x19\x95\x61\xe8\x59\x40\x1f" + "\x9d\xbf\x78\x7d\x8f\x84\xff\x6f" + "\xd0\xd5\x63\xd2\x22\xbd\xc8\x4e" + "\xfb\xe7\x9f\x06\xe6\xe7\x39\x6d" + "\x6a\x96\x9f\xf0\x74\x7e\xc9\x35" + "\xb7\x26\xb8\x1c\x0a\xa6\x27\x2c" + "\xa2\x2b\xfe\xbe\x0f\x07\x73\xae" + "\x7f\x7f\x54\xf5\x7c\x6a\x0a\x56" + "\x49\xd4\x81\xe5\x85\x53\x99\x1f" + "\x95\x05\x13\x58\x8d\x0e\x1b\x90" + "\xc3\x75\x48\x64\x58\x98\x67\x84" + "\xae\xe2\x21\xa2\x8a\x04\x0a\x0b" + "\x61\xaa\xb0\xd4\x28\x60\x7a\xf8" + "\xbc\x52\xfb\x24\x7f\xed\x0d\x2a" + "\x0a\xb2\xf9\xc6\x95\xb5\x11\xc9" + "\xf4\x0f\x26\x11\xcf\x2a\x57\x87" + "\x7a\xf3\xe7\x94\x65\xc2\xb5\xb3" + "\xab\x98\xe3\xc1\x2b\x59\x19\x7c" + "\xd6\xf3\xf9\xbf\xff\x6d\xc6\x82" + "\x13\x2f\x4a\x2e\xcd\x26\xfe\x2d" + "\x01\x70\xf4\xc2\x7f\x1f\x4c\xcb" + "\x47\x77\x0c\xa0\xa3\x03\xec\xda" + "\xa9\xbf\x0d\x2d\xae\xe4\xb8\x7b" + "\xa9\xbc\x08\xb4\x68\x2e\xc5\x60" + "\x8d\x87\x41\x2b\x0f\x69\xf0\xaf" + "\x5f\xba\x72\x20\x0f\x33\xcd\x6d" + "\x36\x7d\x7b\xd5\x05\xf1\x4b\x05" + "\xc4\xfc\x7f\x80\xb9\x4d\xbd\xf7" + "\x7c\x84\x07\x01\xc2\x40\x66\x5b" + "\x98\xc7\x2c\xe3\x97\xfa\xdf\x87" + "\xa0\x1f\xe9\x21\x42\x0f\x3b\xeb" + "\x89\x1c\x3b\xca\x83\x61\x77\x68" + "\x84\xbb\x60\x87\x38\x2e\x25\xd5" + "\x9e\x04\x41\x70\xac\xda\xc0\x9c" + "\x9c\x69\xea\x8d\x4e\x55\x2a\x29" + "\xed\x05\x4b\x7b\x73\x71\x90\x59" + "\x4d\xc8\xd8\x44\xf0\x4c\xe1\x5e" + "\x84\x47\x55\xcc\x32\x3f\xe7\x97" + "\x42\xc6\x32\xac\x40\xe5\xa5\xc7" + "\x8b\xed\xdb\xf7\x83\xd6\xb1\xc2" + "\x52\x5e\x34\xb7\xeb\x6e\xd9\xfc" + "\xe5\x93\x9a\x97\x3e\xb0\xdc\xd9" + "\xd7\x06\x10\xb6\x1d\x80\x59\xdd" + "\x0d\xfe\x64\x35\xcd\x5d\xec\xf0" + "\xba\xd0\x34\xc9\x2d\x91\xc5\x17" + "\x11", + .ilen = 1281, + .rlen = 1281, + .also_non_np = 1, + .np = 3, + .tap = { 1200, 1, 80 }, + }, +}; + +/* + * Same as XChaCha20 test vectors above, but recomputed the ciphertext with + * XChaCha12, using a modified libsodium. + */ +static const struct cipher_testvec xchacha12_tv_template[] = { + { + .key = "\x79\xc9\x97\x98\xac\x67\x30\x0b" + "\xbb\x27\x04\xc9\x5c\x34\x1e\x32" + "\x45\xf3\xdc\xb2\x17\x61\xb9\x8e" + "\x52\xff\x45\xb2\x4f\x30\x4f\xc4", + .klen = 32, + .iv = "\xb3\x3f\xfd\x30\x96\x47\x9b\xcf" + "\xbc\x9a\xee\x49\x41\x76\x88\xa0" + "\xa2\x55\x4f\x8d\x95\x38\x94\x19" + "\x00\x00\x00\x00\x00\x00\x00\x00", + .input = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00", + .result = "\x1b\x78\x7f\xd7\xa1\x41\x68\xab" + "\x3d\x3f\xd1\x7b\x69\x56\xb2\xd5" + "\x43\xce\xeb\xaf\x36\xf0\x29\x9d" + "\x3a\xfb\x18\xae\x1b", + .ilen = 29, + .rlen = 29, + }, { + .key = "\x9d\x23\xbd\x41\x49\xcb\x97\x9c" + "\xcf\x3c\x5c\x94\xdd\x21\x7e\x98" + "\x08\xcb\x0e\x50\xcd\x0f\x67\x81" + "\x22\x35\xea\xaf\x60\x1d\x62\x32", + .klen = 32, + .iv = "\xc0\x47\x54\x82\x66\xb7\xc3\x70" + "\xd3\x35\x66\xa2\x42\x5c\xbf\x30" + "\xd8\x2d\x1e\xaf\x52\x94\x10\x9e" + "\x00\x00\x00\x00\x00\x00\x00\x00", + .input = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00", + .result = "\xfb\x32\x09\x1d\x83\x05\xae\x4c" + "\x13\x1f\x12\x71\xf2\xca\xb2\xeb" + "\x5b\x83\x14\x7d\x83\xf6\x57\x77" + "\x2e\x40\x1f\x92\x2c\xf9\xec\x35" + "\x34\x1f\x93\xdf\xfb\x30\xd7\x35" + "\x03\x05\x78\xc1\x20\x3b\x7a\xe3" + "\x62\xa3\x89\xdc\x11\x11\x45\xa8" + "\x82\x89\xa0\xf1\x4e\xc7\x0f\x11" + "\x69\xdd\x0c\x84\x2b\x89\x5c\xdc" + "\xf0\xde\x01\xef\xc5\x65\x79\x23" + "\x87\x67\xd6\x50\xd9\x8d\xd9\x92" + "\x54\x5b\x0e", + .ilen = 91, + .rlen = 91, + }, { + .key = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00", + .klen = 32, + .iv = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x67\xc6\x69\x73" + "\x51\xff\x4a\xec\x29\xcd\xba\xab" + "\x00\x00\x00\x00\x00\x00\x00\x00", + .input = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00", + .result = "\xdf\x2d\xc6\x21\x2a\x9d\xa1\xbb" + "\xc2\x77\x66\x0c\x5c\x46\xef\xa7" + "\x79\x1b\xb9\xdf\x55\xe2\xf9\x61" + "\x4c\x7b\xa4\x52\x24\xaf\xa2\xda" + "\xd1\x8f\x8f\xa2\x9e\x53\x4d\xc4" + "\xb8\x55\x98\x08\x7c\x08\xd4\x18" + "\x67\x8f\xef\x50\xb1\x5f\xa5\x77" + "\x4c\x25\xe7\x86\x26\x42\xca\x44", + .ilen = 64, + .rlen = 64, + }, { + .key = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x00\x00\x00\x00\x01", + .klen = 32, + .iv = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x02\xf2\xfb\xe3\x46" + "\x7c\xc2\x54\xf8\x1b\xe8\xe7\x8d" + "\x01\x00\x00\x00\x00\x00\x00\x00", + .input = "\x41\x6e\x79\x20\x73\x75\x62\x6d" + "\x69\x73\x73\x69\x6f\x6e\x20\x74" + "\x6f\x20\x74\x68\x65\x20\x49\x45" + "\x54\x46\x20\x69\x6e\x74\x65\x6e" + "\x64\x65\x64\x20\x62\x79\x20\x74" + "\x68\x65\x20\x43\x6f\x6e\x74\x72" + "\x69\x62\x75\x74\x6f\x72\x20\x66" + "\x6f\x72\x20\x70\x75\x62\x6c\x69" + "\x63\x61\x74\x69\x6f\x6e\x20\x61" + "\x73\x20\x61\x6c\x6c\x20\x6f\x72" + "\x20\x70\x61\x72\x74\x20\x6f\x66" + "\x20\x61\x6e\x20\x49\x45\x54\x46" + "\x20\x49\x6e\x74\x65\x72\x6e\x65" + "\x74\x2d\x44\x72\x61\x66\x74\x20" + "\x6f\x72\x20\x52\x46\x43\x20\x61" + "\x6e\x64\x20\x61\x6e\x79\x20\x73" + "\x74\x61\x74\x65\x6d\x65\x6e\x74" + "\x20\x6d\x61\x64\x65\x20\x77\x69" + "\x74\x68\x69\x6e\x20\x74\x68\x65" + "\x20\x63\x6f\x6e\x74\x65\x78\x74" + "\x20\x6f\x66\x20\x61\x6e\x20\x49" + "\x45\x54\x46\x20\x61\x63\x74\x69" + "\x76\x69\x74\x79\x20\x69\x73\x20" + "\x63\x6f\x6e\x73\x69\x64\x65\x72" + "\x65\x64\x20\x61\x6e\x20\x22\x49" + "\x45\x54\x46\x20\x43\x6f\x6e\x74" + "\x72\x69\x62\x75\x74\x69\x6f\x6e" + "\x22\x2e\x20\x53\x75\x63\x68\x20" + "\x73\x74\x61\x74\x65\x6d\x65\x6e" + "\x74\x73\x20\x69\x6e\x63\x6c\x75" + "\x64\x65\x20\x6f\x72\x61\x6c\x20" + "\x73\x74\x61\x74\x65\x6d\x65\x6e" + "\x74\x73\x20\x69\x6e\x20\x49\x45" + "\x54\x46\x20\x73\x65\x73\x73\x69" + "\x6f\x6e\x73\x2c\x20\x61\x73\x20" + "\x77\x65\x6c\x6c\x20\x61\x73\x20" + "\x77\x72\x69\x74\x74\x65\x6e\x20" + "\x61\x6e\x64\x20\x65\x6c\x65\x63" + "\x74\x72\x6f\x6e\x69\x63\x20\x63" + "\x6f\x6d\x6d\x75\x6e\x69\x63\x61" + "\x74\x69\x6f\x6e\x73\x20\x6d\x61" + "\x64\x65\x20\x61\x74\x20\x61\x6e" + "\x79\x20\x74\x69\x6d\x65\x20\x6f" + "\x72\x20\x70\x6c\x61\x63\x65\x2c" + "\x20\x77\x68\x69\x63\x68\x20\x61" + "\x72\x65\x20\x61\x64\x64\x72\x65" + "\x73\x73\x65\x64\x20\x74\x6f", + .result = "\xe4\xa6\xc8\x30\xc4\x23\x13\xd6" + "\x08\x4d\xc9\xb7\xa5\x64\x7c\xb9" + "\x71\xe2\xab\x3e\xa8\x30\x8a\x1c" + "\x4a\x94\x6d\x9b\xe0\xb3\x6f\xf1" + "\xdc\xe3\x1b\xb3\xa9\x6d\x0d\xd6" + "\xd0\xca\x12\xef\xe7\x5f\xd8\x61" + "\x3c\x82\xd3\x99\x86\x3c\x6f\x66" + "\x02\x06\xdc\x55\xf9\xed\xdf\x38" + "\xb4\xa6\x17\x00\x7f\xef\xbf\x4f" + "\xf8\x36\xf1\x60\x7e\x47\xaf\xdb" + "\x55\x9b\x12\xcb\x56\x44\xa7\x1f" + "\xd3\x1a\x07\x3b\x00\xec\xe6\x4c" + "\xa2\x43\x27\xdf\x86\x19\x4f\x16" + "\xed\xf9\x4a\xf3\x63\x6f\xfa\x7f" + "\x78\x11\xf6\x7d\x97\x6f\xec\x6f" + "\x85\x0f\x5c\x36\x13\x8d\x87\xe0" + "\x80\xb1\x69\x0b\x98\x89\x9c\x4e" + "\xf8\xdd\xee\x5c\x0a\x85\xce\xd4" + "\xea\x1b\x48\xbe\x08\xf8\xe2\xa8" + "\xa5\xb0\x3c\x79\xb1\x15\xb4\xb9" + "\x75\x10\x95\x35\x81\x7e\x26\xe6" + "\x78\xa4\x88\xcf\xdb\x91\x34\x18" + "\xad\xd7\x8e\x07\x7d\xab\x39\xf9" + "\xa3\x9e\xa5\x1d\xbb\xed\x61\xfd" + "\xdc\xb7\x5a\x27\xfc\xb5\xc9\x10" + "\xa8\xcc\x52\x7f\x14\x76\x90\xe7" + "\x1b\x29\x60\x74\xc0\x98\x77\xbb" + "\xe0\x54\xbb\x27\x49\x59\x1e\x62" + "\x3d\xaf\x74\x06\xa4\x42\x6f\xc6" + "\x52\x97\xc4\x1d\xc4\x9f\xe2\xe5" + "\x38\x57\x91\xd1\xa2\x28\xcc\x40" + "\xcc\x70\x59\x37\xfc\x9f\x4b\xda" + "\xa0\xeb\x97\x9a\x7d\xed\x14\x5c" + "\x9c\xb7\x93\x26\x41\xa8\x66\xdd" + "\x87\x6a\xc0\xd3\xc2\xa9\x3e\xae" + "\xe9\x72\xfe\xd1\xb3\xac\x38\xea" + "\x4d\x15\xa9\xd5\x36\x61\xe9\x96" + "\x6c\x23\xf8\x43\xe4\x92\x29\xd9" + "\x8b\x78\xf7\x0a\x52\xe0\x19\x5b" + "\x59\x69\x5b\x5d\xa1\x53\xc4\x68" + "\xe1\xbb\xac\x89\x14\xe2\xe2\x85" + "\x41\x18\xf5\xb3\xd1\xfa\x68\x19" + "\x44\x78\xdc\xcf\xe7\x88\x2d\x52" + "\x5f\x40\xb5\x7e\xf8\x88\xa2\xae" + "\x4a\xb2\x07\x35\x9d\x9b\x07\x88" + "\xb7\x00\xd0\x0c\xb6\xa0\x47\x59" + "\xda\x4e\xc9\xab\x9b\x8a\x7b", + + .ilen = 375, + .rlen = 375, + .also_non_np = 1, + .np = 3, + .tap = { 375 - 20, 4, 16 }, + + }, { + .key = "\x1c\x92\x40\xa5\xeb\x55\xd3\x8a" + "\xf3\x33\x88\x86\x04\xf6\xb5\xf0" + "\x47\x39\x17\xc1\x40\x2b\x80\x09" + "\x9d\xca\x5c\xbc\x20\x70\x75\xc0", + .klen = 32, + .iv = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x02\x76\x5a\x2e\x63" + "\x33\x9f\xc9\x9a\x66\x32\x0d\xb7" + "\x2a\x00\x00\x00\x00\x00\x00\x00", + .input = "\x27\x54\x77\x61\x73\x20\x62\x72" + "\x69\x6c\x6c\x69\x67\x2c\x20\x61" + "\x6e\x64\x20\x74\x68\x65\x20\x73" + "\x6c\x69\x74\x68\x79\x20\x74\x6f" + "\x76\x65\x73\x0a\x44\x69\x64\x20" + "\x67\x79\x72\x65\x20\x61\x6e\x64" + "\x20\x67\x69\x6d\x62\x6c\x65\x20" + "\x69\x6e\x20\x74\x68\x65\x20\x77" + "\x61\x62\x65\x3a\x0a\x41\x6c\x6c" + "\x20\x6d\x69\x6d\x73\x79\x20\x77" + "\x65\x72\x65\x20\x74\x68\x65\x20" + "\x62\x6f\x72\x6f\x67\x6f\x76\x65" + "\x73\x2c\x0a\x41\x6e\x64\x20\x74" + "\x68\x65\x20\x6d\x6f\x6d\x65\x20" + "\x72\x61\x74\x68\x73\x20\x6f\x75" + "\x74\x67\x72\x61\x62\x65\x2e", + .result = "\xb9\x68\xbc\x6a\x24\xbc\xcc\xd8" + "\x9b\x2a\x8d\x5b\x96\xaf\x56\xe3" + "\x11\x61\xe7\xa7\x9b\xce\x4e\x7d" + "\x60\x02\x48\xac\xeb\xd5\x3a\x26" + "\x9d\x77\x3b\xb5\x32\x13\x86\x8e" + "\x20\x82\x26\x72\xae\x64\x1b\x7e" + "\x2e\x01\x68\xb4\x87\x45\xa1\x24" + "\xe4\x48\x40\xf0\xaa\xac\xee\xa9" + "\xfc\x31\xad\x9d\x89\xa3\xbb\xd2" + "\xe4\x25\x13\xad\x0f\x5e\xdf\x3c" + "\x27\xab\xb8\x62\x46\x22\x30\x48" + "\x55\x2c\x4e\x84\x78\x1d\x0d\x34" + "\x8d\x3c\x91\x0a\x7f\x5b\x19\x9f" + "\x97\x05\x4c\xa7\x62\x47\x8b\xc5" + "\x44\x2e\x20\x33\xdd\xa0\x82\xa9" + "\x25\x76\x37\xe6\x3c\x67\x5b", + .ilen = 127, + .rlen = 127, + }, { + .key = "\x1c\x92\x40\xa5\xeb\x55\xd3\x8a" + "\xf3\x33\x88\x86\x04\xf6\xb5\xf0" + "\x47\x39\x17\xc1\x40\x2b\x80\x09" + "\x9d\xca\x5c\xbc\x20\x70\x75\xc0", + .klen = 32, + .iv = "\x00\x00\x00\x00\x00\x00\x00\x00" + "\x00\x00\x00\x01\x31\x58\xa3\x5a" + "\x25\x5d\x05\x17\x58\xe9\x5e\xd4" + "\x1c\x00\x00\x00\x00\x00\x00\x00", + .input = "\x49\xee\xe0\xdc\x24\x90\x40\xcd" + "\xc5\x40\x8f\x47\x05\xbc\xdd\x81" + "\x47\xc6\x8d\xe6\xb1\x8f\xd7\xcb" + "\x09\x0e\x6e\x22\x48\x1f\xbf\xb8" + "\x5c\xf7\x1e\x8a\xc1\x23\xf2\xd4" + "\x19\x4b\x01\x0f\x4e\xa4\x43\xce" + "\x01\xc6\x67\xda\x03\x91\x18\x90" + "\xa5\xa4\x8e\x45\x03\xb3\x2d\xac" + "\x74\x92\xd3\x53\x47\xc8\xdd\x25" + "\x53\x6c\x02\x03\x87\x0d\x11\x0c" + "\x58\xe3\x12\x18\xfd\x2a\x5b\x40" + "\x0c\x30\xf0\xb8\x3f\x43\xce\xae" + "\x65\x3a\x7d\x7c\xf4\x54\xaa\xcc" + "\x33\x97\xc3\x77\xba\xc5\x70\xde" + "\xd7\xd5\x13\xa5\x65\xc4\x5f\x0f" + "\x46\x1a\x0d\x97\xb5\xf3\xbb\x3c" + "\x84\x0f\x2b\xc5\xaa\xea\xf2\x6c" + "\xc9\xb5\x0c\xee\x15\xf3\x7d\xbe" + "\x9f\x7b\x5a\xa6\xae\x4f\x83\xb6" + "\x79\x49\x41\xf4\x58\x18\xcb\x86" + "\x7f\x30\x0e\xf8\x7d\x44\x36\xea" + "\x75\xeb\x88\x84\x40\x3c\xad\x4f" + "\x6f\x31\x6b\xaa\x5d\xe5\xa5\xc5" + "\x21\x66\xe9\xa7\xe3\xb2\x15\x88" + "\x78\xf6\x79\xa1\x59\x47\x12\x4e" + "\x9f\x9f\x64\x1a\xa0\x22\x5b\x08" + "\xbe\x7c\x36\xc2\x2b\x66\x33\x1b" + "\xdd\x60\x71\xf7\x47\x8c\x61\xc3" + "\xda\x8a\x78\x1e\x16\xfa\x1e\x86" + "\x81\xa6\x17\x2a\xa7\xb5\xc2\xe7" + "\xa4\xc7\x42\xf1\xcf\x6a\xca\xb4" + "\x45\xcf\xf3\x93\xf0\xe7\xea\xf6" + "\xf4\xe6\x33\x43\x84\x93\xa5\x67" + "\x9b\x16\x58\x58\x80\x0f\x2b\x5c" + "\x24\x74\x75\x7f\x95\x81\xb7\x30" + "\x7a\x33\xa7\xf7\x94\x87\x32\x27" + "\x10\x5d\x14\x4c\x43\x29\xdd\x26" + "\xbd\x3e\x3c\x0e\xfe\x0e\xa5\x10" + "\xea\x6b\x64\xfd\x73\xc6\xed\xec" + "\xa8\xc9\xbf\xb3\xba\x0b\x4d\x07" + "\x70\xfc\x16\xfd\x79\x1e\xd7\xc5" + "\x49\x4e\x1c\x8b\x8d\x79\x1b\xb1" + "\xec\xca\x60\x09\x4c\x6a\xd5\x09" + "\x49\x46\x00\x88\x22\x8d\xce\xea" + "\xb1\x17\x11\xde\x42\xd2\x23\xc1" + "\x72\x11\xf5\x50\x73\x04\x40\x47" + "\xf9\x5d\xe7\xa7\x26\xb1\x7e\xb0" + "\x3f\x58\xc1\x52\xab\x12\x67\x9d" + "\x3f\x43\x4b\x68\xd4\x9c\x68\x38" + "\x07\x8a\x2d\x3e\xf3\xaf\x6a\x4b" + "\xf9\xe5\x31\x69\x22\xf9\xa6\x69" + "\xc6\x9c\x96\x9a\x12\x35\x95\x1d" + "\x95\xd5\xdd\xbe\xbf\x93\x53\x24" + "\xfd\xeb\xc2\x0a\x64\xb0\x77\x00" + "\x6f\x88\xc4\x37\x18\x69\x7c\xd7" + "\x41\x92\x55\x4c\x03\xa1\x9a\x4b" + "\x15\xe5\xdf\x7f\x37\x33\x72\xc1" + "\x8b\x10\x67\xa3\x01\x57\x94\x25" + "\x7b\x38\x71\x7e\xdd\x1e\xcc\x73" + "\x55\xd2\x8e\xeb\x07\xdd\xf1\xda" + "\x58\xb1\x47\x90\xfe\x42\x21\x72" + "\xa3\x54\x7a\xa0\x40\xec\x9f\xdd" + "\xc6\x84\x6e\xca\xae\xe3\x68\xb4" + "\x9d\xe4\x78\xff\x57\xf2\xf8\x1b" + "\x03\xa1\x31\xd9\xde\x8d\xf5\x22" + "\x9c\xdd\x20\xa4\x1e\x27\xb1\x76" + "\x4f\x44\x55\xe2\x9b\xa1\x9c\xfe" + "\x54\xf7\x27\x1b\xf4\xde\x02\xf5" + "\x1b\x55\x48\x5c\xdc\x21\x4b\x9e" + "\x4b\x6e\xed\x46\x23\xdc\x65\xb2" + "\xcf\x79\x5f\x28\xe0\x9e\x8b\xe7" + "\x4c\x9d\x8a\xff\xc1\xa6\x28\xb8" + "\x65\x69\x8a\x45\x29\xef\x74\x85" + "\xde\x79\xc7\x08\xae\x30\xb0\xf4" + "\xa3\x1d\x51\x41\xab\xce\xcb\xf6" + "\xb5\xd8\x6d\xe0\x85\xe1\x98\xb3" + "\x43\xbb\x86\x83\x0a\xa0\xf5\xb7" + "\x04\x0b\xfa\x71\x1f\xb0\xf6\xd9" + "\x13\x00\x15\xf0\xc7\xeb\x0d\x5a" + "\x9f\xd7\xb9\x6c\x65\x14\x22\x45" + "\x6e\x45\x32\x3e\x7e\x60\x1a\x12" + "\x97\x82\x14\xfb\xaa\x04\x22\xfa" + "\xa0\xe5\x7e\x8c\x78\x02\x48\x5d" + "\x78\x33\x5a\x7c\xad\xdb\x29\xce" + "\xbb\x8b\x61\xa4\xb7\x42\xe2\xac" + "\x8b\x1a\xd9\x2f\x0b\x8b\x62\x21" + "\x83\x35\x7e\xad\x73\xc2\xb5\x6c" + "\x10\x26\x38\x07\xe5\xc7\x36\x80" + "\xe2\x23\x12\x61\xf5\x48\x4b\x2b" + "\xc5\xdf\x15\xd9\x87\x01\xaa\xac" + "\x1e\x7c\xad\x73\x78\x18\x63\xe0" + "\x8b\x9f\x81\xd8\x12\x6a\x28\x10" + "\xbe\x04\x68\x8a\x09\x7c\x1b\x1c" + "\x83\x66\x80\x47\x80\xe8\xfd\x35" + "\x1c\x97\x6f\xae\x49\x10\x66\xcc" + "\xc6\xd8\xcc\x3a\x84\x91\x20\x77" + "\x72\xe4\x24\xd2\x37\x9f\xc5\xc9" + "\x25\x94\x10\x5f\x40\x00\x64\x99" + "\xdc\xae\xd7\x21\x09\x78\x50\x15" + "\xac\x5f\xc6\x2c\xa2\x0b\xa9\x39" + "\x87\x6e\x6d\xab\xde\x08\x51\x16" + "\xc7\x13\xe9\xea\xed\x06\x8e\x2c" + "\xf8\x37\x8c\xf0\xa6\x96\x8d\x43" + "\xb6\x98\x37\xb2\x43\xed\xde\xdf" + "\x89\x1a\xe7\xeb\x9d\xa1\x7b\x0b" + "\x77\xb0\xe2\x75\xc0\xf1\x98\xd9" + "\x80\x55\xc9\x34\x91\xd1\x59\xe8" + "\x4b\x0f\xc1\xa9\x4b\x7a\x84\x06" + "\x20\xa8\x5d\xfa\xd1\xde\x70\x56" + "\x2f\x9e\x91\x9c\x20\xb3\x24\xd8" + "\x84\x3d\xe1\x8c\x7e\x62\x52\xe5" + "\x44\x4b\x9f\xc2\x93\x03\xea\x2b" + "\x59\xc5\xfa\x3f\x91\x2b\xbb\x23" + "\xf5\xb2\x7b\xf5\x38\xaf\xb3\xee" + "\x63\xdc\x7b\xd1\xff\xaa\x8b\xab" + "\x82\x6b\x37\x04\xeb\x74\xbe\x79" + "\xb9\x83\x90\xef\x20\x59\x46\xff" + "\xe9\x97\x3e\x2f\xee\xb6\x64\x18" + "\x38\x4c\x7a\x4a\xf9\x61\xe8\x9a" + "\xa1\xb5\x01\xa6\x47\xd3\x11\xd4" + "\xce\xd3\x91\x49\x88\xc7\xb8\x4d" + "\xb1\xb9\x07\x6d\x16\x72\xae\x46" + "\x5e\x03\xa1\x4b\xb6\x02\x30\xa8" + "\x3d\xa9\x07\x2a\x7c\x19\xe7\x62" + "\x87\xe3\x82\x2f\x6f\xe1\x09\xd9" + "\x94\x97\xea\xdd\x58\x9e\xae\x76" + "\x7e\x35\xe5\xb4\xda\x7e\xf4\xde" + "\xf7\x32\x87\xcd\x93\xbf\x11\x56" + "\x11\xbe\x08\x74\xe1\x69\xad\xe2" + "\xd7\xf8\x86\x75\x8a\x3c\xa4\xbe" + "\x70\xa7\x1b\xfc\x0b\x44\x2a\x76" + "\x35\xea\x5d\x85\x81\xaf\x85\xeb" + "\xa0\x1c\x61\xc2\xf7\x4f\xa5\xdc" + "\x02\x7f\xf6\x95\x40\x6e\x8a\x9a" + "\xf3\x5d\x25\x6e\x14\x3a\x22\xc9" + "\x37\x1c\xeb\x46\x54\x3f\xa5\x91" + "\xc2\xb5\x8c\xfe\x53\x08\x97\x32" + "\x1b\xb2\x30\x27\xfe\x25\x5d\xdc" + "\x08\x87\xd0\xe5\x94\x1a\xd4\xf1" + "\xfe\xd6\xb4\xa3\xe6\x74\x81\x3c" + "\x1b\xb7\x31\xa7\x22\xfd\xd4\xdd" + "\x20\x4e\x7c\x51\xb0\x60\x73\xb8" + "\x9c\xac\x91\x90\x7e\x01\xb0\xe1" + "\x8a\x2f\x75\x1c\x53\x2a\x98\x2a" + "\x06\x52\x95\x52\xb2\xe9\x25\x2e" + "\x4c\xe2\x5a\x00\xb2\x13\x81\x03" + "\x77\x66\x0d\xa5\x99\xda\x4e\x8c" + "\xac\xf3\x13\x53\x27\x45\xaf\x64" + "\x46\xdc\xea\x23\xda\x97\xd1\xab" + "\x7d\x6c\x30\x96\x1f\xbc\x06\x34" + "\x18\x0b\x5e\x21\x35\x11\x8d\x4c" + "\xe0\x2d\xe9\x50\x16\x74\x81\xa8" + "\xb4\x34\xb9\x72\x42\xa6\xcc\xbc" + "\xca\x34\x83\x27\x10\x5b\x68\x45" + "\x8f\x52\x22\x0c\x55\x3d\x29\x7c" + "\xe3\xc0\x66\x05\x42\x91\x5f\x58" + "\xfe\x4a\x62\xd9\x8c\xa9\x04\x19" + "\x04\xa9\x08\x4b\x57\xfc\x67\x53" + "\x08\x7c\xbc\x66\x8a\xb0\xb6\x9f" + "\x92\xd6\x41\x7c\x5b\x2a\x00\x79" + "\x72", + .result = "\xe1\xb6\x8b\x5c\x80\xb8\xcc\x08" + "\x1b\x84\xb2\xd1\xad\xa4\x70\xac" + "\x67\xa9\x39\x27\xac\xb4\x5b\xb7" + "\x4c\x26\x77\x23\x1d\xce\x0a\xbe" + "\x18\x9e\x42\x8b\xbd\x7f\xd6\xf1" + "\xf1\x6b\xe2\x6d\x7f\x92\x0e\xcb" + "\xb8\x79\xba\xb4\xac\x7e\x2d\xc0" + "\x9e\x83\x81\x91\xd5\xea\xc3\x12" + "\x8d\xa4\x26\x70\xa4\xf9\x71\x0b" + "\xbd\x2e\xe1\xb3\x80\x42\x25\xb3" + "\x0b\x31\x99\xe1\x0d\xde\xa6\x90" + "\xf2\xa3\x10\xf7\xe5\xf3\x83\x1e" + "\x2c\xfb\x4d\xf0\x45\x3d\x28\x3c" + "\xb8\xf1\xcb\xbf\x67\xd8\x43\x5a" + "\x9d\x7b\x73\x29\x88\x0f\x13\x06" + "\x37\x50\x0d\x7c\xe6\x9b\x07\xdd" + "\x7e\x01\x1f\x81\x90\x10\x69\xdb" + "\xa4\xad\x8a\x5e\xac\x30\x72\xf2" + "\x36\xcd\xe3\x23\x49\x02\x93\xfa" + "\x3d\xbb\xe2\x98\x83\xeb\xe9\x8d" + "\xb3\x8f\x11\xaa\x53\xdb\xaf\x2e" + "\x95\x13\x99\x3d\x71\xbd\x32\x92" + "\xdd\xfc\x9d\x5e\x6f\x63\x2c\xee" + "\x91\x1f\x4c\x64\x3d\x87\x55\x0f" + "\xcc\x3d\x89\x61\x53\x02\x57\x8f" + "\xe4\x77\x29\x32\xaf\xa6\x2f\x0a" + "\xae\x3c\x3f\x3f\xf4\xfb\x65\x52" + "\xc5\xc1\x78\x78\x53\x28\xad\xed" + "\xd1\x67\x37\xc7\x59\x70\xcd\x0a" + "\xb8\x0f\x80\x51\x9f\xc0\x12\x5e" + "\x06\x0a\x7e\xec\x24\x5f\x73\x00" + "\xb1\x0b\x31\x47\x4f\x73\x8d\xb4" + "\xce\xf3\x55\x45\x6c\x84\x27\xba" + "\xb9\x6f\x03\x4a\xeb\x98\x88\x6e" + "\x53\xed\x25\x19\x0d\x8f\xfe\xca" + "\x60\xe5\x00\x93\x6e\x3c\xff\x19" + "\xae\x08\x3b\x8a\xa6\x84\x05\xfe" + "\x9b\x59\xa0\x8c\xc8\x05\x45\xf5" + "\x05\x37\xdc\x45\x6f\x8b\x95\x8c" + "\x4e\x11\x45\x7a\xce\x21\xa5\xf7" + "\x71\x67\xb9\xce\xd7\xf9\xe9\x5e" + "\x60\xf5\x53\x7a\xa8\x85\x14\x03" + "\xa0\x92\xec\xf3\x51\x80\x84\xc4" + "\xdc\x11\x9e\x57\xce\x4b\x45\xcf" + "\x90\x95\x85\x0b\x96\xe9\xee\x35" + "\x10\xb8\x9b\xf2\x59\x4a\xc6\x7e" + "\x85\xe5\x6f\x38\x51\x93\x40\x0c" + "\x99\xd7\x7f\x32\xa8\x06\x27\xd1" + "\x2b\xd5\xb5\x3a\x1a\xe1\x5e\xda" + "\xcd\x5a\x50\x30\x3c\xc7\xe7\x65" + "\xa6\x07\x0b\x98\x91\xc6\x20\x27" + "\x2a\x03\x63\x1b\x1e\x3d\xaf\xc8" + "\x71\x48\x46\x6a\x64\x28\xf9\x3d" + "\xd1\x1d\xab\xc8\x40\x76\xc2\x39" + "\x4e\x00\x75\xd2\x0e\x82\x58\x8c" + "\xd3\x73\x5a\xea\x46\x89\xbe\xfd" + "\x4e\x2c\x0d\x94\xaa\x9b\x68\xac" + "\x86\x87\x30\x7e\xa9\x16\xcd\x59" + "\xd2\xa6\xbe\x0a\xd8\xf5\xfd\x2d" + "\x49\x69\xd2\x1a\x90\xd2\x1b\xed" + "\xff\x71\x04\x87\x87\x21\xc4\xb8" + "\x1f\x5b\x51\x33\xd0\xd6\x59\x9a" + "\x03\x0e\xd3\x8b\xfb\x57\x73\xfd" + "\x5a\x52\x63\x82\xc8\x85\x2f\xcb" + "\x74\x6d\x4e\xd9\x68\x37\x85\x6a" + "\xd4\xfb\x94\xed\x8d\xd1\x1a\xaf" + "\x76\xa7\xb7\x88\xd0\x2b\x4e\xda" + "\xec\x99\x94\x27\x6f\x87\x8c\xdf" + "\x4b\x5e\xa6\x66\xdd\xcb\x33\x7b" + "\x64\x94\x31\xa8\x37\xa6\x1d\xdb" + "\x0d\x5c\x93\xa4\x40\xf9\x30\x53" + "\x4b\x74\x8d\xdd\xf6\xde\x3c\xac" + "\x5c\x80\x01\x3a\xef\xb1\x9a\x02" + "\x0c\x22\x8e\xe7\x44\x09\x74\x4c" + "\xf2\x9a\x27\x69\x7f\x12\x32\x36" + "\xde\x92\xdf\xde\x8f\x5b\x31\xab" + "\x4a\x01\x26\xe0\xb1\xda\xe8\x37" + "\x21\x64\xe8\xff\x69\xfc\x9e\x41" + "\xd2\x96\x2d\x18\x64\x98\x33\x78" + "\x24\x61\x73\x9b\x47\x29\xf1\xa7" + "\xcb\x27\x0f\xf0\x85\x6d\x8c\x9d" + "\x2c\x95\x9e\xe5\xb2\x8e\x30\x29" + "\x78\x8a\x9d\x65\xb4\x8e\xde\x7b" + "\xd9\x00\x50\xf5\x7f\x81\xc3\x1b" + "\x25\x85\xeb\xc2\x8c\x33\x22\x1e" + "\x68\x38\x22\x30\xd8\x2e\x00\x98" + "\x85\x16\x06\x56\xb4\x81\x74\x20" + "\x95\xdb\x1c\x05\x19\xe8\x23\x4d" + "\x65\x5d\xcc\xd8\x7f\xc4\x2d\x0f" + "\x57\x26\x71\x07\xad\xaa\x71\x9f" + "\x19\x76\x2f\x25\x51\x88\xe4\xc0" + "\x82\x6e\x08\x05\x37\x04\xee\x25" + "\x23\x90\xe9\x4e\xce\x9b\x16\xc1" + "\x31\xe7\x6e\x2c\x1b\xe1\x85\x9a" + "\x0c\x8c\xbb\x12\x1e\x68\x7b\x93" + "\xa9\x3c\x39\x56\x23\x3e\x6e\xc7" + "\x77\x84\xd3\xe0\x86\x59\xaa\xb9" + "\xd5\x53\x58\xc9\x0a\x83\x5f\x85" + "\xd8\x47\x14\x67\x8a\x3c\x17\xe0" + "\xab\x02\x51\xea\xf1\xf0\x4f\x30" + "\x7d\xe0\x92\xc2\x5f\xfb\x19\x5a" + "\x3f\xbd\xf4\x39\xa4\x31\x0c\x39" + "\xd1\xae\x4e\xf7\x65\x7f\x1f\xce" + "\xc2\x39\xd1\x84\xd4\xe5\x02\xe0" + "\x58\xaa\xf1\x5e\x81\xaf\x7f\x72" + "\x0f\x08\x99\x43\xb9\xd8\xac\x41" + "\x35\x55\xf2\xb2\xd4\x98\xb8\x3b" + "\x2b\x3c\x3e\x16\x06\x31\xfc\x79" + "\x47\x38\x63\x51\xc5\xd0\x26\xd7" + "\x43\xb4\x2b\xd9\xc5\x05\xf2\x9d" + "\x18\xc9\x26\x82\x56\xd2\x11\x05" + "\xb6\x89\xb4\x43\x9c\xb5\x9d\x11" + "\x6c\x83\x37\x71\x27\x1c\xae\xbf" + "\xcd\x57\xd2\xee\x0d\x5a\x15\x26" + "\x67\x88\x80\x80\x1b\xdc\xc1\x62" + "\xdd\x4c\xff\x92\x5c\x6c\xe1\xa0" + "\xe3\x79\xa9\x65\x8c\x8c\x14\x42" + "\xe5\x11\xd2\x1a\xad\xa9\x56\x6f" + "\x98\xfc\x8a\x7b\x56\x1f\xc6\xc1" + "\x52\x12\x92\x9b\x41\x0f\x4b\xae" + "\x1b\x4a\xbc\xfe\x23\xb6\x94\x70" + "\x04\x30\x9e\x69\x47\xbe\xb8\x8f" + "\xca\x45\xd7\x8a\xf4\x78\x3e\xaa" + "\x71\x17\xd8\x1e\xb8\x11\x8f\xbc" + "\xc8\x1a\x65\x7b\x41\x89\x72\xc7" + "\x5f\xbe\xc5\x2a\xdb\x5c\x54\xf9" + "\x25\xa3\x7a\x80\x56\x9c\x8c\xab" + "\x26\x19\x10\x36\xa6\xf3\x14\x79" + "\x40\x98\x70\x68\xb7\x35\xd9\xb9" + "\x27\xd4\xe7\x74\x5b\x3d\x97\xb4" + "\xd9\xaa\xd9\xf2\xb5\x14\x84\x1f" + "\xa9\xde\x12\x44\x5b\x00\xc0\xbc" + "\xc8\x11\x25\x1b\x67\x7a\x15\x72" + "\xa6\x31\x6f\xf4\x68\x7a\x86\x9d" + "\x43\x1c\x5f\x16\xd3\xad\x2e\x52" + "\xf3\xb4\xc3\xfa\x27\x2e\x68\x6c" + "\x06\xe7\x4c\x4f\xa2\xe0\xe4\x21" + "\x5d\x9e\x33\x58\x8d\xbf\xd5\x70" + "\xf8\x80\xa5\xdd\xe7\x18\x79\xfa" + "\x7b\xfd\x09\x69\x2c\x37\x32\xa8" + "\x65\xfa\x8d\x8b\x5c\xcc\xe8\xf3" + "\x37\xf6\xa6\xc6\x5c\xa2\x66\x79" + "\xfa\x8a\xa7\xd1\x0b\x2e\x1b\x5e" + "\x95\x35\x00\x76\xae\x42\xf7\x50" + "\x51\x78\xfb\xb4\x28\x24\xde\x1a" + "\x70\x8b\xed\xca\x3c\x5e\xe4\xbd" + "\x28\xb5\xf3\x76\x4f\x67\x5d\x81" + "\xb2\x60\x87\xd9\x7b\x19\x1a\xa7" + "\x79\xa2\xfa\x3f\x9e\xa9\xd7\x25" + "\x61\xe1\x74\x31\xa2\x77\xa0\x1b" + "\xf6\xf7\xcb\xc5\xaa\x9e\xce\xf9" + "\x9b\x96\xef\x51\xc3\x1a\x44\x96" + "\xae\x17\x50\xab\x29\x08\xda\xcc" + "\x1a\xb3\x12\xd0\x24\xe4\xe2\xe0" + "\xc6\xe3\xcc\x82\xd0\xba\x47\x4c" + "\x3f\x49\xd7\xe8\xb6\x61\xaa\x65" + "\x25\x18\x40\x2d\x62\x25\x02\x71" + "\x61\xa2\xc1\xb2\x13\xd2\x71\x3f" + "\x43\x1a\xc9\x09\x92\xff\xd5\x57" + "\xf0\xfc\x5e\x1c\xf1\xf5\xf9\xf3" + "\x5b", + .ilen = 1281, + .rlen = 1281, + .also_non_np = 1, + .np = 3, + .tap = { 1200, 1, 80 }, + }, +}; + +/* Adiantum test vectors from https://github.com/google/adiantum */ +static const struct cipher_testvec adiantum_xchacha12_aes_enc_tv_template[] = { + { + .key = "\x9e\xeb\xb2\x49\x3c\x1c\xf5\xf4" + "\x6a\x99\xc2\xc4\xdf\xb1\xf4\xdd" + "\x75\x20\x57\xea\x2c\x4f\xcd\xb2" + "\xa5\x3d\x7b\x49\x1e\xab\xfd\x0f", + .klen = 32, + .iv = "\xdf\x63\xd4\xab\xd2\x49\xf3\xd8" + "\x33\x81\x37\x60\x7d\xfa\x73\x08" + "\xd8\x49\x6d\x80\xe8\x2f\x62\x54" + "\xeb\x0e\xa9\x39\x5b\x45\x7f\x8a", + .input = "\x67\xc9\xf2\x30\x84\x41\x8e\x43" + "\xfb\xf3\xb3\x3e\x79\x36\x7f\xe8", + .result = "\x6d\x32\x86\x18\x67\x86\x0f\x3f" + "\x96\x7c\x9d\x28\x0d\x53\xec\x9f", + .ilen = 16, + .rlen = 16, + .also_non_np = 1, + .np = 2, + .tap = { 14, 2 }, + }, { + .key = "\x36\x2b\x57\x97\xf8\x5d\xcd\x99" + "\x5f\x1a\x5a\x44\x1d\x92\x0f\x27" + "\xcc\x16\xd7\x2b\x85\x63\x99\xd3" + "\xba\x96\xa1\xdb\xd2\x60\x68\xda", + .klen = 32, + .iv = "\xef\x58\x69\xb1\x2c\x5e\x9a\x47" + "\x24\xc1\xb1\x69\xe1\x12\x93\x8f" + "\x43\x3d\x6d\x00\xdb\x5e\xd8\xd9" + "\x12\x9a\xfe\xd9\xff\x2d\xaa\xc4", + .input = "\x5e\xa8\x68\x19\x85\x98\x12\x23" + "\x26\x0a\xcc\xdb\x0a\x04\xb9\xdf" + "\x4d\xb3\x48\x7b\xb0\xe3\xc8\x19" + "\x43\x5a\x46\x06\x94\x2d\xf2", + .result = "\xc7\xc6\xf1\x73\x8f\xc4\xff\x4a" + "\x39\xbe\x78\xbe\x8d\x28\xc8\x89" + "\x46\x63\xe7\x0c\x7d\x87\xe8\x4e" + "\xc9\x18\x7b\xbe\x18\x60\x50", + .ilen = 31, + .rlen = 31, + }, { + .key = "\xa5\x28\x24\x34\x1a\x3c\xd8\xf7" + "\x05\x91\x8f\xee\x85\x1f\x35\x7f" + "\x80\x3d\xfc\x9b\x94\xf6\xfc\x9e" + "\x19\x09\x00\xa9\x04\x31\x4f\x11", + .klen = 32, + .iv = "\xa1\xba\x49\x95\xff\x34\x6d\xb8" + "\xcd\x87\x5d\x5e\xfd\xea\x85\xdb" + "\x8a\x7b\x5e\xb2\x5d\x57\xdd\x62" + "\xac\xa9\x8c\x41\x42\x94\x75\xb7", + .input = "\x69\xb4\xe8\x8c\x37\xe8\x67\x82" + "\xf1\xec\x5d\x04\xe5\x14\x91\x13" + "\xdf\xf2\x87\x1b\x69\x81\x1d\x71" + "\x70\x9e\x9c\x3b\xde\x49\x70\x11" + "\xa0\xa3\xdb\x0d\x54\x4f\x66\x69" + "\xd7\xdb\x80\xa7\x70\x92\x68\xce" + "\x81\x04\x2c\xc6\xab\xae\xe5\x60" + "\x15\xe9\x6f\xef\xaa\x8f\xa7\xa7" + "\x63\x8f\xf2\xf0\x77\xf1\xa8\xea" + "\xe1\xb7\x1f\x9e\xab\x9e\x4b\x3f" + "\x07\x87\x5b\x6f\xcd\xa8\xaf\xb9" + "\xfa\x70\x0b\x52\xb8\xa8\xa7\x9e" + "\x07\x5f\xa6\x0e\xb3\x9b\x79\x13" + "\x79\xc3\x3e\x8d\x1c\x2c\x68\xc8" + "\x51\x1d\x3c\x7b\x7d\x79\x77\x2a" + "\x56\x65\xc5\x54\x23\x28\xb0\x03", + .result = "\x9e\x16\xab\xed\x4b\xa7\x42\x5a" + "\xc6\xfb\x4e\x76\xff\xbe\x03\xa0" + "\x0f\xe3\xad\xba\xe4\x98\x2b\x0e" + "\x21\x48\xa0\xb8\x65\x48\x27\x48" + "\x84\x54\x54\xb2\x9a\x94\x7b\xe6" + "\x4b\x29\xe9\xcf\x05\x91\x80\x1a" + "\x3a\xf3\x41\x96\x85\x1d\x9f\x74" + "\x51\x56\x63\xfa\x7c\x28\x85\x49" + "\xf7\x2f\xf9\xf2\x18\x46\xf5\x33" + "\x80\xa3\x3c\xce\xb2\x57\x93\xf5" + "\xae\xbd\xa9\xf5\x7b\x30\xc4\x93" + "\x66\xe0\x30\x77\x16\xe4\xa0\x31" + "\xba\x70\xbc\x68\x13\xf5\xb0\x9a" + "\xc1\xfc\x7e\xfe\x55\x80\x5c\x48" + "\x74\xa6\xaa\xa3\xac\xdc\xc2\xf5" + "\x8d\xde\x34\x86\x78\x60\x75\x8d", + .ilen = 128, + .rlen = 128, + .also_non_np = 1, + .np = 4, + .tap = { 104, 16, 4, 4 }, + }, { + .key = "\xd3\x81\x72\x18\x23\xff\x6f\x4a" + "\x25\x74\x29\x0d\x51\x8a\x0e\x13" + "\xc1\x53\x5d\x30\x8d\xee\x75\x0d" + "\x14\xd6\x69\xc9\x15\xa9\x0c\x60", + .klen = 32, + .iv = "\x65\x9b\xd4\xa8\x7d\x29\x1d\xf4" + "\xc4\xd6\x9b\x6a\x28\xab\x64\xe2" + "\x62\x81\x97\xc5\x81\xaa\xf9\x44" + "\xc1\x72\x59\x82\xaf\x16\xc8\x2c", + .input = "\xc7\x6b\x52\x6a\x10\xf0\xcc\x09" + "\xc1\x12\x1d\x6d\x21\xa6\x78\xf5" + "\x05\xa3\x69\x60\x91\x36\x98\x57" + "\xba\x0c\x14\xcc\xf3\x2d\x73\x03" + "\xc6\xb2\x5f\xc8\x16\x27\x37\x5d" + "\xd0\x0b\x87\xb2\x50\x94\x7b\x58" + "\x04\xf4\xe0\x7f\x6e\x57\x8e\xc9" + "\x41\x84\xc1\xb1\x7e\x4b\x91\x12" + "\x3a\x8b\x5d\x50\x82\x7b\xcb\xd9" + "\x9a\xd9\x4e\x18\x06\x23\x9e\xd4" + "\xa5\x20\x98\xef\xb5\xda\xe5\xc0" + "\x8a\x6a\x83\x77\x15\x84\x1e\xae" + "\x78\x94\x9d\xdf\xb7\xd1\xea\x67" + "\xaa\xb0\x14\x15\xfa\x67\x21\x84" + "\xd3\x41\x2a\xce\xba\x4b\x4a\xe8" + "\x95\x62\xa9\x55\xf0\x80\xad\xbd" + "\xab\xaf\xdd\x4f\xa5\x7c\x13\x36" + "\xed\x5e\x4f\x72\xad\x4b\xf1\xd0" + "\x88\x4e\xec\x2c\x88\x10\x5e\xea" + "\x12\xc0\x16\x01\x29\xa3\xa0\x55" + "\xaa\x68\xf3\xe9\x9d\x3b\x0d\x3b" + "\x6d\xec\xf8\xa0\x2d\xf0\x90\x8d" + "\x1c\xe2\x88\xd4\x24\x71\xf9\xb3" + "\xc1\x9f\xc5\xd6\x76\x70\xc5\x2e" + "\x9c\xac\xdb\x90\xbd\x83\x72\xba" + "\x6e\xb5\xa5\x53\x83\xa9\xa5\xbf" + "\x7d\x06\x0e\x3c\x2a\xd2\x04\xb5" + "\x1e\x19\x38\x09\x16\xd2\x82\x1f" + "\x75\x18\x56\xb8\x96\x0b\xa6\xf9" + "\xcf\x62\xd9\x32\x5d\xa9\xd7\x1d" + "\xec\xe4\xdf\x1b\xbe\xf1\x36\xee" + "\xe3\x7b\xb5\x2f\xee\xf8\x53\x3d" + "\x6a\xb7\x70\xa9\xfc\x9c\x57\x25" + "\xf2\x89\x10\xd3\xb8\xa8\x8c\x30" + "\xae\x23\x4f\x0e\x13\x66\x4f\xe1" + "\xb6\xc0\xe4\xf8\xef\x93\xbd\x6e" + "\x15\x85\x6b\xe3\x60\x81\x1d\x68" + "\xd7\x31\x87\x89\x09\xab\xd5\x96" + "\x1d\xf3\x6d\x67\x80\xca\x07\x31" + "\x5d\xa7\xe4\xfb\x3e\xf2\x9b\x33" + "\x52\x18\xc8\x30\xfe\x2d\xca\x1e" + "\x79\x92\x7a\x60\x5c\xb6\x58\x87" + "\xa4\x36\xa2\x67\x92\x8b\xa4\xb7" + "\xf1\x86\xdf\xdc\xc0\x7e\x8f\x63" + "\xd2\xa2\xdc\x78\xeb\x4f\xd8\x96" + "\x47\xca\xb8\x91\xf9\xf7\x94\x21" + "\x5f\x9a\x9f\x5b\xb8\x40\x41\x4b" + "\x66\x69\x6a\x72\xd0\xcb\x70\xb7" + "\x93\xb5\x37\x96\x05\x37\x4f\xe5" + "\x8c\xa7\x5a\x4e\x8b\xb7\x84\xea" + "\xc7\xfc\x19\x6e\x1f\x5a\xa1\xac" + "\x18\x7d\x52\x3b\xb3\x34\x62\x99" + "\xe4\x9e\x31\x04\x3f\xc0\x8d\x84" + "\x17\x7c\x25\x48\x52\x67\x11\x27" + "\x67\xbb\x5a\x85\xca\x56\xb2\x5c" + "\xe6\xec\xd5\x96\x3d\x15\xfc\xfb" + "\x22\x25\xf4\x13\xe5\x93\x4b\x9a" + "\x77\xf1\x52\x18\xfa\x16\x5e\x49" + "\x03\x45\xa8\x08\xfa\xb3\x41\x92" + "\x79\x50\x33\xca\xd0\xd7\x42\x55" + "\xc3\x9a\x0c\x4e\xd9\xa4\x3c\x86" + "\x80\x9f\x53\xd1\xa4\x2e\xd1\xbc" + "\xf1\x54\x6e\x93\xa4\x65\x99\x8e" + "\xdf\x29\xc0\x64\x63\x07\xbb\xea", + .result = "\x15\x97\xd0\x86\x18\x03\x9c\x51" + "\xc5\x11\x36\x62\x13\x92\xe6\x73" + "\x29\x79\xde\xa1\x00\x3e\x08\x64" + "\x17\x1a\xbc\xd5\xfe\x33\x0e\x0c" + "\x7c\x94\xa7\xc6\x3c\xbe\xac\xa2" + "\x89\xe6\xbc\xdf\x0c\x33\x27\x42" + "\x46\x73\x2f\xba\x4e\xa6\x46\x8f" + "\xe4\xee\x39\x63\x42\x65\xa3\x88" + "\x7a\xad\x33\x23\xa9\xa7\x20\x7f" + "\x0b\xe6\x6a\xc3\x60\xda\x9e\xb4" + "\xd6\x07\x8a\x77\x26\xd1\xab\x44" + "\x99\x55\x03\x5e\xed\x8d\x7b\xbd" + "\xc8\x21\xb7\x21\x30\x3f\xc0\xb5" + "\xc8\xec\x6c\x23\xa6\xa3\x6d\xf1" + "\x30\x0a\xd0\xa6\xa9\x28\x69\xae" + "\x2a\xe6\x54\xac\x82\x9d\x6a\x95" + "\x6f\x06\x44\xc5\x5a\x77\x6e\xec" + "\xf8\xf8\x63\xb2\xe6\xaa\xbd\x8e" + "\x0e\x8a\x62\x00\x03\xc8\x84\xdd" + "\x47\x4a\xc3\x55\xba\xb7\xe7\xdf" + "\x08\xbf\x62\xf5\xe8\xbc\xb6\x11" + "\xe4\xcb\xd0\x66\x74\x32\xcf\xd4" + "\xf8\x51\x80\x39\x14\x05\x12\xdb" + "\x87\x93\xe2\x26\x30\x9c\x3a\x21" + "\xe5\xd0\x38\x57\x80\x15\xe4\x08" + "\x58\x05\x49\x7d\xe6\x92\x77\x70" + "\xfb\x1e\x2d\x6a\x84\x00\xc8\x68" + "\xf7\x1a\xdd\xf0\x7b\x38\x1e\xd8" + "\x2c\x78\x78\x61\xcf\xe3\xde\x69" + "\x1f\xd5\x03\xd5\x1a\xb4\xcf\x03" + "\xc8\x7a\x70\x68\x35\xb4\xf6\xbe" + "\x90\x62\xb2\x28\x99\x86\xf5\x44" + "\x99\xeb\x31\xcf\xca\xdf\xd0\x21" + "\xd6\x60\xf7\x0f\x40\xb4\x80\xb7" + "\xab\xe1\x9b\x45\xba\x66\xda\xee" + "\xdd\x04\x12\x40\x98\xe1\x69\xe5" + "\x2b\x9c\x59\x80\xe7\x7b\xcc\x63" + "\xa6\xc0\x3a\xa9\xfe\x8a\xf9\x62" + "\x11\x34\x61\x94\x35\xfe\xf2\x99" + "\xfd\xee\x19\xea\x95\xb6\x12\xbf" + "\x1b\xdf\x02\x1a\xcc\x3e\x7e\x65" + "\x78\x74\x10\x50\x29\x63\x28\xea" + "\x6b\xab\xd4\x06\x4d\x15\x24\x31" + "\xc7\x0a\xc9\x16\xb6\x48\xf0\xbf" + "\x49\xdb\x68\x71\x31\x8f\x87\xe2" + "\x13\x05\x64\xd6\x22\x0c\xf8\x36" + "\x84\x24\x3e\x69\x5e\xb8\x9e\x16" + "\x73\x6c\x83\x1e\xe0\x9f\x9e\xba" + "\xe5\x59\x21\x33\x1b\xa9\x26\xc2" + "\xc7\xd9\x30\x73\xb6\xa6\x73\x82" + "\x19\xfa\x44\x4d\x40\x8b\x69\x04" + "\x94\x74\xea\x6e\xb3\x09\x47\x01" + "\x2a\xb9\x78\x34\x43\x11\xed\xd6" + "\x8c\x95\x65\x1b\x85\x67\xa5\x40" + "\xac\x9c\x05\x4b\x57\x4a\xa9\x96" + "\x0f\xdd\x4f\xa1\xe0\xcf\x6e\xc7" + "\x1b\xed\xa2\xb4\x56\x8c\x09\x6e" + "\xa6\x65\xd7\x55\x81\xb7\xed\x11" + "\x9b\x40\x75\xa8\x6b\x56\xaf\x16" + "\x8b\x3d\xf4\xcb\xfe\xd5\x1d\x3d" + "\x85\xc2\xc0\xde\x43\x39\x4a\x96" + "\xba\x88\x97\xc0\xd6\x00\x0e\x27" + "\x21\xb0\x21\x52\xba\xa7\x37\xaa" + "\xcc\xbf\x95\xa8\xf4\xd0\x91\xf6", + .ilen = 512, + .rlen = 512, + .also_non_np = 1, + .np = 2, + .tap = { 144, 368 }, + } +}; + +static const struct cipher_testvec adiantum_xchacha12_aes_dec_tv_template[] = { + { + .key = "\x9e\xeb\xb2\x49\x3c\x1c\xf5\xf4" + "\x6a\x99\xc2\xc4\xdf\xb1\xf4\xdd" + "\x75\x20\x57\xea\x2c\x4f\xcd\xb2" + "\xa5\x3d\x7b\x49\x1e\xab\xfd\x0f", + .klen = 32, + .iv = "\xdf\x63\xd4\xab\xd2\x49\xf3\xd8" + "\x33\x81\x37\x60\x7d\xfa\x73\x08" + "\xd8\x49\x6d\x80\xe8\x2f\x62\x54" + "\xeb\x0e\xa9\x39\x5b\x45\x7f\x8a", + .result = "\x67\xc9\xf2\x30\x84\x41\x8e\x43" + "\xfb\xf3\xb3\x3e\x79\x36\x7f\xe8", + .input = "\x6d\x32\x86\x18\x67\x86\x0f\x3f" + "\x96\x7c\x9d\x28\x0d\x53\xec\x9f", + .ilen = 16, + .rlen = 16, + .also_non_np = 1, + .np = 2, + .tap = { 14, 2 }, + }, { + .key = "\x36\x2b\x57\x97\xf8\x5d\xcd\x99" + "\x5f\x1a\x5a\x44\x1d\x92\x0f\x27" + "\xcc\x16\xd7\x2b\x85\x63\x99\xd3" + "\xba\x96\xa1\xdb\xd2\x60\x68\xda", + .klen = 32, + .iv = "\xef\x58\x69\xb1\x2c\x5e\x9a\x47" + "\x24\xc1\xb1\x69\xe1\x12\x93\x8f" + "\x43\x3d\x6d\x00\xdb\x5e\xd8\xd9" + "\x12\x9a\xfe\xd9\xff\x2d\xaa\xc4", + .result = "\x5e\xa8\x68\x19\x85\x98\x12\x23" + "\x26\x0a\xcc\xdb\x0a\x04\xb9\xdf" + "\x4d\xb3\x48\x7b\xb0\xe3\xc8\x19" + "\x43\x5a\x46\x06\x94\x2d\xf2", + .input = "\xc7\xc6\xf1\x73\x8f\xc4\xff\x4a" + "\x39\xbe\x78\xbe\x8d\x28\xc8\x89" + "\x46\x63\xe7\x0c\x7d\x87\xe8\x4e" + "\xc9\x18\x7b\xbe\x18\x60\x50", + .ilen = 31, + .rlen = 31, + }, { + .key = "\xa5\x28\x24\x34\x1a\x3c\xd8\xf7" + "\x05\x91\x8f\xee\x85\x1f\x35\x7f" + "\x80\x3d\xfc\x9b\x94\xf6\xfc\x9e" + "\x19\x09\x00\xa9\x04\x31\x4f\x11", + .klen = 32, + .iv = "\xa1\xba\x49\x95\xff\x34\x6d\xb8" + "\xcd\x87\x5d\x5e\xfd\xea\x85\xdb" + "\x8a\x7b\x5e\xb2\x5d\x57\xdd\x62" + "\xac\xa9\x8c\x41\x42\x94\x75\xb7", + .result = "\x69\xb4\xe8\x8c\x37\xe8\x67\x82" + "\xf1\xec\x5d\x04\xe5\x14\x91\x13" + "\xdf\xf2\x87\x1b\x69\x81\x1d\x71" + "\x70\x9e\x9c\x3b\xde\x49\x70\x11" + "\xa0\xa3\xdb\x0d\x54\x4f\x66\x69" + "\xd7\xdb\x80\xa7\x70\x92\x68\xce" + "\x81\x04\x2c\xc6\xab\xae\xe5\x60" + "\x15\xe9\x6f\xef\xaa\x8f\xa7\xa7" + "\x63\x8f\xf2\xf0\x77\xf1\xa8\xea" + "\xe1\xb7\x1f\x9e\xab\x9e\x4b\x3f" + "\x07\x87\x5b\x6f\xcd\xa8\xaf\xb9" + "\xfa\x70\x0b\x52\xb8\xa8\xa7\x9e" + "\x07\x5f\xa6\x0e\xb3\x9b\x79\x13" + "\x79\xc3\x3e\x8d\x1c\x2c\x68\xc8" + "\x51\x1d\x3c\x7b\x7d\x79\x77\x2a" + "\x56\x65\xc5\x54\x23\x28\xb0\x03", + .input = "\x9e\x16\xab\xed\x4b\xa7\x42\x5a" + "\xc6\xfb\x4e\x76\xff\xbe\x03\xa0" + "\x0f\xe3\xad\xba\xe4\x98\x2b\x0e" + "\x21\x48\xa0\xb8\x65\x48\x27\x48" + "\x84\x54\x54\xb2\x9a\x94\x7b\xe6" + "\x4b\x29\xe9\xcf\x05\x91\x80\x1a" + "\x3a\xf3\x41\x96\x85\x1d\x9f\x74" + "\x51\x56\x63\xfa\x7c\x28\x85\x49" + "\xf7\x2f\xf9\xf2\x18\x46\xf5\x33" + "\x80\xa3\x3c\xce\xb2\x57\x93\xf5" + "\xae\xbd\xa9\xf5\x7b\x30\xc4\x93" + "\x66\xe0\x30\x77\x16\xe4\xa0\x31" + "\xba\x70\xbc\x68\x13\xf5\xb0\x9a" + "\xc1\xfc\x7e\xfe\x55\x80\x5c\x48" + "\x74\xa6\xaa\xa3\xac\xdc\xc2\xf5" + "\x8d\xde\x34\x86\x78\x60\x75\x8d", + .ilen = 128, + .rlen = 128, + .also_non_np = 1, + .np = 4, + .tap = { 104, 16, 4, 4 }, + }, { + .key = "\xd3\x81\x72\x18\x23\xff\x6f\x4a" + "\x25\x74\x29\x0d\x51\x8a\x0e\x13" + "\xc1\x53\x5d\x30\x8d\xee\x75\x0d" + "\x14\xd6\x69\xc9\x15\xa9\x0c\x60", + .klen = 32, + .iv = "\x65\x9b\xd4\xa8\x7d\x29\x1d\xf4" + "\xc4\xd6\x9b\x6a\x28\xab\x64\xe2" + "\x62\x81\x97\xc5\x81\xaa\xf9\x44" + "\xc1\x72\x59\x82\xaf\x16\xc8\x2c", + .result = "\xc7\x6b\x52\x6a\x10\xf0\xcc\x09" + "\xc1\x12\x1d\x6d\x21\xa6\x78\xf5" + "\x05\xa3\x69\x60\x91\x36\x98\x57" + "\xba\x0c\x14\xcc\xf3\x2d\x73\x03" + "\xc6\xb2\x5f\xc8\x16\x27\x37\x5d" + "\xd0\x0b\x87\xb2\x50\x94\x7b\x58" + "\x04\xf4\xe0\x7f\x6e\x57\x8e\xc9" + "\x41\x84\xc1\xb1\x7e\x4b\x91\x12" + "\x3a\x8b\x5d\x50\x82\x7b\xcb\xd9" + "\x9a\xd9\x4e\x18\x06\x23\x9e\xd4" + "\xa5\x20\x98\xef\xb5\xda\xe5\xc0" + "\x8a\x6a\x83\x77\x15\x84\x1e\xae" + "\x78\x94\x9d\xdf\xb7\xd1\xea\x67" + "\xaa\xb0\x14\x15\xfa\x67\x21\x84" + "\xd3\x41\x2a\xce\xba\x4b\x4a\xe8" + "\x95\x62\xa9\x55\xf0\x80\xad\xbd" + "\xab\xaf\xdd\x4f\xa5\x7c\x13\x36" + "\xed\x5e\x4f\x72\xad\x4b\xf1\xd0" + "\x88\x4e\xec\x2c\x88\x10\x5e\xea" + "\x12\xc0\x16\x01\x29\xa3\xa0\x55" + "\xaa\x68\xf3\xe9\x9d\x3b\x0d\x3b" + "\x6d\xec\xf8\xa0\x2d\xf0\x90\x8d" + "\x1c\xe2\x88\xd4\x24\x71\xf9\xb3" + "\xc1\x9f\xc5\xd6\x76\x70\xc5\x2e" + "\x9c\xac\xdb\x90\xbd\x83\x72\xba" + "\x6e\xb5\xa5\x53\x83\xa9\xa5\xbf" + "\x7d\x06\x0e\x3c\x2a\xd2\x04\xb5" + "\x1e\x19\x38\x09\x16\xd2\x82\x1f" + "\x75\x18\x56\xb8\x96\x0b\xa6\xf9" + "\xcf\x62\xd9\x32\x5d\xa9\xd7\x1d" + "\xec\xe4\xdf\x1b\xbe\xf1\x36\xee" + "\xe3\x7b\xb5\x2f\xee\xf8\x53\x3d" + "\x6a\xb7\x70\xa9\xfc\x9c\x57\x25" + "\xf2\x89\x10\xd3\xb8\xa8\x8c\x30" + "\xae\x23\x4f\x0e\x13\x66\x4f\xe1" + "\xb6\xc0\xe4\xf8\xef\x93\xbd\x6e" + "\x15\x85\x6b\xe3\x60\x81\x1d\x68" + "\xd7\x31\x87\x89\x09\xab\xd5\x96" + "\x1d\xf3\x6d\x67\x80\xca\x07\x31" + "\x5d\xa7\xe4\xfb\x3e\xf2\x9b\x33" + "\x52\x18\xc8\x30\xfe\x2d\xca\x1e" + "\x79\x92\x7a\x60\x5c\xb6\x58\x87" + "\xa4\x36\xa2\x67\x92\x8b\xa4\xb7" + "\xf1\x86\xdf\xdc\xc0\x7e\x8f\x63" + "\xd2\xa2\xdc\x78\xeb\x4f\xd8\x96" + "\x47\xca\xb8\x91\xf9\xf7\x94\x21" + "\x5f\x9a\x9f\x5b\xb8\x40\x41\x4b" + "\x66\x69\x6a\x72\xd0\xcb\x70\xb7" + "\x93\xb5\x37\x96\x05\x37\x4f\xe5" + "\x8c\xa7\x5a\x4e\x8b\xb7\x84\xea" + "\xc7\xfc\x19\x6e\x1f\x5a\xa1\xac" + "\x18\x7d\x52\x3b\xb3\x34\x62\x99" + "\xe4\x9e\x31\x04\x3f\xc0\x8d\x84" + "\x17\x7c\x25\x48\x52\x67\x11\x27" + "\x67\xbb\x5a\x85\xca\x56\xb2\x5c" + "\xe6\xec\xd5\x96\x3d\x15\xfc\xfb" + "\x22\x25\xf4\x13\xe5\x93\x4b\x9a" + "\x77\xf1\x52\x18\xfa\x16\x5e\x49" + "\x03\x45\xa8\x08\xfa\xb3\x41\x92" + "\x79\x50\x33\xca\xd0\xd7\x42\x55" + "\xc3\x9a\x0c\x4e\xd9\xa4\x3c\x86" + "\x80\x9f\x53\xd1\xa4\x2e\xd1\xbc" + "\xf1\x54\x6e\x93\xa4\x65\x99\x8e" + "\xdf\x29\xc0\x64\x63\x07\xbb\xea", + .input = "\x15\x97\xd0\x86\x18\x03\x9c\x51" + "\xc5\x11\x36\x62\x13\x92\xe6\x73" + "\x29\x79\xde\xa1\x00\x3e\x08\x64" + "\x17\x1a\xbc\xd5\xfe\x33\x0e\x0c" + "\x7c\x94\xa7\xc6\x3c\xbe\xac\xa2" + "\x89\xe6\xbc\xdf\x0c\x33\x27\x42" + "\x46\x73\x2f\xba\x4e\xa6\x46\x8f" + "\xe4\xee\x39\x63\x42\x65\xa3\x88" + "\x7a\xad\x33\x23\xa9\xa7\x20\x7f" + "\x0b\xe6\x6a\xc3\x60\xda\x9e\xb4" + "\xd6\x07\x8a\x77\x26\xd1\xab\x44" + "\x99\x55\x03\x5e\xed\x8d\x7b\xbd" + "\xc8\x21\xb7\x21\x30\x3f\xc0\xb5" + "\xc8\xec\x6c\x23\xa6\xa3\x6d\xf1" + "\x30\x0a\xd0\xa6\xa9\x28\x69\xae" + "\x2a\xe6\x54\xac\x82\x9d\x6a\x95" + "\x6f\x06\x44\xc5\x5a\x77\x6e\xec" + "\xf8\xf8\x63\xb2\xe6\xaa\xbd\x8e" + "\x0e\x8a\x62\x00\x03\xc8\x84\xdd" + "\x47\x4a\xc3\x55\xba\xb7\xe7\xdf" + "\x08\xbf\x62\xf5\xe8\xbc\xb6\x11" + "\xe4\xcb\xd0\x66\x74\x32\xcf\xd4" + "\xf8\x51\x80\x39\x14\x05\x12\xdb" + "\x87\x93\xe2\x26\x30\x9c\x3a\x21" + "\xe5\xd0\x38\x57\x80\x15\xe4\x08" + "\x58\x05\x49\x7d\xe6\x92\x77\x70" + "\xfb\x1e\x2d\x6a\x84\x00\xc8\x68" + "\xf7\x1a\xdd\xf0\x7b\x38\x1e\xd8" + "\x2c\x78\x78\x61\xcf\xe3\xde\x69" + "\x1f\xd5\x03\xd5\x1a\xb4\xcf\x03" + "\xc8\x7a\x70\x68\x35\xb4\xf6\xbe" + "\x90\x62\xb2\x28\x99\x86\xf5\x44" + "\x99\xeb\x31\xcf\xca\xdf\xd0\x21" + "\xd6\x60\xf7\x0f\x40\xb4\x80\xb7" + "\xab\xe1\x9b\x45\xba\x66\xda\xee" + "\xdd\x04\x12\x40\x98\xe1\x69\xe5" + "\x2b\x9c\x59\x80\xe7\x7b\xcc\x63" + "\xa6\xc0\x3a\xa9\xfe\x8a\xf9\x62" + "\x11\x34\x61\x94\x35\xfe\xf2\x99" + "\xfd\xee\x19\xea\x95\xb6\x12\xbf" + "\x1b\xdf\x02\x1a\xcc\x3e\x7e\x65" + "\x78\x74\x10\x50\x29\x63\x28\xea" + "\x6b\xab\xd4\x06\x4d\x15\x24\x31" + "\xc7\x0a\xc9\x16\xb6\x48\xf0\xbf" + "\x49\xdb\x68\x71\x31\x8f\x87\xe2" + "\x13\x05\x64\xd6\x22\x0c\xf8\x36" + "\x84\x24\x3e\x69\x5e\xb8\x9e\x16" + "\x73\x6c\x83\x1e\xe0\x9f\x9e\xba" + "\xe5\x59\x21\x33\x1b\xa9\x26\xc2" + "\xc7\xd9\x30\x73\xb6\xa6\x73\x82" + "\x19\xfa\x44\x4d\x40\x8b\x69\x04" + "\x94\x74\xea\x6e\xb3\x09\x47\x01" + "\x2a\xb9\x78\x34\x43\x11\xed\xd6" + "\x8c\x95\x65\x1b\x85\x67\xa5\x40" + "\xac\x9c\x05\x4b\x57\x4a\xa9\x96" + "\x0f\xdd\x4f\xa1\xe0\xcf\x6e\xc7" + "\x1b\xed\xa2\xb4\x56\x8c\x09\x6e" + "\xa6\x65\xd7\x55\x81\xb7\xed\x11" + "\x9b\x40\x75\xa8\x6b\x56\xaf\x16" + "\x8b\x3d\xf4\xcb\xfe\xd5\x1d\x3d" + "\x85\xc2\xc0\xde\x43\x39\x4a\x96" + "\xba\x88\x97\xc0\xd6\x00\x0e\x27" + "\x21\xb0\x21\x52\xba\xa7\x37\xaa" + "\xcc\xbf\x95\xa8\xf4\xd0\x91\xf6", + .ilen = 512, + .rlen = 512, + .also_non_np = 1, + .np = 2, + .tap = { 144, 368 }, + } +}; + +/* Adiantum with XChaCha20 instead of XChaCha12 */ +/* Test vectors from https://github.com/google/adiantum */ +static const struct cipher_testvec adiantum_xchacha20_aes_enc_tv_template[] = { + { + .key = "\x9e\xeb\xb2\x49\x3c\x1c\xf5\xf4" + "\x6a\x99\xc2\xc4\xdf\xb1\xf4\xdd" + "\x75\x20\x57\xea\x2c\x4f\xcd\xb2" + "\xa5\x3d\x7b\x49\x1e\xab\xfd\x0f", + .klen = 32, + .iv = "\xdf\x63\xd4\xab\xd2\x49\xf3\xd8" + "\x33\x81\x37\x60\x7d\xfa\x73\x08" + "\xd8\x49\x6d\x80\xe8\x2f\x62\x54" + "\xeb\x0e\xa9\x39\x5b\x45\x7f\x8a", + .input = "\x67\xc9\xf2\x30\x84\x41\x8e\x43" + "\xfb\xf3\xb3\x3e\x79\x36\x7f\xe8", + .result = "\xf6\x78\x97\xd6\xaa\x94\x01\x27" + "\x2e\x4d\x83\xe0\x6e\x64\x9a\xdf", + .ilen = 16, + .rlen = 16, + .also_non_np = 1, + .np = 3, + .tap = { 5, 2, 9 }, + }, { + .key = "\x36\x2b\x57\x97\xf8\x5d\xcd\x99" + "\x5f\x1a\x5a\x44\x1d\x92\x0f\x27" + "\xcc\x16\xd7\x2b\x85\x63\x99\xd3" + "\xba\x96\xa1\xdb\xd2\x60\x68\xda", + .klen = 32, + .iv = "\xef\x58\x69\xb1\x2c\x5e\x9a\x47" + "\x24\xc1\xb1\x69\xe1\x12\x93\x8f" + "\x43\x3d\x6d\x00\xdb\x5e\xd8\xd9" + "\x12\x9a\xfe\xd9\xff\x2d\xaa\xc4", + .input = "\x5e\xa8\x68\x19\x85\x98\x12\x23" + "\x26\x0a\xcc\xdb\x0a\x04\xb9\xdf" + "\x4d\xb3\x48\x7b\xb0\xe3\xc8\x19" + "\x43\x5a\x46\x06\x94\x2d\xf2", + .result = "\x4b\xb8\x90\x10\xdf\x7f\x64\x08" + "\x0e\x14\x42\x5f\x00\x74\x09\x36" + "\x57\x72\xb5\xfd\xb5\x5d\xb8\x28" + "\x0c\x04\x91\x14\x91\xe9\x37", + .ilen = 31, + .rlen = 31, + .also_non_np = 1, + .np = 2, + .tap = { 16, 15 }, + }, { + .key = "\xa5\x28\x24\x34\x1a\x3c\xd8\xf7" + "\x05\x91\x8f\xee\x85\x1f\x35\x7f" + "\x80\x3d\xfc\x9b\x94\xf6\xfc\x9e" + "\x19\x09\x00\xa9\x04\x31\x4f\x11", + .klen = 32, + .iv = "\xa1\xba\x49\x95\xff\x34\x6d\xb8" + "\xcd\x87\x5d\x5e\xfd\xea\x85\xdb" + "\x8a\x7b\x5e\xb2\x5d\x57\xdd\x62" + "\xac\xa9\x8c\x41\x42\x94\x75\xb7", + .input = "\x69\xb4\xe8\x8c\x37\xe8\x67\x82" + "\xf1\xec\x5d\x04\xe5\x14\x91\x13" + "\xdf\xf2\x87\x1b\x69\x81\x1d\x71" + "\x70\x9e\x9c\x3b\xde\x49\x70\x11" + "\xa0\xa3\xdb\x0d\x54\x4f\x66\x69" + "\xd7\xdb\x80\xa7\x70\x92\x68\xce" + "\x81\x04\x2c\xc6\xab\xae\xe5\x60" + "\x15\xe9\x6f\xef\xaa\x8f\xa7\xa7" + "\x63\x8f\xf2\xf0\x77\xf1\xa8\xea" + "\xe1\xb7\x1f\x9e\xab\x9e\x4b\x3f" + "\x07\x87\x5b\x6f\xcd\xa8\xaf\xb9" + "\xfa\x70\x0b\x52\xb8\xa8\xa7\x9e" + "\x07\x5f\xa6\x0e\xb3\x9b\x79\x13" + "\x79\xc3\x3e\x8d\x1c\x2c\x68\xc8" + "\x51\x1d\x3c\x7b\x7d\x79\x77\x2a" + "\x56\x65\xc5\x54\x23\x28\xb0\x03", + .result = "\xb1\x8b\xa0\x05\x77\xa8\x4d\x59" + "\x1b\x8e\x21\xfc\x3a\x49\xfa\xd4" + "\xeb\x36\xf3\xc4\xdf\xdc\xae\x67" + "\x07\x3f\x70\x0e\xe9\x66\xf5\x0c" + "\x30\x4d\x66\xc9\xa4\x2f\x73\x9c" + "\x13\xc8\x49\x44\xcc\x0a\x90\x9d" + "\x7c\xdd\x19\x3f\xea\x72\x8d\x58" + "\xab\xe7\x09\x2c\xec\xb5\x44\xd2" + "\xca\xa6\x2d\x7a\x5c\x9c\x2b\x15" + "\xec\x2a\xa6\x69\x91\xf9\xf3\x13" + "\xf7\x72\xc1\xc1\x40\xd5\xe1\x94" + "\xf4\x29\xa1\x3e\x25\x02\xa8\x3e" + "\x94\xc1\x91\x14\xa1\x14\xcb\xbe" + "\x67\x4c\xb9\x38\xfe\xa7\xaa\x32" + "\x29\x62\x0d\xb2\xf6\x3c\x58\x57" + "\xc1\xd5\x5a\xbb\xd6\xa6\x2a\xe5", + .ilen = 128, + .rlen = 128, + .also_non_np = 1, + .np = 4, + .tap = { 112, 7, 8, 1 }, + }, { + .key = "\xd3\x81\x72\x18\x23\xff\x6f\x4a" + "\x25\x74\x29\x0d\x51\x8a\x0e\x13" + "\xc1\x53\x5d\x30\x8d\xee\x75\x0d" + "\x14\xd6\x69\xc9\x15\xa9\x0c\x60", + .klen = 32, + .iv = "\x65\x9b\xd4\xa8\x7d\x29\x1d\xf4" + "\xc4\xd6\x9b\x6a\x28\xab\x64\xe2" + "\x62\x81\x97\xc5\x81\xaa\xf9\x44" + "\xc1\x72\x59\x82\xaf\x16\xc8\x2c", + .input = "\xc7\x6b\x52\x6a\x10\xf0\xcc\x09" + "\xc1\x12\x1d\x6d\x21\xa6\x78\xf5" + "\x05\xa3\x69\x60\x91\x36\x98\x57" + "\xba\x0c\x14\xcc\xf3\x2d\x73\x03" + "\xc6\xb2\x5f\xc8\x16\x27\x37\x5d" + "\xd0\x0b\x87\xb2\x50\x94\x7b\x58" + "\x04\xf4\xe0\x7f\x6e\x57\x8e\xc9" + "\x41\x84\xc1\xb1\x7e\x4b\x91\x12" + "\x3a\x8b\x5d\x50\x82\x7b\xcb\xd9" + "\x9a\xd9\x4e\x18\x06\x23\x9e\xd4" + "\xa5\x20\x98\xef\xb5\xda\xe5\xc0" + "\x8a\x6a\x83\x77\x15\x84\x1e\xae" + "\x78\x94\x9d\xdf\xb7\xd1\xea\x67" + "\xaa\xb0\x14\x15\xfa\x67\x21\x84" + "\xd3\x41\x2a\xce\xba\x4b\x4a\xe8" + "\x95\x62\xa9\x55\xf0\x80\xad\xbd" + "\xab\xaf\xdd\x4f\xa5\x7c\x13\x36" + "\xed\x5e\x4f\x72\xad\x4b\xf1\xd0" + "\x88\x4e\xec\x2c\x88\x10\x5e\xea" + "\x12\xc0\x16\x01\x29\xa3\xa0\x55" + "\xaa\x68\xf3\xe9\x9d\x3b\x0d\x3b" + "\x6d\xec\xf8\xa0\x2d\xf0\x90\x8d" + "\x1c\xe2\x88\xd4\x24\x71\xf9\xb3" + "\xc1\x9f\xc5\xd6\x76\x70\xc5\x2e" + "\x9c\xac\xdb\x90\xbd\x83\x72\xba" + "\x6e\xb5\xa5\x53\x83\xa9\xa5\xbf" + "\x7d\x06\x0e\x3c\x2a\xd2\x04\xb5" + "\x1e\x19\x38\x09\x16\xd2\x82\x1f" + "\x75\x18\x56\xb8\x96\x0b\xa6\xf9" + "\xcf\x62\xd9\x32\x5d\xa9\xd7\x1d" + "\xec\xe4\xdf\x1b\xbe\xf1\x36\xee" + "\xe3\x7b\xb5\x2f\xee\xf8\x53\x3d" + "\x6a\xb7\x70\xa9\xfc\x9c\x57\x25" + "\xf2\x89\x10\xd3\xb8\xa8\x8c\x30" + "\xae\x23\x4f\x0e\x13\x66\x4f\xe1" + "\xb6\xc0\xe4\xf8\xef\x93\xbd\x6e" + "\x15\x85\x6b\xe3\x60\x81\x1d\x68" + "\xd7\x31\x87\x89\x09\xab\xd5\x96" + "\x1d\xf3\x6d\x67\x80\xca\x07\x31" + "\x5d\xa7\xe4\xfb\x3e\xf2\x9b\x33" + "\x52\x18\xc8\x30\xfe\x2d\xca\x1e" + "\x79\x92\x7a\x60\x5c\xb6\x58\x87" + "\xa4\x36\xa2\x67\x92\x8b\xa4\xb7" + "\xf1\x86\xdf\xdc\xc0\x7e\x8f\x63" + "\xd2\xa2\xdc\x78\xeb\x4f\xd8\x96" + "\x47\xca\xb8\x91\xf9\xf7\x94\x21" + "\x5f\x9a\x9f\x5b\xb8\x40\x41\x4b" + "\x66\x69\x6a\x72\xd0\xcb\x70\xb7" + "\x93\xb5\x37\x96\x05\x37\x4f\xe5" + "\x8c\xa7\x5a\x4e\x8b\xb7\x84\xea" + "\xc7\xfc\x19\x6e\x1f\x5a\xa1\xac" + "\x18\x7d\x52\x3b\xb3\x34\x62\x99" + "\xe4\x9e\x31\x04\x3f\xc0\x8d\x84" + "\x17\x7c\x25\x48\x52\x67\x11\x27" + "\x67\xbb\x5a\x85\xca\x56\xb2\x5c" + "\xe6\xec\xd5\x96\x3d\x15\xfc\xfb" + "\x22\x25\xf4\x13\xe5\x93\x4b\x9a" + "\x77\xf1\x52\x18\xfa\x16\x5e\x49" + "\x03\x45\xa8\x08\xfa\xb3\x41\x92" + "\x79\x50\x33\xca\xd0\xd7\x42\x55" + "\xc3\x9a\x0c\x4e\xd9\xa4\x3c\x86" + "\x80\x9f\x53\xd1\xa4\x2e\xd1\xbc" + "\xf1\x54\x6e\x93\xa4\x65\x99\x8e" + "\xdf\x29\xc0\x64\x63\x07\xbb\xea", + .result = "\xe0\x33\xf6\xe0\xb4\xa5\xdd\x2b" + "\xdd\xce\xfc\x12\x1e\xfc\x2d\xf2" + "\x8b\xc7\xeb\xc1\xc4\x2a\xe8\x44" + "\x0f\x3d\x97\x19\x2e\x6d\xa2\x38" + "\x9d\xa6\xaa\xe1\x96\xb9\x08\xe8" + "\x0b\x70\x48\x5c\xed\xb5\x9b\xcb" + "\x8b\x40\x88\x7e\x69\x73\xf7\x16" + "\x71\xbb\x5b\xfc\xa3\x47\x5d\xa6" + "\xae\x3a\x64\xc4\xe7\xb8\xa8\xe7" + "\xb1\x32\x19\xdb\xe3\x01\xb8\xf0" + "\xa4\x86\xb4\x4c\xc2\xde\x5c\xd2" + "\x6c\x77\xd2\xe8\x18\xb7\x0a\xc9" + "\x3d\x53\xb5\xc4\x5c\xf0\x8c\x06" + "\xdc\x90\xe0\x74\x47\x1b\x0b\xf6" + "\xd2\x71\x6b\xc4\xf1\x97\x00\x2d" + "\x63\x57\x44\x1f\x8c\xf4\xe6\x9b" + "\xe0\x7a\xdd\xec\x32\x73\x42\x32" + "\x7f\x35\x67\x60\x0d\xcf\x10\x52" + "\x61\x22\x53\x8d\x8e\xbb\x33\x76" + "\x59\xd9\x10\xce\xdf\xef\xc0\x41" + "\xd5\x33\x29\x6a\xda\x46\xa4\x51" + "\xf0\x99\x3d\x96\x31\xdd\xb5\xcb" + "\x3e\x2a\x1f\xc7\x5c\x79\xd3\xc5" + "\x20\xa1\xb1\x39\x1b\xc6\x0a\x70" + "\x26\x39\x95\x07\xad\x7a\xc9\x69" + "\xfe\x81\xc7\x88\x08\x38\xaf\xad" + "\x9e\x8d\xfb\xe8\x24\x0d\x22\xb8" + "\x0e\xed\xbe\x37\x53\x7c\xa6\xc6" + "\x78\x62\xec\xa3\x59\xd9\xc6\x9d" + "\xb8\x0e\x69\x77\x84\x2d\x6a\x4c" + "\xc5\xd9\xb2\xa0\x2b\xa8\x80\xcc" + "\xe9\x1e\x9c\x5a\xc4\xa1\xb2\x37" + "\x06\x9b\x30\x32\x67\xf7\xe7\xd2" + "\x42\xc7\xdf\x4e\xd4\xcb\xa0\x12" + "\x94\xa1\x34\x85\x93\x50\x4b\x0a" + "\x3c\x7d\x49\x25\x01\x41\x6b\x96" + "\xa9\x12\xbb\x0b\xc0\xd7\xd0\x93" + "\x1f\x70\x38\xb8\x21\xee\xf6\xa7" + "\xee\xeb\xe7\x81\xa4\x13\xb4\x87" + "\xfa\xc1\xb0\xb5\x37\x8b\x74\xa2" + "\x4e\xc7\xc2\xad\x3d\x62\x3f\xf8" + "\x34\x42\xe5\xae\x45\x13\x63\xfe" + "\xfc\x2a\x17\x46\x61\xa9\xd3\x1c" + "\x4c\xaf\xf0\x09\x62\x26\x66\x1e" + "\x74\xcf\xd6\x68\x3d\x7d\xd8\xb7" + "\xe7\xe6\xf8\xf0\x08\x20\xf7\x47" + "\x1c\x52\xaa\x0f\x3e\x21\xa3\xf2" + "\xbf\x2f\x95\x16\xa8\xc8\xc8\x8c" + "\x99\x0f\x5d\xfb\xfa\x2b\x58\x8a" + "\x7e\xd6\x74\x02\x60\xf0\xd0\x5b" + "\x65\xa8\xac\xea\x8d\x68\x46\x34" + "\x26\x9d\x4f\xb1\x9a\x8e\xc0\x1a" + "\xf1\xed\xc6\x7a\x83\xfd\x8a\x57" + "\xf2\xe6\xe4\xba\xfc\xc6\x3c\xad" + "\x5b\x19\x50\x2f\x3a\xcc\x06\x46" + "\x04\x51\x3f\x91\x97\xf0\xd2\x07" + "\xe7\x93\x89\x7e\xb5\x32\x0f\x03" + "\xe5\x58\x9e\x74\x72\xeb\xc2\x38" + "\x00\x0c\x91\x72\x69\xed\x7d\x6d" + "\xc8\x71\xf0\xec\xff\x80\xd9\x1c" + "\x9e\xd2\xfa\x15\xfc\x6c\x4e\xbc" + "\xb1\xa6\xbd\xbd\x70\x40\xca\x20" + "\xb8\x78\xd2\xa3\xc6\xf3\x79\x9c" + "\xc7\x27\xe1\x6a\x29\xad\xa4\x03", + .ilen = 512, + .rlen = 512, + } +}; + +static const struct cipher_testvec adiantum_xchacha20_aes_dec_tv_template[] = { + { + .key = "\x9e\xeb\xb2\x49\x3c\x1c\xf5\xf4" + "\x6a\x99\xc2\xc4\xdf\xb1\xf4\xdd" + "\x75\x20\x57\xea\x2c\x4f\xcd\xb2" + "\xa5\x3d\x7b\x49\x1e\xab\xfd\x0f", + .klen = 32, + .iv = "\xdf\x63\xd4\xab\xd2\x49\xf3\xd8" + "\x33\x81\x37\x60\x7d\xfa\x73\x08" + "\xd8\x49\x6d\x80\xe8\x2f\x62\x54" + "\xeb\x0e\xa9\x39\x5b\x45\x7f\x8a", + .result = "\x67\xc9\xf2\x30\x84\x41\x8e\x43" + "\xfb\xf3\xb3\x3e\x79\x36\x7f\xe8", + .input = "\xf6\x78\x97\xd6\xaa\x94\x01\x27" + "\x2e\x4d\x83\xe0\x6e\x64\x9a\xdf", + .ilen = 16, + .rlen = 16, + .also_non_np = 1, + .np = 3, + .tap = { 5, 2, 9 }, + }, { + .key = "\x36\x2b\x57\x97\xf8\x5d\xcd\x99" + "\x5f\x1a\x5a\x44\x1d\x92\x0f\x27" + "\xcc\x16\xd7\x2b\x85\x63\x99\xd3" + "\xba\x96\xa1\xdb\xd2\x60\x68\xda", + .klen = 32, + .iv = "\xef\x58\x69\xb1\x2c\x5e\x9a\x47" + "\x24\xc1\xb1\x69\xe1\x12\x93\x8f" + "\x43\x3d\x6d\x00\xdb\x5e\xd8\xd9" + "\x12\x9a\xfe\xd9\xff\x2d\xaa\xc4", + .result = "\x5e\xa8\x68\x19\x85\x98\x12\x23" + "\x26\x0a\xcc\xdb\x0a\x04\xb9\xdf" + "\x4d\xb3\x48\x7b\xb0\xe3\xc8\x19" + "\x43\x5a\x46\x06\x94\x2d\xf2", + .input = "\x4b\xb8\x90\x10\xdf\x7f\x64\x08" + "\x0e\x14\x42\x5f\x00\x74\x09\x36" + "\x57\x72\xb5\xfd\xb5\x5d\xb8\x28" + "\x0c\x04\x91\x14\x91\xe9\x37", + .ilen = 31, + .rlen = 31, + .also_non_np = 1, + .np = 2, + .tap = { 16, 15 }, + }, { + .key = "\xa5\x28\x24\x34\x1a\x3c\xd8\xf7" + "\x05\x91\x8f\xee\x85\x1f\x35\x7f" + "\x80\x3d\xfc\x9b\x94\xf6\xfc\x9e" + "\x19\x09\x00\xa9\x04\x31\x4f\x11", + .klen = 32, + .iv = "\xa1\xba\x49\x95\xff\x34\x6d\xb8" + "\xcd\x87\x5d\x5e\xfd\xea\x85\xdb" + "\x8a\x7b\x5e\xb2\x5d\x57\xdd\x62" + "\xac\xa9\x8c\x41\x42\x94\x75\xb7", + .result = "\x69\xb4\xe8\x8c\x37\xe8\x67\x82" + "\xf1\xec\x5d\x04\xe5\x14\x91\x13" + "\xdf\xf2\x87\x1b\x69\x81\x1d\x71" + "\x70\x9e\x9c\x3b\xde\x49\x70\x11" + "\xa0\xa3\xdb\x0d\x54\x4f\x66\x69" + "\xd7\xdb\x80\xa7\x70\x92\x68\xce" + "\x81\x04\x2c\xc6\xab\xae\xe5\x60" + "\x15\xe9\x6f\xef\xaa\x8f\xa7\xa7" + "\x63\x8f\xf2\xf0\x77\xf1\xa8\xea" + "\xe1\xb7\x1f\x9e\xab\x9e\x4b\x3f" + "\x07\x87\x5b\x6f\xcd\xa8\xaf\xb9" + "\xfa\x70\x0b\x52\xb8\xa8\xa7\x9e" + "\x07\x5f\xa6\x0e\xb3\x9b\x79\x13" + "\x79\xc3\x3e\x8d\x1c\x2c\x68\xc8" + "\x51\x1d\x3c\x7b\x7d\x79\x77\x2a" + "\x56\x65\xc5\x54\x23\x28\xb0\x03", + .input = "\xb1\x8b\xa0\x05\x77\xa8\x4d\x59" + "\x1b\x8e\x21\xfc\x3a\x49\xfa\xd4" + "\xeb\x36\xf3\xc4\xdf\xdc\xae\x67" + "\x07\x3f\x70\x0e\xe9\x66\xf5\x0c" + "\x30\x4d\x66\xc9\xa4\x2f\x73\x9c" + "\x13\xc8\x49\x44\xcc\x0a\x90\x9d" + "\x7c\xdd\x19\x3f\xea\x72\x8d\x58" + "\xab\xe7\x09\x2c\xec\xb5\x44\xd2" + "\xca\xa6\x2d\x7a\x5c\x9c\x2b\x15" + "\xec\x2a\xa6\x69\x91\xf9\xf3\x13" + "\xf7\x72\xc1\xc1\x40\xd5\xe1\x94" + "\xf4\x29\xa1\x3e\x25\x02\xa8\x3e" + "\x94\xc1\x91\x14\xa1\x14\xcb\xbe" + "\x67\x4c\xb9\x38\xfe\xa7\xaa\x32" + "\x29\x62\x0d\xb2\xf6\x3c\x58\x57" + "\xc1\xd5\x5a\xbb\xd6\xa6\x2a\xe5", + .ilen = 128, + .rlen = 128, + .also_non_np = 1, + .np = 4, + .tap = { 112, 7, 8, 1 }, + }, { + .key = "\xd3\x81\x72\x18\x23\xff\x6f\x4a" + "\x25\x74\x29\x0d\x51\x8a\x0e\x13" + "\xc1\x53\x5d\x30\x8d\xee\x75\x0d" + "\x14\xd6\x69\xc9\x15\xa9\x0c\x60", + .klen = 32, + .iv = "\x65\x9b\xd4\xa8\x7d\x29\x1d\xf4" + "\xc4\xd6\x9b\x6a\x28\xab\x64\xe2" + "\x62\x81\x97\xc5\x81\xaa\xf9\x44" + "\xc1\x72\x59\x82\xaf\x16\xc8\x2c", + .result = "\xc7\x6b\x52\x6a\x10\xf0\xcc\x09" + "\xc1\x12\x1d\x6d\x21\xa6\x78\xf5" + "\x05\xa3\x69\x60\x91\x36\x98\x57" + "\xba\x0c\x14\xcc\xf3\x2d\x73\x03" + "\xc6\xb2\x5f\xc8\x16\x27\x37\x5d" + "\xd0\x0b\x87\xb2\x50\x94\x7b\x58" + "\x04\xf4\xe0\x7f\x6e\x57\x8e\xc9" + "\x41\x84\xc1\xb1\x7e\x4b\x91\x12" + "\x3a\x8b\x5d\x50\x82\x7b\xcb\xd9" + "\x9a\xd9\x4e\x18\x06\x23\x9e\xd4" + "\xa5\x20\x98\xef\xb5\xda\xe5\xc0" + "\x8a\x6a\x83\x77\x15\x84\x1e\xae" + "\x78\x94\x9d\xdf\xb7\xd1\xea\x67" + "\xaa\xb0\x14\x15\xfa\x67\x21\x84" + "\xd3\x41\x2a\xce\xba\x4b\x4a\xe8" + "\x95\x62\xa9\x55\xf0\x80\xad\xbd" + "\xab\xaf\xdd\x4f\xa5\x7c\x13\x36" + "\xed\x5e\x4f\x72\xad\x4b\xf1\xd0" + "\x88\x4e\xec\x2c\x88\x10\x5e\xea" + "\x12\xc0\x16\x01\x29\xa3\xa0\x55" + "\xaa\x68\xf3\xe9\x9d\x3b\x0d\x3b" + "\x6d\xec\xf8\xa0\x2d\xf0\x90\x8d" + "\x1c\xe2\x88\xd4\x24\x71\xf9\xb3" + "\xc1\x9f\xc5\xd6\x76\x70\xc5\x2e" + "\x9c\xac\xdb\x90\xbd\x83\x72\xba" + "\x6e\xb5\xa5\x53\x83\xa9\xa5\xbf" + "\x7d\x06\x0e\x3c\x2a\xd2\x04\xb5" + "\x1e\x19\x38\x09\x16\xd2\x82\x1f" + "\x75\x18\x56\xb8\x96\x0b\xa6\xf9" + "\xcf\x62\xd9\x32\x5d\xa9\xd7\x1d" + "\xec\xe4\xdf\x1b\xbe\xf1\x36\xee" + "\xe3\x7b\xb5\x2f\xee\xf8\x53\x3d" + "\x6a\xb7\x70\xa9\xfc\x9c\x57\x25" + "\xf2\x89\x10\xd3\xb8\xa8\x8c\x30" + "\xae\x23\x4f\x0e\x13\x66\x4f\xe1" + "\xb6\xc0\xe4\xf8\xef\x93\xbd\x6e" + "\x15\x85\x6b\xe3\x60\x81\x1d\x68" + "\xd7\x31\x87\x89\x09\xab\xd5\x96" + "\x1d\xf3\x6d\x67\x80\xca\x07\x31" + "\x5d\xa7\xe4\xfb\x3e\xf2\x9b\x33" + "\x52\x18\xc8\x30\xfe\x2d\xca\x1e" + "\x79\x92\x7a\x60\x5c\xb6\x58\x87" + "\xa4\x36\xa2\x67\x92\x8b\xa4\xb7" + "\xf1\x86\xdf\xdc\xc0\x7e\x8f\x63" + "\xd2\xa2\xdc\x78\xeb\x4f\xd8\x96" + "\x47\xca\xb8\x91\xf9\xf7\x94\x21" + "\x5f\x9a\x9f\x5b\xb8\x40\x41\x4b" + "\x66\x69\x6a\x72\xd0\xcb\x70\xb7" + "\x93\xb5\x37\x96\x05\x37\x4f\xe5" + "\x8c\xa7\x5a\x4e\x8b\xb7\x84\xea" + "\xc7\xfc\x19\x6e\x1f\x5a\xa1\xac" + "\x18\x7d\x52\x3b\xb3\x34\x62\x99" + "\xe4\x9e\x31\x04\x3f\xc0\x8d\x84" + "\x17\x7c\x25\x48\x52\x67\x11\x27" + "\x67\xbb\x5a\x85\xca\x56\xb2\x5c" + "\xe6\xec\xd5\x96\x3d\x15\xfc\xfb" + "\x22\x25\xf4\x13\xe5\x93\x4b\x9a" + "\x77\xf1\x52\x18\xfa\x16\x5e\x49" + "\x03\x45\xa8\x08\xfa\xb3\x41\x92" + "\x79\x50\x33\xca\xd0\xd7\x42\x55" + "\xc3\x9a\x0c\x4e\xd9\xa4\x3c\x86" + "\x80\x9f\x53\xd1\xa4\x2e\xd1\xbc" + "\xf1\x54\x6e\x93\xa4\x65\x99\x8e" + "\xdf\x29\xc0\x64\x63\x07\xbb\xea", + .input = "\xe0\x33\xf6\xe0\xb4\xa5\xdd\x2b" + "\xdd\xce\xfc\x12\x1e\xfc\x2d\xf2" + "\x8b\xc7\xeb\xc1\xc4\x2a\xe8\x44" + "\x0f\x3d\x97\x19\x2e\x6d\xa2\x38" + "\x9d\xa6\xaa\xe1\x96\xb9\x08\xe8" + "\x0b\x70\x48\x5c\xed\xb5\x9b\xcb" + "\x8b\x40\x88\x7e\x69\x73\xf7\x16" + "\x71\xbb\x5b\xfc\xa3\x47\x5d\xa6" + "\xae\x3a\x64\xc4\xe7\xb8\xa8\xe7" + "\xb1\x32\x19\xdb\xe3\x01\xb8\xf0" + "\xa4\x86\xb4\x4c\xc2\xde\x5c\xd2" + "\x6c\x77\xd2\xe8\x18\xb7\x0a\xc9" + "\x3d\x53\xb5\xc4\x5c\xf0\x8c\x06" + "\xdc\x90\xe0\x74\x47\x1b\x0b\xf6" + "\xd2\x71\x6b\xc4\xf1\x97\x00\x2d" + "\x63\x57\x44\x1f\x8c\xf4\xe6\x9b" + "\xe0\x7a\xdd\xec\x32\x73\x42\x32" + "\x7f\x35\x67\x60\x0d\xcf\x10\x52" + "\x61\x22\x53\x8d\x8e\xbb\x33\x76" + "\x59\xd9\x10\xce\xdf\xef\xc0\x41" + "\xd5\x33\x29\x6a\xda\x46\xa4\x51" + "\xf0\x99\x3d\x96\x31\xdd\xb5\xcb" + "\x3e\x2a\x1f\xc7\x5c\x79\xd3\xc5" + "\x20\xa1\xb1\x39\x1b\xc6\x0a\x70" + "\x26\x39\x95\x07\xad\x7a\xc9\x69" + "\xfe\x81\xc7\x88\x08\x38\xaf\xad" + "\x9e\x8d\xfb\xe8\x24\x0d\x22\xb8" + "\x0e\xed\xbe\x37\x53\x7c\xa6\xc6" + "\x78\x62\xec\xa3\x59\xd9\xc6\x9d" + "\xb8\x0e\x69\x77\x84\x2d\x6a\x4c" + "\xc5\xd9\xb2\xa0\x2b\xa8\x80\xcc" + "\xe9\x1e\x9c\x5a\xc4\xa1\xb2\x37" + "\x06\x9b\x30\x32\x67\xf7\xe7\xd2" + "\x42\xc7\xdf\x4e\xd4\xcb\xa0\x12" + "\x94\xa1\x34\x85\x93\x50\x4b\x0a" + "\x3c\x7d\x49\x25\x01\x41\x6b\x96" + "\xa9\x12\xbb\x0b\xc0\xd7\xd0\x93" + "\x1f\x70\x38\xb8\x21\xee\xf6\xa7" + "\xee\xeb\xe7\x81\xa4\x13\xb4\x87" + "\xfa\xc1\xb0\xb5\x37\x8b\x74\xa2" + "\x4e\xc7\xc2\xad\x3d\x62\x3f\xf8" + "\x34\x42\xe5\xae\x45\x13\x63\xfe" + "\xfc\x2a\x17\x46\x61\xa9\xd3\x1c" + "\x4c\xaf\xf0\x09\x62\x26\x66\x1e" + "\x74\xcf\xd6\x68\x3d\x7d\xd8\xb7" + "\xe7\xe6\xf8\xf0\x08\x20\xf7\x47" + "\x1c\x52\xaa\x0f\x3e\x21\xa3\xf2" + "\xbf\x2f\x95\x16\xa8\xc8\xc8\x8c" + "\x99\x0f\x5d\xfb\xfa\x2b\x58\x8a" + "\x7e\xd6\x74\x02\x60\xf0\xd0\x5b" + "\x65\xa8\xac\xea\x8d\x68\x46\x34" + "\x26\x9d\x4f\xb1\x9a\x8e\xc0\x1a" + "\xf1\xed\xc6\x7a\x83\xfd\x8a\x57" + "\xf2\xe6\xe4\xba\xfc\xc6\x3c\xad" + "\x5b\x19\x50\x2f\x3a\xcc\x06\x46" + "\x04\x51\x3f\x91\x97\xf0\xd2\x07" + "\xe7\x93\x89\x7e\xb5\x32\x0f\x03" + "\xe5\x58\x9e\x74\x72\xeb\xc2\x38" + "\x00\x0c\x91\x72\x69\xed\x7d\x6d" + "\xc8\x71\xf0\xec\xff\x80\xd9\x1c" + "\x9e\xd2\xfa\x15\xfc\x6c\x4e\xbc" + "\xb1\xa6\xbd\xbd\x70\x40\xca\x20" + "\xb8\x78\xd2\xa3\xc6\xf3\x79\x9c" + "\xc7\x27\xe1\x6a\x29\xad\xa4\x03", + .ilen = 512, + .rlen = 512, + } +}; + /* * CTS (Cipher Text Stealing) mode tests */ @@ -34680,4 +38013,75 @@ static const struct comp_testvec lz4hc_decomp_tv_template[] = { }, }; +static const struct comp_testvec zstd_comp_tv_template[] = { + { + .inlen = 68, + .outlen = 39, + .input = "The algorithm is zstd. " + "The algorithm is zstd. " + "The algorithm is zstd.", + .output = "\x28\xb5\x2f\xfd\x00\x50\xf5\x00\x00\xb8\x54\x68\x65" + "\x20\x61\x6c\x67\x6f\x72\x69\x74\x68\x6d\x20\x69\x73" + "\x20\x7a\x73\x74\x64\x2e\x20\x01\x00\x55\x73\x36\x01" + , + }, + { + .inlen = 244, + .outlen = 151, + .input = "zstd, short for Zstandard, is a fast lossless " + "compression algorithm, targeting real-time " + "compression scenarios at zlib-level and better " + "compression ratios. The zstd compression library " + "provides in-memory compression and decompression " + "functions.", + .output = "\x28\xb5\x2f\xfd\x00\x50\x75\x04\x00\x42\x4b\x1e\x17" + "\x90\x81\x31\x00\xf2\x2f\xe4\x36\xc9\xef\x92\x88\x32" + "\xc9\xf2\x24\x94\xd8\x68\x9a\x0f\x00\x0c\xc4\x31\x6f" + "\x0d\x0c\x38\xac\x5c\x48\x03\xcd\x63\x67\xc0\xf3\xad" + "\x4e\x90\xaa\x78\xa0\xa4\xc5\x99\xda\x2f\xb6\x24\x60" + "\xe2\x79\x4b\xaa\xb6\x6b\x85\x0b\xc9\xc6\x04\x66\x86" + "\xe2\xcc\xe2\x25\x3f\x4f\x09\xcd\xb8\x9d\xdb\xc1\x90" + "\xa9\x11\xbc\x35\x44\x69\x2d\x9c\x64\x4f\x13\x31\x64" + "\xcc\xfb\x4d\x95\x93\x86\x7f\x33\x7f\x1a\xef\xe9\x30" + "\xf9\x67\xa1\x94\x0a\x69\x0f\x60\xcd\xc3\xab\x99\xdc" + "\x42\xed\x97\x05\x00\x33\xc3\x15\x95\x3a\x06\xa0\x0e" + "\x20\xa9\x0e\x82\xb9\x43\x45\x01", + }, +}; + +static const struct comp_testvec zstd_decomp_tv_template[] = { + { + .inlen = 43, + .outlen = 68, + .input = "\x28\xb5\x2f\xfd\x04\x50\xf5\x00\x00\xb8\x54\x68\x65" + "\x20\x61\x6c\x67\x6f\x72\x69\x74\x68\x6d\x20\x69\x73" + "\x20\x7a\x73\x74\x64\x2e\x20\x01\x00\x55\x73\x36\x01" + "\x6b\xf4\x13\x35", + .output = "The algorithm is zstd. " + "The algorithm is zstd. " + "The algorithm is zstd.", + }, + { + .inlen = 155, + .outlen = 244, + .input = "\x28\xb5\x2f\xfd\x04\x50\x75\x04\x00\x42\x4b\x1e\x17" + "\x90\x81\x31\x00\xf2\x2f\xe4\x36\xc9\xef\x92\x88\x32" + "\xc9\xf2\x24\x94\xd8\x68\x9a\x0f\x00\x0c\xc4\x31\x6f" + "\x0d\x0c\x38\xac\x5c\x48\x03\xcd\x63\x67\xc0\xf3\xad" + "\x4e\x90\xaa\x78\xa0\xa4\xc5\x99\xda\x2f\xb6\x24\x60" + "\xe2\x79\x4b\xaa\xb6\x6b\x85\x0b\xc9\xc6\x04\x66\x86" + "\xe2\xcc\xe2\x25\x3f\x4f\x09\xcd\xb8\x9d\xdb\xc1\x90" + "\xa9\x11\xbc\x35\x44\x69\x2d\x9c\x64\x4f\x13\x31\x64" + "\xcc\xfb\x4d\x95\x93\x86\x7f\x33\x7f\x1a\xef\xe9\x30" + "\xf9\x67\xa1\x94\x0a\x69\x0f\x60\xcd\xc3\xab\x99\xdc" + "\x42\xed\x97\x05\x00\x33\xc3\x15\x95\x3a\x06\xa0\x0e" + "\x20\xa9\x0e\x82\xb9\x43\x45\x01\xaa\x6d\xda\x0d", + .output = "zstd, short for Zstandard, is a fast lossless " + "compression algorithm, targeting real-time " + "compression scenarios at zlib-level and better " + "compression ratios. The zstd compression library " + "provides in-memory compression and decompression " + "functions.", + }, +}; #endif /* _CRYPTO_TESTMGR_H */ diff --git a/crypto/zstd.c b/crypto/zstd.c new file mode 100644 index 000000000000..9a76b3ed8b8b --- /dev/null +++ b/crypto/zstd.c @@ -0,0 +1,265 @@ +/* + * Cryptographic API. + * + * Copyright (c) 2017-present, Facebook, Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ +#include <linux/crypto.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/net.h> +#include <linux/vmalloc.h> +#include <linux/zstd.h> +#include <crypto/internal/scompress.h> + + +#define ZSTD_DEF_LEVEL 3 + +struct zstd_ctx { + ZSTD_CCtx *cctx; + ZSTD_DCtx *dctx; + void *cwksp; + void *dwksp; +}; + +static ZSTD_parameters zstd_params(void) +{ + return ZSTD_getParams(ZSTD_DEF_LEVEL, 0, 0); +} + +static int zstd_comp_init(struct zstd_ctx *ctx) +{ + int ret = 0; + const ZSTD_parameters params = zstd_params(); + const size_t wksp_size = ZSTD_CCtxWorkspaceBound(params.cParams); + + ctx->cwksp = vzalloc(wksp_size); + if (!ctx->cwksp) { + ret = -ENOMEM; + goto out; + } + + ctx->cctx = ZSTD_initCCtx(ctx->cwksp, wksp_size); + if (!ctx->cctx) { + ret = -EINVAL; + goto out_free; + } +out: + return ret; +out_free: + vfree(ctx->cwksp); + goto out; +} + +static int zstd_decomp_init(struct zstd_ctx *ctx) +{ + int ret = 0; + const size_t wksp_size = ZSTD_DCtxWorkspaceBound(); + + ctx->dwksp = vzalloc(wksp_size); + if (!ctx->dwksp) { + ret = -ENOMEM; + goto out; + } + + ctx->dctx = ZSTD_initDCtx(ctx->dwksp, wksp_size); + if (!ctx->dctx) { + ret = -EINVAL; + goto out_free; + } +out: + return ret; +out_free: + vfree(ctx->dwksp); + goto out; +} + +static void zstd_comp_exit(struct zstd_ctx *ctx) +{ + vfree(ctx->cwksp); + ctx->cwksp = NULL; + ctx->cctx = NULL; +} + +static void zstd_decomp_exit(struct zstd_ctx *ctx) +{ + vfree(ctx->dwksp); + ctx->dwksp = NULL; + ctx->dctx = NULL; +} + +static int __zstd_init(void *ctx) +{ + int ret; + + ret = zstd_comp_init(ctx); + if (ret) + return ret; + ret = zstd_decomp_init(ctx); + if (ret) + zstd_comp_exit(ctx); + return ret; +} + +static void *zstd_alloc_ctx(struct crypto_scomp *tfm) +{ + int ret; + struct zstd_ctx *ctx; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return ERR_PTR(-ENOMEM); + + ret = __zstd_init(ctx); + if (ret) { + kfree(ctx); + return ERR_PTR(ret); + } + + return ctx; +} + +static int zstd_init(struct crypto_tfm *tfm) +{ + struct zstd_ctx *ctx = crypto_tfm_ctx(tfm); + + return __zstd_init(ctx); +} + +static void __zstd_exit(void *ctx) +{ + zstd_comp_exit(ctx); + zstd_decomp_exit(ctx); +} + +static void zstd_free_ctx(struct crypto_scomp *tfm, void *ctx) +{ + __zstd_exit(ctx); + kzfree(ctx); +} + +static void zstd_exit(struct crypto_tfm *tfm) +{ + struct zstd_ctx *ctx = crypto_tfm_ctx(tfm); + + __zstd_exit(ctx); +} + +static int __zstd_compress(const u8 *src, unsigned int slen, + u8 *dst, unsigned int *dlen, void *ctx) +{ + size_t out_len; + struct zstd_ctx *zctx = ctx; + const ZSTD_parameters params = zstd_params(); + + out_len = ZSTD_compressCCtx(zctx->cctx, dst, *dlen, src, slen, params); + if (ZSTD_isError(out_len)) + return -EINVAL; + *dlen = out_len; + return 0; +} + +static int zstd_compress(struct crypto_tfm *tfm, const u8 *src, + unsigned int slen, u8 *dst, unsigned int *dlen) +{ + struct zstd_ctx *ctx = crypto_tfm_ctx(tfm); + + return __zstd_compress(src, slen, dst, dlen, ctx); +} + +static int zstd_scompress(struct crypto_scomp *tfm, const u8 *src, + unsigned int slen, u8 *dst, unsigned int *dlen, + void *ctx) +{ + return __zstd_compress(src, slen, dst, dlen, ctx); +} + +static int __zstd_decompress(const u8 *src, unsigned int slen, + u8 *dst, unsigned int *dlen, void *ctx) +{ + size_t out_len; + struct zstd_ctx *zctx = ctx; + + out_len = ZSTD_decompressDCtx(zctx->dctx, dst, *dlen, src, slen); + if (ZSTD_isError(out_len)) + return -EINVAL; + *dlen = out_len; + return 0; +} + +static int zstd_decompress(struct crypto_tfm *tfm, const u8 *src, + unsigned int slen, u8 *dst, unsigned int *dlen) +{ + struct zstd_ctx *ctx = crypto_tfm_ctx(tfm); + + return __zstd_decompress(src, slen, dst, dlen, ctx); +} + +static int zstd_sdecompress(struct crypto_scomp *tfm, const u8 *src, + unsigned int slen, u8 *dst, unsigned int *dlen, + void *ctx) +{ + return __zstd_decompress(src, slen, dst, dlen, ctx); +} + +static struct crypto_alg alg = { + .cra_name = "zstd", + .cra_flags = CRYPTO_ALG_TYPE_COMPRESS, + .cra_ctxsize = sizeof(struct zstd_ctx), + .cra_module = THIS_MODULE, + .cra_init = zstd_init, + .cra_exit = zstd_exit, + .cra_u = { .compress = { + .coa_compress = zstd_compress, + .coa_decompress = zstd_decompress } } +}; + +static struct scomp_alg scomp = { + .alloc_ctx = zstd_alloc_ctx, + .free_ctx = zstd_free_ctx, + .compress = zstd_scompress, + .decompress = zstd_sdecompress, + .base = { + .cra_name = "zstd", + .cra_driver_name = "zstd-scomp", + .cra_module = THIS_MODULE, + } +}; + +static int __init zstd_mod_init(void) +{ + int ret; + + ret = crypto_register_alg(&alg); + if (ret) + return ret; + + ret = crypto_register_scomp(&scomp); + if (ret) + crypto_unregister_alg(&alg); + + return ret; +} + +static void __exit zstd_mod_fini(void) +{ + crypto_unregister_alg(&alg); + crypto_unregister_scomp(&scomp); +} + +module_init(zstd_mod_init); +module_exit(zstd_mod_fini); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Zstd Compression Algorithm"); +MODULE_ALIAS_CRYPTO("zstd"); diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c index 9e80802e3603..a3297306f544 100644 --- a/drivers/acpi/button.c +++ b/drivers/acpi/button.c @@ -557,7 +557,8 @@ static int acpi_button_remove(struct acpi_device *device) return 0; } -static int param_set_lid_init_state(const char *val, struct kernel_param *kp) +static int param_set_lid_init_state(const char *val, + const struct kernel_param *kp) { int result = 0; @@ -575,7 +576,8 @@ static int param_set_lid_init_state(const char *val, struct kernel_param *kp) return result; } -static int param_get_lid_init_state(char *buffer, struct kernel_param *kp) +static int param_get_lid_init_state(char *buffer, + const struct kernel_param *kp) { switch (lid_init_state) { case ACPI_BUTTON_LID_INIT_OPEN: diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index ebfc06f29f7b..bcadb6fd4729 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -2015,7 +2015,8 @@ static const struct dev_pm_ops acpi_ec_pm = { SET_SYSTEM_SLEEP_PM_OPS(acpi_ec_suspend, acpi_ec_resume) }; -static int param_set_event_clearing(const char *val, struct kernel_param *kp) +static int param_set_event_clearing(const char *val, + const struct kernel_param *kp) { int result = 0; @@ -2033,7 +2034,8 @@ static int param_set_event_clearing(const char *val, struct kernel_param *kp) return result; } -static int param_get_event_clearing(char *buffer, struct kernel_param *kp) +static int param_get_event_clearing(char *buffer, + const struct kernel_param *kp) { switch (ec_event_clearing) { case ACPI_EC_EVT_TIMING_STATUS: diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c index 3b7e23866b42..1828b335c28a 100644 --- a/drivers/acpi/sysfs.c +++ b/drivers/acpi/sysfs.c @@ -230,7 +230,8 @@ module_param_cb(trace_method_name, ¶m_ops_trace_method, &trace_method_name, module_param_cb(trace_debug_layer, ¶m_ops_trace_attrib, &acpi_gbl_trace_dbg_layer, 0644); module_param_cb(trace_debug_level, ¶m_ops_trace_attrib, &acpi_gbl_trace_dbg_level, 0644); -static int param_set_trace_state(const char *val, struct kernel_param *kp) +static int param_set_trace_state(const char *val, + const struct kernel_param *kp) { acpi_status status; const char *method = trace_method_name; @@ -266,7 +267,7 @@ static int param_set_trace_state(const char *val, struct kernel_param *kp) return 0; } -static int param_get_trace_state(char *buffer, struct kernel_param *kp) +static int param_get_trace_state(char *buffer, const struct kernel_param *kp) { if (!(acpi_gbl_trace_flags & ACPI_TRACE_ENABLED)) return sprintf(buffer, "disable"); @@ -295,7 +296,8 @@ MODULE_PARM_DESC(aml_debug_output, "To enable/disable the ACPI Debug Object output."); /* /sys/module/acpi/parameters/acpica_version */ -static int param_get_acpica_version(char *buffer, struct kernel_param *kp) +static int param_get_acpica_version(char *buffer, + const struct kernel_param *kp) { int result; diff --git a/drivers/android/Kconfig b/drivers/android/Kconfig index 7dce3795b887..ee4880bfdcdc 100644 --- a/drivers/android/Kconfig +++ b/drivers/android/Kconfig @@ -10,7 +10,7 @@ if ANDROID config ANDROID_BINDER_IPC bool "Android Binder IPC Driver" - depends on MMU + depends on MMU && !M68K default n ---help--- Binder is used in Android for both communication between processes, @@ -32,19 +32,6 @@ config ANDROID_BINDER_DEVICES created. Each binder device has its own context manager, and is therefore logically separated from the other devices. -config ANDROID_BINDER_IPC_32BIT - bool "Use old (Android 4.4 and earlier) 32-bit binder API" - depends on !64BIT && ANDROID_BINDER_IPC - default y - ---help--- - The Binder API has been changed to support both 32 and 64bit - applications in a mixed environment. - - Enable this to support an old 32-bit Android user-space (v4.4 and - earlier). - - Note that enabling this will break newer Android user-space. - config ANDROID_BINDER_IPC_SELFTEST bool "Android Binder IPC Driver Selftest" depends on ANDROID_BINDER_IPC diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 05e75d18b4d9..2c8b629c90c3 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -72,11 +72,8 @@ #include <linux/security.h> #include <linux/spinlock.h> -#ifdef CONFIG_ANDROID_BINDER_IPC_32BIT -#define BINDER_IPC_32BIT 1 -#endif - #include <uapi/linux/android/binder.h> +#include <uapi/linux/sched/types.h> #include "binder_alloc.h" #include "binder_trace.h" @@ -141,7 +138,7 @@ enum { }; static uint32_t binder_debug_mask = BINDER_DEBUG_USER_ERROR | BINDER_DEBUG_FAILED_TRANSACTION | BINDER_DEBUG_DEAD_TRANSACTION; -module_param_named(debug_mask, binder_debug_mask, uint, S_IWUSR | S_IRUGO); +module_param_named(debug_mask, binder_debug_mask, uint, 0644); static char *binder_devices_param = CONFIG_ANDROID_BINDER_DEVICES; module_param_named(devices, binder_devices_param, charp, 0444); @@ -150,7 +147,7 @@ static DECLARE_WAIT_QUEUE_HEAD(binder_user_error_wait); static int binder_stop_on_user_error; static int binder_set_stop_on_user_error(const char *val, - struct kernel_param *kp) + const struct kernel_param *kp) { int ret; @@ -160,7 +157,7 @@ static int binder_set_stop_on_user_error(const char *val, return ret; } module_param_call(stop_on_user_error, binder_set_stop_on_user_error, - param_get_int, &binder_stop_on_user_error, S_IWUSR | S_IRUGO); + param_get_int, &binder_stop_on_user_error, 0644); #define binder_debug(mask, x...) \ do { \ @@ -249,7 +246,7 @@ static struct binder_transaction_log_entry *binder_transaction_log_add( unsigned int cur = atomic_inc_return(&log->cur); if (cur >= ARRAY_SIZE(log->entry)) - log->full = 1; + log->full = true; e = &log->entry[cur % ARRAY_SIZE(log->entry)]; WRITE_ONCE(e->debug_id_done, 0); /* @@ -351,10 +348,15 @@ struct binder_error { * and by @lock) * @has_async_transaction: async transaction to node in progress * (protected by @lock) + * @sched_policy: minimum scheduling policy for node + * (invariant after initialized) * @accept_fds: file descriptor operations supported for node * (invariant after initialized) * @min_priority: minimum scheduling priority * (invariant after initialized) + * @inherit_rt: inherit RT scheduling policy from caller + * @txn_security_ctx: require sender's security context + * (invariant after initialized) * @async_todo: list of async work items * (protected by @proc->inner_lock) * @@ -390,7 +392,10 @@ struct binder_node { /* * invariant after initialization */ + u8 sched_policy:2; + u8 inherit_rt:1; u8 accept_fds:1; + u8 txn_security_ctx:1; u8 min_priority; }; bool has_async_transaction; @@ -464,6 +469,22 @@ enum binder_deferred_state { }; /** + * struct binder_priority - scheduler policy and priority + * @sched_policy scheduler policy + * @prio [100..139] for SCHED_NORMAL, [0..99] for FIFO/RT + * + * The binder driver supports inheriting the following scheduler policies: + * SCHED_NORMAL + * SCHED_BATCH + * SCHED_FIFO + * SCHED_RR + */ +struct binder_priority { + unsigned int sched_policy; + int prio; +}; + +/** * struct binder_proc - binder process bookkeeping * @proc_node: element for binder_procs list * @threads: rbtree of binder_threads in this proc @@ -493,8 +514,6 @@ enum binder_deferred_state { * (protected by @inner_lock) * @todo: list of work for this process * (protected by @inner_lock) - * @wait: wait queue head to wait for proc work - * (invariant after initialized) * @stats: per-process binder statistics * (atomics, no lock needed) * @delivered_death: list of delivered death notification @@ -537,14 +556,13 @@ struct binder_proc { bool is_dead; struct list_head todo; - wait_queue_head_t wait; struct binder_stats stats; struct list_head delivered_death; int max_threads; int requested_threads; int requested_threads_started; int tmp_ref; - long default_priority; + struct binder_priority default_priority; struct dentry *debugfs_entry; struct binder_alloc alloc; struct binder_context *context; @@ -579,6 +597,8 @@ enum { * (protected by @proc->inner_lock) * @todo: list of work to do for this thread * (protected by @proc->inner_lock) + * @process_todo: whether work in @todo should be processed + * (protected by @proc->inner_lock) * @return_error: transaction errors reported by this thread * (only accessed by this thread) * @reply_error: transaction errors reported by target thread @@ -592,6 +612,7 @@ enum { * @is_dead: thread is dead and awaiting free * when outstanding transactions are cleaned up * (protected by @proc->inner_lock) + * @task: struct task_struct for this thread * * Bookkeeping structure for binder threads. */ @@ -604,12 +625,14 @@ struct binder_thread { bool looper_need_return; /* can be written by other thread */ struct binder_transaction *transaction_stack; struct list_head todo; + bool process_todo; struct binder_error return_error; struct binder_error reply_error; wait_queue_head_t wait; struct binder_stats stats; atomic_t tmp_ref; bool is_dead; + struct task_struct *task; }; struct binder_transaction { @@ -626,9 +649,11 @@ struct binder_transaction { struct binder_buffer *buffer; unsigned int code; unsigned int flags; - long priority; - long saved_priority; + struct binder_priority priority; + struct binder_priority saved_priority; + bool set_priority_called; kuid_t sender_euid; + binder_uintptr_t security_ctx; /** * @lock: protects @from, @to_proc, and @to_thread * @@ -639,6 +664,26 @@ struct binder_transaction { }; /** + * struct binder_object - union of flat binder object types + * @hdr: generic object header + * @fbo: binder object (nodes and refs) + * @fdo: file descriptor object + * @bbo: binder buffer pointer + * @fdao: file descriptor array + * + * Used for type-independent object copies + */ +struct binder_object { + union { + struct binder_object_header hdr; + struct flat_binder_object fbo; + struct binder_fd_object fdo; + struct binder_buffer_object bbo; + struct binder_fd_array_object fdao; + }; +}; + +/** * binder_proc_lock() - Acquire outer lock for given binder_proc * @proc: struct binder_proc to acquire * @@ -789,6 +834,16 @@ static bool binder_worklist_empty(struct binder_proc *proc, return ret; } +/** + * binder_enqueue_work_ilocked() - Add an item to the work list + * @work: struct binder_work to add to list + * @target_list: list to add work to + * + * Adds the work to the specified list. Asserts that work + * is not already on a list. + * + * Requires the proc->inner_lock to be held. + */ static void binder_enqueue_work_ilocked(struct binder_work *work, struct list_head *target_list) @@ -799,22 +854,56 @@ binder_enqueue_work_ilocked(struct binder_work *work, } /** - * binder_enqueue_work() - Add an item to the work list - * @proc: binder_proc associated with list + * binder_enqueue_deferred_thread_work_ilocked() - Add deferred thread work + * @thread: thread to queue work to * @work: struct binder_work to add to list - * @target_list: list to add work to * - * Adds the work to the specified list. Asserts that work - * is not already on a list. + * Adds the work to the todo list of the thread. Doesn't set the process_todo + * flag, which means that (if it wasn't already set) the thread will go to + * sleep without handling this work when it calls read. + * + * Requires the proc->inner_lock to be held. */ static void -binder_enqueue_work(struct binder_proc *proc, - struct binder_work *work, - struct list_head *target_list) +binder_enqueue_deferred_thread_work_ilocked(struct binder_thread *thread, + struct binder_work *work) { - binder_inner_proc_lock(proc); - binder_enqueue_work_ilocked(work, target_list); - binder_inner_proc_unlock(proc); + binder_enqueue_work_ilocked(work, &thread->todo); +} + +/** + * binder_enqueue_thread_work_ilocked() - Add an item to the thread work list + * @thread: thread to queue work to + * @work: struct binder_work to add to list + * + * Adds the work to the todo list of the thread, and enables processing + * of the todo queue. + * + * Requires the proc->inner_lock to be held. + */ +static void +binder_enqueue_thread_work_ilocked(struct binder_thread *thread, + struct binder_work *work) +{ + binder_enqueue_work_ilocked(work, &thread->todo); + thread->process_todo = true; +} + +/** + * binder_enqueue_thread_work() - Add an item to the thread work list + * @thread: thread to queue work to + * @work: struct binder_work to add to list + * + * Adds the work to the todo list of the thread, and enables processing + * of the todo queue. + */ +static void +binder_enqueue_thread_work(struct binder_thread *thread, + struct binder_work *work) +{ + binder_inner_proc_lock(thread->proc); + binder_enqueue_thread_work_ilocked(thread, work); + binder_inner_proc_unlock(thread->proc); } static void @@ -940,7 +1029,7 @@ err: static bool binder_has_work_ilocked(struct binder_thread *thread, bool do_proc_work) { - return !binder_worklist_empty_ilocked(&thread->todo) || + return thread->process_todo || thread->looper_need_return || (do_proc_work && !binder_worklist_empty_ilocked(&thread->proc->todo)); @@ -1064,22 +1153,145 @@ static void binder_wakeup_proc_ilocked(struct binder_proc *proc) binder_wakeup_thread_ilocked(proc, thread, /* sync = */false); } -static void binder_set_nice(long nice) +static bool is_rt_policy(int policy) { - long min_nice; + return policy == SCHED_FIFO || policy == SCHED_RR; +} + +static bool is_fair_policy(int policy) +{ + return policy == SCHED_NORMAL || policy == SCHED_BATCH; +} + +static bool binder_supported_policy(int policy) +{ + return is_fair_policy(policy) || is_rt_policy(policy); +} + +static int to_userspace_prio(int policy, int kernel_priority) +{ + if (is_fair_policy(policy)) + return PRIO_TO_NICE(kernel_priority); + else + return MAX_USER_RT_PRIO - 1 - kernel_priority; +} - if (can_nice(current, nice)) { - set_user_nice(current, nice); +static int to_kernel_prio(int policy, int user_priority) +{ + if (is_fair_policy(policy)) + return NICE_TO_PRIO(user_priority); + else + return MAX_USER_RT_PRIO - 1 - user_priority; +} + +static void binder_do_set_priority(struct task_struct *task, + struct binder_priority desired, + bool verify) +{ + int priority; /* user-space prio value */ + bool has_cap_nice; + unsigned int policy = desired.sched_policy; + + if (task->policy == policy && task->normal_prio == desired.prio) return; + + has_cap_nice = has_capability_noaudit(task, CAP_SYS_NICE); + + priority = to_userspace_prio(policy, desired.prio); + + if (verify && is_rt_policy(policy) && !has_cap_nice) { + long max_rtprio = task_rlimit(task, RLIMIT_RTPRIO); + + if (max_rtprio == 0) { + policy = SCHED_NORMAL; + priority = MIN_NICE; + } else if (priority > max_rtprio) { + priority = max_rtprio; + } + } + + if (verify && is_fair_policy(policy) && !has_cap_nice) { + long min_nice = rlimit_to_nice(task_rlimit(task, RLIMIT_NICE)); + + if (min_nice > MAX_NICE) { + binder_user_error("%d RLIMIT_NICE not set\n", + task->pid); + return; + } else if (priority < min_nice) { + priority = min_nice; + } } - min_nice = rlimit_to_nice(rlimit(RLIMIT_NICE)); - binder_debug(BINDER_DEBUG_PRIORITY_CAP, - "%d: nice value %ld not allowed use %ld instead\n", - current->pid, nice, min_nice); - set_user_nice(current, min_nice); - if (min_nice <= MAX_NICE) + + if (policy != desired.sched_policy || + to_kernel_prio(policy, priority) != desired.prio) + binder_debug(BINDER_DEBUG_PRIORITY_CAP, + "%d: priority %d not allowed, using %d instead\n", + task->pid, desired.prio, + to_kernel_prio(policy, priority)); + + trace_binder_set_priority(task->tgid, task->pid, task->normal_prio, + to_kernel_prio(policy, priority), + desired.prio); + + /* Set the actual priority */ + if (task->policy != policy || is_rt_policy(policy)) { + struct sched_param params; + + params.sched_priority = is_rt_policy(policy) ? priority : 0; + + sched_setscheduler_nocheck(task, + policy | SCHED_RESET_ON_FORK, + ¶ms); + } + if (is_fair_policy(policy)) + set_user_nice(task, priority); +} + +static void binder_set_priority(struct task_struct *task, + struct binder_priority desired) +{ + binder_do_set_priority(task, desired, /* verify = */ true); +} + +static void binder_restore_priority(struct task_struct *task, + struct binder_priority desired) +{ + binder_do_set_priority(task, desired, /* verify = */ false); +} + +static void binder_transaction_priority(struct task_struct *task, + struct binder_transaction *t, + struct binder_priority node_prio, + bool inherit_rt) +{ + struct binder_priority desired_prio = t->priority; + + if (t->set_priority_called) return; - binder_user_error("%d RLIMIT_NICE not set\n", current->pid); + + t->set_priority_called = true; + t->saved_priority.sched_policy = task->policy; + t->saved_priority.prio = task->normal_prio; + + if (!inherit_rt && is_rt_policy(desired_prio.sched_policy)) { + desired_prio.prio = NICE_TO_PRIO(0); + desired_prio.sched_policy = SCHED_NORMAL; + } + + if (node_prio.prio < t->priority.prio || + (node_prio.prio == t->priority.prio && + node_prio.sched_policy == SCHED_FIFO)) { + /* + * In case the minimum priority on the node is + * higher (lower value), use that priority. If + * the priority is the same, but the node uses + * SCHED_FIFO, prefer SCHED_FIFO, since it can + * run unbounded, unlike SCHED_RR. + */ + desired_prio = node_prio; + } + + binder_set_priority(task, desired_prio); } static struct binder_node *binder_get_node_ilocked(struct binder_proc *proc, @@ -1132,6 +1344,7 @@ static struct binder_node *binder_init_node_ilocked( binder_uintptr_t ptr = fp ? fp->binder : 0; binder_uintptr_t cookie = fp ? fp->cookie : 0; __u32 flags = fp ? fp->flags : 0; + s8 priority; assert_spin_locked(&proc->inner_lock); @@ -1164,8 +1377,13 @@ static struct binder_node *binder_init_node_ilocked( node->ptr = ptr; node->cookie = cookie; node->work.type = BINDER_WORK_NODE; - node->min_priority = flags & FLAT_BINDER_FLAG_PRIORITY_MASK; + priority = flags & FLAT_BINDER_FLAG_PRIORITY_MASK; + node->sched_policy = (flags & FLAT_BINDER_FLAG_SCHED_POLICY_MASK) >> + FLAT_BINDER_FLAG_SCHED_POLICY_SHIFT; + node->min_priority = to_kernel_prio(node->sched_policy, priority); node->accept_fds = !!(flags & FLAT_BINDER_FLAG_ACCEPTS_FDS); + node->inherit_rt = !!(flags & FLAT_BINDER_FLAG_INHERIT_RT); + node->txn_security_ctx = !!(flags & FLAT_BINDER_FLAG_TXN_SECURITY_CTX); spin_lock_init(&node->lock); INIT_LIST_HEAD(&node->work.entry); INIT_LIST_HEAD(&node->async_todo); @@ -1228,6 +1446,17 @@ static int binder_inc_node_nilocked(struct binder_node *node, int strong, node->local_strong_refs++; if (!node->has_strong_ref && target_list) { binder_dequeue_work_ilocked(&node->work); + /* + * Note: this function is the only place where we queue + * directly to a thread->todo without using the + * corresponding binder_enqueue_thread_work() helper + * functions; in this case it's ok to not set the + * process_todo flag, since we know this node work will + * always be followed by other work that starts queue + * processing: in case of synchronous transactions, a + * BR_REPLY or BR_ERROR; in case of oneway + * transactions, a BR_TRANSACTION_COMPLETE. + */ binder_enqueue_work_ilocked(&node->work, target_list); } } else { @@ -1239,6 +1468,9 @@ static int binder_inc_node_nilocked(struct binder_node *node, int strong, node->debug_id); return -EINVAL; } + /* + * See comment above + */ binder_enqueue_work_ilocked(&node->work, target_list); } } @@ -1938,9 +2170,9 @@ static void binder_send_failed_reply(struct binder_transaction *t, binder_pop_transaction_ilocked(target_thread, t); if (target_thread->reply_error.cmd == BR_OK) { target_thread->reply_error.cmd = error_code; - binder_enqueue_work_ilocked( - &target_thread->reply_error.work, - &target_thread->todo); + binder_enqueue_thread_work_ilocked( + target_thread, + &target_thread->reply_error.work); wake_up_interruptible(&target_thread->wait); } else { /* @@ -1997,26 +2229,34 @@ static void binder_cleanup_transaction(struct binder_transaction *t, } /** - * binder_validate_object() - checks for a valid metadata object in a buffer. + * binder_get_object() - gets object and checks for valid metadata + * @proc: binder_proc owning the buffer * @buffer: binder_buffer that we're parsing. - * @offset: offset in the buffer at which to validate an object. + * @offset: offset in the @buffer at which to validate an object. + * @object: struct binder_object to read into * * Return: If there's a valid metadata object at @offset in @buffer, the - * size of that object. Otherwise, it returns zero. + * size of that object. Otherwise, it returns zero. The object + * is read into the struct binder_object pointed to by @object. */ -static size_t binder_validate_object(struct binder_buffer *buffer, u64 offset) +static size_t binder_get_object(struct binder_proc *proc, + struct binder_buffer *buffer, + unsigned long offset, + struct binder_object *object) { - /* Check if we can read a header first */ + size_t read_size; struct binder_object_header *hdr; size_t object_size = 0; - if (offset > buffer->data_size - sizeof(*hdr) || - buffer->data_size < sizeof(*hdr) || + read_size = min_t(size_t, sizeof(*object), buffer->data_size - offset); + if (offset > buffer->data_size || read_size < sizeof(*hdr) || !IS_ALIGNED(offset, sizeof(u32))) return 0; + binder_alloc_copy_from_buffer(&proc->alloc, object, buffer, + offset, read_size); - /* Ok, now see if we can read a complete object. */ - hdr = (struct binder_object_header *)(buffer->data + offset); + /* Ok, now see if we read a complete object. */ + hdr = &object->hdr; switch (hdr->type) { case BINDER_TYPE_BINDER: case BINDER_TYPE_WEAK_BINDER: @@ -2045,10 +2285,13 @@ static size_t binder_validate_object(struct binder_buffer *buffer, u64 offset) /** * binder_validate_ptr() - validates binder_buffer_object in a binder_buffer. + * @proc: binder_proc owning the buffer * @b: binder_buffer containing the object + * @object: struct binder_object to read into * @index: index in offset array at which the binder_buffer_object is * located - * @start: points to the start of the offset array + * @start_offset: points to the start of the offset array + * @object_offsetp: offset of @object read from @b * @num_valid: the number of valid offsets in the offset array * * Return: If @index is within the valid range of the offset array @@ -2059,34 +2302,46 @@ static size_t binder_validate_object(struct binder_buffer *buffer, u64 offset) * Note that the offset found in index @index itself is not * verified; this function assumes that @num_valid elements * from @start were previously verified to have valid offsets. + * If @object_offsetp is non-NULL, then the offset within + * @b is written to it. */ -static struct binder_buffer_object *binder_validate_ptr(struct binder_buffer *b, - binder_size_t index, - binder_size_t *start, - binder_size_t num_valid) +static struct binder_buffer_object *binder_validate_ptr( + struct binder_proc *proc, + struct binder_buffer *b, + struct binder_object *object, + binder_size_t index, + binder_size_t start_offset, + binder_size_t *object_offsetp, + binder_size_t num_valid) { - struct binder_buffer_object *buffer_obj; - binder_size_t *offp; + size_t object_size; + binder_size_t object_offset; + unsigned long buffer_offset; if (index >= num_valid) return NULL; - offp = start + index; - buffer_obj = (struct binder_buffer_object *)(b->data + *offp); - if (buffer_obj->hdr.type != BINDER_TYPE_PTR) + buffer_offset = start_offset + sizeof(binder_size_t) * index; + binder_alloc_copy_from_buffer(&proc->alloc, &object_offset, + b, buffer_offset, sizeof(object_offset)); + object_size = binder_get_object(proc, b, object_offset, object); + if (!object_size || object->hdr.type != BINDER_TYPE_PTR) return NULL; + if (object_offsetp) + *object_offsetp = object_offset; - return buffer_obj; + return &object->bbo; } /** * binder_validate_fixup() - validates pointer/fd fixups happen in order. + * @proc: binder_proc owning the buffer * @b: transaction buffer - * @objects_start start of objects buffer - * @buffer: binder_buffer_object in which to fix up - * @offset: start offset in @buffer to fix up - * @last_obj: last binder_buffer_object that we fixed up in - * @last_min_offset: minimum fixup offset in @last_obj + * @objects_start_offset: offset to start of objects buffer + * @buffer_obj_offset: offset to binder_buffer_object in which to fix up + * @fixup_offset: start offset in @buffer to fix up + * @last_obj_offset: offset to last binder_buffer_object that we fixed + * @last_min_offset: minimum fixup offset in object at @last_obj_offset * * Return: %true if a fixup in buffer @buffer at offset @offset is * allowed. @@ -2117,63 +2372,83 @@ static struct binder_buffer_object *binder_validate_ptr(struct binder_buffer *b, * C (parent = A, offset = 16) * D (parent = B, offset = 0) // B is not A or any of A's parents */ -static bool binder_validate_fixup(struct binder_buffer *b, - binder_size_t *objects_start, - struct binder_buffer_object *buffer, +static bool binder_validate_fixup(struct binder_proc *proc, + struct binder_buffer *b, + binder_size_t objects_start_offset, + binder_size_t buffer_obj_offset, binder_size_t fixup_offset, - struct binder_buffer_object *last_obj, + binder_size_t last_obj_offset, binder_size_t last_min_offset) { - if (!last_obj) { + if (!last_obj_offset) { /* Nothing to fix up in */ return false; } - while (last_obj != buffer) { + while (last_obj_offset != buffer_obj_offset) { + unsigned long buffer_offset; + struct binder_object last_object; + struct binder_buffer_object *last_bbo; + size_t object_size = binder_get_object(proc, b, last_obj_offset, + &last_object); + if (object_size != sizeof(*last_bbo)) + return false; + + last_bbo = &last_object.bbo; /* * Safe to retrieve the parent of last_obj, since it * was already previously verified by the driver. */ - if ((last_obj->flags & BINDER_BUFFER_FLAG_HAS_PARENT) == 0) + if ((last_bbo->flags & BINDER_BUFFER_FLAG_HAS_PARENT) == 0) return false; - last_min_offset = last_obj->parent_offset + sizeof(uintptr_t); - last_obj = (struct binder_buffer_object *) - (b->data + *(objects_start + last_obj->parent)); + last_min_offset = last_bbo->parent_offset + sizeof(uintptr_t); + buffer_offset = objects_start_offset + + sizeof(binder_size_t) * last_bbo->parent, + binder_alloc_copy_from_buffer(&proc->alloc, &last_obj_offset, + b, buffer_offset, + sizeof(last_obj_offset)); } return (fixup_offset >= last_min_offset); } static void binder_transaction_buffer_release(struct binder_proc *proc, struct binder_buffer *buffer, - binder_size_t *failed_at) + binder_size_t failed_at, + bool is_failure) { - binder_size_t *offp, *off_start, *off_end; int debug_id = buffer->debug_id; + binder_size_t off_start_offset, buffer_offset, off_end_offset; binder_debug(BINDER_DEBUG_TRANSACTION, - "%d buffer release %d, size %zd-%zd, failed at %pK\n", + "%d buffer release %d, size %zd-%zd, failed at %llx\n", proc->pid, buffer->debug_id, - buffer->data_size, buffer->offsets_size, failed_at); + buffer->data_size, buffer->offsets_size, + (unsigned long long)failed_at); if (buffer->target_node) binder_dec_node(buffer->target_node, 1, 0); - off_start = (binder_size_t *)(buffer->data + - ALIGN(buffer->data_size, sizeof(void *))); - if (failed_at) - off_end = failed_at; - else - off_end = (void *)off_start + buffer->offsets_size; - for (offp = off_start; offp < off_end; offp++) { + off_start_offset = ALIGN(buffer->data_size, sizeof(void *)); + off_end_offset = is_failure ? failed_at : + off_start_offset + buffer->offsets_size; + for (buffer_offset = off_start_offset; buffer_offset < off_end_offset; + buffer_offset += sizeof(binder_size_t)) { struct binder_object_header *hdr; - size_t object_size = binder_validate_object(buffer, *offp); - + size_t object_size; + struct binder_object object; + binder_size_t object_offset; + + binder_alloc_copy_from_buffer(&proc->alloc, &object_offset, + buffer, buffer_offset, + sizeof(object_offset)); + object_size = binder_get_object(proc, buffer, + object_offset, &object); if (object_size == 0) { pr_err("transaction release %d bad object at offset %lld, size %zd\n", - debug_id, (u64)*offp, buffer->data_size); + debug_id, (u64)object_offset, buffer->data_size); continue; } - hdr = (struct binder_object_header *)(buffer->data + *offp); + hdr = &object.hdr; switch (hdr->type) { case BINDER_TYPE_BINDER: case BINDER_TYPE_WEAK_BINDER: { @@ -2231,28 +2506,25 @@ static void binder_transaction_buffer_release(struct binder_proc *proc, case BINDER_TYPE_FDA: { struct binder_fd_array_object *fda; struct binder_buffer_object *parent; - uintptr_t parent_buffer; - u32 *fd_array; + struct binder_object ptr_object; + binder_size_t fda_offset; size_t fd_index; binder_size_t fd_buf_size; + binder_size_t num_valid; + num_valid = (buffer_offset - off_start_offset) / + sizeof(binder_size_t); fda = to_binder_fd_array_object(hdr); - parent = binder_validate_ptr(buffer, fda->parent, - off_start, - offp - off_start); + parent = binder_validate_ptr(proc, buffer, &ptr_object, + fda->parent, + off_start_offset, + NULL, + num_valid); if (!parent) { pr_err("transaction release %d bad parent offset", debug_id); continue; } - /* - * Since the parent was already fixed up, convert it - * back to kernel address space to access it - */ - parent_buffer = parent->buffer - - binder_alloc_get_user_buffer_offset( - &proc->alloc); - fd_buf_size = sizeof(u32) * fda->num_fds; if (fda->num_fds >= SIZE_MAX / sizeof(u32)) { pr_err("transaction release %d invalid number of fds (%lld)\n", @@ -2266,9 +2538,29 @@ static void binder_transaction_buffer_release(struct binder_proc *proc, debug_id, (u64)fda->num_fds); continue; } - fd_array = (u32 *)(parent_buffer + (uintptr_t)fda->parent_offset); - for (fd_index = 0; fd_index < fda->num_fds; fd_index++) - task_close_fd(proc, fd_array[fd_index]); + /* + * the source data for binder_buffer_object is visible + * to user-space and the @buffer element is the user + * pointer to the buffer_object containing the fd_array. + * Convert the address to an offset relative to + * the base of the transaction buffer. + */ + fda_offset = + (parent->buffer - (uintptr_t)buffer->user_data) + + fda->parent_offset; + for (fd_index = 0; fd_index < fda->num_fds; + fd_index++) { + u32 fd; + binder_size_t offset = fda_offset + + fd_index * sizeof(fd); + + binder_alloc_copy_from_buffer(&proc->alloc, + &fd, + buffer, + offset, + sizeof(fd)); + task_close_fd(proc, fd); + } } break; default: pr_err("transaction release %d bad object type %x\n", @@ -2465,9 +2757,8 @@ static int binder_translate_fd_array(struct binder_fd_array_object *fda, struct binder_transaction *in_reply_to) { binder_size_t fdi, fd_buf_size, num_installed_fds; + binder_size_t fda_offset; int target_fd; - uintptr_t parent_buffer; - u32 *fd_array; struct binder_proc *proc = thread->proc; struct binder_proc *target_proc = t->to_proc; @@ -2485,23 +2776,33 @@ static int binder_translate_fd_array(struct binder_fd_array_object *fda, return -EINVAL; } /* - * Since the parent was already fixed up, convert it - * back to the kernel address space to access it + * the source data for binder_buffer_object is visible + * to user-space and the @buffer element is the user + * pointer to the buffer_object containing the fd_array. + * Convert the address to an offset relative to + * the base of the transaction buffer. */ - parent_buffer = parent->buffer - - binder_alloc_get_user_buffer_offset(&target_proc->alloc); - fd_array = (u32 *)(parent_buffer + (uintptr_t)fda->parent_offset); - if (!IS_ALIGNED((unsigned long)fd_array, sizeof(u32))) { + fda_offset = (parent->buffer - (uintptr_t)t->buffer->user_data) + + fda->parent_offset; + if (!IS_ALIGNED((unsigned long)fda_offset, sizeof(u32))) { binder_user_error("%d:%d parent offset not aligned correctly.\n", proc->pid, thread->pid); return -EINVAL; } for (fdi = 0; fdi < fda->num_fds; fdi++) { - target_fd = binder_translate_fd(fd_array[fdi], t, thread, - in_reply_to); + u32 fd; + + binder_size_t offset = fda_offset + fdi * sizeof(fd); + + binder_alloc_copy_from_buffer(&target_proc->alloc, + &fd, t->buffer, + offset, sizeof(fd)); + target_fd = binder_translate_fd(fd, t, thread, in_reply_to); if (target_fd < 0) goto err_translate_fd_failed; - fd_array[fdi] = target_fd; + binder_alloc_copy_to_buffer(&target_proc->alloc, + t->buffer, offset, + &target_fd, sizeof(fd)); } return 0; @@ -2511,38 +2812,48 @@ err_translate_fd_failed: * installed so far. */ num_installed_fds = fdi; - for (fdi = 0; fdi < num_installed_fds; fdi++) - task_close_fd(target_proc, fd_array[fdi]); + for (fdi = 0; fdi < num_installed_fds; fdi++) { + u32 fd; + binder_size_t offset = fda_offset + fdi * sizeof(fd); + binder_alloc_copy_from_buffer(&target_proc->alloc, + &fd, t->buffer, + offset, sizeof(fd)); + task_close_fd(target_proc, fd); + } return target_fd; } static int binder_fixup_parent(struct binder_transaction *t, struct binder_thread *thread, struct binder_buffer_object *bp, - binder_size_t *off_start, + binder_size_t off_start_offset, binder_size_t num_valid, - struct binder_buffer_object *last_fixup_obj, + binder_size_t last_fixup_obj_off, binder_size_t last_fixup_min_off) { struct binder_buffer_object *parent; - u8 *parent_buffer; struct binder_buffer *b = t->buffer; struct binder_proc *proc = thread->proc; struct binder_proc *target_proc = t->to_proc; + struct binder_object object; + binder_size_t buffer_offset; + binder_size_t parent_offset; if (!(bp->flags & BINDER_BUFFER_FLAG_HAS_PARENT)) return 0; - parent = binder_validate_ptr(b, bp->parent, off_start, num_valid); + parent = binder_validate_ptr(target_proc, b, &object, bp->parent, + off_start_offset, &parent_offset, + num_valid); if (!parent) { binder_user_error("%d:%d got transaction with invalid parent offset or type\n", proc->pid, thread->pid); return -EINVAL; } - if (!binder_validate_fixup(b, off_start, - parent, bp->parent_offset, - last_fixup_obj, + if (!binder_validate_fixup(target_proc, b, off_start_offset, + parent_offset, bp->parent_offset, + last_fixup_obj_off, last_fixup_min_off)) { binder_user_error("%d:%d got transaction with out-of-order buffer fixup\n", proc->pid, thread->pid); @@ -2556,10 +2867,10 @@ static int binder_fixup_parent(struct binder_transaction *t, proc->pid, thread->pid); return -EINVAL; } - parent_buffer = (u8 *)((uintptr_t)parent->buffer - - binder_alloc_get_user_buffer_offset( - &target_proc->alloc)); - *(binder_uintptr_t *)(parent_buffer + bp->parent_offset) = bp->buffer; + buffer_offset = bp->parent_offset + + (uintptr_t)parent->buffer - (uintptr_t)b->user_data; + binder_alloc_copy_to_buffer(&target_proc->alloc, b, buffer_offset, + &bp->buffer, sizeof(bp->buffer)); return 0; } @@ -2585,20 +2896,22 @@ static bool binder_proc_transaction(struct binder_transaction *t, struct binder_proc *proc, struct binder_thread *thread) { - struct list_head *target_list = NULL; struct binder_node *node = t->buffer->target_node; + struct binder_priority node_prio; bool oneway = !!(t->flags & TF_ONE_WAY); - bool wakeup = true; + bool pending_async = false; BUG_ON(!node); binder_node_lock(node); + node_prio.prio = node->min_priority; + node_prio.sched_policy = node->sched_policy; + if (oneway) { BUG_ON(thread); if (node->has_async_transaction) { - target_list = &node->async_todo; - wakeup = false; + pending_async = true; } else { - node->has_async_transaction = 1; + node->has_async_transaction = true; } } @@ -2610,19 +2923,20 @@ static bool binder_proc_transaction(struct binder_transaction *t, return false; } - if (!thread && !target_list) + if (!thread && !pending_async) thread = binder_select_thread_ilocked(proc); - if (thread) - target_list = &thread->todo; - else if (!target_list) - target_list = &proc->todo; - else - BUG_ON(target_list != &node->async_todo); - - binder_enqueue_work_ilocked(&t->work, target_list); + if (thread) { + binder_transaction_priority(thread->task, t, node_prio, + node->inherit_rt); + binder_enqueue_thread_work_ilocked(thread, &t->work); + } else if (!pending_async) { + binder_enqueue_work_ilocked(&t->work, &proc->todo); + } else { + binder_enqueue_work_ilocked(&t->work, &node->async_todo); + } - if (wakeup) + if (!pending_async) binder_wakeup_thread_ilocked(proc, thread, !oneway /* sync */); binder_inner_proc_unlock(proc); @@ -2681,9 +2995,10 @@ static void binder_transaction(struct binder_proc *proc, int ret; struct binder_transaction *t; struct binder_work *tcomplete; - binder_size_t *offp, *off_end, *off_start; + binder_size_t buffer_offset = 0; + binder_size_t off_start_offset, off_end_offset; binder_size_t off_min; - u8 *sg_bufp, *sg_buf_end; + binder_size_t sg_buf_offset, sg_buf_end_offset; struct binder_proc *target_proc = NULL; struct binder_thread *target_thread = NULL; struct binder_node *target_node = NULL; @@ -2692,10 +3007,12 @@ static void binder_transaction(struct binder_proc *proc, uint32_t return_error = 0; uint32_t return_error_param = 0; uint32_t return_error_line = 0; - struct binder_buffer_object *last_fixup_obj = NULL; + binder_size_t last_fixup_obj_off = 0; binder_size_t last_fixup_min_off = 0; struct binder_context *context = proc->context; int t_debug_id = atomic_inc_return(&binder_last_id); + char *secctx = NULL; + u32 secctx_sz = 0; e = binder_transaction_log_add(&binder_transaction_log); e->debug_id = t_debug_id; @@ -2737,7 +3054,6 @@ static void binder_transaction(struct binder_proc *proc, } thread->transaction_stack = in_reply_to->to_parent; binder_inner_proc_unlock(proc); - binder_set_nice(in_reply_to->saved_priority); target_thread = binder_get_txn_from_and_acq_inner(in_reply_to); if (target_thread == NULL) { return_error = BR_DEAD_REPLY; @@ -2910,7 +3226,38 @@ static void binder_transaction(struct binder_proc *proc, t->to_thread = target_thread; t->code = tr->code; t->flags = tr->flags; - t->priority = task_nice(current); + if (!(t->flags & TF_ONE_WAY) && + binder_supported_policy(current->policy)) { + /* Inherit supported policies for synchronous transactions */ + t->priority.sched_policy = current->policy; + t->priority.prio = current->normal_prio; + } else { + /* Otherwise, fall back to the default priority */ + t->priority = target_proc->default_priority; + } + + if (target_node && target_node->txn_security_ctx) { + u32 secid; + size_t added_size; + + security_task_getsecid(proc->tsk, &secid); + ret = security_secid_to_secctx(secid, &secctx, &secctx_sz); + if (ret) { + return_error = BR_FAILED_REPLY; + return_error_param = ret; + return_error_line = __LINE__; + goto err_get_secctx_failed; + } + added_size = ALIGN(secctx_sz, sizeof(u64)); + extra_buffers_size += added_size; + if (extra_buffers_size < added_size) { + /* integer overflow of extra_buffers_size */ + return_error = BR_FAILED_REPLY; + return_error_param = EINVAL; + return_error_line = __LINE__; + goto err_bad_extra_size; + } + } trace_binder_transaction(reply, t, target_node); @@ -2928,16 +3275,30 @@ static void binder_transaction(struct binder_proc *proc, t->buffer = NULL; goto err_binder_alloc_buf_failed; } + if (secctx) { + size_t buf_offset = ALIGN(tr->data_size, sizeof(void *)) + + ALIGN(tr->offsets_size, sizeof(void *)) + + ALIGN(extra_buffers_size, sizeof(void *)) - + ALIGN(secctx_sz, sizeof(u64)); + + t->security_ctx = (uintptr_t)t->buffer->user_data + buf_offset; + binder_alloc_copy_to_buffer(&target_proc->alloc, + t->buffer, buf_offset, + secctx, secctx_sz); + security_release_secctx(secctx, secctx_sz); + secctx = NULL; + } t->buffer->debug_id = t->debug_id; t->buffer->transaction = t; t->buffer->target_node = target_node; trace_binder_transaction_alloc_buf(t->buffer); - off_start = (binder_size_t *)(t->buffer->data + - ALIGN(tr->data_size, sizeof(void *))); - offp = off_start; - if (copy_from_user(t->buffer->data, (const void __user *)(uintptr_t) - tr->data.ptr.buffer, tr->data_size)) { + if (binder_alloc_copy_user_to_buffer( + &target_proc->alloc, + t->buffer, 0, + (const void __user *) + (uintptr_t)tr->data.ptr.buffer, + tr->data_size)) { binder_user_error("%d:%d got transaction with invalid data ptr\n", proc->pid, thread->pid); return_error = BR_FAILED_REPLY; @@ -2945,8 +3306,13 @@ static void binder_transaction(struct binder_proc *proc, return_error_line = __LINE__; goto err_copy_data_failed; } - if (copy_from_user(offp, (const void __user *)(uintptr_t) - tr->data.ptr.offsets, tr->offsets_size)) { + if (binder_alloc_copy_user_to_buffer( + &target_proc->alloc, + t->buffer, + ALIGN(tr->data_size, sizeof(void *)), + (const void __user *) + (uintptr_t)tr->data.ptr.offsets, + tr->offsets_size)) { binder_user_error("%d:%d got transaction with invalid offsets ptr\n", proc->pid, thread->pid); return_error = BR_FAILED_REPLY; @@ -2971,17 +3337,31 @@ static void binder_transaction(struct binder_proc *proc, return_error_line = __LINE__; goto err_bad_offset; } - off_end = (void *)off_start + tr->offsets_size; - sg_bufp = (u8 *)(PTR_ALIGN(off_end, sizeof(void *))); - sg_buf_end = sg_bufp + extra_buffers_size; + off_start_offset = ALIGN(tr->data_size, sizeof(void *)); + buffer_offset = off_start_offset; + off_end_offset = off_start_offset + tr->offsets_size; + sg_buf_offset = ALIGN(off_end_offset, sizeof(void *)); + sg_buf_end_offset = sg_buf_offset + extra_buffers_size - + ALIGN(secctx_sz, sizeof(u64)); off_min = 0; - for (; offp < off_end; offp++) { + for (buffer_offset = off_start_offset; buffer_offset < off_end_offset; + buffer_offset += sizeof(binder_size_t)) { struct binder_object_header *hdr; - size_t object_size = binder_validate_object(t->buffer, *offp); - - if (object_size == 0 || *offp < off_min) { + size_t object_size; + struct binder_object object; + binder_size_t object_offset; + + binder_alloc_copy_from_buffer(&target_proc->alloc, + &object_offset, + t->buffer, + buffer_offset, + sizeof(object_offset)); + object_size = binder_get_object(target_proc, t->buffer, + object_offset, &object); + if (object_size == 0 || object_offset < off_min) { binder_user_error("%d:%d got transaction with invalid offset (%lld, min %lld max %lld) or object.\n", - proc->pid, thread->pid, (u64)*offp, + proc->pid, thread->pid, + (u64)object_offset, (u64)off_min, (u64)t->buffer->data_size); return_error = BR_FAILED_REPLY; @@ -2990,8 +3370,8 @@ static void binder_transaction(struct binder_proc *proc, goto err_bad_offset; } - hdr = (struct binder_object_header *)(t->buffer->data + *offp); - off_min = *offp + object_size; + hdr = &object.hdr; + off_min = object_offset + object_size; switch (hdr->type) { case BINDER_TYPE_BINDER: case BINDER_TYPE_WEAK_BINDER: { @@ -3005,6 +3385,9 @@ static void binder_transaction(struct binder_proc *proc, return_error_line = __LINE__; goto err_translate_failed; } + binder_alloc_copy_to_buffer(&target_proc->alloc, + t->buffer, object_offset, + fp, sizeof(*fp)); } break; case BINDER_TYPE_HANDLE: case BINDER_TYPE_WEAK_HANDLE: { @@ -3018,6 +3401,9 @@ static void binder_transaction(struct binder_proc *proc, return_error_line = __LINE__; goto err_translate_failed; } + binder_alloc_copy_to_buffer(&target_proc->alloc, + t->buffer, object_offset, + fp, sizeof(*fp)); } break; case BINDER_TYPE_FD: { @@ -3033,14 +3419,23 @@ static void binder_transaction(struct binder_proc *proc, } fp->pad_binder = 0; fp->fd = target_fd; + binder_alloc_copy_to_buffer(&target_proc->alloc, + t->buffer, object_offset, + fp, sizeof(*fp)); } break; case BINDER_TYPE_FDA: { + struct binder_object ptr_object; + binder_size_t parent_offset; struct binder_fd_array_object *fda = to_binder_fd_array_object(hdr); + size_t num_valid = (buffer_offset - off_start_offset) / + sizeof(binder_size_t); struct binder_buffer_object *parent = - binder_validate_ptr(t->buffer, fda->parent, - off_start, - offp - off_start); + binder_validate_ptr(target_proc, t->buffer, + &ptr_object, fda->parent, + off_start_offset, + &parent_offset, + num_valid); if (!parent) { binder_user_error("%d:%d got transaction with invalid parent offset or type\n", proc->pid, thread->pid); @@ -3049,9 +3444,11 @@ static void binder_transaction(struct binder_proc *proc, return_error_line = __LINE__; goto err_bad_parent; } - if (!binder_validate_fixup(t->buffer, off_start, - parent, fda->parent_offset, - last_fixup_obj, + if (!binder_validate_fixup(target_proc, t->buffer, + off_start_offset, + parent_offset, + fda->parent_offset, + last_fixup_obj_off, last_fixup_min_off)) { binder_user_error("%d:%d got transaction with out-of-order buffer fixup\n", proc->pid, thread->pid); @@ -3068,14 +3465,15 @@ static void binder_transaction(struct binder_proc *proc, return_error_line = __LINE__; goto err_translate_failed; } - last_fixup_obj = parent; + last_fixup_obj_off = parent_offset; last_fixup_min_off = fda->parent_offset + sizeof(u32) * fda->num_fds; } break; case BINDER_TYPE_PTR: { struct binder_buffer_object *bp = to_binder_buffer_object(hdr); - size_t buf_left = sg_buf_end - sg_bufp; + size_t buf_left = sg_buf_end_offset - sg_buf_offset; + size_t num_valid; if (bp->length > buf_left) { binder_user_error("%d:%d got transaction with too large buffer\n", @@ -3085,9 +3483,13 @@ static void binder_transaction(struct binder_proc *proc, return_error_line = __LINE__; goto err_bad_offset; } - if (copy_from_user(sg_bufp, - (const void __user *)(uintptr_t) - bp->buffer, bp->length)) { + if (binder_alloc_copy_user_to_buffer( + &target_proc->alloc, + t->buffer, + sg_buf_offset, + (const void __user *) + (uintptr_t)bp->buffer, + bp->length)) { binder_user_error("%d:%d got transaction with invalid offsets ptr\n", proc->pid, thread->pid); return_error_param = -EFAULT; @@ -3096,14 +3498,16 @@ static void binder_transaction(struct binder_proc *proc, goto err_copy_data_failed; } /* Fixup buffer pointer to target proc address space */ - bp->buffer = (uintptr_t)sg_bufp + - binder_alloc_get_user_buffer_offset( - &target_proc->alloc); - sg_bufp += ALIGN(bp->length, sizeof(u64)); - - ret = binder_fixup_parent(t, thread, bp, off_start, - offp - off_start, - last_fixup_obj, + bp->buffer = (uintptr_t) + t->buffer->user_data + sg_buf_offset; + sg_buf_offset += ALIGN(bp->length, sizeof(u64)); + + num_valid = (buffer_offset - off_start_offset) / + sizeof(binder_size_t); + ret = binder_fixup_parent(t, thread, bp, + off_start_offset, + num_valid, + last_fixup_obj_off, last_fixup_min_off); if (ret < 0) { return_error = BR_FAILED_REPLY; @@ -3111,7 +3515,10 @@ static void binder_transaction(struct binder_proc *proc, return_error_line = __LINE__; goto err_translate_failed; } - last_fixup_obj = bp; + binder_alloc_copy_to_buffer(&target_proc->alloc, + t->buffer, object_offset, + bp, sizeof(*bp)); + last_fixup_obj_off = object_offset; last_fixup_min_off = 0; } break; default: @@ -3124,10 +3531,10 @@ static void binder_transaction(struct binder_proc *proc, } } tcomplete->type = BINDER_WORK_TRANSACTION_COMPLETE; - binder_enqueue_work(proc, tcomplete, &thread->todo); t->work.type = BINDER_WORK_TRANSACTION; if (reply) { + binder_enqueue_thread_work(thread, tcomplete); binder_inner_proc_lock(target_proc); if (target_thread->is_dead) { binder_inner_proc_unlock(target_proc); @@ -3135,13 +3542,22 @@ static void binder_transaction(struct binder_proc *proc, } BUG_ON(t->buffer->async_transaction != 0); binder_pop_transaction_ilocked(target_thread, in_reply_to); - binder_enqueue_work_ilocked(&t->work, &target_thread->todo); + binder_enqueue_thread_work_ilocked(target_thread, &t->work); binder_inner_proc_unlock(target_proc); wake_up_interruptible_sync(&target_thread->wait); + binder_restore_priority(current, in_reply_to->saved_priority); binder_free_transaction(in_reply_to); } else if (!(t->flags & TF_ONE_WAY)) { BUG_ON(t->buffer->async_transaction != 0); binder_inner_proc_lock(proc); + /* + * Defer the TRANSACTION_COMPLETE, so we don't return to + * userspace immediately; this allows the target process to + * immediately start processing this transaction, reducing + * latency. We will then return the TRANSACTION_COMPLETE when + * the target replies (or there is an error). + */ + binder_enqueue_deferred_thread_work_ilocked(thread, tcomplete); t->need_reply = 1; t->from_parent = thread->transaction_stack; thread->transaction_stack = t; @@ -3155,6 +3571,7 @@ static void binder_transaction(struct binder_proc *proc, } else { BUG_ON(target_node == NULL); BUG_ON(t->buffer->async_transaction != 1); + binder_enqueue_thread_work(thread, tcomplete); if (!binder_proc_transaction(t, target_proc, NULL)) goto err_dead_proc_or_thread; } @@ -3181,13 +3598,18 @@ err_bad_offset: err_bad_parent: err_copy_data_failed: trace_binder_transaction_failed_buffer_release(t->buffer); - binder_transaction_buffer_release(target_proc, t->buffer, offp); + binder_transaction_buffer_release(target_proc, t->buffer, + buffer_offset, true); if (target_node) binder_dec_node_tmpref(target_node); target_node = NULL; t->buffer->transaction = NULL; binder_alloc_free_buf(&target_proc->alloc, t->buffer); err_binder_alloc_buf_failed: +err_bad_extra_size: + if (secctx) + security_release_secctx(secctx, secctx_sz); +err_get_secctx_failed: kfree(tcomplete); binder_stats_deleted(BINDER_STAT_TRANSACTION_COMPLETE); err_alloc_tcomplete_failed: @@ -3232,16 +3654,13 @@ err_invalid_target_handle: BUG_ON(thread->return_error.cmd != BR_OK); if (in_reply_to) { + binder_restore_priority(current, in_reply_to->saved_priority); thread->return_error.cmd = BR_TRANSACTION_COMPLETE; - binder_enqueue_work(thread->proc, - &thread->return_error.work, - &thread->todo); + binder_enqueue_thread_work(thread, &thread->return_error.work); binder_send_failed_reply(in_reply_to, return_error); } else { thread->return_error.cmd = return_error; - binder_enqueue_work(thread->proc, - &thread->return_error.work, - &thread->todo); + binder_enqueue_thread_work(thread, &thread->return_error.work); } } @@ -3453,7 +3872,7 @@ static int binder_thread_write(struct binder_proc *proc, w = binder_dequeue_work_head_ilocked( &buf_node->async_todo); if (!w) { - buf_node->has_async_transaction = 0; + buf_node->has_async_transaction = false; } else { binder_enqueue_work_ilocked( w, &proc->todo); @@ -3462,7 +3881,7 @@ static int binder_thread_write(struct binder_proc *proc, binder_node_inner_unlock(buf_node); } trace_binder_transaction_buffer_release(buffer); - binder_transaction_buffer_release(proc, buffer, NULL); + binder_transaction_buffer_release(proc, buffer, 0, false); binder_alloc_free_buf(&proc->alloc, buffer); break; } @@ -3551,10 +3970,9 @@ static int binder_thread_write(struct binder_proc *proc, WARN_ON(thread->return_error.cmd != BR_OK); thread->return_error.cmd = BR_ERROR; - binder_enqueue_work( - thread->proc, - &thread->return_error.work, - &thread->todo); + binder_enqueue_thread_work( + thread, + &thread->return_error.work); binder_debug( BINDER_DEBUG_FAILED_TRANSACTION, "%d:%d BC_REQUEST_DEATH_NOTIFICATION failed\n", @@ -3634,9 +4052,9 @@ static int binder_thread_write(struct binder_proc *proc, if (thread->looper & (BINDER_LOOPER_STATE_REGISTERED | BINDER_LOOPER_STATE_ENTERED)) - binder_enqueue_work_ilocked( - &death->work, - &thread->todo); + binder_enqueue_thread_work_ilocked( + thread, + &death->work); else { binder_enqueue_work_ilocked( &death->work, @@ -3691,8 +4109,8 @@ static int binder_thread_write(struct binder_proc *proc, if (thread->looper & (BINDER_LOOPER_STATE_REGISTERED | BINDER_LOOPER_STATE_ENTERED)) - binder_enqueue_work_ilocked( - &death->work, &thread->todo); + binder_enqueue_thread_work_ilocked( + thread, &death->work); else { binder_enqueue_work_ilocked( &death->work, @@ -3823,7 +4241,7 @@ retry: wait_event_interruptible(binder_user_error_wait, binder_stop_on_user_error < 2); } - binder_set_nice(proc->default_priority); + binder_restore_priority(current, proc->default_priority); } if (non_block) { @@ -3840,11 +4258,13 @@ retry: while (1) { uint32_t cmd; - struct binder_transaction_data tr; + struct binder_transaction_data_secctx tr; + struct binder_transaction_data *trd = &tr.transaction_data; struct binder_work *w = NULL; struct list_head *list = NULL; struct binder_transaction *t = NULL; struct binder_thread *t_from; + size_t trsize = sizeof(*trd); binder_inner_proc_lock(proc); if (!binder_worklist_empty_ilocked(&thread->todo)) @@ -3866,6 +4286,8 @@ retry: break; } w = binder_dequeue_work_head_ilocked(list); + if (binder_worklist_empty_ilocked(&thread->todo)) + thread->process_todo = false; switch (w->type) { case BINDER_WORK_TRANSACTION: { @@ -3880,6 +4302,7 @@ retry: binder_inner_proc_unlock(proc); if (put_user(e->cmd, (uint32_t __user *)ptr)) return -EFAULT; + cmd = e->cmd; e->cmd = BR_OK; ptr += sizeof(uint32_t); @@ -4035,45 +4458,47 @@ retry: BUG_ON(t->buffer == NULL); if (t->buffer->target_node) { struct binder_node *target_node = t->buffer->target_node; - - tr.target.ptr = target_node->ptr; - tr.cookie = target_node->cookie; - t->saved_priority = task_nice(current); - if (t->priority < target_node->min_priority && - !(t->flags & TF_ONE_WAY)) - binder_set_nice(t->priority); - else if (!(t->flags & TF_ONE_WAY) || - t->saved_priority > target_node->min_priority) - binder_set_nice(target_node->min_priority); + struct binder_priority node_prio; + + trd->target.ptr = target_node->ptr; + trd->cookie = target_node->cookie; + node_prio.sched_policy = target_node->sched_policy; + node_prio.prio = target_node->min_priority; + binder_transaction_priority(current, t, node_prio, + target_node->inherit_rt); cmd = BR_TRANSACTION; } else { - tr.target.ptr = 0; - tr.cookie = 0; + trd->target.ptr = 0; + trd->cookie = 0; cmd = BR_REPLY; } - tr.code = t->code; - tr.flags = t->flags; - tr.sender_euid = from_kuid(current_user_ns(), t->sender_euid); + trd->code = t->code; + trd->flags = t->flags; + trd->sender_euid = from_kuid(current_user_ns(), t->sender_euid); t_from = binder_get_txn_from(t); if (t_from) { struct task_struct *sender = t_from->proc->tsk; - tr.sender_pid = task_tgid_nr_ns(sender, - task_active_pid_ns(current)); + trd->sender_pid = + task_tgid_nr_ns(sender, + task_active_pid_ns(current)); } else { - tr.sender_pid = 0; + trd->sender_pid = 0; } - tr.data_size = t->buffer->data_size; - tr.offsets_size = t->buffer->offsets_size; - tr.data.ptr.buffer = (binder_uintptr_t) - ((uintptr_t)t->buffer->data + - binder_alloc_get_user_buffer_offset(&proc->alloc)); - tr.data.ptr.offsets = tr.data.ptr.buffer + + trd->data_size = t->buffer->data_size; + trd->offsets_size = t->buffer->offsets_size; + trd->data.ptr.buffer = (uintptr_t)t->buffer->user_data; + trd->data.ptr.offsets = trd->data.ptr.buffer + ALIGN(t->buffer->data_size, sizeof(void *)); + tr.secctx = t->security_ctx; + if (t->security_ctx) { + cmd = BR_TRANSACTION_SEC_CTX; + trsize = sizeof(tr); + } if (put_user(cmd, (uint32_t __user *)ptr)) { if (t_from) binder_thread_dec_tmpref(t_from); @@ -4084,7 +4509,7 @@ retry: return -EFAULT; } ptr += sizeof(uint32_t); - if (copy_to_user(ptr, &tr, sizeof(tr))) { + if (copy_to_user(ptr, &tr, trsize)) { if (t_from) binder_thread_dec_tmpref(t_from); @@ -4093,7 +4518,7 @@ retry: return -EFAULT; } - ptr += sizeof(tr); + ptr += trsize; trace_binder_transaction_received(t); binder_stat_br(proc, thread, cmd); @@ -4101,16 +4526,18 @@ retry: "%d:%d %s %d %d:%d, cmd %d size %zd-%zd ptr %016llx-%016llx\n", proc->pid, thread->pid, (cmd == BR_TRANSACTION) ? "BR_TRANSACTION" : - "BR_REPLY", + (cmd == BR_TRANSACTION_SEC_CTX) ? + "BR_TRANSACTION_SEC_CTX" : "BR_REPLY", t->debug_id, t_from ? t_from->proc->pid : 0, t_from ? t_from->pid : 0, cmd, t->buffer->data_size, t->buffer->offsets_size, - (u64)tr.data.ptr.buffer, (u64)tr.data.ptr.offsets); + (u64)trd->data.ptr.buffer, + (u64)trd->data.ptr.offsets); if (t_from) binder_thread_dec_tmpref(t_from); t->buffer->allow_user_free = 1; - if (cmd == BR_TRANSACTION && !(t->flags & TF_ONE_WAY)) { + if (cmd != BR_REPLY && !(t->flags & TF_ONE_WAY)) { binder_inner_proc_lock(thread->proc); t->to_parent = thread->transaction_stack; t->to_thread = thread; @@ -4222,6 +4649,8 @@ static struct binder_thread *binder_get_thread_ilocked( binder_stats_created(BINDER_STAT_THREAD); thread->proc = proc; thread->pid = current->pid; + get_task_struct(current); + thread->task = current; atomic_set(&thread->tmp_ref, 0); init_waitqueue_head(&thread->wait); INIT_LIST_HEAD(&thread->todo); @@ -4272,6 +4701,7 @@ static void binder_free_thread(struct binder_thread *thread) BUG_ON(!list_empty(&thread->todo)); binder_stats_deleted(BINDER_STAT_THREAD); binder_proc_dec_tmpref(thread->proc); + put_task_struct(thread->task); kfree(thread); } @@ -4452,7 +4882,8 @@ out: return ret; } -static int binder_ioctl_set_ctx_mgr(struct file *filp) +static int binder_ioctl_set_ctx_mgr(struct file *filp, + struct flat_binder_object *fbo) { int ret = 0; struct binder_proc *proc = filp->private_data; @@ -4481,7 +4912,7 @@ static int binder_ioctl_set_ctx_mgr(struct file *filp) } else { context->binder_context_mgr_uid = curr_euid; } - new_node = binder_new_node(proc, NULL); + new_node = binder_new_node(proc, fbo); if (!new_node) { ret = -ENOMEM; goto out; @@ -4499,6 +4930,42 @@ out: return ret; } +static int binder_ioctl_get_node_info_for_ref(struct binder_proc *proc, + struct binder_node_info_for_ref *info) +{ + struct binder_node *node; + struct binder_context *context = proc->context; + __u32 handle = info->handle; + + if (info->strong_count || info->weak_count || info->reserved1 || + info->reserved2 || info->reserved3) { + binder_user_error("%d BINDER_GET_NODE_INFO_FOR_REF: only handle may be non-zero.", + proc->pid); + return -EINVAL; + } + + /* This ioctl may only be used by the context manager */ + mutex_lock(&context->context_mgr_node_lock); + if (!context->binder_context_mgr_node || + context->binder_context_mgr_node->proc != proc) { + mutex_unlock(&context->context_mgr_node_lock); + return -EPERM; + } + mutex_unlock(&context->context_mgr_node_lock); + + node = binder_get_node_from_ref(proc, handle, true, NULL); + if (!node) + return -EINVAL; + + info->strong_count = node->local_strong_refs + + node->internal_strong_refs; + info->weak_count = node->local_weak_refs; + + binder_put_node(node); + + return 0; +} + static int binder_ioctl_get_node_debug_info(struct binder_proc *proc, struct binder_node_debug_info *info) { @@ -4568,8 +5035,20 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) binder_inner_proc_unlock(proc); break; } + case BINDER_SET_CONTEXT_MGR_EXT: { + struct flat_binder_object fbo; + + if (copy_from_user(&fbo, ubuf, sizeof(fbo))) { + ret = -EINVAL; + goto err; + } + ret = binder_ioctl_set_ctx_mgr(filp, &fbo); + if (ret) + goto err; + break; + } case BINDER_SET_CONTEXT_MGR: - ret = binder_ioctl_set_ctx_mgr(filp); + ret = binder_ioctl_set_ctx_mgr(filp, NULL); if (ret) goto err; break; @@ -4593,6 +5072,25 @@ static long binder_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) } break; } + case BINDER_GET_NODE_INFO_FOR_REF: { + struct binder_node_info_for_ref info; + + if (copy_from_user(&info, ubuf, sizeof(info))) { + ret = -EFAULT; + goto err; + } + + ret = binder_ioctl_get_node_info_for_ref(proc, &info); + if (ret < 0) + goto err; + + if (copy_to_user(ubuf, &info, sizeof(info))) { + ret = -EFAULT; + goto err; + } + + break; + } case BINDER_GET_NODE_DEBUG_INFO: { struct binder_node_debug_info info; @@ -4685,7 +5183,9 @@ static int binder_mmap(struct file *filp, struct vm_area_struct *vma) failure_string = "bad vm_flags"; goto err_bad_arg; } - vma->vm_flags = (vma->vm_flags | VM_DONTCOPY) & ~VM_MAYWRITE; + vma->vm_flags |= VM_DONTCOPY | VM_MIXEDMAP; + vma->vm_flags &= ~VM_MAYWRITE; + vma->vm_ops = &binder_vm_ops; vma->vm_private_data = proc; @@ -4698,7 +5198,7 @@ static int binder_mmap(struct file *filp, struct vm_area_struct *vma) return 0; err_bad_arg: - pr_err("binder_mmap: %d %lx-%lx %s failed %d\n", + pr_err("%s: %d %lx-%lx %s failed %d\n", __func__, proc->pid, vma->vm_start, vma->vm_end, failure_string, ret); return ret; } @@ -4708,7 +5208,7 @@ static int binder_open(struct inode *nodp, struct file *filp) struct binder_proc *proc; struct binder_device *binder_dev; - binder_debug(BINDER_DEBUG_OPEN_CLOSE, "binder_open: %d:%d\n", + binder_debug(BINDER_DEBUG_OPEN_CLOSE, "%s: %d:%d\n", __func__, current->group_leader->pid, current->pid); proc = kzalloc(sizeof(*proc), GFP_KERNEL); @@ -4720,7 +5220,14 @@ static int binder_open(struct inode *nodp, struct file *filp) proc->tsk = current->group_leader; mutex_init(&proc->files_lock); INIT_LIST_HEAD(&proc->todo); - proc->default_priority = task_nice(current); + if (binder_supported_policy(current->policy)) { + proc->default_priority.sched_policy = current->policy; + proc->default_priority.prio = current->normal_prio; + } else { + proc->default_priority.sched_policy = SCHED_NORMAL; + proc->default_priority.prio = NICE_TO_PRIO(0); + } + binder_dev = container_of(filp->private_data, struct binder_device, miscdev); proc->context = &binder_dev->context; @@ -4747,7 +5254,7 @@ static int binder_open(struct inode *nodp, struct file *filp) * anyway print all contexts that a given PID has, so this * is not a problem. */ - proc->debugfs_entry = debugfs_create_file(strbuf, S_IRUGO, + proc->debugfs_entry = debugfs_create_file(strbuf, 0444, binder_debugfs_dir_entry_proc, (void *)(unsigned long)proc->pid, &binder_proc_fops); @@ -5014,13 +5521,14 @@ static void print_binder_transaction_ilocked(struct seq_file *m, spin_lock(&t->lock); to_proc = t->to_proc; seq_printf(m, - "%s %d: %pK from %d:%d to %d:%d code %x flags %x pri %ld r%d", + "%s %d: %pK from %d:%d to %d:%d code %x flags %x pri %d:%d r%d", prefix, t->debug_id, t, t->from ? t->from->proc->pid : 0, t->from ? t->from->pid : 0, to_proc ? to_proc->pid : 0, t->to_thread ? t->to_thread->pid : 0, - t->code, t->flags, t->priority, t->need_reply); + t->code, t->flags, t->priority.sched_policy, + t->priority.prio, t->need_reply); spin_unlock(&t->lock); if (proc != to_proc) { @@ -5040,7 +5548,7 @@ static void print_binder_transaction_ilocked(struct seq_file *m, seq_printf(m, " node %d", buffer->target_node->debug_id); seq_printf(m, " size %zd:%zd data %pK\n", buffer->data_size, buffer->offsets_size, - buffer->data); + buffer->user_data); } static void print_binder_work_ilocked(struct seq_file *m, @@ -5138,8 +5646,9 @@ static void print_binder_node_nilocked(struct seq_file *m, hlist_for_each_entry(ref, &node->refs, node_entry) count++; - seq_printf(m, " node %d: u%016llx c%016llx hs %d hw %d ls %d lw %d is %d iw %d tr %d", + seq_printf(m, " node %d: u%016llx c%016llx pri %d:%d hs %d hw %d ls %d lw %d is %d iw %d tr %d", node->debug_id, (u64)node->ptr, (u64)node->cookie, + node->sched_policy, node->min_priority, node->has_strong_ref, node->has_weak_ref, node->local_strong_refs, node->local_weak_refs, node->internal_strong_refs, count, node->tmp_refs); @@ -5189,6 +5698,9 @@ static void print_binder_proc(struct seq_file *m, for (n = rb_first(&proc->nodes); n != NULL; n = rb_next(n)) { struct binder_node *node = rb_entry(n, struct binder_node, rb_node); + if (!print_all && !node->has_async_transaction) + continue; + /* * take a temporary reference on the node so it * survives and isn't removed from the tree @@ -5576,7 +6088,9 @@ static int __init binder_init(void) struct binder_device *device; struct hlist_node *tmp; - binder_alloc_shrinker_init(); + ret = binder_alloc_shrinker_init(); + if (ret) + return ret; atomic_set(&binder_transaction_log.cur, ~0U); atomic_set(&binder_transaction_log_failed.cur, ~0U); @@ -5588,27 +6102,27 @@ static int __init binder_init(void) if (binder_debugfs_dir_entry_root) { debugfs_create_file("state", - S_IRUGO, + 0444, binder_debugfs_dir_entry_root, NULL, &binder_state_fops); debugfs_create_file("stats", - S_IRUGO, + 0444, binder_debugfs_dir_entry_root, NULL, &binder_stats_fops); debugfs_create_file("transactions", - S_IRUGO, + 0444, binder_debugfs_dir_entry_root, NULL, &binder_transactions_fops); debugfs_create_file("transaction_log", - S_IRUGO, + 0444, binder_debugfs_dir_entry_root, &binder_transaction_log, &binder_transaction_log_fops); debugfs_create_file("failed_transaction_log", - S_IRUGO, + 0444, binder_debugfs_dir_entry_root, &binder_transaction_log_failed, &binder_transaction_log_fops); diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index f89ea0866892..1b5a131278bc 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -28,6 +28,8 @@ #include <linux/slab.h> #include <linux/sched.h> #include <linux/list_lru.h> +#include <linux/uaccess.h> +#include <linux/highmem.h> #include "binder_alloc.h" #include "binder_trace.h" @@ -65,9 +67,8 @@ static size_t binder_alloc_buffer_size(struct binder_alloc *alloc, struct binder_buffer *buffer) { if (list_is_last(&buffer->entry, &alloc->buffers)) - return (u8 *)alloc->buffer + - alloc->buffer_size - (u8 *)buffer->data; - return (u8 *)binder_buffer_next(buffer)->data - (u8 *)buffer->data; + return alloc->buffer + alloc->buffer_size - buffer->user_data; + return binder_buffer_next(buffer)->user_data - buffer->user_data; } static void binder_insert_free_buffer(struct binder_alloc *alloc, @@ -117,9 +118,9 @@ static void binder_insert_allocated_buffer_locked( buffer = rb_entry(parent, struct binder_buffer, rb_node); BUG_ON(buffer->free); - if (new_buffer->data < buffer->data) + if (new_buffer->user_data < buffer->user_data) p = &parent->rb_left; - else if (new_buffer->data > buffer->data) + else if (new_buffer->user_data > buffer->user_data) p = &parent->rb_right; else BUG(); @@ -134,17 +135,17 @@ static struct binder_buffer *binder_alloc_prepare_to_free_locked( { struct rb_node *n = alloc->allocated_buffers.rb_node; struct binder_buffer *buffer; - void *kern_ptr; + void __user *uptr; - kern_ptr = (void *)(user_ptr - alloc->user_buffer_offset); + uptr = (void __user *)user_ptr; while (n) { buffer = rb_entry(n, struct binder_buffer, rb_node); BUG_ON(buffer->free); - if (kern_ptr < buffer->data) + if (uptr < buffer->user_data) n = n->rb_left; - else if (kern_ptr > buffer->data) + else if (uptr > buffer->user_data) n = n->rb_right; else { /* @@ -184,12 +185,12 @@ struct binder_buffer *binder_alloc_prepare_to_free(struct binder_alloc *alloc, } static int binder_update_page_range(struct binder_alloc *alloc, int allocate, - void *start, void *end, - struct vm_area_struct *vma) + void __user *start, void __user *end) { - void *page_addr; + void __user *page_addr; unsigned long user_page_addr; struct binder_lru_page *page; + struct vm_area_struct *vma = NULL; struct mm_struct *mm = NULL; bool need_mm = false; @@ -213,11 +214,11 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate, } } - if (!vma && need_mm && mmget_not_zero(alloc->vma_vm_mm)) + if (need_mm && mmget_not_zero(alloc->vma_vm_mm)) mm = alloc->vma_vm_mm; if (mm) { - down_write(&mm->mmap_sem); + down_read(&mm->mmap_sem); vma = alloc->vma; } @@ -260,18 +261,7 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate, page->alloc = alloc; INIT_LIST_HEAD(&page->lru); - ret = map_kernel_range_noflush((unsigned long)page_addr, - PAGE_SIZE, PAGE_KERNEL, - &page->page_ptr); - flush_cache_vmap((unsigned long)page_addr, - (unsigned long)page_addr + PAGE_SIZE); - if (ret != 1) { - pr_err("%d: binder_alloc_buf failed to map page at %pK in kernel\n", - alloc->pid, page_addr); - goto err_map_kernel_failed; - } - user_page_addr = - (uintptr_t)page_addr + alloc->user_buffer_offset; + user_page_addr = (uintptr_t)page_addr; ret = vm_insert_page(vma, user_page_addr, page[0].page_ptr); if (ret) { pr_err("%d: binder_alloc_buf failed to map page at %lx in userspace\n", @@ -279,11 +269,14 @@ static int binder_update_page_range(struct binder_alloc *alloc, int allocate, goto err_vm_insert_page_failed; } + if (index + 1 > alloc->pages_high) + alloc->pages_high = index + 1; + trace_binder_alloc_page_end(alloc, index); /* vm_insert_page does not seem to increment the refcount */ } if (mm) { - up_write(&mm->mmap_sem); + up_read(&mm->mmap_sem); mmput(mm); } return 0; @@ -307,8 +300,6 @@ free_range: continue; err_vm_insert_page_failed: - unmap_kernel_range((unsigned long)page_addr, PAGE_SIZE); -err_map_kernel_failed: __free_page(page->page_ptr); page->page_ptr = NULL; err_alloc_page_failed: @@ -318,7 +309,7 @@ err_page_ptr_cleared: } err_no_vma: if (mm) { - up_write(&mm->mmap_sem); + up_read(&mm->mmap_sem); mmput(mm); } return vma ? -ENOMEM : -ESRCH; @@ -352,18 +343,19 @@ static inline struct vm_area_struct *binder_alloc_get_vma( return vma; } -struct binder_buffer *binder_alloc_new_buf_locked(struct binder_alloc *alloc, - size_t data_size, - size_t offsets_size, - size_t extra_buffers_size, - int is_async) +static struct binder_buffer *binder_alloc_new_buf_locked( + struct binder_alloc *alloc, + size_t data_size, + size_t offsets_size, + size_t extra_buffers_size, + int is_async) { struct rb_node *n = alloc->free_buffers.rb_node; struct binder_buffer *buffer; size_t buffer_size; struct rb_node *best_fit = NULL; - void *has_page_addr; - void *end_page_addr; + void __user *has_page_addr; + void __user *end_page_addr; size_t size, data_offsets_size; int ret; @@ -457,15 +449,15 @@ struct binder_buffer *binder_alloc_new_buf_locked(struct binder_alloc *alloc, "%d: binder_alloc_buf size %zd got buffer %pK size %zd\n", alloc->pid, size, buffer, buffer_size); - has_page_addr = - (void *)(((uintptr_t)buffer->data + buffer_size) & PAGE_MASK); + has_page_addr = (void __user *) + (((uintptr_t)buffer->user_data + buffer_size) & PAGE_MASK); WARN_ON(n && buffer_size != size); end_page_addr = - (void *)PAGE_ALIGN((uintptr_t)buffer->data + size); + (void __user *)PAGE_ALIGN((uintptr_t)buffer->user_data + size); if (end_page_addr > has_page_addr) end_page_addr = has_page_addr; - ret = binder_update_page_range(alloc, 1, - (void *)PAGE_ALIGN((uintptr_t)buffer->data), end_page_addr, NULL); + ret = binder_update_page_range(alloc, 1, (void __user *) + PAGE_ALIGN((uintptr_t)buffer->user_data), end_page_addr); if (ret) return ERR_PTR(ret); @@ -478,7 +470,7 @@ struct binder_buffer *binder_alloc_new_buf_locked(struct binder_alloc *alloc, __func__, alloc->pid); goto err_alloc_buf_struct_failed; } - new_buffer->data = (u8 *)buffer->data + size; + new_buffer->user_data = (u8 __user *)buffer->user_data + size; list_add(&new_buffer->entry, &buffer->entry); new_buffer->free = 1; binder_insert_free_buffer(alloc, new_buffer); @@ -504,9 +496,9 @@ struct binder_buffer *binder_alloc_new_buf_locked(struct binder_alloc *alloc, return buffer; err_alloc_buf_struct_failed: - binder_update_page_range(alloc, 0, - (void *)PAGE_ALIGN((uintptr_t)buffer->data), - end_page_addr, NULL); + binder_update_page_range(alloc, 0, (void __user *) + PAGE_ALIGN((uintptr_t)buffer->user_data), + end_page_addr); return ERR_PTR(-ENOMEM); } @@ -540,14 +532,15 @@ struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc, return buffer; } -static void *buffer_start_page(struct binder_buffer *buffer) +static void __user *buffer_start_page(struct binder_buffer *buffer) { - return (void *)((uintptr_t)buffer->data & PAGE_MASK); + return (void __user *)((uintptr_t)buffer->user_data & PAGE_MASK); } -static void *prev_buffer_end_page(struct binder_buffer *buffer) +static void __user *prev_buffer_end_page(struct binder_buffer *buffer) { - return (void *)(((uintptr_t)(buffer->data) - 1) & PAGE_MASK); + return (void __user *) + (((uintptr_t)(buffer->user_data) - 1) & PAGE_MASK); } static void binder_delete_free_buffer(struct binder_alloc *alloc, @@ -562,7 +555,8 @@ static void binder_delete_free_buffer(struct binder_alloc *alloc, to_free = false; binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC, "%d: merge free, buffer %pK share page with %pK\n", - alloc->pid, buffer->data, prev->data); + alloc->pid, buffer->user_data, + prev->user_data); } if (!list_is_last(&buffer->entry, &alloc->buffers)) { @@ -572,26 +566,26 @@ static void binder_delete_free_buffer(struct binder_alloc *alloc, binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC, "%d: merge free, buffer %pK share page with %pK\n", alloc->pid, - buffer->data, - next->data); + buffer->user_data, + next->user_data); } } - if (PAGE_ALIGNED(buffer->data)) { + if (PAGE_ALIGNED(buffer->user_data)) { binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC, "%d: merge free, buffer start %pK is page aligned\n", - alloc->pid, buffer->data); + alloc->pid, buffer->user_data); to_free = false; } if (to_free) { binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC, "%d: merge free, buffer %pK do not share page with %pK or %pK\n", - alloc->pid, buffer->data, - prev->data, next ? next->data : NULL); + alloc->pid, buffer->user_data, + prev->user_data, + next ? next->user_data : NULL); binder_update_page_range(alloc, 0, buffer_start_page(buffer), - buffer_start_page(buffer) + PAGE_SIZE, - NULL); + buffer_start_page(buffer) + PAGE_SIZE); } list_del(&buffer->entry); kfree(buffer); @@ -615,8 +609,8 @@ static void binder_free_buf_locked(struct binder_alloc *alloc, BUG_ON(buffer->free); BUG_ON(size > buffer_size); BUG_ON(buffer->transaction != NULL); - BUG_ON(buffer->data < alloc->buffer); - BUG_ON(buffer->data > alloc->buffer + alloc->buffer_size); + BUG_ON(buffer->user_data < alloc->buffer); + BUG_ON(buffer->user_data > alloc->buffer + alloc->buffer_size); if (buffer->async_transaction) { alloc->free_async_space += size + sizeof(struct binder_buffer); @@ -627,9 +621,9 @@ static void binder_free_buf_locked(struct binder_alloc *alloc, } binder_update_page_range(alloc, 0, - (void *)PAGE_ALIGN((uintptr_t)buffer->data), - (void *)(((uintptr_t)buffer->data + buffer_size) & PAGE_MASK), - NULL); + (void __user *)PAGE_ALIGN((uintptr_t)buffer->user_data), + (void __user *)(((uintptr_t) + buffer->user_data + buffer_size) & PAGE_MASK)); rb_erase(&buffer->rb_node, &alloc->allocated_buffers); buffer->free = 1; @@ -685,7 +679,6 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc, struct vm_area_struct *vma) { int ret; - struct vm_struct *area; const char *failure_string; struct binder_buffer *buffer; @@ -696,28 +689,9 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc, goto err_already_mapped; } - area = get_vm_area(vma->vm_end - vma->vm_start, VM_ALLOC); - if (area == NULL) { - ret = -ENOMEM; - failure_string = "get_vm_area"; - goto err_get_vm_area_failed; - } - alloc->buffer = area->addr; - alloc->user_buffer_offset = - vma->vm_start - (uintptr_t)alloc->buffer; + alloc->buffer = (void __user *)vma->vm_start; mutex_unlock(&binder_alloc_mmap_lock); -#ifdef CONFIG_CPU_CACHE_VIPT - if (cache_is_vipt_aliasing()) { - while (CACHE_COLOUR( - (vma->vm_start ^ (uint32_t)alloc->buffer))) { - pr_info("%s: %d %lx-%lx maps %pK bad alignment\n", - __func__, alloc->pid, vma->vm_start, - vma->vm_end, alloc->buffer); - vma->vm_start += PAGE_SIZE; - } - } -#endif alloc->pages = kzalloc(sizeof(alloc->pages[0]) * ((vma->vm_end - vma->vm_start) / PAGE_SIZE), GFP_KERNEL); @@ -735,7 +709,7 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc, goto err_alloc_buf_struct_failed; } - buffer->data = alloc->buffer; + buffer->user_data = alloc->buffer; list_add(&buffer->entry, &alloc->buffers); buffer->free = 1; binder_insert_free_buffer(alloc, buffer); @@ -750,9 +724,7 @@ err_alloc_buf_struct_failed: alloc->pages = NULL; err_alloc_pages_failed: mutex_lock(&binder_alloc_mmap_lock); - vfree(alloc->buffer); alloc->buffer = NULL; -err_get_vm_area_failed: err_already_mapped: mutex_unlock(&binder_alloc_mmap_lock); pr_err("%s: %d %lx-%lx %s failed %d\n", __func__, @@ -796,7 +768,7 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc) int i; for (i = 0; i < alloc->buffer_size / PAGE_SIZE; i++) { - void *page_addr; + void __user *page_addr; bool on_lru; if (!alloc->pages[i].page_ptr) @@ -809,12 +781,10 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc) "%s: %d: page %d at %pK %s\n", __func__, alloc->pid, i, page_addr, on_lru ? "on lru" : "active"); - unmap_kernel_range((unsigned long)page_addr, PAGE_SIZE); __free_page(alloc->pages[i].page_ptr); page_count++; } kfree(alloc->pages); - vfree(alloc->buffer); } mutex_unlock(&alloc->mutex); if (alloc->vma_vm_mm) @@ -829,7 +799,7 @@ static void print_binder_buffer(struct seq_file *m, const char *prefix, struct binder_buffer *buffer) { seq_printf(m, "%s %d: %pK size %zd:%zd:%zd %s\n", - prefix, buffer->debug_id, buffer->data, + prefix, buffer->debug_id, buffer->user_data, buffer->data_size, buffer->offsets_size, buffer->extra_buffers_size, buffer->transaction ? "active" : "delivered"); @@ -881,6 +851,7 @@ void binder_alloc_print_pages(struct seq_file *m, } mutex_unlock(&alloc->mutex); seq_printf(m, " pages: %d:%d:%d\n", active, lru, free); + seq_printf(m, " pages high watermark: %zu\n", alloc->pages_high); } /** @@ -961,9 +932,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item, if (vma) { trace_binder_unmap_user_start(alloc, index); - zap_page_range(vma, - page_addr + alloc->user_buffer_offset, - PAGE_SIZE); + zap_page_range(vma, page_addr, PAGE_SIZE); trace_binder_unmap_user_end(alloc, index); } @@ -972,7 +941,6 @@ enum lru_status binder_alloc_free_page(struct list_head *item, trace_binder_unmap_kernel_start(alloc, index); - unmap_kernel_range(page_addr, PAGE_SIZE); __free_page(page->page_ptr); page->page_ptr = NULL; @@ -1008,7 +976,7 @@ binder_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) return ret; } -struct shrinker binder_shrinker = { +static struct shrinker binder_shrinker = { .count_objects = binder_shrink_count, .scan_objects = binder_shrink_scan, .seeks = DEFAULT_SEEKS, @@ -1028,8 +996,184 @@ void binder_alloc_init(struct binder_alloc *alloc) INIT_LIST_HEAD(&alloc->buffers); } -void binder_alloc_shrinker_init(void) +int binder_alloc_shrinker_init(void) +{ + int ret = list_lru_init(&binder_alloc_lru); + + if (ret == 0) { + ret = register_shrinker(&binder_shrinker); + if (ret) + list_lru_destroy(&binder_alloc_lru); + } + return ret; +} + +/** + * check_buffer() - verify that buffer/offset is safe to access + * @alloc: binder_alloc for this proc + * @buffer: binder buffer to be accessed + * @offset: offset into @buffer data + * @bytes: bytes to access from offset + * + * Check that the @offset/@bytes are within the size of the given + * @buffer and that the buffer is currently active and not freeable. + * Offsets must also be multiples of sizeof(u32). The kernel is + * allowed to touch the buffer in two cases: + * + * 1) when the buffer is being created: + * (buffer->free == 0 && buffer->allow_user_free == 0) + * 2) when the buffer is being torn down: + * (buffer->free == 0 && buffer->transaction == NULL). + * + * Return: true if the buffer is safe to access + */ +static inline bool check_buffer(struct binder_alloc *alloc, + struct binder_buffer *buffer, + binder_size_t offset, size_t bytes) +{ + size_t buffer_size = binder_alloc_buffer_size(alloc, buffer); + + return buffer_size >= bytes && + offset <= buffer_size - bytes && + IS_ALIGNED(offset, sizeof(u32)) && + !buffer->free && + (!buffer->allow_user_free || !buffer->transaction); +} + +/** + * binder_alloc_get_page() - get kernel pointer for given buffer offset + * @alloc: binder_alloc for this proc + * @buffer: binder buffer to be accessed + * @buffer_offset: offset into @buffer data + * @pgoffp: address to copy final page offset to + * + * Lookup the struct page corresponding to the address + * at @buffer_offset into @buffer->user_data. If @pgoffp is not + * NULL, the byte-offset into the page is written there. + * + * The caller is responsible to ensure that the offset points + * to a valid address within the @buffer and that @buffer is + * not freeable by the user. Since it can't be freed, we are + * guaranteed that the corresponding elements of @alloc->pages[] + * cannot change. + * + * Return: struct page + */ +static struct page *binder_alloc_get_page(struct binder_alloc *alloc, + struct binder_buffer *buffer, + binder_size_t buffer_offset, + pgoff_t *pgoffp) +{ + binder_size_t buffer_space_offset = buffer_offset + + (buffer->user_data - alloc->buffer); + pgoff_t pgoff = buffer_space_offset & ~PAGE_MASK; + size_t index = buffer_space_offset >> PAGE_SHIFT; + struct binder_lru_page *lru_page; + + lru_page = &alloc->pages[index]; + *pgoffp = pgoff; + return lru_page->page_ptr; +} + +/** + * binder_alloc_copy_user_to_buffer() - copy src user to tgt user + * @alloc: binder_alloc for this proc + * @buffer: binder buffer to be accessed + * @buffer_offset: offset into @buffer data + * @from: userspace pointer to source buffer + * @bytes: bytes to copy + * + * Copy bytes from source userspace to target buffer. + * + * Return: bytes remaining to be copied + */ +unsigned long +binder_alloc_copy_user_to_buffer(struct binder_alloc *alloc, + struct binder_buffer *buffer, + binder_size_t buffer_offset, + const void __user *from, + size_t bytes) +{ + if (!check_buffer(alloc, buffer, buffer_offset, bytes)) + return bytes; + + while (bytes) { + unsigned long size; + unsigned long ret; + struct page *page; + pgoff_t pgoff; + void *kptr; + + page = binder_alloc_get_page(alloc, buffer, + buffer_offset, &pgoff); + size = min_t(size_t, bytes, PAGE_SIZE - pgoff); + kptr = kmap(page) + pgoff; + ret = copy_from_user(kptr, from, size); + kunmap(page); + if (ret) + return bytes - size + ret; + bytes -= size; + from += size; + buffer_offset += size; + } + return 0; +} + +static void binder_alloc_do_buffer_copy(struct binder_alloc *alloc, + bool to_buffer, + struct binder_buffer *buffer, + binder_size_t buffer_offset, + void *ptr, + size_t bytes) { - list_lru_init(&binder_alloc_lru); - register_shrinker(&binder_shrinker); + /* All copies must be 32-bit aligned and 32-bit size */ + BUG_ON(!check_buffer(alloc, buffer, buffer_offset, bytes)); + + while (bytes) { + unsigned long size; + struct page *page; + pgoff_t pgoff; + void *tmpptr; + void *base_ptr; + + page = binder_alloc_get_page(alloc, buffer, + buffer_offset, &pgoff); + size = min_t(size_t, bytes, PAGE_SIZE - pgoff); + base_ptr = kmap_atomic(page); + tmpptr = base_ptr + pgoff; + if (to_buffer) + memcpy(tmpptr, ptr, size); + else + memcpy(ptr, tmpptr, size); + /* + * kunmap_atomic() takes care of flushing the cache + * if this device has VIVT cache arch + */ + kunmap_atomic(base_ptr); + bytes -= size; + pgoff = 0; + ptr = ptr + size; + buffer_offset += size; + } } + +void binder_alloc_copy_to_buffer(struct binder_alloc *alloc, + struct binder_buffer *buffer, + binder_size_t buffer_offset, + void *src, + size_t bytes) +{ + binder_alloc_do_buffer_copy(alloc, true, buffer, buffer_offset, + src, bytes); +} + +void binder_alloc_copy_from_buffer(struct binder_alloc *alloc, + void *dest, + struct binder_buffer *buffer, + binder_size_t buffer_offset, + size_t bytes) +{ + binder_alloc_do_buffer_copy(alloc, false, buffer, buffer_offset, + dest, bytes); +} + diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h index a3ad7683b6f2..b60d161b7a7a 100644 --- a/drivers/android/binder_alloc.h +++ b/drivers/android/binder_alloc.h @@ -22,6 +22,7 @@ #include <linux/vmalloc.h> #include <linux/slab.h> #include <linux/list_lru.h> +#include <uapi/linux/android/binder.h> extern struct list_lru binder_alloc_lru; struct binder_transaction; @@ -30,16 +31,16 @@ struct binder_transaction; * struct binder_buffer - buffer used for binder transactions * @entry: entry alloc->buffers * @rb_node: node for allocated_buffers/free_buffers rb trees - * @free: true if buffer is free - * @allow_user_free: describe the second member of struct blah, - * @async_transaction: describe the second member of struct blah, - * @debug_id: describe the second member of struct blah, - * @transaction: describe the second member of struct blah, - * @target_node: describe the second member of struct blah, - * @data_size: describe the second member of struct blah, - * @offsets_size: describe the second member of struct blah, - * @extra_buffers_size: describe the second member of struct blah, - * @data:i describe the second member of struct blah, + * @free: %true if buffer is free + * @allow_user_free: %true if user is allowed to free buffer + * @async_transaction: %true if buffer is in use for an async txn + * @debug_id: unique ID for debugging + * @transaction: pointer to associated struct binder_transaction + * @target_node: struct binder_node associated with this buffer + * @data_size: size of @transaction data + * @offsets_size: size of array of offsets + * @extra_buffers_size: size of space for other objects (like sg lists) + * @user_data: user pointer to base of buffer space * * Bookkeeping structure for binder transaction buffers */ @@ -58,7 +59,7 @@ struct binder_buffer { size_t data_size; size_t offsets_size; size_t extra_buffers_size; - void *data; + void __user *user_data; }; /** @@ -81,7 +82,6 @@ struct binder_lru_page { * (invariant after init) * @vma_vm_mm: copy of vma->vm_mm (invarient after mmap) * @buffer: base of per-proc address space mapped via mmap - * @user_buffer_offset: offset between user and kernel VAs for buffer * @buffers: list of all buffers for this proc * @free_buffers: rb tree of buffers available for allocation * sorted by size @@ -91,6 +91,7 @@ struct binder_lru_page { * @pages: array of binder_lru_page * @buffer_size: size of address space specified via mmap * @pid: pid for associated binder_proc (invariant after init) + * @pages_high: high watermark of offset in @pages * * Bookkeeping structure for per-proc address space management for binder * buffers. It is normally initialized during binder_init() and binder_mmap() @@ -101,8 +102,7 @@ struct binder_alloc { struct mutex mutex; struct vm_area_struct *vma; struct mm_struct *vma_vm_mm; - void *buffer; - ptrdiff_t user_buffer_offset; + void __user *buffer; struct list_head buffers; struct rb_root free_buffers; struct rb_root allocated_buffers; @@ -111,6 +111,7 @@ struct binder_alloc { size_t buffer_size; uint32_t buffer_free; int pid; + size_t pages_high; }; #ifdef CONFIG_ANDROID_BINDER_IPC_SELFTEST @@ -127,7 +128,7 @@ extern struct binder_buffer *binder_alloc_new_buf(struct binder_alloc *alloc, size_t extra_buffers_size, int is_async); extern void binder_alloc_init(struct binder_alloc *alloc); -void binder_alloc_shrinker_init(void); +extern int binder_alloc_shrinker_init(void); extern void binder_alloc_vma_close(struct binder_alloc *alloc); extern struct binder_buffer * binder_alloc_prepare_to_free(struct binder_alloc *alloc, @@ -160,26 +161,24 @@ binder_alloc_get_free_async_space(struct binder_alloc *alloc) return free_async_space; } -/** - * binder_alloc_get_user_buffer_offset() - get offset between kernel/user addrs - * @alloc: binder_alloc for this proc - * - * Return: the offset between kernel and user-space addresses to use for - * virtual address conversion - */ -static inline ptrdiff_t -binder_alloc_get_user_buffer_offset(struct binder_alloc *alloc) -{ - /* - * user_buffer_offset is constant if vma is set and - * undefined if vma is not set. It is possible to - * get here with !alloc->vma if the target process - * is dying while a transaction is being initiated. - * Returning the old value is ok in this case and - * the transaction will fail. - */ - return alloc->user_buffer_offset; -} +unsigned long +binder_alloc_copy_user_to_buffer(struct binder_alloc *alloc, + struct binder_buffer *buffer, + binder_size_t buffer_offset, + const void __user *from, + size_t bytes); + +void binder_alloc_copy_to_buffer(struct binder_alloc *alloc, + struct binder_buffer *buffer, + binder_size_t buffer_offset, + void *src, + size_t bytes); + +void binder_alloc_copy_from_buffer(struct binder_alloc *alloc, + void *dest, + struct binder_buffer *buffer, + binder_size_t buffer_offset, + size_t bytes); #endif /* _LINUX_BINDER_ALLOC_H */ diff --git a/drivers/android/binder_alloc_selftest.c b/drivers/android/binder_alloc_selftest.c index 8bd7bcef967d..b72708918b06 100644 --- a/drivers/android/binder_alloc_selftest.c +++ b/drivers/android/binder_alloc_selftest.c @@ -102,11 +102,12 @@ static bool check_buffer_pages_allocated(struct binder_alloc *alloc, struct binder_buffer *buffer, size_t size) { - void *page_addr, *end; + void __user *page_addr; + void __user *end; int page_index; - end = (void *)PAGE_ALIGN((uintptr_t)buffer->data + size); - page_addr = buffer->data; + end = (void __user *)PAGE_ALIGN((uintptr_t)buffer->user_data + size); + page_addr = buffer->user_data; for (; page_addr < end; page_addr += PAGE_SIZE) { page_index = (page_addr - alloc->buffer) / PAGE_SIZE; if (!alloc->pages[page_index].page_ptr || diff --git a/drivers/android/binder_trace.h b/drivers/android/binder_trace.h index 76e3b9c8a8a2..7674231af8cb 100644 --- a/drivers/android/binder_trace.h +++ b/drivers/android/binder_trace.h @@ -85,6 +85,30 @@ DEFINE_BINDER_FUNCTION_RETURN_EVENT(binder_ioctl_done); DEFINE_BINDER_FUNCTION_RETURN_EVENT(binder_write_done); DEFINE_BINDER_FUNCTION_RETURN_EVENT(binder_read_done); +TRACE_EVENT(binder_set_priority, + TP_PROTO(int proc, int thread, unsigned int old_prio, + unsigned int desired_prio, unsigned int new_prio), + TP_ARGS(proc, thread, old_prio, new_prio, desired_prio), + + TP_STRUCT__entry( + __field(int, proc) + __field(int, thread) + __field(unsigned int, old_prio) + __field(unsigned int, new_prio) + __field(unsigned int, desired_prio) + ), + TP_fast_assign( + __entry->proc = proc; + __entry->thread = thread; + __entry->old_prio = old_prio; + __entry->new_prio = new_prio; + __entry->desired_prio = desired_prio; + ), + TP_printk("proc=%d thread=%d old=%d => new=%d desired=%d", + __entry->proc, __entry->thread, __entry->old_prio, + __entry->new_prio, __entry->desired_prio) +); + TRACE_EVENT(binder_wait_for_work, TP_PROTO(bool proc_work, bool transaction_stack, bool thread_todo), TP_ARGS(proc_work, transaction_stack, thread_todo), @@ -272,7 +296,7 @@ DEFINE_EVENT(binder_buffer_class, binder_transaction_failed_buffer_release, TRACE_EVENT(binder_update_page_range, TP_PROTO(struct binder_alloc *alloc, bool allocate, - void *start, void *end), + void __user *start, void __user *end), TP_ARGS(alloc, allocate, start, end), TP_STRUCT__entry( __field(int, proc) diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 3da53cc6cf2b..db5ba5786467 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -21,15 +21,49 @@ #include <linux/slab.h> #include <linux/string.h> #include <linux/sched/topology.h> +#include <linux/sched/energy.h> +#include <linux/cpuset.h> -static DEFINE_MUTEX(cpu_scale_mutex); -static DEFINE_PER_CPU(unsigned long, cpu_scale) = SCHED_CAPACITY_SCALE; +DEFINE_PER_CPU(unsigned long, freq_scale) = SCHED_CAPACITY_SCALE; +DEFINE_PER_CPU(unsigned long, max_cpu_freq); +DEFINE_PER_CPU(unsigned long, max_freq_scale) = SCHED_CAPACITY_SCALE; -unsigned long topology_get_cpu_scale(struct sched_domain *sd, int cpu) +void arch_set_freq_scale(struct cpumask *cpus, unsigned long cur_freq, + unsigned long max_freq) { - return per_cpu(cpu_scale, cpu); + unsigned long scale; + int i; + + scale = (cur_freq << SCHED_CAPACITY_SHIFT) / max_freq; + + for_each_cpu(i, cpus) { + per_cpu(freq_scale, i) = scale; + per_cpu(max_cpu_freq, i) = max_freq; + } } +void arch_set_max_freq_scale(struct cpumask *cpus, + unsigned long policy_max_freq) +{ + unsigned long scale, max_freq; + int cpu = cpumask_first(cpus); + + if (cpu > nr_cpu_ids) + return; + + max_freq = per_cpu(max_cpu_freq, cpu); + if (!max_freq) + return; + + scale = (policy_max_freq << SCHED_CAPACITY_SHIFT) / max_freq; + + for_each_cpu(cpu, cpus) + per_cpu(max_freq_scale, cpu) = scale; +} + +static DEFINE_MUTEX(cpu_scale_mutex); +DEFINE_PER_CPU(unsigned long, cpu_scale) = SCHED_CAPACITY_SCALE; + void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity) { per_cpu(cpu_scale, cpu) = capacity; @@ -44,6 +78,9 @@ static ssize_t cpu_capacity_show(struct device *dev, return sprintf(buf, "%lu\n", topology_get_cpu_scale(NULL, cpu->dev.id)); } +static void update_topology_flags_workfn(struct work_struct *work); +static DECLARE_WORK(update_topology_flags_work, update_topology_flags_workfn); + static ssize_t cpu_capacity_store(struct device *dev, struct device_attribute *attr, const char *buf, @@ -54,6 +91,7 @@ static ssize_t cpu_capacity_store(struct device *dev, int i; unsigned long new_capacity; ssize_t ret; + cpumask_var_t mask; if (!count) return 0; @@ -65,10 +103,41 @@ static ssize_t cpu_capacity_store(struct device *dev, return -EINVAL; mutex_lock(&cpu_scale_mutex); - for_each_cpu(i, &cpu_topology[this_cpu].core_sibling) + + if (new_capacity < SCHED_CAPACITY_SCALE) { + int highest_score_cpu = 0; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) { + mutex_unlock(&cpu_scale_mutex); + return -ENOMEM; + } + + cpumask_andnot(mask, cpu_online_mask, + topology_core_cpumask(this_cpu)); + + for_each_cpu(i, mask) { + if (topology_get_cpu_scale(NULL, i) == + SCHED_CAPACITY_SCALE) { + highest_score_cpu = 1; + break; + } + } + + free_cpumask_var(mask); + + if (!highest_score_cpu) { + mutex_unlock(&cpu_scale_mutex); + return -EINVAL; + } + } + + for_each_cpu(i, topology_core_cpumask(this_cpu)) topology_set_cpu_scale(i, new_capacity); mutex_unlock(&cpu_scale_mutex); + if (topology_detect_flags()) + schedule_work(&update_topology_flags_work); + return count; } @@ -93,6 +162,191 @@ static int register_cpu_capacity_sysctl(void) } subsys_initcall(register_cpu_capacity_sysctl); +enum asym_cpucap_type { no_asym, asym_thread, asym_core, asym_die }; +static enum asym_cpucap_type asym_cpucap = no_asym; +enum share_cap_type { no_share_cap, share_cap_thread, share_cap_core, share_cap_die}; +static enum share_cap_type share_cap = no_share_cap; + +#ifdef CONFIG_CPU_FREQ +int detect_share_cap_flag(void) +{ + int cpu; + enum share_cap_type share_cap_level = no_share_cap; + struct cpufreq_policy *policy; + + for_each_possible_cpu(cpu) { + policy = cpufreq_cpu_get(cpu); + + if (!policy) + return 0; + + if (share_cap_level < share_cap_thread && + cpumask_equal(topology_sibling_cpumask(cpu), + policy->related_cpus)) { + share_cap_level = share_cap_thread; + cpufreq_cpu_put(policy); + continue; + } + + if (cpumask_equal(topology_core_cpumask(cpu), + policy->related_cpus)) { + share_cap_level = share_cap_core; + cpufreq_cpu_put(policy); + continue; + } + + if (cpumask_equal(cpu_cpu_mask(cpu), + policy->related_cpus)) { + share_cap_level = share_cap_die; + cpufreq_cpu_put(policy); + continue; + } + + cpufreq_cpu_put(policy); + } + + if (share_cap != share_cap_level) { + share_cap = share_cap_level; + return 1; + } + + return 0; +} +#else +int detect_share_cap_flag(void) { return 0; } +#endif + +/* + * Walk cpu topology to determine sched_domain flags. + * + * SD_ASYM_CPUCAPACITY: Indicates the lowest level that spans all cpu + * capacities found in the system for all cpus, i.e. the flag is set + * at the same level for all systems. The current algorithm implements + * this by looking for higher capacities, which doesn't work for all + * conceivable topology, but don't complicate things until it is + * necessary. + */ +int topology_detect_flags(void) +{ + unsigned long max_capacity, capacity; + enum asym_cpucap_type asym_level = no_asym; + int cpu, die_cpu, core, thread, flags_changed = 0; + + for_each_possible_cpu(cpu) { + max_capacity = 0; + + if (asym_level >= asym_thread) + goto check_core; + + for_each_cpu(thread, topology_sibling_cpumask(cpu)) { + capacity = topology_get_cpu_scale(NULL, thread); + + if (capacity > max_capacity) { + if (max_capacity != 0) + asym_level = asym_thread; + + max_capacity = capacity; + } + } + +check_core: + if (asym_level >= asym_core) + goto check_die; + + for_each_cpu(core, topology_core_cpumask(cpu)) { + capacity = topology_get_cpu_scale(NULL, core); + + if (capacity > max_capacity) { + if (max_capacity != 0) + asym_level = asym_core; + + max_capacity = capacity; + } + } +check_die: + for_each_possible_cpu(die_cpu) { + capacity = topology_get_cpu_scale(NULL, die_cpu); + + if (capacity > max_capacity) { + if (max_capacity != 0) { + asym_level = asym_die; + goto done; + } + } + } + } + +done: + if (asym_cpucap != asym_level) { + asym_cpucap = asym_level; + flags_changed = 1; + pr_debug("topology flag change detected\n"); + } + + if (detect_share_cap_flag()) + flags_changed = 1; + + return flags_changed; +} + +int topology_smt_flags(void) +{ + int flags = 0; + + if (asym_cpucap == asym_thread) + flags |= SD_ASYM_CPUCAPACITY; + + if (share_cap == share_cap_thread) + flags |= SD_SHARE_CAP_STATES; + + return flags; +} + +int topology_core_flags(void) +{ + int flags = 0; + + if (asym_cpucap == asym_core) + flags |= SD_ASYM_CPUCAPACITY; + + if (share_cap == share_cap_core) + flags |= SD_SHARE_CAP_STATES; + + return flags; +} + +int topology_cpu_flags(void) +{ + int flags = 0; + + if (asym_cpucap == asym_die) + flags |= SD_ASYM_CPUCAPACITY; + + if (share_cap == share_cap_die) + flags |= SD_SHARE_CAP_STATES; + + return flags; +} + +static int update_topology = 0; + +int topology_update_cpu_topology(void) +{ + return update_topology; +} + +/* + * Updating the sched_domains can't be done directly from cpufreq callbacks + * due to locking, so queue the work for later. + */ +static void update_topology_flags_workfn(struct work_struct *work) +{ + update_topology = 1; + rebuild_sched_domains(); + pr_debug("sched_domain hierarchy rebuilt, flags updated\n"); + update_topology = 0; +} + static u32 capacity_scale; static u32 *raw_capacity; @@ -115,13 +369,12 @@ void topology_normalize_cpu_scale(void) pr_debug("cpu_capacity: capacity_scale=%u\n", capacity_scale); mutex_lock(&cpu_scale_mutex); for_each_possible_cpu(cpu) { - pr_debug("cpu_capacity: cpu=%d raw_capacity=%u\n", - cpu, raw_capacity[cpu]); capacity = (raw_capacity[cpu] << SCHED_CAPACITY_SHIFT) / capacity_scale; topology_set_cpu_scale(cpu, capacity); - pr_debug("cpu_capacity: CPU%d cpu_capacity=%lu\n", - cpu, topology_get_cpu_scale(NULL, cpu)); + pr_debug("cpu_capacity: CPU%d cpu_capacity=%lu raw_capacity=%u\n", + cpu, topology_get_cpu_scale(NULL, cpu), + raw_capacity[cpu]); } mutex_unlock(&cpu_scale_mutex); } @@ -198,6 +451,9 @@ init_cpu_capacity_callback(struct notifier_block *nb, if (cpumask_empty(cpus_to_visit)) { topology_normalize_cpu_scale(); + init_sched_energy_costs(); + if (topology_detect_flags()) + schedule_work(&update_topology_flags_work); free_raw_capacity(); pr_debug("cpu_capacity: parsing done\n"); schedule_work(&parsing_done_work); @@ -212,6 +468,8 @@ static struct notifier_block init_cpu_capacity_notifier = { static int __init register_cpufreq_notifier(void) { + int ret; + /* * on ACPI-based systems we need to use the default cpu capacity * until we have the necessary code to parse the cpu capacity, so @@ -227,8 +485,13 @@ static int __init register_cpufreq_notifier(void) cpumask_copy(cpus_to_visit, cpu_possible_mask); - return cpufreq_register_notifier(&init_cpu_capacity_notifier, - CPUFREQ_POLICY_NOTIFIER); + ret = cpufreq_register_notifier(&init_cpu_capacity_notifier, + CPUFREQ_POLICY_NOTIFIER); + + if (ret) + free_cpumask_var(cpus_to_visit); + + return ret; } core_initcall(register_cpufreq_notifier); @@ -236,6 +499,7 @@ static void parsing_done_workfn(struct work_struct *work) { cpufreq_unregister_notifier(&init_cpu_capacity_notifier, CPUFREQ_POLICY_NOTIFIER); + free_cpumask_var(cpus_to_visit); } #else diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 0e7fa1f27ad4..e9036d74b86c 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -34,6 +34,7 @@ #include <linux/cpufreq.h> #include <linux/cpuidle.h> #include <linux/timer.h> +#include <linux/wakeup_reason.h> #include "../base.h" #include "power.h" @@ -1487,6 +1488,7 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) pm_callback_t callback = NULL; const char *info = NULL; int error = 0; + char suspend_abort[MAX_SUSPEND_ABORT_LEN]; DECLARE_DPM_WATCHDOG_ON_STACK(wd); TRACE_DEVICE(dev); @@ -1509,6 +1511,9 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) pm_wakeup_event(dev, 0); if (pm_wakeup_pending()) { + pm_get_active_wakeup_sources(suspend_abort, + MAX_SUSPEND_ABORT_LEN); + log_suspend_abort_reason(suspend_abort); dev->power.direct_complete = false; async_error = -EBUSY; goto Complete; diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c index 877b2a1767a5..74d062f8b22a 100644 --- a/drivers/base/power/wakeup.c +++ b/drivers/base/power/wakeup.c @@ -15,6 +15,7 @@ #include <linux/seq_file.h> #include <linux/debugfs.h> #include <linux/pm_wakeirq.h> +#include <linux/types.h> #include <trace/events/power.h> #include "power.h" @@ -811,6 +812,37 @@ void pm_wakeup_dev_event(struct device *dev, unsigned int msec, bool hard) } EXPORT_SYMBOL_GPL(pm_wakeup_dev_event); +void pm_get_active_wakeup_sources(char *pending_wakeup_source, size_t max) +{ + struct wakeup_source *ws, *last_active_ws = NULL; + int len = 0; + bool active = false; + + rcu_read_lock(); + list_for_each_entry_rcu(ws, &wakeup_sources, entry) { + if (ws->active && len < max) { + if (!active) + len += scnprintf(pending_wakeup_source, max, + "Pending Wakeup Sources: "); + len += scnprintf(pending_wakeup_source + len, max - len, + "%s ", ws->name); + active = true; + } else if (!active && + (!last_active_ws || + ktime_to_ns(ws->last_time) > + ktime_to_ns(last_active_ws->last_time))) { + last_active_ws = ws; + } + } + if (!active && last_active_ws) { + scnprintf(pending_wakeup_source, max, + "Last active Wakeup Source: %s", + last_active_ws->name); + } + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(pm_get_active_wakeup_sources); + void pm_print_active_wakeup_sources(void) { struct wakeup_source *ws; @@ -1024,7 +1056,7 @@ static int print_wakeup_source_stats(struct seq_file *m, active_time = 0; } - seq_printf(m, "%-12s\t%lu\t\t%lu\t\t%lu\t\t%lu\t\t%lld\t\t%lld\t\t%lld\t\t%lld\t\t%lld\n", + seq_printf(m, "%-32s\t%lu\t\t%lu\t\t%lu\t\t%lu\t\t%lld\t\t%lld\t\t%lld\t\t%lld\t\t%lld\n", ws->name, active_count, ws->event_count, ws->wakeup_count, ws->expire_count, ktime_to_ms(active_time), ktime_to_ms(total_time), @@ -1045,7 +1077,7 @@ static int wakeup_sources_stats_show(struct seq_file *m, void *unused) struct wakeup_source *ws; int srcuidx; - seq_puts(m, "name\t\tactive_count\tevent_count\twakeup_count\t" + seq_puts(m, "name\t\t\t\t\tactive_count\tevent_count\twakeup_count\t" "expire_count\tactive_since\ttotal_time\tmax_time\t" "last_change\tprevent_suspend_time\n"); diff --git a/drivers/base/syscore.c b/drivers/base/syscore.c index 8d98a329f6ea..96c34a95cc62 100644 --- a/drivers/base/syscore.c +++ b/drivers/base/syscore.c @@ -11,6 +11,7 @@ #include <linux/module.h> #include <linux/suspend.h> #include <trace/events/power.h> +#include <linux/wakeup_reason.h> static LIST_HEAD(syscore_ops_list); static DEFINE_MUTEX(syscore_ops_lock); @@ -75,6 +76,8 @@ int syscore_suspend(void) return 0; err_out: + log_suspend_abort_reason("System core suspend callback %pF failed", + ops->suspend); pr_err("PM: System core suspend callback %pF failed.\n", ops->suspend); list_for_each_entry_continue(ops, &syscore_ops_list, node) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index c6157ccb9498..c518f9336ab3 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -211,7 +211,8 @@ static void __loop_update_dio(struct loop_device *lo, bool dio) * LO_FLAGS_READ_ONLY, both are set from kernel, and losetup * will get updated by ioctl(LOOP_GET_STATUS) */ - blk_mq_freeze_queue(lo->lo_queue); + if (lo->lo_state == Lo_bound) + blk_mq_freeze_queue(lo->lo_queue); lo->use_dio = use_dio; if (use_dio) { queue_flag_clear_unlocked(QUEUE_FLAG_NOMERGES, lo->lo_queue); @@ -220,7 +221,8 @@ static void __loop_update_dio(struct loop_device *lo, bool dio) queue_flag_set_unlocked(QUEUE_FLAG_NOMERGES, lo->lo_queue); lo->lo_flags &= ~LO_FLAGS_DIRECT_IO; } - blk_mq_unfreeze_queue(lo->lo_queue); + if (lo->lo_state == Lo_bound) + blk_mq_unfreeze_queue(lo->lo_queue); } static int @@ -940,6 +942,16 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync) blk_queue_write_cache(lo->lo_queue, true, false); + if (io_is_direct(lo->lo_backing_file) && inode->i_sb->s_bdev) { + /* In case of direct I/O, match underlying block size */ + unsigned short bsize = bdev_logical_block_size( + inode->i_sb->s_bdev); + + blk_queue_logical_block_size(lo->lo_queue, bsize); + blk_queue_physical_block_size(lo->lo_queue, bsize); + blk_queue_io_min(lo->lo_queue, bsize); + } + loop_update_dio(lo); set_capacity(lo->lo_disk, size); bd_set_size(bdev, size << 9); @@ -1378,16 +1390,16 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg) if (arg < 512 || arg > PAGE_SIZE || !is_power_of_2(arg)) return -EINVAL; - if (lo->lo_queue->limits.logical_block_size != arg) { - sync_blockdev(lo->lo_device); - invalidate_bdev(lo->lo_device); - } + if (lo->lo_queue->limits.logical_block_size == arg) + return 0; + + sync_blockdev(lo->lo_device); + invalidate_bdev(lo->lo_device); blk_mq_freeze_queue(lo->lo_queue); /* invalidate_bdev should have truncated all the pages */ - if (lo->lo_queue->limits.logical_block_size != arg && - lo->lo_device->bd_inode->i_mapping->nrpages) { + if (lo->lo_device->bd_inode->i_mapping->nrpages) { err = -EAGAIN; pr_warn("%s: loop%d (%s) has still dirty pages (nrpages=%lu)\n", __func__, lo->lo_number, lo->lo_file_name, @@ -1615,6 +1627,7 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode, arg = (unsigned long) compat_ptr(arg); case LOOP_SET_FD: case LOOP_CHANGE_FD: + case LOOP_SET_BLOCK_SIZE: case LOOP_SET_DIRECT_IO: err = lo_ioctl(bdev, mode, cmd, arg); break; diff --git a/drivers/block/zram/Kconfig b/drivers/block/zram/Kconfig index ac3a31d433b2..99a2c60c7c6f 100644 --- a/drivers/block/zram/Kconfig +++ b/drivers/block/zram/Kconfig @@ -13,10 +13,10 @@ config ZRAM It has several use cases, for example: /tmp storage, use as swap disks and maybe many more. - See zram.txt for more information. + See Documentation/blockdev/zram.txt for more information. config ZRAM_WRITEBACK - bool "Write back incompressible page to backing device" + bool "Write back incompressible or idle page to backing device" depends on ZRAM default n help @@ -25,4 +25,17 @@ config ZRAM_WRITEBACK For this feature, admin should set up backing device via /sys/block/zramX/backing_dev. - See zram.txt for more infomration. + With /sys/block/zramX/{idle,writeback}, application could ask + idle page's writeback to the backing device to save in memory. + + See Documentation/blockdev/zram.txt for more information. + +config ZRAM_MEMORY_TRACKING + bool "Track zRam block status" + depends on ZRAM && DEBUG_FS + help + With this feature, admin can track the state of allocated blocks + of zRAM. Admin could see the information via + /sys/kernel/debug/zram/zramX/block_state. + + See Documentation/blockdev/zram.txt for more information. diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c index 5b8992beffec..cc66daec7bbc 100644 --- a/drivers/block/zram/zcomp.c +++ b/drivers/block/zram/zcomp.c @@ -32,6 +32,9 @@ static const char * const backends[] = { #if IS_ENABLED(CONFIG_CRYPTO_842) "842", #endif +#if IS_ENABLED(CONFIG_CRYPTO_ZSTD) + "zstd", +#endif NULL }; diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 0d906ca8d4f5..07d69851c3f4 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -31,6 +31,7 @@ #include <linux/err.h> #include <linux/idr.h> #include <linux/sysfs.h> +#include <linux/debugfs.h> #include <linux/cpuhotplug.h> #include "zram_drv.h" @@ -44,8 +45,31 @@ static const char *default_compressor = "lzo"; /* Module params (documentation at end) */ static unsigned int num_devices = 1; +/* + * Pages that compress to sizes equals or greater than this are stored + * uncompressed in memory. + */ +static size_t huge_class_size; static void zram_free_page(struct zram *zram, size_t index); +static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, + u32 index, int offset, struct bio *bio); + + +static int zram_slot_trylock(struct zram *zram, u32 index) +{ + return bit_spin_trylock(ZRAM_LOCK, &zram->table[index].flags); +} + +static void zram_slot_lock(struct zram *zram, u32 index) +{ + bit_spin_lock(ZRAM_LOCK, &zram->table[index].flags); +} + +static void zram_slot_unlock(struct zram *zram, u32 index) +{ + bit_spin_unlock(ZRAM_LOCK, &zram->table[index].flags); +} static inline bool init_done(struct zram *zram) { @@ -68,22 +92,22 @@ static void zram_set_handle(struct zram *zram, u32 index, unsigned long handle) } /* flag operations require table entry bit_spin_lock() being held */ -static int zram_test_flag(struct zram *zram, u32 index, +static bool zram_test_flag(struct zram *zram, u32 index, enum zram_pageflags flag) { - return zram->table[index].value & BIT(flag); + return zram->table[index].flags & BIT(flag); } static void zram_set_flag(struct zram *zram, u32 index, enum zram_pageflags flag) { - zram->table[index].value |= BIT(flag); + zram->table[index].flags |= BIT(flag); } static void zram_clear_flag(struct zram *zram, u32 index, enum zram_pageflags flag) { - zram->table[index].value &= ~BIT(flag); + zram->table[index].flags &= ~BIT(flag); } static inline void zram_set_element(struct zram *zram, u32 index, @@ -99,15 +123,22 @@ static unsigned long zram_get_element(struct zram *zram, u32 index) static size_t zram_get_obj_size(struct zram *zram, u32 index) { - return zram->table[index].value & (BIT(ZRAM_FLAG_SHIFT) - 1); + return zram->table[index].flags & (BIT(ZRAM_FLAG_SHIFT) - 1); } static void zram_set_obj_size(struct zram *zram, u32 index, size_t size) { - unsigned long flags = zram->table[index].value >> ZRAM_FLAG_SHIFT; + unsigned long flags = zram->table[index].flags >> ZRAM_FLAG_SHIFT; + + zram->table[index].flags = (flags << ZRAM_FLAG_SHIFT) | size; +} - zram->table[index].value = (flags << ZRAM_FLAG_SHIFT) | size; +static inline bool zram_allocated(struct zram *zram, u32 index) +{ + return zram_get_obj_size(zram, index) || + zram_test_flag(zram, index, ZRAM_SAME) || + zram_test_flag(zram, index, ZRAM_WB); } #if PAGE_SIZE != 4096 @@ -122,14 +153,6 @@ static inline bool is_partial_io(struct bio_vec *bvec) } #endif -static void zram_revalidate_disk(struct zram *zram) -{ - revalidate_disk(zram->disk); - /* revalidate_disk reset the BDI_CAP_STABLE_WRITES so set again */ - zram->disk->queue->backing_dev_info->capabilities |= - BDI_CAP_STABLE_WRITES; -} - /* * Check if request is within bounds and aligned on zram logical blocks. */ @@ -261,17 +284,125 @@ static ssize_t mem_used_max_store(struct device *dev, return len; } +static ssize_t idle_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + struct zram *zram = dev_to_zram(dev); + unsigned long nr_pages = zram->disksize >> PAGE_SHIFT; + int index; + char mode_buf[8]; + ssize_t sz; + + sz = strscpy(mode_buf, buf, sizeof(mode_buf)); + if (sz <= 0) + return -EINVAL; + + /* ignore trailing new line */ + if (mode_buf[sz - 1] == '\n') + mode_buf[sz - 1] = 0x00; + + if (strcmp(mode_buf, "all")) + return -EINVAL; + + down_read(&zram->init_lock); + if (!init_done(zram)) { + up_read(&zram->init_lock); + return -EINVAL; + } + + for (index = 0; index < nr_pages; index++) { + /* + * Do not mark ZRAM_UNDER_WB slot as ZRAM_IDLE to close race. + * See the comment in writeback_store. + */ + zram_slot_lock(zram, index); + if (zram_allocated(zram, index) && + !zram_test_flag(zram, index, ZRAM_UNDER_WB)) + zram_set_flag(zram, index, ZRAM_IDLE); + zram_slot_unlock(zram, index); + } + + up_read(&zram->init_lock); + + return len; +} + #ifdef CONFIG_ZRAM_WRITEBACK -static bool zram_wb_enabled(struct zram *zram) +static ssize_t writeback_limit_enable_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + struct zram *zram = dev_to_zram(dev); + u64 val; + ssize_t ret = -EINVAL; + + if (kstrtoull(buf, 10, &val)) + return ret; + + down_read(&zram->init_lock); + spin_lock(&zram->wb_limit_lock); + zram->wb_limit_enable = val; + spin_unlock(&zram->wb_limit_lock); + up_read(&zram->init_lock); + ret = len; + + return ret; +} + +static ssize_t writeback_limit_enable_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + bool val; + struct zram *zram = dev_to_zram(dev); + + down_read(&zram->init_lock); + spin_lock(&zram->wb_limit_lock); + val = zram->wb_limit_enable; + spin_unlock(&zram->wb_limit_lock); + up_read(&zram->init_lock); + + return scnprintf(buf, PAGE_SIZE, "%d\n", val); +} + +static ssize_t writeback_limit_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) { - return zram->backing_dev; + struct zram *zram = dev_to_zram(dev); + u64 val; + ssize_t ret = -EINVAL; + + if (kstrtoull(buf, 10, &val)) + return ret; + + down_read(&zram->init_lock); + spin_lock(&zram->wb_limit_lock); + zram->bd_wb_limit = val; + spin_unlock(&zram->wb_limit_lock); + up_read(&zram->init_lock); + ret = len; + + return ret; +} + +static ssize_t writeback_limit_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + u64 val; + struct zram *zram = dev_to_zram(dev); + + down_read(&zram->init_lock); + spin_lock(&zram->wb_limit_lock); + val = zram->bd_wb_limit; + spin_unlock(&zram->wb_limit_lock); + up_read(&zram->init_lock); + + return scnprintf(buf, PAGE_SIZE, "%llu\n", val); } static void reset_bdev(struct zram *zram) { struct block_device *bdev; - if (!zram_wb_enabled(zram)) + if (!zram->backing_dev) return; bdev = zram->bdev; @@ -386,7 +517,6 @@ static ssize_t backing_dev_store(struct device *dev, goto out; reset_bdev(zram); - spin_lock_init(&zram->bitmap_lock); zram->old_block_size = old_block_size; zram->bdev = bdev; @@ -416,35 +546,32 @@ out: return err; } -static unsigned long get_entry_bdev(struct zram *zram) +static unsigned long alloc_block_bdev(struct zram *zram) { - unsigned long entry; - - spin_lock(&zram->bitmap_lock); + unsigned long blk_idx = 1; +retry: /* skip 0 bit to confuse zram.handle = 0 */ - entry = find_next_zero_bit(zram->bitmap, zram->nr_pages, 1); - if (entry == zram->nr_pages) { - spin_unlock(&zram->bitmap_lock); + blk_idx = find_next_zero_bit(zram->bitmap, zram->nr_pages, blk_idx); + if (blk_idx == zram->nr_pages) return 0; - } - set_bit(entry, zram->bitmap); - spin_unlock(&zram->bitmap_lock); + if (test_and_set_bit(blk_idx, zram->bitmap)) + goto retry; - return entry; + atomic64_inc(&zram->stats.bd_count); + return blk_idx; } -static void put_entry_bdev(struct zram *zram, unsigned long entry) +static void free_block_bdev(struct zram *zram, unsigned long blk_idx) { int was_set; - spin_lock(&zram->bitmap_lock); - was_set = test_and_clear_bit(entry, zram->bitmap); - spin_unlock(&zram->bitmap_lock); + was_set = test_and_clear_bit(blk_idx, zram->bitmap); WARN_ON_ONCE(!was_set); + atomic64_dec(&zram->stats.bd_count); } -void zram_page_end_io(struct bio *bio) +static void zram_page_end_io(struct bio *bio) { struct page *page = bio->bi_io_vec[0].bv_page; @@ -484,6 +611,172 @@ static int read_from_bdev_async(struct zram *zram, struct bio_vec *bvec, return 1; } +#define HUGE_WRITEBACK 1 +#define IDLE_WRITEBACK 2 + +static ssize_t writeback_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + struct zram *zram = dev_to_zram(dev); + unsigned long nr_pages = zram->disksize >> PAGE_SHIFT; + unsigned long index; + struct bio bio; + struct bio_vec bio_vec; + struct page *page; + ssize_t ret, sz; + char mode_buf[8]; + int mode = -1; + unsigned long blk_idx = 0; + + sz = strscpy(mode_buf, buf, sizeof(mode_buf)); + if (sz <= 0) + return -EINVAL; + + /* ignore trailing newline */ + if (mode_buf[sz - 1] == '\n') + mode_buf[sz - 1] = 0x00; + + if (!strcmp(mode_buf, "idle")) + mode = IDLE_WRITEBACK; + else if (!strcmp(mode_buf, "huge")) + mode = HUGE_WRITEBACK; + + if (mode == -1) + return -EINVAL; + + down_read(&zram->init_lock); + if (!init_done(zram)) { + ret = -EINVAL; + goto release_init_lock; + } + + if (!zram->backing_dev) { + ret = -ENODEV; + goto release_init_lock; + } + + page = alloc_page(GFP_KERNEL); + if (!page) { + ret = -ENOMEM; + goto release_init_lock; + } + + for (index = 0; index < nr_pages; index++) { + struct bio_vec bvec; + + bvec.bv_page = page; + bvec.bv_len = PAGE_SIZE; + bvec.bv_offset = 0; + + spin_lock(&zram->wb_limit_lock); + if (zram->wb_limit_enable && !zram->bd_wb_limit) { + spin_unlock(&zram->wb_limit_lock); + ret = -EIO; + break; + } + spin_unlock(&zram->wb_limit_lock); + + if (!blk_idx) { + blk_idx = alloc_block_bdev(zram); + if (!blk_idx) { + ret = -ENOSPC; + break; + } + } + + zram_slot_lock(zram, index); + if (!zram_allocated(zram, index)) + goto next; + + if (zram_test_flag(zram, index, ZRAM_WB) || + zram_test_flag(zram, index, ZRAM_SAME) || + zram_test_flag(zram, index, ZRAM_UNDER_WB)) + goto next; + + if (mode == IDLE_WRITEBACK && + !zram_test_flag(zram, index, ZRAM_IDLE)) + goto next; + if (mode == HUGE_WRITEBACK && + !zram_test_flag(zram, index, ZRAM_HUGE)) + goto next; + /* + * Clearing ZRAM_UNDER_WB is duty of caller. + * IOW, zram_free_page never clear it. + */ + zram_set_flag(zram, index, ZRAM_UNDER_WB); + /* Need for hugepage writeback racing */ + zram_set_flag(zram, index, ZRAM_IDLE); + zram_slot_unlock(zram, index); + if (zram_bvec_read(zram, &bvec, index, 0, NULL)) { + zram_slot_lock(zram, index); + zram_clear_flag(zram, index, ZRAM_UNDER_WB); + zram_clear_flag(zram, index, ZRAM_IDLE); + zram_slot_unlock(zram, index); + continue; + } + + bio_init(&bio, &bio_vec, 1); + bio_set_dev(&bio, zram->bdev); + bio.bi_iter.bi_sector = blk_idx * (PAGE_SIZE >> 9); + bio.bi_opf = REQ_OP_WRITE | REQ_SYNC; + + bio_add_page(&bio, bvec.bv_page, bvec.bv_len, + bvec.bv_offset); + /* + * XXX: A single page IO would be inefficient for write + * but it would be not bad as starter. + */ + ret = submit_bio_wait(&bio); + if (ret) { + zram_slot_lock(zram, index); + zram_clear_flag(zram, index, ZRAM_UNDER_WB); + zram_clear_flag(zram, index, ZRAM_IDLE); + zram_slot_unlock(zram, index); + continue; + } + + atomic64_inc(&zram->stats.bd_writes); + /* + * We released zram_slot_lock so need to check if the slot was + * changed. If there is freeing for the slot, we can catch it + * easily by zram_allocated. + * A subtle case is the slot is freed/reallocated/marked as + * ZRAM_IDLE again. To close the race, idle_store doesn't + * mark ZRAM_IDLE once it found the slot was ZRAM_UNDER_WB. + * Thus, we could close the race by checking ZRAM_IDLE bit. + */ + zram_slot_lock(zram, index); + if (!zram_allocated(zram, index) || + !zram_test_flag(zram, index, ZRAM_IDLE)) { + zram_clear_flag(zram, index, ZRAM_UNDER_WB); + zram_clear_flag(zram, index, ZRAM_IDLE); + goto next; + } + + zram_free_page(zram, index); + zram_clear_flag(zram, index, ZRAM_UNDER_WB); + zram_set_flag(zram, index, ZRAM_WB); + zram_set_element(zram, index, blk_idx); + blk_idx = 0; + atomic64_inc(&zram->stats.pages_stored); + spin_lock(&zram->wb_limit_lock); + if (zram->wb_limit_enable && zram->bd_wb_limit > 0) + zram->bd_wb_limit -= 1UL << (PAGE_SHIFT - 12); + spin_unlock(&zram->wb_limit_lock); +next: + zram_slot_unlock(zram, index); + } + + if (blk_idx) + free_block_bdev(zram, blk_idx); + ret = len; + __free_page(page); +release_init_lock: + up_read(&zram->init_lock); + + return ret; +} + struct zram_work { struct work_struct work; struct zram *zram; @@ -537,82 +830,131 @@ static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec, static int read_from_bdev(struct zram *zram, struct bio_vec *bvec, unsigned long entry, struct bio *parent, bool sync) { + atomic64_inc(&zram->stats.bd_reads); if (sync) return read_from_bdev_sync(zram, bvec, entry, parent); else return read_from_bdev_async(zram, bvec, entry, parent); } +#else +static inline void reset_bdev(struct zram *zram) {}; +static int read_from_bdev(struct zram *zram, struct bio_vec *bvec, + unsigned long entry, struct bio *parent, bool sync) +{ + return -EIO; +} + +static void free_block_bdev(struct zram *zram, unsigned long blk_idx) {}; +#endif + +#ifdef CONFIG_ZRAM_MEMORY_TRACKING + +static struct dentry *zram_debugfs_root; + +static void zram_debugfs_create(void) +{ + zram_debugfs_root = debugfs_create_dir("zram", NULL); +} -static int write_to_bdev(struct zram *zram, struct bio_vec *bvec, - u32 index, struct bio *parent, - unsigned long *pentry) +static void zram_debugfs_destroy(void) { - struct bio *bio; - unsigned long entry; + debugfs_remove_recursive(zram_debugfs_root); +} - bio = bio_alloc(GFP_ATOMIC, 1); - if (!bio) +static void zram_accessed(struct zram *zram, u32 index) +{ + zram_clear_flag(zram, index, ZRAM_IDLE); + zram->table[index].ac_time = ktime_get_boottime(); +} + +static ssize_t read_block_state(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + char *kbuf; + ssize_t index, written = 0; + struct zram *zram = file->private_data; + unsigned long nr_pages = zram->disksize >> PAGE_SHIFT; + struct timespec64 ts; + + kbuf = kvmalloc(count, GFP_KERNEL); + if (!kbuf) return -ENOMEM; - entry = get_entry_bdev(zram); - if (!entry) { - bio_put(bio); - return -ENOSPC; + down_read(&zram->init_lock); + if (!init_done(zram)) { + up_read(&zram->init_lock); + kvfree(kbuf); + return -EINVAL; } - bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9); - bio_set_dev(bio, zram->bdev); - if (!bio_add_page(bio, bvec->bv_page, bvec->bv_len, - bvec->bv_offset)) { - bio_put(bio); - put_entry_bdev(zram, entry); - return -EIO; - } + for (index = *ppos; index < nr_pages; index++) { + int copied; - if (!parent) { - bio->bi_opf = REQ_OP_WRITE | REQ_SYNC; - bio->bi_end_io = zram_page_end_io; - } else { - bio->bi_opf = parent->bi_opf; - bio_chain(bio, parent); + zram_slot_lock(zram, index); + if (!zram_allocated(zram, index)) + goto next; + + ts = ktime_to_timespec64(zram->table[index].ac_time); + copied = snprintf(kbuf + written, count, + "%12zd %12lld.%06lu %c%c%c%c\n", + index, (s64)ts.tv_sec, + ts.tv_nsec / NSEC_PER_USEC, + zram_test_flag(zram, index, ZRAM_SAME) ? 's' : '.', + zram_test_flag(zram, index, ZRAM_WB) ? 'w' : '.', + zram_test_flag(zram, index, ZRAM_HUGE) ? 'h' : '.', + zram_test_flag(zram, index, ZRAM_IDLE) ? 'i' : '.'); + + if (count < copied) { + zram_slot_unlock(zram, index); + break; + } + written += copied; + count -= copied; +next: + zram_slot_unlock(zram, index); + *ppos += 1; } - submit_bio(bio); - *pentry = entry; + up_read(&zram->init_lock); + if (copy_to_user(buf, kbuf, written)) + written = -EFAULT; + kvfree(kbuf); - return 0; + return written; } -static void zram_wb_clear(struct zram *zram, u32 index) +static const struct file_operations proc_zram_block_state_op = { + .open = simple_open, + .read = read_block_state, + .llseek = default_llseek, +}; + +static void zram_debugfs_register(struct zram *zram) { - unsigned long entry; + if (!zram_debugfs_root) + return; - zram_clear_flag(zram, index, ZRAM_WB); - entry = zram_get_element(zram, index); - zram_set_element(zram, index, 0); - put_entry_bdev(zram, entry); + zram->debugfs_dir = debugfs_create_dir(zram->disk->disk_name, + zram_debugfs_root); + debugfs_create_file("block_state", 0400, zram->debugfs_dir, + zram, &proc_zram_block_state_op); } -#else -static bool zram_wb_enabled(struct zram *zram) { return false; } -static inline void reset_bdev(struct zram *zram) {}; -static int write_to_bdev(struct zram *zram, struct bio_vec *bvec, - u32 index, struct bio *parent, - unsigned long *pentry) - +static void zram_debugfs_unregister(struct zram *zram) { - return -EIO; + debugfs_remove_recursive(zram->debugfs_dir); } - -static int read_from_bdev(struct zram *zram, struct bio_vec *bvec, - unsigned long entry, struct bio *parent, bool sync) +#else +static void zram_debugfs_create(void) {}; +static void zram_debugfs_destroy(void) {}; +static void zram_accessed(struct zram *zram, u32 index) { - return -EIO; -} -static void zram_wb_clear(struct zram *zram, u32 index) {} + zram_clear_flag(zram, index, ZRAM_IDLE); +}; +static void zram_debugfs_register(struct zram *zram) {}; +static void zram_debugfs_unregister(struct zram *zram) {}; #endif - /* * We switched to per-cpu streams and this attr is not needed anymore. * However, we will keep it around for some time, because: @@ -731,19 +1073,40 @@ static ssize_t mm_stat_show(struct device *dev, max_used = atomic_long_read(&zram->stats.max_used_pages); ret = scnprintf(buf, PAGE_SIZE, - "%8llu %8llu %8llu %8lu %8ld %8llu %8lu\n", + "%8llu %8llu %8llu %8lu %8ld %8llu %8lu %8llu\n", orig_size << PAGE_SHIFT, (u64)atomic64_read(&zram->stats.compr_data_size), mem_used << PAGE_SHIFT, zram->limit_pages << PAGE_SHIFT, max_used << PAGE_SHIFT, (u64)atomic64_read(&zram->stats.same_pages), - pool_stats.pages_compacted); + pool_stats.pages_compacted, + (u64)atomic64_read(&zram->stats.huge_pages)); up_read(&zram->init_lock); return ret; } +#ifdef CONFIG_ZRAM_WRITEBACK +#define FOUR_K(x) ((x) * (1 << (PAGE_SHIFT - 12))) +static ssize_t bd_stat_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct zram *zram = dev_to_zram(dev); + ssize_t ret; + + down_read(&zram->init_lock); + ret = scnprintf(buf, PAGE_SIZE, + "%8llu %8llu %8llu\n", + FOUR_K((u64)atomic64_read(&zram->stats.bd_count)), + FOUR_K((u64)atomic64_read(&zram->stats.bd_reads)), + FOUR_K((u64)atomic64_read(&zram->stats.bd_writes))); + up_read(&zram->init_lock); + + return ret; +} +#endif + static ssize_t debug_stat_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -753,9 +1116,10 @@ static ssize_t debug_stat_show(struct device *dev, down_read(&zram->init_lock); ret = scnprintf(buf, PAGE_SIZE, - "version: %d\n%8llu\n", + "version: %d\n%8llu %8llu\n", version, - (u64)atomic64_read(&zram->stats.writestall)); + (u64)atomic64_read(&zram->stats.writestall), + (u64)atomic64_read(&zram->stats.miss_free)); up_read(&zram->init_lock); return ret; @@ -763,18 +1127,11 @@ static ssize_t debug_stat_show(struct device *dev, static DEVICE_ATTR_RO(io_stat); static DEVICE_ATTR_RO(mm_stat); +#ifdef CONFIG_ZRAM_WRITEBACK +static DEVICE_ATTR_RO(bd_stat); +#endif static DEVICE_ATTR_RO(debug_stat); -static void zram_slot_lock(struct zram *zram, u32 index) -{ - bit_spin_lock(ZRAM_ACCESS, &zram->table[index].value); -} - -static void zram_slot_unlock(struct zram *zram, u32 index) -{ - bit_spin_unlock(ZRAM_ACCESS, &zram->table[index].value); -} - static void zram_meta_free(struct zram *zram, u64 disksize) { size_t num_pages = disksize >> PAGE_SHIFT; @@ -803,6 +1160,8 @@ static bool zram_meta_alloc(struct zram *zram, u64 disksize) return false; } + if (!huge_class_size) + huge_class_size = zs_huge_class_size(zram->mem_pool); return true; } @@ -815,10 +1174,21 @@ static void zram_free_page(struct zram *zram, size_t index) { unsigned long handle; - if (zram_wb_enabled(zram) && zram_test_flag(zram, index, ZRAM_WB)) { - zram_wb_clear(zram, index); - atomic64_dec(&zram->stats.pages_stored); - return; +#ifdef CONFIG_ZRAM_MEMORY_TRACKING + zram->table[index].ac_time = 0; +#endif + if (zram_test_flag(zram, index, ZRAM_IDLE)) + zram_clear_flag(zram, index, ZRAM_IDLE); + + if (zram_test_flag(zram, index, ZRAM_HUGE)) { + zram_clear_flag(zram, index, ZRAM_HUGE); + atomic64_dec(&zram->stats.huge_pages); + } + + if (zram_test_flag(zram, index, ZRAM_WB)) { + zram_clear_flag(zram, index, ZRAM_WB); + free_block_bdev(zram, zram_get_element(zram, index)); + goto out; } /* @@ -827,10 +1197,8 @@ static void zram_free_page(struct zram *zram, size_t index) */ if (zram_test_flag(zram, index, ZRAM_SAME)) { zram_clear_flag(zram, index, ZRAM_SAME); - zram_set_element(zram, index, 0); atomic64_dec(&zram->stats.same_pages); - atomic64_dec(&zram->stats.pages_stored); - return; + goto out; } handle = zram_get_handle(zram, index); @@ -841,10 +1209,12 @@ static void zram_free_page(struct zram *zram, size_t index) atomic64_sub(zram_get_obj_size(zram, index), &zram->stats.compr_data_size); +out: atomic64_dec(&zram->stats.pages_stored); - zram_set_handle(zram, index, 0); zram_set_obj_size(zram, index, 0); + WARN_ON_ONCE(zram->table[index].flags & + ~(1UL << ZRAM_LOCK | 1UL << ZRAM_UNDER_WB)); } static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index, @@ -855,24 +1225,20 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index, unsigned int size; void *src, *dst; - if (zram_wb_enabled(zram)) { - zram_slot_lock(zram, index); - if (zram_test_flag(zram, index, ZRAM_WB)) { - struct bio_vec bvec; - - zram_slot_unlock(zram, index); + zram_slot_lock(zram, index); + if (zram_test_flag(zram, index, ZRAM_WB)) { + struct bio_vec bvec; - bvec.bv_page = page; - bvec.bv_len = PAGE_SIZE; - bvec.bv_offset = 0; - return read_from_bdev(zram, &bvec, - zram_get_element(zram, index), - bio, partial_io); - } zram_slot_unlock(zram, index); + + bvec.bv_page = page; + bvec.bv_len = PAGE_SIZE; + bvec.bv_offset = 0; + return read_from_bdev(zram, &bvec, + zram_get_element(zram, index), + bio, partial_io); } - zram_slot_lock(zram, index); handle = zram_get_handle(zram, index); if (!handle || zram_test_flag(zram, index, ZRAM_SAME)) { unsigned long value; @@ -957,7 +1323,6 @@ static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec, struct page *page = bvec->bv_page; unsigned long element = 0; enum zram_pageflags flags = 0; - bool allow_wb = true; mem = kmap_atomic(page); if (page_same_filled(mem, &element)) { @@ -982,21 +1347,8 @@ compress_again: return ret; } - if (unlikely(comp_len > max_zpage_size)) { - if (zram_wb_enabled(zram) && allow_wb) { - zcomp_stream_put(zram->comp); - ret = write_to_bdev(zram, bvec, index, bio, &element); - if (!ret) { - flags = ZRAM_WB; - ret = 1; - goto out; - } - allow_wb = false; - goto compress_again; - } + if (comp_len >= huge_class_size) comp_len = PAGE_SIZE; - } - /* * handle allocation has 2 paths: * a) fast path is executed with preemption disabled (for @@ -1056,6 +1408,11 @@ out: zram_slot_lock(zram, index); zram_free_page(zram, index); + if (comp_len == PAGE_SIZE) { + zram_set_flag(zram, index, ZRAM_HUGE); + atomic64_inc(&zram->stats.huge_pages); + } + if (flags) { zram_set_flag(zram, index, flags); zram_set_element(zram, index, element); @@ -1176,6 +1533,10 @@ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index, generic_end_io_acct(q, rw_acct, &zram->disk->part0, start_time); + zram_slot_lock(zram, index); + zram_accessed(zram, index); + zram_slot_unlock(zram, index); + if (unlikely(ret < 0)) { if (!is_write) atomic64_inc(&zram->stats.failed_reads); @@ -1260,10 +1621,14 @@ static void zram_slot_free_notify(struct block_device *bdev, zram = bdev->bd_disk->private_data; - zram_slot_lock(zram, index); + atomic64_inc(&zram->stats.notify_free); + if (!zram_slot_trylock(zram, index)) { + atomic64_inc(&zram->stats.miss_free); + return; + } + zram_free_page(zram, index); zram_slot_unlock(zram, index); - atomic64_inc(&zram->stats.notify_free); } static int zram_rw_page(struct block_device *bdev, sector_t sector, @@ -1382,7 +1747,8 @@ static ssize_t disksize_store(struct device *dev, zram->comp = comp; zram->disksize = disksize; set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT); - zram_revalidate_disk(zram); + + revalidate_disk(zram->disk); up_write(&zram->init_lock); return len; @@ -1429,7 +1795,7 @@ static ssize_t reset_store(struct device *dev, /* Make sure all the pending I/O are finished */ fsync_bdev(bdev); zram_reset_device(zram); - zram_revalidate_disk(zram); + revalidate_disk(zram->disk); bdput(bdev); mutex_lock(&bdev->bd_mutex); @@ -1467,10 +1833,14 @@ static DEVICE_ATTR_RO(initstate); static DEVICE_ATTR_WO(reset); static DEVICE_ATTR_WO(mem_limit); static DEVICE_ATTR_WO(mem_used_max); +static DEVICE_ATTR_WO(idle); static DEVICE_ATTR_RW(max_comp_streams); static DEVICE_ATTR_RW(comp_algorithm); #ifdef CONFIG_ZRAM_WRITEBACK static DEVICE_ATTR_RW(backing_dev); +static DEVICE_ATTR_WO(writeback); +static DEVICE_ATTR_RW(writeback_limit); +static DEVICE_ATTR_RW(writeback_limit_enable); #endif static struct attribute *zram_disk_attrs[] = { @@ -1480,13 +1850,20 @@ static struct attribute *zram_disk_attrs[] = { &dev_attr_compact.attr, &dev_attr_mem_limit.attr, &dev_attr_mem_used_max.attr, + &dev_attr_idle.attr, &dev_attr_max_comp_streams.attr, &dev_attr_comp_algorithm.attr, #ifdef CONFIG_ZRAM_WRITEBACK &dev_attr_backing_dev.attr, + &dev_attr_writeback.attr, + &dev_attr_writeback_limit.attr, + &dev_attr_writeback_limit_enable.attr, #endif &dev_attr_io_stat.attr, &dev_attr_mm_stat.attr, +#ifdef CONFIG_ZRAM_WRITEBACK + &dev_attr_bd_stat.attr, +#endif &dev_attr_debug_stat.attr, NULL, }; @@ -1520,7 +1897,9 @@ static int zram_add(void) device_id = ret; init_rwsem(&zram->init_lock); - +#ifdef CONFIG_ZRAM_WRITEBACK + spin_lock_init(&zram->wb_limit_lock); +#endif queue = blk_alloc_queue(GFP_KERNEL); if (!queue) { pr_err("Error allocating disk queue for device %d\n", @@ -1553,6 +1932,7 @@ static int zram_add(void) /* zram devices sort of resembles non-rotational disks */ queue_flag_set_unlocked(QUEUE_FLAG_NONROT, zram->disk->queue); queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, zram->disk->queue); + /* * To ensure that we always get PAGE_SIZE aligned * and n*PAGE_SIZED sized I/O requests. @@ -1577,11 +1957,15 @@ static int zram_add(void) if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE) blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX); + zram->disk->queue->backing_dev_info->capabilities |= + BDI_CAP_STABLE_WRITES; + disk_to_dev(zram->disk)->groups = zram_disk_attr_groups; add_disk(zram->disk); strlcpy(zram->compressor, default_compressor, sizeof(zram->compressor)); + zram_debugfs_register(zram); pr_info("Added device: %s\n", zram->disk->disk_name); return device_id; @@ -1612,6 +1996,8 @@ static int zram_remove(struct zram *zram) zram->claim = true; mutex_unlock(&bdev->bd_mutex); + zram_debugfs_unregister(zram); + /* Make sure all the pending I/O are finished */ fsync_bdev(bdev); zram_reset_device(zram); @@ -1619,8 +2005,8 @@ static int zram_remove(struct zram *zram) pr_info("Removed device: %s\n", zram->disk->disk_name); - blk_cleanup_queue(zram->disk->queue); del_gendisk(zram->disk); + blk_cleanup_queue(zram->disk->queue); put_disk(zram->disk); kfree(zram); return 0; @@ -1705,6 +2091,7 @@ static void destroy_devices(void) { class_unregister(&zram_control_class); idr_for_each(&zram_index_idr, &zram_remove_cb, NULL); + zram_debugfs_destroy(); idr_destroy(&zram_index_idr); unregister_blkdev(zram_major, "zram"); cpuhp_remove_multi_state(CPUHP_ZCOMP_PREPARE); @@ -1726,6 +2113,7 @@ static int __init zram_init(void) return ret; } + zram_debugfs_create(); zram_major = register_blkdev(0, "zram"); if (zram_major <= 0) { pr_err("Unable to get major number\n"); diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index 31762db861e3..29af8d024b47 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -21,22 +21,6 @@ #include "zcomp.h" -/*-- Configurable parameters */ - -/* - * Pages that compress to size greater than this are stored - * uncompressed in memory. - */ -static const size_t max_zpage_size = PAGE_SIZE / 4 * 3; - -/* - * NOTE: max_zpage_size must be less than or equal to: - * ZS_MAX_ALLOC_SIZE. Otherwise, zs_malloc() would - * always return failure. - */ - -/*-- End of configurable params */ - #define SECTOR_SHIFT 9 #define SECTORS_PER_PAGE_SHIFT (PAGE_SHIFT - SECTOR_SHIFT) #define SECTORS_PER_PAGE (1 << SECTORS_PER_PAGE_SHIFT) @@ -47,7 +31,7 @@ static const size_t max_zpage_size = PAGE_SIZE / 4 * 3; /* - * The lower ZRAM_FLAG_SHIFT bits of table.value is for + * The lower ZRAM_FLAG_SHIFT bits of table.flags is for * object size (excluding header), the higher bits is for * zram_pageflags. * @@ -58,12 +42,15 @@ static const size_t max_zpage_size = PAGE_SIZE / 4 * 3; */ #define ZRAM_FLAG_SHIFT 24 -/* Flags for zram pages (table[page_no].value) */ +/* Flags for zram pages (table[page_no].flags) */ enum zram_pageflags { - /* Page consists the same element */ - ZRAM_SAME = ZRAM_FLAG_SHIFT, - ZRAM_ACCESS, /* page is now accessed */ + /* zram slot is locked */ + ZRAM_LOCK = ZRAM_FLAG_SHIFT, + ZRAM_SAME, /* Page consists the same element */ ZRAM_WB, /* page is stored on backing_device */ + ZRAM_UNDER_WB, /* page is under writeback */ + ZRAM_HUGE, /* Incompressible page */ + ZRAM_IDLE, /* not accessed page since last idle marking */ __NR_ZRAM_PAGEFLAGS, }; @@ -76,7 +63,10 @@ struct zram_table_entry { unsigned long handle; unsigned long element; }; - unsigned long value; + unsigned long flags; +#ifdef CONFIG_ZRAM_MEMORY_TRACKING + ktime_t ac_time; +#endif }; struct zram_stats { @@ -88,9 +78,16 @@ struct zram_stats { atomic64_t invalid_io; /* non-page-aligned I/O requests */ atomic64_t notify_free; /* no. of swap slot free notifications */ atomic64_t same_pages; /* no. of same element filled pages */ + atomic64_t huge_pages; /* no. of huge pages */ atomic64_t pages_stored; /* no. of pages currently stored */ atomic_long_t max_used_pages; /* no. of maximum pages stored */ atomic64_t writestall; /* no. of write slow paths */ + atomic64_t miss_free; /* no. of missed free */ +#ifdef CONFIG_ZRAM_WRITEBACK + atomic64_t bd_count; /* no. of pages in backing device */ + atomic64_t bd_reads; /* no. of reads from backing device */ + atomic64_t bd_writes; /* no. of writes from backing device */ +#endif }; struct zram { @@ -116,13 +113,18 @@ struct zram { * zram is claimed so open request will be failed */ bool claim; /* Protected by bdev->bd_mutex */ -#ifdef CONFIG_ZRAM_WRITEBACK struct file *backing_dev; +#ifdef CONFIG_ZRAM_WRITEBACK + spinlock_t wb_limit_lock; + bool wb_limit_enable; + u64 bd_wb_limit; struct block_device *bdev; unsigned int old_block_size; unsigned long *bitmap; unsigned long nr_pages; - spinlock_t bitmap_lock; +#endif +#ifdef CONFIG_ZRAM_MEMORY_TRACKING + struct dentry *debugfs_dir; #endif }; #endif diff --git a/drivers/char/ipmi/ipmi_poweroff.c b/drivers/char/ipmi/ipmi_poweroff.c index 9f2e3be2c5b8..676c910e990f 100644 --- a/drivers/char/ipmi/ipmi_poweroff.c +++ b/drivers/char/ipmi/ipmi_poweroff.c @@ -66,7 +66,7 @@ static void (*specific_poweroff_func)(ipmi_user_t user); /* Holds the old poweroff function so we can restore it on removal. */ static void (*old_poweroff_func)(void); -static int set_param_ifnum(const char *val, struct kernel_param *kp) +static int set_param_ifnum(const char *val, const struct kernel_param *kp) { int rv = param_set_int(val, kp); if (rv) diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index f6ba90b90503..1965cb5813b1 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -1359,7 +1359,7 @@ static unsigned int num_slave_addrs; #define IPMI_MEM_ADDR_SPACE 1 static const char * const addr_space_to_str[] = { "i/o", "mem" }; -static int hotmod_handler(const char *val, struct kernel_param *kp); +static int hotmod_handler(const char *val, const struct kernel_param *kp); module_param_call(hotmod, hotmod_handler, NULL, NULL, 0200); MODULE_PARM_DESC(hotmod, "Add and remove interfaces. See" @@ -1825,7 +1825,7 @@ static struct smi_info *smi_info_alloc(void) return info; } -static int hotmod_handler(const char *val, struct kernel_param *kp) +static int hotmod_handler(const char *val, const struct kernel_param *kp) { char *str = kstrdup(val, GFP_KERNEL); int rv; diff --git a/drivers/char/random.c b/drivers/char/random.c index 868d2620b7ac..7ac948753007 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -265,7 +265,7 @@ #include <linux/syscalls.h> #include <linux/completion.h> #include <linux/uuid.h> -#include <crypto/chacha20.h> +#include <crypto/chacha.h> #include <asm/processor.h> #include <linux/uaccess.h> @@ -431,11 +431,10 @@ static int crng_init = 0; #define crng_ready() (likely(crng_init > 1)) static int crng_init_cnt = 0; static unsigned long crng_global_init_time = 0; -#define CRNG_INIT_CNT_THRESH (2*CHACHA20_KEY_SIZE) -static void _extract_crng(struct crng_state *crng, - __u8 out[CHACHA20_BLOCK_SIZE]); +#define CRNG_INIT_CNT_THRESH (2*CHACHA_KEY_SIZE) +static void _extract_crng(struct crng_state *crng, __u8 out[CHACHA_BLOCK_SIZE]); static void _crng_backtrack_protect(struct crng_state *crng, - __u8 tmp[CHACHA20_BLOCK_SIZE], int used); + __u8 tmp[CHACHA_BLOCK_SIZE], int used); static void process_random_ready_list(void); static void _get_random_bytes(void *buf, int nbytes); @@ -848,7 +847,7 @@ static int crng_fast_load(const char *cp, size_t len) } p = (unsigned char *) &primary_crng.state[4]; while (len > 0 && crng_init_cnt < CRNG_INIT_CNT_THRESH) { - p[crng_init_cnt % CHACHA20_KEY_SIZE] ^= *cp; + p[crng_init_cnt % CHACHA_KEY_SIZE] ^= *cp; cp++; crng_init_cnt++; len--; } spin_unlock_irqrestore(&primary_crng.lock, flags); @@ -880,7 +879,7 @@ static int crng_slow_load(const char *cp, size_t len) unsigned long flags; static unsigned char lfsr = 1; unsigned char tmp; - unsigned i, max = CHACHA20_KEY_SIZE; + unsigned i, max = CHACHA_KEY_SIZE; const char * src_buf = cp; char * dest_buf = (char *) &primary_crng.state[4]; @@ -898,8 +897,8 @@ static int crng_slow_load(const char *cp, size_t len) lfsr >>= 1; if (tmp & 1) lfsr ^= 0xE1; - tmp = dest_buf[i % CHACHA20_KEY_SIZE]; - dest_buf[i % CHACHA20_KEY_SIZE] ^= src_buf[i % len] ^ lfsr; + tmp = dest_buf[i % CHACHA_KEY_SIZE]; + dest_buf[i % CHACHA_KEY_SIZE] ^= src_buf[i % len] ^ lfsr; lfsr += (tmp << 3) | (tmp >> 5); } spin_unlock_irqrestore(&primary_crng.lock, flags); @@ -911,7 +910,7 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r) unsigned long flags; int i, num; union { - __u8 block[CHACHA20_BLOCK_SIZE]; + __u8 block[CHACHA_BLOCK_SIZE]; __u32 key[8]; } buf; @@ -922,7 +921,7 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r) } else { _extract_crng(&primary_crng, buf.block); _crng_backtrack_protect(&primary_crng, buf.block, - CHACHA20_KEY_SIZE); + CHACHA_KEY_SIZE); } spin_lock_irqsave(&crng->lock, flags); for (i = 0; i < 8; i++) { @@ -958,7 +957,7 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r) } static void _extract_crng(struct crng_state *crng, - __u8 out[CHACHA20_BLOCK_SIZE]) + __u8 out[CHACHA_BLOCK_SIZE]) { unsigned long v, flags; @@ -975,7 +974,7 @@ static void _extract_crng(struct crng_state *crng, spin_unlock_irqrestore(&crng->lock, flags); } -static void extract_crng(__u8 out[CHACHA20_BLOCK_SIZE]) +static void extract_crng(__u8 out[CHACHA_BLOCK_SIZE]) { struct crng_state *crng = NULL; @@ -993,14 +992,14 @@ static void extract_crng(__u8 out[CHACHA20_BLOCK_SIZE]) * enough) to mutate the CRNG key to provide backtracking protection. */ static void _crng_backtrack_protect(struct crng_state *crng, - __u8 tmp[CHACHA20_BLOCK_SIZE], int used) + __u8 tmp[CHACHA_BLOCK_SIZE], int used) { unsigned long flags; __u32 *s, *d; int i; used = round_up(used, sizeof(__u32)); - if (used + CHACHA20_KEY_SIZE > CHACHA20_BLOCK_SIZE) { + if (used + CHACHA_KEY_SIZE > CHACHA_BLOCK_SIZE) { extract_crng(tmp); used = 0; } @@ -1012,7 +1011,7 @@ static void _crng_backtrack_protect(struct crng_state *crng, spin_unlock_irqrestore(&crng->lock, flags); } -static void crng_backtrack_protect(__u8 tmp[CHACHA20_BLOCK_SIZE], int used) +static void crng_backtrack_protect(__u8 tmp[CHACHA_BLOCK_SIZE], int used) { struct crng_state *crng = NULL; @@ -1027,8 +1026,8 @@ static void crng_backtrack_protect(__u8 tmp[CHACHA20_BLOCK_SIZE], int used) static ssize_t extract_crng_user(void __user *buf, size_t nbytes) { - ssize_t ret = 0, i = CHACHA20_BLOCK_SIZE; - __u8 tmp[CHACHA20_BLOCK_SIZE]; + ssize_t ret = 0, i = CHACHA_BLOCK_SIZE; + __u8 tmp[CHACHA_BLOCK_SIZE] __aligned(4); int large_request = (nbytes > 256); while (nbytes) { @@ -1042,7 +1041,7 @@ static ssize_t extract_crng_user(void __user *buf, size_t nbytes) } extract_crng(tmp); - i = min_t(int, nbytes, CHACHA20_BLOCK_SIZE); + i = min_t(int, nbytes, CHACHA_BLOCK_SIZE); if (copy_to_user(buf, tmp, i)) { ret = -EFAULT; break; @@ -1614,14 +1613,14 @@ static void _warn_unseeded_randomness(const char *func_name, void *caller, */ static void _get_random_bytes(void *buf, int nbytes) { - __u8 tmp[CHACHA20_BLOCK_SIZE]; + __u8 tmp[CHACHA_BLOCK_SIZE] __aligned(4); trace_get_random_bytes(nbytes, _RET_IP_); - while (nbytes >= CHACHA20_BLOCK_SIZE) { + while (nbytes >= CHACHA_BLOCK_SIZE) { extract_crng(buf); - buf += CHACHA20_BLOCK_SIZE; - nbytes -= CHACHA20_BLOCK_SIZE; + buf += CHACHA_BLOCK_SIZE; + nbytes -= CHACHA_BLOCK_SIZE; } if (nbytes > 0) { @@ -1629,7 +1628,7 @@ static void _get_random_bytes(void *buf, int nbytes) memcpy(buf, tmp, nbytes); crng_backtrack_protect(tmp, nbytes); } else - crng_backtrack_protect(tmp, CHACHA20_BLOCK_SIZE); + crng_backtrack_protect(tmp, CHACHA_BLOCK_SIZE); memzero_explicit(tmp, sizeof(tmp)); } @@ -2184,8 +2183,8 @@ struct ctl_table random_table[] = { struct batched_entropy { union { - u64 entropy_u64[CHACHA20_BLOCK_SIZE / sizeof(u64)]; - u32 entropy_u32[CHACHA20_BLOCK_SIZE / sizeof(u32)]; + u64 entropy_u64[CHACHA_BLOCK_SIZE / sizeof(u64)]; + u32 entropy_u32[CHACHA_BLOCK_SIZE / sizeof(u32)]; }; unsigned int position; spinlock_t batch_lock; diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig index d8addbce40bc..b374515f9813 100644 --- a/drivers/cpufreq/Kconfig +++ b/drivers/cpufreq/Kconfig @@ -37,6 +37,13 @@ config CPU_FREQ_STAT If in doubt, say N. +config CPU_FREQ_TIMES + bool "CPU frequency time-in-state statistics" + help + Export CPU time-in-state information through procfs. + + If in doubt, say N. + choice prompt "Default CPUFreq governor" default CPU_FREQ_DEFAULT_GOV_USERSPACE if ARM_SA1100_CPUFREQ || ARM_SA1110_CPUFREQ diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile index 812f9e0d01a3..3ad8aeb687ef 100644 --- a/drivers/cpufreq/Makefile +++ b/drivers/cpufreq/Makefile @@ -5,7 +5,10 @@ obj-$(CONFIG_CPU_FREQ) += cpufreq.o freq_table.o # CPUfreq stats obj-$(CONFIG_CPU_FREQ_STAT) += cpufreq_stats.o -# CPUfreq governors +# CPUfreq times +obj-$(CONFIG_CPU_FREQ_TIMES) += cpufreq_times.o + +# CPUfreq governors obj-$(CONFIG_CPU_FREQ_GOV_PERFORMANCE) += cpufreq_performance.o obj-$(CONFIG_CPU_FREQ_GOV_POWERSAVE) += cpufreq_powersave.o obj-$(CONFIG_CPU_FREQ_GOV_USERSPACE) += cpufreq_userspace.o diff --git a/drivers/cpufreq/arm_big_little.c b/drivers/cpufreq/arm_big_little.c index 17504129fd77..0c41ab3b16eb 100644 --- a/drivers/cpufreq/arm_big_little.c +++ b/drivers/cpufreq/arm_big_little.c @@ -213,6 +213,7 @@ static int bL_cpufreq_set_target(struct cpufreq_policy *policy, { u32 cpu = policy->cpu, cur_cluster, new_cluster, actual_cluster; unsigned int freqs_new; + int ret; cur_cluster = cpu_to_cluster(cpu); new_cluster = actual_cluster = per_cpu(physical_cluster, cpu); @@ -229,7 +230,14 @@ static int bL_cpufreq_set_target(struct cpufreq_policy *policy, } } - return bL_cpufreq_set_rate(cpu, actual_cluster, new_cluster, freqs_new); + ret = bL_cpufreq_set_rate(cpu, actual_cluster, new_cluster, freqs_new); + + if (!ret) { + arch_set_freq_scale(policy->related_cpus, freqs_new, + policy->cpuinfo.max_freq); + } + + return ret; } static inline u32 get_table_count(struct cpufreq_frequency_table *table) diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c index ca6ee9f389b6..9546218edfcc 100644 --- a/drivers/cpufreq/cpufreq-dt.c +++ b/drivers/cpufreq/cpufreq-dt.c @@ -44,9 +44,17 @@ static struct freq_attr *cpufreq_dt_attr[] = { static int set_target(struct cpufreq_policy *policy, unsigned int index) { struct private_data *priv = policy->driver_data; + unsigned long freq = policy->freq_table[index].frequency; + int ret; + + ret = dev_pm_opp_set_rate(priv->cpu_dev, freq * 1000); - return dev_pm_opp_set_rate(priv->cpu_dev, - policy->freq_table[index].frequency * 1000); + if (!ret) { + arch_set_freq_scale(policy->related_cpus, freq, + policy->cpuinfo.max_freq); + } + + return ret; } /* diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index c798a1233e6a..ac9f3382a8bc 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -19,6 +19,7 @@ #include <linux/cpu.h> #include <linux/cpufreq.h> +#include <linux/cpufreq_times.h> #include <linux/delay.h> #include <linux/device.h> #include <linux/init.h> @@ -339,6 +340,7 @@ static void __cpufreq_notify_transition(struct cpufreq_policy *policy, (unsigned long)freqs->new, (unsigned long)freqs->cpu); trace_cpu_frequency(freqs->new, freqs->cpu); cpufreq_stats_record_transition(policy, freqs->new); + cpufreq_times_record_transition(policy, freqs->new); srcu_notifier_call_chain(&cpufreq_transition_notifier_list, CPUFREQ_POSTCHANGE, freqs); if (likely(policy) && likely(policy->cpu == freqs->cpu)) @@ -1296,6 +1298,7 @@ static int cpufreq_online(unsigned int cpu) goto out_exit_policy; cpufreq_stats_create_table(policy); + cpufreq_times_create_policy(policy); write_lock_irqsave(&cpufreq_driver_lock, flags); list_add(&policy->policy_list, &cpufreq_policy_list); @@ -1859,9 +1862,14 @@ EXPORT_SYMBOL(cpufreq_unregister_notifier); unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy, unsigned int target_freq) { + int ret; target_freq = clamp_val(target_freq, policy->min, policy->max); - return cpufreq_driver->fast_switch(policy, target_freq); + ret = cpufreq_driver->fast_switch(policy, target_freq); + if (ret) + cpufreq_times_record_transition(policy, ret); + + return ret; } EXPORT_SYMBOL_GPL(cpufreq_driver_fast_switch); @@ -2241,6 +2249,10 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy, policy->min = new_policy->min; policy->max = new_policy->max; + arch_set_max_freq_scale(policy->cpus, policy->max); + + trace_cpu_frequency_limits(policy->max, policy->min, policy->cpu); + policy->cached_target_freq = UINT_MAX; pr_debug("new min and max freqs are %u - %u kHz\n", @@ -2439,6 +2451,23 @@ int cpufreq_boost_enabled(void) EXPORT_SYMBOL_GPL(cpufreq_boost_enabled); /********************************************************************* + * FREQUENCY INVARIANT ACCOUNTING SUPPORT * + *********************************************************************/ + +__weak void arch_set_freq_scale(struct cpumask *cpus, + unsigned long cur_freq, + unsigned long max_freq) +{ +} +EXPORT_SYMBOL_GPL(arch_set_freq_scale); + +__weak void arch_set_max_freq_scale(struct cpumask *cpus, + unsigned long policy_max_freq) +{ +} +EXPORT_SYMBOL_GPL(arch_set_max_freq_scale); + +/********************************************************************* * REGISTER / UNREGISTER CPUFREQ DRIVER * *********************************************************************/ static enum cpuhp_state hp_online; diff --git a/drivers/cpufreq/cpufreq_times.c b/drivers/cpufreq/cpufreq_times.c new file mode 100644 index 000000000000..5b5248a7c87c --- /dev/null +++ b/drivers/cpufreq/cpufreq_times.c @@ -0,0 +1,632 @@ +/* drivers/cpufreq/cpufreq_times.c + * + * Copyright (C) 2018 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/cpufreq.h> +#include <linux/cpufreq_times.h> +#include <linux/hashtable.h> +#include <linux/init.h> +#include <linux/jiffies.h> +#include <linux/proc_fs.h> +#include <linux/sched.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/threads.h> + +#define UID_HASH_BITS 10 + +static DECLARE_HASHTABLE(uid_hash_table, UID_HASH_BITS); + +static DEFINE_SPINLOCK(task_time_in_state_lock); /* task->time_in_state */ +static DEFINE_SPINLOCK(uid_lock); /* uid_hash_table */ + +struct concurrent_times { + atomic64_t active[NR_CPUS]; + atomic64_t policy[NR_CPUS]; +}; + +struct uid_entry { + uid_t uid; + unsigned int max_state; + struct hlist_node hash; + struct rcu_head rcu; + struct concurrent_times *concurrent_times; + u64 time_in_state[0]; +}; + +/** + * struct cpu_freqs - per-cpu frequency information + * @offset: start of these freqs' stats in task time_in_state array + * @max_state: number of entries in freq_table + * @last_index: index in freq_table of last frequency switched to + * @freq_table: list of available frequencies + */ +struct cpu_freqs { + unsigned int offset; + unsigned int max_state; + unsigned int last_index; + unsigned int freq_table[0]; +}; + +static struct cpu_freqs *all_freqs[NR_CPUS]; + +static unsigned int next_offset; + + +/* Caller must hold rcu_read_lock() */ +static struct uid_entry *find_uid_entry_rcu(uid_t uid) +{ + struct uid_entry *uid_entry; + + hash_for_each_possible_rcu(uid_hash_table, uid_entry, hash, uid) { + if (uid_entry->uid == uid) + return uid_entry; + } + return NULL; +} + +/* Caller must hold uid lock */ +static struct uid_entry *find_uid_entry_locked(uid_t uid) +{ + struct uid_entry *uid_entry; + + hash_for_each_possible(uid_hash_table, uid_entry, hash, uid) { + if (uid_entry->uid == uid) + return uid_entry; + } + return NULL; +} + +/* Caller must hold uid lock */ +static struct uid_entry *find_or_register_uid_locked(uid_t uid) +{ + struct uid_entry *uid_entry, *temp; + struct concurrent_times *times; + unsigned int max_state = READ_ONCE(next_offset); + size_t alloc_size = sizeof(*uid_entry) + max_state * + sizeof(uid_entry->time_in_state[0]); + + uid_entry = find_uid_entry_locked(uid); + if (uid_entry) { + if (uid_entry->max_state == max_state) + return uid_entry; + /* uid_entry->time_in_state is too small to track all freqs, so + * expand it. + */ + temp = __krealloc(uid_entry, alloc_size, GFP_ATOMIC); + if (!temp) + return uid_entry; + temp->max_state = max_state; + memset(temp->time_in_state + uid_entry->max_state, 0, + (max_state - uid_entry->max_state) * + sizeof(uid_entry->time_in_state[0])); + if (temp != uid_entry) { + hlist_replace_rcu(&uid_entry->hash, &temp->hash); + kfree_rcu(uid_entry, rcu); + } + return temp; + } + + uid_entry = kzalloc(alloc_size, GFP_ATOMIC); + if (!uid_entry) + return NULL; + times = kzalloc(sizeof(*times), GFP_ATOMIC); + if (!times) { + kfree(uid_entry); + return NULL; + } + + uid_entry->uid = uid; + uid_entry->max_state = max_state; + uid_entry->concurrent_times = times; + + hash_add_rcu(uid_hash_table, &uid_entry->hash, uid); + + return uid_entry; +} + +static int single_uid_time_in_state_show(struct seq_file *m, void *ptr) +{ + struct uid_entry *uid_entry; + unsigned int i; + uid_t uid = from_kuid_munged(current_user_ns(), *(kuid_t *)m->private); + + if (uid == overflowuid) + return -EINVAL; + + rcu_read_lock(); + + uid_entry = find_uid_entry_rcu(uid); + if (!uid_entry) { + rcu_read_unlock(); + return 0; + } + + for (i = 0; i < uid_entry->max_state; ++i) { + u64 time = nsec_to_clock_t(uid_entry->time_in_state[i]); + seq_write(m, &time, sizeof(time)); + } + + rcu_read_unlock(); + + return 0; +} + +static void *uid_seq_start(struct seq_file *seq, loff_t *pos) +{ + if (*pos >= HASH_SIZE(uid_hash_table)) + return NULL; + + return &uid_hash_table[*pos]; +} + +static void *uid_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + do { + (*pos)++; + + if (*pos >= HASH_SIZE(uid_hash_table)) + return NULL; + } while (hlist_empty(&uid_hash_table[*pos])); + + return &uid_hash_table[*pos]; +} + +static void uid_seq_stop(struct seq_file *seq, void *v) { } + +static int uid_time_in_state_seq_show(struct seq_file *m, void *v) +{ + struct uid_entry *uid_entry; + struct cpu_freqs *freqs, *last_freqs = NULL; + int i, cpu; + + if (v == uid_hash_table) { + seq_puts(m, "uid:"); + for_each_possible_cpu(cpu) { + freqs = all_freqs[cpu]; + if (!freqs || freqs == last_freqs) + continue; + last_freqs = freqs; + for (i = 0; i < freqs->max_state; i++) { + seq_put_decimal_ull(m, " ", + freqs->freq_table[i]); + } + } + seq_putc(m, '\n'); + } + + rcu_read_lock(); + + hlist_for_each_entry_rcu(uid_entry, (struct hlist_head *)v, hash) { + if (uid_entry->max_state) { + seq_put_decimal_ull(m, "", uid_entry->uid); + seq_putc(m, ':'); + } + for (i = 0; i < uid_entry->max_state; ++i) { + u64 time = nsec_to_clock_t(uid_entry->time_in_state[i]); + seq_put_decimal_ull(m, " ", time); + } + if (uid_entry->max_state) + seq_putc(m, '\n'); + } + + rcu_read_unlock(); + return 0; +} + +static int concurrent_time_seq_show(struct seq_file *m, void *v, + atomic64_t *(*get_times)(struct concurrent_times *)) +{ + struct uid_entry *uid_entry; + int i, num_possible_cpus = num_possible_cpus(); + + rcu_read_lock(); + + hlist_for_each_entry_rcu(uid_entry, (struct hlist_head *)v, hash) { + atomic64_t *times = get_times(uid_entry->concurrent_times); + + seq_put_decimal_ull(m, "", (u64)uid_entry->uid); + seq_putc(m, ':'); + + for (i = 0; i < num_possible_cpus; ++i) { + u64 time = nsec_to_clock_t(atomic64_read(×[i])); + + seq_put_decimal_ull(m, " ", time); + } + seq_putc(m, '\n'); + } + + rcu_read_unlock(); + + return 0; +} + +static inline atomic64_t *get_active_times(struct concurrent_times *times) +{ + return times->active; +} + +static int concurrent_active_time_seq_show(struct seq_file *m, void *v) +{ + if (v == uid_hash_table) { + seq_put_decimal_ull(m, "cpus: ", num_possible_cpus()); + seq_putc(m, '\n'); + } + + return concurrent_time_seq_show(m, v, get_active_times); +} + +static inline atomic64_t *get_policy_times(struct concurrent_times *times) +{ + return times->policy; +} + +static int concurrent_policy_time_seq_show(struct seq_file *m, void *v) +{ + int i; + struct cpu_freqs *freqs, *last_freqs = NULL; + + if (v == uid_hash_table) { + int cnt = 0; + + for_each_possible_cpu(i) { + freqs = all_freqs[i]; + if (!freqs) + continue; + if (freqs != last_freqs) { + if (last_freqs) { + seq_put_decimal_ull(m, ": ", cnt); + seq_putc(m, ' '); + cnt = 0; + } + seq_put_decimal_ull(m, "policy", i); + + last_freqs = freqs; + } + cnt++; + } + if (last_freqs) { + seq_put_decimal_ull(m, ": ", cnt); + seq_putc(m, '\n'); + } + } + + return concurrent_time_seq_show(m, v, get_policy_times); +} + +void cpufreq_task_times_init(struct task_struct *p) +{ + unsigned long flags; + + spin_lock_irqsave(&task_time_in_state_lock, flags); + p->time_in_state = NULL; + spin_unlock_irqrestore(&task_time_in_state_lock, flags); + p->max_state = 0; +} + +void cpufreq_task_times_alloc(struct task_struct *p) +{ + void *temp; + unsigned long flags; + unsigned int max_state = READ_ONCE(next_offset); + + /* We use one array to avoid multiple allocs per task */ + temp = kcalloc(max_state, sizeof(p->time_in_state[0]), GFP_ATOMIC); + if (!temp) + return; + + spin_lock_irqsave(&task_time_in_state_lock, flags); + p->time_in_state = temp; + spin_unlock_irqrestore(&task_time_in_state_lock, flags); + p->max_state = max_state; +} + +/* Caller must hold task_time_in_state_lock */ +static int cpufreq_task_times_realloc_locked(struct task_struct *p) +{ + void *temp; + unsigned int max_state = READ_ONCE(next_offset); + + temp = krealloc(p->time_in_state, max_state * sizeof(u64), GFP_ATOMIC); + if (!temp) + return -ENOMEM; + p->time_in_state = temp; + memset(p->time_in_state + p->max_state, 0, + (max_state - p->max_state) * sizeof(u64)); + p->max_state = max_state; + return 0; +} + +void cpufreq_task_times_exit(struct task_struct *p) +{ + unsigned long flags; + void *temp; + + if (!p->time_in_state) + return; + + spin_lock_irqsave(&task_time_in_state_lock, flags); + temp = p->time_in_state; + p->time_in_state = NULL; + spin_unlock_irqrestore(&task_time_in_state_lock, flags); + kfree(temp); +} + +int proc_time_in_state_show(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *p) +{ + unsigned int cpu, i; + u64 cputime; + unsigned long flags; + struct cpu_freqs *freqs; + struct cpu_freqs *last_freqs = NULL; + + spin_lock_irqsave(&task_time_in_state_lock, flags); + for_each_possible_cpu(cpu) { + freqs = all_freqs[cpu]; + if (!freqs || freqs == last_freqs) + continue; + last_freqs = freqs; + + seq_printf(m, "cpu%u\n", cpu); + for (i = 0; i < freqs->max_state; i++) { + cputime = 0; + if (freqs->offset + i < p->max_state && + p->time_in_state) + cputime = p->time_in_state[freqs->offset + i]; + seq_printf(m, "%u %lu\n", freqs->freq_table[i], + (unsigned long)nsec_to_clock_t(cputime)); + } + } + spin_unlock_irqrestore(&task_time_in_state_lock, flags); + return 0; +} + +void cpufreq_acct_update_power(struct task_struct *p, u64 cputime) +{ + unsigned long flags; + unsigned int state; + unsigned int active_cpu_cnt = 0; + unsigned int policy_cpu_cnt = 0; + unsigned int policy_first_cpu; + struct uid_entry *uid_entry; + struct cpu_freqs *freqs = all_freqs[task_cpu(p)]; + struct cpufreq_policy *policy; + uid_t uid = from_kuid_munged(current_user_ns(), task_uid(p)); + int cpu = 0; + + if (!freqs || is_idle_task(p) || p->flags & PF_EXITING) + return; + + state = freqs->offset + READ_ONCE(freqs->last_index); + + spin_lock_irqsave(&task_time_in_state_lock, flags); + if ((state < p->max_state || !cpufreq_task_times_realloc_locked(p)) && + p->time_in_state) + p->time_in_state[state] += cputime; + spin_unlock_irqrestore(&task_time_in_state_lock, flags); + + spin_lock_irqsave(&uid_lock, flags); + uid_entry = find_or_register_uid_locked(uid); + if (uid_entry && state < uid_entry->max_state) + uid_entry->time_in_state[state] += cputime; + spin_unlock_irqrestore(&uid_lock, flags); + + rcu_read_lock(); + uid_entry = find_uid_entry_rcu(uid); + if (!uid_entry) { + rcu_read_unlock(); + return; + } + + for_each_possible_cpu(cpu) + if (!idle_cpu(cpu)) + ++active_cpu_cnt; + + atomic64_add(cputime, + &uid_entry->concurrent_times->active[active_cpu_cnt - 1]); + + policy = cpufreq_cpu_get(task_cpu(p)); + if (!policy) { + /* + * This CPU may have just come up and not have a cpufreq policy + * yet. + */ + rcu_read_unlock(); + return; + } + + for_each_cpu(cpu, policy->related_cpus) + if (!idle_cpu(cpu)) + ++policy_cpu_cnt; + + policy_first_cpu = cpumask_first(policy->related_cpus); + cpufreq_cpu_put(policy); + + atomic64_add(cputime, + &uid_entry->concurrent_times->policy[policy_first_cpu + + policy_cpu_cnt - 1]); + rcu_read_unlock(); +} + +static int cpufreq_times_get_index(struct cpu_freqs *freqs, unsigned int freq) +{ + int index; + for (index = 0; index < freqs->max_state; ++index) { + if (freqs->freq_table[index] == freq) + return index; + } + return -1; +} + +void cpufreq_times_create_policy(struct cpufreq_policy *policy) +{ + int cpu, index = 0; + unsigned int count = 0; + struct cpufreq_frequency_table *pos, *table; + struct cpu_freqs *freqs; + void *tmp; + + if (all_freqs[policy->cpu]) + return; + + table = policy->freq_table; + if (!table) + return; + + cpufreq_for_each_valid_entry(pos, table) + count++; + + tmp = kzalloc(sizeof(*freqs) + sizeof(freqs->freq_table[0]) * count, + GFP_KERNEL); + if (!tmp) + return; + + freqs = tmp; + freqs->max_state = count; + + cpufreq_for_each_valid_entry(pos, table) + freqs->freq_table[index++] = pos->frequency; + + index = cpufreq_times_get_index(freqs, policy->cur); + if (index >= 0) + WRITE_ONCE(freqs->last_index, index); + + freqs->offset = next_offset; + WRITE_ONCE(next_offset, freqs->offset + count); + for_each_cpu(cpu, policy->related_cpus) + all_freqs[cpu] = freqs; +} + +static void uid_entry_reclaim(struct rcu_head *rcu) +{ + struct uid_entry *uid_entry = container_of(rcu, struct uid_entry, rcu); + + kfree(uid_entry->concurrent_times); + kfree(uid_entry); +} + +void cpufreq_task_times_remove_uids(uid_t uid_start, uid_t uid_end) +{ + struct uid_entry *uid_entry; + struct hlist_node *tmp; + unsigned long flags; + + spin_lock_irqsave(&uid_lock, flags); + + for (; uid_start <= uid_end; uid_start++) { + hash_for_each_possible_safe(uid_hash_table, uid_entry, tmp, + hash, uid_start) { + if (uid_start == uid_entry->uid) { + hash_del_rcu(&uid_entry->hash); + call_rcu(&uid_entry->rcu, uid_entry_reclaim); + } + } + } + + spin_unlock_irqrestore(&uid_lock, flags); +} + +void cpufreq_times_record_transition(struct cpufreq_policy *policy, + unsigned int new_freq) +{ + int index; + struct cpu_freqs *freqs = all_freqs[policy->cpu]; + if (!freqs) + return; + + index = cpufreq_times_get_index(freqs, new_freq); + if (index >= 0) + WRITE_ONCE(freqs->last_index, index); +} + +static const struct seq_operations uid_time_in_state_seq_ops = { + .start = uid_seq_start, + .next = uid_seq_next, + .stop = uid_seq_stop, + .show = uid_time_in_state_seq_show, +}; + +static int uid_time_in_state_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &uid_time_in_state_seq_ops); +} + +int single_uid_time_in_state_open(struct inode *inode, struct file *file) +{ + return single_open(file, single_uid_time_in_state_show, + &(inode->i_uid)); +} + +static const struct file_operations uid_time_in_state_fops = { + .open = uid_time_in_state_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static const struct seq_operations concurrent_active_time_seq_ops = { + .start = uid_seq_start, + .next = uid_seq_next, + .stop = uid_seq_stop, + .show = concurrent_active_time_seq_show, +}; + +static int concurrent_active_time_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &concurrent_active_time_seq_ops); +} + +static const struct file_operations concurrent_active_time_fops = { + .open = concurrent_active_time_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static const struct seq_operations concurrent_policy_time_seq_ops = { + .start = uid_seq_start, + .next = uid_seq_next, + .stop = uid_seq_stop, + .show = concurrent_policy_time_seq_show, +}; + +static int concurrent_policy_time_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &concurrent_policy_time_seq_ops); +} + +static const struct file_operations concurrent_policy_time_fops = { + .open = concurrent_policy_time_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static int __init cpufreq_times_init(void) +{ + proc_create_data("uid_time_in_state", 0444, NULL, + &uid_time_in_state_fops, NULL); + + proc_create_data("uid_concurrent_active_time", 0444, NULL, + &concurrent_active_time_fops, NULL); + + proc_create_data("uid_concurrent_policy_time", 0444, NULL, + &concurrent_policy_time_fops, NULL); + + return 0; +} + +early_initcall(cpufreq_times_init); diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index ed4df58a855e..7c33193216ea 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -212,7 +212,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, } /* Take note of the planned idle state. */ - sched_idle_set_state(target_state); + sched_idle_set_state(target_state, index); trace_cpu_idle_rcuidle(index, dev->cpu); time_start = ns_to_ktime(local_clock()); @@ -226,7 +226,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu); /* The cpu is no longer idle or about to enter idle. */ - sched_idle_set_state(NULL); + sched_idle_set_state(NULL, -1); if (broadcast) { if (WARN_ON_ONCE(!irqs_disabled())) @@ -263,12 +263,18 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, * * @drv: the cpuidle driver * @dev: the cpuidle device + * @stop_tick: indication on whether or not to stop the tick * * Returns the index of the idle state. The return value must not be negative. + * + * The memory location pointed to by @stop_tick is expected to be written the + * 'false' boolean value if the scheduler tick should not be stopped before + * entering the returned state. */ -int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) +int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, + bool *stop_tick) { - return cpuidle_curr_governor->select(drv, dev); + return cpuidle_curr_governor->select(drv, dev, stop_tick); } /** diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c index ce1a2ffffb2a..0213e07abe9c 100644 --- a/drivers/cpuidle/governors/ladder.c +++ b/drivers/cpuidle/governors/ladder.c @@ -62,9 +62,10 @@ static inline void ladder_do_selection(struct ladder_device *ldev, * ladder_select_state - selects the next state to enter * @drv: cpuidle driver * @dev: the CPU + * @dummy: not used */ static int ladder_select_state(struct cpuidle_driver *drv, - struct cpuidle_device *dev) + struct cpuidle_device *dev, bool *dummy) { struct ladder_device *ldev = this_cpu_ptr(&ladder_devices); struct ladder_device_state *last_state; diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index 48eaf2879228..55f55aec6ccb 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -123,6 +123,7 @@ struct menu_device { int last_state_idx; int needs_update; + int tick_wakeup; unsigned int next_timer_us; unsigned int predicted_us; @@ -132,10 +133,6 @@ struct menu_device { int interval_ptr; }; - -#define LOAD_INT(x) ((x) >> FSHIFT) -#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) - static inline int get_loadavg(unsigned long load) { return LOAD_INT(load) * 10 + LOAD_FRAC(load) / 10; @@ -180,7 +177,12 @@ static inline int performance_multiplier(unsigned long nr_iowaiters, unsigned lo /* for higher loadavg, we are more reluctant */ - mult += 2 * get_loadavg(load); + /* + * this doesn't work as intended - it is almost always 0, but can + * sometimes, depending on workload, spike very high into the hundreds + * even when the average cpu load is under 10%. + */ + /* mult += 2 * get_loadavg(); */ /* for IO wait tasks (per cpu!) we add 5x each */ mult += 10 * nr_iowaiters; @@ -279,8 +281,10 @@ again: * menu_select - selects the next idle state to enter * @drv: cpuidle driver containing state data * @dev: the CPU + * @stop_tick: indication on whether or not to stop the tick */ -static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) +static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, + bool *stop_tick) { struct menu_device *data = this_cpu_ptr(&menu_devices); struct device *device = get_cpu_device(dev->cpu); @@ -292,6 +296,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) unsigned int expected_interval; unsigned long nr_iowaiters, cpu_load; int resume_latency = dev_pm_qos_raw_read_value(device); + ktime_t delta_next; if (data->needs_update) { menu_update(drv, dev); @@ -303,11 +308,13 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) latency_req = resume_latency; /* Special case when user has set very strict latency requirement */ - if (unlikely(latency_req == 0)) + if (unlikely(latency_req == 0)) { + *stop_tick = false; return 0; + } /* determine the expected residency time, round up */ - data->next_timer_us = ktime_to_us(tick_nohz_get_sleep_length()); + data->next_timer_us = ktime_to_us(tick_nohz_get_sleep_length(&delta_next)); get_iowait_load(&nr_iowaiters, &cpu_load); data->bucket = which_bucket(data->next_timer_us, nr_iowaiters); @@ -346,14 +353,30 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) */ data->predicted_us = min(data->predicted_us, expected_interval); - /* - * Use the performance multiplier and the user-configurable - * latency_req to determine the maximum exit latency. - */ - interactivity_req = data->predicted_us / performance_multiplier(nr_iowaiters, cpu_load); - if (latency_req > interactivity_req) - latency_req = interactivity_req; + if (tick_nohz_tick_stopped()) { + /* + * If the tick is already stopped, the cost of possible short + * idle duration misprediction is much higher, because the CPU + * may be stuck in a shallow idle state for a long time as a + * result of it. In that case say we might mispredict and try + * to force the CPU into a state for which we would have stopped + * the tick, unless a timer is going to expire really soon + * anyway. + */ + if (data->predicted_us < TICK_USEC) + data->predicted_us = min_t(unsigned int, TICK_USEC, + ktime_to_us(delta_next)); + } else { + /* + * Use the performance multiplier and the user-configurable + * latency_req to determine the maximum exit latency. + */ + interactivity_req = data->predicted_us / performance_multiplier(nr_iowaiters, cpu_load); + if (latency_req > interactivity_req) + latency_req = interactivity_req; + } + expected_interval = data->predicted_us; /* * Find the idle state with the lowest power while satisfying * our constraints. @@ -369,15 +392,52 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) idx = i; /* first enabled state */ if (s->target_residency > data->predicted_us) break; - if (s->exit_latency > latency_req) + if (s->exit_latency > latency_req) { + /* + * If we break out of the loop for latency reasons, use + * the target residency of the selected state as the + * expected idle duration so that the tick is retained + * as long as that target residency is low enough. + */ + expected_interval = drv->states[idx].target_residency; break; - + } idx = i; } if (idx == -1) idx = 0; /* No states enabled. Must use 0. */ + /* + * Don't stop the tick if the selected state is a polling one or if the + * expected idle duration is shorter than the tick period length. + */ + if ((drv->states[idx].flags & CPUIDLE_FLAG_POLLING) || + expected_interval < TICK_USEC) { + unsigned int delta_next_us = ktime_to_us(delta_next); + + *stop_tick = false; + + if (!tick_nohz_tick_stopped() && idx > 0 && + drv->states[idx].target_residency > delta_next_us) { + /* + * The tick is not going to be stopped and the target + * residency of the state to be returned is not within + * the time until the next timer event including the + * tick, so try to correct that. + */ + for (i = idx - 1; i >= 0; i--) { + if (drv->states[i].disabled || + dev->states_usage[i].disable) + continue; + + idx = i; + if (drv->states[i].target_residency <= delta_next_us) + break; + } + } + } + data->last_state_idx = idx; return data->last_state_idx; @@ -397,6 +457,7 @@ static void menu_reflect(struct cpuidle_device *dev, int index) data->last_state_idx = index; data->needs_update = 1; + data->tick_wakeup = tick_nohz_idle_got_tick(); } /** @@ -427,14 +488,27 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) * assume the state was never reached and the exit latency is 0. */ - /* measured value */ - measured_us = cpuidle_get_last_residency(dev); - - /* Deduct exit latency */ - if (measured_us > 2 * target->exit_latency) - measured_us -= target->exit_latency; - else - measured_us /= 2; + if (data->tick_wakeup && data->next_timer_us > TICK_USEC) { + /* + * The nohz code said that there wouldn't be any events within + * the tick boundary (if the tick was stopped), but the idle + * duration predictor had a differing opinion. Since the CPU + * was woken up by a tick (that wasn't stopped after all), the + * predictor was not quite right, so assume that the CPU could + * have been idle long (but not forever) to help the idle + * duration predictor do a better job next time. + */ + measured_us = 9 * MAX_INTERESTING / 10; + } else { + /* measured value */ + measured_us = cpuidle_get_last_residency(dev); + + /* Deduct exit latency */ + if (measured_us > 2 * target->exit_latency) + measured_us -= target->exit_latency; + else + measured_us /= 2; + } /* Make sure our coefficients do not exceed unity */ if (measured_us > data->next_timer_us) diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index 9a302799040e..33ea68b45654 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -329,8 +329,12 @@ dma_fence_remove_callback(struct dma_fence *fence, struct dma_fence_cb *cb) spin_lock_irqsave(fence->lock, flags); ret = !list_empty(&cb->node); - if (ret) + if (ret) { list_del_init(&cb->node); + if (list_empty(&fence->cb_list)) + if (fence->ops->disable_signaling) + fence->ops->disable_signaling(fence); + } spin_unlock_irqrestore(fence->lock, flags); diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c index 114b36674af4..8145f4cd05bd 100644 --- a/drivers/dma-buf/sw_sync.c +++ b/drivers/dma-buf/sw_sync.c @@ -166,6 +166,13 @@ static bool timeline_fence_enable_signaling(struct dma_fence *fence) return true; } +static void timeline_fence_disable_signaling(struct dma_fence *fence) +{ + struct sync_pt *pt = dma_fence_to_sync_pt(fence); + + list_del_init(&pt->link); +} + static void timeline_fence_value_str(struct dma_fence *fence, char *str, int size) { @@ -184,6 +191,7 @@ static const struct dma_fence_ops timeline_fence_ops = { .get_driver_name = timeline_fence_get_driver_name, .get_timeline_name = timeline_fence_get_timeline_name, .enable_signaling = timeline_fence_enable_signaling, + .disable_signaling = timeline_fence_disable_signaling, .signaled = timeline_fence_signaled, .wait = dma_fence_default_wait, .release = timeline_fence_release, diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c index a4acfa81dfe0..223f00552350 100644 --- a/drivers/edac/edac_mc_sysfs.c +++ b/drivers/edac/edac_mc_sysfs.c @@ -50,7 +50,7 @@ unsigned int edac_mc_get_poll_msec(void) return edac_mc_poll_msec; } -static int edac_set_poll_msec(const char *val, struct kernel_param *kp) +static int edac_set_poll_msec(const char *val, const struct kernel_param *kp) { unsigned int i; int ret; diff --git a/drivers/edac/edac_module.c b/drivers/edac/edac_module.c index 172598a27d7d..32a931d0cb71 100644 --- a/drivers/edac/edac_module.c +++ b/drivers/edac/edac_module.c @@ -19,7 +19,8 @@ #ifdef CONFIG_EDAC_DEBUG -static int edac_set_debug_level(const char *buf, struct kernel_param *kp) +static int edac_set_debug_level(const char *buf, + const struct kernel_param *kp) { unsigned long val; int ret; diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index 678bc910e080..8a1e54bc7e0d 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -21,7 +21,8 @@ cflags-$(CONFIG_EFI_ARMSTUB) += -I$(srctree)/scripts/dtc/libfdt KBUILD_CFLAGS := $(cflags-y) -DDISABLE_BRANCH_PROFILING \ -D__NO_FORTIFY \ $(call cc-option,-ffreestanding) \ - $(call cc-option,-fno-stack-protector) + $(call cc-option,-fno-stack-protector) \ + $(DISABLE_LTO) GCOV_PROFILE := n KASAN_SANITIZE := n diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c index 8c993f95e3ba..78e37bb25aee 100644 --- a/drivers/hid/hid-magicmouse.c +++ b/drivers/hid/hid-magicmouse.c @@ -34,7 +34,8 @@ module_param(emulate_scroll_wheel, bool, 0644); MODULE_PARM_DESC(emulate_scroll_wheel, "Emulate a scroll wheel"); static unsigned int scroll_speed = 32; -static int param_set_scroll_speed(const char *val, struct kernel_param *kp) { +static int param_set_scroll_speed(const char *val, + const struct kernel_param *kp) { unsigned long speed; if (!val || kstrtoul(val, 0, &speed) || speed > 63) return -EINVAL; diff --git a/drivers/ide/ide.c b/drivers/ide/ide.c index d127ace6aa57..6ee866fcc5dd 100644 --- a/drivers/ide/ide.c +++ b/drivers/ide/ide.c @@ -244,7 +244,7 @@ struct chs_geom { static unsigned int ide_disks; static struct chs_geom ide_disks_chs[MAX_HWIFS * MAX_DRIVES]; -static int ide_set_disk_chs(const char *str, struct kernel_param *kp) +static int ide_set_disk_chs(const char *str, const struct kernel_param *kp) { unsigned int a, b, c = 0, h = 0, s = 0, i, j = 1; @@ -328,7 +328,7 @@ static void ide_dev_apply_params(ide_drive_t *drive, u8 unit) static unsigned int ide_ignore_cable; -static int ide_set_ignore_cable(const char *s, struct kernel_param *kp) +static int ide_set_ignore_cable(const char *s, const struct kernel_param *kp) { int i, j = 1; diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c index 14cadf6d6214..a45e46098914 100644 --- a/drivers/infiniband/hw/qib/qib_iba7322.c +++ b/drivers/infiniband/hw/qib/qib_iba7322.c @@ -150,7 +150,7 @@ static struct kparam_string kp_txselect = { .string = txselect_list, .maxlen = MAX_ATTEN_LEN }; -static int setup_txselect(const char *, struct kernel_param *); +static int setup_txselect(const char *, const struct kernel_param *); module_param_call(txselect, setup_txselect, param_get_string, &kp_txselect, S_IWUSR | S_IRUGO); MODULE_PARM_DESC(txselect, @@ -6169,7 +6169,7 @@ static void set_no_qsfp_atten(struct qib_devdata *dd, int change) } /* handle the txselect parameter changing */ -static int setup_txselect(const char *str, struct kernel_param *kp) +static int setup_txselect(const char *str, const struct kernel_param *kp) { struct qib_devdata *dd; unsigned long val; diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index 1446e1cc69ae..5f1055c94d66 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -80,7 +80,7 @@ module_param(srpt_srq_size, int, 0444); MODULE_PARM_DESC(srpt_srq_size, "Shared receive queue (SRQ) size."); -static int srpt_get_u64_x(char *buffer, struct kernel_param *kp) +static int srpt_get_u64_x(char *buffer, const struct kernel_param *kp) { return sprintf(buffer, "0x%016llx", *(u64 *)kp->arg); } diff --git a/drivers/input/Kconfig b/drivers/input/Kconfig index ff8037798779..724715e4f8bc 100644 --- a/drivers/input/Kconfig +++ b/drivers/input/Kconfig @@ -184,6 +184,19 @@ config INPUT_APMPOWER To compile this driver as a module, choose M here: the module will be called apm-power. +config INPUT_KEYRESET + bool "Reset key" + depends on INPUT + select INPUT_KEYCOMBO + ---help--- + Say Y here if you want to reboot when some keys are pressed; + +config INPUT_KEYCOMBO + bool "Key combo" + depends on INPUT + ---help--- + Say Y here if you want to take action when some keys are pressed; + comment "Input Device Drivers" source "drivers/input/keyboard/Kconfig" diff --git a/drivers/input/Makefile b/drivers/input/Makefile index 40de6a7be641..f0351af763bd 100644 --- a/drivers/input/Makefile +++ b/drivers/input/Makefile @@ -27,5 +27,7 @@ obj-$(CONFIG_INPUT_TOUCHSCREEN) += touchscreen/ obj-$(CONFIG_INPUT_MISC) += misc/ obj-$(CONFIG_INPUT_APMPOWER) += apm-power.o +obj-$(CONFIG_INPUT_KEYRESET) += keyreset.o +obj-$(CONFIG_INPUT_KEYCOMBO) += keycombo.o obj-$(CONFIG_RMI4_CORE) += rmi4/ diff --git a/drivers/input/keyboard/goldfish_events.c b/drivers/input/keyboard/goldfish_events.c index f6e643b589b6..c877e56a9bd5 100644 --- a/drivers/input/keyboard/goldfish_events.c +++ b/drivers/input/keyboard/goldfish_events.c @@ -17,6 +17,7 @@ #include <linux/interrupt.h> #include <linux/types.h> #include <linux/input.h> +#include <linux/input/mt.h> #include <linux/kernel.h> #include <linux/platform_device.h> #include <linux/slab.h> @@ -24,6 +25,8 @@ #include <linux/io.h> #include <linux/acpi.h> +#define GOLDFISH_MAX_FINGERS 5 + enum { REG_READ = 0x00, REG_SET_PAGE = 0x00, @@ -52,7 +55,21 @@ static irqreturn_t events_interrupt(int irq, void *dev_id) value = __raw_readl(edev->addr + REG_READ); input_event(edev->input, type, code, value); - input_sync(edev->input); + // Send an extra (EV_SYN, SYN_REPORT, 0x0) event + // if a key was pressed. Some keyboard device + // drivers may only send the EV_KEY event and + // not EV_SYN. + // Note that sending an extra SYN_REPORT is not + // necessary nor correct protocol with other + // devices such as touchscreens, which will send + // their own SYN_REPORT's when sufficient event + // information has been collected (e.g., for + // touchscreens, when pressure and X/Y coordinates + // have been received). Hence, we will only send + // this extra SYN_REPORT if type == EV_KEY. + if (type == EV_KEY) { + input_sync(edev->input); + } return IRQ_HANDLED; } @@ -154,6 +171,15 @@ static int events_probe(struct platform_device *pdev) input_dev->name = edev->name; input_dev->id.bustype = BUS_HOST; + // Set the Goldfish Device to be multi-touch. + // In the Ranchu kernel, there is multi-touch-specific + // code for handling ABS_MT_SLOT events. + // See drivers/input/input.c:input_handle_abs_event. + // If we do not issue input_mt_init_slots, + // the kernel will filter out needed ABS_MT_SLOT + // events when we touch the screen in more than one place, + // preventing multi-touch with more than one finger from working. + input_mt_init_slots(input_dev, GOLDFISH_MAX_FINGERS, 0); events_import_bits(edev, input_dev->evbit, EV_SYN, EV_MAX); events_import_bits(edev, input_dev->keybit, EV_KEY, KEY_MAX); diff --git a/drivers/input/keycombo.c b/drivers/input/keycombo.c new file mode 100644 index 000000000000..2fba451b91d5 --- /dev/null +++ b/drivers/input/keycombo.c @@ -0,0 +1,261 @@ +/* drivers/input/keycombo.c + * + * Copyright (C) 2014 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/input.h> +#include <linux/keycombo.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/reboot.h> +#include <linux/sched.h> +#include <linux/slab.h> + +struct keycombo_state { + struct input_handler input_handler; + unsigned long keybit[BITS_TO_LONGS(KEY_CNT)]; + unsigned long upbit[BITS_TO_LONGS(KEY_CNT)]; + unsigned long key[BITS_TO_LONGS(KEY_CNT)]; + spinlock_t lock; + struct workqueue_struct *wq; + int key_down_target; + int key_down; + int key_up; + struct delayed_work key_down_work; + int delay; + struct work_struct key_up_work; + void (*key_up_fn)(void *); + void (*key_down_fn)(void *); + void *priv; + int key_is_down; + struct wakeup_source combo_held_wake_source; + struct wakeup_source combo_up_wake_source; +}; + +static void do_key_down(struct work_struct *work) +{ + struct delayed_work *dwork = container_of(work, struct delayed_work, + work); + struct keycombo_state *state = container_of(dwork, + struct keycombo_state, key_down_work); + if (state->key_down_fn) + state->key_down_fn(state->priv); +} + +static void do_key_up(struct work_struct *work) +{ + struct keycombo_state *state = container_of(work, struct keycombo_state, + key_up_work); + if (state->key_up_fn) + state->key_up_fn(state->priv); + __pm_relax(&state->combo_up_wake_source); +} + +static void keycombo_event(struct input_handle *handle, unsigned int type, + unsigned int code, int value) +{ + unsigned long flags; + struct keycombo_state *state = handle->private; + + if (type != EV_KEY) + return; + + if (code >= KEY_MAX) + return; + + if (!test_bit(code, state->keybit)) + return; + + spin_lock_irqsave(&state->lock, flags); + if (!test_bit(code, state->key) == !value) + goto done; + __change_bit(code, state->key); + if (test_bit(code, state->upbit)) { + if (value) + state->key_up++; + else + state->key_up--; + } else { + if (value) + state->key_down++; + else + state->key_down--; + } + if (state->key_down == state->key_down_target && state->key_up == 0) { + __pm_stay_awake(&state->combo_held_wake_source); + state->key_is_down = 1; + if (queue_delayed_work(state->wq, &state->key_down_work, + state->delay)) + pr_debug("Key down work already queued!"); + } else if (state->key_is_down) { + if (!cancel_delayed_work(&state->key_down_work)) { + __pm_stay_awake(&state->combo_up_wake_source); + queue_work(state->wq, &state->key_up_work); + } + __pm_relax(&state->combo_held_wake_source); + state->key_is_down = 0; + } +done: + spin_unlock_irqrestore(&state->lock, flags); +} + +static int keycombo_connect(struct input_handler *handler, + struct input_dev *dev, + const struct input_device_id *id) +{ + int i; + int ret; + struct input_handle *handle; + struct keycombo_state *state = + container_of(handler, struct keycombo_state, input_handler); + for (i = 0; i < KEY_MAX; i++) { + if (test_bit(i, state->keybit) && test_bit(i, dev->keybit)) + break; + } + if (i == KEY_MAX) + return -ENODEV; + + handle = kzalloc(sizeof(*handle), GFP_KERNEL); + if (!handle) + return -ENOMEM; + + handle->dev = dev; + handle->handler = handler; + handle->name = KEYCOMBO_NAME; + handle->private = state; + + ret = input_register_handle(handle); + if (ret) + goto err_input_register_handle; + + ret = input_open_device(handle); + if (ret) + goto err_input_open_device; + + return 0; + +err_input_open_device: + input_unregister_handle(handle); +err_input_register_handle: + kfree(handle); + return ret; +} + +static void keycombo_disconnect(struct input_handle *handle) +{ + input_close_device(handle); + input_unregister_handle(handle); + kfree(handle); +} + +static const struct input_device_id keycombo_ids[] = { + { + .flags = INPUT_DEVICE_ID_MATCH_EVBIT, + .evbit = { BIT_MASK(EV_KEY) }, + }, + { }, +}; +MODULE_DEVICE_TABLE(input, keycombo_ids); + +static int keycombo_probe(struct platform_device *pdev) +{ + int ret; + int key, *keyp; + struct keycombo_state *state; + struct keycombo_platform_data *pdata = pdev->dev.platform_data; + + if (!pdata) + return -EINVAL; + + state = kzalloc(sizeof(*state), GFP_KERNEL); + if (!state) + return -ENOMEM; + + spin_lock_init(&state->lock); + keyp = pdata->keys_down; + while ((key = *keyp++)) { + if (key >= KEY_MAX) + continue; + state->key_down_target++; + __set_bit(key, state->keybit); + } + if (pdata->keys_up) { + keyp = pdata->keys_up; + while ((key = *keyp++)) { + if (key >= KEY_MAX) + continue; + __set_bit(key, state->keybit); + __set_bit(key, state->upbit); + } + } + + state->wq = alloc_ordered_workqueue("keycombo", 0); + if (!state->wq) + return -ENOMEM; + + state->priv = pdata->priv; + + if (pdata->key_down_fn) + state->key_down_fn = pdata->key_down_fn; + INIT_DELAYED_WORK(&state->key_down_work, do_key_down); + + if (pdata->key_up_fn) + state->key_up_fn = pdata->key_up_fn; + INIT_WORK(&state->key_up_work, do_key_up); + + wakeup_source_init(&state->combo_held_wake_source, "key combo"); + wakeup_source_init(&state->combo_up_wake_source, "key combo up"); + state->delay = msecs_to_jiffies(pdata->key_down_delay); + + state->input_handler.event = keycombo_event; + state->input_handler.connect = keycombo_connect; + state->input_handler.disconnect = keycombo_disconnect; + state->input_handler.name = KEYCOMBO_NAME; + state->input_handler.id_table = keycombo_ids; + ret = input_register_handler(&state->input_handler); + if (ret) { + kfree(state); + return ret; + } + platform_set_drvdata(pdev, state); + return 0; +} + +int keycombo_remove(struct platform_device *pdev) +{ + struct keycombo_state *state = platform_get_drvdata(pdev); + input_unregister_handler(&state->input_handler); + destroy_workqueue(state->wq); + kfree(state); + return 0; +} + + +struct platform_driver keycombo_driver = { + .driver.name = KEYCOMBO_NAME, + .probe = keycombo_probe, + .remove = keycombo_remove, +}; + +static int __init keycombo_init(void) +{ + return platform_driver_register(&keycombo_driver); +} + +static void __exit keycombo_exit(void) +{ + return platform_driver_unregister(&keycombo_driver); +} + +module_init(keycombo_init); +module_exit(keycombo_exit); diff --git a/drivers/input/keyreset.c b/drivers/input/keyreset.c new file mode 100644 index 000000000000..7e5222aec7c1 --- /dev/null +++ b/drivers/input/keyreset.c @@ -0,0 +1,144 @@ +/* drivers/input/keyreset.c + * + * Copyright (C) 2014 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/input.h> +#include <linux/keyreset.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/reboot.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/syscalls.h> +#include <linux/keycombo.h> + +struct keyreset_state { + int restart_requested; + int (*reset_fn)(void); + struct platform_device *pdev_child; + struct work_struct restart_work; +}; + +static void do_restart(struct work_struct *unused) +{ + orderly_reboot(); +} + +static void do_reset_fn(void *priv) +{ + struct keyreset_state *state = priv; + if (state->restart_requested) + panic("keyboard reset failed, %d", state->restart_requested); + if (state->reset_fn) { + state->restart_requested = state->reset_fn(); + } else { + pr_info("keyboard reset\n"); + schedule_work(&state->restart_work); + state->restart_requested = 1; + } +} + +static int keyreset_probe(struct platform_device *pdev) +{ + int ret = -ENOMEM; + struct keycombo_platform_data *pdata_child; + struct keyreset_platform_data *pdata = pdev->dev.platform_data; + int up_size = 0, down_size = 0, size; + int key, *keyp; + struct keyreset_state *state; + + if (!pdata) + return -EINVAL; + state = devm_kzalloc(&pdev->dev, sizeof(*state), GFP_KERNEL); + if (!state) + return -ENOMEM; + + state->pdev_child = platform_device_alloc(KEYCOMBO_NAME, + PLATFORM_DEVID_AUTO); + if (!state->pdev_child) + return -ENOMEM; + state->pdev_child->dev.parent = &pdev->dev; + INIT_WORK(&state->restart_work, do_restart); + + keyp = pdata->keys_down; + while ((key = *keyp++)) { + if (key >= KEY_MAX) + continue; + down_size++; + } + if (pdata->keys_up) { + keyp = pdata->keys_up; + while ((key = *keyp++)) { + if (key >= KEY_MAX) + continue; + up_size++; + } + } + size = sizeof(struct keycombo_platform_data) + + sizeof(int) * (down_size + 1); + pdata_child = devm_kzalloc(&pdev->dev, size, GFP_KERNEL); + if (!pdata_child) + goto error; + memcpy(pdata_child->keys_down, pdata->keys_down, + sizeof(int) * down_size); + if (up_size > 0) { + pdata_child->keys_up = devm_kzalloc(&pdev->dev, up_size + 1, + GFP_KERNEL); + if (!pdata_child->keys_up) + goto error; + memcpy(pdata_child->keys_up, pdata->keys_up, + sizeof(int) * up_size); + if (!pdata_child->keys_up) + goto error; + } + state->reset_fn = pdata->reset_fn; + pdata_child->key_down_fn = do_reset_fn; + pdata_child->priv = state; + pdata_child->key_down_delay = pdata->key_down_delay; + ret = platform_device_add_data(state->pdev_child, pdata_child, size); + if (ret) + goto error; + platform_set_drvdata(pdev, state); + return platform_device_add(state->pdev_child); +error: + platform_device_put(state->pdev_child); + return ret; +} + +int keyreset_remove(struct platform_device *pdev) +{ + struct keyreset_state *state = platform_get_drvdata(pdev); + platform_device_put(state->pdev_child); + return 0; +} + + +struct platform_driver keyreset_driver = { + .driver.name = KEYRESET_NAME, + .probe = keyreset_probe, + .remove = keyreset_remove, +}; + +static int __init keyreset_init(void) +{ + return platform_driver_register(&keyreset_driver); +} + +static void __exit keyreset_exit(void) +{ + return platform_driver_unregister(&keyreset_driver); +} + +module_init(keyreset_init); +module_exit(keyreset_exit); diff --git a/drivers/input/misc/Kconfig b/drivers/input/misc/Kconfig index 9f082a388388..3ad985ed8cd6 100644 --- a/drivers/input/misc/Kconfig +++ b/drivers/input/misc/Kconfig @@ -535,6 +535,11 @@ config INPUT_SGI_BTNS To compile this driver as a module, choose M here: the module will be called sgi_btns. +config INPUT_GPIO + tristate "GPIO driver support" + help + Say Y here if you want to support gpio based keys, wheels etc... + config HP_SDC_RTC tristate "HP SDC Real Time Clock" depends on (GSC || HP300) && SERIO diff --git a/drivers/input/misc/Makefile b/drivers/input/misc/Makefile index 4b6118d313fe..8da2b882c134 100644 --- a/drivers/input/misc/Makefile +++ b/drivers/input/misc/Makefile @@ -38,6 +38,7 @@ obj-$(CONFIG_INPUT_GP2A) += gp2ap002a00f.o obj-$(CONFIG_INPUT_GPIO_BEEPER) += gpio-beeper.o obj-$(CONFIG_INPUT_GPIO_TILT_POLLED) += gpio_tilt_polled.o obj-$(CONFIG_INPUT_GPIO_DECODER) += gpio_decoder.o +obj-$(CONFIG_INPUT_GPIO) += gpio_event.o gpio_matrix.o gpio_input.o gpio_output.o gpio_axis.o obj-$(CONFIG_INPUT_HISI_POWERKEY) += hisi_powerkey.o obj-$(CONFIG_HP_SDC_RTC) += hp_sdc_rtc.o obj-$(CONFIG_INPUT_IMS_PCU) += ims-pcu.o diff --git a/drivers/input/misc/gpio_axis.c b/drivers/input/misc/gpio_axis.c new file mode 100644 index 000000000000..0acf4a576f53 --- /dev/null +++ b/drivers/input/misc/gpio_axis.c @@ -0,0 +1,192 @@ +/* drivers/input/misc/gpio_axis.c + * + * Copyright (C) 2007 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/kernel.h> +#include <linux/gpio.h> +#include <linux/gpio_event.h> +#include <linux/interrupt.h> +#include <linux/slab.h> + +struct gpio_axis_state { + struct gpio_event_input_devs *input_devs; + struct gpio_event_axis_info *info; + uint32_t pos; +}; + +uint16_t gpio_axis_4bit_gray_map_table[] = { + [0x0] = 0x0, [0x1] = 0x1, /* 0000 0001 */ + [0x3] = 0x2, [0x2] = 0x3, /* 0011 0010 */ + [0x6] = 0x4, [0x7] = 0x5, /* 0110 0111 */ + [0x5] = 0x6, [0x4] = 0x7, /* 0101 0100 */ + [0xc] = 0x8, [0xd] = 0x9, /* 1100 1101 */ + [0xf] = 0xa, [0xe] = 0xb, /* 1111 1110 */ + [0xa] = 0xc, [0xb] = 0xd, /* 1010 1011 */ + [0x9] = 0xe, [0x8] = 0xf, /* 1001 1000 */ +}; +uint16_t gpio_axis_4bit_gray_map(struct gpio_event_axis_info *info, uint16_t in) +{ + return gpio_axis_4bit_gray_map_table[in]; +} + +uint16_t gpio_axis_5bit_singletrack_map_table[] = { + [0x10] = 0x00, [0x14] = 0x01, [0x1c] = 0x02, /* 10000 10100 11100 */ + [0x1e] = 0x03, [0x1a] = 0x04, [0x18] = 0x05, /* 11110 11010 11000 */ + [0x08] = 0x06, [0x0a] = 0x07, [0x0e] = 0x08, /* 01000 01010 01110 */ + [0x0f] = 0x09, [0x0d] = 0x0a, [0x0c] = 0x0b, /* 01111 01101 01100 */ + [0x04] = 0x0c, [0x05] = 0x0d, [0x07] = 0x0e, /* 00100 00101 00111 */ + [0x17] = 0x0f, [0x16] = 0x10, [0x06] = 0x11, /* 10111 10110 00110 */ + [0x02] = 0x12, [0x12] = 0x13, [0x13] = 0x14, /* 00010 10010 10011 */ + [0x1b] = 0x15, [0x0b] = 0x16, [0x03] = 0x17, /* 11011 01011 00011 */ + [0x01] = 0x18, [0x09] = 0x19, [0x19] = 0x1a, /* 00001 01001 11001 */ + [0x1d] = 0x1b, [0x15] = 0x1c, [0x11] = 0x1d, /* 11101 10101 10001 */ +}; +uint16_t gpio_axis_5bit_singletrack_map( + struct gpio_event_axis_info *info, uint16_t in) +{ + return gpio_axis_5bit_singletrack_map_table[in]; +} + +static void gpio_event_update_axis(struct gpio_axis_state *as, int report) +{ + struct gpio_event_axis_info *ai = as->info; + int i; + int change; + uint16_t state = 0; + uint16_t pos; + uint16_t old_pos = as->pos; + for (i = ai->count - 1; i >= 0; i--) + state = (state << 1) | gpio_get_value(ai->gpio[i]); + pos = ai->map(ai, state); + if (ai->flags & GPIOEAF_PRINT_RAW) + pr_info("axis %d-%d raw %x, pos %d -> %d\n", + ai->type, ai->code, state, old_pos, pos); + if (report && pos != old_pos) { + if (ai->type == EV_REL) { + change = (ai->decoded_size + pos - old_pos) % + ai->decoded_size; + if (change > ai->decoded_size / 2) + change -= ai->decoded_size; + if (change == ai->decoded_size / 2) { + if (ai->flags & GPIOEAF_PRINT_EVENT) + pr_info("axis %d-%d unknown direction, " + "pos %d -> %d\n", ai->type, + ai->code, old_pos, pos); + change = 0; /* no closest direction */ + } + if (ai->flags & GPIOEAF_PRINT_EVENT) + pr_info("axis %d-%d change %d\n", + ai->type, ai->code, change); + input_report_rel(as->input_devs->dev[ai->dev], + ai->code, change); + } else { + if (ai->flags & GPIOEAF_PRINT_EVENT) + pr_info("axis %d-%d now %d\n", + ai->type, ai->code, pos); + input_event(as->input_devs->dev[ai->dev], + ai->type, ai->code, pos); + } + input_sync(as->input_devs->dev[ai->dev]); + } + as->pos = pos; +} + +static irqreturn_t gpio_axis_irq_handler(int irq, void *dev_id) +{ + struct gpio_axis_state *as = dev_id; + gpio_event_update_axis(as, 1); + return IRQ_HANDLED; +} + +int gpio_event_axis_func(struct gpio_event_input_devs *input_devs, + struct gpio_event_info *info, void **data, int func) +{ + int ret; + int i; + int irq; + struct gpio_event_axis_info *ai; + struct gpio_axis_state *as; + + ai = container_of(info, struct gpio_event_axis_info, info); + if (func == GPIO_EVENT_FUNC_SUSPEND) { + for (i = 0; i < ai->count; i++) + disable_irq(gpio_to_irq(ai->gpio[i])); + return 0; + } + if (func == GPIO_EVENT_FUNC_RESUME) { + for (i = 0; i < ai->count; i++) + enable_irq(gpio_to_irq(ai->gpio[i])); + return 0; + } + + if (func == GPIO_EVENT_FUNC_INIT) { + *data = as = kmalloc(sizeof(*as), GFP_KERNEL); + if (as == NULL) { + ret = -ENOMEM; + goto err_alloc_axis_state_failed; + } + as->input_devs = input_devs; + as->info = ai; + if (ai->dev >= input_devs->count) { + pr_err("gpio_event_axis: bad device index %d >= %d " + "for %d:%d\n", ai->dev, input_devs->count, + ai->type, ai->code); + ret = -EINVAL; + goto err_bad_device_index; + } + + input_set_capability(input_devs->dev[ai->dev], + ai->type, ai->code); + if (ai->type == EV_ABS) { + input_set_abs_params(input_devs->dev[ai->dev], ai->code, + 0, ai->decoded_size - 1, 0, 0); + } + for (i = 0; i < ai->count; i++) { + ret = gpio_request(ai->gpio[i], "gpio_event_axis"); + if (ret < 0) + goto err_request_gpio_failed; + ret = gpio_direction_input(ai->gpio[i]); + if (ret < 0) + goto err_gpio_direction_input_failed; + ret = irq = gpio_to_irq(ai->gpio[i]); + if (ret < 0) + goto err_get_irq_num_failed; + ret = request_irq(irq, gpio_axis_irq_handler, + IRQF_TRIGGER_RISING | + IRQF_TRIGGER_FALLING, + "gpio_event_axis", as); + if (ret < 0) + goto err_request_irq_failed; + } + gpio_event_update_axis(as, 0); + return 0; + } + + ret = 0; + as = *data; + for (i = ai->count - 1; i >= 0; i--) { + free_irq(gpio_to_irq(ai->gpio[i]), as); +err_request_irq_failed: +err_get_irq_num_failed: +err_gpio_direction_input_failed: + gpio_free(ai->gpio[i]); +err_request_gpio_failed: + ; + } +err_bad_device_index: + kfree(as); + *data = NULL; +err_alloc_axis_state_failed: + return ret; +} diff --git a/drivers/input/misc/gpio_event.c b/drivers/input/misc/gpio_event.c new file mode 100644 index 000000000000..90f07eba3ce9 --- /dev/null +++ b/drivers/input/misc/gpio_event.c @@ -0,0 +1,228 @@ +/* drivers/input/misc/gpio_event.c + * + * Copyright (C) 2007 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/module.h> +#include <linux/input.h> +#include <linux/gpio_event.h> +#include <linux/hrtimer.h> +#include <linux/platform_device.h> +#include <linux/slab.h> + +struct gpio_event { + struct gpio_event_input_devs *input_devs; + const struct gpio_event_platform_data *info; + void *state[0]; +}; + +static int gpio_input_event( + struct input_dev *dev, unsigned int type, unsigned int code, int value) +{ + int i; + int devnr; + int ret = 0; + int tmp_ret; + struct gpio_event_info **ii; + struct gpio_event *ip = input_get_drvdata(dev); + + for (devnr = 0; devnr < ip->input_devs->count; devnr++) + if (ip->input_devs->dev[devnr] == dev) + break; + if (devnr == ip->input_devs->count) { + pr_err("gpio_input_event: unknown device %p\n", dev); + return -EIO; + } + + for (i = 0, ii = ip->info->info; i < ip->info->info_count; i++, ii++) { + if ((*ii)->event) { + tmp_ret = (*ii)->event(ip->input_devs, *ii, + &ip->state[i], + devnr, type, code, value); + if (tmp_ret) + ret = tmp_ret; + } + } + return ret; +} + +static int gpio_event_call_all_func(struct gpio_event *ip, int func) +{ + int i; + int ret; + struct gpio_event_info **ii; + + if (func == GPIO_EVENT_FUNC_INIT || func == GPIO_EVENT_FUNC_RESUME) { + ii = ip->info->info; + for (i = 0; i < ip->info->info_count; i++, ii++) { + if ((*ii)->func == NULL) { + ret = -ENODEV; + pr_err("gpio_event_probe: Incomplete pdata, " + "no function\n"); + goto err_no_func; + } + if (func == GPIO_EVENT_FUNC_RESUME && (*ii)->no_suspend) + continue; + ret = (*ii)->func(ip->input_devs, *ii, &ip->state[i], + func); + if (ret) { + pr_err("gpio_event_probe: function failed\n"); + goto err_func_failed; + } + } + return 0; + } + + ret = 0; + i = ip->info->info_count; + ii = ip->info->info + i; + while (i > 0) { + i--; + ii--; + if ((func & ~1) == GPIO_EVENT_FUNC_SUSPEND && (*ii)->no_suspend) + continue; + (*ii)->func(ip->input_devs, *ii, &ip->state[i], func & ~1); +err_func_failed: +err_no_func: + ; + } + return ret; +} + +static void __maybe_unused gpio_event_suspend(struct gpio_event *ip) +{ + gpio_event_call_all_func(ip, GPIO_EVENT_FUNC_SUSPEND); + if (ip->info->power) + ip->info->power(ip->info, 0); +} + +static void __maybe_unused gpio_event_resume(struct gpio_event *ip) +{ + if (ip->info->power) + ip->info->power(ip->info, 1); + gpio_event_call_all_func(ip, GPIO_EVENT_FUNC_RESUME); +} + +static int gpio_event_probe(struct platform_device *pdev) +{ + int err; + struct gpio_event *ip; + struct gpio_event_platform_data *event_info; + int dev_count = 1; + int i; + int registered = 0; + + event_info = pdev->dev.platform_data; + if (event_info == NULL) { + pr_err("gpio_event_probe: No pdata\n"); + return -ENODEV; + } + if ((!event_info->name && !event_info->names[0]) || + !event_info->info || !event_info->info_count) { + pr_err("gpio_event_probe: Incomplete pdata\n"); + return -ENODEV; + } + if (!event_info->name) + while (event_info->names[dev_count]) + dev_count++; + ip = kzalloc(sizeof(*ip) + + sizeof(ip->state[0]) * event_info->info_count + + sizeof(*ip->input_devs) + + sizeof(ip->input_devs->dev[0]) * dev_count, GFP_KERNEL); + if (ip == NULL) { + err = -ENOMEM; + pr_err("gpio_event_probe: Failed to allocate private data\n"); + goto err_kp_alloc_failed; + } + ip->input_devs = (void*)&ip->state[event_info->info_count]; + platform_set_drvdata(pdev, ip); + + for (i = 0; i < dev_count; i++) { + struct input_dev *input_dev = input_allocate_device(); + if (input_dev == NULL) { + err = -ENOMEM; + pr_err("gpio_event_probe: " + "Failed to allocate input device\n"); + goto err_input_dev_alloc_failed; + } + input_set_drvdata(input_dev, ip); + input_dev->name = event_info->name ? + event_info->name : event_info->names[i]; + input_dev->event = gpio_input_event; + ip->input_devs->dev[i] = input_dev; + } + ip->input_devs->count = dev_count; + ip->info = event_info; + if (event_info->power) + ip->info->power(ip->info, 1); + + err = gpio_event_call_all_func(ip, GPIO_EVENT_FUNC_INIT); + if (err) + goto err_call_all_func_failed; + + for (i = 0; i < dev_count; i++) { + err = input_register_device(ip->input_devs->dev[i]); + if (err) { + pr_err("gpio_event_probe: Unable to register %s " + "input device\n", ip->input_devs->dev[i]->name); + goto err_input_register_device_failed; + } + registered++; + } + + return 0; + +err_input_register_device_failed: + gpio_event_call_all_func(ip, GPIO_EVENT_FUNC_UNINIT); +err_call_all_func_failed: + if (event_info->power) + ip->info->power(ip->info, 0); + for (i = 0; i < registered; i++) + input_unregister_device(ip->input_devs->dev[i]); + for (i = dev_count - 1; i >= registered; i--) { + input_free_device(ip->input_devs->dev[i]); +err_input_dev_alloc_failed: + ; + } + kfree(ip); +err_kp_alloc_failed: + return err; +} + +static int gpio_event_remove(struct platform_device *pdev) +{ + struct gpio_event *ip = platform_get_drvdata(pdev); + int i; + + gpio_event_call_all_func(ip, GPIO_EVENT_FUNC_UNINIT); + if (ip->info->power) + ip->info->power(ip->info, 0); + for (i = 0; i < ip->input_devs->count; i++) + input_unregister_device(ip->input_devs->dev[i]); + kfree(ip); + return 0; +} + +static struct platform_driver gpio_event_driver = { + .probe = gpio_event_probe, + .remove = gpio_event_remove, + .driver = { + .name = GPIO_EVENT_DEV_NAME, + }, +}; + +module_platform_driver(gpio_event_driver); + +MODULE_DESCRIPTION("GPIO Event Driver"); +MODULE_LICENSE("GPL"); + diff --git a/drivers/input/misc/gpio_input.c b/drivers/input/misc/gpio_input.c new file mode 100644 index 000000000000..5875d739c550 --- /dev/null +++ b/drivers/input/misc/gpio_input.c @@ -0,0 +1,390 @@ +/* drivers/input/misc/gpio_input.c + * + * Copyright (C) 2007 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/kernel.h> +#include <linux/gpio.h> +#include <linux/gpio_event.h> +#include <linux/hrtimer.h> +#include <linux/input.h> +#include <linux/interrupt.h> +#include <linux/slab.h> +#include <linux/pm_wakeup.h> + +enum { + DEBOUNCE_UNSTABLE = BIT(0), /* Got irq, while debouncing */ + DEBOUNCE_PRESSED = BIT(1), + DEBOUNCE_NOTPRESSED = BIT(2), + DEBOUNCE_WAIT_IRQ = BIT(3), /* Stable irq state */ + DEBOUNCE_POLL = BIT(4), /* Stable polling state */ + + DEBOUNCE_UNKNOWN = + DEBOUNCE_PRESSED | DEBOUNCE_NOTPRESSED, +}; + +struct gpio_key_state { + struct gpio_input_state *ds; + uint8_t debounce; +}; + +struct gpio_input_state { + struct gpio_event_input_devs *input_devs; + const struct gpio_event_input_info *info; + struct hrtimer timer; + int use_irq; + int debounce_count; + spinlock_t irq_lock; + struct wakeup_source *ws; + struct gpio_key_state key_state[0]; +}; + +static enum hrtimer_restart gpio_event_input_timer_func(struct hrtimer *timer) +{ + int i; + int pressed; + struct gpio_input_state *ds = + container_of(timer, struct gpio_input_state, timer); + unsigned gpio_flags = ds->info->flags; + unsigned npolarity; + int nkeys = ds->info->keymap_size; + const struct gpio_event_direct_entry *key_entry; + struct gpio_key_state *key_state; + unsigned long irqflags; + uint8_t debounce; + bool sync_needed; + +#if 0 + key_entry = kp->keys_info->keymap; + key_state = kp->key_state; + for (i = 0; i < nkeys; i++, key_entry++, key_state++) + pr_info("gpio_read_detect_status %d %d\n", key_entry->gpio, + gpio_read_detect_status(key_entry->gpio)); +#endif + key_entry = ds->info->keymap; + key_state = ds->key_state; + sync_needed = false; + spin_lock_irqsave(&ds->irq_lock, irqflags); + for (i = 0; i < nkeys; i++, key_entry++, key_state++) { + debounce = key_state->debounce; + if (debounce & DEBOUNCE_WAIT_IRQ) + continue; + if (key_state->debounce & DEBOUNCE_UNSTABLE) { + debounce = key_state->debounce = DEBOUNCE_UNKNOWN; + enable_irq(gpio_to_irq(key_entry->gpio)); + if (gpio_flags & GPIOEDF_PRINT_KEY_UNSTABLE) + pr_info("gpio_keys_scan_keys: key %x-%x, %d " + "(%d) continue debounce\n", + ds->info->type, key_entry->code, + i, key_entry->gpio); + } + npolarity = !(gpio_flags & GPIOEDF_ACTIVE_HIGH); + pressed = gpio_get_value(key_entry->gpio) ^ npolarity; + if (debounce & DEBOUNCE_POLL) { + if (pressed == !(debounce & DEBOUNCE_PRESSED)) { + ds->debounce_count++; + key_state->debounce = DEBOUNCE_UNKNOWN; + if (gpio_flags & GPIOEDF_PRINT_KEY_DEBOUNCE) + pr_info("gpio_keys_scan_keys: key %x-" + "%x, %d (%d) start debounce\n", + ds->info->type, key_entry->code, + i, key_entry->gpio); + } + continue; + } + if (pressed && (debounce & DEBOUNCE_NOTPRESSED)) { + if (gpio_flags & GPIOEDF_PRINT_KEY_DEBOUNCE) + pr_info("gpio_keys_scan_keys: key %x-%x, %d " + "(%d) debounce pressed 1\n", + ds->info->type, key_entry->code, + i, key_entry->gpio); + key_state->debounce = DEBOUNCE_PRESSED; + continue; + } + if (!pressed && (debounce & DEBOUNCE_PRESSED)) { + if (gpio_flags & GPIOEDF_PRINT_KEY_DEBOUNCE) + pr_info("gpio_keys_scan_keys: key %x-%x, %d " + "(%d) debounce pressed 0\n", + ds->info->type, key_entry->code, + i, key_entry->gpio); + key_state->debounce = DEBOUNCE_NOTPRESSED; + continue; + } + /* key is stable */ + ds->debounce_count--; + if (ds->use_irq) + key_state->debounce |= DEBOUNCE_WAIT_IRQ; + else + key_state->debounce |= DEBOUNCE_POLL; + if (gpio_flags & GPIOEDF_PRINT_KEYS) + pr_info("gpio_keys_scan_keys: key %x-%x, %d (%d) " + "changed to %d\n", ds->info->type, + key_entry->code, i, key_entry->gpio, pressed); + input_event(ds->input_devs->dev[key_entry->dev], ds->info->type, + key_entry->code, pressed); + sync_needed = true; + } + if (sync_needed) { + for (i = 0; i < ds->input_devs->count; i++) + input_sync(ds->input_devs->dev[i]); + } + +#if 0 + key_entry = kp->keys_info->keymap; + key_state = kp->key_state; + for (i = 0; i < nkeys; i++, key_entry++, key_state++) { + pr_info("gpio_read_detect_status %d %d\n", key_entry->gpio, + gpio_read_detect_status(key_entry->gpio)); + } +#endif + + if (ds->debounce_count) + hrtimer_start(timer, ds->info->debounce_time, HRTIMER_MODE_REL); + else if (!ds->use_irq) + hrtimer_start(timer, ds->info->poll_time, HRTIMER_MODE_REL); + else + __pm_relax(ds->ws); + + spin_unlock_irqrestore(&ds->irq_lock, irqflags); + + return HRTIMER_NORESTART; +} + +static irqreturn_t gpio_event_input_irq_handler(int irq, void *dev_id) +{ + struct gpio_key_state *ks = dev_id; + struct gpio_input_state *ds = ks->ds; + int keymap_index = ks - ds->key_state; + const struct gpio_event_direct_entry *key_entry; + unsigned long irqflags; + int pressed; + + if (!ds->use_irq) + return IRQ_HANDLED; + + key_entry = &ds->info->keymap[keymap_index]; + + if (ds->info->debounce_time) { + spin_lock_irqsave(&ds->irq_lock, irqflags); + if (ks->debounce & DEBOUNCE_WAIT_IRQ) { + ks->debounce = DEBOUNCE_UNKNOWN; + if (ds->debounce_count++ == 0) { + __pm_stay_awake(ds->ws); + hrtimer_start( + &ds->timer, ds->info->debounce_time, + HRTIMER_MODE_REL); + } + if (ds->info->flags & GPIOEDF_PRINT_KEY_DEBOUNCE) + pr_info("gpio_event_input_irq_handler: " + "key %x-%x, %d (%d) start debounce\n", + ds->info->type, key_entry->code, + keymap_index, key_entry->gpio); + } else { + disable_irq_nosync(irq); + ks->debounce = DEBOUNCE_UNSTABLE; + } + spin_unlock_irqrestore(&ds->irq_lock, irqflags); + } else { + pressed = gpio_get_value(key_entry->gpio) ^ + !(ds->info->flags & GPIOEDF_ACTIVE_HIGH); + if (ds->info->flags & GPIOEDF_PRINT_KEYS) + pr_info("gpio_event_input_irq_handler: key %x-%x, %d " + "(%d) changed to %d\n", + ds->info->type, key_entry->code, keymap_index, + key_entry->gpio, pressed); + input_event(ds->input_devs->dev[key_entry->dev], ds->info->type, + key_entry->code, pressed); + input_sync(ds->input_devs->dev[key_entry->dev]); + } + return IRQ_HANDLED; +} + +static int gpio_event_input_request_irqs(struct gpio_input_state *ds) +{ + int i; + int err; + unsigned int irq; + unsigned long req_flags = IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING; + + for (i = 0; i < ds->info->keymap_size; i++) { + err = irq = gpio_to_irq(ds->info->keymap[i].gpio); + if (err < 0) + goto err_gpio_get_irq_num_failed; + err = request_irq(irq, gpio_event_input_irq_handler, + req_flags, "gpio_keys", &ds->key_state[i]); + if (err) { + pr_err("gpio_event_input_request_irqs: request_irq " + "failed for input %d, irq %d\n", + ds->info->keymap[i].gpio, irq); + goto err_request_irq_failed; + } + if (ds->info->info.no_suspend) { + err = enable_irq_wake(irq); + if (err) { + pr_err("gpio_event_input_request_irqs: " + "enable_irq_wake failed for input %d, " + "irq %d\n", + ds->info->keymap[i].gpio, irq); + goto err_enable_irq_wake_failed; + } + } + } + return 0; + + for (i = ds->info->keymap_size - 1; i >= 0; i--) { + irq = gpio_to_irq(ds->info->keymap[i].gpio); + if (ds->info->info.no_suspend) + disable_irq_wake(irq); +err_enable_irq_wake_failed: + free_irq(irq, &ds->key_state[i]); +err_request_irq_failed: +err_gpio_get_irq_num_failed: + ; + } + return err; +} + +int gpio_event_input_func(struct gpio_event_input_devs *input_devs, + struct gpio_event_info *info, void **data, int func) +{ + int ret; + int i; + unsigned long irqflags; + struct gpio_event_input_info *di; + struct gpio_input_state *ds = *data; + char *wlname; + + di = container_of(info, struct gpio_event_input_info, info); + + if (func == GPIO_EVENT_FUNC_SUSPEND) { + if (ds->use_irq) + for (i = 0; i < di->keymap_size; i++) + disable_irq(gpio_to_irq(di->keymap[i].gpio)); + hrtimer_cancel(&ds->timer); + return 0; + } + if (func == GPIO_EVENT_FUNC_RESUME) { + spin_lock_irqsave(&ds->irq_lock, irqflags); + if (ds->use_irq) + for (i = 0; i < di->keymap_size; i++) + enable_irq(gpio_to_irq(di->keymap[i].gpio)); + hrtimer_start(&ds->timer, ktime_set(0, 0), HRTIMER_MODE_REL); + spin_unlock_irqrestore(&ds->irq_lock, irqflags); + return 0; + } + + if (func == GPIO_EVENT_FUNC_INIT) { + if (ktime_to_ns(di->poll_time) <= 0) + di->poll_time = ktime_set(0, 20 * NSEC_PER_MSEC); + + *data = ds = kzalloc(sizeof(*ds) + sizeof(ds->key_state[0]) * + di->keymap_size, GFP_KERNEL); + if (ds == NULL) { + ret = -ENOMEM; + pr_err("gpio_event_input_func: " + "Failed to allocate private data\n"); + goto err_ds_alloc_failed; + } + ds->debounce_count = di->keymap_size; + ds->input_devs = input_devs; + ds->info = di; + wlname = kasprintf(GFP_KERNEL, "gpio_input:%s%s", + input_devs->dev[0]->name, + (input_devs->count > 1) ? "..." : ""); + + ds->ws = wakeup_source_register(wlname); + kfree(wlname); + if (!ds->ws) { + ret = -ENOMEM; + pr_err("gpio_event_input_func: " + "Failed to allocate wakeup source\n"); + goto err_ws_failed; + } + + spin_lock_init(&ds->irq_lock); + + for (i = 0; i < di->keymap_size; i++) { + int dev = di->keymap[i].dev; + if (dev >= input_devs->count) { + pr_err("gpio_event_input_func: bad device " + "index %d >= %d for key code %d\n", + dev, input_devs->count, + di->keymap[i].code); + ret = -EINVAL; + goto err_bad_keymap; + } + input_set_capability(input_devs->dev[dev], di->type, + di->keymap[i].code); + ds->key_state[i].ds = ds; + ds->key_state[i].debounce = DEBOUNCE_UNKNOWN; + } + + for (i = 0; i < di->keymap_size; i++) { + ret = gpio_request(di->keymap[i].gpio, "gpio_kp_in"); + if (ret) { + pr_err("gpio_event_input_func: gpio_request " + "failed for %d\n", di->keymap[i].gpio); + goto err_gpio_request_failed; + } + ret = gpio_direction_input(di->keymap[i].gpio); + if (ret) { + pr_err("gpio_event_input_func: " + "gpio_direction_input failed for %d\n", + di->keymap[i].gpio); + goto err_gpio_configure_failed; + } + } + + ret = gpio_event_input_request_irqs(ds); + + spin_lock_irqsave(&ds->irq_lock, irqflags); + ds->use_irq = ret == 0; + + pr_info("GPIO Input Driver: Start gpio inputs for %s%s in %s " + "mode\n", input_devs->dev[0]->name, + (input_devs->count > 1) ? "..." : "", + ret == 0 ? "interrupt" : "polling"); + + hrtimer_init(&ds->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + ds->timer.function = gpio_event_input_timer_func; + hrtimer_start(&ds->timer, ktime_set(0, 0), HRTIMER_MODE_REL); + spin_unlock_irqrestore(&ds->irq_lock, irqflags); + return 0; + } + + ret = 0; + spin_lock_irqsave(&ds->irq_lock, irqflags); + hrtimer_cancel(&ds->timer); + if (ds->use_irq) { + for (i = di->keymap_size - 1; i >= 0; i--) { + int irq = gpio_to_irq(di->keymap[i].gpio); + if (ds->info->info.no_suspend) + disable_irq_wake(irq); + free_irq(irq, &ds->key_state[i]); + } + } + spin_unlock_irqrestore(&ds->irq_lock, irqflags); + + for (i = di->keymap_size - 1; i >= 0; i--) { +err_gpio_configure_failed: + gpio_free(di->keymap[i].gpio); +err_gpio_request_failed: + ; + } +err_bad_keymap: + wakeup_source_unregister(ds->ws); +err_ws_failed: + kfree(ds); +err_ds_alloc_failed: + return ret; +} diff --git a/drivers/input/misc/gpio_matrix.c b/drivers/input/misc/gpio_matrix.c new file mode 100644 index 000000000000..08769dd88f56 --- /dev/null +++ b/drivers/input/misc/gpio_matrix.c @@ -0,0 +1,440 @@ +/* drivers/input/misc/gpio_matrix.c + * + * Copyright (C) 2007 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/kernel.h> +#include <linux/gpio.h> +#include <linux/gpio_event.h> +#include <linux/hrtimer.h> +#include <linux/interrupt.h> +#include <linux/slab.h> + +struct gpio_kp { + struct gpio_event_input_devs *input_devs; + struct gpio_event_matrix_info *keypad_info; + struct hrtimer timer; + struct wakeup_source wake_src; + int current_output; + unsigned int use_irq:1; + unsigned int key_state_changed:1; + unsigned int last_key_state_changed:1; + unsigned int some_keys_pressed:2; + unsigned int disabled_irq:1; + unsigned long keys_pressed[0]; +}; + +static void clear_phantom_key(struct gpio_kp *kp, int out, int in) +{ + struct gpio_event_matrix_info *mi = kp->keypad_info; + int key_index = out * mi->ninputs + in; + unsigned short keyentry = mi->keymap[key_index]; + unsigned short keycode = keyentry & MATRIX_KEY_MASK; + unsigned short dev = keyentry >> MATRIX_CODE_BITS; + + if (!test_bit(keycode, kp->input_devs->dev[dev]->key)) { + if (mi->flags & GPIOKPF_PRINT_PHANTOM_KEYS) + pr_info("gpiomatrix: phantom key %x, %d-%d (%d-%d) " + "cleared\n", keycode, out, in, + mi->output_gpios[out], mi->input_gpios[in]); + __clear_bit(key_index, kp->keys_pressed); + } else { + if (mi->flags & GPIOKPF_PRINT_PHANTOM_KEYS) + pr_info("gpiomatrix: phantom key %x, %d-%d (%d-%d) " + "not cleared\n", keycode, out, in, + mi->output_gpios[out], mi->input_gpios[in]); + } +} + +static int restore_keys_for_input(struct gpio_kp *kp, int out, int in) +{ + int rv = 0; + int key_index; + + key_index = out * kp->keypad_info->ninputs + in; + while (out < kp->keypad_info->noutputs) { + if (test_bit(key_index, kp->keys_pressed)) { + rv = 1; + clear_phantom_key(kp, out, in); + } + key_index += kp->keypad_info->ninputs; + out++; + } + return rv; +} + +static void remove_phantom_keys(struct gpio_kp *kp) +{ + int out, in, inp; + int key_index; + + if (kp->some_keys_pressed < 3) + return; + + for (out = 0; out < kp->keypad_info->noutputs; out++) { + inp = -1; + key_index = out * kp->keypad_info->ninputs; + for (in = 0; in < kp->keypad_info->ninputs; in++, key_index++) { + if (test_bit(key_index, kp->keys_pressed)) { + if (inp == -1) { + inp = in; + continue; + } + if (inp >= 0) { + if (!restore_keys_for_input(kp, out + 1, + inp)) + break; + clear_phantom_key(kp, out, inp); + inp = -2; + } + restore_keys_for_input(kp, out, in); + } + } + } +} + +static void report_key(struct gpio_kp *kp, int key_index, int out, int in) +{ + struct gpio_event_matrix_info *mi = kp->keypad_info; + int pressed = test_bit(key_index, kp->keys_pressed); + unsigned short keyentry = mi->keymap[key_index]; + unsigned short keycode = keyentry & MATRIX_KEY_MASK; + unsigned short dev = keyentry >> MATRIX_CODE_BITS; + + if (pressed != test_bit(keycode, kp->input_devs->dev[dev]->key)) { + if (keycode == KEY_RESERVED) { + if (mi->flags & GPIOKPF_PRINT_UNMAPPED_KEYS) + pr_info("gpiomatrix: unmapped key, %d-%d " + "(%d-%d) changed to %d\n", + out, in, mi->output_gpios[out], + mi->input_gpios[in], pressed); + } else { + if (mi->flags & GPIOKPF_PRINT_MAPPED_KEYS) + pr_info("gpiomatrix: key %x, %d-%d (%d-%d) " + "changed to %d\n", keycode, + out, in, mi->output_gpios[out], + mi->input_gpios[in], pressed); + input_report_key(kp->input_devs->dev[dev], keycode, pressed); + } + } +} + +static void report_sync(struct gpio_kp *kp) +{ + int i; + + for (i = 0; i < kp->input_devs->count; i++) + input_sync(kp->input_devs->dev[i]); +} + +static enum hrtimer_restart gpio_keypad_timer_func(struct hrtimer *timer) +{ + int out, in; + int key_index; + int gpio; + struct gpio_kp *kp = container_of(timer, struct gpio_kp, timer); + struct gpio_event_matrix_info *mi = kp->keypad_info; + unsigned gpio_keypad_flags = mi->flags; + unsigned polarity = !!(gpio_keypad_flags & GPIOKPF_ACTIVE_HIGH); + + out = kp->current_output; + if (out == mi->noutputs) { + out = 0; + kp->last_key_state_changed = kp->key_state_changed; + kp->key_state_changed = 0; + kp->some_keys_pressed = 0; + } else { + key_index = out * mi->ninputs; + for (in = 0; in < mi->ninputs; in++, key_index++) { + gpio = mi->input_gpios[in]; + if (gpio_get_value(gpio) ^ !polarity) { + if (kp->some_keys_pressed < 3) + kp->some_keys_pressed++; + kp->key_state_changed |= !__test_and_set_bit( + key_index, kp->keys_pressed); + } else + kp->key_state_changed |= __test_and_clear_bit( + key_index, kp->keys_pressed); + } + gpio = mi->output_gpios[out]; + if (gpio_keypad_flags & GPIOKPF_DRIVE_INACTIVE) + gpio_set_value(gpio, !polarity); + else + gpio_direction_input(gpio); + out++; + } + kp->current_output = out; + if (out < mi->noutputs) { + gpio = mi->output_gpios[out]; + if (gpio_keypad_flags & GPIOKPF_DRIVE_INACTIVE) + gpio_set_value(gpio, polarity); + else + gpio_direction_output(gpio, polarity); + hrtimer_start(timer, mi->settle_time, HRTIMER_MODE_REL); + return HRTIMER_NORESTART; + } + if (gpio_keypad_flags & GPIOKPF_DEBOUNCE) { + if (kp->key_state_changed) { + hrtimer_start(&kp->timer, mi->debounce_delay, + HRTIMER_MODE_REL); + return HRTIMER_NORESTART; + } + kp->key_state_changed = kp->last_key_state_changed; + } + if (kp->key_state_changed) { + if (gpio_keypad_flags & GPIOKPF_REMOVE_SOME_PHANTOM_KEYS) + remove_phantom_keys(kp); + key_index = 0; + for (out = 0; out < mi->noutputs; out++) + for (in = 0; in < mi->ninputs; in++, key_index++) + report_key(kp, key_index, out, in); + report_sync(kp); + } + if (!kp->use_irq || kp->some_keys_pressed) { + hrtimer_start(timer, mi->poll_time, HRTIMER_MODE_REL); + return HRTIMER_NORESTART; + } + + /* No keys are pressed, reenable interrupt */ + for (out = 0; out < mi->noutputs; out++) { + if (gpio_keypad_flags & GPIOKPF_DRIVE_INACTIVE) + gpio_set_value(mi->output_gpios[out], polarity); + else + gpio_direction_output(mi->output_gpios[out], polarity); + } + for (in = 0; in < mi->ninputs; in++) + enable_irq(gpio_to_irq(mi->input_gpios[in])); + __pm_relax(&kp->wake_src); + return HRTIMER_NORESTART; +} + +static irqreturn_t gpio_keypad_irq_handler(int irq_in, void *dev_id) +{ + int i; + struct gpio_kp *kp = dev_id; + struct gpio_event_matrix_info *mi = kp->keypad_info; + unsigned gpio_keypad_flags = mi->flags; + + if (!kp->use_irq) { + /* ignore interrupt while registering the handler */ + kp->disabled_irq = 1; + disable_irq_nosync(irq_in); + return IRQ_HANDLED; + } + + for (i = 0; i < mi->ninputs; i++) + disable_irq_nosync(gpio_to_irq(mi->input_gpios[i])); + for (i = 0; i < mi->noutputs; i++) { + if (gpio_keypad_flags & GPIOKPF_DRIVE_INACTIVE) + gpio_set_value(mi->output_gpios[i], + !(gpio_keypad_flags & GPIOKPF_ACTIVE_HIGH)); + else + gpio_direction_input(mi->output_gpios[i]); + } + __pm_stay_awake(&kp->wake_src); + hrtimer_start(&kp->timer, ktime_set(0, 0), HRTIMER_MODE_REL); + return IRQ_HANDLED; +} + +static int gpio_keypad_request_irqs(struct gpio_kp *kp) +{ + int i; + int err; + unsigned int irq; + unsigned long request_flags; + struct gpio_event_matrix_info *mi = kp->keypad_info; + + switch (mi->flags & (GPIOKPF_ACTIVE_HIGH|GPIOKPF_LEVEL_TRIGGERED_IRQ)) { + default: + request_flags = IRQF_TRIGGER_FALLING; + break; + case GPIOKPF_ACTIVE_HIGH: + request_flags = IRQF_TRIGGER_RISING; + break; + case GPIOKPF_LEVEL_TRIGGERED_IRQ: + request_flags = IRQF_TRIGGER_LOW; + break; + case GPIOKPF_LEVEL_TRIGGERED_IRQ | GPIOKPF_ACTIVE_HIGH: + request_flags = IRQF_TRIGGER_HIGH; + break; + } + + for (i = 0; i < mi->ninputs; i++) { + err = irq = gpio_to_irq(mi->input_gpios[i]); + if (err < 0) + goto err_gpio_get_irq_num_failed; + err = request_irq(irq, gpio_keypad_irq_handler, request_flags, + "gpio_kp", kp); + if (err) { + pr_err("gpiomatrix: request_irq failed for input %d, " + "irq %d\n", mi->input_gpios[i], irq); + goto err_request_irq_failed; + } + err = enable_irq_wake(irq); + if (err) { + pr_err("gpiomatrix: set_irq_wake failed for input %d, " + "irq %d\n", mi->input_gpios[i], irq); + } + disable_irq(irq); + if (kp->disabled_irq) { + kp->disabled_irq = 0; + enable_irq(irq); + } + } + return 0; + + for (i = mi->noutputs - 1; i >= 0; i--) { + free_irq(gpio_to_irq(mi->input_gpios[i]), kp); +err_request_irq_failed: +err_gpio_get_irq_num_failed: + ; + } + return err; +} + +int gpio_event_matrix_func(struct gpio_event_input_devs *input_devs, + struct gpio_event_info *info, void **data, int func) +{ + int i; + int err; + int key_count; + struct gpio_kp *kp; + struct gpio_event_matrix_info *mi; + + mi = container_of(info, struct gpio_event_matrix_info, info); + if (func == GPIO_EVENT_FUNC_SUSPEND || func == GPIO_EVENT_FUNC_RESUME) { + /* TODO: disable scanning */ + return 0; + } + + if (func == GPIO_EVENT_FUNC_INIT) { + if (mi->keymap == NULL || + mi->input_gpios == NULL || + mi->output_gpios == NULL) { + err = -ENODEV; + pr_err("gpiomatrix: Incomplete pdata\n"); + goto err_invalid_platform_data; + } + key_count = mi->ninputs * mi->noutputs; + + *data = kp = kzalloc(sizeof(*kp) + sizeof(kp->keys_pressed[0]) * + BITS_TO_LONGS(key_count), GFP_KERNEL); + if (kp == NULL) { + err = -ENOMEM; + pr_err("gpiomatrix: Failed to allocate private data\n"); + goto err_kp_alloc_failed; + } + kp->input_devs = input_devs; + kp->keypad_info = mi; + for (i = 0; i < key_count; i++) { + unsigned short keyentry = mi->keymap[i]; + unsigned short keycode = keyentry & MATRIX_KEY_MASK; + unsigned short dev = keyentry >> MATRIX_CODE_BITS; + if (dev >= input_devs->count) { + pr_err("gpiomatrix: bad device index %d >= " + "%d for key code %d\n", + dev, input_devs->count, keycode); + err = -EINVAL; + goto err_bad_keymap; + } + if (keycode && keycode <= KEY_MAX) + input_set_capability(input_devs->dev[dev], + EV_KEY, keycode); + } + + for (i = 0; i < mi->noutputs; i++) { + err = gpio_request(mi->output_gpios[i], "gpio_kp_out"); + if (err) { + pr_err("gpiomatrix: gpio_request failed for " + "output %d\n", mi->output_gpios[i]); + goto err_request_output_gpio_failed; + } + if (gpio_cansleep(mi->output_gpios[i])) { + pr_err("gpiomatrix: unsupported output gpio %d," + " can sleep\n", mi->output_gpios[i]); + err = -EINVAL; + goto err_output_gpio_configure_failed; + } + if (mi->flags & GPIOKPF_DRIVE_INACTIVE) + err = gpio_direction_output(mi->output_gpios[i], + !(mi->flags & GPIOKPF_ACTIVE_HIGH)); + else + err = gpio_direction_input(mi->output_gpios[i]); + if (err) { + pr_err("gpiomatrix: gpio_configure failed for " + "output %d\n", mi->output_gpios[i]); + goto err_output_gpio_configure_failed; + } + } + for (i = 0; i < mi->ninputs; i++) { + err = gpio_request(mi->input_gpios[i], "gpio_kp_in"); + if (err) { + pr_err("gpiomatrix: gpio_request failed for " + "input %d\n", mi->input_gpios[i]); + goto err_request_input_gpio_failed; + } + err = gpio_direction_input(mi->input_gpios[i]); + if (err) { + pr_err("gpiomatrix: gpio_direction_input failed" + " for input %d\n", mi->input_gpios[i]); + goto err_gpio_direction_input_failed; + } + } + kp->current_output = mi->noutputs; + kp->key_state_changed = 1; + + hrtimer_init(&kp->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + kp->timer.function = gpio_keypad_timer_func; + wakeup_source_init(&kp->wake_src, "gpio_kp"); + err = gpio_keypad_request_irqs(kp); + kp->use_irq = err == 0; + + pr_info("GPIO Matrix Keypad Driver: Start keypad matrix for " + "%s%s in %s mode\n", input_devs->dev[0]->name, + (input_devs->count > 1) ? "..." : "", + kp->use_irq ? "interrupt" : "polling"); + + if (kp->use_irq) + __pm_stay_awake(&kp->wake_src); + hrtimer_start(&kp->timer, ktime_set(0, 0), HRTIMER_MODE_REL); + + return 0; + } + + err = 0; + kp = *data; + + if (kp->use_irq) + for (i = mi->noutputs - 1; i >= 0; i--) + free_irq(gpio_to_irq(mi->input_gpios[i]), kp); + + hrtimer_cancel(&kp->timer); + wakeup_source_trash(&kp->wake_src); + for (i = mi->noutputs - 1; i >= 0; i--) { +err_gpio_direction_input_failed: + gpio_free(mi->input_gpios[i]); +err_request_input_gpio_failed: + ; + } + for (i = mi->noutputs - 1; i >= 0; i--) { +err_output_gpio_configure_failed: + gpio_free(mi->output_gpios[i]); +err_request_output_gpio_failed: + ; + } +err_bad_keymap: + kfree(kp); +err_kp_alloc_failed: +err_invalid_platform_data: + return err; +} diff --git a/drivers/input/misc/gpio_output.c b/drivers/input/misc/gpio_output.c new file mode 100644 index 000000000000..2aac2fad0a17 --- /dev/null +++ b/drivers/input/misc/gpio_output.c @@ -0,0 +1,97 @@ +/* drivers/input/misc/gpio_output.c + * + * Copyright (C) 2007 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/kernel.h> +#include <linux/gpio.h> +#include <linux/gpio_event.h> + +int gpio_event_output_event( + struct gpio_event_input_devs *input_devs, struct gpio_event_info *info, + void **data, unsigned int dev, unsigned int type, + unsigned int code, int value) +{ + int i; + struct gpio_event_output_info *oi; + oi = container_of(info, struct gpio_event_output_info, info); + if (type != oi->type) + return 0; + if (!(oi->flags & GPIOEDF_ACTIVE_HIGH)) + value = !value; + for (i = 0; i < oi->keymap_size; i++) + if (dev == oi->keymap[i].dev && code == oi->keymap[i].code) + gpio_set_value(oi->keymap[i].gpio, value); + return 0; +} + +int gpio_event_output_func( + struct gpio_event_input_devs *input_devs, struct gpio_event_info *info, + void **data, int func) +{ + int ret; + int i; + struct gpio_event_output_info *oi; + oi = container_of(info, struct gpio_event_output_info, info); + + if (func == GPIO_EVENT_FUNC_SUSPEND || func == GPIO_EVENT_FUNC_RESUME) + return 0; + + if (func == GPIO_EVENT_FUNC_INIT) { + int output_level = !(oi->flags & GPIOEDF_ACTIVE_HIGH); + + for (i = 0; i < oi->keymap_size; i++) { + int dev = oi->keymap[i].dev; + if (dev >= input_devs->count) { + pr_err("gpio_event_output_func: bad device " + "index %d >= %d for key code %d\n", + dev, input_devs->count, + oi->keymap[i].code); + ret = -EINVAL; + goto err_bad_keymap; + } + input_set_capability(input_devs->dev[dev], oi->type, + oi->keymap[i].code); + } + + for (i = 0; i < oi->keymap_size; i++) { + ret = gpio_request(oi->keymap[i].gpio, + "gpio_event_output"); + if (ret) { + pr_err("gpio_event_output_func: gpio_request " + "failed for %d\n", oi->keymap[i].gpio); + goto err_gpio_request_failed; + } + ret = gpio_direction_output(oi->keymap[i].gpio, + output_level); + if (ret) { + pr_err("gpio_event_output_func: " + "gpio_direction_output failed for %d\n", + oi->keymap[i].gpio); + goto err_gpio_direction_output_failed; + } + } + return 0; + } + + ret = 0; + for (i = oi->keymap_size - 1; i >= 0; i--) { +err_gpio_direction_output_failed: + gpio_free(oi->keymap[i].gpio); +err_gpio_request_failed: + ; + } +err_bad_keymap: + return ret; +} + diff --git a/drivers/isdn/hardware/mISDN/avmfritz.c b/drivers/isdn/hardware/mISDN/avmfritz.c index dce6632daae1..ae2b2669af1b 100644 --- a/drivers/isdn/hardware/mISDN/avmfritz.c +++ b/drivers/isdn/hardware/mISDN/avmfritz.c @@ -156,7 +156,7 @@ _set_debug(struct fritzcard *card) } static int -set_debug(const char *val, struct kernel_param *kp) +set_debug(const char *val, const struct kernel_param *kp) { int ret; struct fritzcard *card; diff --git a/drivers/isdn/hardware/mISDN/mISDNinfineon.c b/drivers/isdn/hardware/mISDN/mISDNinfineon.c index d5bdbaf93a1a..1fc290659e94 100644 --- a/drivers/isdn/hardware/mISDN/mISDNinfineon.c +++ b/drivers/isdn/hardware/mISDN/mISDNinfineon.c @@ -244,7 +244,7 @@ _set_debug(struct inf_hw *card) } static int -set_debug(const char *val, struct kernel_param *kp) +set_debug(const char *val, const struct kernel_param *kp) { int ret; struct inf_hw *card; diff --git a/drivers/isdn/hardware/mISDN/netjet.c b/drivers/isdn/hardware/mISDN/netjet.c index 6a6d848bd18e..89d9ba8ed535 100644 --- a/drivers/isdn/hardware/mISDN/netjet.c +++ b/drivers/isdn/hardware/mISDN/netjet.c @@ -111,7 +111,7 @@ _set_debug(struct tiger_hw *card) } static int -set_debug(const char *val, struct kernel_param *kp) +set_debug(const char *val, const struct kernel_param *kp) { int ret; struct tiger_hw *card; diff --git a/drivers/isdn/hardware/mISDN/speedfax.c b/drivers/isdn/hardware/mISDN/speedfax.c index 9815bb4eec9c..1f1446ed8d5f 100644 --- a/drivers/isdn/hardware/mISDN/speedfax.c +++ b/drivers/isdn/hardware/mISDN/speedfax.c @@ -94,7 +94,7 @@ _set_debug(struct sfax_hw *card) } static int -set_debug(const char *val, struct kernel_param *kp) +set_debug(const char *val, const struct kernel_param *kp) { int ret; struct sfax_hw *card; diff --git a/drivers/isdn/hardware/mISDN/w6692.c b/drivers/isdn/hardware/mISDN/w6692.c index d80072fef434..209036a4af3a 100644 --- a/drivers/isdn/hardware/mISDN/w6692.c +++ b/drivers/isdn/hardware/mISDN/w6692.c @@ -101,7 +101,7 @@ _set_debug(struct w6692_hw *card) } static int -set_debug(const char *val, struct kernel_param *kp) +set_debug(const char *val, const struct kernel_param *kp) { int ret; struct w6692_hw *card; diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index 4a249ee86364..0e643556bb44 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -540,4 +540,63 @@ config DM_ZONED If unsure, say N. +config DM_VERITY_AVB + tristate "Support AVB specific verity error behavior" + depends on DM_VERITY + ---help--- + Enables Android Verified Boot platform-specific error + behavior. In particular, it will modify the vbmeta partition + specified on the kernel command-line when non-transient error + occurs (followed by a panic). + +config DM_ANDROID_VERITY + bool "Android verity target support" + depends on BLK_DEV_DM=y + depends on DM_VERITY=y + depends on X509_CERTIFICATE_PARSER + depends on SYSTEM_TRUSTED_KEYRING + depends on CRYPTO_RSA + depends on KEYS + depends on ASYMMETRIC_KEY_TYPE + depends on ASYMMETRIC_PUBLIC_KEY_SUBTYPE + ---help--- + This device-mapper target is virtually a VERITY target. This + target is setup by reading the metadata contents piggybacked + to the actual data blocks in the block device. The signature + of the metadata contents are verified against the key included + in the system keyring. Upon success, the underlying verity + target is setup. + +config DM_ANDROID_VERITY_AT_MOST_ONCE_DEFAULT_ENABLED + bool "Verity will validate blocks at most once" + depends on DM_VERITY + ---help--- + Default enables at_most_once option for dm-verity + + Verify data blocks only the first time they are read from the + data device, rather than every time. This reduces the overhead + of dm-verity so that it can be used on systems that are memory + and/or CPU constrained. However, it provides a reduced level + of security because only offline tampering of the data device's + content will be detected, not online tampering. + + Hash blocks are still verified each time they are read from the + hash device, since verification of hash blocks is less performance + critical than data blocks, and a hash block will not be verified + any more after all the data blocks it covers have been verified anyway. + + If unsure, say N. + +config DM_BOW + tristate "Backup block device" + depends on BLK_DEV_DM + select DM_BUFIO + ---help--- + This device-mapper target takes a device and keeps a log of all + changes using free blocks identified by issuing a trim command. + This can then be restored by running a command line utility, + or committed by simply replacing the target. + + If unsure, say N. + endif # MD diff --git a/drivers/md/Makefile b/drivers/md/Makefile index e94b6f9be941..214be71181f4 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -63,6 +63,7 @@ obj-$(CONFIG_DM_ERA) += dm-era.o obj-$(CONFIG_DM_LOG_WRITES) += dm-log-writes.o obj-$(CONFIG_DM_INTEGRITY) += dm-integrity.o obj-$(CONFIG_DM_ZONED) += dm-zoned.o +obj-$(CONFIG_DM_BOW) += dm-bow.o ifeq ($(CONFIG_DM_UEVENT),y) dm-mod-objs += dm-uevent.o @@ -71,3 +72,11 @@ endif ifeq ($(CONFIG_DM_VERITY_FEC),y) dm-verity-objs += dm-verity-fec.o endif + +ifeq ($(CONFIG_DM_VERITY_AVB),y) +dm-verity-objs += dm-verity-avb.o +endif + +ifeq ($(CONFIG_DM_ANDROID_VERITY),y) +dm-verity-objs += dm-android-verity.o +endif diff --git a/drivers/md/dm-android-verity.c b/drivers/md/dm-android-verity.c new file mode 100644 index 000000000000..20e05936551f --- /dev/null +++ b/drivers/md/dm-android-verity.c @@ -0,0 +1,925 @@ +/* + * Copyright (C) 2015 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/buffer_head.h> +#include <linux/debugfs.h> +#include <linux/delay.h> +#include <linux/device.h> +#include <linux/device-mapper.h> +#include <linux/errno.h> +#include <linux/fs.h> +#include <linux/fcntl.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/key.h> +#include <linux/module.h> +#include <linux/mount.h> +#include <linux/namei.h> +#include <linux/of.h> +#include <linux/reboot.h> +#include <linux/string.h> +#include <linux/vmalloc.h> + +#include <asm/setup.h> +#include <crypto/hash.h> +#include <crypto/hash_info.h> +#include <crypto/public_key.h> +#include <crypto/sha.h> +#include <keys/asymmetric-type.h> +#include <keys/system_keyring.h> + +#include "dm-verity.h" +#include "dm-android-verity.h" + +static char verifiedbootstate[VERITY_COMMANDLINE_PARAM_LENGTH]; +static char veritymode[VERITY_COMMANDLINE_PARAM_LENGTH]; +static char veritykeyid[VERITY_DEFAULT_KEY_ID_LENGTH]; +static char buildvariant[BUILD_VARIANT]; + +static bool target_added; +static bool verity_enabled = true; +struct dentry *debug_dir; +static int android_verity_ctr(struct dm_target *ti, unsigned argc, char **argv); + +static struct target_type android_verity_target = { + .name = "android-verity", + .version = {1, 0, 0}, + .module = THIS_MODULE, + .ctr = android_verity_ctr, + .dtr = verity_dtr, + .map = verity_map, + .status = verity_status, + .prepare_ioctl = verity_prepare_ioctl, + .iterate_devices = verity_iterate_devices, + .io_hints = verity_io_hints, +}; + +static int __init verified_boot_state_param(char *line) +{ + strlcpy(verifiedbootstate, line, sizeof(verifiedbootstate)); + return 1; +} + +__setup("androidboot.verifiedbootstate=", verified_boot_state_param); + +static int __init verity_mode_param(char *line) +{ + strlcpy(veritymode, line, sizeof(veritymode)); + return 1; +} + +__setup("androidboot.veritymode=", verity_mode_param); + +static int __init verity_keyid_param(char *line) +{ + strlcpy(veritykeyid, line, sizeof(veritykeyid)); + return 1; +} + +__setup("veritykeyid=", verity_keyid_param); + +static int __init verity_buildvariant(char *line) +{ + strlcpy(buildvariant, line, sizeof(buildvariant)); + return 1; +} + +__setup("buildvariant=", verity_buildvariant); + +static inline bool default_verity_key_id(void) +{ + return veritykeyid[0] != '\0'; +} + +static inline bool is_eng(void) +{ + static const char typeeng[] = "eng"; + + return !strncmp(buildvariant, typeeng, sizeof(typeeng)); +} + +static inline bool is_userdebug(void) +{ + static const char typeuserdebug[] = "userdebug"; + + return !strncmp(buildvariant, typeuserdebug, sizeof(typeuserdebug)); +} + +static inline bool is_unlocked(void) +{ + static const char unlocked[] = "orange"; + + return !strncmp(verifiedbootstate, unlocked, sizeof(unlocked)); +} + +static int read_block_dev(struct bio_read *payload, struct block_device *bdev, + sector_t offset, int length) +{ + struct bio *bio; + int err = 0, i; + + payload->number_of_pages = DIV_ROUND_UP(length, PAGE_SIZE); + + bio = bio_alloc(GFP_KERNEL, payload->number_of_pages); + if (!bio) { + DMERR("Error while allocating bio"); + return -ENOMEM; + } + + bio_set_dev(bio, bdev); + bio->bi_iter.bi_sector = offset; + bio_set_op_attrs(bio, REQ_OP_READ, 0); + + payload->page_io = kzalloc(sizeof(struct page *) * + payload->number_of_pages, GFP_KERNEL); + if (!payload->page_io) { + DMERR("page_io array alloc failed"); + err = -ENOMEM; + goto free_bio; + } + + for (i = 0; i < payload->number_of_pages; i++) { + payload->page_io[i] = alloc_page(GFP_KERNEL); + if (!payload->page_io[i]) { + DMERR("alloc_page failed"); + err = -ENOMEM; + goto free_pages; + } + if (!bio_add_page(bio, payload->page_io[i], PAGE_SIZE, 0)) { + DMERR("bio_add_page error"); + err = -EIO; + goto free_pages; + } + } + + if (!submit_bio_wait(bio)) + /* success */ + goto free_bio; + DMERR("bio read failed"); + err = -EIO; + +free_pages: + for (i = 0; i < payload->number_of_pages; i++) + if (payload->page_io[i]) + __free_page(payload->page_io[i]); + kfree(payload->page_io); +free_bio: + bio_put(bio); + return err; +} + +static inline u64 fec_div_round_up(u64 x, u64 y) +{ + u64 remainder; + + return div64_u64_rem(x, y, &remainder) + + (remainder > 0 ? 1 : 0); +} + +static inline void populate_fec_metadata(struct fec_header *header, + struct fec_ecc_metadata *ecc) +{ + ecc->blocks = fec_div_round_up(le64_to_cpu(header->inp_size), + FEC_BLOCK_SIZE); + ecc->roots = le32_to_cpu(header->roots); + ecc->start = le64_to_cpu(header->inp_size); +} + +static inline int validate_fec_header(struct fec_header *header, u64 offset) +{ + /* move offset to make the sanity check work for backup header + * as well. */ + offset -= offset % FEC_BLOCK_SIZE; + if (le32_to_cpu(header->magic) != FEC_MAGIC || + le32_to_cpu(header->version) != FEC_VERSION || + le32_to_cpu(header->size) != sizeof(struct fec_header) || + le32_to_cpu(header->roots) == 0 || + le32_to_cpu(header->roots) >= FEC_RSM) + return -EINVAL; + + return 0; +} + +static int extract_fec_header(dev_t dev, struct fec_header *fec, + struct fec_ecc_metadata *ecc) +{ + u64 device_size; + struct bio_read payload; + int i, err = 0; + struct block_device *bdev; + + bdev = blkdev_get_by_dev(dev, FMODE_READ, NULL); + + if (IS_ERR_OR_NULL(bdev)) { + DMERR("bdev get error"); + return PTR_ERR(bdev); + } + + device_size = i_size_read(bdev->bd_inode); + + /* fec metadata size is a power of 2 and PAGE_SIZE + * is a power of 2 as well. + */ + BUG_ON(FEC_BLOCK_SIZE > PAGE_SIZE); + /* 512 byte sector alignment */ + BUG_ON(((device_size - FEC_BLOCK_SIZE) % (1 << SECTOR_SHIFT)) != 0); + + err = read_block_dev(&payload, bdev, (device_size - + FEC_BLOCK_SIZE) / (1 << SECTOR_SHIFT), FEC_BLOCK_SIZE); + if (err) { + DMERR("Error while reading verity metadata"); + goto error; + } + + BUG_ON(sizeof(struct fec_header) > PAGE_SIZE); + memcpy(fec, page_address(payload.page_io[0]), + sizeof(*fec)); + + ecc->valid = true; + if (validate_fec_header(fec, device_size - FEC_BLOCK_SIZE)) { + /* Try the backup header */ + memcpy(fec, page_address(payload.page_io[0]) + FEC_BLOCK_SIZE + - sizeof(*fec) , + sizeof(*fec)); + if (validate_fec_header(fec, device_size - + sizeof(struct fec_header))) + ecc->valid = false; + } + + if (ecc->valid) + populate_fec_metadata(fec, ecc); + + for (i = 0; i < payload.number_of_pages; i++) + __free_page(payload.page_io[i]); + kfree(payload.page_io); + +error: + blkdev_put(bdev, FMODE_READ); + return err; +} +static void find_metadata_offset(struct fec_header *fec, + struct block_device *bdev, u64 *metadata_offset) +{ + u64 device_size; + + device_size = i_size_read(bdev->bd_inode); + + if (le32_to_cpu(fec->magic) == FEC_MAGIC) + *metadata_offset = le64_to_cpu(fec->inp_size) - + VERITY_METADATA_SIZE; + else + *metadata_offset = device_size - VERITY_METADATA_SIZE; +} + +static int find_size(dev_t dev, u64 *device_size) +{ + struct block_device *bdev; + + bdev = blkdev_get_by_dev(dev, FMODE_READ, NULL); + if (IS_ERR_OR_NULL(bdev)) { + DMERR("blkdev_get_by_dev failed"); + return PTR_ERR(bdev); + } + + *device_size = i_size_read(bdev->bd_inode); + *device_size >>= SECTOR_SHIFT; + + DMINFO("blkdev size in sectors: %llu", *device_size); + blkdev_put(bdev, FMODE_READ); + return 0; +} + +static int verify_header(struct android_metadata_header *header) +{ + int retval = -EINVAL; + + if (is_userdebug() && le32_to_cpu(header->magic_number) == + VERITY_METADATA_MAGIC_DISABLE) + return VERITY_STATE_DISABLE; + + if (!(le32_to_cpu(header->magic_number) == + VERITY_METADATA_MAGIC_NUMBER) || + (le32_to_cpu(header->magic_number) == + VERITY_METADATA_MAGIC_DISABLE)) { + DMERR("Incorrect magic number"); + return retval; + } + + if (le32_to_cpu(header->protocol_version) != + VERITY_METADATA_VERSION) { + DMERR("Unsupported version %u", + le32_to_cpu(header->protocol_version)); + return retval; + } + + return 0; +} + +static int extract_metadata(dev_t dev, struct fec_header *fec, + struct android_metadata **metadata, + bool *verity_enabled) +{ + struct block_device *bdev; + struct android_metadata_header *header; + int i; + u32 table_length, copy_length, offset; + u64 metadata_offset; + struct bio_read payload; + int err = 0; + + bdev = blkdev_get_by_dev(dev, FMODE_READ, NULL); + + if (IS_ERR_OR_NULL(bdev)) { + DMERR("blkdev_get_by_dev failed"); + return -ENODEV; + } + + find_metadata_offset(fec, bdev, &metadata_offset); + + /* Verity metadata size is a power of 2 and PAGE_SIZE + * is a power of 2 as well. + * PAGE_SIZE is also a multiple of 512 bytes. + */ + if (VERITY_METADATA_SIZE > PAGE_SIZE) + BUG_ON(VERITY_METADATA_SIZE % PAGE_SIZE != 0); + /* 512 byte sector alignment */ + BUG_ON(metadata_offset % (1 << SECTOR_SHIFT) != 0); + + err = read_block_dev(&payload, bdev, metadata_offset / + (1 << SECTOR_SHIFT), VERITY_METADATA_SIZE); + if (err) { + DMERR("Error while reading verity metadata"); + goto blkdev_release; + } + + header = kzalloc(sizeof(*header), GFP_KERNEL); + if (!header) { + DMERR("kzalloc failed for header"); + err = -ENOMEM; + goto free_payload; + } + + memcpy(header, page_address(payload.page_io[0]), + sizeof(*header)); + + DMINFO("bio magic_number:%u protocol_version:%d table_length:%u", + le32_to_cpu(header->magic_number), + le32_to_cpu(header->protocol_version), + le32_to_cpu(header->table_length)); + + err = verify_header(header); + + if (err == VERITY_STATE_DISABLE) { + DMERR("Mounting root with verity disabled"); + *verity_enabled = false; + /* we would still have to read the metadata to figure out + * the data blocks size. Or may be could map the entire + * partition similar to mounting the device. + * + * Reset error as well as the verity_enabled flag is changed. + */ + err = 0; + } else if (err) + goto free_header; + + *metadata = kzalloc(sizeof(**metadata), GFP_KERNEL); + if (!*metadata) { + DMERR("kzalloc for metadata failed"); + err = -ENOMEM; + goto free_header; + } + + (*metadata)->header = header; + table_length = le32_to_cpu(header->table_length); + + if (table_length == 0 || + table_length > (VERITY_METADATA_SIZE - + sizeof(struct android_metadata_header))) { + DMERR("table_length too long"); + err = -EINVAL; + goto free_metadata; + } + + (*metadata)->verity_table = kzalloc(table_length + 1, GFP_KERNEL); + + if (!(*metadata)->verity_table) { + DMERR("kzalloc verity_table failed"); + err = -ENOMEM; + goto free_metadata; + } + + if (sizeof(struct android_metadata_header) + + table_length <= PAGE_SIZE) { + memcpy((*metadata)->verity_table, + page_address(payload.page_io[0]) + + sizeof(struct android_metadata_header), + table_length); + } else { + copy_length = PAGE_SIZE - + sizeof(struct android_metadata_header); + memcpy((*metadata)->verity_table, + page_address(payload.page_io[0]) + + sizeof(struct android_metadata_header), + copy_length); + table_length -= copy_length; + offset = copy_length; + i = 1; + while (table_length != 0) { + if (table_length > PAGE_SIZE) { + memcpy((*metadata)->verity_table + offset, + page_address(payload.page_io[i]), + PAGE_SIZE); + offset += PAGE_SIZE; + table_length -= PAGE_SIZE; + } else { + memcpy((*metadata)->verity_table + offset, + page_address(payload.page_io[i]), + table_length); + table_length = 0; + } + i++; + } + } + (*metadata)->verity_table[table_length] = '\0'; + + DMINFO("verity_table: %s", (*metadata)->verity_table); + goto free_payload; + +free_metadata: + kfree(*metadata); +free_header: + kfree(header); +free_payload: + for (i = 0; i < payload.number_of_pages; i++) + if (payload.page_io[i]) + __free_page(payload.page_io[i]); + kfree(payload.page_io); +blkdev_release: + blkdev_put(bdev, FMODE_READ); + return err; +} + +/* helper functions to extract properties from dts */ +const char *find_dt_value(const char *name) +{ + struct device_node *firmware; + const char *value; + + firmware = of_find_node_by_path("/firmware/android"); + if (!firmware) + return NULL; + value = of_get_property(firmware, name, NULL); + of_node_put(firmware); + + return value; +} + +static int verity_mode(void) +{ + static const char enforcing[] = "enforcing"; + static const char verified_mode_prop[] = "veritymode"; + const char *value; + + value = find_dt_value(verified_mode_prop); + if (!value) + value = veritymode; + if (!strncmp(value, enforcing, sizeof(enforcing) - 1)) + return DM_VERITY_MODE_RESTART; + + return DM_VERITY_MODE_EIO; +} + +static void handle_error(void) +{ + int mode = verity_mode(); + if (mode == DM_VERITY_MODE_RESTART) { + DMERR("triggering restart"); + kernel_restart("dm-verity device corrupted"); + } else { + DMERR("Mounting verity root failed"); + } +} + +static struct public_key_signature *table_make_digest( + enum hash_algo hash, + const void *table, + unsigned long table_len) +{ + struct public_key_signature *pks = NULL; + struct crypto_shash *tfm; + struct shash_desc *desc; + size_t digest_size, desc_size; + int ret; + + /* Allocate the hashing algorithm we're going to need and find out how + * big the hash operational data will be. + */ + tfm = crypto_alloc_shash(hash_algo_name[hash], 0, 0); + if (IS_ERR(tfm)) + return ERR_CAST(tfm); + + desc_size = crypto_shash_descsize(tfm) + sizeof(*desc); + digest_size = crypto_shash_digestsize(tfm); + + /* We allocate the hash operational data storage on the end of out + * context data and the digest output buffer on the end of that. + */ + ret = -ENOMEM; + pks = kzalloc(digest_size + sizeof(*pks) + desc_size, GFP_KERNEL); + if (!pks) + goto error; + + pks->pkey_algo = "rsa"; + pks->hash_algo = hash_algo_name[hash]; + pks->digest = (u8 *)pks + sizeof(*pks) + desc_size; + pks->digest_size = digest_size; + + desc = (struct shash_desc *)(pks + 1); + desc->tfm = tfm; + desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + + ret = crypto_shash_init(desc); + if (ret < 0) + goto error; + + ret = crypto_shash_finup(desc, table, table_len, pks->digest); + if (ret < 0) + goto error; + + crypto_free_shash(tfm); + return pks; + +error: + kfree(pks); + crypto_free_shash(tfm); + return ERR_PTR(ret); +} + + +static int verify_verity_signature(char *key_id, + struct android_metadata *metadata) +{ + struct public_key_signature *pks = NULL; + int retval = -EINVAL; + + if (!key_id) + goto error; + + pks = table_make_digest(HASH_ALGO_SHA256, + (const void *)metadata->verity_table, + le32_to_cpu(metadata->header->table_length)); + if (IS_ERR(pks)) { + DMERR("hashing failed"); + retval = PTR_ERR(pks); + pks = NULL; + goto error; + } + + pks->s = kmemdup(&metadata->header->signature[0], RSANUMBYTES, GFP_KERNEL); + if (!pks->s) { + DMERR("Error allocating memory for signature"); + goto error; + } + pks->s_size = RSANUMBYTES; + + retval = verify_signature_one(pks, NULL, key_id); + kfree(pks->s); +error: + kfree(pks); + return retval; +} + +static inline bool test_mult_overflow(sector_t a, u32 b) +{ + sector_t r = (sector_t)~0ULL; + + sector_div(r, b); + return a > r; +} + +static int add_as_linear_device(struct dm_target *ti, char *dev) +{ + /*Move to linear mapping defines*/ + char *linear_table_args[DM_LINEAR_ARGS] = {dev, + DM_LINEAR_TARGET_OFFSET}; + int err = 0; + + android_verity_target.dtr = dm_linear_dtr, + android_verity_target.map = dm_linear_map, + android_verity_target.status = dm_linear_status, + android_verity_target.end_io = dm_linear_end_io, + android_verity_target.prepare_ioctl = dm_linear_prepare_ioctl, + android_verity_target.iterate_devices = dm_linear_iterate_devices, + android_verity_target.direct_access = dm_linear_dax_direct_access, + android_verity_target.dax_copy_from_iter = dm_linear_dax_copy_from_iter, + android_verity_target.io_hints = NULL; + + set_disk_ro(dm_disk(dm_table_get_md(ti->table)), 0); + + err = dm_linear_ctr(ti, DM_LINEAR_ARGS, linear_table_args); + + if (!err) { + DMINFO("Added android-verity as a linear target"); + target_added = true; + } else + DMERR("Failed to add android-verity as linear target"); + + return err; +} + +static int create_linear_device(struct dm_target *ti, dev_t dev, + char *target_device) +{ + u64 device_size = 0; + int err = find_size(dev, &device_size); + + if (err) { + DMERR("error finding bdev size"); + handle_error(); + return err; + } + + ti->len = device_size; + err = add_as_linear_device(ti, target_device); + if (err) { + handle_error(); + return err; + } + verity_enabled = false; + return 0; +} + +/* + * Target parameters: + * <key id> Key id of the public key in the system keyring. + * Verity metadata's signature would be verified against + * this. If the key id contains spaces, replace them + * with '#'. + * <block device> The block device for which dm-verity is being setup. + */ +static int android_verity_ctr(struct dm_target *ti, unsigned argc, char **argv) +{ + dev_t uninitialized_var(dev); + struct android_metadata *metadata = NULL; + int err = 0, i, mode; + char *key_id = NULL, *table_ptr, dummy, *target_device; + char *verity_table_args[VERITY_TABLE_ARGS + 2 + VERITY_TABLE_OPT_FEC_ARGS]; + /* One for specifying number of opt args and one for mode */ + sector_t data_sectors; + u32 data_block_size; + unsigned int no_of_args = VERITY_TABLE_ARGS + 2 + VERITY_TABLE_OPT_FEC_ARGS; + struct fec_header uninitialized_var(fec); + struct fec_ecc_metadata uninitialized_var(ecc); + char buf[FEC_ARG_LENGTH], *buf_ptr; + unsigned long long tmpll; + + if (argc == 1) { + /* Use the default keyid */ + if (default_verity_key_id()) + key_id = veritykeyid; + else if (!is_eng()) { + DMERR("veritykeyid= is not set"); + handle_error(); + return -EINVAL; + } + target_device = argv[0]; + } else if (argc == 2) { + key_id = argv[0]; + target_device = argv[1]; + } else { + DMERR("Incorrect number of arguments"); + handle_error(); + return -EINVAL; + } + + dev = name_to_dev_t(target_device); + if (!dev) { + DMERR("no dev found for %s", target_device); + handle_error(); + return -EINVAL; + } + + if (is_eng()) + return create_linear_device(ti, dev, target_device); + + strreplace(key_id, '#', ' '); + + DMINFO("key:%s dev:%s", key_id, target_device); + + if (extract_fec_header(dev, &fec, &ecc)) { + DMERR("Error while extracting fec header"); + handle_error(); + return -EINVAL; + } + + err = extract_metadata(dev, &fec, &metadata, &verity_enabled); + + if (err) { + /* Allow invalid metadata when the device is unlocked */ + if (is_unlocked()) { + DMWARN("Allow invalid metadata when unlocked"); + return create_linear_device(ti, dev, target_device); + } + DMERR("Error while extracting metadata"); + handle_error(); + goto free_metadata; + } + + if (verity_enabled) { + err = verify_verity_signature(key_id, metadata); + + if (err) { + DMERR("Signature verification failed"); + handle_error(); + goto free_metadata; + } else + DMINFO("Signature verification success"); + } + + table_ptr = metadata->verity_table; + + for (i = 0; i < VERITY_TABLE_ARGS; i++) { + verity_table_args[i] = strsep(&table_ptr, " "); + if (verity_table_args[i] == NULL) + break; + } + + if (i != VERITY_TABLE_ARGS) { + DMERR("Verity table not in the expected format"); + err = -EINVAL; + handle_error(); + goto free_metadata; + } + + if (sscanf(verity_table_args[5], "%llu%c", &tmpll, &dummy) + != 1) { + DMERR("Verity table not in the expected format"); + handle_error(); + err = -EINVAL; + goto free_metadata; + } + + if (tmpll > ULONG_MAX) { + DMERR("<num_data_blocks> too large. Forgot to turn on CONFIG_LBDAF?"); + handle_error(); + err = -EINVAL; + goto free_metadata; + } + + data_sectors = tmpll; + + if (sscanf(verity_table_args[3], "%u%c", &data_block_size, &dummy) + != 1) { + DMERR("Verity table not in the expected format"); + handle_error(); + err = -EINVAL; + goto free_metadata; + } + + if (test_mult_overflow(data_sectors, data_block_size >> + SECTOR_SHIFT)) { + DMERR("data_sectors too large"); + handle_error(); + err = -EOVERFLOW; + goto free_metadata; + } + + data_sectors *= data_block_size >> SECTOR_SHIFT; + DMINFO("Data sectors %llu", (unsigned long long)data_sectors); + + /* update target length */ + ti->len = data_sectors; + + /* Setup linear target and free */ + if (!verity_enabled) { + err = add_as_linear_device(ti, target_device); + goto free_metadata; + } + + /*substitute data_dev and hash_dev*/ + verity_table_args[1] = target_device; + verity_table_args[2] = target_device; + + mode = verity_mode(); + + if (ecc.valid && IS_BUILTIN(CONFIG_DM_VERITY_FEC)) { + if (mode) { + err = snprintf(buf, FEC_ARG_LENGTH, + "%u %s " VERITY_TABLE_OPT_FEC_FORMAT, + 1 + VERITY_TABLE_OPT_FEC_ARGS, + mode == DM_VERITY_MODE_RESTART ? + VERITY_TABLE_OPT_RESTART : + VERITY_TABLE_OPT_LOGGING, + target_device, + ecc.start / FEC_BLOCK_SIZE, ecc.blocks, + ecc.roots); + } else { + err = snprintf(buf, FEC_ARG_LENGTH, + "%u " VERITY_TABLE_OPT_FEC_FORMAT, + VERITY_TABLE_OPT_FEC_ARGS, target_device, + ecc.start / FEC_BLOCK_SIZE, ecc.blocks, + ecc.roots); + } + } else if (mode) { + err = snprintf(buf, FEC_ARG_LENGTH, + "2 " VERITY_TABLE_OPT_IGNZERO " %s", + mode == DM_VERITY_MODE_RESTART ? + VERITY_TABLE_OPT_RESTART : VERITY_TABLE_OPT_LOGGING); + } else { + err = snprintf(buf, FEC_ARG_LENGTH, "1 %s", + "ignore_zero_blocks"); + } + + if (err < 0 || err >= FEC_ARG_LENGTH) + goto free_metadata; + + buf_ptr = buf; + + for (i = VERITY_TABLE_ARGS; i < (VERITY_TABLE_ARGS + + VERITY_TABLE_OPT_FEC_ARGS + 2); i++) { + verity_table_args[i] = strsep(&buf_ptr, " "); + if (verity_table_args[i] == NULL) { + no_of_args = i; + break; + } + } + + err = verity_ctr(ti, no_of_args, verity_table_args); + if (err) { + DMERR("android-verity failed to create a verity target"); + } else { + target_added = true; + DMINFO("android-verity created as verity target"); + } + +free_metadata: + if (metadata) { + kfree(metadata->header); + kfree(metadata->verity_table); + } + kfree(metadata); + return err; +} + +static int __init dm_android_verity_init(void) +{ + int r; + struct dentry *file; + + r = dm_register_target(&android_verity_target); + if (r < 0) + DMERR("register failed %d", r); + + /* Tracks the status of the last added target */ + debug_dir = debugfs_create_dir("android_verity", NULL); + + if (IS_ERR_OR_NULL(debug_dir)) { + DMERR("Cannot create android_verity debugfs directory: %ld", + PTR_ERR(debug_dir)); + goto end; + } + + file = debugfs_create_bool("target_added", S_IRUGO, debug_dir, + &target_added); + + if (IS_ERR_OR_NULL(file)) { + DMERR("Cannot create android_verity debugfs directory: %ld", + PTR_ERR(debug_dir)); + debugfs_remove_recursive(debug_dir); + goto end; + } + + file = debugfs_create_bool("verity_enabled", S_IRUGO, debug_dir, + &verity_enabled); + + if (IS_ERR_OR_NULL(file)) { + DMERR("Cannot create android_verity debugfs directory: %ld", + PTR_ERR(debug_dir)); + debugfs_remove_recursive(debug_dir); + } + +end: + return r; +} + +static void __exit dm_android_verity_exit(void) +{ + if (!IS_ERR_OR_NULL(debug_dir)) + debugfs_remove_recursive(debug_dir); + + dm_unregister_target(&android_verity_target); +} + +module_init(dm_android_verity_init); +module_exit(dm_android_verity_exit); diff --git a/drivers/md/dm-android-verity.h b/drivers/md/dm-android-verity.h new file mode 100644 index 000000000000..ef406c136fcd --- /dev/null +++ b/drivers/md/dm-android-verity.h @@ -0,0 +1,128 @@ +/* + * Copyright (C) 2015 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#ifndef DM_ANDROID_VERITY_H +#define DM_ANDROID_VERITY_H + +#include <crypto/sha.h> + +#define RSANUMBYTES 256 +#define VERITY_METADATA_MAGIC_NUMBER 0xb001b001 +#define VERITY_METADATA_MAGIC_DISABLE 0x46464f56 +#define VERITY_METADATA_VERSION 0 +#define VERITY_STATE_DISABLE 1 +#define DATA_BLOCK_SIZE (4 * 1024) +#define VERITY_METADATA_SIZE (8 * DATA_BLOCK_SIZE) +#define VERITY_TABLE_ARGS 10 +#define VERITY_COMMANDLINE_PARAM_LENGTH 20 +#define BUILD_VARIANT 20 + +/* + * <subject>:<sha1-id> is the format for the identifier. + * subject can either be the Common Name(CN) + Organization Name(O) or + * just the CN if the it is prefixed with O + * From https://tools.ietf.org/html/rfc5280#appendix-A + * ub-organization-name-length INTEGER ::= 64 + * ub-common-name-length INTEGER ::= 64 + * + * http://lxr.free-electrons.com/source/crypto/asymmetric_keys/x509_cert_parser.c?v=3.9#L278 + * ctx->o_size + 2 + ctx->cn_size + 1 + * + 41 characters for ":" and sha1 id + * 64 + 2 + 64 + 1 + 1 + 40 (172) + * setting VERITY_DEFAULT_KEY_ID_LENGTH to 200 characters. + */ +#define VERITY_DEFAULT_KEY_ID_LENGTH 200 + +#define FEC_MAGIC 0xFECFECFE +#define FEC_BLOCK_SIZE (4 * 1024) +#define FEC_VERSION 0 +#define FEC_RSM 255 +#define FEC_ARG_LENGTH 300 + +#define VERITY_TABLE_OPT_RESTART "restart_on_corruption" +#define VERITY_TABLE_OPT_LOGGING "ignore_corruption" +#define VERITY_TABLE_OPT_IGNZERO "ignore_zero_blocks" + +#define VERITY_TABLE_OPT_FEC_FORMAT \ + "use_fec_from_device %s fec_start %llu fec_blocks %llu fec_roots %u ignore_zero_blocks" +#define VERITY_TABLE_OPT_FEC_ARGS 9 + +#define VERITY_DEBUG 0 + +#define DM_MSG_PREFIX "android-verity" + +#define DM_LINEAR_ARGS 2 +#define DM_LINEAR_TARGET_OFFSET "0" + +/* + * There can be two formats. + * if fec is present + * <data_blocks> <verity_tree> <verity_metdata_32K><fec_data><fec_data_4K> + * if fec is not present + * <data_blocks> <verity_tree> <verity_metdata_32K> + */ +struct fec_header { + __le32 magic; + __le32 version; + __le32 size; + __le32 roots; + __le32 fec_size; + __le64 inp_size; + u8 hash[SHA256_DIGEST_SIZE]; +} __attribute__((packed)); + +struct android_metadata_header { + __le32 magic_number; + __le32 protocol_version; + char signature[RSANUMBYTES]; + __le32 table_length; +}; + +struct android_metadata { + struct android_metadata_header *header; + char *verity_table; +}; + +struct fec_ecc_metadata { + bool valid; + u32 roots; + u64 blocks; + u64 rounds; + u64 start; +}; + +struct bio_read { + struct page **page_io; + int number_of_pages; +}; + +extern struct target_type linear_target; + +extern void dm_linear_dtr(struct dm_target *ti); +extern int dm_linear_map(struct dm_target *ti, struct bio *bio); +extern int dm_linear_end_io(struct dm_target *ti, struct bio *bio, + blk_status_t *error); +extern void dm_linear_status(struct dm_target *ti, status_type_t type, + unsigned status_flags, char *result, unsigned maxlen); +extern int dm_linear_prepare_ioctl(struct dm_target *ti, + struct block_device **bdev, fmode_t *mode); +extern int dm_linear_iterate_devices(struct dm_target *ti, + iterate_devices_callout_fn fn, void *data); +extern int dm_linear_ctr(struct dm_target *ti, unsigned int argc, char **argv); +extern long dm_linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, + long nr_pages, void **kaddr, + pfn_t *pfn); +extern size_t dm_linear_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff, + void *addr, size_t bytes, struct iov_iter *i); +#endif /* DM_ANDROID_VERITY_H */ diff --git a/drivers/md/dm-bow.c b/drivers/md/dm-bow.c new file mode 100644 index 000000000000..ce6d4d834b17 --- /dev/null +++ b/drivers/md/dm-bow.c @@ -0,0 +1,1234 @@ +/* + * Copyright (C) 2018 Google Limited. + * + * This file is released under the GPL. + */ + +#include "dm.h" +#include "dm-bufio.h" +#include "dm-core.h" + +#include <linux/crc32.h> +#include <linux/module.h> + +#define DM_MSG_PREFIX "bow" +#define SECTOR_SIZE 512 + +struct log_entry { + u64 source; + u64 dest; + u32 size; + u32 checksum; +} __packed; + +struct log_sector { + u32 magic; + u16 header_version; + u16 header_size; + u32 block_size; + u32 count; + u32 sequence; + sector_t sector0; + struct log_entry entries[]; +} __packed; + +/* + * MAGIC is BOW in ascii + */ +#define MAGIC 0x00574f42 +#define HEADER_VERSION 0x0100 + +/* + * A sorted set of ranges representing the state of the data on the device. + * Use an rb_tree for fast lookup of a given sector + * Consecutive ranges are always of different type - operations on this + * set must merge matching consecutive ranges. + * + * Top range is always of type TOP + */ +struct bow_range { + struct rb_node node; + sector_t sector; + enum { + INVALID, /* Type not set */ + SECTOR0, /* First sector - holds log record */ + SECTOR0_CURRENT,/* Live contents of sector0 */ + UNCHANGED, /* Original contents */ + TRIMMED, /* Range has been trimmed */ + CHANGED, /* Range has been changed */ + BACKUP, /* Range is being used as a backup */ + TOP, /* Final range - sector is size of device */ + } type; + struct list_head trimmed_list; /* list of TRIMMED ranges */ +}; + +static const char * const readable_type[] = { + "Invalid", + "Sector0", + "Sector0_current", + "Unchanged", + "Free", + "Changed", + "Backup", + "Top", +}; + +enum state { + TRIM, + CHECKPOINT, + COMMITTED, +}; + +struct bow_context { + struct dm_dev *dev; + u32 block_size; + u32 block_shift; + struct workqueue_struct *workqueue; + struct dm_bufio_client *bufio; + struct mutex ranges_lock; /* Hold to access this struct and/or ranges */ + struct rb_root ranges; + struct dm_kobject_holder kobj_holder; /* for sysfs attributes */ + atomic_t state; /* One of the enum state values above */ + u64 trims_total; + struct log_sector *log_sector; + struct list_head trimmed_list; + bool forward_trims; +}; + +sector_t range_top(struct bow_range *br) +{ + return container_of(rb_next(&br->node), struct bow_range, node) + ->sector; +} + +u64 range_size(struct bow_range *br) +{ + return (range_top(br) - br->sector) * SECTOR_SIZE; +} + +static sector_t bvec_top(struct bvec_iter *bi_iter) +{ + return bi_iter->bi_sector + bi_iter->bi_size / SECTOR_SIZE; +} + +/* + * Find the first range that overlaps with bi_iter + * bi_iter is set to the size of the overlapping sub-range + */ +static struct bow_range *find_first_overlapping_range(struct rb_root *ranges, + struct bvec_iter *bi_iter) +{ + struct rb_node *node = ranges->rb_node; + struct bow_range *br; + + while (node) { + br = container_of(node, struct bow_range, node); + + if (br->sector <= bi_iter->bi_sector + && bi_iter->bi_sector < range_top(br)) + break; + + if (bi_iter->bi_sector < br->sector) + node = node->rb_left; + else + node = node->rb_right; + } + + WARN_ON(!node); + if (!node) + return NULL; + + if (range_top(br) - bi_iter->bi_sector + < bi_iter->bi_size >> SECTOR_SHIFT) + bi_iter->bi_size = (range_top(br) - bi_iter->bi_sector) + << SECTOR_SHIFT; + + return br; +} + +void add_before(struct rb_root *ranges, struct bow_range *new_br, + struct bow_range *existing) +{ + struct rb_node *parent = &(existing->node); + struct rb_node **link = &(parent->rb_left); + + while (*link) { + parent = *link; + link = &((*link)->rb_right); + } + + rb_link_node(&new_br->node, parent, link); + rb_insert_color(&new_br->node, ranges); +} + +/* + * Given a range br returned by find_first_overlapping_range, split br into a + * leading range, a range matching the bi_iter and a trailing range. + * Leading and trailing may end up size 0 and will then be deleted. The + * new range matching the bi_iter is then returned and should have its type + * and type specific fields populated. + * If bi_iter runs off the end of the range, bi_iter is truncated accordingly + */ +static int split_range(struct bow_context *bc, struct bow_range **br, + struct bvec_iter *bi_iter) +{ + struct bow_range *new_br; + + if (bi_iter->bi_sector < (*br)->sector) { + WARN_ON(true); + return BLK_STS_IOERR; + } + + if (bi_iter->bi_sector > (*br)->sector) { + struct bow_range *leading_br = + kzalloc(sizeof(*leading_br), GFP_KERNEL); + + if (!leading_br) + return BLK_STS_RESOURCE; + + *leading_br = **br; + if (leading_br->type == TRIMMED) + list_add(&leading_br->trimmed_list, &bc->trimmed_list); + + add_before(&bc->ranges, leading_br, *br); + (*br)->sector = bi_iter->bi_sector; + } + + if (bvec_top(bi_iter) >= range_top(*br)) { + bi_iter->bi_size = (range_top(*br) - (*br)->sector) + * SECTOR_SIZE; + return BLK_STS_OK; + } + + /* new_br will be the beginning, existing br will be the tail */ + new_br = kzalloc(sizeof(*new_br), GFP_KERNEL); + if (!new_br) + return BLK_STS_RESOURCE; + + new_br->sector = (*br)->sector; + (*br)->sector = bvec_top(bi_iter); + add_before(&bc->ranges, new_br, *br); + *br = new_br; + + return BLK_STS_OK; +} + +/* + * Sets type of a range. May merge range into surrounding ranges + * Since br may be invalidated, always sets br to NULL to prevent + * usage after this is called + */ +static void set_type(struct bow_context *bc, struct bow_range **br, int type) +{ + struct bow_range *prev = container_of(rb_prev(&(*br)->node), + struct bow_range, node); + struct bow_range *next = container_of(rb_next(&(*br)->node), + struct bow_range, node); + + if ((*br)->type == TRIMMED) { + bc->trims_total -= range_size(*br); + list_del(&(*br)->trimmed_list); + } + + if (type == TRIMMED) { + bc->trims_total += range_size(*br); + list_add(&(*br)->trimmed_list, &bc->trimmed_list); + } + + (*br)->type = type; + + if (next->type == type) { + if (type == TRIMMED) + list_del(&next->trimmed_list); + rb_erase(&next->node, &bc->ranges); + kfree(next); + } + + if (prev->type == type) { + if (type == TRIMMED) + list_del(&(*br)->trimmed_list); + rb_erase(&(*br)->node, &bc->ranges); + kfree(*br); + } + + *br = NULL; +} + +static struct bow_range *find_free_range(struct bow_context *bc) +{ + if (list_empty(&bc->trimmed_list)) { + DMERR("Unable to find free space to back up to"); + return NULL; + } + + return list_first_entry(&bc->trimmed_list, struct bow_range, + trimmed_list); +} + +static sector_t sector_to_page(struct bow_context const *bc, sector_t sector) +{ + WARN_ON((sector & (((sector_t)1 << (bc->block_shift - SECTOR_SHIFT)) - 1)) + != 0); + return sector >> (bc->block_shift - SECTOR_SHIFT); +} + +static int copy_data(struct bow_context const *bc, + struct bow_range *source, struct bow_range *dest, + u32 *checksum) +{ + int i; + + if (range_size(source) != range_size(dest)) { + WARN_ON(1); + return BLK_STS_IOERR; + } + + if (checksum) + *checksum = sector_to_page(bc, source->sector); + + for (i = 0; i < range_size(source) >> bc->block_shift; ++i) { + struct dm_buffer *read_buffer, *write_buffer; + u8 *read, *write; + sector_t page = sector_to_page(bc, source->sector) + i; + + read = dm_bufio_read(bc->bufio, page, &read_buffer); + if (IS_ERR(read)) { + DMERR("Cannot read page %llu", + (unsigned long long)page); + return PTR_ERR(read); + } + + if (checksum) + *checksum = crc32(*checksum, read, bc->block_size); + + write = dm_bufio_new(bc->bufio, + sector_to_page(bc, dest->sector) + i, + &write_buffer); + if (IS_ERR(write)) { + DMERR("Cannot write sector"); + dm_bufio_release(read_buffer); + return PTR_ERR(write); + } + + memcpy(write, read, bc->block_size); + + dm_bufio_mark_buffer_dirty(write_buffer); + dm_bufio_release(write_buffer); + dm_bufio_release(read_buffer); + } + + dm_bufio_write_dirty_buffers(bc->bufio); + return BLK_STS_OK; +} + +/****** logging functions ******/ + +static int add_log_entry(struct bow_context *bc, sector_t source, sector_t dest, + unsigned int size, u32 checksum); + +static int backup_log_sector(struct bow_context *bc) +{ + struct bow_range *first_br, *free_br; + struct bvec_iter bi_iter; + u32 checksum = 0; + int ret; + + first_br = container_of(rb_first(&bc->ranges), struct bow_range, node); + + if (first_br->type != SECTOR0) { + WARN_ON(1); + return BLK_STS_IOERR; + } + + if (range_size(first_br) != bc->block_size) { + WARN_ON(1); + return BLK_STS_IOERR; + } + + free_br = find_free_range(bc); + /* No space left - return this error to userspace */ + if (!free_br) + return BLK_STS_NOSPC; + bi_iter.bi_sector = free_br->sector; + bi_iter.bi_size = bc->block_size; + ret = split_range(bc, &free_br, &bi_iter); + if (ret) + return ret; + if (bi_iter.bi_size != bc->block_size) { + WARN_ON(1); + return BLK_STS_IOERR; + } + + ret = copy_data(bc, first_br, free_br, &checksum); + if (ret) + return ret; + + bc->log_sector->count = 0; + bc->log_sector->sequence++; + ret = add_log_entry(bc, first_br->sector, free_br->sector, + range_size(first_br), checksum); + if (ret) + return ret; + + set_type(bc, &free_br, BACKUP); + return BLK_STS_OK; +} + +static int add_log_entry(struct bow_context *bc, sector_t source, sector_t dest, + unsigned int size, u32 checksum) +{ + struct dm_buffer *sector_buffer; + u8 *sector; + + if (sizeof(struct log_sector) + + sizeof(struct log_entry) * (bc->log_sector->count + 1) + > bc->block_size) { + int ret = backup_log_sector(bc); + + if (ret) + return ret; + } + + sector = dm_bufio_new(bc->bufio, 0, §or_buffer); + if (IS_ERR(sector)) { + DMERR("Cannot write boot sector"); + dm_bufio_release(sector_buffer); + return BLK_STS_NOSPC; + } + + bc->log_sector->entries[bc->log_sector->count].source = source; + bc->log_sector->entries[bc->log_sector->count].dest = dest; + bc->log_sector->entries[bc->log_sector->count].size = size; + bc->log_sector->entries[bc->log_sector->count].checksum = checksum; + bc->log_sector->count++; + + memcpy(sector, bc->log_sector, bc->block_size); + dm_bufio_mark_buffer_dirty(sector_buffer); + dm_bufio_release(sector_buffer); + dm_bufio_write_dirty_buffers(bc->bufio); + return BLK_STS_OK; +} + +static int prepare_log(struct bow_context *bc) +{ + struct bow_range *free_br, *first_br; + struct bvec_iter bi_iter; + u32 checksum = 0; + int ret; + + /* Carve out first sector as log sector */ + first_br = container_of(rb_first(&bc->ranges), struct bow_range, node); + if (first_br->type != UNCHANGED) { + WARN_ON(1); + return BLK_STS_IOERR; + } + + if (range_size(first_br) < bc->block_size) { + WARN_ON(1); + return BLK_STS_IOERR; + } + bi_iter.bi_sector = 0; + bi_iter.bi_size = bc->block_size; + ret = split_range(bc, &first_br, &bi_iter); + if (ret) + return ret; + first_br->type = SECTOR0; + if (range_size(first_br) != bc->block_size) { + WARN_ON(1); + return BLK_STS_IOERR; + } + + /* Find free sector for active sector0 reads/writes */ + free_br = find_free_range(bc); + if (!free_br) + return BLK_STS_NOSPC; + bi_iter.bi_sector = free_br->sector; + bi_iter.bi_size = bc->block_size; + ret = split_range(bc, &free_br, &bi_iter); + if (ret) + return ret; + free_br->type = SECTOR0_CURRENT; + + /* Copy data */ + ret = copy_data(bc, first_br, free_br, NULL); + if (ret) + return ret; + + bc->log_sector->sector0 = free_br->sector; + + /* Find free sector to back up original sector zero */ + free_br = find_free_range(bc); + if (!free_br) + return BLK_STS_NOSPC; + bi_iter.bi_sector = free_br->sector; + bi_iter.bi_size = bc->block_size; + ret = split_range(bc, &free_br, &bi_iter); + if (ret) + return ret; + + /* Back up */ + ret = copy_data(bc, first_br, free_br, &checksum); + if (ret) + return ret; + + /* + * Set up our replacement boot sector - it will get written when we + * add the first log entry, which we do immediately + */ + bc->log_sector->magic = MAGIC; + bc->log_sector->header_version = HEADER_VERSION; + bc->log_sector->header_size = sizeof(*bc->log_sector); + bc->log_sector->block_size = bc->block_size; + bc->log_sector->count = 0; + bc->log_sector->sequence = 0; + + /* Add log entry */ + ret = add_log_entry(bc, first_br->sector, free_br->sector, + range_size(first_br), checksum); + if (ret) + return ret; + + set_type(bc, &free_br, BACKUP); + return BLK_STS_OK; +} + +static struct bow_range *find_sector0_current(struct bow_context *bc) +{ + struct bvec_iter bi_iter; + + bi_iter.bi_sector = bc->log_sector->sector0; + bi_iter.bi_size = bc->block_size; + return find_first_overlapping_range(&bc->ranges, &bi_iter); +} + +/****** sysfs interface functions ******/ + +static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct bow_context *bc = container_of(kobj, struct bow_context, + kobj_holder.kobj); + + return scnprintf(buf, PAGE_SIZE, "%d\n", atomic_read(&bc->state)); +} + +static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct bow_context *bc = container_of(kobj, struct bow_context, + kobj_holder.kobj); + enum state state, original_state; + int ret; + + state = buf[0] - '0'; + if (state < TRIM || state > COMMITTED) { + DMERR("State value %d out of range", state); + return -EINVAL; + } + + mutex_lock(&bc->ranges_lock); + original_state = atomic_read(&bc->state); + if (state != original_state + 1) { + DMERR("Invalid state change from %d to %d", + original_state, state); + ret = -EINVAL; + goto bad; + } + + DMINFO("Switching to state %s", state == CHECKPOINT ? "Checkpoint" + : state == COMMITTED ? "Committed" : "Unknown"); + + if (state == CHECKPOINT) { + ret = prepare_log(bc); + if (ret) { + DMERR("Failed to switch to checkpoint state"); + goto bad; + } + } else if (state == COMMITTED) { + struct bow_range *br = find_sector0_current(bc); + struct bow_range *sector0_br = + container_of(rb_first(&bc->ranges), struct bow_range, + node); + + ret = copy_data(bc, br, sector0_br, 0); + if (ret) { + DMERR("Failed to switch to committed state"); + goto bad; + } + } + atomic_inc(&bc->state); + ret = count; + +bad: + mutex_unlock(&bc->ranges_lock); + return ret; +} + +static ssize_t free_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct bow_context *bc = container_of(kobj, struct bow_context, + kobj_holder.kobj); + u64 trims_total; + + mutex_lock(&bc->ranges_lock); + trims_total = bc->trims_total; + mutex_unlock(&bc->ranges_lock); + + return scnprintf(buf, PAGE_SIZE, "%llu\n", trims_total); +} + +static struct kobj_attribute attr_state = __ATTR_RW(state); +static struct kobj_attribute attr_free = __ATTR_RO(free); + +static struct attribute *bow_attrs[] = { + &attr_state.attr, + &attr_free.attr, + NULL +}; + +static struct kobj_type bow_ktype = { + .sysfs_ops = &kobj_sysfs_ops, + .default_attrs = bow_attrs, + .release = dm_kobject_release +}; + +/****** constructor/destructor ******/ + +static void dm_bow_dtr(struct dm_target *ti) +{ + struct bow_context *bc = (struct bow_context *) ti->private; + struct kobject *kobj; + + while (rb_first(&bc->ranges)) { + struct bow_range *br = container_of(rb_first(&bc->ranges), + struct bow_range, node); + + rb_erase(&br->node, &bc->ranges); + kfree(br); + } + if (bc->workqueue) + destroy_workqueue(bc->workqueue); + if (bc->bufio) + dm_bufio_client_destroy(bc->bufio); + + kobj = &bc->kobj_holder.kobj; + if (kobj->state_initialized) { + kobject_put(kobj); + wait_for_completion(dm_get_completion_from_kobject(kobj)); + } + + kfree(bc->log_sector); + kfree(bc); +} + +static int dm_bow_ctr(struct dm_target *ti, unsigned int argc, char **argv) +{ + struct bow_context *bc; + struct bow_range *br; + int ret; + struct mapped_device *md = dm_table_get_md(ti->table); + + if (argc != 1) { + ti->error = "Invalid argument count"; + return -EINVAL; + } + + bc = kzalloc(sizeof(*bc), GFP_KERNEL); + if (!bc) { + ti->error = "Cannot allocate bow context"; + return -ENOMEM; + } + + ti->num_flush_bios = 1; + ti->num_discard_bios = 1; + ti->num_write_same_bios = 1; + ti->private = bc; + + ret = dm_get_device(ti, argv[0], dm_table_get_mode(ti->table), + &bc->dev); + if (ret) { + ti->error = "Device lookup failed"; + goto bad; + } + + if (bc->dev->bdev->bd_queue->limits.max_discard_sectors == 0) { + bc->dev->bdev->bd_queue->limits.discard_granularity = 1 << 12; + bc->dev->bdev->bd_queue->limits.max_hw_discard_sectors = 1 << 15; + bc->dev->bdev->bd_queue->limits.max_discard_sectors = 1 << 15; + bc->forward_trims = false; + } else { + bc->forward_trims = true; + } + + bc->block_size = bc->dev->bdev->bd_queue->limits.logical_block_size; + bc->block_shift = ilog2(bc->block_size); + bc->log_sector = kzalloc(bc->block_size, GFP_KERNEL); + if (!bc->log_sector) { + ti->error = "Cannot allocate log sector"; + goto bad; + } + + init_completion(&bc->kobj_holder.completion); + ret = kobject_init_and_add(&bc->kobj_holder.kobj, &bow_ktype, + &disk_to_dev(dm_disk(md))->kobj, "%s", + "bow"); + if (ret) { + ti->error = "Cannot create sysfs node"; + goto bad; + } + + mutex_init(&bc->ranges_lock); + bc->ranges = RB_ROOT; + bc->bufio = dm_bufio_client_create(bc->dev->bdev, bc->block_size, 1, 0, + NULL, NULL); + if (IS_ERR(bc->bufio)) { + ti->error = "Cannot initialize dm-bufio"; + ret = PTR_ERR(bc->bufio); + bc->bufio = NULL; + goto bad; + } + + bc->workqueue = alloc_workqueue("dm-bow", + WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM + | WQ_UNBOUND, num_online_cpus()); + if (!bc->workqueue) { + ti->error = "Cannot allocate workqueue"; + ret = -ENOMEM; + goto bad; + } + + INIT_LIST_HEAD(&bc->trimmed_list); + + br = kzalloc(sizeof(*br), GFP_KERNEL); + if (!br) { + ti->error = "Cannot allocate ranges"; + ret = -ENOMEM; + goto bad; + } + + br->sector = ti->len; + br->type = TOP; + rb_link_node(&br->node, NULL, &bc->ranges.rb_node); + rb_insert_color(&br->node, &bc->ranges); + + br = kzalloc(sizeof(*br), GFP_KERNEL); + if (!br) { + ti->error = "Cannot allocate ranges"; + ret = -ENOMEM; + goto bad; + } + + br->sector = 0; + br->type = UNCHANGED; + rb_link_node(&br->node, bc->ranges.rb_node, + &bc->ranges.rb_node->rb_left); + rb_insert_color(&br->node, &bc->ranges); + + ti->discards_supported = true; + + return 0; + +bad: + dm_bow_dtr(ti); + return ret; +} + +/****** Handle writes ******/ + +static int prepare_unchanged_range(struct bow_context *bc, struct bow_range *br, + struct bvec_iter *bi_iter, + bool record_checksum) +{ + struct bow_range *backup_br; + struct bvec_iter backup_bi; + sector_t log_source, log_dest; + unsigned int log_size; + u32 checksum = 0; + int ret; + int original_type; + sector_t sector0; + + /* Find a free range */ + backup_br = find_free_range(bc); + if (!backup_br) + return BLK_STS_NOSPC; + + /* Carve out a backup range. This may be smaller than the br given */ + backup_bi.bi_sector = backup_br->sector; + backup_bi.bi_size = min(range_size(backup_br), (u64) bi_iter->bi_size); + ret = split_range(bc, &backup_br, &backup_bi); + if (ret) + return ret; + + /* + * Carve out a changed range. This will not be smaller than the backup + * br since the backup br is smaller than the source range and iterator + */ + bi_iter->bi_size = backup_bi.bi_size; + ret = split_range(bc, &br, bi_iter); + if (ret) + return ret; + if (range_size(br) != range_size(backup_br)) { + WARN_ON(1); + return BLK_STS_IOERR; + } + + + /* Copy data over */ + ret = copy_data(bc, br, backup_br, record_checksum ? &checksum : NULL); + if (ret) + return ret; + + /* Add an entry to the log */ + log_source = br->sector; + log_dest = backup_br->sector; + log_size = range_size(br); + + /* + * Set the types. Note that since set_type also amalgamates ranges + * we have to set both sectors to their final type before calling + * set_type on either + */ + original_type = br->type; + sector0 = backup_br->sector; + bc->trims_total -= range_size(backup_br); + if (backup_br->type == TRIMMED) + list_del(&backup_br->trimmed_list); + backup_br->type = br->type == SECTOR0_CURRENT ? SECTOR0_CURRENT + : BACKUP; + br->type = CHANGED; + set_type(bc, &backup_br, backup_br->type); + + /* + * Add the log entry after marking the backup sector, since adding a log + * can cause another backup + */ + ret = add_log_entry(bc, log_source, log_dest, log_size, checksum); + if (ret) { + br->type = original_type; + return ret; + } + + /* Now it is safe to mark this backup successful */ + if (original_type == SECTOR0_CURRENT) + bc->log_sector->sector0 = sector0; + + set_type(bc, &br, br->type); + return ret; +} + +static int prepare_free_range(struct bow_context *bc, struct bow_range *br, + struct bvec_iter *bi_iter) +{ + int ret; + + ret = split_range(bc, &br, bi_iter); + if (ret) + return ret; + set_type(bc, &br, CHANGED); + return BLK_STS_OK; +} + +static int prepare_changed_range(struct bow_context *bc, struct bow_range *br, + struct bvec_iter *bi_iter) +{ + /* Nothing to do ... */ + return BLK_STS_OK; +} + +static int prepare_one_range(struct bow_context *bc, + struct bvec_iter *bi_iter) +{ + struct bow_range *br = find_first_overlapping_range(&bc->ranges, + bi_iter); + switch (br->type) { + case CHANGED: + return prepare_changed_range(bc, br, bi_iter); + + case TRIMMED: + return prepare_free_range(bc, br, bi_iter); + + case UNCHANGED: + case BACKUP: + return prepare_unchanged_range(bc, br, bi_iter, true); + + /* + * We cannot track the checksum for the active sector0, since it + * may change at any point. + */ + case SECTOR0_CURRENT: + return prepare_unchanged_range(bc, br, bi_iter, false); + + case SECTOR0: /* Handled in the dm_bow_map */ + case TOP: /* Illegal - top is off the end of the device */ + default: + WARN_ON(1); + return BLK_STS_IOERR; + } +} + +struct write_work { + struct work_struct work; + struct bow_context *bc; + struct bio *bio; +}; + +static void bow_write(struct work_struct *work) +{ + struct write_work *ww = container_of(work, struct write_work, work); + struct bow_context *bc = ww->bc; + struct bio *bio = ww->bio; + struct bvec_iter bi_iter = bio->bi_iter; + int ret = BLK_STS_OK; + + kfree(ww); + + mutex_lock(&bc->ranges_lock); + do { + ret = prepare_one_range(bc, &bi_iter); + bi_iter.bi_sector += bi_iter.bi_size / SECTOR_SIZE; + bi_iter.bi_size = bio->bi_iter.bi_size + - (bi_iter.bi_sector - bio->bi_iter.bi_sector) + * SECTOR_SIZE; + } while (!ret && bi_iter.bi_size); + + mutex_unlock(&bc->ranges_lock); + + if (!ret) { + bio_set_dev(bio, bc->dev->bdev); + submit_bio(bio); + } else { + DMERR("Write failure with error %d", -ret); + bio->bi_status = ret; + bio_endio(bio); + } +} + +static int queue_write(struct bow_context *bc, struct bio *bio) +{ + struct write_work *ww = kmalloc(sizeof(*ww), GFP_NOIO | __GFP_NORETRY + | __GFP_NOMEMALLOC | __GFP_NOWARN); + if (!ww) { + DMERR("Failed to allocate write_work"); + return -ENOMEM; + } + + INIT_WORK(&ww->work, bow_write); + ww->bc = bc; + ww->bio = bio; + queue_work(bc->workqueue, &ww->work); + return DM_MAPIO_SUBMITTED; +} + +static int handle_sector0(struct bow_context *bc, struct bio *bio) +{ + int ret = DM_MAPIO_REMAPPED; + + if (bio->bi_iter.bi_size > bc->block_size) { + struct bio * split = bio_split(bio, + bc->block_size >> SECTOR_SHIFT, + GFP_NOIO, + fs_bio_set); + if (!split) { + DMERR("Failed to split bio"); + bio->bi_status = BLK_STS_RESOURCE; + bio_endio(bio); + return DM_MAPIO_SUBMITTED; + } + + bio_chain(split, bio); + split->bi_iter.bi_sector = bc->log_sector->sector0; + bio_set_dev(split, bc->dev->bdev); + submit_bio(split); + + if (bio_data_dir(bio) == WRITE) + ret = queue_write(bc, bio); + } else { + bio->bi_iter.bi_sector = bc->log_sector->sector0; + } + + return ret; +} + +static int add_trim(struct bow_context *bc, struct bio *bio) +{ + struct bow_range *br; + struct bvec_iter bi_iter = bio->bi_iter; + + DMDEBUG("add_trim: %llu, %u", + (unsigned long long)bio->bi_iter.bi_sector, + bio->bi_iter.bi_size); + + do { + br = find_first_overlapping_range(&bc->ranges, &bi_iter); + + switch (br->type) { + case UNCHANGED: + if (!split_range(bc, &br, &bi_iter)) + set_type(bc, &br, TRIMMED); + break; + + case TRIMMED: + /* Nothing to do */ + break; + + default: + /* No other case is legal in TRIM state */ + WARN_ON(true); + break; + } + + bi_iter.bi_sector += bi_iter.bi_size / SECTOR_SIZE; + bi_iter.bi_size = bio->bi_iter.bi_size + - (bi_iter.bi_sector - bio->bi_iter.bi_sector) + * SECTOR_SIZE; + + } while (bi_iter.bi_size); + + bio_endio(bio); + return DM_MAPIO_SUBMITTED; +} + +static int remove_trim(struct bow_context *bc, struct bio *bio) +{ + struct bow_range *br; + struct bvec_iter bi_iter = bio->bi_iter; + + DMDEBUG("remove_trim: %llu, %u", + (unsigned long long)bio->bi_iter.bi_sector, + bio->bi_iter.bi_size); + + do { + br = find_first_overlapping_range(&bc->ranges, &bi_iter); + + switch (br->type) { + case UNCHANGED: + /* Nothing to do */ + break; + + case TRIMMED: + if (!split_range(bc, &br, &bi_iter)) + set_type(bc, &br, UNCHANGED); + break; + + default: + /* No other case is legal in TRIM state */ + WARN_ON(true); + break; + } + + bi_iter.bi_sector += bi_iter.bi_size / SECTOR_SIZE; + bi_iter.bi_size = bio->bi_iter.bi_size + - (bi_iter.bi_sector - bio->bi_iter.bi_sector) + * SECTOR_SIZE; + + } while (bi_iter.bi_size); + + return DM_MAPIO_REMAPPED; +} + +int remap_unless_illegal_trim(struct bow_context *bc, struct bio *bio) +{ + if (!bc->forward_trims && bio_op(bio) == REQ_OP_DISCARD) { + bio->bi_status = BLK_STS_NOTSUPP; + bio_endio(bio); + return DM_MAPIO_SUBMITTED; + } else { + bio_set_dev(bio, bc->dev->bdev); + return DM_MAPIO_REMAPPED; + } +} + +/****** dm interface ******/ + +static int dm_bow_map(struct dm_target *ti, struct bio *bio) +{ + int ret = DM_MAPIO_REMAPPED; + struct bow_context *bc = ti->private; + + if (likely(bc->state.counter == COMMITTED)) + return remap_unless_illegal_trim(bc, bio); + + if (bio_data_dir(bio) == READ && bio->bi_iter.bi_sector != 0) + return remap_unless_illegal_trim(bc, bio); + + if (atomic_read(&bc->state) != COMMITTED) { + enum state state; + + mutex_lock(&bc->ranges_lock); + state = atomic_read(&bc->state); + if (state == TRIM) { + if (bio_op(bio) == REQ_OP_DISCARD) + ret = add_trim(bc, bio); + else if (bio_data_dir(bio) == WRITE) + ret = remove_trim(bc, bio); + else + /* pass-through */; + } else if (state == CHECKPOINT) { + if (bio->bi_iter.bi_sector == 0) + ret = handle_sector0(bc, bio); + else if (bio_data_dir(bio) == WRITE) + ret = queue_write(bc, bio); + else + /* pass-through */; + } else { + /* pass-through */ + } + mutex_unlock(&bc->ranges_lock); + } + + if (ret == DM_MAPIO_REMAPPED) + return remap_unless_illegal_trim(bc, bio); + + return ret; +} + +static void dm_bow_tablestatus(struct dm_target *ti, char *result, + unsigned int maxlen) +{ + char *end = result + maxlen; + struct bow_context *bc = ti->private; + struct rb_node *i; + int trimmed_list_length = 0; + int trimmed_range_count = 0; + struct bow_range *br; + + if (maxlen == 0) + return; + result[0] = 0; + + list_for_each_entry(br, &bc->trimmed_list, trimmed_list) + if (br->type == TRIMMED) { + ++trimmed_list_length; + } else { + scnprintf(result, end - result, + "ERROR: non-trimmed entry in trimmed_list"); + return; + } + + if (!rb_first(&bc->ranges)) { + scnprintf(result, end - result, "ERROR: Empty ranges"); + return; + } + + if (container_of(rb_first(&bc->ranges), struct bow_range, node) + ->sector) { + scnprintf(result, end - result, + "ERROR: First range does not start at sector 0"); + return; + } + + for (i = rb_first(&bc->ranges); i; i = rb_next(i)) { + struct bow_range *br = container_of(i, struct bow_range, node); + + result += scnprintf(result, end - result, "%s: %llu", + readable_type[br->type], + (unsigned long long)br->sector); + if (result >= end) + return; + + result += scnprintf(result, end - result, "\n"); + if (result >= end) + return; + + if (br->type == TRIMMED) + ++trimmed_range_count; + + if (br->type == TOP) { + if (br->sector != ti->len) { + scnprintf(result, end - result, + "\nERROR: Top sector is incorrect"); + } + + if (&br->node != rb_last(&bc->ranges)) { + scnprintf(result, end - result, + "\nERROR: Top sector is not last"); + } + + break; + } + + if (!rb_next(i)) { + scnprintf(result, end - result, + "\nERROR: Last range not of type TOP"); + return; + } + + if (br->sector > range_top(br)) { + scnprintf(result, end - result, + "\nERROR: sectors out of order"); + return; + } + } + + if (trimmed_range_count != trimmed_list_length) + scnprintf(result, end - result, + "\nERROR: not all trimmed ranges in trimmed list"); +} + +static void dm_bow_status(struct dm_target *ti, status_type_t type, + unsigned int status_flags, char *result, + unsigned int maxlen) +{ + switch (type) { + case STATUSTYPE_INFO: + if (maxlen) + result[0] = 0; + break; + + case STATUSTYPE_TABLE: + dm_bow_tablestatus(ti, result, maxlen); + break; + } +} + +int dm_bow_prepare_ioctl(struct dm_target *ti, struct block_device **bdev, + fmode_t *mode) +{ + struct bow_context *bc = ti->private; + struct dm_dev *dev = bc->dev; + + *bdev = dev->bdev; + /* Only pass ioctls through if the device sizes match exactly. */ + return ti->len != i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT; +} + +static int dm_bow_iterate_devices(struct dm_target *ti, + iterate_devices_callout_fn fn, void *data) +{ + struct bow_context *bc = ti->private; + + return fn(ti, bc->dev, 0, ti->len, data); +} + +static struct target_type bow_target = { + .name = "bow", + .version = {1, 1, 1}, + .module = THIS_MODULE, + .ctr = dm_bow_ctr, + .dtr = dm_bow_dtr, + .map = dm_bow_map, + .status = dm_bow_status, + .prepare_ioctl = dm_bow_prepare_ioctl, + .iterate_devices = dm_bow_iterate_devices, +}; + +int __init dm_bow_init(void) +{ + int r = dm_register_target(&bow_target); + + if (r < 0) + DMERR("registering bow failed %d", r); + return r; +} + +void dm_bow_exit(void) +{ + dm_unregister_target(&bow_target); +} + +MODULE_LICENSE("GPL"); + +module_init(dm_bow_init); +module_exit(dm_bow_exit); diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 5e38ceb36000..45feee003666 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1899,6 +1899,13 @@ static int crypt_alloc_tfms_skcipher(struct crypt_config *cc, char *ciphermode) } } + /* + * dm-crypt performance can vary greatly depending on which crypto + * algorithm implementation is used. Help people debug performance + * problems by logging the ->cra_driver_name. + */ + DMINFO("%s using implementation \"%s\"", ciphermode, + crypto_skcipher_alg(any_tfm(cc))->base.cra_driver_name); return 0; } @@ -1917,6 +1924,8 @@ static int crypt_alloc_tfms_aead(struct crypt_config *cc, char *ciphermode) return err; } + DMINFO("%s using implementation \"%s\"", ciphermode, + crypto_aead_alg(any_tfm_aead(cc))->base.cra_driver_name); return 0; } diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index a53de71bc30c..e6fd31b03c38 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -26,7 +26,7 @@ struct linear_c { /* * Construct a linear mapping: <dev_path> <offset> */ -static int linear_ctr(struct dm_target *ti, unsigned int argc, char **argv) +int dm_linear_ctr(struct dm_target *ti, unsigned int argc, char **argv) { struct linear_c *lc; unsigned long long tmp; @@ -69,7 +69,7 @@ static int linear_ctr(struct dm_target *ti, unsigned int argc, char **argv) return ret; } -static void linear_dtr(struct dm_target *ti) +void dm_linear_dtr(struct dm_target *ti) { struct linear_c *lc = (struct linear_c *) ti->private; @@ -94,15 +94,14 @@ static void linear_map_bio(struct dm_target *ti, struct bio *bio) linear_map_sector(ti, bio->bi_iter.bi_sector); } -static int linear_map(struct dm_target *ti, struct bio *bio) +int dm_linear_map(struct dm_target *ti, struct bio *bio) { linear_map_bio(ti, bio); return DM_MAPIO_REMAPPED; } -#ifdef CONFIG_BLK_DEV_ZONED -static int linear_end_io(struct dm_target *ti, struct bio *bio, +int dm_linear_end_io(struct dm_target *ti, struct bio *bio, blk_status_t *error) { struct linear_c *lc = ti->private; @@ -112,9 +111,9 @@ static int linear_end_io(struct dm_target *ti, struct bio *bio, return DM_ENDIO_DONE; } -#endif +EXPORT_SYMBOL_GPL(dm_linear_end_io); -static void linear_status(struct dm_target *ti, status_type_t type, +void dm_linear_status(struct dm_target *ti, status_type_t type, unsigned status_flags, char *result, unsigned maxlen) { struct linear_c *lc = (struct linear_c *) ti->private; @@ -131,7 +130,7 @@ static void linear_status(struct dm_target *ti, status_type_t type, } } -static int linear_prepare_ioctl(struct dm_target *ti, +int dm_linear_prepare_ioctl(struct dm_target *ti, struct block_device **bdev, fmode_t *mode) { struct linear_c *lc = (struct linear_c *) ti->private; @@ -148,7 +147,7 @@ static int linear_prepare_ioctl(struct dm_target *ti, return 0; } -static int linear_iterate_devices(struct dm_target *ti, +int dm_linear_iterate_devices(struct dm_target *ti, iterate_devices_callout_fn fn, void *data) { struct linear_c *lc = ti->private; @@ -156,7 +155,7 @@ static int linear_iterate_devices(struct dm_target *ti, return fn(ti, lc->dev, lc->start, ti->len, data); } -static long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, +long dm_linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn) { long ret; @@ -171,8 +170,9 @@ static long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, return ret; return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn); } +EXPORT_SYMBOL_GPL(dm_linear_dax_direct_access); -static size_t linear_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff, +size_t dm_linear_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) { struct linear_c *lc = ti->private; @@ -185,25 +185,22 @@ static size_t linear_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff, return 0; return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i); } +EXPORT_SYMBOL_GPL(dm_linear_dax_copy_from_iter); static struct target_type linear_target = { .name = "linear", .version = {1, 4, 0}, -#ifdef CONFIG_BLK_DEV_ZONED - .end_io = linear_end_io, .features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_ZONED_HM, -#else - .features = DM_TARGET_PASSES_INTEGRITY, -#endif .module = THIS_MODULE, - .ctr = linear_ctr, - .dtr = linear_dtr, - .map = linear_map, - .status = linear_status, - .prepare_ioctl = linear_prepare_ioctl, - .iterate_devices = linear_iterate_devices, - .direct_access = linear_dax_direct_access, - .dax_copy_from_iter = linear_dax_copy_from_iter, + .ctr = dm_linear_ctr, + .dtr = dm_linear_dtr, + .map = dm_linear_map, + .status = dm_linear_status, + .end_io = dm_linear_end_io, + .prepare_ioctl = dm_linear_prepare_ioctl, + .iterate_devices = dm_linear_iterate_devices, + .direct_access = dm_linear_dax_direct_access, + .dax_copy_from_iter = dm_linear_dax_copy_from_iter, }; int __init dm_linear_init(void) diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 8f070debe498..6e184378ac61 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -547,14 +547,14 @@ static int adjoin(struct dm_table *table, struct dm_target *ti) * On the other hand, dm-switch needs to process bulk data using messages and * excessive use of GFP_NOIO could cause trouble. */ -static char **realloc_argv(unsigned *array_size, char **old_argv) +static char **realloc_argv(unsigned *size, char **old_argv) { char **argv; unsigned new_size; gfp_t gfp; - if (*array_size) { - new_size = *array_size * 2; + if (*size) { + new_size = *size * 2; gfp = GFP_KERNEL; } else { new_size = 8; @@ -562,8 +562,8 @@ static char **realloc_argv(unsigned *array_size, char **old_argv) } argv = kmalloc(new_size * sizeof(*argv), gfp); if (argv) { - memcpy(argv, old_argv, *array_size * sizeof(*argv)); - *array_size = new_size; + memcpy(argv, old_argv, *size * sizeof(*argv)); + *size = new_size; } kfree(old_argv); @@ -1900,6 +1900,9 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, smp_mb(); if (dm_table_request_based(t)) queue_flag_set_unlocked(QUEUE_FLAG_STACKABLE, q); + + /* io_pages is used for readahead */ + q->backing_dev_info->io_pages = limits->max_sectors >> (PAGE_SHIFT - 9); } unsigned int dm_table_get_num_targets(struct dm_table *t) diff --git a/drivers/md/dm-verity-avb.c b/drivers/md/dm-verity-avb.c new file mode 100644 index 000000000000..a9f102aa379e --- /dev/null +++ b/drivers/md/dm-verity-avb.c @@ -0,0 +1,229 @@ +/* + * Copyright (C) 2017 Google. + * + * This file is released under the GPLv2. + * + * Based on drivers/md/dm-verity-chromeos.c + */ + +#include <linux/device-mapper.h> +#include <linux/module.h> +#include <linux/mount.h> + +#define DM_MSG_PREFIX "verity-avb" + +/* Set via module parameters. */ +static char avb_vbmeta_device[64]; +static char avb_invalidate_on_error[4]; + +static void invalidate_vbmeta_endio(struct bio *bio) +{ + if (bio->bi_status) + DMERR("invalidate_vbmeta_endio: error %d", bio->bi_status); + complete(bio->bi_private); +} + +static int invalidate_vbmeta_submit(struct bio *bio, + struct block_device *bdev, + int op, int access_last_sector, + struct page *page) +{ + DECLARE_COMPLETION_ONSTACK(wait); + + bio->bi_private = &wait; + bio->bi_end_io = invalidate_vbmeta_endio; + bio_set_dev(bio, bdev); + bio_set_op_attrs(bio, op, REQ_SYNC); + + bio->bi_iter.bi_sector = 0; + if (access_last_sector) { + sector_t last_sector; + + last_sector = (i_size_read(bdev->bd_inode)>>SECTOR_SHIFT) - 1; + bio->bi_iter.bi_sector = last_sector; + } + if (!bio_add_page(bio, page, PAGE_SIZE, 0)) { + DMERR("invalidate_vbmeta_submit: bio_add_page error"); + return -EIO; + } + + submit_bio(bio); + /* Wait up to 2 seconds for completion or fail. */ + if (!wait_for_completion_timeout(&wait, msecs_to_jiffies(2000))) + return -EIO; + return 0; +} + +static int invalidate_vbmeta(dev_t vbmeta_devt) +{ + int ret = 0; + struct block_device *bdev; + struct bio *bio; + struct page *page; + fmode_t dev_mode; + /* Ensure we do synchronous unblocked I/O. We may also need + * sync_bdev() on completion, but it really shouldn't. + */ + int access_last_sector = 0; + + DMINFO("invalidate_vbmeta: acting on device %d:%d", + MAJOR(vbmeta_devt), MINOR(vbmeta_devt)); + + /* First we open the device for reading. */ + dev_mode = FMODE_READ | FMODE_EXCL; + bdev = blkdev_get_by_dev(vbmeta_devt, dev_mode, + invalidate_vbmeta); + if (IS_ERR(bdev)) { + DMERR("invalidate_kernel: could not open device for reading"); + dev_mode = 0; + ret = -ENOENT; + goto failed_to_read; + } + + bio = bio_alloc(GFP_NOIO, 1); + if (!bio) { + ret = -ENOMEM; + goto failed_bio_alloc; + } + + page = alloc_page(GFP_NOIO); + if (!page) { + ret = -ENOMEM; + goto failed_to_alloc_page; + } + + access_last_sector = 0; + ret = invalidate_vbmeta_submit(bio, bdev, REQ_OP_READ, + access_last_sector, page); + if (ret) { + DMERR("invalidate_vbmeta: error reading"); + goto failed_to_submit_read; + } + + /* We have a page. Let's make sure it looks right. */ + if (memcmp("AVB0", page_address(page), 4) == 0) { + /* Stamp it. */ + memcpy(page_address(page), "AVE0", 4); + DMINFO("invalidate_vbmeta: found vbmeta partition"); + } else { + /* Could be this is on a AVB footer, check. Also, since the + * AVB footer is in the last 64 bytes, adjust for the fact that + * we're dealing with 512-byte sectors. + */ + size_t offset = (1<<SECTOR_SHIFT) - 64; + + access_last_sector = 1; + ret = invalidate_vbmeta_submit(bio, bdev, REQ_OP_READ, + access_last_sector, page); + if (ret) { + DMERR("invalidate_vbmeta: error reading"); + goto failed_to_submit_read; + } + if (memcmp("AVBf", page_address(page) + offset, 4) != 0) { + DMERR("invalidate_vbmeta on non-vbmeta partition"); + ret = -EINVAL; + goto invalid_header; + } + /* Stamp it. */ + memcpy(page_address(page) + offset, "AVE0", 4); + DMINFO("invalidate_vbmeta: found vbmeta footer partition"); + } + + /* Now rewrite the changed page - the block dev was being + * changed on read. Let's reopen here. + */ + blkdev_put(bdev, dev_mode); + dev_mode = FMODE_WRITE | FMODE_EXCL; + bdev = blkdev_get_by_dev(vbmeta_devt, dev_mode, + invalidate_vbmeta); + if (IS_ERR(bdev)) { + DMERR("invalidate_vbmeta: could not open device for writing"); + dev_mode = 0; + ret = -ENOENT; + goto failed_to_write; + } + + /* We re-use the same bio to do the write after the read. Need to reset + * it to initialize bio->bi_remaining. + */ + bio_reset(bio); + + ret = invalidate_vbmeta_submit(bio, bdev, REQ_OP_WRITE, + access_last_sector, page); + if (ret) { + DMERR("invalidate_vbmeta: error writing"); + goto failed_to_submit_write; + } + + DMERR("invalidate_vbmeta: completed."); + ret = 0; +failed_to_submit_write: +failed_to_write: +invalid_header: + __free_page(page); +failed_to_submit_read: + /* Technically, we'll leak a page with the pending bio, but + * we're about to reboot anyway. + */ +failed_to_alloc_page: + bio_put(bio); +failed_bio_alloc: + if (dev_mode) + blkdev_put(bdev, dev_mode); +failed_to_read: + return ret; +} + +void dm_verity_avb_error_handler(void) +{ + dev_t dev; + + DMINFO("AVB error handler called for %s", avb_vbmeta_device); + + if (strcmp(avb_invalidate_on_error, "yes") != 0) { + DMINFO("Not configured to invalidate"); + return; + } + + if (avb_vbmeta_device[0] == '\0') { + DMERR("avb_vbmeta_device parameter not set"); + goto fail_no_dev; + } + + dev = name_to_dev_t(avb_vbmeta_device); + if (!dev) { + DMERR("No matching partition for device: %s", + avb_vbmeta_device); + goto fail_no_dev; + } + + invalidate_vbmeta(dev); + +fail_no_dev: + ; +} + +static int __init dm_verity_avb_init(void) +{ + DMINFO("AVB error handler initialized with vbmeta device: %s", + avb_vbmeta_device); + return 0; +} + +static void __exit dm_verity_avb_exit(void) +{ +} + +module_init(dm_verity_avb_init); +module_exit(dm_verity_avb_exit); + +MODULE_AUTHOR("David Zeuthen <zeuthen@google.com>"); +MODULE_DESCRIPTION("AVB-specific error handler for dm-verity"); +MODULE_LICENSE("GPL"); + +/* Declare parameter with no module prefix */ +#undef MODULE_PARAM_PREFIX +#define MODULE_PARAM_PREFIX "androidboot.vbmeta." +module_param_string(device, avb_vbmeta_device, sizeof(avb_vbmeta_device), 0); +module_param_string(invalidate_on_error, avb_invalidate_on_error, + sizeof(avb_invalidate_on_error), 0); diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c index 0fe6cc3007f5..052419ac1ce6 100644 --- a/drivers/md/dm-verity-fec.c +++ b/drivers/md/dm-verity-fec.c @@ -11,6 +11,7 @@ #include "dm-verity-fec.h" #include <linux/math64.h> +#include <linux/sysfs.h> #define DM_MSG_PREFIX "verity-fec" @@ -175,9 +176,11 @@ error: if (r < 0 && neras) DMERR_LIMIT("%s: FEC %llu: failed to correct: %d", v->data_dev->name, (unsigned long long)rsb, r); - else if (r > 0) + else if (r > 0) { DMWARN_LIMIT("%s: FEC %llu: corrected %d errors", v->data_dev->name, (unsigned long long)rsb, r); + atomic_add_unless(&v->fec->corrected, 1, INT_MAX); + } return r; } @@ -545,6 +548,7 @@ unsigned verity_fec_status_table(struct dm_verity *v, unsigned sz, void verity_fec_dtr(struct dm_verity *v) { struct dm_verity_fec *f = v->fec; + struct kobject *kobj = &f->kobj_holder.kobj; if (!verity_fec_is_enabled(v)) goto out; @@ -562,6 +566,12 @@ void verity_fec_dtr(struct dm_verity *v) if (f->dev) dm_put_device(v->ti, f->dev); + + if (kobj->state_initialized) { + kobject_put(kobj); + wait_for_completion(dm_get_completion_from_kobject(kobj)); + } + out: kfree(f); v->fec = NULL; @@ -650,6 +660,28 @@ int verity_fec_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v, return 0; } +static ssize_t corrected_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct dm_verity_fec *f = container_of(kobj, struct dm_verity_fec, + kobj_holder.kobj); + + return sprintf(buf, "%d\n", atomic_read(&f->corrected)); +} + +static struct kobj_attribute attr_corrected = __ATTR_RO(corrected); + +static struct attribute *fec_attrs[] = { + &attr_corrected.attr, + NULL +}; + +static struct kobj_type fec_ktype = { + .sysfs_ops = &kobj_sysfs_ops, + .default_attrs = fec_attrs, + .release = dm_kobject_release +}; + /* * Allocate dm_verity_fec for v->fec. Must be called before verity_fec_ctr. */ @@ -673,8 +705,10 @@ int verity_fec_ctr_alloc(struct dm_verity *v) */ int verity_fec_ctr(struct dm_verity *v) { + int r; struct dm_verity_fec *f = v->fec; struct dm_target *ti = v->ti; + struct mapped_device *md = dm_table_get_md(ti->table); u64 hash_blocks; if (!verity_fec_is_enabled(v)) { @@ -682,6 +716,16 @@ int verity_fec_ctr(struct dm_verity *v) return 0; } + /* Create a kobject and sysfs attributes */ + init_completion(&f->kobj_holder.completion); + + r = kobject_init_and_add(&f->kobj_holder.kobj, &fec_ktype, + &disk_to_dev(dm_disk(md))->kobj, "%s", "fec"); + if (r) { + ti->error = "Cannot create kobject"; + return r; + } + /* * FEC is computed over data blocks, possible metadata, and * hash blocks. In other words, FEC covers total of fec_blocks diff --git a/drivers/md/dm-verity-fec.h b/drivers/md/dm-verity-fec.h index bb31ce87a933..4db0cae262eb 100644 --- a/drivers/md/dm-verity-fec.h +++ b/drivers/md/dm-verity-fec.h @@ -12,6 +12,8 @@ #ifndef DM_VERITY_FEC_H #define DM_VERITY_FEC_H +#include "dm.h" +#include "dm-core.h" #include "dm-verity.h" #include <linux/rslib.h> @@ -51,6 +53,8 @@ struct dm_verity_fec { mempool_t *extra_pool; /* mempool for extra buffers */ mempool_t *output_pool; /* mempool for output */ struct kmem_cache *cache; /* cache for buffers */ + atomic_t corrected; /* corrected errors */ + struct dm_kobject_holder kobj_holder; /* for sysfs attributes */ }; /* per-bio data */ diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index e705799976c2..d60d15fac7e2 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -32,6 +32,7 @@ #define DM_VERITY_OPT_LOGGING "ignore_corruption" #define DM_VERITY_OPT_RESTART "restart_on_corruption" #define DM_VERITY_OPT_IGN_ZEROES "ignore_zero_blocks" +#define DM_VERITY_OPT_AT_MOST_ONCE "check_at_most_once" #define DM_VERITY_OPTS_MAX (2 + DM_VERITY_OPTS_FEC) @@ -291,8 +292,12 @@ out: if (v->mode == DM_VERITY_MODE_LOGGING) return 0; - if (v->mode == DM_VERITY_MODE_RESTART) + if (v->mode == DM_VERITY_MODE_RESTART) { +#ifdef CONFIG_DM_VERITY_AVB + dm_verity_avb_error_handler(); +#endif kernel_restart("dm-verity device corrupted"); + } return 1; } @@ -490,6 +495,18 @@ static int verity_bv_zero(struct dm_verity *v, struct dm_verity_io *io, } /* + * Moves the bio iter one data block forward. + */ +static inline void verity_bv_skip_block(struct dm_verity *v, + struct dm_verity_io *io, + struct bvec_iter *iter) +{ + struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_io_data_size); + + bio_advance_iter(bio, iter, 1 << v->data_dev_block_bits); +} + +/* * Verify one "dm_verity_io" structure. */ static int verity_verify_io(struct dm_verity_io *io) @@ -502,9 +519,16 @@ static int verity_verify_io(struct dm_verity_io *io) for (b = 0; b < io->n_blocks; b++) { int r; + sector_t cur_block = io->block + b; struct ahash_request *req = verity_io_hash_req(v, io); - r = verity_hash_for_block(v, io, io->block + b, + if (v->validated_blocks && + likely(test_bit(cur_block, v->validated_blocks))) { + verity_bv_skip_block(v, io, &io->iter); + continue; + } + + r = verity_hash_for_block(v, io, cur_block, verity_io_want_digest(v, io), &is_zero); if (unlikely(r < 0)) @@ -538,13 +562,16 @@ static int verity_verify_io(struct dm_verity_io *io) return r; if (likely(memcmp(verity_io_real_digest(v, io), - verity_io_want_digest(v, io), v->digest_size) == 0)) + verity_io_want_digest(v, io), v->digest_size) == 0)) { + if (v->validated_blocks) + set_bit(cur_block, v->validated_blocks); continue; + } else if (verity_fec_decode(v, io, DM_VERITY_BLOCK_TYPE_DATA, - io->block + b, NULL, &start) == 0) + cur_block, NULL, &start) == 0) continue; else if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_DATA, - io->block + b)) + cur_block)) return -EIO; } @@ -648,7 +675,7 @@ static void verity_submit_prefetch(struct dm_verity *v, struct dm_verity_io *io) * Bio map function. It allocates dm_verity_io structure and bio vector and * fills them. Then it issues prefetches and the I/O. */ -static int verity_map(struct dm_target *ti, struct bio *bio) +int verity_map(struct dm_target *ti, struct bio *bio) { struct dm_verity *v = ti->private; struct dm_verity_io *io; @@ -693,7 +720,7 @@ static int verity_map(struct dm_target *ti, struct bio *bio) /* * Status: V (valid) or C (corruption found) */ -static void verity_status(struct dm_target *ti, status_type_t type, +void verity_status(struct dm_target *ti, status_type_t type, unsigned status_flags, char *result, unsigned maxlen) { struct dm_verity *v = ti->private; @@ -730,6 +757,8 @@ static void verity_status(struct dm_target *ti, status_type_t type, args += DM_VERITY_OPTS_FEC; if (v->zero_digest) args++; + if (v->validated_blocks) + args++; if (!args) return; DMEMIT(" %u", args); @@ -748,12 +777,14 @@ static void verity_status(struct dm_target *ti, status_type_t type, } if (v->zero_digest) DMEMIT(" " DM_VERITY_OPT_IGN_ZEROES); + if (v->validated_blocks) + DMEMIT(" " DM_VERITY_OPT_AT_MOST_ONCE); sz = verity_fec_status_table(v, sz, result, maxlen); break; } } -static int verity_prepare_ioctl(struct dm_target *ti, +int verity_prepare_ioctl(struct dm_target *ti, struct block_device **bdev, fmode_t *mode) { struct dm_verity *v = ti->private; @@ -766,7 +797,7 @@ static int verity_prepare_ioctl(struct dm_target *ti, return 0; } -static int verity_iterate_devices(struct dm_target *ti, +int verity_iterate_devices(struct dm_target *ti, iterate_devices_callout_fn fn, void *data) { struct dm_verity *v = ti->private; @@ -774,7 +805,7 @@ static int verity_iterate_devices(struct dm_target *ti, return fn(ti, v->data_dev, v->data_start, ti->len, data); } -static void verity_io_hints(struct dm_target *ti, struct queue_limits *limits) +void verity_io_hints(struct dm_target *ti, struct queue_limits *limits) { struct dm_verity *v = ti->private; @@ -787,7 +818,7 @@ static void verity_io_hints(struct dm_target *ti, struct queue_limits *limits) blk_limits_io_min(limits, limits->logical_block_size); } -static void verity_dtr(struct dm_target *ti) +void verity_dtr(struct dm_target *ti) { struct dm_verity *v = ti->private; @@ -797,6 +828,7 @@ static void verity_dtr(struct dm_target *ti) if (v->bufio) dm_bufio_client_destroy(v->bufio); + kvfree(v->validated_blocks); kfree(v->salt); kfree(v->root_digest); kfree(v->zero_digest); @@ -817,6 +849,26 @@ static void verity_dtr(struct dm_target *ti) kfree(v); } +static int verity_alloc_most_once(struct dm_verity *v) +{ + struct dm_target *ti = v->ti; + + /* the bitset can only handle INT_MAX blocks */ + if (v->data_blocks > INT_MAX) { + ti->error = "device too large to use check_at_most_once"; + return -E2BIG; + } + + v->validated_blocks = kvzalloc(BITS_TO_LONGS(v->data_blocks) * + sizeof(unsigned long), GFP_KERNEL); + if (!v->validated_blocks) { + ti->error = "failed to allocate bitset for check_at_most_once"; + return -ENOMEM; + } + + return 0; +} + static int verity_alloc_zero_digest(struct dm_verity *v) { int r = -ENOMEM; @@ -886,6 +938,12 @@ static int verity_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v) } continue; + } else if (!strcasecmp(arg_name, DM_VERITY_OPT_AT_MOST_ONCE)) { + r = verity_alloc_most_once(v); + if (r) + return r; + continue; + } else if (verity_is_fec_opt_arg(arg_name)) { r = verity_fec_parse_opt_args(as, v, &argc, arg_name); if (r) @@ -914,7 +972,7 @@ static int verity_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v) * <digest> * <salt> Hex string or "-" if no salt. */ -static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) +int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) { struct dm_verity *v; struct dm_arg_set as; @@ -1027,6 +1085,15 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) v->tfm = NULL; goto bad; } + + /* + * dm-verity performance can vary greatly depending on which hash + * algorithm implementation is used. Help people debug performance + * problems by logging the ->cra_driver_name. + */ + DMINFO("%s using implementation \"%s\"", v->alg_name, + crypto_hash_alg_common(v->tfm)->base.cra_driver_name); + v->digest_size = crypto_ahash_digestsize(v->tfm); if ((1 << v->hash_dev_block_bits) < v->digest_size * 2) { ti->error = "Digest size too big"; @@ -1078,6 +1145,14 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) goto bad; } +#ifdef CONFIG_DM_ANDROID_VERITY_AT_MOST_ONCE_DEFAULT_ENABLED + if (!v->validated_blocks) { + r = verity_alloc_most_once(v); + if (r) + goto bad; + } +#endif + v->hash_per_block_bits = __fls((1 << v->hash_dev_block_bits) / v->digest_size); @@ -1153,7 +1228,7 @@ bad: static struct target_type verity_target = { .name = "verity", - .version = {1, 3, 0}, + .version = {1, 4, 0}, .module = THIS_MODULE, .ctr = verity_ctr, .dtr = verity_dtr, diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h index a59e0ada6fd3..116e91fa50d7 100644 --- a/drivers/md/dm-verity.h +++ b/drivers/md/dm-verity.h @@ -63,6 +63,7 @@ struct dm_verity { sector_t hash_level_block[DM_VERITY_MAX_LEVELS]; struct dm_verity_fec *fec; /* forward error correction */ + unsigned long *validated_blocks; /* bitset blocks validated */ }; struct dm_verity_io { @@ -131,4 +132,15 @@ extern int verity_hash(struct dm_verity *v, struct ahash_request *req, extern int verity_hash_for_block(struct dm_verity *v, struct dm_verity_io *io, sector_t block, u8 *digest, bool *is_zero); +extern void verity_status(struct dm_target *ti, status_type_t type, + unsigned status_flags, char *result, unsigned maxlen); +extern int verity_prepare_ioctl(struct dm_target *ti, + struct block_device **bdev, fmode_t *mode); +extern int verity_iterate_devices(struct dm_target *ti, + iterate_devices_callout_fn fn, void *data); +extern void verity_io_hints(struct dm_target *ti, struct queue_limits *limits); +extern void verity_dtr(struct dm_target *ti); +extern int verity_ctr(struct dm_target *ti, unsigned argc, char **argv); +extern int verity_map(struct dm_target *ti, struct bio *bio); +extern void dm_verity_avb_error_handler(void); #endif /* DM_VERITY_H */ diff --git a/drivers/md/md.c b/drivers/md/md.c index 702a7d2c7e1e..223e1f5e5e23 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5390,7 +5390,7 @@ static struct kobject *md_probe(dev_t dev, int *part, void *data) return NULL; } -static int add_named_array(const char *val, struct kernel_param *kp) +static int add_named_array(const char *val, const struct kernel_param *kp) { /* * val must be "md_*" or "mdNNN". @@ -9384,11 +9384,11 @@ static __exit void md_exit(void) subsys_initcall(md_init); module_exit(md_exit) -static int get_ro(char *buffer, struct kernel_param *kp) +static int get_ro(char *buffer, const struct kernel_param *kp) { return sprintf(buffer, "%d", start_readonly); } -static int set_ro(const char *val, struct kernel_param *kp) +static int set_ro(const char *val, const struct kernel_param *kp) { return kstrtouint(val, 10, (unsigned int *)&start_readonly); } diff --git a/drivers/media/pci/tw686x/tw686x-core.c b/drivers/media/pci/tw686x/tw686x-core.c index 336e2f9bc1b6..b762e5f0ba1d 100644 --- a/drivers/media/pci/tw686x/tw686x-core.c +++ b/drivers/media/pci/tw686x/tw686x-core.c @@ -72,12 +72,12 @@ static const char *dma_mode_name(unsigned int mode) } } -static int tw686x_dma_mode_get(char *buffer, struct kernel_param *kp) +static int tw686x_dma_mode_get(char *buffer, const struct kernel_param *kp) { return sprintf(buffer, "%s", dma_mode_name(dma_mode)); } -static int tw686x_dma_mode_set(const char *val, struct kernel_param *kp) +static int tw686x_dma_mode_set(const char *val, const struct kernel_param *kp) { if (!strcasecmp(val, dma_mode_name(TW686X_DMA_MODE_MEMCPY))) dma_mode = TW686X_DMA_MODE_MEMCPY; diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c index 5899593dabaf..591ca125bd96 100644 --- a/drivers/media/usb/uvc/uvc_driver.c +++ b/drivers/media/usb/uvc/uvc_driver.c @@ -2245,7 +2245,7 @@ static int uvc_reset_resume(struct usb_interface *intf) * Module parameters */ -static int uvc_clock_param_get(char *buffer, struct kernel_param *kp) +static int uvc_clock_param_get(char *buffer, const struct kernel_param *kp) { if (uvc_clock_param == CLOCK_MONOTONIC) return sprintf(buffer, "CLOCK_MONOTONIC"); @@ -2253,7 +2253,7 @@ static int uvc_clock_param_get(char *buffer, struct kernel_param *kp) return sprintf(buffer, "CLOCK_REALTIME"); } -static int uvc_clock_param_set(const char *val, struct kernel_param *kp) +static int uvc_clock_param_set(const char *val, const struct kernel_param *kp) { if (strncasecmp(val, "clock_", strlen("clock_")) == 0) val += strlen("clock_"); diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 8eb52139684a..80ff481e4253 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -2500,11 +2500,8 @@ struct v4l2_ioctl_info { unsigned int ioctl; u32 flags; const char * const name; - union { - u32 offset; - int (*func)(const struct v4l2_ioctl_ops *ops, - struct file *file, void *fh, void *p); - } u; + int (*func)(const struct v4l2_ioctl_ops *ops, struct file *file, + void *fh, void *p); void (*debug)(const void *arg, bool write_only); }; @@ -2512,27 +2509,23 @@ struct v4l2_ioctl_info { #define INFO_FL_PRIO (1 << 0) /* This control can be valid if the filehandle passes a control handler. */ #define INFO_FL_CTRL (1 << 1) -/* This is a standard ioctl, no need for special code */ -#define INFO_FL_STD (1 << 2) /* This is ioctl has its own function */ -#define INFO_FL_FUNC (1 << 3) +#define INFO_FL_FUNC (1 << 2) /* Queuing ioctl */ -#define INFO_FL_QUEUE (1 << 4) +#define INFO_FL_QUEUE (1 << 3) /* Always copy back result, even on error */ -#define INFO_FL_ALWAYS_COPY (1 << 5) +#define INFO_FL_ALWAYS_COPY (1 << 4) /* Zero struct from after the field to the end */ #define INFO_FL_CLEAR(v4l2_struct, field) \ ((offsetof(struct v4l2_struct, field) + \ sizeof(((struct v4l2_struct *)0)->field)) << 16) #define INFO_FL_CLEAR_MASK (_IOC_SIZEMASK << 16) -#define IOCTL_INFO_STD(_ioctl, _vidioc, _debug, _flags) \ - [_IOC_NR(_ioctl)] = { \ - .ioctl = _ioctl, \ - .flags = _flags | INFO_FL_STD, \ - .name = #_ioctl, \ - .u.offset = offsetof(struct v4l2_ioctl_ops, _vidioc), \ - .debug = _debug, \ +#define DEFINE_IOCTL_STD_FNC(_vidioc) \ + static int __v4l_ ## _vidioc ## _fnc( \ + const struct v4l2_ioctl_ops *ops, \ + struct file *file, void *fh, void *p) { \ + return ops->_vidioc(file, fh, p); \ } #define IOCTL_INFO_FNC(_ioctl, _func, _debug, _flags) \ @@ -2540,10 +2533,42 @@ struct v4l2_ioctl_info { .ioctl = _ioctl, \ .flags = _flags | INFO_FL_FUNC, \ .name = #_ioctl, \ - .u.func = _func, \ + .func = _func, \ .debug = _debug, \ } +#define IOCTL_INFO_STD(_ioctl, _vidioc, _debug, _flags) \ + IOCTL_INFO_FNC(_ioctl, __v4l_ ## _vidioc ## _fnc, _debug, _flags) + +DEFINE_IOCTL_STD_FNC(vidioc_g_fbuf) +DEFINE_IOCTL_STD_FNC(vidioc_s_fbuf) +DEFINE_IOCTL_STD_FNC(vidioc_expbuf) +DEFINE_IOCTL_STD_FNC(vidioc_g_std) +DEFINE_IOCTL_STD_FNC(vidioc_g_audio) +DEFINE_IOCTL_STD_FNC(vidioc_s_audio) +DEFINE_IOCTL_STD_FNC(vidioc_g_input) +DEFINE_IOCTL_STD_FNC(vidioc_g_edid) +DEFINE_IOCTL_STD_FNC(vidioc_s_edid) +DEFINE_IOCTL_STD_FNC(vidioc_g_output) +DEFINE_IOCTL_STD_FNC(vidioc_g_audout) +DEFINE_IOCTL_STD_FNC(vidioc_s_audout) +DEFINE_IOCTL_STD_FNC(vidioc_g_jpegcomp) +DEFINE_IOCTL_STD_FNC(vidioc_s_jpegcomp) +DEFINE_IOCTL_STD_FNC(vidioc_enumaudio) +DEFINE_IOCTL_STD_FNC(vidioc_enumaudout) +DEFINE_IOCTL_STD_FNC(vidioc_enum_framesizes) +DEFINE_IOCTL_STD_FNC(vidioc_enum_frameintervals) +DEFINE_IOCTL_STD_FNC(vidioc_g_enc_index) +DEFINE_IOCTL_STD_FNC(vidioc_encoder_cmd) +DEFINE_IOCTL_STD_FNC(vidioc_try_encoder_cmd) +DEFINE_IOCTL_STD_FNC(vidioc_decoder_cmd) +DEFINE_IOCTL_STD_FNC(vidioc_try_decoder_cmd) +DEFINE_IOCTL_STD_FNC(vidioc_s_dv_timings) +DEFINE_IOCTL_STD_FNC(vidioc_g_dv_timings) +DEFINE_IOCTL_STD_FNC(vidioc_enum_dv_timings) +DEFINE_IOCTL_STD_FNC(vidioc_query_dv_timings) +DEFINE_IOCTL_STD_FNC(vidioc_dv_timings_cap) + static struct v4l2_ioctl_info v4l2_ioctls[] = { IOCTL_INFO_FNC(VIDIOC_QUERYCAP, v4l_querycap, v4l_print_querycap, 0), IOCTL_INFO_FNC(VIDIOC_ENUM_FMT, v4l_enum_fmt, v4l_print_fmtdesc, INFO_FL_CLEAR(v4l2_fmtdesc, type)), @@ -2728,14 +2753,8 @@ static long __video_do_ioctl(struct file *file, } write_only = _IOC_DIR(cmd) == _IOC_WRITE; - if (info->flags & INFO_FL_STD) { - typedef int (*vidioc_op)(struct file *file, void *fh, void *p); - const void *p = vfd->ioctl_ops; - const vidioc_op *vidioc = p + info->u.offset; - - ret = (*vidioc)(file, fh, arg); - } else if (info->flags & INFO_FL_FUNC) { - ret = info->u.func(ops, file, fh, arg); + if (info->flags & INFO_FL_FUNC) { + ret = info->func(ops, file, fh, arg); } else if (!ops->vidioc_default) { ret = -ENOTTY; } else { diff --git a/drivers/message/fusion/mptbase.c b/drivers/message/fusion/mptbase.c index 84eab28665f3..7a93400eea2a 100644 --- a/drivers/message/fusion/mptbase.c +++ b/drivers/message/fusion/mptbase.c @@ -99,7 +99,7 @@ module_param(mpt_channel_mapping, int, 0); MODULE_PARM_DESC(mpt_channel_mapping, " Mapping id's to channels (default=0)"); static int mpt_debug_level; -static int mpt_set_debug_level(const char *val, struct kernel_param *kp); +static int mpt_set_debug_level(const char *val, const struct kernel_param *kp); module_param_call(mpt_debug_level, mpt_set_debug_level, param_get_int, &mpt_debug_level, 0600); MODULE_PARM_DESC(mpt_debug_level, @@ -242,7 +242,7 @@ pci_enable_io_access(struct pci_dev *pdev) pci_write_config_word(pdev, PCI_COMMAND, command_reg); } -static int mpt_set_debug_level(const char *val, struct kernel_param *kp) +static int mpt_set_debug_level(const char *val, const struct kernel_param *kp) { int ret = param_set_int(val, kp); MPT_ADAPTER *ioc; diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig index 8136dc7e863d..ce2449ad1688 100644 --- a/drivers/misc/Kconfig +++ b/drivers/misc/Kconfig @@ -506,6 +506,27 @@ config PCI_ENDPOINT_TEST Enable this configuration option to enable the host side test driver for PCI Endpoint. +config UID_SYS_STATS + bool "Per-UID statistics" + depends on PROFILING && TASK_XACCT && TASK_IO_ACCOUNTING + help + Per UID based cpu time statistics exported to /proc/uid_cputime + Per UID based io statistics exported to /proc/uid_io + Per UID based procstat control in /proc/uid_procstat + +config UID_SYS_STATS_DEBUG + bool "Per-TASK statistics" + depends on UID_SYS_STATS + default n + help + Per TASK based io statistics exported to /proc/uid_io + +config MEMORY_STATE_TIME + tristate "Memory freq/bandwidth time statistics" + depends on PROFILING + help + Memory time statistics exported to /sys/kernel/memory_state_time + source "drivers/misc/c2port/Kconfig" source "drivers/misc/eeprom/Kconfig" source "drivers/misc/cb710/Kconfig" diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile index 76f6a4f628b3..99bac49b8c6b 100644 --- a/drivers/misc/Makefile +++ b/drivers/misc/Makefile @@ -57,6 +57,9 @@ obj-$(CONFIG_ASPEED_LPC_CTRL) += aspeed-lpc-ctrl.o obj-$(CONFIG_ASPEED_LPC_SNOOP) += aspeed-lpc-snoop.o obj-$(CONFIG_PCI_ENDPOINT_TEST) += pci_endpoint_test.o +obj-$(CONFIG_UID_SYS_STATS) += uid_sys_stats.o +obj-$(CONFIG_MEMORY_STATE_TIME) += memory_state_time.o + lkdtm-$(CONFIG_LKDTM) += lkdtm_core.o lkdtm-$(CONFIG_LKDTM) += lkdtm_bugs.o lkdtm-$(CONFIG_LKDTM) += lkdtm_heap.o @@ -66,6 +69,7 @@ lkdtm-$(CONFIG_LKDTM) += lkdtm_rodata_objcopy.o lkdtm-$(CONFIG_LKDTM) += lkdtm_usercopy.o KCOV_INSTRUMENT_lkdtm_rodata.o := n +CFLAGS_lkdtm_rodata.o += $(DISABLE_LTO) OBJCOPYFLAGS := OBJCOPYFLAGS_lkdtm_rodata_objcopy.o := \ diff --git a/drivers/misc/kgdbts.c b/drivers/misc/kgdbts.c index 05824ff6b916..83d220ede65f 100644 --- a/drivers/misc/kgdbts.c +++ b/drivers/misc/kgdbts.c @@ -1128,7 +1128,8 @@ static void kgdbts_put_char(u8 chr) ts.run_test(0, chr); } -static int param_set_kgdbts_var(const char *kmessage, struct kernel_param *kp) +static int param_set_kgdbts_var(const char *kmessage, + const struct kernel_param *kp) { size_t len = strlen(kmessage); diff --git a/drivers/misc/memory_state_time.c b/drivers/misc/memory_state_time.c new file mode 100644 index 000000000000..ba94dcf09169 --- /dev/null +++ b/drivers/misc/memory_state_time.c @@ -0,0 +1,462 @@ +/* drivers/misc/memory_state_time.c + * + * Copyright (C) 2016 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/device.h> +#include <linux/err.h> +#include <linux/errno.h> +#include <linux/hashtable.h> +#include <linux/kconfig.h> +#include <linux/kernel.h> +#include <linux/kobject.h> +#include <linux/memory-state-time.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/of_platform.h> +#include <linux/slab.h> +#include <linux/sysfs.h> +#include <linux/time.h> +#include <linux/timekeeping.h> +#include <linux/workqueue.h> + +#define KERNEL_ATTR_RO(_name) \ +static struct kobj_attribute _name##_attr = __ATTR_RO(_name) + +#define KERNEL_ATTR_RW(_name) \ +static struct kobj_attribute _name##_attr = \ + __ATTR(_name, 0644, _name##_show, _name##_store) + +#define FREQ_HASH_BITS 4 +DECLARE_HASHTABLE(freq_hash_table, FREQ_HASH_BITS); + +static DEFINE_MUTEX(mem_lock); + +#define TAG "memory_state_time" +#define BW_NODE "/soc/memory-state-time" +#define FREQ_TBL "freq-tbl" +#define BW_TBL "bw-buckets" +#define NUM_SOURCES "num-sources" + +#define LOWEST_FREQ 2 + +static int curr_bw; +static int curr_freq; +static u32 *bw_buckets; +static u32 *freq_buckets; +static int num_freqs; +static int num_buckets; +static int registered_bw_sources; +static u64 last_update; +static bool init_success; +static struct workqueue_struct *memory_wq; +static u32 num_sources = 10; +static int *bandwidths; + +struct freq_entry { + int freq; + u64 *buckets; /* Bandwidth buckets. */ + struct hlist_node hash; +}; + +struct queue_container { + struct work_struct update_state; + int value; + u64 time_now; + int id; + struct mutex *lock; +}; + +static int find_bucket(int bw) +{ + int i; + + if (bw_buckets != NULL) { + for (i = 0; i < num_buckets; i++) { + if (bw_buckets[i] > bw) { + pr_debug("Found bucket %d for bandwidth %d\n", + i, bw); + return i; + } + } + return num_buckets - 1; + } + return 0; +} + +static u64 get_time_diff(u64 time_now) +{ + u64 ms; + + ms = time_now - last_update; + last_update = time_now; + return ms; +} + +static ssize_t show_stat_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + int i, j; + int len = 0; + struct freq_entry *freq_entry; + + for (i = 0; i < num_freqs; i++) { + hash_for_each_possible(freq_hash_table, freq_entry, hash, + freq_buckets[i]) { + if (freq_entry->freq == freq_buckets[i]) { + len += scnprintf(buf + len, PAGE_SIZE - len, + "%d ", freq_buckets[i]); + if (len >= PAGE_SIZE) + break; + for (j = 0; j < num_buckets; j++) { + len += scnprintf(buf + len, + PAGE_SIZE - len, + "%llu ", + freq_entry->buckets[j]); + } + len += scnprintf(buf + len, PAGE_SIZE - len, + "\n"); + } + } + } + pr_debug("Current Time: %llu\n", ktime_get_boot_ns()); + return len; +} +KERNEL_ATTR_RO(show_stat); + +static void update_table(u64 time_now) +{ + struct freq_entry *freq_entry; + + pr_debug("Last known bw %d freq %d\n", curr_bw, curr_freq); + hash_for_each_possible(freq_hash_table, freq_entry, hash, curr_freq) { + if (curr_freq == freq_entry->freq) { + freq_entry->buckets[find_bucket(curr_bw)] + += get_time_diff(time_now); + break; + } + } +} + +static bool freq_exists(int freq) +{ + int i; + + for (i = 0; i < num_freqs; i++) { + if (freq == freq_buckets[i]) + return true; + } + return false; +} + +static int calculate_total_bw(int bw, int index) +{ + int i; + int total_bw = 0; + + pr_debug("memory_state_time New bw %d for id %d\n", bw, index); + bandwidths[index] = bw; + for (i = 0; i < registered_bw_sources; i++) + total_bw += bandwidths[i]; + return total_bw; +} + +static void freq_update_do_work(struct work_struct *work) +{ + struct queue_container *freq_state_update + = container_of(work, struct queue_container, + update_state); + if (freq_state_update) { + mutex_lock(&mem_lock); + update_table(freq_state_update->time_now); + curr_freq = freq_state_update->value; + mutex_unlock(&mem_lock); + kfree(freq_state_update); + } +} + +static void bw_update_do_work(struct work_struct *work) +{ + struct queue_container *bw_state_update + = container_of(work, struct queue_container, + update_state); + if (bw_state_update) { + mutex_lock(&mem_lock); + update_table(bw_state_update->time_now); + curr_bw = calculate_total_bw(bw_state_update->value, + bw_state_update->id); + mutex_unlock(&mem_lock); + kfree(bw_state_update); + } +} + +static void memory_state_freq_update(struct memory_state_update_block *ub, + int value) +{ + if (IS_ENABLED(CONFIG_MEMORY_STATE_TIME)) { + if (freq_exists(value) && init_success) { + struct queue_container *freq_container + = kmalloc(sizeof(struct queue_container), + GFP_KERNEL); + if (!freq_container) + return; + INIT_WORK(&freq_container->update_state, + freq_update_do_work); + freq_container->time_now = ktime_get_boot_ns(); + freq_container->value = value; + pr_debug("Scheduling freq update in work queue\n"); + queue_work(memory_wq, &freq_container->update_state); + } else { + pr_debug("Freq does not exist.\n"); + } + } +} + +static void memory_state_bw_update(struct memory_state_update_block *ub, + int value) +{ + if (IS_ENABLED(CONFIG_MEMORY_STATE_TIME)) { + if (init_success) { + struct queue_container *bw_container + = kmalloc(sizeof(struct queue_container), + GFP_KERNEL); + if (!bw_container) + return; + INIT_WORK(&bw_container->update_state, + bw_update_do_work); + bw_container->time_now = ktime_get_boot_ns(); + bw_container->value = value; + bw_container->id = ub->id; + pr_debug("Scheduling bandwidth update in work queue\n"); + queue_work(memory_wq, &bw_container->update_state); + } + } +} + +struct memory_state_update_block *memory_state_register_frequency_source(void) +{ + struct memory_state_update_block *block; + + if (IS_ENABLED(CONFIG_MEMORY_STATE_TIME)) { + pr_debug("Allocating frequency source\n"); + block = kmalloc(sizeof(struct memory_state_update_block), + GFP_KERNEL); + if (!block) + return NULL; + block->update_call = memory_state_freq_update; + return block; + } + pr_err("Config option disabled.\n"); + return NULL; +} +EXPORT_SYMBOL_GPL(memory_state_register_frequency_source); + +struct memory_state_update_block *memory_state_register_bandwidth_source(void) +{ + struct memory_state_update_block *block; + + if (IS_ENABLED(CONFIG_MEMORY_STATE_TIME)) { + pr_debug("Allocating bandwidth source %d\n", + registered_bw_sources); + block = kmalloc(sizeof(struct memory_state_update_block), + GFP_KERNEL); + if (!block) + return NULL; + block->update_call = memory_state_bw_update; + if (registered_bw_sources < num_sources) { + block->id = registered_bw_sources++; + } else { + pr_err("Unable to allocate source; max number reached\n"); + kfree(block); + return NULL; + } + return block; + } + pr_err("Config option disabled.\n"); + return NULL; +} +EXPORT_SYMBOL_GPL(memory_state_register_bandwidth_source); + +/* Buckets are designated by their maximum. + * Returns the buckets decided by the capability of the device. + */ +static int get_bw_buckets(struct device *dev) +{ + int ret, lenb; + struct device_node *node = dev->of_node; + + of_property_read_u32(node, NUM_SOURCES, &num_sources); + if (!of_find_property(node, BW_TBL, &lenb)) { + pr_err("Missing %s property\n", BW_TBL); + return -ENODATA; + } + + bandwidths = devm_kzalloc(dev, + sizeof(*bandwidths) * num_sources, GFP_KERNEL); + if (!bandwidths) + return -ENOMEM; + lenb /= sizeof(*bw_buckets); + bw_buckets = devm_kzalloc(dev, lenb * sizeof(*bw_buckets), + GFP_KERNEL); + if (!bw_buckets) { + devm_kfree(dev, bandwidths); + return -ENOMEM; + } + ret = of_property_read_u32_array(node, BW_TBL, bw_buckets, + lenb); + if (ret < 0) { + devm_kfree(dev, bandwidths); + devm_kfree(dev, bw_buckets); + pr_err("Unable to read bandwidth table from device tree.\n"); + return ret; + } + + curr_bw = 0; + num_buckets = lenb; + return 0; +} + +/* Adds struct freq_entry nodes to the hashtable for each compatible frequency. + * Returns the supported number of frequencies. + */ +static int freq_buckets_init(struct device *dev) +{ + struct freq_entry *freq_entry; + int i; + int ret, lenf; + struct device_node *node = dev->of_node; + + if (!of_find_property(node, FREQ_TBL, &lenf)) { + pr_err("Missing %s property\n", FREQ_TBL); + return -ENODATA; + } + + lenf /= sizeof(*freq_buckets); + freq_buckets = devm_kzalloc(dev, lenf * sizeof(*freq_buckets), + GFP_KERNEL); + if (!freq_buckets) + return -ENOMEM; + pr_debug("freqs found len %d\n", lenf); + ret = of_property_read_u32_array(node, FREQ_TBL, freq_buckets, + lenf); + if (ret < 0) { + devm_kfree(dev, freq_buckets); + pr_err("Unable to read frequency table from device tree.\n"); + return ret; + } + pr_debug("ret freq %d\n", ret); + + num_freqs = lenf; + curr_freq = freq_buckets[LOWEST_FREQ]; + + for (i = 0; i < num_freqs; i++) { + freq_entry = devm_kzalloc(dev, sizeof(struct freq_entry), + GFP_KERNEL); + if (!freq_entry) + return -ENOMEM; + freq_entry->buckets = devm_kzalloc(dev, sizeof(u64)*num_buckets, + GFP_KERNEL); + if (!freq_entry->buckets) { + devm_kfree(dev, freq_entry); + return -ENOMEM; + } + pr_debug("memory_state_time Adding freq to ht %d\n", + freq_buckets[i]); + freq_entry->freq = freq_buckets[i]; + hash_add(freq_hash_table, &freq_entry->hash, freq_buckets[i]); + } + return 0; +} + +struct kobject *memory_kobj; +EXPORT_SYMBOL_GPL(memory_kobj); + +static struct attribute *memory_attrs[] = { + &show_stat_attr.attr, + NULL +}; + +static struct attribute_group memory_attr_group = { + .attrs = memory_attrs, +}; + +static int memory_state_time_probe(struct platform_device *pdev) +{ + int error; + + error = get_bw_buckets(&pdev->dev); + if (error) + return error; + error = freq_buckets_init(&pdev->dev); + if (error) + return error; + last_update = ktime_get_boot_ns(); + init_success = true; + + pr_debug("memory_state_time initialized with num_freqs %d\n", + num_freqs); + return 0; +} + +static const struct of_device_id match_table[] = { + { .compatible = "memory-state-time" }, + {} +}; + +static struct platform_driver memory_state_time_driver = { + .probe = memory_state_time_probe, + .driver = { + .name = "memory-state-time", + .of_match_table = match_table, + .owner = THIS_MODULE, + }, +}; + +static int __init memory_state_time_init(void) +{ + int error; + + hash_init(freq_hash_table); + memory_wq = create_singlethread_workqueue("memory_wq"); + if (!memory_wq) { + pr_err("Unable to create workqueue.\n"); + return -EINVAL; + } + /* + * Create sys/kernel directory for memory_state_time. + */ + memory_kobj = kobject_create_and_add(TAG, kernel_kobj); + if (!memory_kobj) { + pr_err("Unable to allocate memory_kobj for sysfs directory.\n"); + error = -ENOMEM; + goto wq; + } + error = sysfs_create_group(memory_kobj, &memory_attr_group); + if (error) { + pr_err("Unable to create sysfs folder.\n"); + goto kobj; + } + + error = platform_driver_register(&memory_state_time_driver); + if (error) { + pr_err("Unable to register memory_state_time platform driver.\n"); + goto group; + } + return 0; + +group: sysfs_remove_group(memory_kobj, &memory_attr_group); +kobj: kobject_put(memory_kobj); +wq: destroy_workqueue(memory_wq); + return error; +} +module_init(memory_state_time_init); diff --git a/drivers/misc/uid_sys_stats.c b/drivers/misc/uid_sys_stats.c new file mode 100644 index 000000000000..88dc1cd3a204 --- /dev/null +++ b/drivers/misc/uid_sys_stats.c @@ -0,0 +1,703 @@ +/* drivers/misc/uid_sys_stats.c + * + * Copyright (C) 2014 - 2015 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/atomic.h> +#include <linux/cpufreq_times.h> +#include <linux/err.h> +#include <linux/hashtable.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/list.h> +#include <linux/mm.h> +#include <linux/proc_fs.h> +#include <linux/profile.h> +#include <linux/rtmutex.h> +#include <linux/sched/cputime.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/uaccess.h> + + +#define UID_HASH_BITS 10 +DECLARE_HASHTABLE(hash_table, UID_HASH_BITS); + +static DEFINE_RT_MUTEX(uid_lock); +static struct proc_dir_entry *cpu_parent; +static struct proc_dir_entry *io_parent; +static struct proc_dir_entry *proc_parent; + +struct io_stats { + u64 read_bytes; + u64 write_bytes; + u64 rchar; + u64 wchar; + u64 fsync; +}; + +#define UID_STATE_FOREGROUND 0 +#define UID_STATE_BACKGROUND 1 +#define UID_STATE_BUCKET_SIZE 2 + +#define UID_STATE_TOTAL_CURR 2 +#define UID_STATE_TOTAL_LAST 3 +#define UID_STATE_DEAD_TASKS 4 +#define UID_STATE_SIZE 5 + +#define MAX_TASK_COMM_LEN 256 + +struct task_entry { + char comm[MAX_TASK_COMM_LEN]; + pid_t pid; + struct io_stats io[UID_STATE_SIZE]; + struct hlist_node hash; +}; + +struct uid_entry { + uid_t uid; + u64 utime; + u64 stime; + u64 active_utime; + u64 active_stime; + int state; + struct io_stats io[UID_STATE_SIZE]; + struct hlist_node hash; +#ifdef CONFIG_UID_SYS_STATS_DEBUG + DECLARE_HASHTABLE(task_entries, UID_HASH_BITS); +#endif +}; + +static u64 compute_write_bytes(struct task_struct *task) +{ + if (task->ioac.write_bytes <= task->ioac.cancelled_write_bytes) + return 0; + + return task->ioac.write_bytes - task->ioac.cancelled_write_bytes; +} + +static void compute_io_bucket_stats(struct io_stats *io_bucket, + struct io_stats *io_curr, + struct io_stats *io_last, + struct io_stats *io_dead) +{ + /* tasks could switch to another uid group, but its io_last in the + * previous uid group could still be positive. + * therefore before each update, do an overflow check first + */ + int64_t delta; + + delta = io_curr->read_bytes + io_dead->read_bytes - + io_last->read_bytes; + io_bucket->read_bytes += delta > 0 ? delta : 0; + delta = io_curr->write_bytes + io_dead->write_bytes - + io_last->write_bytes; + io_bucket->write_bytes += delta > 0 ? delta : 0; + delta = io_curr->rchar + io_dead->rchar - io_last->rchar; + io_bucket->rchar += delta > 0 ? delta : 0; + delta = io_curr->wchar + io_dead->wchar - io_last->wchar; + io_bucket->wchar += delta > 0 ? delta : 0; + delta = io_curr->fsync + io_dead->fsync - io_last->fsync; + io_bucket->fsync += delta > 0 ? delta : 0; + + io_last->read_bytes = io_curr->read_bytes; + io_last->write_bytes = io_curr->write_bytes; + io_last->rchar = io_curr->rchar; + io_last->wchar = io_curr->wchar; + io_last->fsync = io_curr->fsync; + + memset(io_dead, 0, sizeof(struct io_stats)); +} + +#ifdef CONFIG_UID_SYS_STATS_DEBUG +static void get_full_task_comm(struct task_entry *task_entry, + struct task_struct *task) +{ + int i = 0, offset = 0, len = 0; + /* save one byte for terminating null character */ + int unused_len = MAX_TASK_COMM_LEN - TASK_COMM_LEN - 1; + char buf[unused_len]; + struct mm_struct *mm = task->mm; + + /* fill the first TASK_COMM_LEN bytes with thread name */ + __get_task_comm(task_entry->comm, TASK_COMM_LEN, task); + i = strlen(task_entry->comm); + while (i < TASK_COMM_LEN) + task_entry->comm[i++] = ' '; + + /* next the executable file name */ + if (mm) { + down_read(&mm->mmap_sem); + if (mm->exe_file) { + char *pathname = d_path(&mm->exe_file->f_path, buf, + unused_len); + + if (!IS_ERR(pathname)) { + len = strlcpy(task_entry->comm + i, pathname, + unused_len); + i += len; + task_entry->comm[i++] = ' '; + unused_len--; + } + } + up_read(&mm->mmap_sem); + } + unused_len -= len; + + /* fill the rest with command line argument + * replace each null or new line character + * between args in argv with whitespace */ + len = get_cmdline(task, buf, unused_len); + while (offset < len) { + if (buf[offset] != '\0' && buf[offset] != '\n') + task_entry->comm[i++] = buf[offset]; + else + task_entry->comm[i++] = ' '; + offset++; + } + + /* get rid of trailing whitespaces in case when arg is memset to + * zero before being reset in userspace + */ + while (task_entry->comm[i-1] == ' ') + i--; + task_entry->comm[i] = '\0'; +} + +static struct task_entry *find_task_entry(struct uid_entry *uid_entry, + struct task_struct *task) +{ + struct task_entry *task_entry; + + hash_for_each_possible(uid_entry->task_entries, task_entry, hash, + task->pid) { + if (task->pid == task_entry->pid) { + /* if thread name changed, update the entire command */ + int len = strnchr(task_entry->comm, ' ', TASK_COMM_LEN) + - task_entry->comm; + + if (strncmp(task_entry->comm, task->comm, len)) + get_full_task_comm(task_entry, task); + return task_entry; + } + } + return NULL; +} + +static struct task_entry *find_or_register_task(struct uid_entry *uid_entry, + struct task_struct *task) +{ + struct task_entry *task_entry; + pid_t pid = task->pid; + + task_entry = find_task_entry(uid_entry, task); + if (task_entry) + return task_entry; + + task_entry = kzalloc(sizeof(struct task_entry), GFP_ATOMIC); + if (!task_entry) + return NULL; + + get_full_task_comm(task_entry, task); + + task_entry->pid = pid; + hash_add(uid_entry->task_entries, &task_entry->hash, (unsigned int)pid); + + return task_entry; +} + +static void remove_uid_tasks(struct uid_entry *uid_entry) +{ + struct task_entry *task_entry; + unsigned long bkt_task; + struct hlist_node *tmp_task; + + hash_for_each_safe(uid_entry->task_entries, bkt_task, + tmp_task, task_entry, hash) { + hash_del(&task_entry->hash); + kfree(task_entry); + } +} + +static void set_io_uid_tasks_zero(struct uid_entry *uid_entry) +{ + struct task_entry *task_entry; + unsigned long bkt_task; + + hash_for_each(uid_entry->task_entries, bkt_task, task_entry, hash) { + memset(&task_entry->io[UID_STATE_TOTAL_CURR], 0, + sizeof(struct io_stats)); + } +} + +static void add_uid_tasks_io_stats(struct uid_entry *uid_entry, + struct task_struct *task, int slot) +{ + struct task_entry *task_entry = find_or_register_task(uid_entry, task); + struct io_stats *task_io_slot = &task_entry->io[slot]; + + task_io_slot->read_bytes += task->ioac.read_bytes; + task_io_slot->write_bytes += compute_write_bytes(task); + task_io_slot->rchar += task->ioac.rchar; + task_io_slot->wchar += task->ioac.wchar; + task_io_slot->fsync += task->ioac.syscfs; +} + +static void compute_io_uid_tasks(struct uid_entry *uid_entry) +{ + struct task_entry *task_entry; + unsigned long bkt_task; + + hash_for_each(uid_entry->task_entries, bkt_task, task_entry, hash) { + compute_io_bucket_stats(&task_entry->io[uid_entry->state], + &task_entry->io[UID_STATE_TOTAL_CURR], + &task_entry->io[UID_STATE_TOTAL_LAST], + &task_entry->io[UID_STATE_DEAD_TASKS]); + } +} + +static void show_io_uid_tasks(struct seq_file *m, struct uid_entry *uid_entry) +{ + struct task_entry *task_entry; + unsigned long bkt_task; + + hash_for_each(uid_entry->task_entries, bkt_task, task_entry, hash) { + /* Separated by comma because space exists in task comm */ + seq_printf(m, "task,%s,%lu,%llu,%llu,%llu,%llu,%llu,%llu,%llu,%llu,%llu,%llu\n", + task_entry->comm, + (unsigned long)task_entry->pid, + task_entry->io[UID_STATE_FOREGROUND].rchar, + task_entry->io[UID_STATE_FOREGROUND].wchar, + task_entry->io[UID_STATE_FOREGROUND].read_bytes, + task_entry->io[UID_STATE_FOREGROUND].write_bytes, + task_entry->io[UID_STATE_BACKGROUND].rchar, + task_entry->io[UID_STATE_BACKGROUND].wchar, + task_entry->io[UID_STATE_BACKGROUND].read_bytes, + task_entry->io[UID_STATE_BACKGROUND].write_bytes, + task_entry->io[UID_STATE_FOREGROUND].fsync, + task_entry->io[UID_STATE_BACKGROUND].fsync); + } +} +#else +static void remove_uid_tasks(struct uid_entry *uid_entry) {}; +static void set_io_uid_tasks_zero(struct uid_entry *uid_entry) {}; +static void add_uid_tasks_io_stats(struct uid_entry *uid_entry, + struct task_struct *task, int slot) {}; +static void compute_io_uid_tasks(struct uid_entry *uid_entry) {}; +static void show_io_uid_tasks(struct seq_file *m, + struct uid_entry *uid_entry) {} +#endif + +static struct uid_entry *find_uid_entry(uid_t uid) +{ + struct uid_entry *uid_entry; + hash_for_each_possible(hash_table, uid_entry, hash, uid) { + if (uid_entry->uid == uid) + return uid_entry; + } + return NULL; +} + +static struct uid_entry *find_or_register_uid(uid_t uid) +{ + struct uid_entry *uid_entry; + + uid_entry = find_uid_entry(uid); + if (uid_entry) + return uid_entry; + + uid_entry = kzalloc(sizeof(struct uid_entry), GFP_ATOMIC); + if (!uid_entry) + return NULL; + + uid_entry->uid = uid; +#ifdef CONFIG_UID_SYS_STATS_DEBUG + hash_init(uid_entry->task_entries); +#endif + hash_add(hash_table, &uid_entry->hash, uid); + + return uid_entry; +} + +static int uid_cputime_show(struct seq_file *m, void *v) +{ + struct uid_entry *uid_entry = NULL; + struct task_struct *task, *temp; + struct user_namespace *user_ns = current_user_ns(); + u64 utime; + u64 stime; + unsigned long bkt; + uid_t uid; + + rt_mutex_lock(&uid_lock); + + hash_for_each(hash_table, bkt, uid_entry, hash) { + uid_entry->active_stime = 0; + uid_entry->active_utime = 0; + } + + rcu_read_lock(); + do_each_thread(temp, task) { + uid = from_kuid_munged(user_ns, task_uid(task)); + if (!uid_entry || uid_entry->uid != uid) + uid_entry = find_or_register_uid(uid); + if (!uid_entry) { + rcu_read_unlock(); + rt_mutex_unlock(&uid_lock); + pr_err("%s: failed to find the uid_entry for uid %d\n", + __func__, uid); + return -ENOMEM; + } + task_cputime_adjusted(task, &utime, &stime); + uid_entry->active_utime += utime; + uid_entry->active_stime += stime; + } while_each_thread(temp, task); + rcu_read_unlock(); + + hash_for_each(hash_table, bkt, uid_entry, hash) { + u64 total_utime = uid_entry->utime + + uid_entry->active_utime; + u64 total_stime = uid_entry->stime + + uid_entry->active_stime; + seq_printf(m, "%d: %llu %llu\n", uid_entry->uid, + ktime_to_ms(total_utime), ktime_to_ms(total_stime)); + } + + rt_mutex_unlock(&uid_lock); + return 0; +} + +static int uid_cputime_open(struct inode *inode, struct file *file) +{ + return single_open(file, uid_cputime_show, PDE_DATA(inode)); +} + +static const struct file_operations uid_cputime_fops = { + .open = uid_cputime_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int uid_remove_open(struct inode *inode, struct file *file) +{ + return single_open(file, NULL, NULL); +} + +static ssize_t uid_remove_write(struct file *file, + const char __user *buffer, size_t count, loff_t *ppos) +{ + struct uid_entry *uid_entry; + struct hlist_node *tmp; + char uids[128]; + char *start_uid, *end_uid = NULL; + long int uid_start = 0, uid_end = 0; + + if (count >= sizeof(uids)) + count = sizeof(uids) - 1; + + if (copy_from_user(uids, buffer, count)) + return -EFAULT; + + uids[count] = '\0'; + end_uid = uids; + start_uid = strsep(&end_uid, "-"); + + if (!start_uid || !end_uid) + return -EINVAL; + + if (kstrtol(start_uid, 10, &uid_start) != 0 || + kstrtol(end_uid, 10, &uid_end) != 0) { + return -EINVAL; + } + + /* Also remove uids from /proc/uid_time_in_state */ + cpufreq_task_times_remove_uids(uid_start, uid_end); + + rt_mutex_lock(&uid_lock); + + for (; uid_start <= uid_end; uid_start++) { + hash_for_each_possible_safe(hash_table, uid_entry, tmp, + hash, (uid_t)uid_start) { + if (uid_start == uid_entry->uid) { + remove_uid_tasks(uid_entry); + hash_del(&uid_entry->hash); + kfree(uid_entry); + } + } + } + + rt_mutex_unlock(&uid_lock); + return count; +} + +static const struct file_operations uid_remove_fops = { + .open = uid_remove_open, + .release = single_release, + .write = uid_remove_write, +}; + + +static void add_uid_io_stats(struct uid_entry *uid_entry, + struct task_struct *task, int slot) +{ + struct io_stats *io_slot = &uid_entry->io[slot]; + + io_slot->read_bytes += task->ioac.read_bytes; + io_slot->write_bytes += compute_write_bytes(task); + io_slot->rchar += task->ioac.rchar; + io_slot->wchar += task->ioac.wchar; + io_slot->fsync += task->ioac.syscfs; + + add_uid_tasks_io_stats(uid_entry, task, slot); +} + +static void update_io_stats_all_locked(void) +{ + struct uid_entry *uid_entry = NULL; + struct task_struct *task, *temp; + struct user_namespace *user_ns = current_user_ns(); + unsigned long bkt; + uid_t uid; + + hash_for_each(hash_table, bkt, uid_entry, hash) { + memset(&uid_entry->io[UID_STATE_TOTAL_CURR], 0, + sizeof(struct io_stats)); + set_io_uid_tasks_zero(uid_entry); + } + + rcu_read_lock(); + do_each_thread(temp, task) { + uid = from_kuid_munged(user_ns, task_uid(task)); + if (!uid_entry || uid_entry->uid != uid) + uid_entry = find_or_register_uid(uid); + if (!uid_entry) + continue; + add_uid_io_stats(uid_entry, task, UID_STATE_TOTAL_CURR); + } while_each_thread(temp, task); + rcu_read_unlock(); + + hash_for_each(hash_table, bkt, uid_entry, hash) { + compute_io_bucket_stats(&uid_entry->io[uid_entry->state], + &uid_entry->io[UID_STATE_TOTAL_CURR], + &uid_entry->io[UID_STATE_TOTAL_LAST], + &uid_entry->io[UID_STATE_DEAD_TASKS]); + compute_io_uid_tasks(uid_entry); + } +} + +static void update_io_stats_uid_locked(struct uid_entry *uid_entry) +{ + struct task_struct *task, *temp; + struct user_namespace *user_ns = current_user_ns(); + + memset(&uid_entry->io[UID_STATE_TOTAL_CURR], 0, + sizeof(struct io_stats)); + set_io_uid_tasks_zero(uid_entry); + + rcu_read_lock(); + do_each_thread(temp, task) { + if (from_kuid_munged(user_ns, task_uid(task)) != uid_entry->uid) + continue; + add_uid_io_stats(uid_entry, task, UID_STATE_TOTAL_CURR); + } while_each_thread(temp, task); + rcu_read_unlock(); + + compute_io_bucket_stats(&uid_entry->io[uid_entry->state], + &uid_entry->io[UID_STATE_TOTAL_CURR], + &uid_entry->io[UID_STATE_TOTAL_LAST], + &uid_entry->io[UID_STATE_DEAD_TASKS]); + compute_io_uid_tasks(uid_entry); +} + + +static int uid_io_show(struct seq_file *m, void *v) +{ + struct uid_entry *uid_entry; + unsigned long bkt; + + rt_mutex_lock(&uid_lock); + + update_io_stats_all_locked(); + + hash_for_each(hash_table, bkt, uid_entry, hash) { + seq_printf(m, "%d %llu %llu %llu %llu %llu %llu %llu %llu %llu %llu\n", + uid_entry->uid, + uid_entry->io[UID_STATE_FOREGROUND].rchar, + uid_entry->io[UID_STATE_FOREGROUND].wchar, + uid_entry->io[UID_STATE_FOREGROUND].read_bytes, + uid_entry->io[UID_STATE_FOREGROUND].write_bytes, + uid_entry->io[UID_STATE_BACKGROUND].rchar, + uid_entry->io[UID_STATE_BACKGROUND].wchar, + uid_entry->io[UID_STATE_BACKGROUND].read_bytes, + uid_entry->io[UID_STATE_BACKGROUND].write_bytes, + uid_entry->io[UID_STATE_FOREGROUND].fsync, + uid_entry->io[UID_STATE_BACKGROUND].fsync); + + show_io_uid_tasks(m, uid_entry); + } + + rt_mutex_unlock(&uid_lock); + return 0; +} + +static int uid_io_open(struct inode *inode, struct file *file) +{ + return single_open(file, uid_io_show, PDE_DATA(inode)); +} + +static const struct file_operations uid_io_fops = { + .open = uid_io_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int uid_procstat_open(struct inode *inode, struct file *file) +{ + return single_open(file, NULL, NULL); +} + +static ssize_t uid_procstat_write(struct file *file, + const char __user *buffer, size_t count, loff_t *ppos) +{ + struct uid_entry *uid_entry; + uid_t uid; + int argc, state; + char input[128]; + + if (count >= sizeof(input)) + return -EINVAL; + + if (copy_from_user(input, buffer, count)) + return -EFAULT; + + input[count] = '\0'; + + argc = sscanf(input, "%u %d", &uid, &state); + if (argc != 2) + return -EINVAL; + + if (state != UID_STATE_BACKGROUND && state != UID_STATE_FOREGROUND) + return -EINVAL; + + rt_mutex_lock(&uid_lock); + + uid_entry = find_or_register_uid(uid); + if (!uid_entry) { + rt_mutex_unlock(&uid_lock); + return -EINVAL; + } + + if (uid_entry->state == state) { + rt_mutex_unlock(&uid_lock); + return count; + } + + update_io_stats_uid_locked(uid_entry); + + uid_entry->state = state; + + rt_mutex_unlock(&uid_lock); + + return count; +} + +static const struct file_operations uid_procstat_fops = { + .open = uid_procstat_open, + .release = single_release, + .write = uid_procstat_write, +}; + +static int process_notifier(struct notifier_block *self, + unsigned long cmd, void *v) +{ + struct task_struct *task = v; + struct uid_entry *uid_entry; + u64 utime, stime; + uid_t uid; + + if (!task) + return NOTIFY_OK; + + rt_mutex_lock(&uid_lock); + uid = from_kuid_munged(current_user_ns(), task_uid(task)); + uid_entry = find_or_register_uid(uid); + if (!uid_entry) { + pr_err("%s: failed to find uid %d\n", __func__, uid); + goto exit; + } + + task_cputime_adjusted(task, &utime, &stime); + uid_entry->utime += utime; + uid_entry->stime += stime; + + add_uid_io_stats(uid_entry, task, UID_STATE_DEAD_TASKS); + +exit: + rt_mutex_unlock(&uid_lock); + return NOTIFY_OK; +} + +static struct notifier_block process_notifier_block = { + .notifier_call = process_notifier, +}; + +static int __init proc_uid_sys_stats_init(void) +{ + hash_init(hash_table); + + cpu_parent = proc_mkdir("uid_cputime", NULL); + if (!cpu_parent) { + pr_err("%s: failed to create uid_cputime proc entry\n", + __func__); + goto err; + } + + proc_create_data("remove_uid_range", 0222, cpu_parent, + &uid_remove_fops, NULL); + proc_create_data("show_uid_stat", 0444, cpu_parent, + &uid_cputime_fops, NULL); + + io_parent = proc_mkdir("uid_io", NULL); + if (!io_parent) { + pr_err("%s: failed to create uid_io proc entry\n", + __func__); + goto err; + } + + proc_create_data("stats", 0444, io_parent, + &uid_io_fops, NULL); + + proc_parent = proc_mkdir("uid_procstat", NULL); + if (!proc_parent) { + pr_err("%s: failed to create uid_procstat proc entry\n", + __func__); + goto err; + } + + proc_create_data("set", 0222, proc_parent, + &uid_procstat_fops, NULL); + + profile_event_register(PROFILE_TASK_EXIT, &process_notifier_block); + + return 0; + +err: + remove_proc_subtree("uid_cputime", NULL); + remove_proc_subtree("uid_io", NULL); + remove_proc_subtree("uid_procstat", NULL); + return -ENOMEM; +} + +early_initcall(proc_uid_sys_stats_init); diff --git a/drivers/mmc/core/Kconfig b/drivers/mmc/core/Kconfig index 42e89060cd41..b3faf1062d4e 100644 --- a/drivers/mmc/core/Kconfig +++ b/drivers/mmc/core/Kconfig @@ -80,3 +80,17 @@ config MMC_TEST This driver is only of interest to those developing or testing a host driver. Most people should say N here. +config MMC_EMBEDDED_SDIO + boolean "MMC embedded SDIO device support" + help + If you say Y here, support will be added for embedded SDIO + devices which do not contain the necessary enumeration + support in hardware to be properly detected. + +config MMC_PARANOID_SD_INIT + bool "Enable paranoid SD card initialization" + help + If you say Y here, the MMC layer will be extra paranoid + about re-trying SD init requests. This can be a useful + work-around for buggy controllers and hardware. Enable + if you are experiencing issues with SD detection. diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index 29bfff2ed4d3..e71e6070ae75 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -2810,6 +2810,22 @@ void mmc_init_context_info(struct mmc_host *host) init_waitqueue_head(&host->context_info.wait); } +#ifdef CONFIG_MMC_EMBEDDED_SDIO +void mmc_set_embedded_sdio_data(struct mmc_host *host, + struct sdio_cis *cis, + struct sdio_cccr *cccr, + struct sdio_embedded_func *funcs, + int num_funcs) +{ + host->embedded_sdio_data.cis = cis; + host->embedded_sdio_data.cccr = cccr; + host->embedded_sdio_data.funcs = funcs; + host->embedded_sdio_data.num_funcs = num_funcs; +} + +EXPORT_SYMBOL(mmc_set_embedded_sdio_data); +#endif + static int __init mmc_init(void) { int ret; diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c index 3740fb0052a4..253122d32d0c 100644 --- a/drivers/mmc/core/host.c +++ b/drivers/mmc/core/host.c @@ -427,7 +427,8 @@ int mmc_add_host(struct mmc_host *host) #endif mmc_start_host(host); - mmc_register_pm_notifier(host); + if (!(host->pm_flags & MMC_PM_IGNORE_PM_NOTIFY)) + mmc_register_pm_notifier(host); return 0; } @@ -444,7 +445,8 @@ EXPORT_SYMBOL(mmc_add_host); */ void mmc_remove_host(struct mmc_host *host) { - mmc_unregister_pm_notifier(host); + if (!(host->pm_flags & MMC_PM_IGNORE_PM_NOTIFY)) + mmc_unregister_pm_notifier(host); mmc_stop_host(host); #ifdef CONFIG_DEBUG_FS diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index 814a04e8fdd7..b682e063628e 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -780,6 +780,7 @@ MMC_DEV_ATTR(manfid, "0x%06x\n", card->cid.manfid); MMC_DEV_ATTR(name, "%s\n", card->cid.prod_name); MMC_DEV_ATTR(oemid, "0x%04x\n", card->cid.oemid); MMC_DEV_ATTR(prv, "0x%x\n", card->cid.prv); +MMC_DEV_ATTR(rev, "0x%x\n", card->ext_csd.rev); MMC_DEV_ATTR(pre_eol_info, "0x%02x\n", card->ext_csd.pre_eol_info); MMC_DEV_ATTR(life_time, "0x%02x 0x%02x\n", card->ext_csd.device_life_time_est_typ_a, @@ -838,6 +839,7 @@ static struct attribute *mmc_std_attrs[] = { &dev_attr_name.attr, &dev_attr_oemid.attr, &dev_attr_prv.attr, + &dev_attr_rev.attr, &dev_attr_pre_eol_info.attr, &dev_attr_life_time.attr, &dev_attr_serial.attr, diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c index f74f9ef460cc..4b79c2639bea 100644 --- a/drivers/mmc/core/queue.c +++ b/drivers/mmc/core/queue.c @@ -17,6 +17,8 @@ #include <linux/mmc/card.h> #include <linux/mmc/host.h> +#include <linux/sched/rt.h> +#include <uapi/linux/sched/types.h> #include "queue.h" #include "block.h" @@ -43,6 +45,11 @@ static int mmc_queue_thread(void *d) struct mmc_queue *mq = d; struct request_queue *q = mq->queue; struct mmc_context_info *cntx = &mq->card->host->context_info; + struct sched_param scheduler_params = {0}; + + scheduler_params.sched_priority = 1; + + sched_setscheduler(current, SCHED_FIFO, &scheduler_params); current->flags |= PF_MEMALLOC; diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c index 33975ec14b7e..bd05a5accf7b 100644 --- a/drivers/mmc/core/sd.c +++ b/drivers/mmc/core/sd.c @@ -842,6 +842,9 @@ int mmc_sd_setup_card(struct mmc_host *host, struct mmc_card *card, bool reinit) { int err; +#ifdef CONFIG_MMC_PARANOID_SD_INIT + int retries; +#endif if (!reinit) { /* @@ -868,7 +871,26 @@ int mmc_sd_setup_card(struct mmc_host *host, struct mmc_card *card, /* * Fetch switch information from card. */ +#ifdef CONFIG_MMC_PARANOID_SD_INIT + for (retries = 1; retries <= 3; retries++) { + err = mmc_read_switch(card); + if (!err) { + if (retries > 1) { + printk(KERN_WARNING + "%s: recovered\n", + mmc_hostname(host)); + } + break; + } else { + printk(KERN_WARNING + "%s: read switch failed (attempt %d)\n", + mmc_hostname(host), retries); + } + } +#else err = mmc_read_switch(card); +#endif + if (err) return err; } @@ -1062,14 +1084,33 @@ static int mmc_sd_alive(struct mmc_host *host) */ static void mmc_sd_detect(struct mmc_host *host) { - int err; + int err = 0; +#ifdef CONFIG_MMC_PARANOID_SD_INIT + int retries = 5; +#endif mmc_get_card(host->card); /* * Just check if our card has been removed. */ +#ifdef CONFIG_MMC_PARANOID_SD_INIT + while(retries) { + err = mmc_send_status(host->card, NULL); + if (err) { + retries--; + udelay(5); + continue; + } + break; + } + if (!retries) { + printk(KERN_ERR "%s(%s): Unable to re-detect card (%d)\n", + __func__, mmc_hostname(host), err); + } +#else err = _mmc_detect_card_removed(host); +#endif mmc_put_card(host->card); @@ -1128,6 +1169,9 @@ static int mmc_sd_suspend(struct mmc_host *host) static int _mmc_sd_resume(struct mmc_host *host) { int err = 0; +#ifdef CONFIG_MMC_PARANOID_SD_INIT + int retries; +#endif mmc_claim_host(host); @@ -1135,7 +1179,23 @@ static int _mmc_sd_resume(struct mmc_host *host) goto out; mmc_power_up(host, host->card->ocr); +#ifdef CONFIG_MMC_PARANOID_SD_INIT + retries = 5; + while (retries) { + err = mmc_sd_init_card(host, host->card->ocr, host->card); + + if (err) { + printk(KERN_ERR "%s: Re-init card rc = %d (retries = %d)\n", + mmc_hostname(host), err, retries); + mdelay(5); + retries--; + continue; + } + break; + } +#else err = mmc_sd_init_card(host, host->card->ocr, host->card); +#endif mmc_card_clr_suspended(host->card); out: @@ -1210,6 +1270,9 @@ int mmc_attach_sd(struct mmc_host *host) { int err; u32 ocr, rocr; +#ifdef CONFIG_MMC_PARANOID_SD_INIT + int retries; +#endif WARN_ON(!host->claimed); @@ -1251,9 +1314,27 @@ int mmc_attach_sd(struct mmc_host *host) /* * Detect and init the card. */ +#ifdef CONFIG_MMC_PARANOID_SD_INIT + retries = 5; + while (retries) { + err = mmc_sd_init_card(host, rocr, NULL); + if (err) { + retries--; + continue; + } + break; + } + + if (!retries) { + printk(KERN_ERR "%s: mmc_sd_init_card() failure (err = %d)\n", + mmc_hostname(host), err); + goto err; + } +#else err = mmc_sd_init_card(host, rocr, NULL); if (err) goto err; +#endif mmc_release_host(host); err = mmc_add_card(host->card); diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c index 7568cea55922..b10909055ec5 100644 --- a/drivers/mmc/core/sdio.c +++ b/drivers/mmc/core/sdio.c @@ -31,6 +31,10 @@ #include "sdio_ops.h" #include "sdio_cis.h" +#ifdef CONFIG_MMC_EMBEDDED_SDIO +#include <linux/mmc/sdio_ids.h> +#endif + static int sdio_read_fbr(struct sdio_func *func) { int ret; @@ -706,27 +710,43 @@ try_again: goto finish; } - /* - * Read the common registers. Note that we should try to - * validate whether UHS would work or not. - */ - err = sdio_read_cccr(card, ocr); - if (err) { - mmc_sdio_resend_if_cond(host, card); - if (ocr & R4_18V_PRESENT) { - /* Retry init sequence, but without R4_18V_PRESENT. */ - retries = 0; - goto try_again; +#ifdef CONFIG_MMC_EMBEDDED_SDIO + if (host->embedded_sdio_data.cccr) + memcpy(&card->cccr, host->embedded_sdio_data.cccr, sizeof(struct sdio_cccr)); + else { +#endif + /* + * Read the common registers. Note that we should try to + * validate whether UHS would work or not. + */ + err = sdio_read_cccr(card, ocr); + if (err) { + mmc_sdio_resend_if_cond(host, card); + if (ocr & R4_18V_PRESENT) { + /* Retry init sequence, but without R4_18V_PRESENT. */ + retries = 0; + goto try_again; + } + return err; } - return err; +#ifdef CONFIG_MMC_EMBEDDED_SDIO } +#endif - /* - * Read the common CIS tuples. - */ - err = sdio_read_common_cis(card); - if (err) - goto remove; +#ifdef CONFIG_MMC_EMBEDDED_SDIO + if (host->embedded_sdio_data.cis) + memcpy(&card->cis, host->embedded_sdio_data.cis, sizeof(struct sdio_cis)); + else { +#endif + /* + * Read the common CIS tuples. + */ + err = sdio_read_common_cis(card); + if (err) + goto remove; +#ifdef CONFIG_MMC_EMBEDDED_SDIO + } +#endif if (oldcard) { int same = (card->cis.vendor == oldcard->cis.vendor && @@ -1139,14 +1159,36 @@ int mmc_attach_sdio(struct mmc_host *host) funcs = (ocr & 0x70000000) >> 28; card->sdio_funcs = 0; +#ifdef CONFIG_MMC_EMBEDDED_SDIO + if (host->embedded_sdio_data.funcs) + card->sdio_funcs = funcs = host->embedded_sdio_data.num_funcs; +#endif + /* * Initialize (but don't add) all present functions. */ for (i = 0; i < funcs; i++, card->sdio_funcs++) { - err = sdio_init_func(host->card, i + 1); - if (err) - goto remove; - +#ifdef CONFIG_MMC_EMBEDDED_SDIO + if (host->embedded_sdio_data.funcs) { + struct sdio_func *tmp; + + tmp = sdio_alloc_func(host->card); + if (IS_ERR(tmp)) + goto remove; + tmp->num = (i + 1); + card->sdio_func[i] = tmp; + tmp->class = host->embedded_sdio_data.funcs[i].f_class; + tmp->max_blksize = host->embedded_sdio_data.funcs[i].f_maxblksize; + tmp->vendor = card->cis.vendor; + tmp->device = card->cis.device; + } else { +#endif + err = sdio_init_func(host->card, i + 1); + if (err) + goto remove; +#ifdef CONFIG_MMC_EMBEDDED_SDIO + } +#endif /* * Enable Runtime PM for this func (if supported) */ diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c index 2b32b88949ba..997d556fccf1 100644 --- a/drivers/mmc/core/sdio_bus.c +++ b/drivers/mmc/core/sdio_bus.c @@ -29,6 +29,10 @@ #include "sdio_cis.h" #include "sdio_bus.h" +#ifdef CONFIG_MMC_EMBEDDED_SDIO +#include <linux/mmc/host.h> +#endif + #define to_sdio_driver(d) container_of(d, struct sdio_driver, drv) /* show configuration fields */ @@ -264,7 +268,14 @@ static void sdio_release_func(struct device *dev) { struct sdio_func *func = dev_to_sdio_func(dev); - sdio_free_func_cis(func); +#ifdef CONFIG_MMC_EMBEDDED_SDIO + /* + * If this device is embedded then we never allocated + * cis tables for this func + */ + if (!func->card->host->embedded_sdio_data.funcs) +#endif + sdio_free_func_cis(func); kfree(func->info); kfree(func->tmpbuf); diff --git a/drivers/mtd/devices/block2mtd.c b/drivers/mtd/devices/block2mtd.c index 7c887f111a7d..62fd6905c648 100644 --- a/drivers/mtd/devices/block2mtd.c +++ b/drivers/mtd/devices/block2mtd.c @@ -431,7 +431,7 @@ static int block2mtd_setup2(const char *val) } -static int block2mtd_setup(const char *val, struct kernel_param *kp) +static int block2mtd_setup(const char *val, const struct kernel_param *kp) { #ifdef MODULE return block2mtd_setup2(val); diff --git a/drivers/mtd/devices/phram.c b/drivers/mtd/devices/phram.c index 9734e6903fe6..d312c1b5a78e 100644 --- a/drivers/mtd/devices/phram.c +++ b/drivers/mtd/devices/phram.c @@ -269,7 +269,7 @@ error: return ret; } -static int phram_param_call(const char *val, struct kernel_param *kp) +static int phram_param_call(const char *val, const struct kernel_param *kp) { #ifdef MODULE return phram_setup(val); diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c index 0104d9537329..e94a63881590 100644 --- a/drivers/mtd/ubi/build.c +++ b/drivers/mtd/ubi/build.c @@ -1349,7 +1349,7 @@ static int bytes_str_to_int(const char *str) * This function returns zero in case of success and a negative error code in * case of error. */ -static int ubi_mtd_param_parse(const char *val, struct kernel_param *kp) +static int ubi_mtd_param_parse(const char *val, const struct kernel_param *kp) { int i, len; struct mtd_dev_param *p; diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c index 3df872f56289..37026473cf6d 100644 --- a/drivers/net/ethernet/sfc/mcdi.c +++ b/drivers/net/ethernet/sfc/mcdi.c @@ -376,7 +376,7 @@ static int efx_mcdi_poll(struct efx_nic *efx) * because generally mcdi responses are fast. After that, back off * and poll once a jiffy (approximately) */ - spins = TICK_USEC; + spins = USER_TICK_USEC; finish = jiffies + MCDI_RPC_TIMEOUT; while (1) { diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c index 297a986e6653..f347e5ac6677 100644 --- a/drivers/net/ppp/ppp_async.c +++ b/drivers/net/ppp/ppp_async.c @@ -770,7 +770,7 @@ process_input_packet(struct asyncppp *ap) { struct sk_buff *skb; unsigned char *p; - unsigned int len, fcs, proto; + unsigned int len, fcs; skb = ap->rpkt; if (ap->state & (SC_TOSS | SC_ESCAPE)) @@ -799,14 +799,14 @@ process_input_packet(struct asyncppp *ap) goto err; p = skb_pull(skb, 2); } - proto = p[0]; - if (proto & 1) { - /* protocol is compressed */ - *(u8 *)skb_push(skb, 1) = 0; - } else { + + /* If protocol field is not compressed, it can be LCP packet */ + if (!(p[0] & 0x01)) { + unsigned int proto; + if (skb->len < 2) goto err; - proto = (proto << 8) + p[1]; + proto = (p[0] << 8) + p[1]; if (proto == PPP_LCP) async_lcp_peek(ap, p, skb->len, 1); } diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 8faf4488340d..bd37ed169b2d 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -1981,6 +1981,46 @@ ppp_do_recv(struct ppp *ppp, struct sk_buff *skb, struct channel *pch) ppp_recv_unlock(ppp); } +/** + * __ppp_decompress_proto - Decompress protocol field, slim version. + * @skb: Socket buffer where protocol field should be decompressed. It must have + * at least 1 byte of head room and 1 byte of linear data. First byte of + * data must be a protocol field byte. + * + * Decompress protocol field in PPP header if it's compressed, e.g. when + * Protocol-Field-Compression (PFC) was negotiated. No checks w.r.t. skb data + * length are done in this function. + */ +static void __ppp_decompress_proto(struct sk_buff *skb) +{ + if (skb->data[0] & 0x01) + *(u8 *)skb_push(skb, 1) = 0x00; +} + +/** + * ppp_decompress_proto - Check skb data room and decompress protocol field. + * @skb: Socket buffer where protocol field should be decompressed. First byte + * of data must be a protocol field byte. + * + * Decompress protocol field in PPP header if it's compressed, e.g. when + * Protocol-Field-Compression (PFC) was negotiated. This function also makes + * sure that skb data room is sufficient for Protocol field, before and after + * decompression. + * + * Return: true - decompressed successfully, false - not enough room in skb. + */ +static bool ppp_decompress_proto(struct sk_buff *skb) +{ + /* At least one byte should be present (if protocol is compressed) */ + if (!pskb_may_pull(skb, 1)) + return false; + + __ppp_decompress_proto(skb); + + /* Protocol field should occupy 2 bytes when not compressed */ + return pskb_may_pull(skb, 2); +} + void ppp_input(struct ppp_channel *chan, struct sk_buff *skb) { @@ -1993,7 +2033,7 @@ ppp_input(struct ppp_channel *chan, struct sk_buff *skb) } read_lock_bh(&pch->upl); - if (!pskb_may_pull(skb, 2)) { + if (!ppp_decompress_proto(skb)) { kfree_skb(skb); if (pch->ppp) { ++pch->ppp->dev->stats.rx_length_errors; @@ -2090,6 +2130,9 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) if (ppp->flags & SC_MUST_COMP && ppp->rstate & SC_DC_FERROR) goto err; + /* At this point the "Protocol" field MUST be decompressed, either in + * ppp_input(), ppp_decompress_frame() or in ppp_receive_mp_frame(). + */ proto = PPP_PROTO(skb); switch (proto) { case PPP_VJC_COMP: @@ -2261,6 +2304,9 @@ ppp_decompress_frame(struct ppp *ppp, struct sk_buff *skb) skb_put(skb, len); skb_pull(skb, 2); /* pull off the A/C bytes */ + /* Don't call __ppp_decompress_proto() here, but instead rely on + * corresponding algo (mppe/bsd/deflate) to decompress it. + */ } else { /* Uncompressed frame - pass to decompressor so it can update its dictionary if necessary. */ @@ -2306,9 +2352,11 @@ ppp_receive_mp_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch) /* * Do protocol ID decompression on the first fragment of each packet. + * We have to do that here, because ppp_receive_nonmp_frame() expects + * decompressed protocol field. */ - if ((PPP_MP_CB(skb)->BEbits & B) && (skb->data[0] & 1)) - *(u8 *)skb_push(skb, 1) = 0; + if (PPP_MP_CB(skb)->BEbits & B) + __ppp_decompress_proto(skb); /* * Expand sequence number to 32 bits, making it as close diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c index 7868c29071d4..41b5b4771556 100644 --- a/drivers/net/ppp/ppp_synctty.c +++ b/drivers/net/ppp/ppp_synctty.c @@ -708,11 +708,10 @@ ppp_sync_input(struct syncppp *ap, const unsigned char *buf, p = skb_pull(skb, 2); } - /* decompress protocol field if compressed */ - if (p[0] & 1) { - /* protocol is compressed */ - *(u8 *)skb_push(skb, 1) = 0; - } else if (skb->len < 2) + /* PPP packet length should be >= 2 bytes when protocol field is not + * compressed. + */ + if (!(p[0] & 0x01) && skb->len < 2) goto err; /* queue the frame to be processed */ diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c index 51d769901397..c22a7892648e 100644 --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -325,11 +325,6 @@ allow_packet: skb_pull(skb, 2); } - if ((*skb->data) & 1) { - /* protocol is compressed */ - *(u8 *)skb_push(skb, 1) = 0; - } - skb->ip_summed = CHECKSUM_NONE; skb_set_network_header(skb, skb->head-skb->data); ppp_input(&po->chan, skb); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index ba34f61d70de..02150fd6dfb2 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -2299,6 +2299,12 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, int le; int ret; +#ifdef CONFIG_ANDROID_PARANOID_NETWORK + if (cmd != TUNGETIFF && !capable(CAP_NET_ADMIN)) { + return -EPERM; + } +#endif + if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || _IOC_TYPE(cmd) == SOCK_IOC_TYPE) { if (copy_from_user(&ifr, argp, ifreq_len)) return -EFAULT; diff --git a/drivers/net/wireless/Kconfig b/drivers/net/wireless/Kconfig index 166920ae23f8..8c456a66ac3b 100644 --- a/drivers/net/wireless/Kconfig +++ b/drivers/net/wireless/Kconfig @@ -114,4 +114,11 @@ config USB_NET_RNDIS_WLAN If you choose to build a module, it'll be called rndis_wlan. +config VIRT_WIFI + tristate "Wifi wrapper for ethernet drivers" + depends on CFG80211 + ---help--- + This option adds support for ethernet connections to appear as if they + are wifi connections through a special rtnetlink device. + endif # WLAN diff --git a/drivers/net/wireless/Makefile b/drivers/net/wireless/Makefile index 7fc96306712a..6cfe74515c95 100644 --- a/drivers/net/wireless/Makefile +++ b/drivers/net/wireless/Makefile @@ -27,3 +27,5 @@ obj-$(CONFIG_PCMCIA_WL3501) += wl3501_cs.o obj-$(CONFIG_USB_NET_RNDIS_WLAN) += rndis_wlan.o obj-$(CONFIG_MAC80211_HWSIM) += mac80211_hwsim.o + +obj-$(CONFIG_VIRT_WIFI) += virt_wifi.o diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index 04fa66ed99a0..31f08aa2723a 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -2841,7 +2841,6 @@ static s32 brcmf_inform_single_bss(struct brcmf_cfg80211_info *cfg, struct brcmf_bss_info_le *bi) { struct wiphy *wiphy = cfg_to_wiphy(cfg); - struct ieee80211_channel *notify_channel; struct cfg80211_bss *bss; struct ieee80211_supported_band *band; struct brcmu_chan ch; @@ -2851,7 +2850,7 @@ static s32 brcmf_inform_single_bss(struct brcmf_cfg80211_info *cfg, u16 notify_interval; u8 *notify_ie; size_t notify_ielen; - s32 notify_signal; + struct cfg80211_inform_bss bss_data = {}; if (le32_to_cpu(bi->length) > WL_BSS_INFO_MAX) { brcmf_err("Bss info is larger than buffer. Discarding\n"); @@ -2871,27 +2870,28 @@ static s32 brcmf_inform_single_bss(struct brcmf_cfg80211_info *cfg, band = wiphy->bands[NL80211_BAND_5GHZ]; freq = ieee80211_channel_to_frequency(channel, band->band); - notify_channel = ieee80211_get_channel(wiphy, freq); + bss_data.chan = ieee80211_get_channel(wiphy, freq); + bss_data.scan_width = NL80211_BSS_CHAN_WIDTH_20; + bss_data.boottime_ns = ktime_to_ns(ktime_get_boottime()); notify_capability = le16_to_cpu(bi->capability); notify_interval = le16_to_cpu(bi->beacon_period); notify_ie = (u8 *)bi + le16_to_cpu(bi->ie_offset); notify_ielen = le32_to_cpu(bi->ie_length); - notify_signal = (s16)le16_to_cpu(bi->RSSI) * 100; + bss_data.signal = (s16)le16_to_cpu(bi->RSSI) * 100; brcmf_dbg(CONN, "bssid: %pM\n", bi->BSSID); brcmf_dbg(CONN, "Channel: %d(%d)\n", channel, freq); brcmf_dbg(CONN, "Capability: %X\n", notify_capability); brcmf_dbg(CONN, "Beacon interval: %d\n", notify_interval); - brcmf_dbg(CONN, "Signal: %d\n", notify_signal); - - bss = cfg80211_inform_bss(wiphy, notify_channel, - CFG80211_BSS_FTYPE_UNKNOWN, - (const u8 *)bi->BSSID, - 0, notify_capability, - notify_interval, notify_ie, - notify_ielen, notify_signal, - GFP_KERNEL); + brcmf_dbg(CONN, "Signal: %d\n", bss_data.signal); + + bss = cfg80211_inform_bss_data(wiphy, &bss_data, + CFG80211_BSS_FTYPE_UNKNOWN, + (const u8 *)bi->BSSID, + 0, notify_capability, + notify_interval, notify_ie, + notify_ielen, GFP_KERNEL); if (!bss) return -ENOMEM; diff --git a/drivers/net/wireless/ti/wlcore/init.c b/drivers/net/wireless/ti/wlcore/init.c index 58898b99d3f7..145e10a8be55 100644 --- a/drivers/net/wireless/ti/wlcore/init.c +++ b/drivers/net/wireless/ti/wlcore/init.c @@ -549,6 +549,11 @@ static int wl12xx_init_ap_role(struct wl1271 *wl, struct wl12xx_vif *wlvif) { int ret; + /* Disable filtering */ + ret = wl1271_acx_group_address_tbl(wl, wlvif, false, NULL, 0); + if (ret < 0) + return ret; + ret = wl1271_acx_ap_max_tx_retry(wl, wlvif); if (ret < 0) return ret; diff --git a/drivers/net/wireless/virt_wifi.c b/drivers/net/wireless/virt_wifi.c new file mode 100644 index 000000000000..45ca9550ee24 --- /dev/null +++ b/drivers/net/wireless/virt_wifi.c @@ -0,0 +1,633 @@ +// SPDX-License-Identifier: GPL-2.0 +/* drivers/net/wireless/virt_wifi.c + * + * A fake implementation of cfg80211_ops that can be tacked on to an ethernet + * net_device to make it appear as a wireless connection. + * + * Copyright (C) 2018 Google, Inc. + * + * Author: schuffelen@google.com + */ + +#include <net/cfg80211.h> +#include <net/rtnetlink.h> +#include <linux/etherdevice.h> +#include <linux/module.h> + +#include <net/cfg80211.h> +#include <net/rtnetlink.h> +#include <linux/etherdevice.h> +#include <linux/module.h> + +static struct wiphy *common_wiphy; + +struct virt_wifi_wiphy_priv { + struct delayed_work scan_result; + struct cfg80211_scan_request *scan_request; + bool being_deleted; +}; + +static struct ieee80211_channel channel_2ghz = { + .band = NL80211_BAND_2GHZ, + .center_freq = 2432, + .hw_value = 2432, + .max_power = 20, +}; + +static struct ieee80211_rate bitrates_2ghz[] = { + { .bitrate = 10 }, + { .bitrate = 20 }, + { .bitrate = 55 }, + { .bitrate = 110 }, + { .bitrate = 60 }, + { .bitrate = 120 }, + { .bitrate = 240 }, +}; + +static struct ieee80211_supported_band band_2ghz = { + .channels = &channel_2ghz, + .bitrates = bitrates_2ghz, + .band = NL80211_BAND_2GHZ, + .n_channels = 1, + .n_bitrates = ARRAY_SIZE(bitrates_2ghz), + .ht_cap = { + .ht_supported = true, + .cap = IEEE80211_HT_CAP_SUP_WIDTH_20_40 | + IEEE80211_HT_CAP_GRN_FLD | + IEEE80211_HT_CAP_SGI_20 | + IEEE80211_HT_CAP_SGI_40 | + IEEE80211_HT_CAP_DSSSCCK40, + .ampdu_factor = 0x3, + .ampdu_density = 0x6, + .mcs = { + .rx_mask = {0xff, 0xff}, + .tx_params = IEEE80211_HT_MCS_TX_DEFINED, + }, + }, +}; + +static struct ieee80211_channel channel_5ghz = { + .band = NL80211_BAND_5GHZ, + .center_freq = 5240, + .hw_value = 5240, + .max_power = 20, +}; + +static struct ieee80211_rate bitrates_5ghz[] = { + { .bitrate = 60 }, + { .bitrate = 120 }, + { .bitrate = 240 }, +}; + +#define RX_MCS_MAP (IEEE80211_VHT_MCS_SUPPORT_0_9 << 0 | \ + IEEE80211_VHT_MCS_SUPPORT_0_9 << 2 | \ + IEEE80211_VHT_MCS_SUPPORT_0_9 << 4 | \ + IEEE80211_VHT_MCS_SUPPORT_0_9 << 6 | \ + IEEE80211_VHT_MCS_SUPPORT_0_9 << 8 | \ + IEEE80211_VHT_MCS_SUPPORT_0_9 << 10 | \ + IEEE80211_VHT_MCS_SUPPORT_0_9 << 12 | \ + IEEE80211_VHT_MCS_SUPPORT_0_9 << 14) + +#define TX_MCS_MAP (IEEE80211_VHT_MCS_SUPPORT_0_9 << 0 | \ + IEEE80211_VHT_MCS_SUPPORT_0_9 << 2 | \ + IEEE80211_VHT_MCS_SUPPORT_0_9 << 4 | \ + IEEE80211_VHT_MCS_SUPPORT_0_9 << 6 | \ + IEEE80211_VHT_MCS_SUPPORT_0_9 << 8 | \ + IEEE80211_VHT_MCS_SUPPORT_0_9 << 10 | \ + IEEE80211_VHT_MCS_SUPPORT_0_9 << 12 | \ + IEEE80211_VHT_MCS_SUPPORT_0_9 << 14) + +static struct ieee80211_supported_band band_5ghz = { + .channels = &channel_5ghz, + .bitrates = bitrates_5ghz, + .band = NL80211_BAND_5GHZ, + .n_channels = 1, + .n_bitrates = ARRAY_SIZE(bitrates_5ghz), + .ht_cap = { + .ht_supported = true, + .cap = IEEE80211_HT_CAP_SUP_WIDTH_20_40 | + IEEE80211_HT_CAP_GRN_FLD | + IEEE80211_HT_CAP_SGI_20 | + IEEE80211_HT_CAP_SGI_40 | + IEEE80211_HT_CAP_DSSSCCK40, + .ampdu_factor = 0x3, + .ampdu_density = 0x6, + .mcs = { + .rx_mask = {0xff, 0xff}, + .tx_params = IEEE80211_HT_MCS_TX_DEFINED, + }, + }, + .vht_cap = { + .vht_supported = true, + .cap = IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 | + IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ | + IEEE80211_VHT_CAP_RXLDPC | + IEEE80211_VHT_CAP_SHORT_GI_80 | + IEEE80211_VHT_CAP_SHORT_GI_160 | + IEEE80211_VHT_CAP_TXSTBC | + IEEE80211_VHT_CAP_RXSTBC_1 | + IEEE80211_VHT_CAP_RXSTBC_2 | + IEEE80211_VHT_CAP_RXSTBC_3 | + IEEE80211_VHT_CAP_RXSTBC_4 | + IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK, + .vht_mcs = { + .rx_mcs_map = cpu_to_le16(RX_MCS_MAP), + .tx_mcs_map = cpu_to_le16(TX_MCS_MAP), + } + }, +}; + +/* Assigned at module init. Guaranteed locally-administered and unicast. */ +static u8 fake_router_bssid[ETH_ALEN] __ro_after_init = {}; + +/* Called with the rtnl lock held. */ +static int virt_wifi_scan(struct wiphy *wiphy, + struct cfg80211_scan_request *request) +{ + struct virt_wifi_wiphy_priv *priv = wiphy_priv(wiphy); + + wiphy_debug(wiphy, "scan\n"); + + if (priv->scan_request || priv->being_deleted) + return -EBUSY; + + priv->scan_request = request; + schedule_delayed_work(&priv->scan_result, HZ * 2); + + return 0; +} + +/* Acquires and releases the rdev BSS lock. */ +static void virt_wifi_scan_result(struct work_struct *work) +{ + struct { + u8 tag; + u8 len; + u8 ssid[8]; + } __packed ssid = { + .tag = WLAN_EID_SSID, .len = 8, .ssid = "VirtWifi", + }; + struct cfg80211_bss *informed_bss; + struct virt_wifi_wiphy_priv *priv = + container_of(work, struct virt_wifi_wiphy_priv, + scan_result.work); + struct wiphy *wiphy = priv_to_wiphy(priv); + struct cfg80211_scan_info scan_info = { .aborted = false }; + + informed_bss = cfg80211_inform_bss(wiphy, &channel_5ghz, + CFG80211_BSS_FTYPE_PRESP, + fake_router_bssid, + ktime_get_boot_ns(), + WLAN_CAPABILITY_ESS, 0, + (void *)&ssid, sizeof(ssid), + DBM_TO_MBM(-50), GFP_KERNEL); + cfg80211_put_bss(wiphy, informed_bss); + + /* Schedules work which acquires and releases the rtnl lock. */ + cfg80211_scan_done(priv->scan_request, &scan_info); + priv->scan_request = NULL; +} + +/* May acquire and release the rdev BSS lock. */ +static void virt_wifi_cancel_scan(struct wiphy *wiphy) +{ + struct virt_wifi_wiphy_priv *priv = wiphy_priv(wiphy); + + cancel_delayed_work_sync(&priv->scan_result); + /* Clean up dangling callbacks if necessary. */ + if (priv->scan_request) { + struct cfg80211_scan_info scan_info = { .aborted = true }; + /* Schedules work which acquires and releases the rtnl lock. */ + cfg80211_scan_done(priv->scan_request, &scan_info); + priv->scan_request = NULL; + } +} + +struct virt_wifi_netdev_priv { + struct delayed_work connect; + struct net_device *lowerdev; + struct net_device *upperdev; + u32 tx_packets; + u32 tx_failed; + u8 connect_requested_bss[ETH_ALEN]; + bool is_up; + bool is_connected; + bool being_deleted; +}; + +/* Called with the rtnl lock held. */ +static int virt_wifi_connect(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_connect_params *sme) +{ + struct virt_wifi_netdev_priv *priv = netdev_priv(netdev); + bool could_schedule; + + if (priv->being_deleted || !priv->is_up) + return -EBUSY; + + could_schedule = schedule_delayed_work(&priv->connect, HZ * 2); + if (!could_schedule) + return -EBUSY; + + if (sme->bssid) + ether_addr_copy(priv->connect_requested_bss, sme->bssid); + else + eth_zero_addr(priv->connect_requested_bss); + + wiphy_debug(wiphy, "connect\n"); + + return 0; +} + +/* Acquires and releases the rdev event lock. */ +static void virt_wifi_connect_complete(struct work_struct *work) +{ + struct virt_wifi_netdev_priv *priv = + container_of(work, struct virt_wifi_netdev_priv, connect.work); + u8 *requested_bss = priv->connect_requested_bss; + bool has_addr = !is_zero_ether_addr(requested_bss); + bool right_addr = ether_addr_equal(requested_bss, fake_router_bssid); + u16 status = WLAN_STATUS_SUCCESS; + + if (!priv->is_up || (has_addr && !right_addr)) + status = WLAN_STATUS_UNSPECIFIED_FAILURE; + else + priv->is_connected = true; + + /* Schedules an event that acquires the rtnl lock. */ + cfg80211_connect_result(priv->upperdev, requested_bss, NULL, 0, NULL, 0, + status, GFP_KERNEL); + netif_carrier_on(priv->upperdev); +} + +/* May acquire and release the rdev event lock. */ +static void virt_wifi_cancel_connect(struct net_device *netdev) +{ + struct virt_wifi_netdev_priv *priv = netdev_priv(netdev); + + /* If there is work pending, clean up dangling callbacks. */ + if (cancel_delayed_work_sync(&priv->connect)) { + /* Schedules an event that acquires the rtnl lock. */ + cfg80211_connect_result(priv->upperdev, + priv->connect_requested_bss, NULL, 0, + NULL, 0, + WLAN_STATUS_UNSPECIFIED_FAILURE, + GFP_KERNEL); + } +} + +/* Called with the rtnl lock held. Acquires the rdev event lock. */ +static int virt_wifi_disconnect(struct wiphy *wiphy, struct net_device *netdev, + u16 reason_code) +{ + struct virt_wifi_netdev_priv *priv = netdev_priv(netdev); + + if (priv->being_deleted) + return -EBUSY; + + wiphy_debug(wiphy, "disconnect\n"); + virt_wifi_cancel_connect(netdev); + + cfg80211_disconnected(netdev, reason_code, NULL, 0, true, GFP_KERNEL); + priv->is_connected = false; + netif_carrier_off(netdev); + + return 0; +} + +/* Called with the rtnl lock held. */ +static int virt_wifi_get_station(struct wiphy *wiphy, struct net_device *dev, + const u8 *mac, struct station_info *sinfo) +{ + struct virt_wifi_netdev_priv *priv = netdev_priv(dev); + + wiphy_debug(wiphy, "get_station\n"); + + if (!priv->is_connected || !ether_addr_equal(mac, fake_router_bssid)) + return -ENOENT; + + sinfo->filled = BIT_ULL(NL80211_STA_INFO_TX_PACKETS) | + BIT_ULL(NL80211_STA_INFO_TX_FAILED) | + BIT_ULL(NL80211_STA_INFO_SIGNAL) | + BIT_ULL(NL80211_STA_INFO_TX_BITRATE); + sinfo->tx_packets = priv->tx_packets; + sinfo->tx_failed = priv->tx_failed; + /* For CFG80211_SIGNAL_TYPE_MBM, value is expressed in _dBm_ */ + sinfo->signal = -50; + sinfo->txrate = (struct rate_info) { + .legacy = 10, /* units are 100kbit/s */ + }; + return 0; +} + +/* Called with the rtnl lock held. */ +static int virt_wifi_dump_station(struct wiphy *wiphy, struct net_device *dev, + int idx, u8 *mac, struct station_info *sinfo) +{ + struct virt_wifi_netdev_priv *priv = netdev_priv(dev); + + wiphy_debug(wiphy, "dump_station\n"); + + if (idx != 0 || !priv->is_connected) + return -ENOENT; + + ether_addr_copy(mac, fake_router_bssid); + return virt_wifi_get_station(wiphy, dev, fake_router_bssid, sinfo); +} + +static const struct cfg80211_ops virt_wifi_cfg80211_ops = { + .scan = virt_wifi_scan, + + .connect = virt_wifi_connect, + .disconnect = virt_wifi_disconnect, + + .get_station = virt_wifi_get_station, + .dump_station = virt_wifi_dump_station, +}; + +/* Acquires and releases the rtnl lock. */ +static struct wiphy *virt_wifi_make_wiphy(void) +{ + struct wiphy *wiphy; + struct virt_wifi_wiphy_priv *priv; + int err; + + wiphy = wiphy_new(&virt_wifi_cfg80211_ops, sizeof(*priv)); + + if (!wiphy) + return NULL; + + wiphy->max_scan_ssids = 4; + wiphy->max_scan_ie_len = 1000; + wiphy->signal_type = CFG80211_SIGNAL_TYPE_MBM; + + wiphy->bands[NL80211_BAND_2GHZ] = &band_2ghz; + wiphy->bands[NL80211_BAND_5GHZ] = &band_5ghz; + wiphy->bands[NL80211_BAND_60GHZ] = NULL; + + wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION); + + priv = wiphy_priv(wiphy); + priv->being_deleted = false; + priv->scan_request = NULL; + INIT_DELAYED_WORK(&priv->scan_result, virt_wifi_scan_result); + + err = wiphy_register(wiphy); + if (err < 0) { + wiphy_free(wiphy); + return NULL; + } + + return wiphy; +} + +/* Acquires and releases the rtnl lock. */ +static void virt_wifi_destroy_wiphy(struct wiphy *wiphy) +{ + struct virt_wifi_wiphy_priv *priv; + + WARN(!wiphy, "%s called with null wiphy", __func__); + if (!wiphy) + return; + + priv = wiphy_priv(wiphy); + priv->being_deleted = true; + virt_wifi_cancel_scan(wiphy); + + if (wiphy->registered) + wiphy_unregister(wiphy); + wiphy_free(wiphy); +} + +/* Enters and exits a RCU-bh critical section. */ +static netdev_tx_t virt_wifi_start_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct virt_wifi_netdev_priv *priv = netdev_priv(dev); + + priv->tx_packets++; + if (!priv->is_connected) { + priv->tx_failed++; + return NET_XMIT_DROP; + } + + skb->dev = priv->lowerdev; + return dev_queue_xmit(skb); +} + +/* Called with rtnl lock held. */ +static int virt_wifi_net_device_open(struct net_device *dev) +{ + struct virt_wifi_netdev_priv *priv = netdev_priv(dev); + + priv->is_up = true; + return 0; +} + +/* Called with rtnl lock held. */ +static int virt_wifi_net_device_stop(struct net_device *dev) +{ + struct virt_wifi_netdev_priv *n_priv = netdev_priv(dev); + struct virt_wifi_wiphy_priv *w_priv; + + n_priv->is_up = false; + + if (!dev->ieee80211_ptr) + return 0; + w_priv = wiphy_priv(dev->ieee80211_ptr->wiphy); + + virt_wifi_cancel_scan(dev->ieee80211_ptr->wiphy); + virt_wifi_cancel_connect(dev); + netif_carrier_off(dev); + + return 0; +} + +static const struct net_device_ops virt_wifi_ops = { + .ndo_start_xmit = virt_wifi_start_xmit, + .ndo_open = virt_wifi_net_device_open, + .ndo_stop = virt_wifi_net_device_stop, +}; + +/* Invoked as part of rtnl lock release. */ +static void virt_wifi_net_device_destructor(struct net_device *dev) +{ + /* Delayed past dellink to allow nl80211 to react to the device being + * deleted. + */ + kfree(dev->ieee80211_ptr); + dev->ieee80211_ptr = NULL; + free_netdev(dev); +} + +/* No lock interaction. */ +static void virt_wifi_setup(struct net_device *dev) +{ + ether_setup(dev); + dev->netdev_ops = &virt_wifi_ops; + dev->priv_destructor = virt_wifi_net_device_destructor; +} + +/* Called in a RCU read critical section from netif_receive_skb */ +static rx_handler_result_t virt_wifi_rx_handler(struct sk_buff **pskb) +{ + struct sk_buff *skb = *pskb; + struct virt_wifi_netdev_priv *priv = + rcu_dereference(skb->dev->rx_handler_data); + + if (!priv->is_connected) + return RX_HANDLER_PASS; + + /* GFP_ATOMIC because this is a packet interrupt handler. */ + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) { + dev_err(&priv->upperdev->dev, "can't skb_share_check\n"); + return RX_HANDLER_CONSUMED; + } + + *pskb = skb; + skb->dev = priv->upperdev; + skb->pkt_type = PACKET_HOST; + return RX_HANDLER_ANOTHER; +} + +/* Called with rtnl lock held. */ +static int virt_wifi_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct virt_wifi_netdev_priv *priv = netdev_priv(dev); + int err; + + if (!tb[IFLA_LINK]) + return -EINVAL; + + netif_carrier_off(dev); + + priv->upperdev = dev; + priv->lowerdev = __dev_get_by_index(src_net, + nla_get_u32(tb[IFLA_LINK])); + + if (!priv->lowerdev) + return -ENODEV; + if (!tb[IFLA_MTU]) + dev->mtu = priv->lowerdev->mtu; + else if (dev->mtu > priv->lowerdev->mtu) + return -EINVAL; + + err = netdev_rx_handler_register(priv->lowerdev, virt_wifi_rx_handler, + priv); + if (err) { + dev_err(&priv->lowerdev->dev, + "can't netdev_rx_handler_register: %d\n", err); + return err; + } + + eth_hw_addr_inherit(dev, priv->lowerdev); + netif_stacked_transfer_operstate(priv->lowerdev, dev); + + SET_NETDEV_DEV(dev, &priv->lowerdev->dev); + dev->ieee80211_ptr = kzalloc(sizeof(*dev->ieee80211_ptr), GFP_KERNEL); + + if (!dev->ieee80211_ptr) { + err = -ENOMEM; + goto remove_handler; + } + + dev->ieee80211_ptr->iftype = NL80211_IFTYPE_STATION; + dev->ieee80211_ptr->wiphy = common_wiphy; + + err = register_netdevice(dev); + if (err) { + dev_err(&priv->lowerdev->dev, "can't register_netdevice: %d\n", + err); + goto free_wireless_dev; + } + + err = netdev_upper_dev_link(priv->lowerdev, dev); + if (err) { + dev_err(&priv->lowerdev->dev, "can't netdev_upper_dev_link: %d\n", + err); + goto unregister_netdev; + } + + priv->being_deleted = false; + priv->is_connected = false; + priv->is_up = false; + INIT_DELAYED_WORK(&priv->connect, virt_wifi_connect_complete); + + return 0; +unregister_netdev: + unregister_netdevice(dev); +free_wireless_dev: + kfree(dev->ieee80211_ptr); + dev->ieee80211_ptr = NULL; +remove_handler: + netdev_rx_handler_unregister(priv->lowerdev); + + return err; +} + +/* Called with rtnl lock held. */ +static void virt_wifi_dellink(struct net_device *dev, + struct list_head *head) +{ + struct virt_wifi_netdev_priv *priv = netdev_priv(dev); + + if (dev->ieee80211_ptr) + virt_wifi_cancel_scan(dev->ieee80211_ptr->wiphy); + + priv->being_deleted = true; + virt_wifi_cancel_connect(dev); + netif_carrier_off(dev); + + netdev_rx_handler_unregister(priv->lowerdev); + netdev_upper_dev_unlink(priv->lowerdev, dev); + + unregister_netdevice_queue(dev, head); + + /* Deleting the wiphy is handled in the module destructor. */ +} + +static struct rtnl_link_ops virt_wifi_link_ops = { + .kind = "virt_wifi", + .setup = virt_wifi_setup, + .newlink = virt_wifi_newlink, + .dellink = virt_wifi_dellink, + .priv_size = sizeof(struct virt_wifi_netdev_priv), +}; + +/* Acquires and releases the rtnl lock. */ +static int __init virt_wifi_init_module(void) +{ + int err; + + /* Guaranteed to be locallly-administered and not multicast. */ + eth_random_addr(fake_router_bssid); + + common_wiphy = virt_wifi_make_wiphy(); + if (!common_wiphy) + return -ENOMEM; + + err = rtnl_link_register(&virt_wifi_link_ops); + if (err) + virt_wifi_destroy_wiphy(common_wiphy); + + return err; +} + +/* Acquires and releases the rtnl lock. */ +static void __exit virt_wifi_cleanup_module(void) +{ + /* Will delete any devices that depend on the wiphy. */ + rtnl_link_unregister(&virt_wifi_link_ops); + virt_wifi_destroy_wiphy(common_wiphy); +} + +module_init(virt_wifi_init_module); +module_exit(virt_wifi_cleanup_module); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Cody Schuffelen <schuffelen@google.com>"); +MODULE_DESCRIPTION("Driver for a wireless wrapper of ethernet devices"); +MODULE_ALIAS_RTNL_LINK("virt_wifi"); diff --git a/drivers/nfc/fdp/i2c.c b/drivers/nfc/fdp/i2c.c index 4020c11a9415..b86c8447df89 100644 --- a/drivers/nfc/fdp/i2c.c +++ b/drivers/nfc/fdp/i2c.c @@ -176,6 +176,16 @@ static int fdp_nci_i2c_read(struct fdp_i2c_phy *phy, struct sk_buff **skb) /* Packet that contains a length */ if (tmp[0] == 0 && tmp[1] == 0) { phy->next_read_size = (tmp[2] << 8) + tmp[3] + 3; + /* + * Ensure next_read_size does not exceed sizeof(tmp) + * for reading that many bytes during next iteration + */ + if (phy->next_read_size > FDP_NCI_I2C_MAX_PAYLOAD) { + dev_dbg(&client->dev, "%s: corrupted packet\n", + __func__); + phy->next_read_size = 5; + goto flush; + } } else { phy->next_read_size = FDP_NCI_I2C_MIN_PAYLOAD; diff --git a/drivers/nfc/st21nfca/dep.c b/drivers/nfc/st21nfca/dep.c index 7399eb2c5e1d..3f81bfdece69 100644 --- a/drivers/nfc/st21nfca/dep.c +++ b/drivers/nfc/st21nfca/dep.c @@ -219,7 +219,8 @@ static int st21nfca_tm_recv_atr_req(struct nfc_hci_dev *hdev, atr_req = (struct st21nfca_atr_req *)skb->data; - if (atr_req->length < sizeof(struct st21nfca_atr_req)) { + if (atr_req->length < sizeof(struct st21nfca_atr_req) || + atr_req->length > skb->len) { r = -EPROTO; goto exit; } diff --git a/drivers/nfc/st21nfca/se.c b/drivers/nfc/st21nfca/se.c index eac608a457f0..9add5fe92558 100644 --- a/drivers/nfc/st21nfca/se.c +++ b/drivers/nfc/st21nfca/se.c @@ -320,10 +320,17 @@ int st21nfca_connectivity_event_received(struct nfc_hci_dev *hdev, u8 host, * AID 81 5 to 16 * PARAMETERS 82 0 to 255 */ - if (skb->len < NFC_MIN_AID_LENGTH + 2 && + if (skb->len < NFC_MIN_AID_LENGTH + 2 || skb->data[0] != NFC_EVT_TRANSACTION_AID_TAG) return -EPROTO; + /* + * Buffer should have enough space for at least + * two tag fields + two length fields + aid_len (skb->data[1]) + */ + if (skb->len < skb->data[1] + 4) + return -EPROTO; + transaction = (struct nfc_evt_transaction *)devm_kzalloc(dev, skb->len - 2, GFP_KERNEL); if (!transaction) @@ -332,13 +339,16 @@ int st21nfca_connectivity_event_received(struct nfc_hci_dev *hdev, u8 host, transaction->aid_len = skb->data[1]; memcpy(transaction->aid, &skb->data[2], transaction->aid_len); + transaction->params_len = skb->data[transaction->aid_len + 3]; - /* Check next byte is PARAMETERS tag (82) */ + /* Check next byte is PARAMETERS tag (82) and the length field */ if (skb->data[transaction->aid_len + 2] != - NFC_EVT_TRANSACTION_PARAMS_TAG) + NFC_EVT_TRANSACTION_PARAMS_TAG || + skb->len < transaction->aid_len + transaction->params_len + 4) { + devm_kfree(dev, transaction); return -EPROTO; + } - transaction->params_len = skb->data[transaction->aid_len + 3]; memcpy(transaction->params, skb->data + transaction->aid_len + 4, transaction->params_len); diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 6337c394bfe3..b1103e519ef6 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -1112,42 +1112,66 @@ int __init early_init_dt_scan_memory(unsigned long node, const char *uname, return 0; } +/* + * Convert configs to something easy to use in C code + */ +#if defined(CONFIG_CMDLINE_FORCE) +static const int overwrite_incoming_cmdline = 1; +static const int read_dt_cmdline; +static const int concat_cmdline; +#elif defined(CONFIG_CMDLINE_EXTEND) +static const int overwrite_incoming_cmdline; +static const int read_dt_cmdline = 1; +static const int concat_cmdline = 1; +#else /* CMDLINE_FROM_BOOTLOADER */ +static const int overwrite_incoming_cmdline; +static const int read_dt_cmdline = 1; +static const int concat_cmdline; +#endif + +#ifdef CONFIG_CMDLINE +static const char *config_cmdline = CONFIG_CMDLINE; +#else +static const char *config_cmdline = ""; +#endif + int __init early_init_dt_scan_chosen(unsigned long node, const char *uname, int depth, void *data) { - int l; - const char *p; + int l = 0; + const char *p = NULL; + char *cmdline = data; pr_debug("search \"chosen\", depth: %d, uname: %s\n", depth, uname); - if (depth != 1 || !data || + if (depth != 1 || !cmdline || (strcmp(uname, "chosen") != 0 && strcmp(uname, "chosen@0") != 0)) return 0; early_init_dt_check_for_initrd(node); - /* Retrieve command line */ - p = of_get_flat_dt_prop(node, "bootargs", &l); - if (p != NULL && l > 0) - strlcpy(data, p, min((int)l, COMMAND_LINE_SIZE)); - - /* - * CONFIG_CMDLINE is meant to be a default in case nothing else - * managed to set the command line, unless CONFIG_CMDLINE_FORCE - * is set in which case we override whatever was found earlier. - */ -#ifdef CONFIG_CMDLINE -#if defined(CONFIG_CMDLINE_EXTEND) - strlcat(data, " ", COMMAND_LINE_SIZE); - strlcat(data, CONFIG_CMDLINE, COMMAND_LINE_SIZE); -#elif defined(CONFIG_CMDLINE_FORCE) - strlcpy(data, CONFIG_CMDLINE, COMMAND_LINE_SIZE); -#else - /* No arguments from boot loader, use kernel's cmdl*/ - if (!((char *)data)[0]) - strlcpy(data, CONFIG_CMDLINE, COMMAND_LINE_SIZE); -#endif -#endif /* CONFIG_CMDLINE */ + /* Put CONFIG_CMDLINE in if forced or if data had nothing in it to start */ + if (overwrite_incoming_cmdline || !cmdline[0]) + strlcpy(cmdline, config_cmdline, COMMAND_LINE_SIZE); + + /* Retrieve command line unless forcing */ + if (read_dt_cmdline) + p = of_get_flat_dt_prop(node, "bootargs", &l); + + if (p != NULL && l > 0) { + if (concat_cmdline) { + int cmdline_len; + int copy_len; + strlcat(cmdline, " ", COMMAND_LINE_SIZE); + cmdline_len = strlen(cmdline); + copy_len = COMMAND_LINE_SIZE - cmdline_len - 1; + copy_len = min((int)l, copy_len); + strncpy(cmdline + cmdline_len, p, copy_len); + cmdline[cmdline_len + copy_len] = '\0'; + } else { + strlcpy(cmdline, p, min((int)l, COMMAND_LINE_SIZE)); + } + } pr_debug("Command line is: %s\n", (char*)data); diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index 04d5c62588b7..13bb1d5a4b49 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -1076,7 +1076,8 @@ void pci_disable_link_state(struct pci_dev *pdev, int state) } EXPORT_SYMBOL(pci_disable_link_state); -static int pcie_aspm_set_policy(const char *val, struct kernel_param *kp) +static int pcie_aspm_set_policy(const char *val, + const struct kernel_param *kp) { int i; struct pcie_link_state *link; @@ -1103,7 +1104,7 @@ static int pcie_aspm_set_policy(const char *val, struct kernel_param *kp) return 0; } -static int pcie_aspm_get_policy(char *buffer, struct kernel_param *kp) +static int pcie_aspm_get_policy(char *buffer, const struct kernel_param *kp) { int i, cnt = 0; for (i = 0; i < ARRAY_SIZE(policy_str); i++) diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index c3fb9d66b768..00d16cdef064 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -9621,7 +9621,7 @@ static struct ibm_init_struct ibms_init[] __initdata = { }, }; -static int __init set_ibm_param(const char *val, struct kernel_param *kp) +static int __init set_ibm_param(const char *val, const struct kernel_param *kp) { unsigned int i; struct ibm_struct *ibm; diff --git a/drivers/power/supply/power_supply_sysfs.c b/drivers/power/supply/power_supply_sysfs.c index 2ccaf4ff4be4..2bbda7f7db04 100644 --- a/drivers/power/supply/power_supply_sysfs.c +++ b/drivers/power/supply/power_supply_sysfs.c @@ -122,7 +122,10 @@ static ssize_t power_supply_show_property(struct device *dev, else if (off >= POWER_SUPPLY_PROP_MODEL_NAME) return sprintf(buf, "%s\n", value.strval); - return sprintf(buf, "%d\n", value.intval); + if (off == POWER_SUPPLY_PROP_CHARGE_COUNTER_EXT) + return sprintf(buf, "%lld\n", value.int64val); + else + return sprintf(buf, "%d\n", value.intval); } static ssize_t power_supply_store_property(struct device *dev, @@ -246,6 +249,12 @@ static struct device_attribute power_supply_attrs[] = { POWER_SUPPLY_ATTR(precharge_current), POWER_SUPPLY_ATTR(charge_term_current), POWER_SUPPLY_ATTR(calibrate), + /* Local extensions */ + POWER_SUPPLY_ATTR(usb_hc), + POWER_SUPPLY_ATTR(usb_otg), + POWER_SUPPLY_ATTR(charge_enabled), + /* Local extensions of type int64_t */ + POWER_SUPPLY_ATTR(charge_counter_ext), /* Properties of type `const char *' */ POWER_SUPPLY_ATTR(model_name), POWER_SUPPLY_ATTR(manufacturer), diff --git a/drivers/rtc/rtc-palmas.c b/drivers/rtc/rtc-palmas.c index 4bcfb88674d3..34aea38ebfa6 100644 --- a/drivers/rtc/rtc-palmas.c +++ b/drivers/rtc/rtc-palmas.c @@ -45,6 +45,42 @@ struct palmas_rtc { /* Total number of RTC registers needed to set time*/ #define PALMAS_NUM_TIME_REGS (PALMAS_YEARS_REG - PALMAS_SECONDS_REG + 1) +/* + * Special bin2bcd mapping to deal with bcd storage of year. + * + * 0-69 -> 0xD0 + * 70-99 (1970 - 1999) -> 0xD0 - 0xF9 (correctly rolls to 0x00) + * 100-199 (2000 - 2099) -> 0x00 - 0x99 (does not roll to 0xA0 :-( ) + * 200-229 (2100 - 2129) -> 0xA0 - 0xC9 (really for completeness) + * 230- -> 0xC9 + * + * Confirmed: the only transition that does not work correctly for this rtc + * clock is the transition from 2099 to 2100, it proceeds to 2000. We will + * accept this issue since the clock retains and transitions the year correctly + * in all other conditions. + */ +static unsigned char year_bin2bcd(int val) +{ + if (val < 70) + return 0xD0; + if (val < 100) + return bin2bcd(val - 20) | 0x80; /* KISS leverage of bin2bcd */ + if (val >= 230) + return 0xC9; + if (val >= 200) + return bin2bcd(val - 180) | 0x80; + return bin2bcd(val - 100); +} + +static int year_bcd2bin(unsigned char val) +{ + if (val >= 0xD0) + return bcd2bin(val & 0x7F) + 20; + if (val >= 0xA0) + return bcd2bin(val & 0x7F) + 180; + return bcd2bin(val) + 100; +} + static int palmas_rtc_read_time(struct device *dev, struct rtc_time *tm) { unsigned char rtc_data[PALMAS_NUM_TIME_REGS]; @@ -71,7 +107,7 @@ static int palmas_rtc_read_time(struct device *dev, struct rtc_time *tm) tm->tm_hour = bcd2bin(rtc_data[2]); tm->tm_mday = bcd2bin(rtc_data[3]); tm->tm_mon = bcd2bin(rtc_data[4]) - 1; - tm->tm_year = bcd2bin(rtc_data[5]) + 100; + tm->tm_year = year_bcd2bin(rtc_data[5]); return ret; } @@ -87,7 +123,7 @@ static int palmas_rtc_set_time(struct device *dev, struct rtc_time *tm) rtc_data[2] = bin2bcd(tm->tm_hour); rtc_data[3] = bin2bcd(tm->tm_mday); rtc_data[4] = bin2bcd(tm->tm_mon + 1); - rtc_data[5] = bin2bcd(tm->tm_year - 100); + rtc_data[5] = year_bin2bcd(tm->tm_year); /* Stop RTC while updating the RTC time registers */ ret = palmas_update_bits(palmas, PALMAS_RTC_BASE, PALMAS_RTC_CTRL_REG, @@ -142,7 +178,7 @@ static int palmas_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alm) alm->time.tm_hour = bcd2bin(alarm_data[2]); alm->time.tm_mday = bcd2bin(alarm_data[3]); alm->time.tm_mon = bcd2bin(alarm_data[4]) - 1; - alm->time.tm_year = bcd2bin(alarm_data[5]) + 100; + alm->time.tm_year = year_bcd2bin(alarm_data[5]); ret = palmas_read(palmas, PALMAS_RTC_BASE, PALMAS_RTC_INTERRUPTS_REG, &int_val); @@ -173,7 +209,7 @@ static int palmas_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alm) alarm_data[2] = bin2bcd(alm->time.tm_hour); alarm_data[3] = bin2bcd(alm->time.tm_mday); alarm_data[4] = bin2bcd(alm->time.tm_mon + 1); - alarm_data[5] = bin2bcd(alm->time.tm_year - 100); + alarm_data[5] = year_bin2bcd(alm->time.tm_year); ret = palmas_bulk_write(palmas, PALMAS_RTC_BASE, PALMAS_ALARM_SECONDS_REG, alarm_data, PALMAS_NUM_TIME_REGS); diff --git a/drivers/scsi/fcoe/fcoe_transport.c b/drivers/scsi/fcoe/fcoe_transport.c index f5ed2d6cc70c..a27aa5149f5d 100644 --- a/drivers/scsi/fcoe/fcoe_transport.c +++ b/drivers/scsi/fcoe/fcoe_transport.c @@ -32,13 +32,13 @@ MODULE_AUTHOR("Open-FCoE.org"); MODULE_DESCRIPTION("FIP discovery protocol and FCoE transport for FCoE HBAs"); MODULE_LICENSE("GPL v2"); -static int fcoe_transport_create(const char *, struct kernel_param *); -static int fcoe_transport_destroy(const char *, struct kernel_param *); +static int fcoe_transport_create(const char *, const struct kernel_param *); +static int fcoe_transport_destroy(const char *, const struct kernel_param *); static int fcoe_transport_show(char *buffer, const struct kernel_param *kp); static struct fcoe_transport *fcoe_transport_lookup(struct net_device *device); static struct fcoe_transport *fcoe_netdev_map_lookup(struct net_device *device); -static int fcoe_transport_enable(const char *, struct kernel_param *); -static int fcoe_transport_disable(const char *, struct kernel_param *); +static int fcoe_transport_enable(const char *, const struct kernel_param *); +static int fcoe_transport_disable(const char *, const struct kernel_param *); static int libfcoe_device_notification(struct notifier_block *notifier, ulong event, void *ptr); @@ -865,7 +865,8 @@ EXPORT_SYMBOL(fcoe_ctlr_destroy_store); * * Returns: 0 for success */ -static int fcoe_transport_create(const char *buffer, struct kernel_param *kp) +static int fcoe_transport_create(const char *buffer, + const struct kernel_param *kp) { int rc = -ENODEV; struct net_device *netdev = NULL; @@ -930,7 +931,8 @@ out_nodev: * * Returns: 0 for success */ -static int fcoe_transport_destroy(const char *buffer, struct kernel_param *kp) +static int fcoe_transport_destroy(const char *buffer, + const struct kernel_param *kp) { int rc = -ENODEV; struct net_device *netdev = NULL; @@ -974,7 +976,8 @@ out_nodev: * * Returns: 0 for success */ -static int fcoe_transport_disable(const char *buffer, struct kernel_param *kp) +static int fcoe_transport_disable(const char *buffer, + const struct kernel_param *kp) { int rc = -ENODEV; struct net_device *netdev = NULL; @@ -1008,7 +1011,8 @@ out_nodev: * * Returns: 0 for success */ -static int fcoe_transport_enable(const char *buffer, struct kernel_param *kp) +static int fcoe_transport_enable(const char *buffer, + const struct kernel_param *kp) { int rc = -ENODEV; struct net_device *netdev = NULL; diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 556971c5f0b0..33a005c9bd65 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -105,7 +105,7 @@ _base_get_ioc_facts(struct MPT3SAS_ADAPTER *ioc); * */ static int -_scsih_set_fwfault_debug(const char *val, struct kernel_param *kp) +_scsih_set_fwfault_debug(const char *val, const struct kernel_param *kp) { int ret = param_set_int(val, kp); struct MPT3SAS_ADAPTER *ioc; diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 400c055167b0..ac6870a56401 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -281,7 +281,7 @@ struct _scsi_io_transfer { * Note: The logging levels are defined in mpt3sas_debug.h. */ static int -_scsih_set_debug_level(const char *val, struct kernel_param *kp) +_scsih_set_debug_level(const char *val, const struct kernel_param *kp) { int ret = param_set_int(val, kp); struct MPT3SAS_ADAPTER *ioc; diff --git a/drivers/staging/android/Kconfig b/drivers/staging/android/Kconfig index 71a50b99caff..29d891355f7a 100644 --- a/drivers/staging/android/Kconfig +++ b/drivers/staging/android/Kconfig @@ -14,6 +14,15 @@ config ASHMEM It is, in theory, a good memory allocator for low-memory devices, because it can discard shared memory units when under memory pressure. +config ANDROID_VSOC + tristate "Android Virtual SoC support" + default n + depends on PCI_MSI + ---help--- + This option adds support for the Virtual SoC driver needed to boot + a 'cuttlefish' Android image inside QEmu. The driver interacts with + a QEmu ivshmem device. If built as a module, it will be called vsoc. + source "drivers/staging/android/ion/Kconfig" endif # if ANDROID diff --git a/drivers/staging/android/Makefile b/drivers/staging/android/Makefile index 7cf1564a49a5..90e6154f11a4 100644 --- a/drivers/staging/android/Makefile +++ b/drivers/staging/android/Makefile @@ -3,3 +3,4 @@ ccflags-y += -I$(src) # needed for trace events obj-y += ion/ obj-$(CONFIG_ASHMEM) += ashmem.o +obj-$(CONFIG_ANDROID_VSOC) += vsoc.o diff --git a/drivers/staging/android/TODO b/drivers/staging/android/TODO index 5f14247392bf..ebd6ba3ae02e 100644 --- a/drivers/staging/android/TODO +++ b/drivers/staging/android/TODO @@ -12,5 +12,14 @@ ion/ - Split /dev/ion up into multiple nodes (e.g. /dev/ion/heap0) - Better test framework (integration with VGEM was suggested) +vsoc.c, uapi/vsoc_shm.h + - The current driver uses the same wait queue for all of the futexes in a + region. This will cause false wakeups in regions with a large number of + waiting threads. We should eventually use multiple queues and select the + queue based on the region. + - Add debugfs support for examining the permissions of regions. + - Remove VSOC_WAIT_FOR_INCOMING_INTERRUPT ioctl. This functionality has been + superseded by the futex and is there for legacy reasons. + Please send patches to Greg Kroah-Hartman <greg@kroah.com> and Cc: Arve Hjønnevåg <arve@android.com> and Riley Andrews <riandrews@android.com> diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c index 9481c0b23386..7b1c3843176a 100644 --- a/drivers/staging/android/ashmem.c +++ b/drivers/staging/android/ashmem.c @@ -434,22 +434,14 @@ static int ashmem_mmap(struct file *file, struct vm_area_struct *vma) } get_file(asma->file); - /* - * XXX - Reworked to use shmem_zero_setup() instead of - * shmem_set_file while we're in staging. -jstultz - */ - if (vma->vm_flags & VM_SHARED) { - ret = shmem_zero_setup(vma); - if (ret) { - fput(asma->file); - goto out; - } + if (vma->vm_flags & VM_SHARED) + shmem_set_file(vma, asma->file); + else { + if (vma->vm_file) + fput(vma->vm_file); + vma->vm_file = asma->file; } - if (vma->vm_file) - fput(vma->vm_file); - vma->vm_file = asma->file; - out: mutex_unlock(&ashmem_mutex); return ret; @@ -486,9 +478,9 @@ ashmem_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) loff_t start = range->pgstart * PAGE_SIZE; loff_t end = (range->pgend + 1) * PAGE_SIZE; - vfs_fallocate(range->asma->file, - FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, - start, end - start); + range->asma->file->f_op->fallocate(range->asma->file, + FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, + start, end - start); range->purged = ASHMEM_WAS_PURGED; lru_del(range); diff --git a/drivers/staging/android/uapi/vsoc_shm.h b/drivers/staging/android/uapi/vsoc_shm.h new file mode 100644 index 000000000000..741b1387c25b --- /dev/null +++ b/drivers/staging/android/uapi/vsoc_shm.h @@ -0,0 +1,303 @@ +/* + * Copyright (C) 2017 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#ifndef _UAPI_LINUX_VSOC_SHM_H +#define _UAPI_LINUX_VSOC_SHM_H + +#include <linux/types.h> + +/** + * A permission is a token that permits a receiver to read and/or write an area + * of memory within a Vsoc region. + * + * An fd_scoped permission grants both read and write access, and can be + * attached to a file description (see open(2)). + * Ownership of the area can then be shared by passing a file descriptor + * among processes. + * + * begin_offset and end_offset define the area of memory that is controlled by + * the permission. owner_offset points to a word, also in shared memory, that + * controls ownership of the area. + * + * ownership of the region expires when the associated file description is + * released. + * + * At most one permission can be attached to each file description. + * + * This is useful when implementing HALs like gralloc that scope and pass + * ownership of shared resources via file descriptors. + * + * The caller is responsibe for doing any fencing. + * + * The calling process will normally identify a currently free area of + * memory. It will construct a proposed fd_scoped_permission_arg structure: + * + * begin_offset and end_offset describe the area being claimed + * + * owner_offset points to the location in shared memory that indicates the + * owner of the area. + * + * owned_value is the value that will be stored in owner_offset iff the + * permission can be granted. It must be different than VSOC_REGION_FREE. + * + * Two fd_scoped_permission structures are compatible if they vary only by + * their owned_value fields. + * + * The driver ensures that, for any group of simultaneous callers proposing + * compatible fd_scoped_permissions, it will accept exactly one of the + * propopsals. The other callers will get a failure with errno of EAGAIN. + * + * A process receiving a file descriptor can identify the region being + * granted using the VSOC_GET_FD_SCOPED_PERMISSION ioctl. + */ +struct fd_scoped_permission { + __u32 begin_offset; + __u32 end_offset; + __u32 owner_offset; + __u32 owned_value; +}; + +/* + * This value represents a free area of memory. The driver expects to see this + * value at owner_offset when creating a permission otherwise it will not do it, + * and will write this value back once the permission is no longer needed. + */ +#define VSOC_REGION_FREE ((__u32)0) + +/** + * ioctl argument for VSOC_CREATE_FD_SCOPE_PERMISSION + */ +struct fd_scoped_permission_arg { + struct fd_scoped_permission perm; + __s32 managed_region_fd; +}; + +#define VSOC_NODE_FREE ((__u32)0) + +/* + * Describes a signal table in shared memory. Each non-zero entry in the + * table indicates that the receiver should signal the futex at the given + * offset. Offsets are relative to the region, not the shared memory window. + * + * interrupt_signalled_offset is used to reliably signal interrupts across the + * vmm boundary. There are two roles: transmitter and receiver. For example, + * in the host_to_guest_signal_table the host is the transmitter and the + * guest is the receiver. The protocol is as follows: + * + * 1. The transmitter should convert the offset of the futex to an offset + * in the signal table [0, (1 << num_nodes_lg2)) + * The transmitter can choose any appropriate hashing algorithm, including + * hash = futex_offset & ((1 << num_nodes_lg2) - 1) + * + * 3. The transmitter should atomically compare and swap futex_offset with 0 + * at hash. There are 3 possible outcomes + * a. The swap fails because the futex_offset is already in the table. + * The transmitter should stop. + * b. Some other offset is in the table. This is a hash collision. The + * transmitter should move to another table slot and try again. One + * possible algorithm: + * hash = (hash + 1) & ((1 << num_nodes_lg2) - 1) + * c. The swap worked. Continue below. + * + * 3. The transmitter atomically swaps 1 with the value at the + * interrupt_signalled_offset. There are two outcomes: + * a. The prior value was 1. In this case an interrupt has already been + * posted. The transmitter is done. + * b. The prior value was 0, indicating that the receiver may be sleeping. + * The transmitter will issue an interrupt. + * + * 4. On waking the receiver immediately exchanges a 0 with the + * interrupt_signalled_offset. If it receives a 0 then this a spurious + * interrupt. That may occasionally happen in the current protocol, but + * should be rare. + * + * 5. The receiver scans the signal table by atomicaly exchanging 0 at each + * location. If a non-zero offset is returned from the exchange the + * receiver wakes all sleepers at the given offset: + * futex((int*)(region_base + old_value), FUTEX_WAKE, MAX_INT); + * + * 6. The receiver thread then does a conditional wait, waking immediately + * if the value at interrupt_signalled_offset is non-zero. This catches cases + * here additional signals were posted while the table was being scanned. + * On the guest the wait is handled via the VSOC_WAIT_FOR_INCOMING_INTERRUPT + * ioctl. + */ +struct vsoc_signal_table_layout { + /* log_2(Number of signal table entries) */ + __u32 num_nodes_lg2; + /* + * Offset to the first signal table entry relative to the start of the + * region + */ + __u32 futex_uaddr_table_offset; + /* + * Offset to an atomic_t / atomic uint32_t. A non-zero value indicates + * that one or more offsets are currently posted in the table. + * semi-unique access to an entry in the table + */ + __u32 interrupt_signalled_offset; +}; + +#define VSOC_REGION_WHOLE ((__s32)0) +#define VSOC_DEVICE_NAME_SZ 16 + +/** + * Each HAL would (usually) talk to a single device region + * Mulitple entities care about these regions: + * - The ivshmem_server will populate the regions in shared memory + * - The guest kernel will read the region, create minor device nodes, and + * allow interested parties to register for FUTEX_WAKE events in the region + * - HALs will access via the minor device nodes published by the guest kernel + * - Host side processes will access the region via the ivshmem_server: + * 1. Pass name to ivshmem_server at a UNIX socket + * 2. ivshmemserver will reply with 2 fds: + * - host->guest doorbell fd + * - guest->host doorbell fd + * - fd for the shared memory region + * - region offset + * 3. Start a futex receiver thread on the doorbell fd pointed at the + * signal_nodes + */ +struct vsoc_device_region { + __u16 current_version; + __u16 min_compatible_version; + __u32 region_begin_offset; + __u32 region_end_offset; + __u32 offset_of_region_data; + struct vsoc_signal_table_layout guest_to_host_signal_table; + struct vsoc_signal_table_layout host_to_guest_signal_table; + /* Name of the device. Must always be terminated with a '\0', so + * the longest supported device name is 15 characters. + */ + char device_name[VSOC_DEVICE_NAME_SZ]; + /* There are two ways that permissions to access regions are handled: + * - When subdivided_by is VSOC_REGION_WHOLE, any process that can + * open the device node for the region gains complete access to it. + * - When subdivided is set processes that open the region cannot + * access it. Access to a sub-region must be established by invoking + * the VSOC_CREATE_FD_SCOPE_PERMISSION ioctl on the region + * referenced in subdivided_by, providing a fileinstance + * (represented by a fd) opened on this region. + */ + __u32 managed_by; +}; + +/* + * The vsoc layout descriptor. + * The first 4K should be reserved for the shm header and region descriptors. + * The regions should be page aligned. + */ + +struct vsoc_shm_layout_descriptor { + __u16 major_version; + __u16 minor_version; + + /* size of the shm. This may be redundant but nice to have */ + __u32 size; + + /* number of shared memory regions */ + __u32 region_count; + + /* The offset to the start of region descriptors */ + __u32 vsoc_region_desc_offset; +}; + +/* + * This specifies the current version that should be stored in + * vsoc_shm_layout_descriptor.major_version and + * vsoc_shm_layout_descriptor.minor_version. + * It should be updated only if the vsoc_device_region and + * vsoc_shm_layout_descriptor structures have changed. + * Versioning within each region is transferred + * via the min_compatible_version and current_version fields in + * vsoc_device_region. The driver does not consult these fields: they are left + * for the HALs and host processes and will change independently of the layout + * version. + */ +#define CURRENT_VSOC_LAYOUT_MAJOR_VERSION 2 +#define CURRENT_VSOC_LAYOUT_MINOR_VERSION 0 + +#define VSOC_CREATE_FD_SCOPED_PERMISSION \ + _IOW(0xF5, 0, struct fd_scoped_permission) +#define VSOC_GET_FD_SCOPED_PERMISSION _IOR(0xF5, 1, struct fd_scoped_permission) + +/* + * This is used to signal the host to scan the guest_to_host_signal_table + * for new futexes to wake. This sends an interrupt if one is not already + * in flight. + */ +#define VSOC_MAYBE_SEND_INTERRUPT_TO_HOST _IO(0xF5, 2) + +/* + * When this returns the guest will scan host_to_guest_signal_table to + * check for new futexes to wake. + */ +/* TODO(ghartman): Consider moving this to the bottom half */ +#define VSOC_WAIT_FOR_INCOMING_INTERRUPT _IO(0xF5, 3) + +/* + * Guest HALs will use this to retrieve the region description after + * opening their device node. + */ +#define VSOC_DESCRIBE_REGION _IOR(0xF5, 4, struct vsoc_device_region) + +/* + * Wake any threads that may be waiting for a host interrupt on this region. + * This is mostly used during shutdown. + */ +#define VSOC_SELF_INTERRUPT _IO(0xF5, 5) + +/* + * This is used to signal the host to scan the guest_to_host_signal_table + * for new futexes to wake. This sends an interrupt unconditionally. + */ +#define VSOC_SEND_INTERRUPT_TO_HOST _IO(0xF5, 6) + +enum wait_types { + VSOC_WAIT_UNDEFINED = 0, + VSOC_WAIT_IF_EQUAL = 1, + VSOC_WAIT_IF_EQUAL_TIMEOUT = 2 +}; + +/* + * Wait for a condition to be true + * + * Note, this is sized and aligned so the 32 bit and 64 bit layouts are + * identical. + */ +struct vsoc_cond_wait { + /* Input: Offset of the 32 bit word to check */ + __u32 offset; + /* Input: Value that will be compared with the offset */ + __u32 value; + /* Monotonic time to wake at in seconds */ + __u64 wake_time_sec; + /* Input: Monotonic time to wait in nanoseconds */ + __u32 wake_time_nsec; + /* Input: Type of wait */ + __u32 wait_type; + /* Output: Number of times the thread woke before returning. */ + __u32 wakes; + /* Ensure that we're 8-byte aligned and 8 byte length for 32/64 bit + * compatibility. + */ + __u32 reserved_1; +}; + +#define VSOC_COND_WAIT _IOWR(0xF5, 7, struct vsoc_cond_wait) + +/* Wake any local threads waiting at the offset given in arg */ +#define VSOC_COND_WAKE _IO(0xF5, 8) + +#endif /* _UAPI_LINUX_VSOC_SHM_H */ diff --git a/drivers/staging/android/vsoc.c b/drivers/staging/android/vsoc.c new file mode 100644 index 000000000000..954ed2c5d807 --- /dev/null +++ b/drivers/staging/android/vsoc.c @@ -0,0 +1,1165 @@ +/* + * drivers/android/staging/vsoc.c + * + * Android Virtual System on a Chip (VSoC) driver + * + * Copyright (C) 2017 Google, Inc. + * + * Author: ghartman@google.com + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * + * Based on drivers/char/kvm_ivshmem.c - driver for KVM Inter-VM shared memory + * Copyright 2009 Cam Macdonell <cam@cs.ualberta.ca> + * + * Based on cirrusfb.c and 8139cp.c: + * Copyright 1999-2001 Jeff Garzik + * Copyright 2001-2004 Jeff Garzik + */ + +#include <linux/dma-mapping.h> +#include <linux/freezer.h> +#include <linux/futex.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/pci.h> +#include <linux/proc_fs.h> +#include <linux/sched.h> +#include <linux/syscalls.h> +#include <linux/uaccess.h> +#include <linux/interrupt.h> +#include <linux/mutex.h> +#include <linux/cdev.h> +#include <linux/file.h> +#include "uapi/vsoc_shm.h" + +#define VSOC_DEV_NAME "vsoc" + +/* + * Description of the ivshmem-doorbell PCI device used by QEmu. These + * constants follow docs/specs/ivshmem-spec.txt, which can be found in + * the QEmu repository. This was last reconciled with the version that + * came out with 2.8 + */ + +/* + * These constants are determined KVM Inter-VM shared memory device + * register offsets + */ +enum { + INTR_MASK = 0x00, /* Interrupt Mask */ + INTR_STATUS = 0x04, /* Interrupt Status */ + IV_POSITION = 0x08, /* VM ID */ + DOORBELL = 0x0c, /* Doorbell */ +}; + +static const int REGISTER_BAR; /* Equal to 0 */ +static const int MAX_REGISTER_BAR_LEN = 0x100; +/* + * The MSI-x BAR is not used directly. + * + * static const int MSI_X_BAR = 1; + */ +static const int SHARED_MEMORY_BAR = 2; + +struct vsoc_region_data { + char name[VSOC_DEVICE_NAME_SZ + 1]; + wait_queue_head_t interrupt_wait_queue; + /* TODO(b/73664181): Use multiple futex wait queues */ + wait_queue_head_t futex_wait_queue; + /* Flag indicating that an interrupt has been signalled by the host. */ + atomic_t *incoming_signalled; + /* Flag indicating the guest has signalled the host. */ + atomic_t *outgoing_signalled; + bool irq_requested; + bool device_created; +}; + +struct vsoc_device { + /* Kernel virtual address of REGISTER_BAR. */ + void __iomem *regs; + /* Physical address of SHARED_MEMORY_BAR. */ + phys_addr_t shm_phys_start; + /* Kernel virtual address of SHARED_MEMORY_BAR. */ + void __iomem *kernel_mapped_shm; + /* Size of the entire shared memory window in bytes. */ + size_t shm_size; + /* + * Pointer to the virtual address of the shared memory layout structure. + * This is probably identical to kernel_mapped_shm, but saving this + * here saves a lot of annoying casts. + */ + struct vsoc_shm_layout_descriptor *layout; + /* + * Points to a table of region descriptors in the kernel's virtual + * address space. Calculated from + * vsoc_shm_layout_descriptor.vsoc_region_desc_offset + */ + struct vsoc_device_region *regions; + /* Head of a list of permissions that have been granted. */ + struct list_head permissions; + struct pci_dev *dev; + /* Per-region (and therefore per-interrupt) information. */ + struct vsoc_region_data *regions_data; + /* + * Table of msi-x entries. This has to be separated from struct + * vsoc_region_data because the kernel deals with them as an array. + */ + struct msix_entry *msix_entries; + /* Mutex that protectes the permission list */ + struct mutex mtx; + /* Major number assigned by the kernel */ + int major; + /* Character device assigned by the kernel */ + struct cdev cdev; + /* Device class assigned by the kernel */ + struct class *class; + /* + * Flags that indicate what we've initialized. These are used to do an + * orderly cleanup of the device. + */ + bool enabled_device; + bool requested_regions; + bool cdev_added; + bool class_added; + bool msix_enabled; +}; + +static struct vsoc_device vsoc_dev; + +/* + * TODO(ghartman): Add a /sys filesystem entry that summarizes the permissions. + */ + +struct fd_scoped_permission_node { + struct fd_scoped_permission permission; + struct list_head list; +}; + +struct vsoc_private_data { + struct fd_scoped_permission_node *fd_scoped_permission_node; +}; + +static long vsoc_ioctl(struct file *, unsigned int, unsigned long); +static int vsoc_mmap(struct file *, struct vm_area_struct *); +static int vsoc_open(struct inode *, struct file *); +static int vsoc_release(struct inode *, struct file *); +static ssize_t vsoc_read(struct file *, char __user *, size_t, loff_t *); +static ssize_t vsoc_write(struct file *, const char __user *, size_t, loff_t *); +static loff_t vsoc_lseek(struct file *filp, loff_t offset, int origin); +static int do_create_fd_scoped_permission( + struct vsoc_device_region *region_p, + struct fd_scoped_permission_node *np, + struct fd_scoped_permission_arg __user *arg); +static void do_destroy_fd_scoped_permission( + struct vsoc_device_region *owner_region_p, + struct fd_scoped_permission *perm); +static long do_vsoc_describe_region(struct file *, + struct vsoc_device_region __user *); +static ssize_t vsoc_get_area(struct file *filp, __u32 *perm_off); + +/** + * Validate arguments on entry points to the driver. + */ +inline int vsoc_validate_inode(struct inode *inode) +{ + if (iminor(inode) >= vsoc_dev.layout->region_count) { + dev_err(&vsoc_dev.dev->dev, + "describe_region: invalid region %d\n", iminor(inode)); + return -ENODEV; + } + return 0; +} + +inline int vsoc_validate_filep(struct file *filp) +{ + int ret = vsoc_validate_inode(file_inode(filp)); + + if (ret) + return ret; + if (!filp->private_data) { + dev_err(&vsoc_dev.dev->dev, + "No private data on fd, region %d\n", + iminor(file_inode(filp))); + return -EBADFD; + } + return 0; +} + +/* Converts from shared memory offset to virtual address */ +static inline void *shm_off_to_virtual_addr(__u32 offset) +{ + return (void __force *)vsoc_dev.kernel_mapped_shm + offset; +} + +/* Converts from shared memory offset to physical address */ +static inline phys_addr_t shm_off_to_phys_addr(__u32 offset) +{ + return vsoc_dev.shm_phys_start + offset; +} + +/** + * Convenience functions to obtain the region from the inode or file. + * Dangerous to call before validating the inode/file. + */ +static inline struct vsoc_device_region *vsoc_region_from_inode( + struct inode *inode) +{ + return &vsoc_dev.regions[iminor(inode)]; +} + +static inline struct vsoc_device_region *vsoc_region_from_filep( + struct file *inode) +{ + return vsoc_region_from_inode(file_inode(inode)); +} + +static inline uint32_t vsoc_device_region_size(struct vsoc_device_region *r) +{ + return r->region_end_offset - r->region_begin_offset; +} + +static const struct file_operations vsoc_ops = { + .owner = THIS_MODULE, + .open = vsoc_open, + .mmap = vsoc_mmap, + .read = vsoc_read, + .unlocked_ioctl = vsoc_ioctl, + .compat_ioctl = vsoc_ioctl, + .write = vsoc_write, + .llseek = vsoc_lseek, + .release = vsoc_release, +}; + +static struct pci_device_id vsoc_id_table[] = { + {0x1af4, 0x1110, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, + {0}, +}; + +MODULE_DEVICE_TABLE(pci, vsoc_id_table); + +static void vsoc_remove_device(struct pci_dev *pdev); +static int vsoc_probe_device(struct pci_dev *pdev, + const struct pci_device_id *ent); + +static struct pci_driver vsoc_pci_driver = { + .name = "vsoc", + .id_table = vsoc_id_table, + .probe = vsoc_probe_device, + .remove = vsoc_remove_device, +}; + +static int do_create_fd_scoped_permission( + struct vsoc_device_region *region_p, + struct fd_scoped_permission_node *np, + struct fd_scoped_permission_arg __user *arg) +{ + struct file *managed_filp; + s32 managed_fd; + atomic_t *owner_ptr = NULL; + struct vsoc_device_region *managed_region_p; + + if (copy_from_user(&np->permission, &arg->perm, sizeof(*np)) || + copy_from_user(&managed_fd, + &arg->managed_region_fd, sizeof(managed_fd))) { + return -EFAULT; + } + managed_filp = fdget(managed_fd).file; + /* Check that it's a valid fd, */ + if (!managed_filp || vsoc_validate_filep(managed_filp)) + return -EPERM; + /* EEXIST if the given fd already has a permission. */ + if (((struct vsoc_private_data *)managed_filp->private_data)-> + fd_scoped_permission_node) + return -EEXIST; + managed_region_p = vsoc_region_from_filep(managed_filp); + /* Check that the provided region is managed by this one */ + if (&vsoc_dev.regions[managed_region_p->managed_by] != region_p) + return -EPERM; + /* The area must be well formed and have non-zero size */ + if (np->permission.begin_offset >= np->permission.end_offset) + return -EINVAL; + /* The area must fit in the memory window */ + if (np->permission.end_offset > + vsoc_device_region_size(managed_region_p)) + return -ERANGE; + /* The area must be in the region data section */ + if (np->permission.begin_offset < + managed_region_p->offset_of_region_data) + return -ERANGE; + /* The area must be page aligned */ + if (!PAGE_ALIGNED(np->permission.begin_offset) || + !PAGE_ALIGNED(np->permission.end_offset)) + return -EINVAL; + /* Owner offset must be naturally aligned in the window */ + if (np->permission.owner_offset & + (sizeof(np->permission.owner_offset) - 1)) + return -EINVAL; + /* The owner flag must reside in the owner memory */ + if (np->permission.owner_offset + sizeof(np->permission.owner_offset) > + vsoc_device_region_size(region_p)) + return -ERANGE; + /* The owner flag must reside in the data section */ + if (np->permission.owner_offset < region_p->offset_of_region_data) + return -EINVAL; + /* The owner value must change to claim the memory */ + if (np->permission.owned_value == VSOC_REGION_FREE) + return -EINVAL; + owner_ptr = + (atomic_t *)shm_off_to_virtual_addr(region_p->region_begin_offset + + np->permission.owner_offset); + /* We've already verified that this is in the shared memory window, so + * it should be safe to write to this address. + */ + if (atomic_cmpxchg(owner_ptr, + VSOC_REGION_FREE, + np->permission.owned_value) != VSOC_REGION_FREE) { + return -EBUSY; + } + ((struct vsoc_private_data *)managed_filp->private_data)-> + fd_scoped_permission_node = np; + /* The file offset needs to be adjusted if the calling + * process did any read/write operations on the fd + * before creating the permission. + */ + if (managed_filp->f_pos) { + if (managed_filp->f_pos > np->permission.end_offset) { + /* If the offset is beyond the permission end, set it + * to the end. + */ + managed_filp->f_pos = np->permission.end_offset; + } else { + /* If the offset is within the permission interval + * keep it there otherwise reset it to zero. + */ + if (managed_filp->f_pos < np->permission.begin_offset) { + managed_filp->f_pos = 0; + } else { + managed_filp->f_pos -= + np->permission.begin_offset; + } + } + } + return 0; +} + +static void do_destroy_fd_scoped_permission_node( + struct vsoc_device_region *owner_region_p, + struct fd_scoped_permission_node *node) +{ + if (node) { + do_destroy_fd_scoped_permission(owner_region_p, + &node->permission); + mutex_lock(&vsoc_dev.mtx); + list_del(&node->list); + mutex_unlock(&vsoc_dev.mtx); + kfree(node); + } +} + +static void do_destroy_fd_scoped_permission( + struct vsoc_device_region *owner_region_p, + struct fd_scoped_permission *perm) +{ + atomic_t *owner_ptr = NULL; + int prev = 0; + + if (!perm) + return; + owner_ptr = (atomic_t *)shm_off_to_virtual_addr( + owner_region_p->region_begin_offset + perm->owner_offset); + prev = atomic_xchg(owner_ptr, VSOC_REGION_FREE); + if (prev != perm->owned_value) + dev_err(&vsoc_dev.dev->dev, + "%x-%x: owner (%s) %x: expected to be %x was %x", + perm->begin_offset, perm->end_offset, + owner_region_p->device_name, perm->owner_offset, + perm->owned_value, prev); +} + +static long do_vsoc_describe_region(struct file *filp, + struct vsoc_device_region __user *dest) +{ + struct vsoc_device_region *region_p; + int retval = vsoc_validate_filep(filp); + + if (retval) + return retval; + region_p = vsoc_region_from_filep(filp); + if (copy_to_user(dest, region_p, sizeof(*region_p))) + return -EFAULT; + return 0; +} + +/** + * Implements the inner logic of cond_wait. Copies to and from userspace are + * done in the helper function below. + */ +static int handle_vsoc_cond_wait(struct file *filp, struct vsoc_cond_wait *arg) +{ + DEFINE_WAIT(wait); + u32 region_number = iminor(file_inode(filp)); + struct vsoc_region_data *data = vsoc_dev.regions_data + region_number; + struct hrtimer_sleeper timeout, *to = NULL; + int ret = 0; + struct vsoc_device_region *region_p = vsoc_region_from_filep(filp); + atomic_t *address = NULL; + struct timespec ts; + + /* Ensure that the offset is aligned */ + if (arg->offset & (sizeof(uint32_t) - 1)) + return -EADDRNOTAVAIL; + /* Ensure that the offset is within shared memory */ + if (((uint64_t)arg->offset) + region_p->region_begin_offset + + sizeof(uint32_t) > region_p->region_end_offset) + return -E2BIG; + address = shm_off_to_virtual_addr(region_p->region_begin_offset + + arg->offset); + + /* Ensure that the type of wait is valid */ + switch (arg->wait_type) { + case VSOC_WAIT_IF_EQUAL: + break; + case VSOC_WAIT_IF_EQUAL_TIMEOUT: + to = &timeout; + break; + default: + return -EINVAL; + } + + if (to) { + /* Copy the user-supplied timesec into the kernel structure. + * We do things this way to flatten differences between 32 bit + * and 64 bit timespecs. + */ + ts.tv_sec = arg->wake_time_sec; + ts.tv_nsec = arg->wake_time_nsec; + + if (!timespec_valid(&ts)) + return -EINVAL; + hrtimer_init_on_stack(&to->timer, CLOCK_MONOTONIC, + HRTIMER_MODE_ABS); + hrtimer_set_expires_range_ns(&to->timer, timespec_to_ktime(ts), + current->timer_slack_ns); + + hrtimer_init_sleeper(to, current); + } + + while (1) { + prepare_to_wait(&data->futex_wait_queue, &wait, + TASK_INTERRUPTIBLE); + /* + * Check the sentinel value after prepare_to_wait. If the value + * changes after this check the writer will call signal, + * changing the task state from INTERRUPTIBLE to RUNNING. That + * will ensure that schedule() will eventually schedule this + * task. + */ + if (atomic_read(address) != arg->value) { + ret = 0; + break; + } + if (to) { + hrtimer_start_expires(&to->timer, HRTIMER_MODE_ABS); + if (likely(to->task)) + freezable_schedule(); + hrtimer_cancel(&to->timer); + if (!to->task) { + ret = -ETIMEDOUT; + break; + } + } else { + freezable_schedule(); + } + /* Count the number of times that we woke up. This is useful + * for unit testing. + */ + ++arg->wakes; + if (signal_pending(current)) { + ret = -EINTR; + break; + } + } + finish_wait(&data->futex_wait_queue, &wait); + if (to) + destroy_hrtimer_on_stack(&to->timer); + return ret; +} + +/** + * Handles the details of copying from/to userspace to ensure that the copies + * happen on all of the return paths of cond_wait. + */ +static int do_vsoc_cond_wait(struct file *filp, + struct vsoc_cond_wait __user *untrusted_in) +{ + struct vsoc_cond_wait arg; + int rval = 0; + + if (copy_from_user(&arg, untrusted_in, sizeof(arg))) + return -EFAULT; + /* wakes is an out parameter. Initialize it to something sensible. */ + arg.wakes = 0; + rval = handle_vsoc_cond_wait(filp, &arg); + if (copy_to_user(untrusted_in, &arg, sizeof(arg))) + return -EFAULT; + return rval; +} + +static int do_vsoc_cond_wake(struct file *filp, uint32_t offset) +{ + struct vsoc_device_region *region_p = vsoc_region_from_filep(filp); + u32 region_number = iminor(file_inode(filp)); + struct vsoc_region_data *data = vsoc_dev.regions_data + region_number; + /* Ensure that the offset is aligned */ + if (offset & (sizeof(uint32_t) - 1)) + return -EADDRNOTAVAIL; + /* Ensure that the offset is within shared memory */ + if (((uint64_t)offset) + region_p->region_begin_offset + + sizeof(uint32_t) > region_p->region_end_offset) + return -E2BIG; + /* + * TODO(b/73664181): Use multiple futex wait queues. + * We need to wake every sleeper when the condition changes. Typically + * only a single thread will be waiting on the condition, but there + * are exceptions. The worst case is about 10 threads. + */ + wake_up_interruptible_all(&data->futex_wait_queue); + return 0; +} + +static long vsoc_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) +{ + int rv = 0; + struct vsoc_device_region *region_p; + u32 reg_num; + struct vsoc_region_data *reg_data; + int retval = vsoc_validate_filep(filp); + + if (retval) + return retval; + region_p = vsoc_region_from_filep(filp); + reg_num = iminor(file_inode(filp)); + reg_data = vsoc_dev.regions_data + reg_num; + switch (cmd) { + case VSOC_CREATE_FD_SCOPED_PERMISSION: + { + struct fd_scoped_permission_node *node = NULL; + + node = kzalloc(sizeof(*node), GFP_KERNEL); + /* We can't allocate memory for the permission */ + if (!node) + return -ENOMEM; + INIT_LIST_HEAD(&node->list); + rv = do_create_fd_scoped_permission( + region_p, + node, + (struct fd_scoped_permission_arg __user *)arg); + if (!rv) { + mutex_lock(&vsoc_dev.mtx); + list_add(&node->list, &vsoc_dev.permissions); + mutex_unlock(&vsoc_dev.mtx); + } else { + kfree(node); + return rv; + } + } + break; + + case VSOC_GET_FD_SCOPED_PERMISSION: + { + struct fd_scoped_permission_node *node = + ((struct vsoc_private_data *)filp->private_data)-> + fd_scoped_permission_node; + if (!node) + return -ENOENT; + if (copy_to_user + ((struct fd_scoped_permission __user *)arg, + &node->permission, sizeof(node->permission))) + return -EFAULT; + } + break; + + case VSOC_MAYBE_SEND_INTERRUPT_TO_HOST: + if (!atomic_xchg( + reg_data->outgoing_signalled, + 1)) { + writel(reg_num, vsoc_dev.regs + DOORBELL); + return 0; + } else { + return -EBUSY; + } + break; + + case VSOC_SEND_INTERRUPT_TO_HOST: + writel(reg_num, vsoc_dev.regs + DOORBELL); + return 0; + + case VSOC_WAIT_FOR_INCOMING_INTERRUPT: + wait_event_interruptible( + reg_data->interrupt_wait_queue, + (atomic_read(reg_data->incoming_signalled) != 0)); + break; + + case VSOC_DESCRIBE_REGION: + return do_vsoc_describe_region( + filp, + (struct vsoc_device_region __user *)arg); + + case VSOC_SELF_INTERRUPT: + atomic_set(reg_data->incoming_signalled, 1); + wake_up_interruptible(®_data->interrupt_wait_queue); + break; + + case VSOC_COND_WAIT: + return do_vsoc_cond_wait(filp, + (struct vsoc_cond_wait __user *)arg); + case VSOC_COND_WAKE: + return do_vsoc_cond_wake(filp, arg); + + default: + return -EINVAL; + } + return 0; +} + +static ssize_t vsoc_read(struct file *filp, char __user *buffer, size_t len, + loff_t *poffset) +{ + __u32 area_off; + const void *area_p; + ssize_t area_len; + int retval = vsoc_validate_filep(filp); + + if (retval) + return retval; + area_len = vsoc_get_area(filp, &area_off); + area_p = shm_off_to_virtual_addr(area_off); + area_p += *poffset; + area_len -= *poffset; + if (area_len <= 0) + return 0; + if (area_len < len) + len = area_len; + if (copy_to_user(buffer, area_p, len)) + return -EFAULT; + *poffset += len; + return len; +} + +static loff_t vsoc_lseek(struct file *filp, loff_t offset, int origin) +{ + ssize_t area_len = 0; + int retval = vsoc_validate_filep(filp); + + if (retval) + return retval; + area_len = vsoc_get_area(filp, NULL); + switch (origin) { + case SEEK_SET: + break; + + case SEEK_CUR: + if (offset > 0 && offset + filp->f_pos < 0) + return -EOVERFLOW; + offset += filp->f_pos; + break; + + case SEEK_END: + if (offset > 0 && offset + area_len < 0) + return -EOVERFLOW; + offset += area_len; + break; + + case SEEK_DATA: + if (offset >= area_len) + return -EINVAL; + if (offset < 0) + offset = 0; + break; + + case SEEK_HOLE: + /* Next hole is always the end of the region, unless offset is + * beyond that + */ + if (offset < area_len) + offset = area_len; + break; + + default: + return -EINVAL; + } + + if (offset < 0 || offset > area_len) + return -EINVAL; + filp->f_pos = offset; + + return offset; +} + +static ssize_t vsoc_write(struct file *filp, const char __user *buffer, + size_t len, loff_t *poffset) +{ + __u32 area_off; + void *area_p; + ssize_t area_len; + int retval = vsoc_validate_filep(filp); + + if (retval) + return retval; + area_len = vsoc_get_area(filp, &area_off); + area_p = shm_off_to_virtual_addr(area_off); + area_p += *poffset; + area_len -= *poffset; + if (area_len <= 0) + return 0; + if (area_len < len) + len = area_len; + if (copy_from_user(area_p, buffer, len)) + return -EFAULT; + *poffset += len; + return len; +} + +static irqreturn_t vsoc_interrupt(int irq, void *region_data_v) +{ + struct vsoc_region_data *region_data = + (struct vsoc_region_data *)region_data_v; + int reg_num = region_data - vsoc_dev.regions_data; + + if (unlikely(!region_data)) + return IRQ_NONE; + + if (unlikely(reg_num < 0 || + reg_num >= vsoc_dev.layout->region_count)) { + dev_err(&vsoc_dev.dev->dev, + "invalid irq @%p reg_num=0x%04x\n", + region_data, reg_num); + return IRQ_NONE; + } + if (unlikely(vsoc_dev.regions_data + reg_num != region_data)) { + dev_err(&vsoc_dev.dev->dev, + "irq not aligned @%p reg_num=0x%04x\n", + region_data, reg_num); + return IRQ_NONE; + } + wake_up_interruptible(®ion_data->interrupt_wait_queue); + return IRQ_HANDLED; +} + +static int vsoc_probe_device(struct pci_dev *pdev, + const struct pci_device_id *ent) +{ + int result; + int i; + resource_size_t reg_size; + dev_t devt; + + vsoc_dev.dev = pdev; + result = pci_enable_device(pdev); + if (result) { + dev_err(&pdev->dev, + "pci_enable_device failed %s: error %d\n", + pci_name(pdev), result); + return result; + } + vsoc_dev.enabled_device = true; + result = pci_request_regions(pdev, "vsoc"); + if (result < 0) { + dev_err(&pdev->dev, "pci_request_regions failed\n"); + vsoc_remove_device(pdev); + return -EBUSY; + } + vsoc_dev.requested_regions = true; + /* Set up the control registers in BAR 0 */ + reg_size = pci_resource_len(pdev, REGISTER_BAR); + if (reg_size > MAX_REGISTER_BAR_LEN) + vsoc_dev.regs = + pci_iomap(pdev, REGISTER_BAR, MAX_REGISTER_BAR_LEN); + else + vsoc_dev.regs = pci_iomap(pdev, REGISTER_BAR, reg_size); + + if (!vsoc_dev.regs) { + dev_err(&pdev->dev, + "cannot map registers of size %zu\n", + (size_t)reg_size); + vsoc_remove_device(pdev); + return -EBUSY; + } + + /* Map the shared memory in BAR 2 */ + vsoc_dev.shm_phys_start = pci_resource_start(pdev, SHARED_MEMORY_BAR); + vsoc_dev.shm_size = pci_resource_len(pdev, SHARED_MEMORY_BAR); + + dev_info(&pdev->dev, "shared memory @ DMA %pa size=0x%zx\n", + &vsoc_dev.shm_phys_start, vsoc_dev.shm_size); + vsoc_dev.kernel_mapped_shm = pci_iomap_wc(pdev, SHARED_MEMORY_BAR, 0); + if (!vsoc_dev.kernel_mapped_shm) { + dev_err(&vsoc_dev.dev->dev, "cannot iomap region\n"); + vsoc_remove_device(pdev); + return -EBUSY; + } + + vsoc_dev.layout = (struct vsoc_shm_layout_descriptor __force *) + vsoc_dev.kernel_mapped_shm; + dev_info(&pdev->dev, "major_version: %d\n", + vsoc_dev.layout->major_version); + dev_info(&pdev->dev, "minor_version: %d\n", + vsoc_dev.layout->minor_version); + dev_info(&pdev->dev, "size: 0x%x\n", vsoc_dev.layout->size); + dev_info(&pdev->dev, "regions: %d\n", vsoc_dev.layout->region_count); + if (vsoc_dev.layout->major_version != + CURRENT_VSOC_LAYOUT_MAJOR_VERSION) { + dev_err(&vsoc_dev.dev->dev, + "driver supports only major_version %d\n", + CURRENT_VSOC_LAYOUT_MAJOR_VERSION); + vsoc_remove_device(pdev); + return -EBUSY; + } + result = alloc_chrdev_region(&devt, 0, vsoc_dev.layout->region_count, + VSOC_DEV_NAME); + if (result) { + dev_err(&vsoc_dev.dev->dev, "alloc_chrdev_region failed\n"); + vsoc_remove_device(pdev); + return -EBUSY; + } + vsoc_dev.major = MAJOR(devt); + cdev_init(&vsoc_dev.cdev, &vsoc_ops); + vsoc_dev.cdev.owner = THIS_MODULE; + result = cdev_add(&vsoc_dev.cdev, devt, vsoc_dev.layout->region_count); + if (result) { + dev_err(&vsoc_dev.dev->dev, "cdev_add error\n"); + vsoc_remove_device(pdev); + return -EBUSY; + } + vsoc_dev.cdev_added = true; + vsoc_dev.class = class_create(THIS_MODULE, VSOC_DEV_NAME); + if (IS_ERR(vsoc_dev.class)) { + dev_err(&vsoc_dev.dev->dev, "class_create failed\n"); + vsoc_remove_device(pdev); + return PTR_ERR(vsoc_dev.class); + } + vsoc_dev.class_added = true; + vsoc_dev.regions = (struct vsoc_device_region __force *) + ((void *)vsoc_dev.layout + + vsoc_dev.layout->vsoc_region_desc_offset); + vsoc_dev.msix_entries = kcalloc( + vsoc_dev.layout->region_count, + sizeof(vsoc_dev.msix_entries[0]), GFP_KERNEL); + if (!vsoc_dev.msix_entries) { + dev_err(&vsoc_dev.dev->dev, + "unable to allocate msix_entries\n"); + vsoc_remove_device(pdev); + return -ENOSPC; + } + vsoc_dev.regions_data = kcalloc( + vsoc_dev.layout->region_count, + sizeof(vsoc_dev.regions_data[0]), GFP_KERNEL); + if (!vsoc_dev.regions_data) { + dev_err(&vsoc_dev.dev->dev, + "unable to allocate regions' data\n"); + vsoc_remove_device(pdev); + return -ENOSPC; + } + for (i = 0; i < vsoc_dev.layout->region_count; ++i) + vsoc_dev.msix_entries[i].entry = i; + + result = pci_enable_msix_exact(vsoc_dev.dev, vsoc_dev.msix_entries, + vsoc_dev.layout->region_count); + if (result) { + dev_info(&pdev->dev, "pci_enable_msix failed: %d\n", result); + vsoc_remove_device(pdev); + return -ENOSPC; + } + /* Check that all regions are well formed */ + for (i = 0; i < vsoc_dev.layout->region_count; ++i) { + const struct vsoc_device_region *region = vsoc_dev.regions + i; + + if (!PAGE_ALIGNED(region->region_begin_offset) || + !PAGE_ALIGNED(region->region_end_offset)) { + dev_err(&vsoc_dev.dev->dev, + "region %d not aligned (%x:%x)", i, + region->region_begin_offset, + region->region_end_offset); + vsoc_remove_device(pdev); + return -EFAULT; + } + if (region->region_begin_offset >= region->region_end_offset || + region->region_end_offset > vsoc_dev.shm_size) { + dev_err(&vsoc_dev.dev->dev, + "region %d offsets are wrong: %x %x %zx", + i, region->region_begin_offset, + region->region_end_offset, vsoc_dev.shm_size); + vsoc_remove_device(pdev); + return -EFAULT; + } + if (region->managed_by >= vsoc_dev.layout->region_count) { + dev_err(&vsoc_dev.dev->dev, + "region %d has invalid owner: %u", + i, region->managed_by); + vsoc_remove_device(pdev); + return -EFAULT; + } + } + vsoc_dev.msix_enabled = true; + for (i = 0; i < vsoc_dev.layout->region_count; ++i) { + const struct vsoc_device_region *region = vsoc_dev.regions + i; + size_t name_sz = sizeof(vsoc_dev.regions_data[i].name) - 1; + const struct vsoc_signal_table_layout *h_to_g_signal_table = + ®ion->host_to_guest_signal_table; + const struct vsoc_signal_table_layout *g_to_h_signal_table = + ®ion->guest_to_host_signal_table; + + vsoc_dev.regions_data[i].name[name_sz] = '\0'; + memcpy(vsoc_dev.regions_data[i].name, region->device_name, + name_sz); + dev_info(&pdev->dev, "region %d name=%s\n", + i, vsoc_dev.regions_data[i].name); + init_waitqueue_head( + &vsoc_dev.regions_data[i].interrupt_wait_queue); + init_waitqueue_head(&vsoc_dev.regions_data[i].futex_wait_queue); + vsoc_dev.regions_data[i].incoming_signalled = + shm_off_to_virtual_addr(region->region_begin_offset) + + h_to_g_signal_table->interrupt_signalled_offset; + vsoc_dev.regions_data[i].outgoing_signalled = + shm_off_to_virtual_addr(region->region_begin_offset) + + g_to_h_signal_table->interrupt_signalled_offset; + result = request_irq( + vsoc_dev.msix_entries[i].vector, + vsoc_interrupt, 0, + vsoc_dev.regions_data[i].name, + vsoc_dev.regions_data + i); + if (result) { + dev_info(&pdev->dev, + "request_irq failed irq=%d vector=%d\n", + i, vsoc_dev.msix_entries[i].vector); + vsoc_remove_device(pdev); + return -ENOSPC; + } + vsoc_dev.regions_data[i].irq_requested = true; + if (!device_create(vsoc_dev.class, NULL, + MKDEV(vsoc_dev.major, i), + NULL, vsoc_dev.regions_data[i].name)) { + dev_err(&vsoc_dev.dev->dev, "device_create failed\n"); + vsoc_remove_device(pdev); + return -EBUSY; + } + vsoc_dev.regions_data[i].device_created = true; + } + return 0; +} + +/* + * This should undo all of the allocations in the probe function in reverse + * order. + * + * Notes: + * + * The device may have been partially initialized, so double check + * that the allocations happened. + * + * This function may be called multiple times, so mark resources as freed + * as they are deallocated. + */ +static void vsoc_remove_device(struct pci_dev *pdev) +{ + int i; + /* + * pdev is the first thing to be set on probe and the last thing + * to be cleared here. If it's NULL then there is no cleanup. + */ + if (!pdev || !vsoc_dev.dev) + return; + dev_info(&pdev->dev, "remove_device\n"); + if (vsoc_dev.regions_data) { + for (i = 0; i < vsoc_dev.layout->region_count; ++i) { + if (vsoc_dev.regions_data[i].device_created) { + device_destroy(vsoc_dev.class, + MKDEV(vsoc_dev.major, i)); + vsoc_dev.regions_data[i].device_created = false; + } + if (vsoc_dev.regions_data[i].irq_requested) + free_irq(vsoc_dev.msix_entries[i].vector, NULL); + vsoc_dev.regions_data[i].irq_requested = false; + } + kfree(vsoc_dev.regions_data); + vsoc_dev.regions_data = NULL; + } + if (vsoc_dev.msix_enabled) { + pci_disable_msix(pdev); + vsoc_dev.msix_enabled = false; + } + kfree(vsoc_dev.msix_entries); + vsoc_dev.msix_entries = NULL; + vsoc_dev.regions = NULL; + if (vsoc_dev.class_added) { + class_destroy(vsoc_dev.class); + vsoc_dev.class_added = false; + } + if (vsoc_dev.cdev_added) { + cdev_del(&vsoc_dev.cdev); + vsoc_dev.cdev_added = false; + } + if (vsoc_dev.major && vsoc_dev.layout) { + unregister_chrdev_region(MKDEV(vsoc_dev.major, 0), + vsoc_dev.layout->region_count); + vsoc_dev.major = 0; + } + vsoc_dev.layout = NULL; + if (vsoc_dev.kernel_mapped_shm) { + pci_iounmap(pdev, vsoc_dev.kernel_mapped_shm); + vsoc_dev.kernel_mapped_shm = NULL; + } + if (vsoc_dev.regs) { + pci_iounmap(pdev, vsoc_dev.regs); + vsoc_dev.regs = NULL; + } + if (vsoc_dev.requested_regions) { + pci_release_regions(pdev); + vsoc_dev.requested_regions = false; + } + if (vsoc_dev.enabled_device) { + pci_disable_device(pdev); + vsoc_dev.enabled_device = false; + } + /* Do this last: it indicates that the device is not initialized. */ + vsoc_dev.dev = NULL; +} + +static void __exit vsoc_cleanup_module(void) +{ + vsoc_remove_device(vsoc_dev.dev); + pci_unregister_driver(&vsoc_pci_driver); +} + +static int __init vsoc_init_module(void) +{ + int err = -ENOMEM; + + INIT_LIST_HEAD(&vsoc_dev.permissions); + mutex_init(&vsoc_dev.mtx); + + err = pci_register_driver(&vsoc_pci_driver); + if (err < 0) + return err; + return 0; +} + +static int vsoc_open(struct inode *inode, struct file *filp) +{ + /* Can't use vsoc_validate_filep because filp is still incomplete */ + int ret = vsoc_validate_inode(inode); + + if (ret) + return ret; + filp->private_data = + kzalloc(sizeof(struct vsoc_private_data), GFP_KERNEL); + if (!filp->private_data) + return -ENOMEM; + return 0; +} + +static int vsoc_release(struct inode *inode, struct file *filp) +{ + struct vsoc_private_data *private_data = NULL; + struct fd_scoped_permission_node *node = NULL; + struct vsoc_device_region *owner_region_p = NULL; + int retval = vsoc_validate_filep(filp); + + if (retval) + return retval; + private_data = (struct vsoc_private_data *)filp->private_data; + if (!private_data) + return 0; + + node = private_data->fd_scoped_permission_node; + if (node) { + owner_region_p = vsoc_region_from_inode(inode); + if (owner_region_p->managed_by != VSOC_REGION_WHOLE) { + owner_region_p = + &vsoc_dev.regions[owner_region_p->managed_by]; + } + do_destroy_fd_scoped_permission_node(owner_region_p, node); + private_data->fd_scoped_permission_node = NULL; + } + kfree(private_data); + filp->private_data = NULL; + + return 0; +} + +/* + * Returns the device relative offset and length of the area specified by the + * fd scoped permission. If there is no fd scoped permission set, a default + * permission covering the entire region is assumed, unless the region is owned + * by another one, in which case the default is a permission with zero size. + */ +static ssize_t vsoc_get_area(struct file *filp, __u32 *area_offset) +{ + __u32 off = 0; + ssize_t length = 0; + struct vsoc_device_region *region_p; + struct fd_scoped_permission *perm; + + region_p = vsoc_region_from_filep(filp); + off = region_p->region_begin_offset; + perm = &((struct vsoc_private_data *)filp->private_data)-> + fd_scoped_permission_node->permission; + if (perm) { + off += perm->begin_offset; + length = perm->end_offset - perm->begin_offset; + } else if (region_p->managed_by == VSOC_REGION_WHOLE) { + /* No permission set and the regions is not owned by another, + * default to full region access. + */ + length = vsoc_device_region_size(region_p); + } else { + /* return zero length, access is denied. */ + length = 0; + } + if (area_offset) + *area_offset = off; + return length; +} + +static int vsoc_mmap(struct file *filp, struct vm_area_struct *vma) +{ + unsigned long len = vma->vm_end - vma->vm_start; + __u32 area_off; + phys_addr_t mem_off; + ssize_t area_len; + int retval = vsoc_validate_filep(filp); + + if (retval) + return retval; + area_len = vsoc_get_area(filp, &area_off); + /* Add the requested offset */ + area_off += (vma->vm_pgoff << PAGE_SHIFT); + area_len -= (vma->vm_pgoff << PAGE_SHIFT); + if (area_len < len) + return -EINVAL; + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + mem_off = shm_off_to_phys_addr(area_off); + if (io_remap_pfn_range(vma, vma->vm_start, mem_off >> PAGE_SHIFT, + len, vma->vm_page_prot)) + return -EAGAIN; + return 0; +} + +module_init(vsoc_init_module); +module_exit(vsoc_cleanup_module); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Greg Hartman <ghartman@google.com>"); +MODULE_DESCRIPTION("VSoC interpretation of QEmu's ivshmem device"); +MODULE_VERSION("1.0"); diff --git a/drivers/staging/goldfish/Kconfig b/drivers/staging/goldfish/Kconfig index 4e094602437c..d293bbc22c79 100644 --- a/drivers/staging/goldfish/Kconfig +++ b/drivers/staging/goldfish/Kconfig @@ -4,6 +4,14 @@ config GOLDFISH_AUDIO ---help--- Emulated audio channel for the Goldfish Android Virtual Device +config GOLDFISH_SYNC + tristate "Goldfish AVD Sync Driver" + depends on GOLDFISH + depends on SW_SYNC + depends on SYNC_FILE + ---help--- + Emulated sync fences for the Goldfish Android Virtual Device + config MTD_GOLDFISH_NAND tristate "Goldfish NAND device" depends on GOLDFISH diff --git a/drivers/staging/goldfish/Makefile b/drivers/staging/goldfish/Makefile index dec34ad58162..3313fce4e940 100644 --- a/drivers/staging/goldfish/Makefile +++ b/drivers/staging/goldfish/Makefile @@ -4,3 +4,9 @@ obj-$(CONFIG_GOLDFISH_AUDIO) += goldfish_audio.o obj-$(CONFIG_MTD_GOLDFISH_NAND) += goldfish_nand.o + +# and sync + +ccflags-y := -Idrivers/staging/android +goldfish_sync-objs := goldfish_sync_timeline_fence.o goldfish_sync_timeline.o +obj-$(CONFIG_GOLDFISH_SYNC) += goldfish_sync.o diff --git a/drivers/staging/goldfish/goldfish_audio.c b/drivers/staging/goldfish/goldfish_audio.c index bd559956f199..0bb0ee2e691f 100644 --- a/drivers/staging/goldfish/goldfish_audio.c +++ b/drivers/staging/goldfish/goldfish_audio.c @@ -28,6 +28,7 @@ #include <linux/uaccess.h> #include <linux/slab.h> #include <linux/goldfish.h> +#include <linux/acpi.h> MODULE_AUTHOR("Google, Inc."); MODULE_DESCRIPTION("Android QEMU Audio Driver"); @@ -116,6 +117,7 @@ static ssize_t goldfish_audio_read(struct file *fp, char __user *buf, size_t count, loff_t *pos) { struct goldfish_audio *data = fp->private_data; + unsigned long irq_flags; int length; int result = 0; @@ -129,6 +131,10 @@ static ssize_t goldfish_audio_read(struct file *fp, char __user *buf, wait_event_interruptible(data->wait, data->buffer_status & AUDIO_INT_READ_BUFFER_FULL); + spin_lock_irqsave(&data->lock, irq_flags); + data->buffer_status &= ~AUDIO_INT_READ_BUFFER_FULL; + spin_unlock_irqrestore(&data->lock, irq_flags); + length = AUDIO_READ(data, AUDIO_READ_BUFFER_AVAILABLE); /* copy data to user space */ @@ -351,12 +357,19 @@ static const struct of_device_id goldfish_audio_of_match[] = { }; MODULE_DEVICE_TABLE(of, goldfish_audio_of_match); +static const struct acpi_device_id goldfish_audio_acpi_match[] = { + { "GFSH0005", 0 }, + { }, +}; +MODULE_DEVICE_TABLE(acpi, goldfish_audio_acpi_match); + static struct platform_driver goldfish_audio_driver = { .probe = goldfish_audio_probe, .remove = goldfish_audio_remove, .driver = { .name = "goldfish_audio", .of_match_table = goldfish_audio_of_match, + .acpi_match_table = ACPI_PTR(goldfish_audio_acpi_match), } }; diff --git a/drivers/staging/goldfish/goldfish_sync_timeline.c b/drivers/staging/goldfish/goldfish_sync_timeline.c new file mode 100644 index 000000000000..880d6e2e5b34 --- /dev/null +++ b/drivers/staging/goldfish/goldfish_sync_timeline.c @@ -0,0 +1,962 @@ +/* + * Copyright (C) 2016 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/fdtable.h> +#include <linux/file.h> +#include <linux/init.h> +#include <linux/miscdevice.h> +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/platform_device.h> + +#include <linux/interrupt.h> +#include <linux/kref.h> +#include <linux/spinlock.h> +#include <linux/types.h> + +#include <linux/io.h> +#include <linux/mm.h> +#include <linux/acpi.h> + +#include <linux/string.h> + +#include <linux/fs.h> +#include <linux/syscalls.h> +#include <linux/sync_file.h> +#include <linux/dma-fence.h> + +#include "goldfish_sync_timeline_fence.h" + +#define ERR(...) printk(KERN_ERR __VA_ARGS__); + +#define INFO(...) printk(KERN_INFO __VA_ARGS__); + +#define DPRINT(...) pr_debug(__VA_ARGS__); + +#define DTRACE() DPRINT("%s: enter", __func__) + +/* The Goldfish sync driver is designed to provide a interface + * between the underlying host's sync device and the kernel's + * fence sync framework.. + * The purpose of the device/driver is to enable lightweight + * creation and signaling of timelines and fences + * in order to synchronize the guest with host-side graphics events. + * + * Each time the interrupt trips, the driver + * may perform a sync operation. + */ + +/* The operations are: */ + +/* Ready signal - used to mark when irq should lower */ +#define CMD_SYNC_READY 0 + +/* Create a new timeline. writes timeline handle */ +#define CMD_CREATE_SYNC_TIMELINE 1 + +/* Create a fence object. reads timeline handle and time argument. + * Writes fence fd to the SYNC_REG_HANDLE register. */ +#define CMD_CREATE_SYNC_FENCE 2 + +/* Increments timeline. reads timeline handle and time argument */ +#define CMD_SYNC_TIMELINE_INC 3 + +/* Destroys a timeline. reads timeline handle */ +#define CMD_DESTROY_SYNC_TIMELINE 4 + +/* Starts a wait on the host with + * the given glsync object and sync thread handle. */ +#define CMD_TRIGGER_HOST_WAIT 5 + +/* The register layout is: */ + +#define SYNC_REG_BATCH_COMMAND 0x00 /* host->guest batch commands */ +#define SYNC_REG_BATCH_GUESTCOMMAND 0x04 /* guest->host batch commands */ +#define SYNC_REG_BATCH_COMMAND_ADDR 0x08 /* communicate physical address of host->guest batch commands */ +#define SYNC_REG_BATCH_COMMAND_ADDR_HIGH 0x0c /* 64-bit part */ +#define SYNC_REG_BATCH_GUESTCOMMAND_ADDR 0x10 /* communicate physical address of guest->host commands */ +#define SYNC_REG_BATCH_GUESTCOMMAND_ADDR_HIGH 0x14 /* 64-bit part */ +#define SYNC_REG_INIT 0x18 /* signals that the device has been probed */ + +/* There is an ioctl associated with goldfish sync driver. + * Make it conflict with ioctls that are not likely to be used + * in the emulator. + * + * '@' 00-0F linux/radeonfb.h conflict! + * '@' 00-0F drivers/video/aty/aty128fb.c conflict! + */ +#define GOLDFISH_SYNC_IOC_MAGIC '@' + +#define GOLDFISH_SYNC_IOC_QUEUE_WORK _IOWR(GOLDFISH_SYNC_IOC_MAGIC, 0, struct goldfish_sync_ioctl_info) + +/* The above definitions (command codes, register layout, ioctl definitions) + * need to be in sync with the following files: + * + * Host-side (emulator): + * external/qemu/android/emulation/goldfish_sync.h + * external/qemu-android/hw/misc/goldfish_sync.c + * + * Guest-side (system image): + * device/generic/goldfish-opengl/system/egl/goldfish_sync.h + * device/generic/goldfish/ueventd.ranchu.rc + * platform/build/target/board/generic/sepolicy/file_contexts + */ +struct goldfish_sync_hostcmd { + /* sorted for alignment */ + uint64_t handle; + uint64_t hostcmd_handle; + uint32_t cmd; + uint32_t time_arg; +}; + +struct goldfish_sync_guestcmd { + uint64_t host_command; /* uint64_t for alignment */ + uint64_t glsync_handle; + uint64_t thread_handle; + uint64_t guest_timeline_handle; +}; + +#define GOLDFISH_SYNC_MAX_CMDS 32 + +struct goldfish_sync_state { + char __iomem *reg_base; + int irq; + + /* Spinlock protects |to_do| / |to_do_end|. */ + spinlock_t lock; + /* |mutex_lock| protects all concurrent access + * to timelines for both kernel and user space. */ + struct mutex mutex_lock; + + /* Buffer holding commands issued from host. */ + struct goldfish_sync_hostcmd to_do[GOLDFISH_SYNC_MAX_CMDS]; + uint32_t to_do_end; + + /* Addresses for the reading or writing + * of individual commands. The host can directly write + * to |batch_hostcmd| (and then this driver immediately + * copies contents to |to_do|). This driver either replies + * through |batch_hostcmd| or simply issues a + * guest->host command through |batch_guestcmd|. + */ + struct goldfish_sync_hostcmd *batch_hostcmd; + struct goldfish_sync_guestcmd *batch_guestcmd; + + /* Used to give this struct itself to a work queue + * function for executing actual sync commands. */ + struct work_struct work_item; +}; + +static struct goldfish_sync_state global_sync_state[1]; + +struct goldfish_sync_timeline_obj { + struct goldfish_sync_timeline *sync_tl; + uint32_t current_time; + /* We need to be careful about when we deallocate + * this |goldfish_sync_timeline_obj| struct. + * In order to ensure proper cleanup, we need to + * consider the triggered host-side wait that may + * still be in flight when the guest close()'s a + * goldfish_sync device's sync context fd (and + * destroys the |sync_tl| field above). + * The host-side wait may raise IRQ + * and tell the kernel to increment the timeline _after_ + * the |sync_tl| has already been set to null. + * + * From observations on OpenGL apps and CTS tests, this + * happens at some very low probability upon context + * destruction or process close, but it does happen + * and it needs to be handled properly. Otherwise, + * if we clean up the surrounding |goldfish_sync_timeline_obj| + * too early, any |handle| field of any host->guest command + * might not even point to a null |sync_tl| field, + * but to garbage memory or even a reclaimed |sync_tl|. + * If we do not count such "pending waits" and kfree the object + * immediately upon |goldfish_sync_timeline_destroy|, + * we might get mysterous RCU stalls after running a long + * time because the garbage memory that is being read + * happens to be interpretable as a |spinlock_t| struct + * that is currently in the locked state. + * + * To track when to free the |goldfish_sync_timeline_obj| + * itself, we maintain a kref. + * The kref essentially counts the timeline itself plus + * the number of waits in flight. kref_init/kref_put + * are issued on + * |goldfish_sync_timeline_create|/|goldfish_sync_timeline_destroy| + * and kref_get/kref_put are issued on + * |goldfish_sync_fence_create|/|goldfish_sync_timeline_inc|. + * + * The timeline is destroyed after reference count + * reaches zero, which would happen after + * |goldfish_sync_timeline_destroy| and all pending + * |goldfish_sync_timeline_inc|'s are fulfilled. + * + * NOTE (1): We assume that |fence_create| and + * |timeline_inc| calls are 1:1, otherwise the kref scheme + * will not work. This is a valid assumption as long + * as the host-side virtual device implementation + * does not insert any timeline increments + * that we did not trigger from here. + * + * NOTE (2): The use of kref by itself requires no locks, + * but this does not mean everything works without locks. + * Related timeline operations do require a lock of some sort, + * or at least are not proven to work without it. + * In particualr, we assume that all the operations + * done on the |kref| field above are done in contexts where + * |global_sync_state->mutex_lock| is held. Do not + * remove that lock until everything is proven to work + * without it!!! */ + struct kref kref; +}; + +/* We will call |delete_timeline_obj| when the last reference count + * of the kref is decremented. This deletes the sync + * timeline object along with the wrapper itself. */ +static void delete_timeline_obj(struct kref* kref) { + struct goldfish_sync_timeline_obj* obj = + container_of(kref, struct goldfish_sync_timeline_obj, kref); + + goldfish_sync_timeline_put_internal(obj->sync_tl); + obj->sync_tl = NULL; + kfree(obj); +} + +static uint64_t gensym_ctr; +static void gensym(char *dst) +{ + sprintf(dst, "goldfish_sync:gensym:%llu", gensym_ctr); + gensym_ctr++; +} + +/* |goldfish_sync_timeline_create| assumes that |global_sync_state->mutex_lock| + * is held. */ +static struct goldfish_sync_timeline_obj* +goldfish_sync_timeline_create(void) +{ + + char timeline_name[256]; + struct goldfish_sync_timeline *res_sync_tl = NULL; + struct goldfish_sync_timeline_obj *res; + + DTRACE(); + + gensym(timeline_name); + + res_sync_tl = goldfish_sync_timeline_create_internal(timeline_name); + if (!res_sync_tl) { + ERR("Failed to create goldfish_sw_sync timeline."); + return NULL; + } + + res = kzalloc(sizeof(struct goldfish_sync_timeline_obj), GFP_KERNEL); + res->sync_tl = res_sync_tl; + res->current_time = 0; + kref_init(&res->kref); + + DPRINT("new timeline_obj=0x%p", res); + return res; +} + +/* |goldfish_sync_fence_create| assumes that |global_sync_state->mutex_lock| + * is held. */ +static int +goldfish_sync_fence_create(struct goldfish_sync_timeline_obj *obj, + uint32_t val) +{ + + int fd; + char fence_name[256]; + struct sync_pt *syncpt = NULL; + struct sync_file *sync_file_obj = NULL; + struct goldfish_sync_timeline *tl; + + DTRACE(); + + if (!obj) return -1; + + tl = obj->sync_tl; + + syncpt = goldfish_sync_pt_create_internal( + tl, sizeof(struct sync_pt) + 4, val); + if (!syncpt) { + ERR("could not create sync point! " + "goldfish_sync_timeline=0x%p val=%d", + tl, val); + return -1; + } + + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) { + ERR("could not get unused fd for sync fence. " + "errno=%d", fd); + goto err_cleanup_pt; + } + + gensym(fence_name); + + sync_file_obj = sync_file_create(&syncpt->base); + if (!sync_file_obj) { + ERR("could not create sync fence! " + "goldfish_sync_timeline=0x%p val=%d sync_pt=0x%p", + tl, val, syncpt); + goto err_cleanup_fd_pt; + } + + DPRINT("installing sync fence into fd %d sync_file_obj=0x%p", + fd, sync_file_obj); + fd_install(fd, sync_file_obj->file); + kref_get(&obj->kref); + + return fd; + +err_cleanup_fd_pt: + put_unused_fd(fd); +err_cleanup_pt: + dma_fence_put(&syncpt->base); + return -1; +} + +/* |goldfish_sync_timeline_inc| assumes that |global_sync_state->mutex_lock| + * is held. */ +static void +goldfish_sync_timeline_inc(struct goldfish_sync_timeline_obj *obj, uint32_t inc) +{ + DTRACE(); + /* Just give up if someone else nuked the timeline. + * Whoever it was won't care that it doesn't get signaled. */ + if (!obj) return; + + DPRINT("timeline_obj=0x%p", obj); + goldfish_sync_timeline_signal_internal(obj->sync_tl, inc); + DPRINT("incremented timeline. increment max_time"); + obj->current_time += inc; + + /* Here, we will end up deleting the timeline object if it + * turns out that this call was a pending increment after + * |goldfish_sync_timeline_destroy| was called. */ + kref_put(&obj->kref, delete_timeline_obj); + DPRINT("done"); +} + +/* |goldfish_sync_timeline_destroy| assumes + * that |global_sync_state->mutex_lock| is held. */ +static void +goldfish_sync_timeline_destroy(struct goldfish_sync_timeline_obj *obj) +{ + DTRACE(); + /* See description of |goldfish_sync_timeline_obj| for why we + * should not immediately destroy |obj| */ + kref_put(&obj->kref, delete_timeline_obj); +} + +static inline void +goldfish_sync_cmd_queue(struct goldfish_sync_state *sync_state, + uint32_t cmd, + uint64_t handle, + uint32_t time_arg, + uint64_t hostcmd_handle) +{ + struct goldfish_sync_hostcmd *to_add; + + DTRACE(); + + BUG_ON(sync_state->to_do_end == GOLDFISH_SYNC_MAX_CMDS); + + to_add = &sync_state->to_do[sync_state->to_do_end]; + + to_add->cmd = cmd; + to_add->handle = handle; + to_add->time_arg = time_arg; + to_add->hostcmd_handle = hostcmd_handle; + + sync_state->to_do_end += 1; +} + +static inline void +goldfish_sync_hostcmd_reply(struct goldfish_sync_state *sync_state, + uint32_t cmd, + uint64_t handle, + uint32_t time_arg, + uint64_t hostcmd_handle) +{ + unsigned long irq_flags; + struct goldfish_sync_hostcmd *batch_hostcmd = + sync_state->batch_hostcmd; + + DTRACE(); + + spin_lock_irqsave(&sync_state->lock, irq_flags); + + batch_hostcmd->cmd = cmd; + batch_hostcmd->handle = handle; + batch_hostcmd->time_arg = time_arg; + batch_hostcmd->hostcmd_handle = hostcmd_handle; + writel(0, sync_state->reg_base + SYNC_REG_BATCH_COMMAND); + + spin_unlock_irqrestore(&sync_state->lock, irq_flags); +} + +static inline void +goldfish_sync_send_guestcmd(struct goldfish_sync_state *sync_state, + uint32_t cmd, + uint64_t glsync_handle, + uint64_t thread_handle, + uint64_t timeline_handle) +{ + unsigned long irq_flags; + struct goldfish_sync_guestcmd *batch_guestcmd = + sync_state->batch_guestcmd; + + DTRACE(); + + spin_lock_irqsave(&sync_state->lock, irq_flags); + + batch_guestcmd->host_command = (uint64_t)cmd; + batch_guestcmd->glsync_handle = (uint64_t)glsync_handle; + batch_guestcmd->thread_handle = (uint64_t)thread_handle; + batch_guestcmd->guest_timeline_handle = (uint64_t)timeline_handle; + writel(0, sync_state->reg_base + SYNC_REG_BATCH_GUESTCOMMAND); + + spin_unlock_irqrestore(&sync_state->lock, irq_flags); +} + +/* |goldfish_sync_interrupt| handles IRQ raises from the virtual device. + * In the context of OpenGL, this interrupt will fire whenever we need + * to signal a fence fd in the guest, with the command + * |CMD_SYNC_TIMELINE_INC|. + * However, because this function will be called in an interrupt context, + * it is necessary to do the actual work of signaling off of interrupt context. + * The shared work queue is used for this purpose. At the end when + * all pending commands are intercepted by the interrupt handler, + * we call |schedule_work|, which will later run the actual + * desired sync command in |goldfish_sync_work_item_fn|. + */ +static irqreturn_t goldfish_sync_interrupt(int irq, void *dev_id) +{ + + struct goldfish_sync_state *sync_state = dev_id; + + uint32_t nextcmd; + uint32_t command_r; + uint64_t handle_rw; + uint32_t time_r; + uint64_t hostcmd_handle_rw; + + int count = 0; + + DTRACE(); + + sync_state = dev_id; + + spin_lock(&sync_state->lock); + + for (;;) { + + readl(sync_state->reg_base + SYNC_REG_BATCH_COMMAND); + nextcmd = sync_state->batch_hostcmd->cmd; + + if (nextcmd == 0) + break; + + command_r = nextcmd; + handle_rw = sync_state->batch_hostcmd->handle; + time_r = sync_state->batch_hostcmd->time_arg; + hostcmd_handle_rw = sync_state->batch_hostcmd->hostcmd_handle; + + goldfish_sync_cmd_queue( + sync_state, + command_r, + handle_rw, + time_r, + hostcmd_handle_rw); + + count++; + } + + spin_unlock(&sync_state->lock); + + schedule_work(&sync_state->work_item); + + return (count == 0) ? IRQ_NONE : IRQ_HANDLED; +} + +/* |goldfish_sync_work_item_fn| does the actual work of servicing + * host->guest sync commands. This function is triggered whenever + * the IRQ for the goldfish sync device is raised. Once it starts + * running, it grabs the contents of the buffer containing the + * commands it needs to execute (there may be multiple, because + * our IRQ is active high and not edge triggered), and then + * runs all of them one after the other. + */ +static void goldfish_sync_work_item_fn(struct work_struct *input) +{ + + struct goldfish_sync_state *sync_state; + int sync_fence_fd; + + struct goldfish_sync_timeline_obj *timeline; + uint64_t timeline_ptr; + + uint64_t hostcmd_handle; + + uint32_t cmd; + uint64_t handle; + uint32_t time_arg; + + struct goldfish_sync_hostcmd *todo; + uint32_t todo_end; + + unsigned long irq_flags; + + struct goldfish_sync_hostcmd to_run[GOLDFISH_SYNC_MAX_CMDS]; + uint32_t i = 0; + + sync_state = container_of(input, struct goldfish_sync_state, work_item); + + mutex_lock(&sync_state->mutex_lock); + + spin_lock_irqsave(&sync_state->lock, irq_flags); { + + todo_end = sync_state->to_do_end; + + DPRINT("num sync todos: %u", sync_state->to_do_end); + + for (i = 0; i < todo_end; i++) + to_run[i] = sync_state->to_do[i]; + + /* We expect that commands will come in at a slow enough rate + * so that incoming items will not be more than + * GOLDFISH_SYNC_MAX_CMDS. + * + * This is because the way the sync device is used, + * it's only for managing buffer data transfers per frame, + * with a sequential dependency between putting things in + * to_do and taking them out. Once a set of commands is + * queued up in to_do, the user of the device waits for + * them to be processed before queuing additional commands, + * which limits the rate at which commands come in + * to the rate at which we take them out here. + * + * We also don't expect more than MAX_CMDS to be issued + * at once; there is a correspondence between + * which buffers need swapping to the (display / buffer queue) + * to particular commands, and we don't expect there to be + * enough display or buffer queues in operation at once + * to overrun GOLDFISH_SYNC_MAX_CMDS. + */ + sync_state->to_do_end = 0; + + } spin_unlock_irqrestore(&sync_state->lock, irq_flags); + + for (i = 0; i < todo_end; i++) { + DPRINT("todo index: %u", i); + + todo = &to_run[i]; + + cmd = todo->cmd; + + handle = (uint64_t)todo->handle; + time_arg = todo->time_arg; + hostcmd_handle = (uint64_t)todo->hostcmd_handle; + + DTRACE(); + + timeline = (struct goldfish_sync_timeline_obj *)(uintptr_t)handle; + + switch (cmd) { + case CMD_SYNC_READY: + break; + case CMD_CREATE_SYNC_TIMELINE: + DPRINT("exec CMD_CREATE_SYNC_TIMELINE: " + "handle=0x%llx time_arg=%d", + handle, time_arg); + timeline = goldfish_sync_timeline_create(); + timeline_ptr = (uintptr_t)timeline; + goldfish_sync_hostcmd_reply(sync_state, CMD_CREATE_SYNC_TIMELINE, + timeline_ptr, + 0, + hostcmd_handle); + DPRINT("sync timeline created: %p", timeline); + break; + case CMD_CREATE_SYNC_FENCE: + DPRINT("exec CMD_CREATE_SYNC_FENCE: " + "handle=0x%llx time_arg=%d", + handle, time_arg); + sync_fence_fd = goldfish_sync_fence_create(timeline, time_arg); + goldfish_sync_hostcmd_reply(sync_state, CMD_CREATE_SYNC_FENCE, + sync_fence_fd, + 0, + hostcmd_handle); + break; + case CMD_SYNC_TIMELINE_INC: + DPRINT("exec CMD_SYNC_TIMELINE_INC: " + "handle=0x%llx time_arg=%d", + handle, time_arg); + goldfish_sync_timeline_inc(timeline, time_arg); + break; + case CMD_DESTROY_SYNC_TIMELINE: + DPRINT("exec CMD_DESTROY_SYNC_TIMELINE: " + "handle=0x%llx time_arg=%d", + handle, time_arg); + goldfish_sync_timeline_destroy(timeline); + break; + } + DPRINT("Done executing sync command"); + } + mutex_unlock(&sync_state->mutex_lock); +} + +/* Guest-side interface: file operations */ + +/* Goldfish sync context and ioctl info. + * + * When a sync context is created by open()-ing the goldfish sync device, we + * create a sync context (|goldfish_sync_context|). + * + * Currently, the only data required to track is the sync timeline itself + * along with the current time, which are all packed up in the + * |goldfish_sync_timeline_obj| field. We use a |goldfish_sync_context| + * as the filp->private_data. + * + * Next, when a sync context user requests that work be queued and a fence + * fd provided, we use the |goldfish_sync_ioctl_info| struct, which holds + * information about which host handles to touch for this particular + * queue-work operation. We need to know about the host-side sync thread + * and the particular host-side GLsync object. We also possibly write out + * a file descriptor. + */ +struct goldfish_sync_context { + struct goldfish_sync_timeline_obj *timeline; +}; + +struct goldfish_sync_ioctl_info { + uint64_t host_glsync_handle_in; + uint64_t host_syncthread_handle_in; + int fence_fd_out; +}; + +static int goldfish_sync_open(struct inode *inode, struct file *file) +{ + + struct goldfish_sync_context *sync_context; + + DTRACE(); + + mutex_lock(&global_sync_state->mutex_lock); + + sync_context = kzalloc(sizeof(struct goldfish_sync_context), GFP_KERNEL); + + if (sync_context == NULL) { + ERR("Creation of goldfish sync context failed!"); + mutex_unlock(&global_sync_state->mutex_lock); + return -ENOMEM; + } + + sync_context->timeline = NULL; + + file->private_data = sync_context; + + DPRINT("successfully create a sync context @0x%p", sync_context); + + mutex_unlock(&global_sync_state->mutex_lock); + + return 0; +} + +static int goldfish_sync_release(struct inode *inode, struct file *file) +{ + + struct goldfish_sync_context *sync_context; + + DTRACE(); + + mutex_lock(&global_sync_state->mutex_lock); + + sync_context = file->private_data; + + if (sync_context->timeline) + goldfish_sync_timeline_destroy(sync_context->timeline); + + sync_context->timeline = NULL; + + kfree(sync_context); + + mutex_unlock(&global_sync_state->mutex_lock); + + return 0; +} + +/* |goldfish_sync_ioctl| is the guest-facing interface of goldfish sync + * and is used in conjunction with eglCreateSyncKHR to queue up the + * actual work of waiting for the EGL sync command to complete, + * possibly returning a fence fd to the guest. + */ +static long goldfish_sync_ioctl(struct file *file, + unsigned int cmd, + unsigned long arg) +{ + struct goldfish_sync_context *sync_context_data; + struct goldfish_sync_timeline_obj *timeline; + int fd_out; + struct goldfish_sync_ioctl_info ioctl_data; + + DTRACE(); + + sync_context_data = file->private_data; + fd_out = -1; + + switch (cmd) { + case GOLDFISH_SYNC_IOC_QUEUE_WORK: + + DPRINT("exec GOLDFISH_SYNC_IOC_QUEUE_WORK"); + + mutex_lock(&global_sync_state->mutex_lock); + + if (copy_from_user(&ioctl_data, + (void __user *)arg, + sizeof(ioctl_data))) { + ERR("Failed to copy memory for ioctl_data from user."); + mutex_unlock(&global_sync_state->mutex_lock); + return -EFAULT; + } + + if (ioctl_data.host_syncthread_handle_in == 0) { + DPRINT("Error: zero host syncthread handle!!!"); + mutex_unlock(&global_sync_state->mutex_lock); + return -EFAULT; + } + + if (!sync_context_data->timeline) { + DPRINT("no timeline yet, create one."); + sync_context_data->timeline = goldfish_sync_timeline_create(); + DPRINT("timeline: 0x%p", &sync_context_data->timeline); + } + + timeline = sync_context_data->timeline; + fd_out = goldfish_sync_fence_create(timeline, + timeline->current_time + 1); + DPRINT("Created fence with fd %d and current time %u (timeline: 0x%p)", + fd_out, + sync_context_data->timeline->current_time + 1, + sync_context_data->timeline); + + ioctl_data.fence_fd_out = fd_out; + + if (copy_to_user((void __user *)arg, + &ioctl_data, + sizeof(ioctl_data))) { + DPRINT("Error, could not copy to user!!!"); + + sys_close(fd_out); + /* We won't be doing an increment, kref_put immediately. */ + kref_put(&timeline->kref, delete_timeline_obj); + mutex_unlock(&global_sync_state->mutex_lock); + return -EFAULT; + } + + /* We are now about to trigger a host-side wait; + * accumulate on |pending_waits|. */ + goldfish_sync_send_guestcmd(global_sync_state, + CMD_TRIGGER_HOST_WAIT, + ioctl_data.host_glsync_handle_in, + ioctl_data.host_syncthread_handle_in, + (uint64_t)(uintptr_t)(sync_context_data->timeline)); + + mutex_unlock(&global_sync_state->mutex_lock); + return 0; + default: + return -ENOTTY; + } +} + +static const struct file_operations goldfish_sync_fops = { + .owner = THIS_MODULE, + .open = goldfish_sync_open, + .release = goldfish_sync_release, + .unlocked_ioctl = goldfish_sync_ioctl, + .compat_ioctl = goldfish_sync_ioctl, +}; + +static struct miscdevice goldfish_sync_device = { + .name = "goldfish_sync", + .fops = &goldfish_sync_fops, +}; + + +static bool setup_verify_batch_cmd_addr(struct goldfish_sync_state *sync_state, + void *batch_addr, + uint32_t addr_offset, + uint32_t addr_offset_high) +{ + uint64_t batch_addr_phys; + uint32_t batch_addr_phys_test_lo; + uint32_t batch_addr_phys_test_hi; + + if (!batch_addr) { + ERR("Could not use batch command address!"); + return false; + } + + batch_addr_phys = virt_to_phys(batch_addr); + writel((uint32_t)(batch_addr_phys), + sync_state->reg_base + addr_offset); + writel((uint32_t)(batch_addr_phys >> 32), + sync_state->reg_base + addr_offset_high); + + batch_addr_phys_test_lo = + readl(sync_state->reg_base + addr_offset); + batch_addr_phys_test_hi = + readl(sync_state->reg_base + addr_offset_high); + + if (virt_to_phys(batch_addr) != + (((uint64_t)batch_addr_phys_test_hi << 32) | + batch_addr_phys_test_lo)) { + ERR("Invalid batch command address!"); + return false; + } + + return true; +} + +int goldfish_sync_probe(struct platform_device *pdev) +{ + struct resource *ioresource; + struct goldfish_sync_state *sync_state = global_sync_state; + int status; + + DTRACE(); + + sync_state->to_do_end = 0; + + spin_lock_init(&sync_state->lock); + mutex_init(&sync_state->mutex_lock); + + platform_set_drvdata(pdev, sync_state); + + ioresource = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (ioresource == NULL) { + ERR("platform_get_resource failed"); + return -ENODEV; + } + + sync_state->reg_base = + devm_ioremap(&pdev->dev, ioresource->start, PAGE_SIZE); + if (sync_state->reg_base == NULL) { + ERR("Could not ioremap"); + return -ENOMEM; + } + + sync_state->irq = platform_get_irq(pdev, 0); + if (sync_state->irq < 0) { + ERR("Could not platform_get_irq"); + return -ENODEV; + } + + status = devm_request_irq(&pdev->dev, + sync_state->irq, + goldfish_sync_interrupt, + IRQF_SHARED, + pdev->name, + sync_state); + if (status) { + ERR("request_irq failed"); + return -ENODEV; + } + + INIT_WORK(&sync_state->work_item, + goldfish_sync_work_item_fn); + + misc_register(&goldfish_sync_device); + + /* Obtain addresses for batch send/recv of commands. */ + { + struct goldfish_sync_hostcmd *batch_addr_hostcmd; + struct goldfish_sync_guestcmd *batch_addr_guestcmd; + + batch_addr_hostcmd = + devm_kzalloc(&pdev->dev, sizeof(struct goldfish_sync_hostcmd), + GFP_KERNEL); + batch_addr_guestcmd = + devm_kzalloc(&pdev->dev, sizeof(struct goldfish_sync_guestcmd), + GFP_KERNEL); + + if (!setup_verify_batch_cmd_addr(sync_state, + batch_addr_hostcmd, + SYNC_REG_BATCH_COMMAND_ADDR, + SYNC_REG_BATCH_COMMAND_ADDR_HIGH)) { + ERR("goldfish_sync: Could not setup batch command address"); + return -ENODEV; + } + + if (!setup_verify_batch_cmd_addr(sync_state, + batch_addr_guestcmd, + SYNC_REG_BATCH_GUESTCOMMAND_ADDR, + SYNC_REG_BATCH_GUESTCOMMAND_ADDR_HIGH)) { + ERR("goldfish_sync: Could not setup batch guest command address"); + return -ENODEV; + } + + sync_state->batch_hostcmd = batch_addr_hostcmd; + sync_state->batch_guestcmd = batch_addr_guestcmd; + } + + INFO("goldfish_sync: Initialized goldfish sync device"); + + writel(0, sync_state->reg_base + SYNC_REG_INIT); + + return 0; +} + +static int goldfish_sync_remove(struct platform_device *pdev) +{ + struct goldfish_sync_state *sync_state = global_sync_state; + + DTRACE(); + + misc_deregister(&goldfish_sync_device); + memset(sync_state, 0, sizeof(struct goldfish_sync_state)); + return 0; +} + +static const struct of_device_id goldfish_sync_of_match[] = { + { .compatible = "google,goldfish-sync", }, + {}, +}; +MODULE_DEVICE_TABLE(of, goldfish_sync_of_match); + +static const struct acpi_device_id goldfish_sync_acpi_match[] = { + { "GFSH0006", 0 }, + { }, +}; + +MODULE_DEVICE_TABLE(acpi, goldfish_sync_acpi_match); + +static struct platform_driver goldfish_sync = { + .probe = goldfish_sync_probe, + .remove = goldfish_sync_remove, + .driver = { + .name = "goldfish_sync", + .of_match_table = goldfish_sync_of_match, + .acpi_match_table = ACPI_PTR(goldfish_sync_acpi_match), + } +}; + +module_platform_driver(goldfish_sync); + +MODULE_AUTHOR("Google, Inc."); +MODULE_DESCRIPTION("Android QEMU Sync Driver"); +MODULE_LICENSE("GPL"); +MODULE_VERSION("1.0"); diff --git a/drivers/staging/goldfish/goldfish_sync_timeline_fence.c b/drivers/staging/goldfish/goldfish_sync_timeline_fence.c new file mode 100644 index 000000000000..a5bc2deab780 --- /dev/null +++ b/drivers/staging/goldfish/goldfish_sync_timeline_fence.c @@ -0,0 +1,254 @@ +#include <linux/slab.h> +#include <linux/fs.h> +#include <linux/syscalls.h> +#include <linux/sync_file.h> +#include <linux/dma-fence.h> + +#include "goldfish_sync_timeline_fence.h" + +/* + * Timeline-based sync for Goldfish Sync + * Based on "Sync File validation framework" + * (drivers/dma-buf/sw_sync.c) + * + * Copyright (C) 2017 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +/** + * struct goldfish_sync_timeline - sync object + * @kref: reference count on fence. + * @name: name of the goldfish_sync_timeline. Useful for debugging + * @child_list_head: list of children sync_pts for this goldfish_sync_timeline + * @child_list_lock: lock protecting @child_list_head and fence.status + * @active_list_head: list of active (unsignaled/errored) sync_pts + */ +struct goldfish_sync_timeline { + struct kref kref; + char name[32]; + + /* protected by child_list_lock */ + u64 context; + int value; + + struct list_head child_list_head; + spinlock_t child_list_lock; + + struct list_head active_list_head; +}; + +static inline struct goldfish_sync_timeline *goldfish_dma_fence_parent(struct dma_fence *fence) +{ + return container_of(fence->lock, struct goldfish_sync_timeline, + child_list_lock); +} + +static const struct dma_fence_ops goldfish_sync_timeline_fence_ops; + +static inline struct sync_pt *goldfish_sync_fence_to_sync_pt(struct dma_fence *fence) +{ + if (fence->ops != &goldfish_sync_timeline_fence_ops) + return NULL; + return container_of(fence, struct sync_pt, base); +} + +/** + * goldfish_sync_timeline_create_internal() - creates a sync object + * @name: sync_timeline name + * + * Creates a new sync_timeline. Returns the sync_timeline object or NULL in + * case of error. + */ +struct goldfish_sync_timeline +*goldfish_sync_timeline_create_internal(const char *name) +{ + struct goldfish_sync_timeline *obj; + + obj = kzalloc(sizeof(*obj), GFP_KERNEL); + if (!obj) + return NULL; + + kref_init(&obj->kref); + obj->context = dma_fence_context_alloc(1); + strlcpy(obj->name, name, sizeof(obj->name)); + + INIT_LIST_HEAD(&obj->child_list_head); + INIT_LIST_HEAD(&obj->active_list_head); + spin_lock_init(&obj->child_list_lock); + + return obj; +} + +static void goldfish_sync_timeline_free_internal(struct kref *kref) +{ + struct goldfish_sync_timeline *obj = + container_of(kref, struct goldfish_sync_timeline, kref); + + kfree(obj); +} + +static void goldfish_sync_timeline_get_internal( + struct goldfish_sync_timeline *obj) +{ + kref_get(&obj->kref); +} + +void goldfish_sync_timeline_put_internal(struct goldfish_sync_timeline *obj) +{ + kref_put(&obj->kref, goldfish_sync_timeline_free_internal); +} + +/** + * goldfish_sync_timeline_signal() - + * signal a status change on a goldfish_sync_timeline + * @obj: sync_timeline to signal + * @inc: num to increment on timeline->value + * + * A sync implementation should call this any time one of it's fences + * has signaled or has an error condition. + */ +void goldfish_sync_timeline_signal_internal(struct goldfish_sync_timeline *obj, + unsigned int inc) +{ + unsigned long flags; + struct sync_pt *pt, *next; + + spin_lock_irqsave(&obj->child_list_lock, flags); + + obj->value += inc; + + list_for_each_entry_safe(pt, next, &obj->active_list_head, + active_list) { + if (dma_fence_is_signaled_locked(&pt->base)) + list_del_init(&pt->active_list); + } + + spin_unlock_irqrestore(&obj->child_list_lock, flags); +} + +/** + * goldfish_sync_pt_create_internal() - creates a sync pt + * @parent: fence's parent sync_timeline + * @size: size to allocate for this pt + * @inc: value of the fence + * + * Creates a new sync_pt as a child of @parent. @size bytes will be + * allocated allowing for implementation specific data to be kept after + * the generic sync_timeline struct. Returns the sync_pt object or + * NULL in case of error. + */ +struct sync_pt *goldfish_sync_pt_create_internal( + struct goldfish_sync_timeline *obj, int size, + unsigned int value) +{ + unsigned long flags; + struct sync_pt *pt; + + if (size < sizeof(*pt)) + return NULL; + + pt = kzalloc(size, GFP_KERNEL); + if (!pt) + return NULL; + + spin_lock_irqsave(&obj->child_list_lock, flags); + goldfish_sync_timeline_get_internal(obj); + dma_fence_init(&pt->base, &goldfish_sync_timeline_fence_ops, &obj->child_list_lock, + obj->context, value); + list_add_tail(&pt->child_list, &obj->child_list_head); + INIT_LIST_HEAD(&pt->active_list); + spin_unlock_irqrestore(&obj->child_list_lock, flags); + return pt; +} + +static const char *goldfish_sync_timeline_fence_get_driver_name( + struct dma_fence *fence) +{ + return "sw_sync"; +} + +static const char *goldfish_sync_timeline_fence_get_timeline_name( + struct dma_fence *fence) +{ + struct goldfish_sync_timeline *parent = goldfish_dma_fence_parent(fence); + + return parent->name; +} + +static void goldfish_sync_timeline_fence_release(struct dma_fence *fence) +{ + struct sync_pt *pt = goldfish_sync_fence_to_sync_pt(fence); + struct goldfish_sync_timeline *parent = goldfish_dma_fence_parent(fence); + unsigned long flags; + + spin_lock_irqsave(fence->lock, flags); + list_del(&pt->child_list); + if (!list_empty(&pt->active_list)) + list_del(&pt->active_list); + spin_unlock_irqrestore(fence->lock, flags); + + goldfish_sync_timeline_put_internal(parent); + dma_fence_free(fence); +} + +static bool goldfish_sync_timeline_fence_signaled(struct dma_fence *fence) +{ + struct goldfish_sync_timeline *parent = goldfish_dma_fence_parent(fence); + + return (fence->seqno > parent->value) ? false : true; +} + +static bool goldfish_sync_timeline_fence_enable_signaling(struct dma_fence *fence) +{ + struct sync_pt *pt = goldfish_sync_fence_to_sync_pt(fence); + struct goldfish_sync_timeline *parent = goldfish_dma_fence_parent(fence); + + if (goldfish_sync_timeline_fence_signaled(fence)) + return false; + + list_add_tail(&pt->active_list, &parent->active_list_head); + return true; +} + +static void goldfish_sync_timeline_fence_disable_signaling(struct dma_fence *fence) +{ + struct sync_pt *pt = container_of(fence, struct sync_pt, base); + + list_del_init(&pt->active_list); +} + +static void goldfish_sync_timeline_fence_value_str(struct dma_fence *fence, + char *str, int size) +{ + snprintf(str, size, "%d", fence->seqno); +} + +static void goldfish_sync_timeline_fence_timeline_value_str( + struct dma_fence *fence, + char *str, int size) +{ + struct goldfish_sync_timeline *parent = goldfish_dma_fence_parent(fence); + + snprintf(str, size, "%d", parent->value); +} + +static const struct dma_fence_ops goldfish_sync_timeline_fence_ops = { + .get_driver_name = goldfish_sync_timeline_fence_get_driver_name, + .get_timeline_name = goldfish_sync_timeline_fence_get_timeline_name, + .enable_signaling = goldfish_sync_timeline_fence_enable_signaling, + .disable_signaling = goldfish_sync_timeline_fence_disable_signaling, + .signaled = goldfish_sync_timeline_fence_signaled, + .wait = dma_fence_default_wait, + .release = goldfish_sync_timeline_fence_release, + .fence_value_str = goldfish_sync_timeline_fence_value_str, + .timeline_value_str = goldfish_sync_timeline_fence_timeline_value_str, +}; diff --git a/drivers/staging/goldfish/goldfish_sync_timeline_fence.h b/drivers/staging/goldfish/goldfish_sync_timeline_fence.h new file mode 100644 index 000000000000..638c6fb68f1e --- /dev/null +++ b/drivers/staging/goldfish/goldfish_sync_timeline_fence.h @@ -0,0 +1,58 @@ +#include <linux/sync_file.h> +#include <linux/dma-fence.h> + +/** + * struct sync_pt - sync_pt object + * @base: base dma_fence object + * @child_list: sync timeline child's list + * @active_list: sync timeline active child's list + */ +struct sync_pt { + struct dma_fence base; + struct list_head child_list; + struct list_head active_list; +}; + +/** + * goldfish_sync_timeline_create_internal() - creates a sync object + * @name: goldfish_sync_timeline name + * + * Creates a new goldfish_sync_timeline. + * Returns the goldfish_sync_timeline object or NULL in case of error. + */ +struct goldfish_sync_timeline +*goldfish_sync_timeline_create_internal(const char *name); + +/** + * goldfish_sync_pt_create_internal() - creates a sync pt + * @parent: fence's parent goldfish_sync_timeline + * @size: size to allocate for this pt + * @inc: value of the fence + * + * Creates a new sync_pt as a child of @parent. @size bytes will be + * allocated allowing for implementation specific data to be kept after + * the generic sync_timeline struct. Returns the sync_pt object or + * NULL in case of error. + */ +struct sync_pt +*goldfish_sync_pt_create_internal(struct goldfish_sync_timeline *obj, + int size, unsigned int value); + +/** + * goldfish_sync_timeline_signal_internal() - + * signal a status change on a sync_timeline + * @obj: goldfish_sync_timeline to signal + * @inc: num to increment on timeline->value + * + * A sync implementation should call this any time one of it's fences + * has signaled or has an error condition. + */ +void goldfish_sync_timeline_signal_internal(struct goldfish_sync_timeline *obj, + unsigned int inc); + +/** + * goldfish_sync_timeline_put_internal() - dec refcount of a sync_timeline + * and clean up memory if it was the last ref. + * @obj: goldfish_sync_timeline to decref + */ +void goldfish_sync_timeline_put_internal(struct goldfish_sync_timeline *obj); diff --git a/drivers/staging/lustre/lustre/mdc/mdc_request.c b/drivers/staging/lustre/lustre/mdc/mdc_request.c index 6ef8ddec4ab6..8c97acd79211 100644 --- a/drivers/staging/lustre/lustre/mdc/mdc_request.c +++ b/drivers/staging/lustre/lustre/mdc/mdc_request.c @@ -1121,9 +1121,9 @@ struct readpage_param { * in PAGE_SIZE (if PAGE_SIZE greater than LU_PAGE_SIZE), and the * lu_dirpage for this integrated page will be adjusted. **/ -static int mdc_read_page_remote(void *data, struct page *page0) +static int mdc_read_page_remote(struct file *data, struct page *page0) { - struct readpage_param *rp = data; + struct readpage_param *rp = (struct readpage_param *)data; struct page **page_pool; struct page *page; struct lu_dirpage *dp; diff --git a/drivers/tty/serial/kgdboc.c b/drivers/tty/serial/kgdboc.c index 0314e78e31ff..ec24e82da169 100644 --- a/drivers/tty/serial/kgdboc.c +++ b/drivers/tty/serial/kgdboc.c @@ -232,7 +232,8 @@ static void kgdboc_put_char(u8 chr) kgdb_tty_line, chr); } -static int param_set_kgdboc_var(const char *kmessage, struct kernel_param *kp) +static int param_set_kgdboc_var(const char *kmessage, + const struct kernel_param *kp) { size_t len = strlen(kmessage); diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig index 31cce7805eb2..f572b645d21b 100644 --- a/drivers/usb/gadget/Kconfig +++ b/drivers/usb/gadget/Kconfig @@ -215,6 +215,12 @@ config USB_F_PRINTER config USB_F_TCM tristate +config USB_F_AUDIO_SRC + tristate + +config USB_F_ACC + tristate + # this first set of drivers all depend on bulk-capable hardware. config USB_CONFIGFS @@ -368,6 +374,30 @@ config USB_CONFIGFS_F_FS implemented in kernel space (for instance Ethernet, serial or mass storage) and other are implemented in user space. +config USB_CONFIGFS_F_ACC + boolean "Accessory gadget" + depends on USB_CONFIGFS + select USB_F_ACC + help + USB gadget Accessory support + +config USB_CONFIGFS_F_AUDIO_SRC + boolean "Audio Source gadget" + depends on USB_CONFIGFS && USB_CONFIGFS_F_ACC + depends on SND + select SND_PCM + select USB_F_AUDIO_SRC + help + USB gadget Audio Source support + +config USB_CONFIGFS_UEVENT + boolean "Uevent notification of Gadget state" + depends on USB_CONFIGFS + help + Enable uevent notifications to userspace when the gadget + state changes. The gadget can be in any of the following + three states: "CONNECTED/DISCONNECTED/CONFIGURED" + config USB_CONFIGFS_F_UAC1 bool "Audio Class 1.0" depends on USB_CONFIGFS diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index 7d2715e899bb..cb12eed54718 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -2059,6 +2059,12 @@ void composite_disconnect(struct usb_gadget *gadget) struct usb_composite_dev *cdev = get_gadget_data(gadget); unsigned long flags; + if (cdev == NULL) { + WARN(1, "%s: Calling disconnect on a Gadget that is \ + not connected\n", __func__); + return; + } + /* REVISIT: should we have config and device level * disconnect callbacks? */ diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index 3dc84e6a904b..e3312d0f4674 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -9,6 +9,31 @@ #include "u_f.h" #include "u_os_desc.h" +#ifdef CONFIG_USB_CONFIGFS_UEVENT +#include <linux/platform_device.h> +#include <linux/kdev_t.h> +#include <linux/usb/ch9.h> + +#ifdef CONFIG_USB_CONFIGFS_F_ACC +extern int acc_ctrlrequest(struct usb_composite_dev *cdev, + const struct usb_ctrlrequest *ctrl); +void acc_disconnect(void); +#endif +static struct class *android_class; +static struct device *android_device; +static int index; + +struct device *create_function_device(char *name) +{ + if (android_device && !IS_ERR(android_device)) + return device_create(android_class, android_device, + MKDEV(0, index++), NULL, name); + else + return ERR_PTR(-EINVAL); +} +EXPORT_SYMBOL_GPL(create_function_device); +#endif + int check_user_usb_string(const char *name, struct usb_gadget_strings *stringtab_dev) { @@ -62,6 +87,12 @@ struct gadget_info { char qw_sign[OS_STRING_QW_SIGN_LEN]; spinlock_t spinlock; bool unbind; +#ifdef CONFIG_USB_CONFIGFS_UEVENT + bool connected; + bool sw_connected; + struct work_struct work; + struct device *dev; +#endif }; static inline struct gadget_info *to_gadget_info(struct config_item *item) @@ -270,7 +301,7 @@ static ssize_t gadget_dev_desc_UDC_store(struct config_item *item, mutex_lock(&gi->lock); - if (!strlen(name)) { + if (!strlen(name) || strcmp(name, "none") == 0) { ret = unregister_gadget(gi); if (ret) goto err; @@ -1377,6 +1408,60 @@ err_comp_cleanup: return ret; } +#ifdef CONFIG_USB_CONFIGFS_UEVENT +static void android_work(struct work_struct *data) +{ + struct gadget_info *gi = container_of(data, struct gadget_info, work); + struct usb_composite_dev *cdev = &gi->cdev; + char *disconnected[2] = { "USB_STATE=DISCONNECTED", NULL }; + char *connected[2] = { "USB_STATE=CONNECTED", NULL }; + char *configured[2] = { "USB_STATE=CONFIGURED", NULL }; + /* 0-connected 1-configured 2-disconnected*/ + bool status[3] = { false, false, false }; + unsigned long flags; + bool uevent_sent = false; + + spin_lock_irqsave(&cdev->lock, flags); + if (cdev->config) + status[1] = true; + + if (gi->connected != gi->sw_connected) { + if (gi->connected) + status[0] = true; + else + status[2] = true; + gi->sw_connected = gi->connected; + } + spin_unlock_irqrestore(&cdev->lock, flags); + + if (status[0]) { + kobject_uevent_env(&android_device->kobj, + KOBJ_CHANGE, connected); + pr_info("%s: sent uevent %s\n", __func__, connected[0]); + uevent_sent = true; + } + + if (status[1]) { + kobject_uevent_env(&android_device->kobj, + KOBJ_CHANGE, configured); + pr_info("%s: sent uevent %s\n", __func__, configured[0]); + uevent_sent = true; + } + + if (status[2]) { + kobject_uevent_env(&android_device->kobj, + KOBJ_CHANGE, disconnected); + pr_info("%s: sent uevent %s\n", __func__, disconnected[0]); + uevent_sent = true; + } + + if (!uevent_sent) { + pr_info("%s: did not send uevent (%d %d %p)\n", __func__, + gi->connected, gi->sw_connected, cdev->config); + } +} +#endif + static void configfs_composite_unbind(struct usb_gadget *gadget) { struct usb_composite_dev *cdev; @@ -1493,14 +1578,91 @@ static void configfs_composite_resume(struct usb_gadget *gadget) spin_unlock_irqrestore(&gi->spinlock, flags); } +#ifdef CONFIG_USB_CONFIGFS_UEVENT +static int android_setup(struct usb_gadget *gadget, + const struct usb_ctrlrequest *c) +{ + struct usb_composite_dev *cdev = get_gadget_data(gadget); + unsigned long flags; + struct gadget_info *gi = container_of(cdev, struct gadget_info, cdev); + int value = -EOPNOTSUPP; + struct usb_function_instance *fi; + + spin_lock_irqsave(&cdev->lock, flags); + if (!gi->connected) { + gi->connected = 1; + schedule_work(&gi->work); + } + spin_unlock_irqrestore(&cdev->lock, flags); + list_for_each_entry(fi, &gi->available_func, cfs_list) { + if (fi != NULL && fi->f != NULL && fi->f->setup != NULL) { + value = fi->f->setup(fi->f, c); + if (value >= 0) + break; + } + } + +#ifdef CONFIG_USB_CONFIGFS_F_ACC + if (value < 0) + value = acc_ctrlrequest(cdev, c); +#endif + + if (value < 0) + value = composite_setup(gadget, c); + + spin_lock_irqsave(&cdev->lock, flags); + if (c->bRequest == USB_REQ_SET_CONFIGURATION && + cdev->config) { + schedule_work(&gi->work); + } + spin_unlock_irqrestore(&cdev->lock, flags); + + return value; +} + +static void android_disconnect(struct usb_gadget *gadget) +{ + struct usb_composite_dev *cdev = get_gadget_data(gadget); + struct gadget_info *gi = container_of(cdev, struct gadget_info, cdev); + + /* FIXME: There's a race between usb_gadget_udc_stop() which is likely + * to set the gadget driver to NULL in the udc driver and this drivers + * gadget disconnect fn which likely checks for the gadget driver to + * be a null ptr. It happens that unbind (doing set_gadget_data(NULL)) + * is called before the gadget driver is set to NULL and the udc driver + * calls disconnect fn which results in cdev being a null ptr. + */ + if (cdev == NULL) { + WARN(1, "%s: gadget driver already disconnected\n", __func__); + return; + } + + /* accessory HID support can be active while the + accessory function is not actually enabled, + so we need to inform it when we are disconnected. + */ + +#ifdef CONFIG_USB_CONFIGFS_F_ACC + acc_disconnect(); +#endif + gi->connected = 0; + schedule_work(&gi->work); + composite_disconnect(gadget); +} +#endif + static const struct usb_gadget_driver configfs_driver_template = { .bind = configfs_composite_bind, .unbind = configfs_composite_unbind, - +#ifdef CONFIG_USB_CONFIGFS_UEVENT + .setup = android_setup, + .reset = android_disconnect, + .disconnect = android_disconnect, +#else .setup = configfs_composite_setup, .reset = configfs_composite_disconnect, .disconnect = configfs_composite_disconnect, - +#endif .suspend = configfs_composite_suspend, .resume = configfs_composite_resume, @@ -1512,6 +1674,89 @@ static const struct usb_gadget_driver configfs_driver_template = { .match_existing_only = 1, }; +#ifdef CONFIG_USB_CONFIGFS_UEVENT +static ssize_t state_show(struct device *pdev, struct device_attribute *attr, + char *buf) +{ + struct gadget_info *dev = dev_get_drvdata(pdev); + struct usb_composite_dev *cdev; + char *state = "DISCONNECTED"; + unsigned long flags; + + if (!dev) + goto out; + + cdev = &dev->cdev; + + if (!cdev) + goto out; + + spin_lock_irqsave(&cdev->lock, flags); + if (cdev->config) + state = "CONFIGURED"; + else if (dev->connected) + state = "CONNECTED"; + spin_unlock_irqrestore(&cdev->lock, flags); +out: + return sprintf(buf, "%s\n", state); +} + +static DEVICE_ATTR(state, S_IRUGO, state_show, NULL); + +static struct device_attribute *android_usb_attributes[] = { + &dev_attr_state, + NULL +}; + +static int android_device_create(struct gadget_info *gi) +{ + struct device_attribute **attrs; + struct device_attribute *attr; + + INIT_WORK(&gi->work, android_work); + android_device = device_create(android_class, NULL, + MKDEV(0, 0), NULL, "android0"); + if (IS_ERR(android_device)) + return PTR_ERR(android_device); + + dev_set_drvdata(android_device, gi); + + attrs = android_usb_attributes; + while ((attr = *attrs++)) { + int err; + + err = device_create_file(android_device, attr); + if (err) { + device_destroy(android_device->class, + android_device->devt); + return err; + } + } + + return 0; +} + +static void android_device_destroy(void) +{ + struct device_attribute **attrs; + struct device_attribute *attr; + + attrs = android_usb_attributes; + while ((attr = *attrs++)) + device_remove_file(android_device, attr); + device_destroy(android_device->class, android_device->devt); +} +#else +static inline int android_device_create(struct gadget_info *gi) +{ + return 0; +} + +static inline void android_device_destroy(void) +{ +} +#endif + static struct config_group *gadgets_make( struct config_group *group, const char *name) @@ -1564,7 +1809,11 @@ static struct config_group *gadgets_make( if (!gi->composite.gadget_driver.function) goto err; + if (android_device_create(gi) < 0) + goto err; + return &gi->group; + err: kfree(gi); return ERR_PTR(-ENOMEM); @@ -1573,6 +1822,7 @@ err: static void gadgets_drop(struct config_group *group, struct config_item *item) { config_item_put(item); + android_device_destroy(); } static struct configfs_group_operations gadgets_ops = { @@ -1612,6 +1862,13 @@ static int __init gadget_cfs_init(void) config_group_init(&gadget_subsys.su_group); ret = configfs_register_subsystem(&gadget_subsys); + +#ifdef CONFIG_USB_CONFIGFS_UEVENT + android_class = class_create(THIS_MODULE, "android_usb"); + if (IS_ERR(android_class)) + return PTR_ERR(android_class); +#endif + return ret; } module_init(gadget_cfs_init); @@ -1619,5 +1876,10 @@ module_init(gadget_cfs_init); static void __exit gadget_cfs_exit(void) { configfs_unregister_subsystem(&gadget_subsys); +#ifdef CONFIG_USB_CONFIGFS_UEVENT + if (!IS_ERR(android_class)) + class_destroy(android_class); +#endif + } module_exit(gadget_cfs_exit); diff --git a/drivers/usb/gadget/function/Makefile b/drivers/usb/gadget/function/Makefile index 5d3a6cf02218..d7d5673d8343 100644 --- a/drivers/usb/gadget/function/Makefile +++ b/drivers/usb/gadget/function/Makefile @@ -50,3 +50,7 @@ usb_f_printer-y := f_printer.o obj-$(CONFIG_USB_F_PRINTER) += usb_f_printer.o usb_f_tcm-y := f_tcm.o obj-$(CONFIG_USB_F_TCM) += usb_f_tcm.o +usb_f_audio_source-y := f_audio_source.o +obj-$(CONFIG_USB_F_AUDIO_SRC) += usb_f_audio_source.o +usb_f_accessory-y := f_accessory.o +obj-$(CONFIG_USB_F_ACC) += usb_f_accessory.o diff --git a/drivers/usb/gadget/function/f_accessory.c b/drivers/usb/gadget/function/f_accessory.c new file mode 100644 index 000000000000..7aa2656a2328 --- /dev/null +++ b/drivers/usb/gadget/function/f_accessory.c @@ -0,0 +1,1352 @@ +/* + * Gadget Function Driver for Android USB accessories + * + * Copyright (C) 2011 Google, Inc. + * Author: Mike Lockwood <lockwood@android.com> + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +/* #define DEBUG */ +/* #define VERBOSE_DEBUG */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/poll.h> +#include <linux/delay.h> +#include <linux/wait.h> +#include <linux/err.h> +#include <linux/interrupt.h> +#include <linux/kthread.h> +#include <linux/freezer.h> + +#include <linux/types.h> +#include <linux/file.h> +#include <linux/device.h> +#include <linux/miscdevice.h> + +#include <linux/hid.h> +#include <linux/hiddev.h> +#include <linux/usb.h> +#include <linux/usb/ch9.h> +#include <linux/usb/f_accessory.h> + +#include <linux/configfs.h> +#include <linux/usb/composite.h> + +#define MAX_INST_NAME_LEN 40 +#define BULK_BUFFER_SIZE 16384 +#define ACC_STRING_SIZE 256 + +#define PROTOCOL_VERSION 2 + +/* String IDs */ +#define INTERFACE_STRING_INDEX 0 + +/* number of tx and rx requests to allocate */ +#define TX_REQ_MAX 4 +#define RX_REQ_MAX 2 + +struct acc_hid_dev { + struct list_head list; + struct hid_device *hid; + struct acc_dev *dev; + /* accessory defined ID */ + int id; + /* HID report descriptor */ + u8 *report_desc; + /* length of HID report descriptor */ + int report_desc_len; + /* number of bytes of report_desc we have received so far */ + int report_desc_offset; +}; + +struct acc_dev { + struct usb_function function; + struct usb_composite_dev *cdev; + spinlock_t lock; + + struct usb_ep *ep_in; + struct usb_ep *ep_out; + + /* online indicates state of function_set_alt & function_unbind + * set to 1 when we connect + */ + int online:1; + + /* disconnected indicates state of open & release + * Set to 1 when we disconnect. + * Not cleared until our file is closed. + */ + int disconnected:1; + + /* strings sent by the host */ + char manufacturer[ACC_STRING_SIZE]; + char model[ACC_STRING_SIZE]; + char description[ACC_STRING_SIZE]; + char version[ACC_STRING_SIZE]; + char uri[ACC_STRING_SIZE]; + char serial[ACC_STRING_SIZE]; + + /* for acc_complete_set_string */ + int string_index; + + /* set to 1 if we have a pending start request */ + int start_requested; + + int audio_mode; + + /* synchronize access to our device file */ + atomic_t open_excl; + + struct list_head tx_idle; + + wait_queue_head_t read_wq; + wait_queue_head_t write_wq; + struct usb_request *rx_req[RX_REQ_MAX]; + int rx_done; + + /* delayed work for handling ACCESSORY_START */ + struct delayed_work start_work; + + /* worker for registering and unregistering hid devices */ + struct work_struct hid_work; + + /* list of active HID devices */ + struct list_head hid_list; + + /* list of new HID devices to register */ + struct list_head new_hid_list; + + /* list of dead HID devices to unregister */ + struct list_head dead_hid_list; +}; + +static struct usb_interface_descriptor acc_interface_desc = { + .bLength = USB_DT_INTERFACE_SIZE, + .bDescriptorType = USB_DT_INTERFACE, + .bInterfaceNumber = 0, + .bNumEndpoints = 2, + .bInterfaceClass = USB_CLASS_VENDOR_SPEC, + .bInterfaceSubClass = USB_SUBCLASS_VENDOR_SPEC, + .bInterfaceProtocol = 0, +}; + +static struct usb_endpoint_descriptor acc_highspeed_in_desc = { + .bLength = USB_DT_ENDPOINT_SIZE, + .bDescriptorType = USB_DT_ENDPOINT, + .bEndpointAddress = USB_DIR_IN, + .bmAttributes = USB_ENDPOINT_XFER_BULK, + .wMaxPacketSize = __constant_cpu_to_le16(512), +}; + +static struct usb_endpoint_descriptor acc_highspeed_out_desc = { + .bLength = USB_DT_ENDPOINT_SIZE, + .bDescriptorType = USB_DT_ENDPOINT, + .bEndpointAddress = USB_DIR_OUT, + .bmAttributes = USB_ENDPOINT_XFER_BULK, + .wMaxPacketSize = __constant_cpu_to_le16(512), +}; + +static struct usb_endpoint_descriptor acc_fullspeed_in_desc = { + .bLength = USB_DT_ENDPOINT_SIZE, + .bDescriptorType = USB_DT_ENDPOINT, + .bEndpointAddress = USB_DIR_IN, + .bmAttributes = USB_ENDPOINT_XFER_BULK, +}; + +static struct usb_endpoint_descriptor acc_fullspeed_out_desc = { + .bLength = USB_DT_ENDPOINT_SIZE, + .bDescriptorType = USB_DT_ENDPOINT, + .bEndpointAddress = USB_DIR_OUT, + .bmAttributes = USB_ENDPOINT_XFER_BULK, +}; + +static struct usb_descriptor_header *fs_acc_descs[] = { + (struct usb_descriptor_header *) &acc_interface_desc, + (struct usb_descriptor_header *) &acc_fullspeed_in_desc, + (struct usb_descriptor_header *) &acc_fullspeed_out_desc, + NULL, +}; + +static struct usb_descriptor_header *hs_acc_descs[] = { + (struct usb_descriptor_header *) &acc_interface_desc, + (struct usb_descriptor_header *) &acc_highspeed_in_desc, + (struct usb_descriptor_header *) &acc_highspeed_out_desc, + NULL, +}; + +static struct usb_string acc_string_defs[] = { + [INTERFACE_STRING_INDEX].s = "Android Accessory Interface", + { }, /* end of list */ +}; + +static struct usb_gadget_strings acc_string_table = { + .language = 0x0409, /* en-US */ + .strings = acc_string_defs, +}; + +static struct usb_gadget_strings *acc_strings[] = { + &acc_string_table, + NULL, +}; + +/* temporary variable used between acc_open() and acc_gadget_bind() */ +static struct acc_dev *_acc_dev; + +struct acc_instance { + struct usb_function_instance func_inst; + const char *name; +}; + +static inline struct acc_dev *func_to_dev(struct usb_function *f) +{ + return container_of(f, struct acc_dev, function); +} + +static struct usb_request *acc_request_new(struct usb_ep *ep, int buffer_size) +{ + struct usb_request *req = usb_ep_alloc_request(ep, GFP_KERNEL); + + if (!req) + return NULL; + + /* now allocate buffers for the requests */ + req->buf = kmalloc(buffer_size, GFP_KERNEL); + if (!req->buf) { + usb_ep_free_request(ep, req); + return NULL; + } + + return req; +} + +static void acc_request_free(struct usb_request *req, struct usb_ep *ep) +{ + if (req) { + kfree(req->buf); + usb_ep_free_request(ep, req); + } +} + +/* add a request to the tail of a list */ +static void req_put(struct acc_dev *dev, struct list_head *head, + struct usb_request *req) +{ + unsigned long flags; + + spin_lock_irqsave(&dev->lock, flags); + list_add_tail(&req->list, head); + spin_unlock_irqrestore(&dev->lock, flags); +} + +/* remove a request from the head of a list */ +static struct usb_request *req_get(struct acc_dev *dev, struct list_head *head) +{ + unsigned long flags; + struct usb_request *req; + + spin_lock_irqsave(&dev->lock, flags); + if (list_empty(head)) { + req = 0; + } else { + req = list_first_entry(head, struct usb_request, list); + list_del(&req->list); + } + spin_unlock_irqrestore(&dev->lock, flags); + return req; +} + +static void acc_set_disconnected(struct acc_dev *dev) +{ + dev->disconnected = 1; +} + +static void acc_complete_in(struct usb_ep *ep, struct usb_request *req) +{ + struct acc_dev *dev = _acc_dev; + + if (req->status == -ESHUTDOWN) { + pr_debug("acc_complete_in set disconnected"); + acc_set_disconnected(dev); + } + + req_put(dev, &dev->tx_idle, req); + + wake_up(&dev->write_wq); +} + +static void acc_complete_out(struct usb_ep *ep, struct usb_request *req) +{ + struct acc_dev *dev = _acc_dev; + + dev->rx_done = 1; + if (req->status == -ESHUTDOWN) { + pr_debug("acc_complete_out set disconnected"); + acc_set_disconnected(dev); + } + + wake_up(&dev->read_wq); +} + +static void acc_complete_set_string(struct usb_ep *ep, struct usb_request *req) +{ + struct acc_dev *dev = ep->driver_data; + char *string_dest = NULL; + int length = req->actual; + + if (req->status != 0) { + pr_err("acc_complete_set_string, err %d\n", req->status); + return; + } + + switch (dev->string_index) { + case ACCESSORY_STRING_MANUFACTURER: + string_dest = dev->manufacturer; + break; + case ACCESSORY_STRING_MODEL: + string_dest = dev->model; + break; + case ACCESSORY_STRING_DESCRIPTION: + string_dest = dev->description; + break; + case ACCESSORY_STRING_VERSION: + string_dest = dev->version; + break; + case ACCESSORY_STRING_URI: + string_dest = dev->uri; + break; + case ACCESSORY_STRING_SERIAL: + string_dest = dev->serial; + break; + } + if (string_dest) { + unsigned long flags; + + if (length >= ACC_STRING_SIZE) + length = ACC_STRING_SIZE - 1; + + spin_lock_irqsave(&dev->lock, flags); + memcpy(string_dest, req->buf, length); + /* ensure zero termination */ + string_dest[length] = 0; + spin_unlock_irqrestore(&dev->lock, flags); + } else { + pr_err("unknown accessory string index %d\n", + dev->string_index); + } +} + +static void acc_complete_set_hid_report_desc(struct usb_ep *ep, + struct usb_request *req) +{ + struct acc_hid_dev *hid = req->context; + struct acc_dev *dev = hid->dev; + int length = req->actual; + + if (req->status != 0) { + pr_err("acc_complete_set_hid_report_desc, err %d\n", + req->status); + return; + } + + memcpy(hid->report_desc + hid->report_desc_offset, req->buf, length); + hid->report_desc_offset += length; + if (hid->report_desc_offset == hid->report_desc_len) { + /* After we have received the entire report descriptor + * we schedule work to initialize the HID device + */ + schedule_work(&dev->hid_work); + } +} + +static void acc_complete_send_hid_event(struct usb_ep *ep, + struct usb_request *req) +{ + struct acc_hid_dev *hid = req->context; + int length = req->actual; + + if (req->status != 0) { + pr_err("acc_complete_send_hid_event, err %d\n", req->status); + return; + } + + hid_report_raw_event(hid->hid, HID_INPUT_REPORT, req->buf, length, 1); +} + +static int acc_hid_parse(struct hid_device *hid) +{ + struct acc_hid_dev *hdev = hid->driver_data; + + hid_parse_report(hid, hdev->report_desc, hdev->report_desc_len); + return 0; +} + +static int acc_hid_start(struct hid_device *hid) +{ + return 0; +} + +static void acc_hid_stop(struct hid_device *hid) +{ +} + +static int acc_hid_open(struct hid_device *hid) +{ + return 0; +} + +static void acc_hid_close(struct hid_device *hid) +{ +} + +static int acc_hid_raw_request(struct hid_device *hid, unsigned char reportnum, + __u8 *buf, size_t len, unsigned char rtype, int reqtype) +{ + return 0; +} + +static struct hid_ll_driver acc_hid_ll_driver = { + .parse = acc_hid_parse, + .start = acc_hid_start, + .stop = acc_hid_stop, + .open = acc_hid_open, + .close = acc_hid_close, + .raw_request = acc_hid_raw_request, +}; + +static struct acc_hid_dev *acc_hid_new(struct acc_dev *dev, + int id, int desc_len) +{ + struct acc_hid_dev *hdev; + + hdev = kzalloc(sizeof(*hdev), GFP_ATOMIC); + if (!hdev) + return NULL; + hdev->report_desc = kzalloc(desc_len, GFP_ATOMIC); + if (!hdev->report_desc) { + kfree(hdev); + return NULL; + } + hdev->dev = dev; + hdev->id = id; + hdev->report_desc_len = desc_len; + + return hdev; +} + +static struct acc_hid_dev *acc_hid_get(struct list_head *list, int id) +{ + struct acc_hid_dev *hid; + + list_for_each_entry(hid, list, list) { + if (hid->id == id) + return hid; + } + return NULL; +} + +static int acc_register_hid(struct acc_dev *dev, int id, int desc_length) +{ + struct acc_hid_dev *hid; + unsigned long flags; + + /* report descriptor length must be > 0 */ + if (desc_length <= 0) + return -EINVAL; + + spin_lock_irqsave(&dev->lock, flags); + /* replace HID if one already exists with this ID */ + hid = acc_hid_get(&dev->hid_list, id); + if (!hid) + hid = acc_hid_get(&dev->new_hid_list, id); + if (hid) + list_move(&hid->list, &dev->dead_hid_list); + + hid = acc_hid_new(dev, id, desc_length); + if (!hid) { + spin_unlock_irqrestore(&dev->lock, flags); + return -ENOMEM; + } + + list_add(&hid->list, &dev->new_hid_list); + spin_unlock_irqrestore(&dev->lock, flags); + + /* schedule work to register the HID device */ + schedule_work(&dev->hid_work); + return 0; +} + +static int acc_unregister_hid(struct acc_dev *dev, int id) +{ + struct acc_hid_dev *hid; + unsigned long flags; + + spin_lock_irqsave(&dev->lock, flags); + hid = acc_hid_get(&dev->hid_list, id); + if (!hid) + hid = acc_hid_get(&dev->new_hid_list, id); + if (!hid) { + spin_unlock_irqrestore(&dev->lock, flags); + return -EINVAL; + } + + list_move(&hid->list, &dev->dead_hid_list); + spin_unlock_irqrestore(&dev->lock, flags); + + schedule_work(&dev->hid_work); + return 0; +} + +static int create_bulk_endpoints(struct acc_dev *dev, + struct usb_endpoint_descriptor *in_desc, + struct usb_endpoint_descriptor *out_desc) +{ + struct usb_composite_dev *cdev = dev->cdev; + struct usb_request *req; + struct usb_ep *ep; + int i; + + DBG(cdev, "create_bulk_endpoints dev: %p\n", dev); + + ep = usb_ep_autoconfig(cdev->gadget, in_desc); + if (!ep) { + DBG(cdev, "usb_ep_autoconfig for ep_in failed\n"); + return -ENODEV; + } + DBG(cdev, "usb_ep_autoconfig for ep_in got %s\n", ep->name); + ep->driver_data = dev; /* claim the endpoint */ + dev->ep_in = ep; + + ep = usb_ep_autoconfig(cdev->gadget, out_desc); + if (!ep) { + DBG(cdev, "usb_ep_autoconfig for ep_out failed\n"); + return -ENODEV; + } + DBG(cdev, "usb_ep_autoconfig for ep_out got %s\n", ep->name); + ep->driver_data = dev; /* claim the endpoint */ + dev->ep_out = ep; + + /* now allocate requests for our endpoints */ + for (i = 0; i < TX_REQ_MAX; i++) { + req = acc_request_new(dev->ep_in, BULK_BUFFER_SIZE); + if (!req) + goto fail; + req->complete = acc_complete_in; + req_put(dev, &dev->tx_idle, req); + } + for (i = 0; i < RX_REQ_MAX; i++) { + req = acc_request_new(dev->ep_out, BULK_BUFFER_SIZE); + if (!req) + goto fail; + req->complete = acc_complete_out; + dev->rx_req[i] = req; + } + + return 0; + +fail: + pr_err("acc_bind() could not allocate requests\n"); + while ((req = req_get(dev, &dev->tx_idle))) + acc_request_free(req, dev->ep_in); + for (i = 0; i < RX_REQ_MAX; i++) + acc_request_free(dev->rx_req[i], dev->ep_out); + return -1; +} + +static ssize_t acc_read(struct file *fp, char __user *buf, + size_t count, loff_t *pos) +{ + struct acc_dev *dev = fp->private_data; + struct usb_request *req; + ssize_t r = count; + unsigned xfer; + int ret = 0; + + pr_debug("acc_read(%zu)\n", count); + + if (dev->disconnected) { + pr_debug("acc_read disconnected"); + return -ENODEV; + } + + if (count > BULK_BUFFER_SIZE) + count = BULK_BUFFER_SIZE; + + /* we will block until we're online */ + pr_debug("acc_read: waiting for online\n"); + ret = wait_event_interruptible(dev->read_wq, dev->online); + if (ret < 0) { + r = ret; + goto done; + } + + if (dev->rx_done) { + // last req cancelled. try to get it. + req = dev->rx_req[0]; + goto copy_data; + } + +requeue_req: + /* queue a request */ + req = dev->rx_req[0]; + req->length = count; + dev->rx_done = 0; + ret = usb_ep_queue(dev->ep_out, req, GFP_KERNEL); + if (ret < 0) { + r = -EIO; + goto done; + } else { + pr_debug("rx %p queue\n", req); + } + + /* wait for a request to complete */ + ret = wait_event_interruptible(dev->read_wq, dev->rx_done); + if (ret < 0) { + r = ret; + ret = usb_ep_dequeue(dev->ep_out, req); + if (ret != 0) { + // cancel failed. There can be a data already received. + // it will be retrieved in the next read. + pr_debug("acc_read: cancelling failed %d", ret); + } + goto done; + } + +copy_data: + dev->rx_done = 0; + if (dev->online) { + /* If we got a 0-len packet, throw it back and try again. */ + if (req->actual == 0) + goto requeue_req; + + pr_debug("rx %p %u\n", req, req->actual); + xfer = (req->actual < count) ? req->actual : count; + r = xfer; + if (copy_to_user(buf, req->buf, xfer)) + r = -EFAULT; + } else + r = -EIO; + +done: + pr_debug("acc_read returning %zd\n", r); + return r; +} + +static ssize_t acc_write(struct file *fp, const char __user *buf, + size_t count, loff_t *pos) +{ + struct acc_dev *dev = fp->private_data; + struct usb_request *req = 0; + ssize_t r = count; + unsigned xfer; + int ret; + + pr_debug("acc_write(%zu)\n", count); + + if (!dev->online || dev->disconnected) { + pr_debug("acc_write disconnected or not online"); + return -ENODEV; + } + + while (count > 0) { + if (!dev->online) { + pr_debug("acc_write dev->error\n"); + r = -EIO; + break; + } + + /* get an idle tx request to use */ + req = 0; + ret = wait_event_interruptible(dev->write_wq, + ((req = req_get(dev, &dev->tx_idle)) || !dev->online)); + if (!req) { + r = ret; + break; + } + + if (count > BULK_BUFFER_SIZE) { + xfer = BULK_BUFFER_SIZE; + /* ZLP, They will be more TX requests so not yet. */ + req->zero = 0; + } else { + xfer = count; + /* If the data length is a multple of the + * maxpacket size then send a zero length packet(ZLP). + */ + req->zero = ((xfer % dev->ep_in->maxpacket) == 0); + } + if (copy_from_user(req->buf, buf, xfer)) { + r = -EFAULT; + break; + } + + req->length = xfer; + ret = usb_ep_queue(dev->ep_in, req, GFP_KERNEL); + if (ret < 0) { + pr_debug("acc_write: xfer error %d\n", ret); + r = -EIO; + break; + } + + buf += xfer; + count -= xfer; + + /* zero this so we don't try to free it on error exit */ + req = 0; + } + + if (req) + req_put(dev, &dev->tx_idle, req); + + pr_debug("acc_write returning %zd\n", r); + return r; +} + +static long acc_ioctl(struct file *fp, unsigned code, unsigned long value) +{ + struct acc_dev *dev = fp->private_data; + char *src = NULL; + int ret; + + switch (code) { + case ACCESSORY_GET_STRING_MANUFACTURER: + src = dev->manufacturer; + break; + case ACCESSORY_GET_STRING_MODEL: + src = dev->model; + break; + case ACCESSORY_GET_STRING_DESCRIPTION: + src = dev->description; + break; + case ACCESSORY_GET_STRING_VERSION: + src = dev->version; + break; + case ACCESSORY_GET_STRING_URI: + src = dev->uri; + break; + case ACCESSORY_GET_STRING_SERIAL: + src = dev->serial; + break; + case ACCESSORY_IS_START_REQUESTED: + return dev->start_requested; + case ACCESSORY_GET_AUDIO_MODE: + return dev->audio_mode; + } + if (!src) + return -EINVAL; + + ret = strlen(src) + 1; + if (copy_to_user((void __user *)value, src, ret)) + ret = -EFAULT; + return ret; +} + +static int acc_open(struct inode *ip, struct file *fp) +{ + printk(KERN_INFO "acc_open\n"); + if (atomic_xchg(&_acc_dev->open_excl, 1)) + return -EBUSY; + + _acc_dev->disconnected = 0; + fp->private_data = _acc_dev; + return 0; +} + +static int acc_release(struct inode *ip, struct file *fp) +{ + printk(KERN_INFO "acc_release\n"); + + WARN_ON(!atomic_xchg(&_acc_dev->open_excl, 0)); + /* indicate that we are disconnected + * still could be online so don't touch online flag + */ + _acc_dev->disconnected = 1; + return 0; +} + +/* file operations for /dev/usb_accessory */ +static const struct file_operations acc_fops = { + .owner = THIS_MODULE, + .read = acc_read, + .write = acc_write, + .unlocked_ioctl = acc_ioctl, + .open = acc_open, + .release = acc_release, +}; + +static int acc_hid_probe(struct hid_device *hdev, + const struct hid_device_id *id) +{ + int ret; + + ret = hid_parse(hdev); + if (ret) + return ret; + return hid_hw_start(hdev, HID_CONNECT_DEFAULT); +} + +static struct miscdevice acc_device = { + .minor = MISC_DYNAMIC_MINOR, + .name = "usb_accessory", + .fops = &acc_fops, +}; + +static const struct hid_device_id acc_hid_table[] = { + { HID_USB_DEVICE(HID_ANY_ID, HID_ANY_ID) }, + { } +}; + +static struct hid_driver acc_hid_driver = { + .name = "USB accessory", + .id_table = acc_hid_table, + .probe = acc_hid_probe, +}; + +static void acc_complete_setup_noop(struct usb_ep *ep, struct usb_request *req) +{ + /* + * Default no-op function when nothing needs to be done for the + * setup request + */ +} + +int acc_ctrlrequest(struct usb_composite_dev *cdev, + const struct usb_ctrlrequest *ctrl) +{ + struct acc_dev *dev = _acc_dev; + int value = -EOPNOTSUPP; + struct acc_hid_dev *hid; + int offset; + u8 b_requestType = ctrl->bRequestType; + u8 b_request = ctrl->bRequest; + u16 w_index = le16_to_cpu(ctrl->wIndex); + u16 w_value = le16_to_cpu(ctrl->wValue); + u16 w_length = le16_to_cpu(ctrl->wLength); + unsigned long flags; + +/* + printk(KERN_INFO "acc_ctrlrequest " + "%02x.%02x v%04x i%04x l%u\n", + b_requestType, b_request, + w_value, w_index, w_length); +*/ + + if (b_requestType == (USB_DIR_OUT | USB_TYPE_VENDOR)) { + if (b_request == ACCESSORY_START) { + dev->start_requested = 1; + schedule_delayed_work( + &dev->start_work, msecs_to_jiffies(10)); + value = 0; + cdev->req->complete = acc_complete_setup_noop; + } else if (b_request == ACCESSORY_SEND_STRING) { + dev->string_index = w_index; + cdev->gadget->ep0->driver_data = dev; + cdev->req->complete = acc_complete_set_string; + value = w_length; + } else if (b_request == ACCESSORY_SET_AUDIO_MODE && + w_index == 0 && w_length == 0) { + dev->audio_mode = w_value; + cdev->req->complete = acc_complete_setup_noop; + value = 0; + } else if (b_request == ACCESSORY_REGISTER_HID) { + cdev->req->complete = acc_complete_setup_noop; + value = acc_register_hid(dev, w_value, w_index); + } else if (b_request == ACCESSORY_UNREGISTER_HID) { + cdev->req->complete = acc_complete_setup_noop; + value = acc_unregister_hid(dev, w_value); + } else if (b_request == ACCESSORY_SET_HID_REPORT_DESC) { + spin_lock_irqsave(&dev->lock, flags); + hid = acc_hid_get(&dev->new_hid_list, w_value); + spin_unlock_irqrestore(&dev->lock, flags); + if (!hid) { + value = -EINVAL; + goto err; + } + offset = w_index; + if (offset != hid->report_desc_offset + || offset + w_length > hid->report_desc_len) { + value = -EINVAL; + goto err; + } + cdev->req->context = hid; + cdev->req->complete = acc_complete_set_hid_report_desc; + value = w_length; + } else if (b_request == ACCESSORY_SEND_HID_EVENT) { + spin_lock_irqsave(&dev->lock, flags); + hid = acc_hid_get(&dev->hid_list, w_value); + spin_unlock_irqrestore(&dev->lock, flags); + if (!hid) { + value = -EINVAL; + goto err; + } + cdev->req->context = hid; + cdev->req->complete = acc_complete_send_hid_event; + value = w_length; + } + } else if (b_requestType == (USB_DIR_IN | USB_TYPE_VENDOR)) { + if (b_request == ACCESSORY_GET_PROTOCOL) { + *((u16 *)cdev->req->buf) = PROTOCOL_VERSION; + value = sizeof(u16); + cdev->req->complete = acc_complete_setup_noop; + /* clear any string left over from a previous session */ + memset(dev->manufacturer, 0, sizeof(dev->manufacturer)); + memset(dev->model, 0, sizeof(dev->model)); + memset(dev->description, 0, sizeof(dev->description)); + memset(dev->version, 0, sizeof(dev->version)); + memset(dev->uri, 0, sizeof(dev->uri)); + memset(dev->serial, 0, sizeof(dev->serial)); + dev->start_requested = 0; + dev->audio_mode = 0; + } + } + + if (value >= 0) { + cdev->req->zero = 0; + cdev->req->length = value; + value = usb_ep_queue(cdev->gadget->ep0, cdev->req, GFP_ATOMIC); + if (value < 0) + ERROR(cdev, "%s setup response queue error\n", + __func__); + } + +err: + if (value == -EOPNOTSUPP) + VDBG(cdev, + "unknown class-specific control req " + "%02x.%02x v%04x i%04x l%u\n", + ctrl->bRequestType, ctrl->bRequest, + w_value, w_index, w_length); + return value; +} +EXPORT_SYMBOL_GPL(acc_ctrlrequest); + +static int +__acc_function_bind(struct usb_configuration *c, + struct usb_function *f, bool configfs) +{ + struct usb_composite_dev *cdev = c->cdev; + struct acc_dev *dev = func_to_dev(f); + int id; + int ret; + + DBG(cdev, "acc_function_bind dev: %p\n", dev); + + if (configfs) { + if (acc_string_defs[INTERFACE_STRING_INDEX].id == 0) { + ret = usb_string_id(c->cdev); + if (ret < 0) + return ret; + acc_string_defs[INTERFACE_STRING_INDEX].id = ret; + acc_interface_desc.iInterface = ret; + } + dev->cdev = c->cdev; + } + ret = hid_register_driver(&acc_hid_driver); + if (ret) + return ret; + + dev->start_requested = 0; + + /* allocate interface ID(s) */ + id = usb_interface_id(c, f); + if (id < 0) + return id; + acc_interface_desc.bInterfaceNumber = id; + + /* allocate endpoints */ + ret = create_bulk_endpoints(dev, &acc_fullspeed_in_desc, + &acc_fullspeed_out_desc); + if (ret) + return ret; + + /* support high speed hardware */ + if (gadget_is_dualspeed(c->cdev->gadget)) { + acc_highspeed_in_desc.bEndpointAddress = + acc_fullspeed_in_desc.bEndpointAddress; + acc_highspeed_out_desc.bEndpointAddress = + acc_fullspeed_out_desc.bEndpointAddress; + } + + DBG(cdev, "%s speed %s: IN/%s, OUT/%s\n", + gadget_is_dualspeed(c->cdev->gadget) ? "dual" : "full", + f->name, dev->ep_in->name, dev->ep_out->name); + return 0; +} + +static int +acc_function_bind_configfs(struct usb_configuration *c, + struct usb_function *f) { + return __acc_function_bind(c, f, true); +} + +static void +kill_all_hid_devices(struct acc_dev *dev) +{ + struct acc_hid_dev *hid; + struct list_head *entry, *temp; + unsigned long flags; + + /* do nothing if usb accessory device doesn't exist */ + if (!dev) + return; + + spin_lock_irqsave(&dev->lock, flags); + list_for_each_safe(entry, temp, &dev->hid_list) { + hid = list_entry(entry, struct acc_hid_dev, list); + list_del(&hid->list); + list_add(&hid->list, &dev->dead_hid_list); + } + list_for_each_safe(entry, temp, &dev->new_hid_list) { + hid = list_entry(entry, struct acc_hid_dev, list); + list_del(&hid->list); + list_add(&hid->list, &dev->dead_hid_list); + } + spin_unlock_irqrestore(&dev->lock, flags); + + schedule_work(&dev->hid_work); +} + +static void +acc_hid_unbind(struct acc_dev *dev) +{ + hid_unregister_driver(&acc_hid_driver); + kill_all_hid_devices(dev); +} + +static void +acc_function_unbind(struct usb_configuration *c, struct usb_function *f) +{ + struct acc_dev *dev = func_to_dev(f); + struct usb_request *req; + int i; + + dev->online = 0; /* clear online flag */ + wake_up(&dev->read_wq); /* unblock reads on closure */ + wake_up(&dev->write_wq); /* likewise for writes */ + + while ((req = req_get(dev, &dev->tx_idle))) + acc_request_free(req, dev->ep_in); + for (i = 0; i < RX_REQ_MAX; i++) + acc_request_free(dev->rx_req[i], dev->ep_out); + + acc_hid_unbind(dev); +} + +static void acc_start_work(struct work_struct *data) +{ + char *envp[2] = { "ACCESSORY=START", NULL }; + + kobject_uevent_env(&acc_device.this_device->kobj, KOBJ_CHANGE, envp); +} + +static int acc_hid_init(struct acc_hid_dev *hdev) +{ + struct hid_device *hid; + int ret; + + hid = hid_allocate_device(); + if (IS_ERR(hid)) + return PTR_ERR(hid); + + hid->ll_driver = &acc_hid_ll_driver; + hid->dev.parent = acc_device.this_device; + + hid->bus = BUS_USB; + hid->vendor = HID_ANY_ID; + hid->product = HID_ANY_ID; + hid->driver_data = hdev; + ret = hid_add_device(hid); + if (ret) { + pr_err("can't add hid device: %d\n", ret); + hid_destroy_device(hid); + return ret; + } + + hdev->hid = hid; + return 0; +} + +static void acc_hid_delete(struct acc_hid_dev *hid) +{ + kfree(hid->report_desc); + kfree(hid); +} + +static void acc_hid_work(struct work_struct *data) +{ + struct acc_dev *dev = _acc_dev; + struct list_head *entry, *temp; + struct acc_hid_dev *hid; + struct list_head new_list, dead_list; + unsigned long flags; + + INIT_LIST_HEAD(&new_list); + + spin_lock_irqsave(&dev->lock, flags); + + /* copy hids that are ready for initialization to new_list */ + list_for_each_safe(entry, temp, &dev->new_hid_list) { + hid = list_entry(entry, struct acc_hid_dev, list); + if (hid->report_desc_offset == hid->report_desc_len) + list_move(&hid->list, &new_list); + } + + if (list_empty(&dev->dead_hid_list)) { + INIT_LIST_HEAD(&dead_list); + } else { + /* move all of dev->dead_hid_list to dead_list */ + dead_list.prev = dev->dead_hid_list.prev; + dead_list.next = dev->dead_hid_list.next; + dead_list.next->prev = &dead_list; + dead_list.prev->next = &dead_list; + INIT_LIST_HEAD(&dev->dead_hid_list); + } + + spin_unlock_irqrestore(&dev->lock, flags); + + /* register new HID devices */ + list_for_each_safe(entry, temp, &new_list) { + hid = list_entry(entry, struct acc_hid_dev, list); + if (acc_hid_init(hid)) { + pr_err("can't add HID device %p\n", hid); + acc_hid_delete(hid); + } else { + spin_lock_irqsave(&dev->lock, flags); + list_move(&hid->list, &dev->hid_list); + spin_unlock_irqrestore(&dev->lock, flags); + } + } + + /* remove dead HID devices */ + list_for_each_safe(entry, temp, &dead_list) { + hid = list_entry(entry, struct acc_hid_dev, list); + list_del(&hid->list); + if (hid->hid) + hid_destroy_device(hid->hid); + acc_hid_delete(hid); + } +} + +static int acc_function_set_alt(struct usb_function *f, + unsigned intf, unsigned alt) +{ + struct acc_dev *dev = func_to_dev(f); + struct usb_composite_dev *cdev = f->config->cdev; + int ret; + + DBG(cdev, "acc_function_set_alt intf: %d alt: %d\n", intf, alt); + + ret = config_ep_by_speed(cdev->gadget, f, dev->ep_in); + if (ret) + return ret; + + ret = usb_ep_enable(dev->ep_in); + if (ret) + return ret; + + ret = config_ep_by_speed(cdev->gadget, f, dev->ep_out); + if (ret) + return ret; + + ret = usb_ep_enable(dev->ep_out); + if (ret) { + usb_ep_disable(dev->ep_in); + return ret; + } + + dev->online = 1; + dev->disconnected = 0; /* if online then not disconnected */ + + /* readers may be blocked waiting for us to go online */ + wake_up(&dev->read_wq); + return 0; +} + +static void acc_function_disable(struct usb_function *f) +{ + struct acc_dev *dev = func_to_dev(f); + struct usb_composite_dev *cdev = dev->cdev; + + DBG(cdev, "acc_function_disable\n"); + acc_set_disconnected(dev); /* this now only sets disconnected */ + dev->online = 0; /* so now need to clear online flag here too */ + usb_ep_disable(dev->ep_in); + usb_ep_disable(dev->ep_out); + + /* readers may be blocked waiting for us to go online */ + wake_up(&dev->read_wq); + + VDBG(cdev, "%s disabled\n", dev->function.name); +} + +static int acc_setup(void) +{ + struct acc_dev *dev; + int ret; + + dev = kzalloc(sizeof(*dev), GFP_KERNEL); + if (!dev) + return -ENOMEM; + + spin_lock_init(&dev->lock); + init_waitqueue_head(&dev->read_wq); + init_waitqueue_head(&dev->write_wq); + atomic_set(&dev->open_excl, 0); + INIT_LIST_HEAD(&dev->tx_idle); + INIT_LIST_HEAD(&dev->hid_list); + INIT_LIST_HEAD(&dev->new_hid_list); + INIT_LIST_HEAD(&dev->dead_hid_list); + INIT_DELAYED_WORK(&dev->start_work, acc_start_work); + INIT_WORK(&dev->hid_work, acc_hid_work); + + /* _acc_dev must be set before calling usb_gadget_register_driver */ + _acc_dev = dev; + + ret = misc_register(&acc_device); + if (ret) + goto err; + + return 0; + +err: + kfree(dev); + pr_err("USB accessory gadget driver failed to initialize\n"); + return ret; +} + +void acc_disconnect(void) +{ + /* unregister all HID devices if USB is disconnected */ + kill_all_hid_devices(_acc_dev); +} +EXPORT_SYMBOL_GPL(acc_disconnect); + +static void acc_cleanup(void) +{ + misc_deregister(&acc_device); + kfree(_acc_dev); + _acc_dev = NULL; +} +static struct acc_instance *to_acc_instance(struct config_item *item) +{ + return container_of(to_config_group(item), struct acc_instance, + func_inst.group); +} + +static void acc_attr_release(struct config_item *item) +{ + struct acc_instance *fi_acc = to_acc_instance(item); + + usb_put_function_instance(&fi_acc->func_inst); +} + +static struct configfs_item_operations acc_item_ops = { + .release = acc_attr_release, +}; + +static struct config_item_type acc_func_type = { + .ct_item_ops = &acc_item_ops, + .ct_owner = THIS_MODULE, +}; + +static struct acc_instance *to_fi_acc(struct usb_function_instance *fi) +{ + return container_of(fi, struct acc_instance, func_inst); +} + +static int acc_set_inst_name(struct usb_function_instance *fi, const char *name) +{ + struct acc_instance *fi_acc; + char *ptr; + int name_len; + + name_len = strlen(name) + 1; + if (name_len > MAX_INST_NAME_LEN) + return -ENAMETOOLONG; + + ptr = kstrndup(name, name_len, GFP_KERNEL); + if (!ptr) + return -ENOMEM; + + fi_acc = to_fi_acc(fi); + fi_acc->name = ptr; + return 0; +} + +static void acc_free_inst(struct usb_function_instance *fi) +{ + struct acc_instance *fi_acc; + + fi_acc = to_fi_acc(fi); + kfree(fi_acc->name); + acc_cleanup(); +} + +static struct usb_function_instance *acc_alloc_inst(void) +{ + struct acc_instance *fi_acc; + struct acc_dev *dev; + int err; + + fi_acc = kzalloc(sizeof(*fi_acc), GFP_KERNEL); + if (!fi_acc) + return ERR_PTR(-ENOMEM); + fi_acc->func_inst.set_inst_name = acc_set_inst_name; + fi_acc->func_inst.free_func_inst = acc_free_inst; + + err = acc_setup(); + if (err) { + kfree(fi_acc); + pr_err("Error setting ACCESSORY\n"); + return ERR_PTR(err); + } + + config_group_init_type_name(&fi_acc->func_inst.group, + "", &acc_func_type); + dev = _acc_dev; + return &fi_acc->func_inst; +} + +static void acc_free(struct usb_function *f) +{ +/*NO-OP: no function specific resource allocation in mtp_alloc*/ +} + +int acc_ctrlrequest_configfs(struct usb_function *f, + const struct usb_ctrlrequest *ctrl) { + if (f->config != NULL && f->config->cdev != NULL) + return acc_ctrlrequest(f->config->cdev, ctrl); + else + return -1; +} + +static struct usb_function *acc_alloc(struct usb_function_instance *fi) +{ + struct acc_dev *dev = _acc_dev; + + pr_info("acc_alloc\n"); + + dev->function.name = "accessory"; + dev->function.strings = acc_strings, + dev->function.fs_descriptors = fs_acc_descs; + dev->function.hs_descriptors = hs_acc_descs; + dev->function.bind = acc_function_bind_configfs; + dev->function.unbind = acc_function_unbind; + dev->function.set_alt = acc_function_set_alt; + dev->function.disable = acc_function_disable; + dev->function.free_func = acc_free; + dev->function.setup = acc_ctrlrequest_configfs; + + return &dev->function; +} +DECLARE_USB_FUNCTION_INIT(accessory, acc_alloc_inst, acc_alloc); +MODULE_LICENSE("GPL"); diff --git a/drivers/usb/gadget/function/f_audio_source.c b/drivers/usb/gadget/function/f_audio_source.c new file mode 100644 index 000000000000..8124af33b738 --- /dev/null +++ b/drivers/usb/gadget/function/f_audio_source.c @@ -0,0 +1,1071 @@ +/* + * Gadget Function Driver for USB audio source device + * + * Copyright (C) 2012 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/device.h> +#include <linux/usb/audio.h> +#include <linux/wait.h> +#include <linux/pm_qos.h> +#include <sound/core.h> +#include <sound/initval.h> +#include <sound/pcm.h> + +#include <linux/usb.h> +#include <linux/usb_usual.h> +#include <linux/usb/ch9.h> +#include <linux/configfs.h> +#include <linux/usb/composite.h> +#include <linux/module.h> +#include <linux/moduleparam.h> +#define SAMPLE_RATE 44100 +#define FRAMES_PER_MSEC (SAMPLE_RATE / 1000) + +#define IN_EP_MAX_PACKET_SIZE 256 + +/* Number of requests to allocate */ +#define IN_EP_REQ_COUNT 4 + +#define AUDIO_AC_INTERFACE 0 +#define AUDIO_AS_INTERFACE 1 +#define AUDIO_NUM_INTERFACES 2 +#define MAX_INST_NAME_LEN 40 + +/* B.3.1 Standard AC Interface Descriptor */ +static struct usb_interface_descriptor ac_interface_desc = { + .bLength = USB_DT_INTERFACE_SIZE, + .bDescriptorType = USB_DT_INTERFACE, + .bNumEndpoints = 0, + .bInterfaceClass = USB_CLASS_AUDIO, + .bInterfaceSubClass = USB_SUBCLASS_AUDIOCONTROL, +}; + +DECLARE_UAC_AC_HEADER_DESCRIPTOR(2); + +#define UAC_DT_AC_HEADER_LENGTH UAC_DT_AC_HEADER_SIZE(AUDIO_NUM_INTERFACES) +/* 1 input terminal, 1 output terminal and 1 feature unit */ +#define UAC_DT_TOTAL_LENGTH (UAC_DT_AC_HEADER_LENGTH \ + + UAC_DT_INPUT_TERMINAL_SIZE + UAC_DT_OUTPUT_TERMINAL_SIZE \ + + UAC_DT_FEATURE_UNIT_SIZE(0)) +/* B.3.2 Class-Specific AC Interface Descriptor */ +static struct uac1_ac_header_descriptor_2 ac_header_desc = { + .bLength = UAC_DT_AC_HEADER_LENGTH, + .bDescriptorType = USB_DT_CS_INTERFACE, + .bDescriptorSubtype = UAC_HEADER, + .bcdADC = __constant_cpu_to_le16(0x0100), + .wTotalLength = __constant_cpu_to_le16(UAC_DT_TOTAL_LENGTH), + .bInCollection = AUDIO_NUM_INTERFACES, + .baInterfaceNr = { + [0] = AUDIO_AC_INTERFACE, + [1] = AUDIO_AS_INTERFACE, + } +}; + +#define INPUT_TERMINAL_ID 1 +static struct uac_input_terminal_descriptor input_terminal_desc = { + .bLength = UAC_DT_INPUT_TERMINAL_SIZE, + .bDescriptorType = USB_DT_CS_INTERFACE, + .bDescriptorSubtype = UAC_INPUT_TERMINAL, + .bTerminalID = INPUT_TERMINAL_ID, + .wTerminalType = UAC_INPUT_TERMINAL_MICROPHONE, + .bAssocTerminal = 0, + .wChannelConfig = 0x3, +}; + +DECLARE_UAC_FEATURE_UNIT_DESCRIPTOR(0); + +#define FEATURE_UNIT_ID 2 +static struct uac_feature_unit_descriptor_0 feature_unit_desc = { + .bLength = UAC_DT_FEATURE_UNIT_SIZE(0), + .bDescriptorType = USB_DT_CS_INTERFACE, + .bDescriptorSubtype = UAC_FEATURE_UNIT, + .bUnitID = FEATURE_UNIT_ID, + .bSourceID = INPUT_TERMINAL_ID, + .bControlSize = 2, +}; + +#define OUTPUT_TERMINAL_ID 3 +static struct uac1_output_terminal_descriptor output_terminal_desc = { + .bLength = UAC_DT_OUTPUT_TERMINAL_SIZE, + .bDescriptorType = USB_DT_CS_INTERFACE, + .bDescriptorSubtype = UAC_OUTPUT_TERMINAL, + .bTerminalID = OUTPUT_TERMINAL_ID, + .wTerminalType = UAC_TERMINAL_STREAMING, + .bAssocTerminal = FEATURE_UNIT_ID, + .bSourceID = FEATURE_UNIT_ID, +}; + +/* B.4.1 Standard AS Interface Descriptor */ +static struct usb_interface_descriptor as_interface_alt_0_desc = { + .bLength = USB_DT_INTERFACE_SIZE, + .bDescriptorType = USB_DT_INTERFACE, + .bAlternateSetting = 0, + .bNumEndpoints = 0, + .bInterfaceClass = USB_CLASS_AUDIO, + .bInterfaceSubClass = USB_SUBCLASS_AUDIOSTREAMING, +}; + +static struct usb_interface_descriptor as_interface_alt_1_desc = { + .bLength = USB_DT_INTERFACE_SIZE, + .bDescriptorType = USB_DT_INTERFACE, + .bAlternateSetting = 1, + .bNumEndpoints = 1, + .bInterfaceClass = USB_CLASS_AUDIO, + .bInterfaceSubClass = USB_SUBCLASS_AUDIOSTREAMING, +}; + +/* B.4.2 Class-Specific AS Interface Descriptor */ +static struct uac1_as_header_descriptor as_header_desc = { + .bLength = UAC_DT_AS_HEADER_SIZE, + .bDescriptorType = USB_DT_CS_INTERFACE, + .bDescriptorSubtype = UAC_AS_GENERAL, + .bTerminalLink = INPUT_TERMINAL_ID, + .bDelay = 1, + .wFormatTag = UAC_FORMAT_TYPE_I_PCM, +}; + +DECLARE_UAC_FORMAT_TYPE_I_DISCRETE_DESC(1); + +static struct uac_format_type_i_discrete_descriptor_1 as_type_i_desc = { + .bLength = UAC_FORMAT_TYPE_I_DISCRETE_DESC_SIZE(1), + .bDescriptorType = USB_DT_CS_INTERFACE, + .bDescriptorSubtype = UAC_FORMAT_TYPE, + .bFormatType = UAC_FORMAT_TYPE_I, + .bSubframeSize = 2, + .bBitResolution = 16, + .bSamFreqType = 1, +}; + +/* Standard ISO IN Endpoint Descriptor for highspeed */ +static struct usb_endpoint_descriptor hs_as_in_ep_desc = { + .bLength = USB_DT_ENDPOINT_AUDIO_SIZE, + .bDescriptorType = USB_DT_ENDPOINT, + .bEndpointAddress = USB_DIR_IN, + .bmAttributes = USB_ENDPOINT_SYNC_SYNC + | USB_ENDPOINT_XFER_ISOC, + .wMaxPacketSize = __constant_cpu_to_le16(IN_EP_MAX_PACKET_SIZE), + .bInterval = 4, /* poll 1 per millisecond */ +}; + +/* Standard ISO IN Endpoint Descriptor for highspeed */ +static struct usb_endpoint_descriptor fs_as_in_ep_desc = { + .bLength = USB_DT_ENDPOINT_AUDIO_SIZE, + .bDescriptorType = USB_DT_ENDPOINT, + .bEndpointAddress = USB_DIR_IN, + .bmAttributes = USB_ENDPOINT_SYNC_SYNC + | USB_ENDPOINT_XFER_ISOC, + .wMaxPacketSize = __constant_cpu_to_le16(IN_EP_MAX_PACKET_SIZE), + .bInterval = 1, /* poll 1 per millisecond */ +}; + +/* Class-specific AS ISO OUT Endpoint Descriptor */ +static struct uac_iso_endpoint_descriptor as_iso_in_desc = { + .bLength = UAC_ISO_ENDPOINT_DESC_SIZE, + .bDescriptorType = USB_DT_CS_ENDPOINT, + .bDescriptorSubtype = UAC_EP_GENERAL, + .bmAttributes = 1, + .bLockDelayUnits = 1, + .wLockDelay = __constant_cpu_to_le16(1), +}; + +static struct usb_descriptor_header *hs_audio_desc[] = { + (struct usb_descriptor_header *)&ac_interface_desc, + (struct usb_descriptor_header *)&ac_header_desc, + + (struct usb_descriptor_header *)&input_terminal_desc, + (struct usb_descriptor_header *)&output_terminal_desc, + (struct usb_descriptor_header *)&feature_unit_desc, + + (struct usb_descriptor_header *)&as_interface_alt_0_desc, + (struct usb_descriptor_header *)&as_interface_alt_1_desc, + (struct usb_descriptor_header *)&as_header_desc, + + (struct usb_descriptor_header *)&as_type_i_desc, + + (struct usb_descriptor_header *)&hs_as_in_ep_desc, + (struct usb_descriptor_header *)&as_iso_in_desc, + NULL, +}; + +static struct usb_descriptor_header *fs_audio_desc[] = { + (struct usb_descriptor_header *)&ac_interface_desc, + (struct usb_descriptor_header *)&ac_header_desc, + + (struct usb_descriptor_header *)&input_terminal_desc, + (struct usb_descriptor_header *)&output_terminal_desc, + (struct usb_descriptor_header *)&feature_unit_desc, + + (struct usb_descriptor_header *)&as_interface_alt_0_desc, + (struct usb_descriptor_header *)&as_interface_alt_1_desc, + (struct usb_descriptor_header *)&as_header_desc, + + (struct usb_descriptor_header *)&as_type_i_desc, + + (struct usb_descriptor_header *)&fs_as_in_ep_desc, + (struct usb_descriptor_header *)&as_iso_in_desc, + NULL, +}; + +static struct snd_pcm_hardware audio_hw_info = { + .info = SNDRV_PCM_INFO_MMAP | + SNDRV_PCM_INFO_MMAP_VALID | + SNDRV_PCM_INFO_BATCH | + SNDRV_PCM_INFO_INTERLEAVED | + SNDRV_PCM_INFO_BLOCK_TRANSFER, + + .formats = SNDRV_PCM_FMTBIT_S16_LE, + .channels_min = 2, + .channels_max = 2, + .rate_min = SAMPLE_RATE, + .rate_max = SAMPLE_RATE, + + .buffer_bytes_max = 1024 * 1024, + .period_bytes_min = 64, + .period_bytes_max = 512 * 1024, + .periods_min = 2, + .periods_max = 1024, +}; + +/*-------------------------------------------------------------------------*/ + +struct audio_source_config { + int card; + int device; +}; + +struct audio_dev { + struct usb_function func; + struct snd_card *card; + struct snd_pcm *pcm; + struct snd_pcm_substream *substream; + + struct list_head idle_reqs; + struct usb_ep *in_ep; + + spinlock_t lock; + + /* beginning, end and current position in our buffer */ + void *buffer_start; + void *buffer_end; + void *buffer_pos; + + /* byte size of a "period" */ + unsigned int period; + /* bytes sent since last call to snd_pcm_period_elapsed */ + unsigned int period_offset; + /* time we started playing */ + ktime_t start_time; + /* number of frames sent since start_time */ + s64 frames_sent; + struct audio_source_config *config; + /* for creating and issuing QoS requests */ + struct pm_qos_request pm_qos; +}; + +static inline struct audio_dev *func_to_audio(struct usb_function *f) +{ + return container_of(f, struct audio_dev, func); +} + +/*-------------------------------------------------------------------------*/ + +struct audio_source_instance { + struct usb_function_instance func_inst; + const char *name; + struct audio_source_config *config; + struct device *audio_device; +}; + +static void audio_source_attr_release(struct config_item *item); + +static struct configfs_item_operations audio_source_item_ops = { + .release = audio_source_attr_release, +}; + +static struct config_item_type audio_source_func_type = { + .ct_item_ops = &audio_source_item_ops, + .ct_owner = THIS_MODULE, +}; + +static ssize_t audio_source_pcm_show(struct device *dev, + struct device_attribute *attr, char *buf); + +static DEVICE_ATTR(pcm, S_IRUGO, audio_source_pcm_show, NULL); + +static struct device_attribute *audio_source_function_attributes[] = { + &dev_attr_pcm, + NULL +}; + +/*--------------------------------------------------------------------------*/ + +static struct usb_request *audio_request_new(struct usb_ep *ep, int buffer_size) +{ + struct usb_request *req = usb_ep_alloc_request(ep, GFP_KERNEL); + + if (!req) + return NULL; + + req->buf = kmalloc(buffer_size, GFP_KERNEL); + if (!req->buf) { + usb_ep_free_request(ep, req); + return NULL; + } + req->length = buffer_size; + return req; +} + +static void audio_request_free(struct usb_request *req, struct usb_ep *ep) +{ + if (req) { + kfree(req->buf); + usb_ep_free_request(ep, req); + } +} + +static void audio_req_put(struct audio_dev *audio, struct usb_request *req) +{ + unsigned long flags; + + spin_lock_irqsave(&audio->lock, flags); + list_add_tail(&req->list, &audio->idle_reqs); + spin_unlock_irqrestore(&audio->lock, flags); +} + +static struct usb_request *audio_req_get(struct audio_dev *audio) +{ + unsigned long flags; + struct usb_request *req; + + spin_lock_irqsave(&audio->lock, flags); + if (list_empty(&audio->idle_reqs)) { + req = 0; + } else { + req = list_first_entry(&audio->idle_reqs, struct usb_request, + list); + list_del(&req->list); + } + spin_unlock_irqrestore(&audio->lock, flags); + return req; +} + +/* send the appropriate number of packets to match our bitrate */ +static void audio_send(struct audio_dev *audio) +{ + struct snd_pcm_runtime *runtime; + struct usb_request *req; + int length, length1, length2, ret; + s64 msecs; + s64 frames; + ktime_t now; + + /* audio->substream will be null if we have been closed */ + if (!audio->substream) + return; + /* audio->buffer_pos will be null if we have been stopped */ + if (!audio->buffer_pos) + return; + + runtime = audio->substream->runtime; + + /* compute number of frames to send */ + now = ktime_get(); + msecs = div_s64((ktime_to_ns(now) - ktime_to_ns(audio->start_time)), + 1000000); + frames = div_s64((msecs * SAMPLE_RATE), 1000); + + /* Readjust our frames_sent if we fall too far behind. + * If we get too far behind it is better to drop some frames than + * to keep sending data too fast in an attempt to catch up. + */ + if (frames - audio->frames_sent > 10 * FRAMES_PER_MSEC) + audio->frames_sent = frames - FRAMES_PER_MSEC; + + frames -= audio->frames_sent; + + /* We need to send something to keep the pipeline going */ + if (frames <= 0) + frames = FRAMES_PER_MSEC; + + while (frames > 0) { + req = audio_req_get(audio); + if (!req) + break; + + length = frames_to_bytes(runtime, frames); + if (length > IN_EP_MAX_PACKET_SIZE) + length = IN_EP_MAX_PACKET_SIZE; + + if (audio->buffer_pos + length > audio->buffer_end) + length1 = audio->buffer_end - audio->buffer_pos; + else + length1 = length; + memcpy(req->buf, audio->buffer_pos, length1); + if (length1 < length) { + /* Wrap around and copy remaining length + * at beginning of buffer. + */ + length2 = length - length1; + memcpy(req->buf + length1, audio->buffer_start, + length2); + audio->buffer_pos = audio->buffer_start + length2; + } else { + audio->buffer_pos += length1; + if (audio->buffer_pos >= audio->buffer_end) + audio->buffer_pos = audio->buffer_start; + } + + req->length = length; + ret = usb_ep_queue(audio->in_ep, req, GFP_ATOMIC); + if (ret < 0) { + pr_err("usb_ep_queue failed ret: %d\n", ret); + audio_req_put(audio, req); + break; + } + + frames -= bytes_to_frames(runtime, length); + audio->frames_sent += bytes_to_frames(runtime, length); + } +} + +static void audio_control_complete(struct usb_ep *ep, struct usb_request *req) +{ + /* nothing to do here */ +} + +static void audio_data_complete(struct usb_ep *ep, struct usb_request *req) +{ + struct audio_dev *audio = req->context; + + pr_debug("audio_data_complete req->status %d req->actual %d\n", + req->status, req->actual); + + audio_req_put(audio, req); + + if (!audio->buffer_start || req->status) + return; + + audio->period_offset += req->actual; + if (audio->period_offset >= audio->period) { + snd_pcm_period_elapsed(audio->substream); + audio->period_offset = 0; + } + audio_send(audio); +} + +static int audio_set_endpoint_req(struct usb_function *f, + const struct usb_ctrlrequest *ctrl) +{ + int value = -EOPNOTSUPP; + u16 ep = le16_to_cpu(ctrl->wIndex); + u16 len = le16_to_cpu(ctrl->wLength); + u16 w_value = le16_to_cpu(ctrl->wValue); + + pr_debug("bRequest 0x%x, w_value 0x%04x, len %d, endpoint %d\n", + ctrl->bRequest, w_value, len, ep); + + switch (ctrl->bRequest) { + case UAC_SET_CUR: + case UAC_SET_MIN: + case UAC_SET_MAX: + case UAC_SET_RES: + value = len; + break; + default: + break; + } + + return value; +} + +static int audio_get_endpoint_req(struct usb_function *f, + const struct usb_ctrlrequest *ctrl) +{ + struct usb_composite_dev *cdev = f->config->cdev; + int value = -EOPNOTSUPP; + u8 ep = ((le16_to_cpu(ctrl->wIndex) >> 8) & 0xFF); + u16 len = le16_to_cpu(ctrl->wLength); + u16 w_value = le16_to_cpu(ctrl->wValue); + u8 *buf = cdev->req->buf; + + pr_debug("bRequest 0x%x, w_value 0x%04x, len %d, endpoint %d\n", + ctrl->bRequest, w_value, len, ep); + + if (w_value == UAC_EP_CS_ATTR_SAMPLE_RATE << 8) { + switch (ctrl->bRequest) { + case UAC_GET_CUR: + case UAC_GET_MIN: + case UAC_GET_MAX: + case UAC_GET_RES: + /* return our sample rate */ + buf[0] = (u8)SAMPLE_RATE; + buf[1] = (u8)(SAMPLE_RATE >> 8); + buf[2] = (u8)(SAMPLE_RATE >> 16); + value = 3; + break; + default: + break; + } + } + + return value; +} + +static int +audio_setup(struct usb_function *f, const struct usb_ctrlrequest *ctrl) +{ + struct usb_composite_dev *cdev = f->config->cdev; + struct usb_request *req = cdev->req; + int value = -EOPNOTSUPP; + u16 w_index = le16_to_cpu(ctrl->wIndex); + u16 w_value = le16_to_cpu(ctrl->wValue); + u16 w_length = le16_to_cpu(ctrl->wLength); + + /* composite driver infrastructure handles everything; interface + * activation uses set_alt(). + */ + switch (ctrl->bRequestType) { + case USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_ENDPOINT: + value = audio_set_endpoint_req(f, ctrl); + break; + + case USB_DIR_IN | USB_TYPE_CLASS | USB_RECIP_ENDPOINT: + value = audio_get_endpoint_req(f, ctrl); + break; + } + + /* respond with data transfer or status phase? */ + if (value >= 0) { + pr_debug("audio req%02x.%02x v%04x i%04x l%d\n", + ctrl->bRequestType, ctrl->bRequest, + w_value, w_index, w_length); + req->zero = 0; + req->length = value; + req->complete = audio_control_complete; + value = usb_ep_queue(cdev->gadget->ep0, req, GFP_ATOMIC); + if (value < 0) + pr_err("audio response on err %d\n", value); + } + + /* device either stalls (value < 0) or reports success */ + return value; +} + +static int audio_set_alt(struct usb_function *f, unsigned intf, unsigned alt) +{ + struct audio_dev *audio = func_to_audio(f); + struct usb_composite_dev *cdev = f->config->cdev; + int ret; + + pr_debug("audio_set_alt intf %d, alt %d\n", intf, alt); + + ret = config_ep_by_speed(cdev->gadget, f, audio->in_ep); + if (ret) + return ret; + + usb_ep_enable(audio->in_ep); + return 0; +} + +static void audio_disable(struct usb_function *f) +{ + struct audio_dev *audio = func_to_audio(f); + + pr_debug("audio_disable\n"); + usb_ep_disable(audio->in_ep); +} + +static void audio_free_func(struct usb_function *f) +{ + /* no-op */ +} + +/*-------------------------------------------------------------------------*/ + +static void audio_build_desc(struct audio_dev *audio) +{ + u8 *sam_freq; + int rate; + + /* Set channel numbers */ + input_terminal_desc.bNrChannels = 2; + as_type_i_desc.bNrChannels = 2; + + /* Set sample rates */ + rate = SAMPLE_RATE; + sam_freq = as_type_i_desc.tSamFreq[0]; + memcpy(sam_freq, &rate, 3); +} + + +static int snd_card_setup(struct usb_configuration *c, + struct audio_source_config *config); +static struct audio_source_instance *to_fi_audio_source( + const struct usb_function_instance *fi); + + +/* audio function driver setup/binding */ +static int +audio_bind(struct usb_configuration *c, struct usb_function *f) +{ + struct usb_composite_dev *cdev = c->cdev; + struct audio_dev *audio = func_to_audio(f); + int status; + struct usb_ep *ep; + struct usb_request *req; + int i; + int err; + + if (IS_ENABLED(CONFIG_USB_CONFIGFS)) { + struct audio_source_instance *fi_audio = + to_fi_audio_source(f->fi); + struct audio_source_config *config = + fi_audio->config; + + err = snd_card_setup(c, config); + if (err) + return err; + } + + audio_build_desc(audio); + + /* allocate instance-specific interface IDs, and patch descriptors */ + status = usb_interface_id(c, f); + if (status < 0) + goto fail; + ac_interface_desc.bInterfaceNumber = status; + + /* AUDIO_AC_INTERFACE */ + ac_header_desc.baInterfaceNr[0] = status; + + status = usb_interface_id(c, f); + if (status < 0) + goto fail; + as_interface_alt_0_desc.bInterfaceNumber = status; + as_interface_alt_1_desc.bInterfaceNumber = status; + + /* AUDIO_AS_INTERFACE */ + ac_header_desc.baInterfaceNr[1] = status; + + status = -ENODEV; + + /* allocate our endpoint */ + ep = usb_ep_autoconfig(cdev->gadget, &fs_as_in_ep_desc); + if (!ep) + goto fail; + audio->in_ep = ep; + ep->driver_data = audio; /* claim */ + + if (gadget_is_dualspeed(c->cdev->gadget)) + hs_as_in_ep_desc.bEndpointAddress = + fs_as_in_ep_desc.bEndpointAddress; + + f->fs_descriptors = fs_audio_desc; + f->hs_descriptors = hs_audio_desc; + + for (i = 0, status = 0; i < IN_EP_REQ_COUNT && status == 0; i++) { + req = audio_request_new(ep, IN_EP_MAX_PACKET_SIZE); + if (req) { + req->context = audio; + req->complete = audio_data_complete; + audio_req_put(audio, req); + } else + status = -ENOMEM; + } + +fail: + return status; +} + +static void +audio_unbind(struct usb_configuration *c, struct usb_function *f) +{ + struct audio_dev *audio = func_to_audio(f); + struct usb_request *req; + + while ((req = audio_req_get(audio))) + audio_request_free(req, audio->in_ep); + + snd_card_free_when_closed(audio->card); + audio->card = NULL; + audio->pcm = NULL; + audio->substream = NULL; + audio->in_ep = NULL; + + if (IS_ENABLED(CONFIG_USB_CONFIGFS)) { + struct audio_source_instance *fi_audio = + to_fi_audio_source(f->fi); + struct audio_source_config *config = + fi_audio->config; + + config->card = -1; + config->device = -1; + } +} + +static void audio_pcm_playback_start(struct audio_dev *audio) +{ + audio->start_time = ktime_get(); + audio->frames_sent = 0; + audio_send(audio); +} + +static void audio_pcm_playback_stop(struct audio_dev *audio) +{ + unsigned long flags; + + spin_lock_irqsave(&audio->lock, flags); + audio->buffer_start = 0; + audio->buffer_end = 0; + audio->buffer_pos = 0; + spin_unlock_irqrestore(&audio->lock, flags); +} + +static int audio_pcm_open(struct snd_pcm_substream *substream) +{ + struct snd_pcm_runtime *runtime = substream->runtime; + struct audio_dev *audio = substream->private_data; + + runtime->private_data = audio; + runtime->hw = audio_hw_info; + snd_pcm_limit_hw_rates(runtime); + runtime->hw.channels_max = 2; + + audio->substream = substream; + + /* Add the QoS request and set the latency to 0 */ + pm_qos_add_request(&audio->pm_qos, PM_QOS_CPU_DMA_LATENCY, 0); + + return 0; +} + +static int audio_pcm_close(struct snd_pcm_substream *substream) +{ + struct audio_dev *audio = substream->private_data; + unsigned long flags; + + spin_lock_irqsave(&audio->lock, flags); + + /* Remove the QoS request */ + pm_qos_remove_request(&audio->pm_qos); + + audio->substream = NULL; + spin_unlock_irqrestore(&audio->lock, flags); + + return 0; +} + +static int audio_pcm_hw_params(struct snd_pcm_substream *substream, + struct snd_pcm_hw_params *params) +{ + unsigned int channels = params_channels(params); + unsigned int rate = params_rate(params); + + if (rate != SAMPLE_RATE) + return -EINVAL; + if (channels != 2) + return -EINVAL; + + return snd_pcm_lib_alloc_vmalloc_buffer(substream, + params_buffer_bytes(params)); +} + +static int audio_pcm_hw_free(struct snd_pcm_substream *substream) +{ + return snd_pcm_lib_free_vmalloc_buffer(substream); +} + +static int audio_pcm_prepare(struct snd_pcm_substream *substream) +{ + struct snd_pcm_runtime *runtime = substream->runtime; + struct audio_dev *audio = runtime->private_data; + + audio->period = snd_pcm_lib_period_bytes(substream); + audio->period_offset = 0; + audio->buffer_start = runtime->dma_area; + audio->buffer_end = audio->buffer_start + + snd_pcm_lib_buffer_bytes(substream); + audio->buffer_pos = audio->buffer_start; + + return 0; +} + +static snd_pcm_uframes_t audio_pcm_pointer(struct snd_pcm_substream *substream) +{ + struct snd_pcm_runtime *runtime = substream->runtime; + struct audio_dev *audio = runtime->private_data; + ssize_t bytes = audio->buffer_pos - audio->buffer_start; + + /* return offset of next frame to fill in our buffer */ + return bytes_to_frames(runtime, bytes); +} + +static int audio_pcm_playback_trigger(struct snd_pcm_substream *substream, + int cmd) +{ + struct audio_dev *audio = substream->runtime->private_data; + int ret = 0; + + switch (cmd) { + case SNDRV_PCM_TRIGGER_START: + case SNDRV_PCM_TRIGGER_RESUME: + audio_pcm_playback_start(audio); + break; + + case SNDRV_PCM_TRIGGER_STOP: + case SNDRV_PCM_TRIGGER_SUSPEND: + audio_pcm_playback_stop(audio); + break; + + default: + ret = -EINVAL; + } + + return ret; +} + +static struct audio_dev _audio_dev = { + .func = { + .name = "audio_source", + .bind = audio_bind, + .unbind = audio_unbind, + .set_alt = audio_set_alt, + .setup = audio_setup, + .disable = audio_disable, + .free_func = audio_free_func, + }, + .lock = __SPIN_LOCK_UNLOCKED(_audio_dev.lock), + .idle_reqs = LIST_HEAD_INIT(_audio_dev.idle_reqs), +}; + +static struct snd_pcm_ops audio_playback_ops = { + .open = audio_pcm_open, + .close = audio_pcm_close, + .ioctl = snd_pcm_lib_ioctl, + .hw_params = audio_pcm_hw_params, + .hw_free = audio_pcm_hw_free, + .prepare = audio_pcm_prepare, + .trigger = audio_pcm_playback_trigger, + .pointer = audio_pcm_pointer, +}; + +int audio_source_bind_config(struct usb_configuration *c, + struct audio_source_config *config) +{ + struct audio_dev *audio; + int err; + + config->card = -1; + config->device = -1; + + audio = &_audio_dev; + + err = snd_card_setup(c, config); + if (err) + return err; + + err = usb_add_function(c, &audio->func); + if (err) + goto add_fail; + + return 0; + +add_fail: + snd_card_free(audio->card); + return err; +} + +static int snd_card_setup(struct usb_configuration *c, + struct audio_source_config *config) +{ + struct audio_dev *audio; + struct snd_card *card; + struct snd_pcm *pcm; + int err; + + audio = &_audio_dev; + + err = snd_card_new(&c->cdev->gadget->dev, + SNDRV_DEFAULT_IDX1, SNDRV_DEFAULT_STR1, + THIS_MODULE, 0, &card); + if (err) + return err; + + err = snd_pcm_new(card, "USB audio source", 0, 1, 0, &pcm); + if (err) + goto pcm_fail; + + pcm->private_data = audio; + pcm->info_flags = 0; + audio->pcm = pcm; + + strlcpy(pcm->name, "USB gadget audio", sizeof(pcm->name)); + + snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &audio_playback_ops); + snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_DEV, + NULL, 0, 64 * 1024); + + strlcpy(card->driver, "audio_source", sizeof(card->driver)); + strlcpy(card->shortname, card->driver, sizeof(card->shortname)); + strlcpy(card->longname, "USB accessory audio source", + sizeof(card->longname)); + + err = snd_card_register(card); + if (err) + goto register_fail; + + config->card = pcm->card->number; + config->device = pcm->device; + audio->card = card; + return 0; + +register_fail: +pcm_fail: + snd_card_free(audio->card); + return err; +} + +static struct audio_source_instance *to_audio_source_instance( + struct config_item *item) +{ + return container_of(to_config_group(item), struct audio_source_instance, + func_inst.group); +} + +static struct audio_source_instance *to_fi_audio_source( + const struct usb_function_instance *fi) +{ + return container_of(fi, struct audio_source_instance, func_inst); +} + +static void audio_source_attr_release(struct config_item *item) +{ + struct audio_source_instance *fi_audio = to_audio_source_instance(item); + + usb_put_function_instance(&fi_audio->func_inst); +} + +static int audio_source_set_inst_name(struct usb_function_instance *fi, + const char *name) +{ + struct audio_source_instance *fi_audio; + char *ptr; + int name_len; + + name_len = strlen(name) + 1; + if (name_len > MAX_INST_NAME_LEN) + return -ENAMETOOLONG; + + ptr = kstrndup(name, name_len, GFP_KERNEL); + if (!ptr) + return -ENOMEM; + + fi_audio = to_fi_audio_source(fi); + fi_audio->name = ptr; + + return 0; +} + +static void audio_source_free_inst(struct usb_function_instance *fi) +{ + struct audio_source_instance *fi_audio; + + fi_audio = to_fi_audio_source(fi); + device_destroy(fi_audio->audio_device->class, + fi_audio->audio_device->devt); + kfree(fi_audio->name); + kfree(fi_audio->config); +} + +static ssize_t audio_source_pcm_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct audio_source_instance *fi_audio = dev_get_drvdata(dev); + struct audio_source_config *config = fi_audio->config; + + /* print PCM card and device numbers */ + return sprintf(buf, "%d %d\n", config->card, config->device); +} + +struct device *create_function_device(char *name); + +static struct usb_function_instance *audio_source_alloc_inst(void) +{ + struct audio_source_instance *fi_audio; + struct device_attribute **attrs; + struct device_attribute *attr; + struct device *dev; + void *err_ptr; + int err = 0; + + fi_audio = kzalloc(sizeof(*fi_audio), GFP_KERNEL); + if (!fi_audio) + return ERR_PTR(-ENOMEM); + + fi_audio->func_inst.set_inst_name = audio_source_set_inst_name; + fi_audio->func_inst.free_func_inst = audio_source_free_inst; + + fi_audio->config = kzalloc(sizeof(struct audio_source_config), + GFP_KERNEL); + if (!fi_audio->config) { + err_ptr = ERR_PTR(-ENOMEM); + goto fail_audio; + } + + config_group_init_type_name(&fi_audio->func_inst.group, "", + &audio_source_func_type); + dev = create_function_device("f_audio_source"); + + if (IS_ERR(dev)) { + err_ptr = dev; + goto fail_audio_config; + } + + fi_audio->config->card = -1; + fi_audio->config->device = -1; + fi_audio->audio_device = dev; + + attrs = audio_source_function_attributes; + if (attrs) { + while ((attr = *attrs++) && !err) + err = device_create_file(dev, attr); + if (err) { + err_ptr = ERR_PTR(-EINVAL); + goto fail_device; + } + } + + dev_set_drvdata(dev, fi_audio); + _audio_dev.config = fi_audio->config; + + return &fi_audio->func_inst; + +fail_device: + device_destroy(dev->class, dev->devt); +fail_audio_config: + kfree(fi_audio->config); +fail_audio: + kfree(fi_audio); + return err_ptr; + +} + +static struct usb_function *audio_source_alloc(struct usb_function_instance *fi) +{ + return &_audio_dev.func; +} + +DECLARE_USB_FUNCTION_INIT(audio_source, audio_source_alloc_inst, + audio_source_alloc); +MODULE_LICENSE("GPL"); diff --git a/drivers/usb/gadget/function/f_midi.c b/drivers/usb/gadget/function/f_midi.c index 71cf552b8828..f0a8e66e7a9c 100644 --- a/drivers/usb/gadget/function/f_midi.c +++ b/drivers/usb/gadget/function/f_midi.c @@ -1208,6 +1208,65 @@ static void f_midi_free_inst(struct usb_function_instance *f) kfree(opts); } +#ifdef CONFIG_USB_CONFIGFS_UEVENT +extern struct device *create_function_device(char *name); +static ssize_t alsa_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct usb_function_instance *fi_midi = dev_get_drvdata(dev); + struct f_midi *midi; + + if (!fi_midi->f) + dev_warn(dev, "f_midi: function not set\n"); + + if (fi_midi && fi_midi->f) { + midi = func_to_midi(fi_midi->f); + if (midi->rmidi && midi->rmidi->card) + return sprintf(buf, "%d %d\n", + midi->rmidi->card->number, midi->rmidi->device); + } + + /* print PCM card and device numbers */ + return sprintf(buf, "%d %d\n", -1, -1); +} + +static DEVICE_ATTR(alsa, S_IRUGO, alsa_show, NULL); + +static struct device_attribute *alsa_function_attributes[] = { + &dev_attr_alsa, + NULL +}; + +static int create_alsa_device(struct usb_function_instance *fi) +{ + struct device *dev; + struct device_attribute **attrs; + struct device_attribute *attr; + int err = 0; + + dev = create_function_device("f_midi"); + if (IS_ERR(dev)) + return PTR_ERR(dev); + + attrs = alsa_function_attributes; + if (attrs) { + while ((attr = *attrs++) && !err) + err = device_create_file(dev, attr); + if (err) { + device_destroy(dev->class, dev->devt); + return -EINVAL; + } + } + dev_set_drvdata(dev, fi); + return 0; +} +#else +static int create_alsa_device(struct usb_function_instance *fi) +{ + return 0; +} +#endif + static struct usb_function_instance *f_midi_alloc_inst(void) { struct f_midi_opts *opts; @@ -1225,6 +1284,11 @@ static struct usb_function_instance *f_midi_alloc_inst(void) opts->in_ports = 1; opts->out_ports = 1; + if (create_alsa_device(&opts->func_inst)) { + kfree(opts); + return ERR_PTR(-ENODEV); + } + config_group_init_type_name(&opts->func_inst.group, "", &midi_func_type); @@ -1243,6 +1307,7 @@ static void f_midi_free(struct usb_function *f) kfree(midi->id); kfifo_free(&midi->in_req_fifo); kfree(midi); + opts->func_inst.f = NULL; --opts->refcnt; } mutex_unlock(&opts->lock); @@ -1329,6 +1394,7 @@ static struct usb_function *f_midi_alloc(struct usb_function_instance *fi) midi->func.disable = f_midi_disable; midi->func.free_func = f_midi_free; + fi->f = &midi->func; return &midi->func; setup_fail: diff --git a/drivers/usb/misc/sisusbvga/sisusb_con.c b/drivers/usb/misc/sisusbvga/sisusb_con.c index f019d80ca9e4..dc45cfc8eb10 100644 --- a/drivers/usb/misc/sisusbvga/sisusb_con.c +++ b/drivers/usb/misc/sisusbvga/sisusb_con.c @@ -1216,7 +1216,7 @@ font_op_error: /* Interface routine */ static int sisusbcon_font_set(struct vc_data *c, struct console_font *font, - unsigned flags) + unsigned int flags) { struct sisusb_usb_data *sisusb; unsigned charcount = font->charcount; @@ -1337,29 +1337,65 @@ static void sisusbdummycon_init(struct vc_data *vc, int init) vc_resize(vc, 80, 25); } -static int sisusbdummycon_dummy(void) +static void sisusbdummycon_deinit(struct vc_data *vc) { } +static void sisusbdummycon_clear(struct vc_data *vc, int sy, int sx, + int height, int width) { } +static void sisusbdummycon_putc(struct vc_data *vc, int c, int ypos, + int xpos) { } +static void sisusbdummycon_putcs(struct vc_data *vc, const unsigned short *s, + int count, int ypos, int xpos) { } +static void sisusbdummycon_cursor(struct vc_data *vc, int mode) { } + +static bool sisusbdummycon_scroll(struct vc_data *vc, unsigned int top, + unsigned int bottom, enum con_scroll dir, + unsigned int lines) { - return 0; + return false; } -#define SISUSBCONDUMMY (void *)sisusbdummycon_dummy +static int sisusbdummycon_switch(struct vc_data *vc) +{ + return 0; +} + +static int sisusbdummycon_blank(struct vc_data *vc, int blank, int mode_switch) +{ + return 0; +} + +static int sisusbdummycon_font_set(struct vc_data *vc, + struct console_font *font, + unsigned int flags) +{ + return 0; +} + +static int sisusbdummycon_font_default(struct vc_data *vc, + struct console_font *font, char *name) +{ + return 0; +} + +static int sisusbdummycon_font_copy(struct vc_data *vc, int con) +{ + return 0; +} static const struct consw sisusb_dummy_con = { .owner = THIS_MODULE, .con_startup = sisusbdummycon_startup, .con_init = sisusbdummycon_init, - .con_deinit = SISUSBCONDUMMY, - .con_clear = SISUSBCONDUMMY, - .con_putc = SISUSBCONDUMMY, - .con_putcs = SISUSBCONDUMMY, - .con_cursor = SISUSBCONDUMMY, - .con_scroll = SISUSBCONDUMMY, - .con_switch = SISUSBCONDUMMY, - .con_blank = SISUSBCONDUMMY, - .con_font_set = SISUSBCONDUMMY, - .con_font_get = SISUSBCONDUMMY, - .con_font_default = SISUSBCONDUMMY, - .con_font_copy = SISUSBCONDUMMY, + .con_deinit = sisusbdummycon_deinit, + .con_clear = sisusbdummycon_clear, + .con_putc = sisusbdummycon_putc, + .con_putcs = sisusbdummycon_putcs, + .con_cursor = sisusbdummycon_cursor, + .con_scroll = sisusbdummycon_scroll, + .con_switch = sisusbdummycon_switch, + .con_blank = sisusbdummycon_blank, + .con_font_set = sisusbdummycon_font_set, + .con_font_default = sisusbdummycon_font_default, + .con_font_copy = sisusbdummycon_font_copy, }; int diff --git a/drivers/usb/phy/Kconfig b/drivers/usb/phy/Kconfig index 440238061edd..75b714ea56e3 100644 --- a/drivers/usb/phy/Kconfig +++ b/drivers/usb/phy/Kconfig @@ -7,6 +7,14 @@ config USB_PHY select EXTCON def_bool n +config USB_OTG_WAKELOCK + bool "Hold a wakelock when USB connected" + depends on PM_WAKELOCKS + select USB_OTG_UTILS + help + Select this to automatically hold a wakelock when USB is + connected, preventing suspend. + # # USB Transceiver Drivers # @@ -202,4 +210,13 @@ config USB_ULPI_VIEWPORT Provides read/write operations to the ULPI phy register set for controllers with a viewport register (e.g. Chipidea/ARC controllers). +config DUAL_ROLE_USB_INTF + bool "Generic DUAL ROLE sysfs interface" + depends on SYSFS && USB_PHY + help + A generic sysfs interface to track and change the state of + dual role usb phys. The usb phy drivers can register to + this interface to expose it capabilities to the userspace + and thereby allowing userspace to change the port mode. + endmenu diff --git a/drivers/usb/phy/Makefile b/drivers/usb/phy/Makefile index 0c40ccc90631..68867d611282 100644 --- a/drivers/usb/phy/Makefile +++ b/drivers/usb/phy/Makefile @@ -4,6 +4,8 @@ # obj-$(CONFIG_USB_PHY) += phy.o obj-$(CONFIG_OF) += of.o +obj-$(CONFIG_USB_OTG_WAKELOCK) += otg-wakelock.o +obj-$(CONFIG_DUAL_ROLE_USB_INTF) += class-dual-role.o # transceiver drivers, keep the list sorted diff --git a/drivers/usb/phy/class-dual-role.c b/drivers/usb/phy/class-dual-role.c new file mode 100644 index 000000000000..51fcb545a9d5 --- /dev/null +++ b/drivers/usb/phy/class-dual-role.c @@ -0,0 +1,529 @@ +/* + * class-dual-role.c + * + * Copyright (C) 2015 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/ctype.h> +#include <linux/device.h> +#include <linux/usb/class-dual-role.h> +#include <linux/err.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/stat.h> +#include <linux/types.h> + +#define DUAL_ROLE_NOTIFICATION_TIMEOUT 2000 + +static ssize_t dual_role_store_property(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count); +static ssize_t dual_role_show_property(struct device *dev, + struct device_attribute *attr, + char *buf); + +#define DUAL_ROLE_ATTR(_name) \ +{ \ + .attr = { .name = #_name }, \ + .show = dual_role_show_property, \ + .store = dual_role_store_property, \ +} + +static struct device_attribute dual_role_attrs[] = { + DUAL_ROLE_ATTR(supported_modes), + DUAL_ROLE_ATTR(mode), + DUAL_ROLE_ATTR(power_role), + DUAL_ROLE_ATTR(data_role), + DUAL_ROLE_ATTR(powers_vconn), +}; + +struct class *dual_role_class; +EXPORT_SYMBOL_GPL(dual_role_class); + +static struct device_type dual_role_dev_type; + +static char *kstrdupcase(const char *str, gfp_t gfp, bool to_upper) +{ + char *ret, *ustr; + + ustr = ret = kmalloc(strlen(str) + 1, gfp); + + if (!ret) + return NULL; + + while (*str) + *ustr++ = to_upper ? toupper(*str++) : tolower(*str++); + + *ustr = 0; + + return ret; +} + +static void dual_role_changed_work(struct work_struct *work) +{ + struct dual_role_phy_instance *dual_role = + container_of(work, struct dual_role_phy_instance, + changed_work); + + dev_dbg(&dual_role->dev, "%s\n", __func__); + kobject_uevent(&dual_role->dev.kobj, KOBJ_CHANGE); +} + +void dual_role_instance_changed(struct dual_role_phy_instance *dual_role) +{ + dev_dbg(&dual_role->dev, "%s\n", __func__); + pm_wakeup_event(&dual_role->dev, DUAL_ROLE_NOTIFICATION_TIMEOUT); + schedule_work(&dual_role->changed_work); +} +EXPORT_SYMBOL_GPL(dual_role_instance_changed); + +int dual_role_get_property(struct dual_role_phy_instance *dual_role, + enum dual_role_property prop, + unsigned int *val) +{ + return dual_role->desc->get_property(dual_role, prop, val); +} +EXPORT_SYMBOL_GPL(dual_role_get_property); + +int dual_role_set_property(struct dual_role_phy_instance *dual_role, + enum dual_role_property prop, + const unsigned int *val) +{ + if (!dual_role->desc->set_property) + return -ENODEV; + + return dual_role->desc->set_property(dual_role, prop, val); +} +EXPORT_SYMBOL_GPL(dual_role_set_property); + +int dual_role_property_is_writeable(struct dual_role_phy_instance *dual_role, + enum dual_role_property prop) +{ + if (!dual_role->desc->property_is_writeable) + return -ENODEV; + + return dual_role->desc->property_is_writeable(dual_role, prop); +} +EXPORT_SYMBOL_GPL(dual_role_property_is_writeable); + +static void dual_role_dev_release(struct device *dev) +{ + struct dual_role_phy_instance *dual_role = + container_of(dev, struct dual_role_phy_instance, dev); + pr_debug("device: '%s': %s\n", dev_name(dev), __func__); + kfree(dual_role); +} + +static struct dual_role_phy_instance *__must_check +__dual_role_register(struct device *parent, + const struct dual_role_phy_desc *desc) +{ + struct device *dev; + struct dual_role_phy_instance *dual_role; + int rc; + + dual_role = kzalloc(sizeof(*dual_role), GFP_KERNEL); + if (!dual_role) + return ERR_PTR(-ENOMEM); + + dev = &dual_role->dev; + + device_initialize(dev); + + dev->class = dual_role_class; + dev->type = &dual_role_dev_type; + dev->parent = parent; + dev->release = dual_role_dev_release; + dev_set_drvdata(dev, dual_role); + dual_role->desc = desc; + + rc = dev_set_name(dev, "%s", desc->name); + if (rc) + goto dev_set_name_failed; + + INIT_WORK(&dual_role->changed_work, dual_role_changed_work); + + rc = device_init_wakeup(dev, true); + if (rc) + goto wakeup_init_failed; + + rc = device_add(dev); + if (rc) + goto device_add_failed; + + dual_role_instance_changed(dual_role); + + return dual_role; + +device_add_failed: + device_init_wakeup(dev, false); +wakeup_init_failed: +dev_set_name_failed: + put_device(dev); + kfree(dual_role); + + return ERR_PTR(rc); +} + +static void dual_role_instance_unregister(struct dual_role_phy_instance + *dual_role) +{ + cancel_work_sync(&dual_role->changed_work); + device_init_wakeup(&dual_role->dev, false); + device_unregister(&dual_role->dev); +} + +static void devm_dual_role_release(struct device *dev, void *res) +{ + struct dual_role_phy_instance **dual_role = res; + + dual_role_instance_unregister(*dual_role); +} + +struct dual_role_phy_instance *__must_check +devm_dual_role_instance_register(struct device *parent, + const struct dual_role_phy_desc *desc) +{ + struct dual_role_phy_instance **ptr, *dual_role; + + ptr = devres_alloc(devm_dual_role_release, sizeof(*ptr), GFP_KERNEL); + + if (!ptr) + return ERR_PTR(-ENOMEM); + dual_role = __dual_role_register(parent, desc); + if (IS_ERR(dual_role)) { + devres_free(ptr); + } else { + *ptr = dual_role; + devres_add(parent, ptr); + } + return dual_role; +} +EXPORT_SYMBOL_GPL(devm_dual_role_instance_register); + +static int devm_dual_role_match(struct device *dev, void *res, void *data) +{ + struct dual_role_phy_instance **r = res; + + if (WARN_ON(!r || !*r)) + return 0; + + return *r == data; +} + +void devm_dual_role_instance_unregister(struct device *dev, + struct dual_role_phy_instance + *dual_role) +{ + int rc; + + rc = devres_release(dev, devm_dual_role_release, + devm_dual_role_match, dual_role); + WARN_ON(rc); +} +EXPORT_SYMBOL_GPL(devm_dual_role_instance_unregister); + +void *dual_role_get_drvdata(struct dual_role_phy_instance *dual_role) +{ + return dual_role->drv_data; +} +EXPORT_SYMBOL_GPL(dual_role_get_drvdata); + +/***************** Device attribute functions **************************/ + +/* port type */ +static char *supported_modes_text[] = { + "ufp dfp", "dfp", "ufp" +}; + +/* current mode */ +static char *mode_text[] = { + "ufp", "dfp", "none" +}; + +/* Power role */ +static char *pr_text[] = { + "source", "sink", "none" +}; + +/* Data role */ +static char *dr_text[] = { + "host", "device", "none" +}; + +/* Vconn supply */ +static char *vconn_supply_text[] = { + "n", "y" +}; + +static ssize_t dual_role_show_property(struct device *dev, + struct device_attribute *attr, char *buf) +{ + ssize_t ret = 0; + struct dual_role_phy_instance *dual_role = dev_get_drvdata(dev); + const ptrdiff_t off = attr - dual_role_attrs; + unsigned int value; + + if (off == DUAL_ROLE_PROP_SUPPORTED_MODES) { + value = dual_role->desc->supported_modes; + } else { + ret = dual_role_get_property(dual_role, off, &value); + + if (ret < 0) { + if (ret == -ENODATA) + dev_dbg(dev, + "driver has no data for `%s' property\n", + attr->attr.name); + else if (ret != -ENODEV) + dev_err(dev, + "driver failed to report `%s' property: %zd\n", + attr->attr.name, ret); + return ret; + } + } + + if (off == DUAL_ROLE_PROP_SUPPORTED_MODES) { + BUILD_BUG_ON(DUAL_ROLE_PROP_SUPPORTED_MODES_TOTAL != + ARRAY_SIZE(supported_modes_text)); + if (value < DUAL_ROLE_PROP_SUPPORTED_MODES_TOTAL) + return snprintf(buf, PAGE_SIZE, "%s\n", + supported_modes_text[value]); + else + return -EIO; + } else if (off == DUAL_ROLE_PROP_MODE) { + BUILD_BUG_ON(DUAL_ROLE_PROP_MODE_TOTAL != + ARRAY_SIZE(mode_text)); + if (value < DUAL_ROLE_PROP_MODE_TOTAL) + return snprintf(buf, PAGE_SIZE, "%s\n", + mode_text[value]); + else + return -EIO; + } else if (off == DUAL_ROLE_PROP_PR) { + BUILD_BUG_ON(DUAL_ROLE_PROP_PR_TOTAL != ARRAY_SIZE(pr_text)); + if (value < DUAL_ROLE_PROP_PR_TOTAL) + return snprintf(buf, PAGE_SIZE, "%s\n", + pr_text[value]); + else + return -EIO; + } else if (off == DUAL_ROLE_PROP_DR) { + BUILD_BUG_ON(DUAL_ROLE_PROP_DR_TOTAL != ARRAY_SIZE(dr_text)); + if (value < DUAL_ROLE_PROP_DR_TOTAL) + return snprintf(buf, PAGE_SIZE, "%s\n", + dr_text[value]); + else + return -EIO; + } else if (off == DUAL_ROLE_PROP_VCONN_SUPPLY) { + BUILD_BUG_ON(DUAL_ROLE_PROP_VCONN_SUPPLY_TOTAL != + ARRAY_SIZE(vconn_supply_text)); + if (value < DUAL_ROLE_PROP_VCONN_SUPPLY_TOTAL) + return snprintf(buf, PAGE_SIZE, "%s\n", + vconn_supply_text[value]); + else + return -EIO; + } else + return -EIO; +} + +static ssize_t dual_role_store_property(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + ssize_t ret; + struct dual_role_phy_instance *dual_role = dev_get_drvdata(dev); + const ptrdiff_t off = attr - dual_role_attrs; + unsigned int value; + int total, i; + char *dup_buf, **text_array; + bool result = false; + + dup_buf = kstrdupcase(buf, GFP_KERNEL, false); + switch (off) { + case DUAL_ROLE_PROP_MODE: + total = DUAL_ROLE_PROP_MODE_TOTAL; + text_array = mode_text; + break; + case DUAL_ROLE_PROP_PR: + total = DUAL_ROLE_PROP_PR_TOTAL; + text_array = pr_text; + break; + case DUAL_ROLE_PROP_DR: + total = DUAL_ROLE_PROP_DR_TOTAL; + text_array = dr_text; + break; + case DUAL_ROLE_PROP_VCONN_SUPPLY: + ret = strtobool(dup_buf, &result); + value = result; + if (!ret) + goto setprop; + default: + ret = -EINVAL; + goto error; + } + + for (i = 0; i <= total; i++) { + if (i == total) { + ret = -ENOTSUPP; + goto error; + } + if (!strncmp(*(text_array + i), dup_buf, + strlen(*(text_array + i)))) { + value = i; + break; + } + } + +setprop: + ret = dual_role->desc->set_property(dual_role, off, &value); + +error: + kfree(dup_buf); + + if (ret < 0) + return ret; + + return count; +} + +static umode_t dual_role_attr_is_visible(struct kobject *kobj, + struct attribute *attr, int attrno) +{ + struct device *dev = container_of(kobj, struct device, kobj); + struct dual_role_phy_instance *dual_role = dev_get_drvdata(dev); + umode_t mode = S_IRUSR | S_IRGRP | S_IROTH; + int i; + + if (attrno == DUAL_ROLE_PROP_SUPPORTED_MODES) + return mode; + + for (i = 0; i < dual_role->desc->num_properties; i++) { + int property = dual_role->desc->properties[i]; + + if (property == attrno) { + if (dual_role->desc->property_is_writeable && + dual_role_property_is_writeable(dual_role, property) + > 0) + mode |= S_IWUSR; + + return mode; + } + } + + return 0; +} + +static struct attribute *__dual_role_attrs[ARRAY_SIZE(dual_role_attrs) + 1]; + +static struct attribute_group dual_role_attr_group = { + .attrs = __dual_role_attrs, + .is_visible = dual_role_attr_is_visible, +}; + +static const struct attribute_group *dual_role_attr_groups[] = { + &dual_role_attr_group, + NULL, +}; + +void dual_role_init_attrs(struct device_type *dev_type) +{ + int i; + + dev_type->groups = dual_role_attr_groups; + + for (i = 0; i < ARRAY_SIZE(dual_role_attrs); i++) + __dual_role_attrs[i] = &dual_role_attrs[i].attr; +} + +int dual_role_uevent(struct device *dev, struct kobj_uevent_env *env) +{ + struct dual_role_phy_instance *dual_role = dev_get_drvdata(dev); + int ret = 0, j; + char *prop_buf; + char *attrname; + + dev_dbg(dev, "uevent\n"); + + if (!dual_role || !dual_role->desc) { + dev_dbg(dev, "No dual_role phy yet\n"); + return ret; + } + + dev_dbg(dev, "DUAL_ROLE_NAME=%s\n", dual_role->desc->name); + + ret = add_uevent_var(env, "DUAL_ROLE_NAME=%s", dual_role->desc->name); + if (ret) + return ret; + + prop_buf = (char *)get_zeroed_page(GFP_KERNEL); + if (!prop_buf) + return -ENOMEM; + + for (j = 0; j < dual_role->desc->num_properties; j++) { + struct device_attribute *attr; + char *line; + + attr = &dual_role_attrs[dual_role->desc->properties[j]]; + + ret = dual_role_show_property(dev, attr, prop_buf); + if (ret == -ENODEV || ret == -ENODATA) { + ret = 0; + continue; + } + + if (ret < 0) + goto out; + line = strnchr(prop_buf, PAGE_SIZE, '\n'); + if (line) + *line = 0; + + attrname = kstrdupcase(attr->attr.name, GFP_KERNEL, true); + if (!attrname) + ret = -ENOMEM; + + dev_dbg(dev, "prop %s=%s\n", attrname, prop_buf); + + ret = add_uevent_var(env, "DUAL_ROLE_%s=%s", attrname, + prop_buf); + kfree(attrname); + if (ret) + goto out; + } + +out: + free_page((unsigned long)prop_buf); + + return ret; +} + +/******************* Module Init ***********************************/ + +static int __init dual_role_class_init(void) +{ + dual_role_class = class_create(THIS_MODULE, "dual_role_usb"); + + if (IS_ERR(dual_role_class)) + return PTR_ERR(dual_role_class); + + dual_role_class->dev_uevent = dual_role_uevent; + dual_role_init_attrs(&dual_role_dev_type); + + return 0; +} + +static void __exit dual_role_class_exit(void) +{ + class_destroy(dual_role_class); +} + +subsys_initcall(dual_role_class_init); +module_exit(dual_role_class_exit); diff --git a/drivers/usb/phy/otg-wakelock.c b/drivers/usb/phy/otg-wakelock.c new file mode 100644 index 000000000000..ecd741027f53 --- /dev/null +++ b/drivers/usb/phy/otg-wakelock.c @@ -0,0 +1,170 @@ +/* + * otg-wakelock.c + * + * Copyright (C) 2011 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/kernel.h> +#include <linux/device.h> +#include <linux/err.h> +#include <linux/module.h> +#include <linux/notifier.h> +#include <linux/spinlock.h> +#include <linux/usb/otg.h> + +#define TEMPORARY_HOLD_TIME 2000 + +static bool enabled = true; +static struct usb_phy *otgwl_xceiv; +static struct notifier_block otgwl_nb; + +/* + * otgwl_spinlock is held while the VBUS lock is grabbed or dropped and the + * held field is updated to match. + */ + +static DEFINE_SPINLOCK(otgwl_spinlock); + +/* + * Only one lock, but since these 3 fields are associated with each other... + */ + +struct otgwl_lock { + char name[40]; + struct wakeup_source wakesrc; + bool held; +}; + +/* + * VBUS present lock. Also used as a timed lock on charger + * connect/disconnect and USB host disconnect, to allow the system + * to react to the change in power. + */ + +static struct otgwl_lock vbus_lock; + +static void otgwl_hold(struct otgwl_lock *lock) +{ + if (!lock->held) { + __pm_stay_awake(&lock->wakesrc); + lock->held = true; + } +} + +static void otgwl_temporary_hold(struct otgwl_lock *lock) +{ + __pm_wakeup_event(&lock->wakesrc, TEMPORARY_HOLD_TIME); + lock->held = false; +} + +static void otgwl_drop(struct otgwl_lock *lock) +{ + if (lock->held) { + __pm_relax(&lock->wakesrc); + lock->held = false; + } +} + +static void otgwl_handle_event(unsigned long event) +{ + unsigned long irqflags; + + spin_lock_irqsave(&otgwl_spinlock, irqflags); + + if (!enabled) { + otgwl_drop(&vbus_lock); + spin_unlock_irqrestore(&otgwl_spinlock, irqflags); + return; + } + + switch (event) { + case USB_EVENT_VBUS: + case USB_EVENT_ENUMERATED: + otgwl_hold(&vbus_lock); + break; + + case USB_EVENT_NONE: + case USB_EVENT_ID: + case USB_EVENT_CHARGER: + otgwl_temporary_hold(&vbus_lock); + break; + + default: + break; + } + + spin_unlock_irqrestore(&otgwl_spinlock, irqflags); +} + +static int otgwl_otg_notifications(struct notifier_block *nb, + unsigned long event, void *unused) +{ + otgwl_handle_event(event); + return NOTIFY_OK; +} + +static int set_enabled(const char *val, const struct kernel_param *kp) +{ + int rv = param_set_bool(val, kp); + + if (rv) + return rv; + + if (otgwl_xceiv) + otgwl_handle_event(otgwl_xceiv->last_event); + + return 0; +} + +static struct kernel_param_ops enabled_param_ops = { + .set = set_enabled, + .get = param_get_bool, +}; + +module_param_cb(enabled, &enabled_param_ops, &enabled, 0644); +MODULE_PARM_DESC(enabled, "enable wakelock when VBUS present"); + +static int __init otg_wakelock_init(void) +{ + int ret; + struct usb_phy *phy; + + phy = usb_get_phy(USB_PHY_TYPE_USB2); + + if (IS_ERR(phy)) { + pr_err("%s: No USB transceiver found\n", __func__); + return PTR_ERR(phy); + } + otgwl_xceiv = phy; + + snprintf(vbus_lock.name, sizeof(vbus_lock.name), "vbus-%s", + dev_name(otgwl_xceiv->dev)); + wakeup_source_init(&vbus_lock.wakesrc, vbus_lock.name); + + otgwl_nb.notifier_call = otgwl_otg_notifications; + ret = usb_register_notifier(otgwl_xceiv, &otgwl_nb); + + if (ret) { + pr_err("%s: usb_register_notifier on transceiver %s" + " failed\n", __func__, + dev_name(otgwl_xceiv->dev)); + otgwl_xceiv = NULL; + wakeup_source_trash(&vbus_lock.wakesrc); + return ret; + } + + otgwl_handle_event(otgwl_xceiv->last_event); + return ret; +} + +late_initcall(otg_wakelock_init); diff --git a/drivers/video/console/dummycon.c b/drivers/video/console/dummycon.c index b90ef96e43d6..f2eafe2ed980 100644 --- a/drivers/video/console/dummycon.c +++ b/drivers/video/console/dummycon.c @@ -41,12 +41,47 @@ static void dummycon_init(struct vc_data *vc, int init) vc_resize(vc, DUMMY_COLUMNS, DUMMY_ROWS); } -static int dummycon_dummy(void) +static void dummycon_deinit(struct vc_data *vc) { } +static void dummycon_clear(struct vc_data *vc, int sy, int sx, int height, + int width) { } +static void dummycon_putc(struct vc_data *vc, int c, int ypos, int xpos) { } +static void dummycon_putcs(struct vc_data *vc, const unsigned short *s, + int count, int ypos, int xpos) { } +static void dummycon_cursor(struct vc_data *vc, int mode) { } + +static bool dummycon_scroll(struct vc_data *vc, unsigned int top, + unsigned int bottom, enum con_scroll dir, + unsigned int lines) +{ + return false; +} + +static int dummycon_switch(struct vc_data *vc) { - return 0; + return 0; } -#define DUMMY (void *)dummycon_dummy +static int dummycon_blank(struct vc_data *vc, int blank, int mode_switch) +{ + return 0; +} + +static int dummycon_font_set(struct vc_data *vc, struct console_font *font, + unsigned int flags) +{ + return 0; +} + +static int dummycon_font_default(struct vc_data *vc, + struct console_font *font, char *name) +{ + return 0; +} + +static int dummycon_font_copy(struct vc_data *vc, int con) +{ + return 0; +} /* * The console `switch' structure for the dummy console @@ -55,19 +90,19 @@ static int dummycon_dummy(void) */ const struct consw dummy_con = { - .owner = THIS_MODULE, - .con_startup = dummycon_startup, - .con_init = dummycon_init, - .con_deinit = DUMMY, - .con_clear = DUMMY, - .con_putc = DUMMY, - .con_putcs = DUMMY, - .con_cursor = DUMMY, - .con_scroll = DUMMY, - .con_switch = DUMMY, - .con_blank = DUMMY, - .con_font_set = DUMMY, - .con_font_default = DUMMY, - .con_font_copy = DUMMY, + .owner = THIS_MODULE, + .con_startup = dummycon_startup, + .con_init = dummycon_init, + .con_deinit = dummycon_deinit, + .con_clear = dummycon_clear, + .con_putc = dummycon_putc, + .con_putcs = dummycon_putcs, + .con_cursor = dummycon_cursor, + .con_scroll = dummycon_scroll, + .con_switch = dummycon_switch, + .con_blank = dummycon_blank, + .con_font_set = dummycon_font_set, + .con_font_default = dummycon_font_default, + .con_font_copy = dummycon_font_copy, }; EXPORT_SYMBOL_GPL(dummy_con); diff --git a/drivers/video/console/newport_con.c b/drivers/video/console/newport_con.c index 42d02a206059..7f2526b43b33 100644 --- a/drivers/video/console/newport_con.c +++ b/drivers/video/console/newport_con.c @@ -673,12 +673,12 @@ static bool newport_scroll(struct vc_data *vc, unsigned int t, unsigned int b, return true; } -static int newport_dummy(struct vc_data *c) +static int newport_set_origin(struct vc_data *vc) { return 0; } -#define DUMMY (void *) newport_dummy +static void newport_save_screen(struct vc_data *vc) { } const struct consw newport_con = { .owner = THIS_MODULE, @@ -694,8 +694,8 @@ const struct consw newport_con = { .con_blank = newport_blank, .con_font_set = newport_font_set, .con_font_default = newport_font_default, - .con_set_origin = DUMMY, - .con_save_screen = DUMMY + .con_set_origin = newport_set_origin, + .con_save_screen = newport_save_screen }; static int newport_probe(struct gio_device *dev, diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c index ff6612a3ddc8..0fdd6761d6c3 100644 --- a/drivers/video/console/vgacon.c +++ b/drivers/video/console/vgacon.c @@ -1272,7 +1272,8 @@ static int vgacon_adjust_height(struct vc_data *vc, unsigned fontheight) return 0; } -static int vgacon_font_set(struct vc_data *c, struct console_font *font, unsigned flags) +static int vgacon_font_set(struct vc_data *c, struct console_font *font, + unsigned int flags) { unsigned charcount = font->charcount; int rc; @@ -1410,21 +1411,20 @@ static bool vgacon_scroll(struct vc_data *c, unsigned int t, unsigned int b, * The console `switch' structure for the VGA based console */ -static int vgacon_dummy(struct vc_data *c) -{ - return 0; -} - -#define DUMMY (void *) vgacon_dummy +static void vgacon_clear(struct vc_data *vc, int sy, int sx, int height, + int width) { } +static void vgacon_putc(struct vc_data *vc, int c, int ypos, int xpos) { } +static void vgacon_putcs(struct vc_data *vc, const unsigned short *s, + int count, int ypos, int xpos) { } const struct consw vga_con = { .owner = THIS_MODULE, .con_startup = vgacon_startup, .con_init = vgacon_init, .con_deinit = vgacon_deinit, - .con_clear = DUMMY, - .con_putc = DUMMY, - .con_putcs = DUMMY, + .con_clear = vgacon_clear, + .con_putc = vgacon_putc, + .con_putcs = vgacon_putcs, .con_cursor = vgacon_cursor, .con_scroll = vgacon_scroll, .con_switch = vgacon_switch, diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 41360caff17f..2f946cdd9945 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -2591,7 +2591,8 @@ static int fbcon_copy_font(struct vc_data *vc, int con) * is ever implemented. */ -static int fbcon_set_font(struct vc_data *vc, struct console_font *font, unsigned flags) +static int fbcon_set_font(struct vc_data *vc, struct console_font *font, + unsigned int flags) { struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; unsigned charcount = font->charcount; diff --git a/drivers/video/fbdev/goldfishfb.c b/drivers/video/fbdev/goldfishfb.c index 66d58e93bc32..8c93ad1dd9cc 100644 --- a/drivers/video/fbdev/goldfishfb.c +++ b/drivers/video/fbdev/goldfishfb.c @@ -26,6 +26,7 @@ #include <linux/interrupt.h> #include <linux/ioport.h> #include <linux/platform_device.h> +#include <linux/acpi.h> enum { FB_GET_WIDTH = 0x00, @@ -305,12 +306,25 @@ static int goldfish_fb_remove(struct platform_device *pdev) return 0; } +static const struct of_device_id goldfish_fb_of_match[] = { + { .compatible = "google,goldfish-fb", }, + {}, +}; +MODULE_DEVICE_TABLE(of, goldfish_fb_of_match); + +static const struct acpi_device_id goldfish_fb_acpi_match[] = { + { "GFSH0004", 0 }, + { }, +}; +MODULE_DEVICE_TABLE(acpi, goldfish_fb_acpi_match); static struct platform_driver goldfish_fb_driver = { .probe = goldfish_fb_probe, .remove = goldfish_fb_remove, .driver = { - .name = "goldfish_fb" + .name = "goldfish_fb", + .of_match_table = goldfish_fb_of_match, + .acpi_match_table = ACPI_PTR(goldfish_fb_acpi_match), } }; diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index 197069303510..0d5a3b84fef4 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -50,9 +50,9 @@ * @page: structure to page * */ -static int v9fs_fid_readpage(void *data, struct page *page) +static int v9fs_fid_readpage(struct file *data, struct page *page) { - struct p9_fid *fid = data; + struct p9_fid *fid = (struct p9_fid *)data; struct inode *inode = page->mapping->host; struct bio_vec bvec = {.bv_page = page, .bv_len = PAGE_SIZE}; struct iov_iter to; @@ -294,7 +294,7 @@ start: if (len == PAGE_SIZE) goto out; - retval = v9fs_fid_readpage(v9inode->writeback_fid, page); + retval = v9fs_fid_readpage((struct file *)v9inode->writeback_fid, page); put_page(page); if (!retval) goto start; diff --git a/fs/Kconfig b/fs/Kconfig index 7aee6d699fd6..121fabf122f2 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -227,6 +227,7 @@ source "fs/orangefs/Kconfig" source "fs/adfs/Kconfig" source "fs/affs/Kconfig" source "fs/ecryptfs/Kconfig" +source "fs/sdcardfs/Kconfig" source "fs/hfs/Kconfig" source "fs/hfsplus/Kconfig" source "fs/befs/Kconfig" diff --git a/fs/Makefile b/fs/Makefile index ef772f1eaff8..1e34e4bc81a3 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -4,7 +4,7 @@ # # 14 Sep 2000, Christoph Hellwig <hch@infradead.org> # Rewritten to use lists instead of if-statements. -# +# obj-y := open.o read_write.o file_table.o super.o \ char_dev.o stat.o exec.o pipe.o namei.o fcntl.o \ @@ -62,7 +62,7 @@ obj-y += devpts/ obj-$(CONFIG_PROFILING) += dcookies.o obj-$(CONFIG_DLM) += dlm/ - + # Do not add any filesystems before this line obj-$(CONFIG_FSCACHE) += fscache/ obj-$(CONFIG_REISERFS_FS) += reiserfs/ @@ -84,6 +84,7 @@ obj-$(CONFIG_ISO9660_FS) += isofs/ obj-$(CONFIG_HFSPLUS_FS) += hfsplus/ # Before hfs to find wrapped HFS+ obj-$(CONFIG_HFS_FS) += hfs/ obj-$(CONFIG_ECRYPT_FS) += ecryptfs/ +obj-$(CONFIG_SDCARD_FS) += sdcardfs/ obj-$(CONFIG_VXFS_FS) += freevxfs/ obj-$(CONFIG_NFS_FS) += nfs/ obj-$(CONFIG_EXPORTFS) += exportfs/ diff --git a/fs/afs/file.c b/fs/afs/file.c index 510cba15fa56..e6e949cdeb51 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -140,12 +140,11 @@ static void afs_file_readpage_read_complete(struct page *page, /* * read page from file, directory or symlink, given a key to use */ -int afs_page_filler(void *data, struct page *page) +static int __afs_page_filler(struct key *key, struct page *page) { struct inode *inode = page->mapping->host; struct afs_vnode *vnode = AFS_FS_I(inode); struct afs_read *req; - struct key *key = data; int ret; _enter("{%x},{%lu},{%lu}", key_serial(key), inode->i_ino, page->index); @@ -249,6 +248,13 @@ error: return ret; } +int afs_page_filler(struct file *data, struct page *page) +{ + struct key *key = (struct key *)data; + + return __afs_page_filler(key, page); +} + /* * read page from file, directory or symlink, given a file to nominate the key * to be used @@ -261,14 +267,14 @@ static int afs_readpage(struct file *file, struct page *page) if (file) { key = file->private_data; ASSERT(key != NULL); - ret = afs_page_filler(key, page); + ret = __afs_page_filler(key, page); } else { struct inode *inode = page->mapping->host; key = afs_request_key(AFS_FS_S(inode->i_sb)->volume->cell); if (IS_ERR(key)) { ret = PTR_ERR(key); } else { - ret = afs_page_filler(key, page); + ret = __afs_page_filler(key, page); key_put(key); } } diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 82e16556afea..ed42f21a6239 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -485,7 +485,7 @@ extern const struct file_operations afs_file_operations; extern int afs_open(struct inode *, struct file *); extern int afs_release(struct inode *, struct file *); -extern int afs_page_filler(void *, struct page *); +extern int afs_page_filler(struct file *, struct page *); extern void afs_put_read(struct afs_read *); /* diff --git a/fs/attr.c b/fs/attr.c index 12ffdb6fb63c..f5510d993284 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -202,7 +202,7 @@ EXPORT_SYMBOL(setattr_copy); * the file open for write, as there can be no conflicting delegation in * that case. */ -int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **delegated_inode) +int notify_change2(struct vfsmount *mnt, struct dentry * dentry, struct iattr * attr, struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; umode_t mode = inode->i_mode; @@ -226,7 +226,7 @@ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **de return -EPERM; if (!inode_owner_or_capable(inode)) { - error = inode_permission(inode, MAY_WRITE); + error = inode_permission2(mnt, inode, MAY_WRITE); if (error) return error; } @@ -309,7 +309,9 @@ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **de if (error) return error; - if (inode->i_op->setattr) + if (mnt && inode->i_op->setattr2) + error = inode->i_op->setattr2(mnt, dentry, attr); + else if (inode->i_op->setattr) error = inode->i_op->setattr(dentry, attr); else error = simple_setattr(dentry, attr); @@ -322,4 +324,10 @@ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **de return error; } +EXPORT_SYMBOL(notify_change2); + +int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **delegated_inode) +{ + return notify_change2(NULL, dentry, attr, delegated_inode); +} EXPORT_SYMBOL(notify_change); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 6d2bfbb63d9b..60e82b7899d2 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3820,8 +3820,8 @@ retry: if (wbc->sync_mode == WB_SYNC_ALL) tag_pages_for_writeback(mapping, index, end); while (!done && !nr_to_write_done && (index <= end) && - (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag, - min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) { + (nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end, + tag))) { unsigned i; scanned = 1; @@ -3831,11 +3831,6 @@ retry: if (!PagePrivate(page)) continue; - if (!wbc->range_cyclic && page->index > end) { - done = 1; - break; - } - spin_lock(&mapping->private_lock); if (!PagePrivate(page)) { spin_unlock(&mapping->private_lock); @@ -3967,8 +3962,8 @@ retry: tag_pages_for_writeback(mapping, index, end); done_index = index; while (!done && !nr_to_write_done && (index <= end) && - (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag, - min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) { + (nr_pages = pagevec_lookup_range_tag(&pvec, mapping, + &index, end, tag))) { unsigned i; scanned = 1; @@ -3993,12 +3988,6 @@ retry: continue; } - if (!wbc->range_cyclic && page->index > end) { - done = 1; - unlock_page(page); - continue; - } - if (wbc->sync_mode != WB_SYNC_NONE) { if (PageWriteback(page)) flush_fn(data); diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 4d622654bfbc..26c682db94ee 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -870,15 +870,10 @@ retry: max_pages = wsize >> PAGE_SHIFT; get_more_pages: - pvec_pages = min_t(unsigned, PAGEVEC_SIZE, - max_pages - locked_pages); - if (end - index < (u64)(pvec_pages - 1)) - pvec_pages = (unsigned)(end - index) + 1; - - pvec_pages = pagevec_lookup_tag(&pvec, mapping, &index, - PAGECACHE_TAG_DIRTY, - pvec_pages); - dout("pagevec_lookup_tag got %d\n", pvec_pages); + pvec_pages = pagevec_lookup_range_nr_tag(&pvec, mapping, &index, + end, PAGECACHE_TAG_DIRTY, + max_pages - locked_pages); + dout("pagevec_lookup_range_tag got %d\n", pvec_pages); if (!pvec_pages && !locked_pages) break; for (i = 0; i < pvec_pages && locked_pages < max_pages; i++) { @@ -896,16 +891,6 @@ get_more_pages: unlock_page(page); continue; } - if (page->index > end) { - dout("end of range %p\n", page); - /* can't be range_cyclic (1st pass) because - * end == -1 in that case. */ - stop = true; - if (ceph_wbc.head_snapc) - done = true; - unlock_page(page); - break; - } if (strip_unit_end && (page->index > strip_unit_end)) { dout("end of strip unit %p\n", page); unlock_page(page); @@ -1177,8 +1162,7 @@ release_pvec_pages: index = 0; while ((index <= end) && (nr = pagevec_lookup_tag(&pvec, mapping, &index, - PAGECACHE_TAG_WRITEBACK, - PAGEVEC_SIZE))) { + PAGECACHE_TAG_WRITEBACK))) { for (i = 0; i < nr; i++) { page = pvec.pages[i]; if (page_snap_context(page) != snapc) diff --git a/fs/coredump.c b/fs/coredump.c index b36e9b094c11..aaadbe71bad8 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -747,7 +747,7 @@ void do_coredump(const siginfo_t *siginfo) goto close_fail; if (!(cprm.file->f_mode & FMODE_CAN_WRITE)) goto close_fail; - if (do_truncate(cprm.file->f_path.dentry, 0, 0, cprm.file)) + if (do_truncate2(cprm.file->f_path.mnt, cprm.file->f_path.dentry, 0, 0, cprm.file)) goto close_fail; } diff --git a/fs/crypto/Makefile b/fs/crypto/Makefile index 9f6607f17b53..cb496989a6b6 100644 --- a/fs/crypto/Makefile +++ b/fs/crypto/Makefile @@ -1,4 +1,4 @@ obj-$(CONFIG_FS_ENCRYPTION) += fscrypto.o -fscrypto-y := crypto.o fname.o policy.o keyinfo.o +fscrypto-y := crypto.o fname.o hooks.o keyinfo.o policy.o fscrypto-$(CONFIG_BLOCK) += bio.o diff --git a/fs/crypto/bio.c b/fs/crypto/bio.c index 0d5e6a569d58..0959044c5cee 100644 --- a/fs/crypto/bio.c +++ b/fs/crypto/bio.c @@ -26,15 +26,8 @@ #include <linux/namei.h> #include "fscrypt_private.h" -/* - * Call fscrypt_decrypt_page on every single page, reusing the encryption - * context. - */ -static void completion_pages(struct work_struct *work) +static void __fscrypt_decrypt_bio(struct bio *bio, bool done) { - struct fscrypt_ctx *ctx = - container_of(work, struct fscrypt_ctx, r.work); - struct bio *bio = ctx->r.bio; struct bio_vec *bv; int i; @@ -46,22 +39,38 @@ static void completion_pages(struct work_struct *work) if (ret) { WARN_ON_ONCE(1); SetPageError(page); - } else { + } else if (done) { SetPageUptodate(page); } - unlock_page(page); + if (done) + unlock_page(page); } +} + +void fscrypt_decrypt_bio(struct bio *bio) +{ + __fscrypt_decrypt_bio(bio, false); +} +EXPORT_SYMBOL(fscrypt_decrypt_bio); + +static void completion_pages(struct work_struct *work) +{ + struct fscrypt_ctx *ctx = + container_of(work, struct fscrypt_ctx, r.work); + struct bio *bio = ctx->r.bio; + + __fscrypt_decrypt_bio(bio, true); fscrypt_release_ctx(ctx); bio_put(bio); } -void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *ctx, struct bio *bio) +void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx, struct bio *bio) { INIT_WORK(&ctx->r.work, completion_pages); ctx->r.bio = bio; - queue_work(fscrypt_read_workqueue, &ctx->r.work); + fscrypt_enqueue_decrypt_work(&ctx->r.work); } -EXPORT_SYMBOL(fscrypt_decrypt_bio_pages); +EXPORT_SYMBOL(fscrypt_enqueue_decrypt_bio); void fscrypt_pullback_bio_page(struct page **page, bool restore) { diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c index f862ad19c714..203e8b69286b 100644 --- a/fs/crypto/crypto.c +++ b/fs/crypto/crypto.c @@ -27,6 +27,7 @@ #include <linux/dcache.h> #include <linux/namei.h> #include <crypto/aes.h> +#include <crypto/skcipher.h> #include "fscrypt_private.h" static unsigned int num_prealloc_crypto_pages = 32; @@ -44,12 +45,18 @@ static mempool_t *fscrypt_bounce_page_pool = NULL; static LIST_HEAD(fscrypt_free_ctxs); static DEFINE_SPINLOCK(fscrypt_ctx_lock); -struct workqueue_struct *fscrypt_read_workqueue; +static struct workqueue_struct *fscrypt_read_workqueue; static DEFINE_MUTEX(fscrypt_init_mutex); static struct kmem_cache *fscrypt_ctx_cachep; struct kmem_cache *fscrypt_info_cachep; +void fscrypt_enqueue_decrypt_work(struct work_struct *work) +{ + queue_work(fscrypt_read_workqueue, work); +} +EXPORT_SYMBOL(fscrypt_enqueue_decrypt_work); + /** * fscrypt_release_ctx() - Releases an encryption context * @ctx: The encryption context to release. @@ -126,19 +133,17 @@ struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *inode, gfp_t gfp_flags) } EXPORT_SYMBOL(fscrypt_get_ctx); -/** - * page_crypt_complete() - completion callback for page crypto - * @req: The asynchronous cipher request context - * @res: The result of the cipher operation - */ -static void page_crypt_complete(struct crypto_async_request *req, int res) +void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num, + const struct fscrypt_info *ci) { - struct fscrypt_completion_result *ecr = req->data; + memset(iv, 0, ci->ci_mode->ivsize); + iv->lblk_num = cpu_to_le64(lblk_num); - if (res == -EINPROGRESS) - return; - ecr->res = res; - complete(&ecr->completion); + if (ci->ci_flags & FS_POLICY_FLAG_DIRECT_KEY) + memcpy(iv->nonce, ci->ci_nonce, FS_KEY_DERIVATION_NONCE_SIZE); + + if (ci->ci_essiv_tfm != NULL) + crypto_cipher_encrypt_one(ci->ci_essiv_tfm, iv->raw, iv->raw); } int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw, @@ -146,12 +151,9 @@ int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw, struct page *dest_page, unsigned int len, unsigned int offs, gfp_t gfp_flags) { - struct { - __le64 index; - u8 padding[FS_IV_SIZE - sizeof(__le64)]; - } iv; + union fscrypt_iv iv; struct skcipher_request *req = NULL; - DECLARE_FS_COMPLETION_RESULT(ecr); + DECLARE_CRYPTO_WAIT(wait); struct scatterlist dst, src; struct fscrypt_info *ci = inode->i_crypt_info; struct crypto_skcipher *tfm = ci->ci_ctfm; @@ -162,27 +164,15 @@ int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw, if (WARN_ON_ONCE(len % FS_CRYPTO_BLOCK_SIZE != 0)) return -EINVAL; - BUILD_BUG_ON(sizeof(iv) != FS_IV_SIZE); - BUILD_BUG_ON(AES_BLOCK_SIZE != FS_IV_SIZE); - iv.index = cpu_to_le64(lblk_num); - memset(iv.padding, 0, sizeof(iv.padding)); - - if (ci->ci_essiv_tfm != NULL) { - crypto_cipher_encrypt_one(ci->ci_essiv_tfm, (u8 *)&iv, - (u8 *)&iv); - } + fscrypt_generate_iv(&iv, lblk_num, ci); req = skcipher_request_alloc(tfm, gfp_flags); - if (!req) { - printk_ratelimited(KERN_ERR - "%s: crypto_request_alloc() failed\n", - __func__); + if (!req) return -ENOMEM; - } skcipher_request_set_callback( req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, - page_crypt_complete, &ecr); + crypto_req_done, &wait); sg_init_table(&dst, 1); sg_set_page(&dst, dest_page, len, offs); @@ -190,19 +180,15 @@ int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw, sg_set_page(&src, src_page, len, offs); skcipher_request_set_crypt(req, &src, &dst, len, &iv); if (rw == FS_DECRYPT) - res = crypto_skcipher_decrypt(req); + res = crypto_wait_req(crypto_skcipher_decrypt(req), &wait); else - res = crypto_skcipher_encrypt(req); - if (res == -EINPROGRESS || res == -EBUSY) { - BUG_ON(req->base.data != &ecr); - wait_for_completion(&ecr.completion); - res = ecr.res; - } + res = crypto_wait_req(crypto_skcipher_encrypt(req), &wait); skcipher_request_free(req); if (res) { - printk_ratelimited(KERN_ERR - "%s: crypto_skcipher_encrypt() returned %d\n", - __func__, res); + fscrypt_err(inode->i_sb, + "%scryption failed for inode %lu, block %llu: %d", + (rw == FS_DECRYPT ? "de" : "en"), + inode->i_ino, lblk_num, res); return res; } return 0; @@ -343,12 +329,11 @@ static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags) return -ECHILD; dir = dget_parent(dentry); - if (!d_inode(dir)->i_sb->s_cop->is_encrypted(d_inode(dir))) { + if (!IS_ENCRYPTED(d_inode(dir))) { dput(dir); return 0; } - /* this should eventually be an flag in d_flags */ spin_lock(&dentry->d_lock); cached_with_key = dentry->d_flags & DCACHE_ENCRYPTED_WITH_KEY; spin_unlock(&dentry->d_lock); @@ -375,7 +360,6 @@ static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags) const struct dentry_operations fscrypt_d_ops = { .d_revalidate = fscrypt_d_revalidate, }; -EXPORT_SYMBOL(fscrypt_d_ops); void fscrypt_restore_control_page(struct page *page) { @@ -444,6 +428,27 @@ fail: return res; } +void fscrypt_msg(struct super_block *sb, const char *level, + const char *fmt, ...) +{ + static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); + struct va_format vaf; + va_list args; + + if (!__ratelimit(&rs)) + return; + + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + if (sb) + printk("%sfscrypt (%s): %pV\n", level, sb->s_id, &vaf); + else + printk("%sfscrypt: %pV\n", level, &vaf); + va_end(args); +} + /** * fscrypt_init() - Set up for fs encryption. */ diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c index 8606da1df0aa..7ff40a73dbec 100644 --- a/fs/crypto/fname.c +++ b/fs/crypto/fname.c @@ -13,89 +13,71 @@ #include <linux/scatterlist.h> #include <linux/ratelimit.h> +#include <crypto/skcipher.h> #include "fscrypt_private.h" -/** - * fname_crypt_complete() - completion callback for filename crypto - * @req: The asynchronous cipher request context - * @res: The result of the cipher operation - */ -static void fname_crypt_complete(struct crypto_async_request *req, int res) +static inline bool fscrypt_is_dot_dotdot(const struct qstr *str) { - struct fscrypt_completion_result *ecr = req->data; + if (str->len == 1 && str->name[0] == '.') + return true; - if (res == -EINPROGRESS) - return; - ecr->res = res; - complete(&ecr->completion); + if (str->len == 2 && str->name[0] == '.' && str->name[1] == '.') + return true; + + return false; } /** * fname_encrypt() - encrypt a filename * - * The caller must have allocated sufficient memory for the @oname string. + * The output buffer must be at least as large as the input buffer. + * Any extra space is filled with NUL padding before encryption. * * Return: 0 on success, -errno on failure */ -static int fname_encrypt(struct inode *inode, - const struct qstr *iname, struct fscrypt_str *oname) +int fname_encrypt(struct inode *inode, const struct qstr *iname, + u8 *out, unsigned int olen) { struct skcipher_request *req = NULL; - DECLARE_FS_COMPLETION_RESULT(ecr); + DECLARE_CRYPTO_WAIT(wait); struct fscrypt_info *ci = inode->i_crypt_info; struct crypto_skcipher *tfm = ci->ci_ctfm; - int res = 0; - char iv[FS_CRYPTO_BLOCK_SIZE]; + union fscrypt_iv iv; struct scatterlist sg; - int padding = 4 << (ci->ci_flags & FS_POLICY_FLAGS_PAD_MASK); - unsigned int lim; - unsigned int cryptlen; - - lim = inode->i_sb->s_cop->max_namelen(inode); - if (iname->len <= 0 || iname->len > lim) - return -EIO; + int res; /* * Copy the filename to the output buffer for encrypting in-place and * pad it with the needed number of NUL bytes. */ - cryptlen = max_t(unsigned int, iname->len, FS_CRYPTO_BLOCK_SIZE); - cryptlen = round_up(cryptlen, padding); - cryptlen = min(cryptlen, lim); - memcpy(oname->name, iname->name, iname->len); - memset(oname->name + iname->len, 0, cryptlen - iname->len); + if (WARN_ON(olen < iname->len)) + return -ENOBUFS; + memcpy(out, iname->name, iname->len); + memset(out + iname->len, 0, olen - iname->len); /* Initialize the IV */ - memset(iv, 0, FS_CRYPTO_BLOCK_SIZE); + fscrypt_generate_iv(&iv, 0, ci); /* Set up the encryption request */ req = skcipher_request_alloc(tfm, GFP_NOFS); - if (!req) { - printk_ratelimited(KERN_ERR - "%s: skcipher_request_alloc() failed\n", __func__); + if (!req) return -ENOMEM; - } skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, - fname_crypt_complete, &ecr); - sg_init_one(&sg, oname->name, cryptlen); - skcipher_request_set_crypt(req, &sg, &sg, cryptlen, iv); + crypto_req_done, &wait); + sg_init_one(&sg, out, olen); + skcipher_request_set_crypt(req, &sg, &sg, olen, &iv); /* Do the encryption */ - res = crypto_skcipher_encrypt(req); - if (res == -EINPROGRESS || res == -EBUSY) { - /* Request is being completed asynchronously; wait for it */ - wait_for_completion(&ecr.completion); - res = ecr.res; - } + res = crypto_wait_req(crypto_skcipher_encrypt(req), &wait); skcipher_request_free(req); if (res < 0) { - printk_ratelimited(KERN_ERR - "%s: Error (error code %d)\n", __func__, res); + fscrypt_err(inode->i_sb, + "Filename encryption failed for inode %lu: %d", + inode->i_ino, res); return res; } - oname->len = cryptlen; return 0; } @@ -111,45 +93,34 @@ static int fname_decrypt(struct inode *inode, struct fscrypt_str *oname) { struct skcipher_request *req = NULL; - DECLARE_FS_COMPLETION_RESULT(ecr); + DECLARE_CRYPTO_WAIT(wait); struct scatterlist src_sg, dst_sg; struct fscrypt_info *ci = inode->i_crypt_info; struct crypto_skcipher *tfm = ci->ci_ctfm; - int res = 0; - char iv[FS_CRYPTO_BLOCK_SIZE]; - unsigned lim; - - lim = inode->i_sb->s_cop->max_namelen(inode); - if (iname->len <= 0 || iname->len > lim) - return -EIO; + union fscrypt_iv iv; + int res; /* Allocate request */ req = skcipher_request_alloc(tfm, GFP_NOFS); - if (!req) { - printk_ratelimited(KERN_ERR - "%s: crypto_request_alloc() failed\n", __func__); + if (!req) return -ENOMEM; - } skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, - fname_crypt_complete, &ecr); + crypto_req_done, &wait); /* Initialize IV */ - memset(iv, 0, FS_CRYPTO_BLOCK_SIZE); + fscrypt_generate_iv(&iv, 0, ci); /* Create decryption request */ sg_init_one(&src_sg, iname->name, iname->len); sg_init_one(&dst_sg, oname->name, oname->len); - skcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, iv); - res = crypto_skcipher_decrypt(req); - if (res == -EINPROGRESS || res == -EBUSY) { - wait_for_completion(&ecr.completion); - res = ecr.res; - } + skcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, &iv); + res = crypto_wait_req(crypto_skcipher_decrypt(req), &wait); skcipher_request_free(req); if (res < 0) { - printk_ratelimited(KERN_ERR - "%s: Error (error code %d)\n", __func__, res); + fscrypt_err(inode->i_sb, + "Filename decryption failed for inode %lu: %d", + inode->i_ino, res); return res; } @@ -212,50 +183,52 @@ static int digest_decode(const char *src, int len, char *dst) return cp - dst; } -u32 fscrypt_fname_encrypted_size(const struct inode *inode, u32 ilen) +bool fscrypt_fname_encrypted_size(const struct inode *inode, u32 orig_len, + u32 max_len, u32 *encrypted_len_ret) { - int padding = 32; - struct fscrypt_info *ci = inode->i_crypt_info; - - if (ci) - padding = 4 << (ci->ci_flags & FS_POLICY_FLAGS_PAD_MASK); - ilen = max(ilen, (u32)FS_CRYPTO_BLOCK_SIZE); - return round_up(ilen, padding); + int padding = 4 << (inode->i_crypt_info->ci_flags & + FS_POLICY_FLAGS_PAD_MASK); + u32 encrypted_len; + + if (orig_len > max_len) + return false; + encrypted_len = max(orig_len, (u32)FS_CRYPTO_BLOCK_SIZE); + encrypted_len = round_up(encrypted_len, padding); + *encrypted_len_ret = min(encrypted_len, max_len); + return true; } -EXPORT_SYMBOL(fscrypt_fname_encrypted_size); /** - * fscrypt_fname_crypto_alloc_obuff() - + * fscrypt_fname_alloc_buffer - allocate a buffer for presented filenames * - * Allocates an output buffer that is sufficient for the crypto operation - * specified by the context and the direction. + * Allocate a buffer that is large enough to hold any decrypted or encoded + * filename (null-terminated), for the given maximum encrypted filename length. + * + * Return: 0 on success, -errno on failure */ int fscrypt_fname_alloc_buffer(const struct inode *inode, - u32 ilen, struct fscrypt_str *crypto_str) + u32 max_encrypted_len, + struct fscrypt_str *crypto_str) { - u32 olen = fscrypt_fname_encrypted_size(inode, ilen); const u32 max_encoded_len = max_t(u32, BASE64_CHARS(FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE), 1 + BASE64_CHARS(sizeof(struct fscrypt_digested_name))); + u32 max_presented_len; - crypto_str->len = olen; - olen = max(olen, max_encoded_len); + max_presented_len = max(max_encoded_len, max_encrypted_len); - /* - * Allocated buffer can hold one more character to null-terminate the - * string - */ - crypto_str->name = kmalloc(olen + 1, GFP_NOFS); - if (!(crypto_str->name)) + crypto_str->name = kmalloc(max_presented_len + 1, GFP_NOFS); + if (!crypto_str->name) return -ENOMEM; + crypto_str->len = max_presented_len; return 0; } EXPORT_SYMBOL(fscrypt_fname_alloc_buffer); /** - * fscrypt_fname_crypto_free_buffer() - + * fscrypt_fname_free_buffer - free the buffer for presented filenames * - * Frees the buffer allocated for crypto operation. + * Free the buffer allocated by fscrypt_fname_alloc_buffer(). */ void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str) { @@ -322,35 +295,6 @@ int fscrypt_fname_disk_to_usr(struct inode *inode, EXPORT_SYMBOL(fscrypt_fname_disk_to_usr); /** - * fscrypt_fname_usr_to_disk() - converts a filename from user space to disk - * space - * - * The caller must have allocated sufficient memory for the @oname string. - * - * Return: 0 on success, -errno on failure - */ -int fscrypt_fname_usr_to_disk(struct inode *inode, - const struct qstr *iname, - struct fscrypt_str *oname) -{ - if (fscrypt_is_dot_dotdot(iname)) { - oname->name[0] = '.'; - oname->name[iname->len - 1] = '.'; - oname->len = iname->len; - return 0; - } - if (inode->i_crypt_info) - return fname_encrypt(inode, iname, oname); - /* - * Without a proper key, a user is not allowed to modify the filenames - * in a directory. Consequently, a user space name cannot be mapped to - * a disk-space name - */ - return -ENOKEY; -} -EXPORT_SYMBOL(fscrypt_fname_usr_to_disk); - -/** * fscrypt_setup_filename() - prepare to search a possibly encrypted directory * @dir: the directory that will be searched * @iname: the user-provided filename being searched for @@ -383,22 +327,27 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname, memset(fname, 0, sizeof(struct fscrypt_name)); fname->usr_fname = iname; - if (!dir->i_sb->s_cop->is_encrypted(dir) || - fscrypt_is_dot_dotdot(iname)) { + if (!IS_ENCRYPTED(dir) || fscrypt_is_dot_dotdot(iname)) { fname->disk_name.name = (unsigned char *)iname->name; fname->disk_name.len = iname->len; return 0; } ret = fscrypt_get_encryption_info(dir); - if (ret && ret != -EOPNOTSUPP) + if (ret) return ret; if (dir->i_crypt_info) { - ret = fscrypt_fname_alloc_buffer(dir, iname->len, - &fname->crypto_buf); - if (ret) - return ret; - ret = fname_encrypt(dir, iname, &fname->crypto_buf); + if (!fscrypt_fname_encrypted_size(dir, iname->len, + dir->i_sb->s_cop->max_namelen, + &fname->crypto_buf.len)) + return -ENAMETOOLONG; + fname->crypto_buf.name = kmalloc(fname->crypto_buf.len, + GFP_NOFS); + if (!fname->crypto_buf.name) + return -ENOMEM; + + ret = fname_encrypt(dir, iname, fname->crypto_buf.name, + fname->crypto_buf.len); if (ret) goto errout; fname->disk_name.name = fname->crypto_buf.name; @@ -450,7 +399,7 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname, return 0; errout: - fscrypt_fname_free_buffer(&fname->crypto_buf); + kfree(fname->crypto_buf.name); return ret; } EXPORT_SYMBOL(fscrypt_setup_filename); diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index 092e9dad1414..7424f851eb5c 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -12,20 +12,12 @@ #ifndef _FSCRYPT_PRIVATE_H #define _FSCRYPT_PRIVATE_H -#include <linux/fscrypt_supp.h> +#define __FS_HAS_ENCRYPTION 1 +#include <linux/fscrypt.h> #include <crypto/hash.h> /* Encryption parameters */ -#define FS_IV_SIZE 16 -#define FS_AES_128_ECB_KEY_SIZE 16 -#define FS_AES_128_CBC_KEY_SIZE 16 -#define FS_AES_128_CTS_KEY_SIZE 16 -#define FS_AES_256_GCM_KEY_SIZE 32 -#define FS_AES_256_CBC_KEY_SIZE 32 -#define FS_AES_256_CTS_KEY_SIZE 32 -#define FS_AES_256_XTS_KEY_SIZE 64 - -#define FS_KEY_DERIVATION_NONCE_SIZE 16 +#define FS_KEY_DERIVATION_NONCE_SIZE 16 /** * Encryption context for inode @@ -49,17 +41,52 @@ struct fscrypt_context { #define FS_ENCRYPTION_CONTEXT_FORMAT_V1 1 +/** + * For encrypted symlinks, the ciphertext length is stored at the beginning + * of the string in little-endian format. + */ +struct fscrypt_symlink_data { + __le16 len; + char encrypted_path[1]; +} __packed; + /* - * A pointer to this structure is stored in the file system's in-core - * representation of an inode. + * fscrypt_info - the "encryption key" for an inode + * + * When an encrypted file's key is made available, an instance of this struct is + * allocated and stored in ->i_crypt_info. Once created, it remains until the + * inode is evicted. */ struct fscrypt_info { + + /* The actual crypto transform used for encryption and decryption */ + struct crypto_skcipher *ci_ctfm; + + /* + * Cipher for ESSIV IV generation. Only set for CBC contents + * encryption, otherwise is NULL. + */ + struct crypto_cipher *ci_essiv_tfm; + + /* + * Encryption mode used for this inode. It corresponds to either + * ci_data_mode or ci_filename_mode, depending on the inode type. + */ + struct fscrypt_mode *ci_mode; + + /* + * If non-NULL, then this inode uses a master key directly rather than a + * derived key, and ci_ctfm will equal ci_master_key->mk_ctfm. + * Otherwise, this inode uses a derived key. + */ + struct fscrypt_master_key *ci_master_key; + + /* fields from the fscrypt_context */ u8 ci_data_mode; u8 ci_filename_mode; u8 ci_flags; - struct crypto_skcipher *ci_ctfm; - struct crypto_cipher *ci_essiv_tfm; - u8 ci_master_key[FS_KEY_DESCRIPTOR_SIZE]; + u8 ci_master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE]; + u8 ci_nonce[FS_KEY_DERIVATION_NONCE_SIZE]; }; typedef enum { @@ -70,19 +97,27 @@ typedef enum { #define FS_CTX_REQUIRES_FREE_ENCRYPT_FL 0x00000001 #define FS_CTX_HAS_BOUNCE_BUFFER_FL 0x00000002 -struct fscrypt_completion_result { - struct completion completion; - int res; -}; +static inline bool fscrypt_valid_enc_modes(u32 contents_mode, + u32 filenames_mode) +{ + if (contents_mode == FS_ENCRYPTION_MODE_AES_128_CBC && + filenames_mode == FS_ENCRYPTION_MODE_AES_128_CTS) + return true; -#define DECLARE_FS_COMPLETION_RESULT(ecr) \ - struct fscrypt_completion_result ecr = { \ - COMPLETION_INITIALIZER_ONSTACK((ecr).completion), 0 } + if (contents_mode == FS_ENCRYPTION_MODE_AES_256_XTS && + filenames_mode == FS_ENCRYPTION_MODE_AES_256_CTS) + return true; + if (contents_mode == FS_ENCRYPTION_MODE_ADIANTUM && + filenames_mode == FS_ENCRYPTION_MODE_ADIANTUM) + return true; + + return false; +} /* crypto.c */ +extern struct kmem_cache *fscrypt_info_cachep; extern int fscrypt_initialize(unsigned int cop_flags); -extern struct workqueue_struct *fscrypt_read_workqueue; extern int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw, u64 lblk_num, struct page *src_page, @@ -91,8 +126,50 @@ extern int fscrypt_do_page_crypto(const struct inode *inode, gfp_t gfp_flags); extern struct page *fscrypt_alloc_bounce_page(struct fscrypt_ctx *ctx, gfp_t gfp_flags); +extern const struct dentry_operations fscrypt_d_ops; + +extern void __printf(3, 4) __cold +fscrypt_msg(struct super_block *sb, const char *level, const char *fmt, ...); + +#define fscrypt_warn(sb, fmt, ...) \ + fscrypt_msg(sb, KERN_WARNING, fmt, ##__VA_ARGS__) +#define fscrypt_err(sb, fmt, ...) \ + fscrypt_msg(sb, KERN_ERR, fmt, ##__VA_ARGS__) + +#define FSCRYPT_MAX_IV_SIZE 32 + +union fscrypt_iv { + struct { + /* logical block number within the file */ + __le64 lblk_num; + + /* per-file nonce; only set in DIRECT_KEY mode */ + u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE]; + }; + u8 raw[FSCRYPT_MAX_IV_SIZE]; +}; + +void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num, + const struct fscrypt_info *ci); + +/* fname.c */ +extern int fname_encrypt(struct inode *inode, const struct qstr *iname, + u8 *out, unsigned int olen); +extern bool fscrypt_fname_encrypted_size(const struct inode *inode, + u32 orig_len, u32 max_len, + u32 *encrypted_len_ret); /* keyinfo.c */ + +struct fscrypt_mode { + const char *friendly_name; + const char *cipher_str; + int keysize; + int ivsize; + bool logged_impl_name; + bool needs_essiv; +}; + extern void __exit fscrypt_essiv_cleanup(void); #endif /* _FSCRYPT_PRIVATE_H */ diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c new file mode 100644 index 000000000000..926e5df20ec3 --- /dev/null +++ b/fs/crypto/hooks.c @@ -0,0 +1,271 @@ +/* + * fs/crypto/hooks.c + * + * Encryption hooks for higher-level filesystem operations. + */ + +#include <linux/ratelimit.h> +#include "fscrypt_private.h" + +/** + * fscrypt_file_open - prepare to open a possibly-encrypted regular file + * @inode: the inode being opened + * @filp: the struct file being set up + * + * Currently, an encrypted regular file can only be opened if its encryption key + * is available; access to the raw encrypted contents is not supported. + * Therefore, we first set up the inode's encryption key (if not already done) + * and return an error if it's unavailable. + * + * We also verify that if the parent directory (from the path via which the file + * is being opened) is encrypted, then the inode being opened uses the same + * encryption policy. This is needed as part of the enforcement that all files + * in an encrypted directory tree use the same encryption policy, as a + * protection against certain types of offline attacks. Note that this check is + * needed even when opening an *unencrypted* file, since it's forbidden to have + * an unencrypted file in an encrypted directory. + * + * Return: 0 on success, -ENOKEY if the key is missing, or another -errno code + */ +int fscrypt_file_open(struct inode *inode, struct file *filp) +{ + int err; + struct dentry *dir; + + err = fscrypt_require_key(inode); + if (err) + return err; + + dir = dget_parent(file_dentry(filp)); + if (IS_ENCRYPTED(d_inode(dir)) && + !fscrypt_has_permitted_context(d_inode(dir), inode)) { + fscrypt_warn(inode->i_sb, + "inconsistent encryption contexts: %lu/%lu", + d_inode(dir)->i_ino, inode->i_ino); + err = -EPERM; + } + dput(dir); + return err; +} +EXPORT_SYMBOL_GPL(fscrypt_file_open); + +int __fscrypt_prepare_link(struct inode *inode, struct inode *dir) +{ + int err; + + err = fscrypt_require_key(dir); + if (err) + return err; + + if (!fscrypt_has_permitted_context(dir, inode)) + return -EPERM; + + return 0; +} +EXPORT_SYMBOL_GPL(__fscrypt_prepare_link); + +int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, + unsigned int flags) +{ + int err; + + err = fscrypt_require_key(old_dir); + if (err) + return err; + + err = fscrypt_require_key(new_dir); + if (err) + return err; + + if (old_dir != new_dir) { + if (IS_ENCRYPTED(new_dir) && + !fscrypt_has_permitted_context(new_dir, + d_inode(old_dentry))) + return -EPERM; + + if ((flags & RENAME_EXCHANGE) && + IS_ENCRYPTED(old_dir) && + !fscrypt_has_permitted_context(old_dir, + d_inode(new_dentry))) + return -EPERM; + } + return 0; +} +EXPORT_SYMBOL_GPL(__fscrypt_prepare_rename); + +int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry) +{ + int err = fscrypt_get_encryption_info(dir); + + if (err) + return err; + + if (fscrypt_has_encryption_key(dir)) { + spin_lock(&dentry->d_lock); + dentry->d_flags |= DCACHE_ENCRYPTED_WITH_KEY; + spin_unlock(&dentry->d_lock); + } + + d_set_d_op(dentry, &fscrypt_d_ops); + return 0; +} +EXPORT_SYMBOL_GPL(__fscrypt_prepare_lookup); + +int __fscrypt_prepare_symlink(struct inode *dir, unsigned int len, + unsigned int max_len, + struct fscrypt_str *disk_link) +{ + int err; + + /* + * To calculate the size of the encrypted symlink target we need to know + * the amount of NUL padding, which is determined by the flags set in + * the encryption policy which will be inherited from the directory. + * The easiest way to get access to this is to just load the directory's + * fscrypt_info, since we'll need it to create the dir_entry anyway. + * + * Note: in test_dummy_encryption mode, @dir may be unencrypted. + */ + err = fscrypt_get_encryption_info(dir); + if (err) + return err; + if (!fscrypt_has_encryption_key(dir)) + return -ENOKEY; + + /* + * Calculate the size of the encrypted symlink and verify it won't + * exceed max_len. Note that for historical reasons, encrypted symlink + * targets are prefixed with the ciphertext length, despite this + * actually being redundant with i_size. This decreases by 2 bytes the + * longest symlink target we can accept. + * + * We could recover 1 byte by not counting a null terminator, but + * counting it (even though it is meaningless for ciphertext) is simpler + * for now since filesystems will assume it is there and subtract it. + */ + if (!fscrypt_fname_encrypted_size(dir, len, + max_len - sizeof(struct fscrypt_symlink_data), + &disk_link->len)) + return -ENAMETOOLONG; + disk_link->len += sizeof(struct fscrypt_symlink_data); + + disk_link->name = NULL; + return 0; +} +EXPORT_SYMBOL_GPL(__fscrypt_prepare_symlink); + +int __fscrypt_encrypt_symlink(struct inode *inode, const char *target, + unsigned int len, struct fscrypt_str *disk_link) +{ + int err; + struct qstr iname = QSTR_INIT(target, len); + struct fscrypt_symlink_data *sd; + unsigned int ciphertext_len; + + err = fscrypt_require_key(inode); + if (err) + return err; + + if (disk_link->name) { + /* filesystem-provided buffer */ + sd = (struct fscrypt_symlink_data *)disk_link->name; + } else { + sd = kmalloc(disk_link->len, GFP_NOFS); + if (!sd) + return -ENOMEM; + } + ciphertext_len = disk_link->len - sizeof(*sd); + sd->len = cpu_to_le16(ciphertext_len); + + err = fname_encrypt(inode, &iname, sd->encrypted_path, ciphertext_len); + if (err) { + if (!disk_link->name) + kfree(sd); + return err; + } + /* + * Null-terminating the ciphertext doesn't make sense, but we still + * count the null terminator in the length, so we might as well + * initialize it just in case the filesystem writes it out. + */ + sd->encrypted_path[ciphertext_len] = '\0'; + + if (!disk_link->name) + disk_link->name = (unsigned char *)sd; + return 0; +} +EXPORT_SYMBOL_GPL(__fscrypt_encrypt_symlink); + +/** + * fscrypt_get_symlink - get the target of an encrypted symlink + * @inode: the symlink inode + * @caddr: the on-disk contents of the symlink + * @max_size: size of @caddr buffer + * @done: if successful, will be set up to free the returned target + * + * If the symlink's encryption key is available, we decrypt its target. + * Otherwise, we encode its target for presentation. + * + * This may sleep, so the filesystem must have dropped out of RCU mode already. + * + * Return: the presentable symlink target or an ERR_PTR() + */ +const char *fscrypt_get_symlink(struct inode *inode, const void *caddr, + unsigned int max_size, + struct delayed_call *done) +{ + const struct fscrypt_symlink_data *sd; + struct fscrypt_str cstr, pstr; + int err; + + /* This is for encrypted symlinks only */ + if (WARN_ON(!IS_ENCRYPTED(inode))) + return ERR_PTR(-EINVAL); + + /* + * Try to set up the symlink's encryption key, but we can continue + * regardless of whether the key is available or not. + */ + err = fscrypt_get_encryption_info(inode); + if (err) + return ERR_PTR(err); + + /* + * For historical reasons, encrypted symlink targets are prefixed with + * the ciphertext length, even though this is redundant with i_size. + */ + + if (max_size < sizeof(*sd)) + return ERR_PTR(-EUCLEAN); + sd = caddr; + cstr.name = (unsigned char *)sd->encrypted_path; + cstr.len = le16_to_cpu(sd->len); + + if (cstr.len == 0) + return ERR_PTR(-EUCLEAN); + + if (cstr.len + sizeof(*sd) - 1 > max_size) + return ERR_PTR(-EUCLEAN); + + err = fscrypt_fname_alloc_buffer(inode, cstr.len, &pstr); + if (err) + return ERR_PTR(err); + + err = fscrypt_fname_disk_to_usr(inode, 0, 0, &cstr, &pstr); + if (err) + goto err_kfree; + + err = -EUCLEAN; + if (pstr.name[0] == '\0') + goto err_kfree; + + pstr.name[pstr.len] = '\0'; + set_delayed_call(done, kfree_link, pstr.name); + return pstr.name; + +err_kfree: + kfree(pstr.name); + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(fscrypt_get_symlink); diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c index a38630214058..1e11a683f63d 100644 --- a/fs/crypto/keyinfo.c +++ b/fs/crypto/keyinfo.c @@ -10,40 +10,35 @@ */ #include <keys/user-type.h> +#include <linux/hashtable.h> #include <linux/scatterlist.h> #include <linux/ratelimit.h> #include <crypto/aes.h> +#include <crypto/algapi.h> #include <crypto/sha.h> +#include <crypto/skcipher.h> #include "fscrypt_private.h" static struct crypto_shash *essiv_hash_tfm; -static void derive_crypt_complete(struct crypto_async_request *req, int rc) -{ - struct fscrypt_completion_result *ecr = req->data; - - if (rc == -EINPROGRESS) - return; - - ecr->res = rc; - complete(&ecr->completion); -} +/* Table of keys referenced by FS_POLICY_FLAG_DIRECT_KEY policies */ +static DEFINE_HASHTABLE(fscrypt_master_keys, 6); /* 6 bits = 64 buckets */ +static DEFINE_SPINLOCK(fscrypt_master_keys_lock); -/** - * derive_key_aes() - Derive a key using AES-128-ECB - * @deriving_key: Encryption key used for derivation. - * @source_key: Source key to which to apply derivation. - * @derived_raw_key: Derived raw key. +/* + * Key derivation function. This generates the derived key by encrypting the + * master key with AES-128-ECB using the inode's nonce as the AES key. * - * Return: Zero on success; non-zero otherwise. + * The master key must be at least as long as the derived key. If the master + * key is longer, then only the first 'derived_keysize' bytes are used. */ -static int derive_key_aes(u8 deriving_key[FS_AES_128_ECB_KEY_SIZE], - const struct fscrypt_key *source_key, - u8 derived_raw_key[FS_MAX_KEY_SIZE]) +static int derive_key_aes(const u8 *master_key, + const struct fscrypt_context *ctx, + u8 *derived_key, unsigned int derived_keysize) { int res = 0; struct skcipher_request *req = NULL; - DECLARE_FS_COMPLETION_RESULT(ecr); + DECLARE_CRYPTO_WAIT(wait); struct scatterlist src_sg, dst_sg; struct crypto_skcipher *tfm = crypto_alloc_skcipher("ecb(aes)", 0, 0); @@ -60,132 +55,326 @@ static int derive_key_aes(u8 deriving_key[FS_AES_128_ECB_KEY_SIZE], } skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, - derive_crypt_complete, &ecr); - res = crypto_skcipher_setkey(tfm, deriving_key, - FS_AES_128_ECB_KEY_SIZE); + crypto_req_done, &wait); + res = crypto_skcipher_setkey(tfm, ctx->nonce, sizeof(ctx->nonce)); if (res < 0) goto out; - sg_init_one(&src_sg, source_key->raw, source_key->size); - sg_init_one(&dst_sg, derived_raw_key, source_key->size); - skcipher_request_set_crypt(req, &src_sg, &dst_sg, source_key->size, + sg_init_one(&src_sg, master_key, derived_keysize); + sg_init_one(&dst_sg, derived_key, derived_keysize); + skcipher_request_set_crypt(req, &src_sg, &dst_sg, derived_keysize, NULL); - res = crypto_skcipher_encrypt(req); - if (res == -EINPROGRESS || res == -EBUSY) { - wait_for_completion(&ecr.completion); - res = ecr.res; - } + res = crypto_wait_req(crypto_skcipher_encrypt(req), &wait); out: skcipher_request_free(req); crypto_free_skcipher(tfm); return res; } -static int validate_user_key(struct fscrypt_info *crypt_info, - struct fscrypt_context *ctx, u8 *raw_key, - const char *prefix, int min_keysize) +/* + * Search the current task's subscribed keyrings for a "logon" key with + * description prefix:descriptor, and if found acquire a read lock on it and + * return a pointer to its validated payload in *payload_ret. + */ +static struct key * +find_and_lock_process_key(const char *prefix, + const u8 descriptor[FS_KEY_DESCRIPTOR_SIZE], + unsigned int min_keysize, + const struct fscrypt_key **payload_ret) { char *description; - struct key *keyring_key; - struct fscrypt_key *master_key; + struct key *key; const struct user_key_payload *ukp; - int res; + const struct fscrypt_key *payload; description = kasprintf(GFP_NOFS, "%s%*phN", prefix, - FS_KEY_DESCRIPTOR_SIZE, - ctx->master_key_descriptor); + FS_KEY_DESCRIPTOR_SIZE, descriptor); if (!description) - return -ENOMEM; + return ERR_PTR(-ENOMEM); - keyring_key = request_key(&key_type_logon, description, NULL); + key = request_key(&key_type_logon, description, NULL); kfree(description); - if (IS_ERR(keyring_key)) - return PTR_ERR(keyring_key); - down_read(&keyring_key->sem); - - if (keyring_key->type != &key_type_logon) { - printk_once(KERN_WARNING - "%s: key type must be logon\n", __func__); - res = -ENOKEY; - goto out; - } - ukp = user_key_payload_locked(keyring_key); - if (!ukp) { - /* key was revoked before we acquired its semaphore */ - res = -EKEYREVOKED; - goto out; - } - if (ukp->datalen != sizeof(struct fscrypt_key)) { - res = -EINVAL; - goto out; + if (IS_ERR(key)) + return key; + + down_read(&key->sem); + ukp = user_key_payload_locked(key); + + if (!ukp) /* was the key revoked before we acquired its semaphore? */ + goto invalid; + + payload = (const struct fscrypt_key *)ukp->data; + + if (ukp->datalen != sizeof(struct fscrypt_key) || + payload->size < 1 || payload->size > FS_MAX_KEY_SIZE) { + fscrypt_warn(NULL, + "key with description '%s' has invalid payload", + key->description); + goto invalid; } - master_key = (struct fscrypt_key *)ukp->data; - BUILD_BUG_ON(FS_AES_128_ECB_KEY_SIZE != FS_KEY_DERIVATION_NONCE_SIZE); - - if (master_key->size < min_keysize || master_key->size > FS_MAX_KEY_SIZE - || master_key->size % AES_BLOCK_SIZE != 0) { - printk_once(KERN_WARNING - "%s: key size incorrect: %d\n", - __func__, master_key->size); - res = -ENOKEY; - goto out; + + if (payload->size < min_keysize) { + fscrypt_warn(NULL, + "key with description '%s' is too short (got %u bytes, need %u+ bytes)", + key->description, payload->size, min_keysize); + goto invalid; } - res = derive_key_aes(ctx->nonce, master_key, raw_key); -out: - up_read(&keyring_key->sem); - key_put(keyring_key); - return res; + + *payload_ret = payload; + return key; + +invalid: + up_read(&key->sem); + key_put(key); + return ERR_PTR(-ENOKEY); } -static const struct { - const char *cipher_str; - int keysize; -} available_modes[] = { - [FS_ENCRYPTION_MODE_AES_256_XTS] = { "xts(aes)", - FS_AES_256_XTS_KEY_SIZE }, - [FS_ENCRYPTION_MODE_AES_256_CTS] = { "cts(cbc(aes))", - FS_AES_256_CTS_KEY_SIZE }, - [FS_ENCRYPTION_MODE_AES_128_CBC] = { "cbc(aes)", - FS_AES_128_CBC_KEY_SIZE }, - [FS_ENCRYPTION_MODE_AES_128_CTS] = { "cts(cbc(aes))", - FS_AES_128_CTS_KEY_SIZE }, +static struct fscrypt_mode available_modes[] = { + [FS_ENCRYPTION_MODE_AES_256_XTS] = { + .friendly_name = "AES-256-XTS", + .cipher_str = "xts(aes)", + .keysize = 64, + .ivsize = 16, + }, + [FS_ENCRYPTION_MODE_AES_256_CTS] = { + .friendly_name = "AES-256-CTS-CBC", + .cipher_str = "cts(cbc(aes))", + .keysize = 32, + .ivsize = 16, + }, + [FS_ENCRYPTION_MODE_AES_128_CBC] = { + .friendly_name = "AES-128-CBC", + .cipher_str = "cbc(aes)", + .keysize = 16, + .ivsize = 16, + .needs_essiv = true, + }, + [FS_ENCRYPTION_MODE_AES_128_CTS] = { + .friendly_name = "AES-128-CTS-CBC", + .cipher_str = "cts(cbc(aes))", + .keysize = 16, + .ivsize = 16, + }, + [FS_ENCRYPTION_MODE_ADIANTUM] = { + .friendly_name = "Adiantum", + .cipher_str = "adiantum(xchacha12,aes)", + .keysize = 32, + .ivsize = 32, + }, }; -static int determine_cipher_type(struct fscrypt_info *ci, struct inode *inode, - const char **cipher_str_ret, int *keysize_ret) +static struct fscrypt_mode * +select_encryption_mode(const struct fscrypt_info *ci, const struct inode *inode) { - u32 mode; - if (!fscrypt_valid_enc_modes(ci->ci_data_mode, ci->ci_filename_mode)) { - pr_warn_ratelimited("fscrypt: inode %lu uses unsupported encryption modes (contents mode %d, filenames mode %d)\n", - inode->i_ino, - ci->ci_data_mode, ci->ci_filename_mode); - return -EINVAL; + fscrypt_warn(inode->i_sb, + "inode %lu uses unsupported encryption modes (contents mode %d, filenames mode %d)", + inode->i_ino, ci->ci_data_mode, + ci->ci_filename_mode); + return ERR_PTR(-EINVAL); } - if (S_ISREG(inode->i_mode)) { - mode = ci->ci_data_mode; - } else if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) { - mode = ci->ci_filename_mode; + if (S_ISREG(inode->i_mode)) + return &available_modes[ci->ci_data_mode]; + + if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) + return &available_modes[ci->ci_filename_mode]; + + WARN_ONCE(1, "fscrypt: filesystem tried to load encryption info for inode %lu, which is not encryptable (file type %d)\n", + inode->i_ino, (inode->i_mode & S_IFMT)); + return ERR_PTR(-EINVAL); +} + +/* Find the master key, then derive the inode's actual encryption key */ +static int find_and_derive_key(const struct inode *inode, + const struct fscrypt_context *ctx, + u8 *derived_key, const struct fscrypt_mode *mode) +{ + struct key *key; + const struct fscrypt_key *payload; + int err; + + key = find_and_lock_process_key(FS_KEY_DESC_PREFIX, + ctx->master_key_descriptor, + mode->keysize, &payload); + if (key == ERR_PTR(-ENOKEY) && inode->i_sb->s_cop->key_prefix) { + key = find_and_lock_process_key(inode->i_sb->s_cop->key_prefix, + ctx->master_key_descriptor, + mode->keysize, &payload); + } + if (IS_ERR(key)) + return PTR_ERR(key); + + if (ctx->flags & FS_POLICY_FLAG_DIRECT_KEY) { + if (mode->ivsize < offsetofend(union fscrypt_iv, nonce)) { + fscrypt_warn(inode->i_sb, + "direct key mode not allowed with %s", + mode->friendly_name); + err = -EINVAL; + } else if (ctx->contents_encryption_mode != + ctx->filenames_encryption_mode) { + fscrypt_warn(inode->i_sb, + "direct key mode not allowed with different contents and filenames modes"); + err = -EINVAL; + } else { + memcpy(derived_key, payload->raw, mode->keysize); + err = 0; + } } else { - WARN_ONCE(1, "fscrypt: filesystem tried to load encryption info for inode %lu, which is not encryptable (file type %d)\n", - inode->i_ino, (inode->i_mode & S_IFMT)); - return -EINVAL; + err = derive_key_aes(payload->raw, ctx, derived_key, + mode->keysize); } + up_read(&key->sem); + key_put(key); + return err; +} - *cipher_str_ret = available_modes[mode].cipher_str; - *keysize_ret = available_modes[mode].keysize; - return 0; +/* Allocate and key a symmetric cipher object for the given encryption mode */ +static struct crypto_skcipher * +allocate_skcipher_for_mode(struct fscrypt_mode *mode, const u8 *raw_key, + const struct inode *inode) +{ + struct crypto_skcipher *tfm; + int err; + + tfm = crypto_alloc_skcipher(mode->cipher_str, 0, 0); + if (IS_ERR(tfm)) { + fscrypt_warn(inode->i_sb, + "error allocating '%s' transform for inode %lu: %ld", + mode->cipher_str, inode->i_ino, PTR_ERR(tfm)); + return tfm; + } + if (unlikely(!mode->logged_impl_name)) { + /* + * fscrypt performance can vary greatly depending on which + * crypto algorithm implementation is used. Help people debug + * performance problems by logging the ->cra_driver_name the + * first time a mode is used. Note that multiple threads can + * race here, but it doesn't really matter. + */ + mode->logged_impl_name = true; + pr_info("fscrypt: %s using implementation \"%s\"\n", + mode->friendly_name, + crypto_skcipher_alg(tfm)->base.cra_driver_name); + } + crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY); + err = crypto_skcipher_setkey(tfm, raw_key, mode->keysize); + if (err) + goto err_free_tfm; + + return tfm; + +err_free_tfm: + crypto_free_skcipher(tfm); + return ERR_PTR(err); } -static void put_crypt_info(struct fscrypt_info *ci) +/* Master key referenced by FS_POLICY_FLAG_DIRECT_KEY policy */ +struct fscrypt_master_key { + struct hlist_node mk_node; + refcount_t mk_refcount; + const struct fscrypt_mode *mk_mode; + struct crypto_skcipher *mk_ctfm; + u8 mk_descriptor[FS_KEY_DESCRIPTOR_SIZE]; + u8 mk_raw[FS_MAX_KEY_SIZE]; +}; + +static void free_master_key(struct fscrypt_master_key *mk) { - if (!ci) + if (mk) { + crypto_free_skcipher(mk->mk_ctfm); + kzfree(mk); + } +} + +static void put_master_key(struct fscrypt_master_key *mk) +{ + if (!refcount_dec_and_lock(&mk->mk_refcount, &fscrypt_master_keys_lock)) return; + hash_del(&mk->mk_node); + spin_unlock(&fscrypt_master_keys_lock); - crypto_free_skcipher(ci->ci_ctfm); - crypto_free_cipher(ci->ci_essiv_tfm); - kmem_cache_free(fscrypt_info_cachep, ci); + free_master_key(mk); +} + +/* + * Find/insert the given master key into the fscrypt_master_keys table. If + * found, it is returned with elevated refcount, and 'to_insert' is freed if + * non-NULL. If not found, 'to_insert' is inserted and returned if it's + * non-NULL; otherwise NULL is returned. + */ +static struct fscrypt_master_key * +find_or_insert_master_key(struct fscrypt_master_key *to_insert, + const u8 *raw_key, const struct fscrypt_mode *mode, + const struct fscrypt_info *ci) +{ + unsigned long hash_key; + struct fscrypt_master_key *mk; + + /* + * Careful: to avoid potentially leaking secret key bytes via timing + * information, we must key the hash table by descriptor rather than by + * raw key, and use crypto_memneq() when comparing raw keys. + */ + + BUILD_BUG_ON(sizeof(hash_key) > FS_KEY_DESCRIPTOR_SIZE); + memcpy(&hash_key, ci->ci_master_key_descriptor, sizeof(hash_key)); + + spin_lock(&fscrypt_master_keys_lock); + hash_for_each_possible(fscrypt_master_keys, mk, mk_node, hash_key) { + if (memcmp(ci->ci_master_key_descriptor, mk->mk_descriptor, + FS_KEY_DESCRIPTOR_SIZE) != 0) + continue; + if (mode != mk->mk_mode) + continue; + if (crypto_memneq(raw_key, mk->mk_raw, mode->keysize)) + continue; + /* using existing tfm with same (descriptor, mode, raw_key) */ + refcount_inc(&mk->mk_refcount); + spin_unlock(&fscrypt_master_keys_lock); + free_master_key(to_insert); + return mk; + } + if (to_insert) + hash_add(fscrypt_master_keys, &to_insert->mk_node, hash_key); + spin_unlock(&fscrypt_master_keys_lock); + return to_insert; +} + +/* Prepare to encrypt directly using the master key in the given mode */ +static struct fscrypt_master_key * +fscrypt_get_master_key(const struct fscrypt_info *ci, struct fscrypt_mode *mode, + const u8 *raw_key, const struct inode *inode) +{ + struct fscrypt_master_key *mk; + int err; + + /* Is there already a tfm for this key? */ + mk = find_or_insert_master_key(NULL, raw_key, mode, ci); + if (mk) + return mk; + + /* Nope, allocate one. */ + mk = kzalloc(sizeof(*mk), GFP_NOFS); + if (!mk) + return ERR_PTR(-ENOMEM); + refcount_set(&mk->mk_refcount, 1); + mk->mk_mode = mode; + mk->mk_ctfm = allocate_skcipher_for_mode(mode, raw_key, inode); + if (IS_ERR(mk->mk_ctfm)) { + err = PTR_ERR(mk->mk_ctfm); + mk->mk_ctfm = NULL; + goto err_free_mk; + } + memcpy(mk->mk_descriptor, ci->ci_master_key_descriptor, + FS_KEY_DESCRIPTOR_SIZE); + memcpy(mk->mk_raw, raw_key, mode->keysize); + + return find_or_insert_master_key(mk, raw_key, mode, ci); + +err_free_mk: + free_master_key(mk); + return ERR_PTR(err); } static int derive_essiv_salt(const u8 *key, int keysize, u8 *salt) @@ -198,8 +387,9 @@ static int derive_essiv_salt(const u8 *key, int keysize, u8 *salt) tfm = crypto_alloc_shash("sha256", 0, 0); if (IS_ERR(tfm)) { - pr_warn_ratelimited("fscrypt: error allocating SHA-256 transform: %ld\n", - PTR_ERR(tfm)); + fscrypt_warn(NULL, + "error allocating SHA-256 transform: %ld", + PTR_ERR(tfm)); return PTR_ERR(tfm); } prev_tfm = cmpxchg(&essiv_hash_tfm, NULL, tfm); @@ -254,13 +444,68 @@ void __exit fscrypt_essiv_cleanup(void) crypto_free_shash(essiv_hash_tfm); } +/* + * Given the encryption mode and key (normally the derived key, but for + * FS_POLICY_FLAG_DIRECT_KEY mode it's the master key), set up the inode's + * symmetric cipher transform object(s). + */ +static int setup_crypto_transform(struct fscrypt_info *ci, + struct fscrypt_mode *mode, + const u8 *raw_key, const struct inode *inode) +{ + struct fscrypt_master_key *mk; + struct crypto_skcipher *ctfm; + int err; + + if (ci->ci_flags & FS_POLICY_FLAG_DIRECT_KEY) { + mk = fscrypt_get_master_key(ci, mode, raw_key, inode); + if (IS_ERR(mk)) + return PTR_ERR(mk); + ctfm = mk->mk_ctfm; + } else { + mk = NULL; + ctfm = allocate_skcipher_for_mode(mode, raw_key, inode); + if (IS_ERR(ctfm)) + return PTR_ERR(ctfm); + } + ci->ci_master_key = mk; + ci->ci_ctfm = ctfm; + + if (mode->needs_essiv) { + /* ESSIV implies 16-byte IVs which implies !DIRECT_KEY */ + WARN_ON(mode->ivsize != AES_BLOCK_SIZE); + WARN_ON(ci->ci_flags & FS_POLICY_FLAG_DIRECT_KEY); + + err = init_essiv_generator(ci, raw_key, mode->keysize); + if (err) { + fscrypt_warn(inode->i_sb, + "error initializing ESSIV generator for inode %lu: %d", + inode->i_ino, err); + return err; + } + } + return 0; +} + +static void put_crypt_info(struct fscrypt_info *ci) +{ + if (!ci) + return; + + if (ci->ci_master_key) { + put_master_key(ci->ci_master_key); + } else { + crypto_free_skcipher(ci->ci_ctfm); + crypto_free_cipher(ci->ci_essiv_tfm); + } + kmem_cache_free(fscrypt_info_cachep, ci); +} + int fscrypt_get_encryption_info(struct inode *inode) { struct fscrypt_info *crypt_info; struct fscrypt_context ctx; - struct crypto_skcipher *ctfm; - const char *cipher_str; - int keysize; + struct fscrypt_mode *mode; u8 *raw_key = NULL; int res; @@ -274,7 +519,7 @@ int fscrypt_get_encryption_info(struct inode *inode) res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx)); if (res < 0) { if (!fscrypt_dummy_context_enabled(inode) || - inode->i_sb->s_cop->is_encrypted(inode)) + IS_ENCRYPTED(inode)) return res; /* Fake up a context for an unencrypted directory */ memset(&ctx, 0, sizeof(ctx)); @@ -292,72 +537,42 @@ int fscrypt_get_encryption_info(struct inode *inode) if (ctx.flags & ~FS_POLICY_FLAGS_VALID) return -EINVAL; - crypt_info = kmem_cache_alloc(fscrypt_info_cachep, GFP_NOFS); + crypt_info = kmem_cache_zalloc(fscrypt_info_cachep, GFP_NOFS); if (!crypt_info) return -ENOMEM; crypt_info->ci_flags = ctx.flags; crypt_info->ci_data_mode = ctx.contents_encryption_mode; crypt_info->ci_filename_mode = ctx.filenames_encryption_mode; - crypt_info->ci_ctfm = NULL; - crypt_info->ci_essiv_tfm = NULL; - memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor, - sizeof(crypt_info->ci_master_key)); + memcpy(crypt_info->ci_master_key_descriptor, ctx.master_key_descriptor, + FS_KEY_DESCRIPTOR_SIZE); + memcpy(crypt_info->ci_nonce, ctx.nonce, FS_KEY_DERIVATION_NONCE_SIZE); - res = determine_cipher_type(crypt_info, inode, &cipher_str, &keysize); - if (res) + mode = select_encryption_mode(crypt_info, inode); + if (IS_ERR(mode)) { + res = PTR_ERR(mode); goto out; + } + WARN_ON(mode->ivsize > FSCRYPT_MAX_IV_SIZE); + crypt_info->ci_mode = mode; /* - * This cannot be a stack buffer because it is passed to the scatterlist - * crypto API as part of key derivation. + * This cannot be a stack buffer because it may be passed to the + * scatterlist crypto API as part of key derivation. */ res = -ENOMEM; - raw_key = kmalloc(FS_MAX_KEY_SIZE, GFP_NOFS); + raw_key = kmalloc(mode->keysize, GFP_NOFS); if (!raw_key) goto out; - res = validate_user_key(crypt_info, &ctx, raw_key, FS_KEY_DESC_PREFIX, - keysize); - if (res && inode->i_sb->s_cop->key_prefix) { - int res2 = validate_user_key(crypt_info, &ctx, raw_key, - inode->i_sb->s_cop->key_prefix, - keysize); - if (res2) { - if (res2 == -ENOKEY) - res = -ENOKEY; - goto out; - } - } else if (res) { - goto out; - } - ctfm = crypto_alloc_skcipher(cipher_str, 0, 0); - if (!ctfm || IS_ERR(ctfm)) { - res = ctfm ? PTR_ERR(ctfm) : -ENOMEM; - pr_debug("%s: error %d (inode %lu) allocating crypto tfm\n", - __func__, res, inode->i_ino); + res = find_and_derive_key(inode, &ctx, raw_key, mode); + if (res) goto out; - } - crypt_info->ci_ctfm = ctfm; - crypto_skcipher_clear_flags(ctfm, ~0); - crypto_skcipher_set_flags(ctfm, CRYPTO_TFM_REQ_WEAK_KEY); - /* - * if the provided key is longer than keysize, we use the first - * keysize bytes of the derived key only - */ - res = crypto_skcipher_setkey(ctfm, raw_key, keysize); + + res = setup_crypto_transform(crypt_info, mode, raw_key, inode); if (res) goto out; - if (S_ISREG(inode->i_mode) && - crypt_info->ci_data_mode == FS_ENCRYPTION_MODE_AES_128_CBC) { - res = init_essiv_generator(crypt_info, raw_key, keysize); - if (res) { - pr_debug("%s: error %d (inode %lu) allocating essiv tfm\n", - __func__, res, inode->i_ino); - goto out; - } - } if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) == NULL) crypt_info = NULL; out: @@ -369,19 +584,9 @@ out: } EXPORT_SYMBOL(fscrypt_get_encryption_info); -void fscrypt_put_encryption_info(struct inode *inode, struct fscrypt_info *ci) +void fscrypt_put_encryption_info(struct inode *inode) { - struct fscrypt_info *prev; - - if (ci == NULL) - ci = ACCESS_ONCE(inode->i_crypt_info); - if (ci == NULL) - return; - - prev = cmpxchg(&inode->i_crypt_info, ci, NULL); - if (prev != ci) - return; - - put_crypt_info(ci); + put_crypt_info(inode->i_crypt_info); + inode->i_crypt_info = NULL; } EXPORT_SYMBOL(fscrypt_put_encryption_info); diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index d13a154c8424..bf6590c945cb 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -112,7 +112,7 @@ int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg) struct fscrypt_policy policy; int res; - if (!inode->i_sb->s_cop->is_encrypted(inode)) + if (!IS_ENCRYPTED(inode)) return -ENODATA; res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx)); @@ -169,11 +169,11 @@ int fscrypt_has_permitted_context(struct inode *parent, struct inode *child) return 1; /* No restrictions if the parent directory is unencrypted */ - if (!cops->is_encrypted(parent)) + if (!IS_ENCRYPTED(parent)) return 1; /* Encrypted directories must not contain unencrypted files */ - if (!cops->is_encrypted(child)) + if (!IS_ENCRYPTED(child)) return 0; /* @@ -201,7 +201,8 @@ int fscrypt_has_permitted_context(struct inode *parent, struct inode *child) child_ci = child->i_crypt_info; if (parent_ci && child_ci) { - return memcmp(parent_ci->ci_master_key, child_ci->ci_master_key, + return memcmp(parent_ci->ci_master_key_descriptor, + child_ci->ci_master_key_descriptor, FS_KEY_DESCRIPTOR_SIZE) == 0 && (parent_ci->ci_data_mode == child_ci->ci_data_mode) && (parent_ci->ci_filename_mode == @@ -256,7 +257,7 @@ int fscrypt_inherit_context(struct inode *parent, struct inode *child, ctx.contents_encryption_mode = ci->ci_data_mode; ctx.filenames_encryption_mode = ci->ci_filename_mode; ctx.flags = ci->ci_flags; - memcpy(ctx.master_key_descriptor, ci->ci_master_key, + memcpy(ctx.master_key_descriptor, ci->ci_master_key_descriptor, FS_KEY_DESCRIPTOR_SIZE); get_random_bytes(ctx.nonce, FS_KEY_DERIVATION_NONCE_SIZE); BUILD_BUG_ON(sizeof(ctx) != FSCRYPT_SET_CONTEXT_MAX_SIZE); diff --git a/fs/dcache.c b/fs/dcache.c index 9ac1290ae44f..c04352b1cf66 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -3279,6 +3279,7 @@ char *d_absolute_path(const struct path *path, return ERR_PTR(error); return res; } +EXPORT_SYMBOL(d_absolute_path); /* * same as __d_path but appends "(deleted)" for unlinked files. diff --git a/fs/eventpoll.c b/fs/eventpoll.c index c291bf61afb9..9a309f74056e 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -34,6 +34,7 @@ #include <linux/mutex.h> #include <linux/anon_inodes.h> #include <linux/device.h> +#include <linux/freezer.h> #include <linux/uaccess.h> #include <asm/io.h> #include <asm/mman.h> @@ -1826,7 +1827,8 @@ fetch_events: } spin_unlock_irqrestore(&ep->lock, flags); - if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS)) + if (!freezable_schedule_hrtimeout_range(to, slack, + HRTIMER_MODE_ABS)) timed_out = 1; spin_lock_irqsave(&ep->lock, flags); diff --git a/fs/exec.c b/fs/exec.c index 92fd21f0b0ff..c81b923e6df1 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1305,7 +1305,7 @@ EXPORT_SYMBOL(flush_old_exec); void would_dump(struct linux_binprm *bprm, struct file *file) { struct inode *inode = file_inode(file); - if (inode_permission(inode, MAY_READ) < 0) { + if (inode_permission2(file->f_path.mnt, inode, MAY_READ) < 0) { struct user_namespace *old, *user_ns; bprm->interp_flags |= BINPRM_FLAGS_ENFORCE_NONDUMP; diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index 0ac62811b341..f17715d140b5 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -377,9 +377,8 @@ err: * and will start a new collection. Eventually caller must submit the last * segment if present. */ -static int readpage_strip(void *data, struct page *page) +static int __readpage_strip(struct page_collect *pcol, struct page *page) { - struct page_collect *pcol = data; struct inode *inode = pcol->inode; struct exofs_i_info *oi = exofs_i(inode); loff_t i_size = i_size_read(inode); @@ -470,6 +469,13 @@ fail: return ret; } +static int readpage_strip(struct file *data, struct page *page) +{ + struct page_collect *pcol = (struct page_collect *)data; + + return __readpage_strip(pcol, page); +} + static int exofs_readpages(struct file *file, struct address_space *mapping, struct list_head *pages, unsigned nr_pages) { @@ -499,7 +505,7 @@ static int _readpage(struct page *page, bool read_4_write) _pcol_init(&pcol, 1, page->mapping->host); pcol.read_4_write = read_4_write; - ret = readpage_strip(&pcol, page); + ret = __readpage_strip(&pcol, page); if (ret) { EXOFS_ERR("_readpage => %d\n", ret); return ret; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 6c5b4301ee37..48b558ed00b4 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -34,17 +34,15 @@ #include <linux/percpu_counter.h> #include <linux/ratelimit.h> #include <crypto/hash.h> -#ifdef CONFIG_EXT4_FS_ENCRYPTION -#include <linux/fscrypt_supp.h> -#else -#include <linux/fscrypt_notsupp.h> -#endif #include <linux/falloc.h> #include <linux/percpu-rwsem.h> #ifdef __KERNEL__ #include <linux/compat.h> #endif +#define __FS_HAS_ENCRYPTION IS_ENABLED(CONFIG_EXT4_FS_ENCRYPTION) +#include <linux/fscrypt.h> + /* * The fourth extended filesystem constants/structures */ diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 6064bcb8572b..29f29d5c0cd3 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -18,6 +18,7 @@ #include "ext4.h" #include "xattr.h" #include "truncate.h" +#include <trace/events/android_fs.h> #define EXT4_XATTR_SYSTEM_DATA "data" #define EXT4_MIN_INLINE_DATA_SIZE ((sizeof(__le32) * EXT4_N_BLOCKS)) @@ -511,6 +512,17 @@ int ext4_readpage_inline(struct inode *inode, struct page *page) return -EAGAIN; } + if (trace_android_fs_dataread_start_enabled()) { + char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; + + path = android_fstrace_get_pathname(pathbuf, + MAX_TRACE_PATHBUF_LEN, + inode); + trace_android_fs_dataread_start(inode, page_offset(page), + PAGE_SIZE, current->pid, + path, current->comm); + } + /* * Current inline data can only exist in the 1st page, * So for all the other pages, just set them uptodate. @@ -522,6 +534,8 @@ int ext4_readpage_inline(struct inode *inode, struct page *page) SetPageUptodate(page); } + trace_android_fs_dataread_end(inode, page_offset(page), PAGE_SIZE); + up_read(&EXT4_I(inode)->xattr_sem); unlock_page(page); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 5f03a4fabeaa..1312111dd9a2 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -46,6 +46,7 @@ #include "truncate.h" #include <trace/events/ext4.h> +#include <trace/events/android_fs.h> #define MPAGE_DA_EXTENT_TAIL 0x01 @@ -1271,6 +1272,16 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping, if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; + if (trace_android_fs_datawrite_start_enabled()) { + char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; + + path = android_fstrace_get_pathname(pathbuf, + MAX_TRACE_PATHBUF_LEN, + inode); + trace_android_fs_datawrite_start(inode, pos, len, + current->pid, path, + current->comm); + } trace_ext4_write_begin(inode, pos, len, flags); /* * Reserve one block more for addition to orphan list in case @@ -1409,6 +1420,7 @@ static int ext4_write_end(struct file *file, int i_size_changed = 0; int inline_data = ext4_has_inline_data(inode); + trace_android_fs_datawrite_end(inode, pos, len); trace_ext4_write_end(inode, pos, len, copied); if (inline_data) { ret = ext4_write_inline_data_end(inode, pos, len, @@ -1514,6 +1526,7 @@ static int ext4_journalled_write_end(struct file *file, int size_changed = 0; int inline_data = ext4_has_inline_data(inode); + trace_android_fs_datawrite_end(inode, pos, len); trace_ext4_journalled_write_end(inode, pos, len, copied); from = pos & (PAGE_SIZE - 1); to = from + len; @@ -2646,8 +2659,8 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd) mpd->map.m_len = 0; mpd->next_page = index; while (index <= end) { - nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag, - min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); + nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end, + tag); if (nr_pages == 0) goto out; @@ -2655,16 +2668,6 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd) struct page *page = pvec.pages[i]; /* - * At this point, the page may be truncated or - * invalidated (changing page->mapping to NULL), or - * even swizzled back from swapper_space to tmpfs file - * mapping. However, page->index will not change - * because we have a reference on the page. - */ - if (page->index > end) - goto out; - - /* * Accumulated enough dirty pages? This doesn't apply * to WB_SYNC_ALL mode. For integrity sync we have to * keep going because someone may be concurrently @@ -3051,6 +3054,16 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, len, flags, pagep, fsdata); } *fsdata = (void *)0; + if (trace_android_fs_datawrite_start_enabled()) { + char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; + + path = android_fstrace_get_pathname(pathbuf, + MAX_TRACE_PATHBUF_LEN, + inode); + trace_android_fs_datawrite_start(inode, pos, len, + current->pid, + path, current->comm); + } trace_ext4_da_write_begin(inode, pos, len, flags); if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { @@ -3169,6 +3182,7 @@ static int ext4_da_write_end(struct file *file, return ext4_write_end(file, mapping, pos, len, copied, page, fsdata); + trace_android_fs_datawrite_end(inode, pos, len); trace_ext4_da_write_end(inode, pos, len, copied); start = pos & (PAGE_SIZE - 1); end = start + copied - 1; @@ -3825,6 +3839,7 @@ static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter) size_t count = iov_iter_count(iter); loff_t offset = iocb->ki_pos; ssize_t ret; + int rw = iov_iter_rw(iter); #ifdef CONFIG_EXT4_FS_ENCRYPTION if (ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode)) @@ -3845,12 +3860,42 @@ static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter) if (WARN_ON_ONCE(IS_DAX(inode))) return 0; + if (trace_android_fs_dataread_start_enabled() && + (rw == READ)) { + char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; + + path = android_fstrace_get_pathname(pathbuf, + MAX_TRACE_PATHBUF_LEN, + inode); + trace_android_fs_dataread_start(inode, offset, count, + current->pid, path, + current->comm); + } + if (trace_android_fs_datawrite_start_enabled() && + (rw == WRITE)) { + char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; + + path = android_fstrace_get_pathname(pathbuf, + MAX_TRACE_PATHBUF_LEN, + inode); + trace_android_fs_datawrite_start(inode, offset, count, + current->pid, path, + current->comm); + } trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter)); if (iov_iter_rw(iter) == READ) ret = ext4_direct_IO_read(iocb, iter); else ret = ext4_direct_IO_write(iocb, iter); trace_ext4_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), ret); + + if (trace_android_fs_dataread_start_enabled() && + (rw == READ)) + trace_android_fs_dataread_end(inode, offset, count); + if (trace_android_fs_datawrite_start_enabled() && + (rw == WRITE)) + trace_android_fs_datawrite_end(inode, offset, count); + return ret; } @@ -4646,10 +4691,13 @@ void ext4_set_inode_flags(struct inode *inode) new_fl |= S_DIRSYNC; if (test_opt(inode->i_sb, DAX) && S_ISREG(inode->i_mode) && !ext4_should_journal_data(inode) && !ext4_has_inline_data(inode) && - !ext4_encrypted_inode(inode)) + !(flags & EXT4_ENCRYPT_FL)) new_fl |= S_DAX; + if (flags & EXT4_ENCRYPT_FL) + new_fl |= S_ENCRYPTED; inode_set_flags(inode, new_fl, - S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX); + S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX| + S_ENCRYPTED); } static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode, diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 161099f39ab9..76559e0f711f 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1562,24 +1562,14 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi struct inode *inode; struct ext4_dir_entry_2 *de; struct buffer_head *bh; + int err; - if (ext4_encrypted_inode(dir)) { - int res = fscrypt_get_encryption_info(dir); - - /* - * DCACHE_ENCRYPTED_WITH_KEY is set if the dentry is - * created while the directory was encrypted and we - * have access to the key. - */ - if (fscrypt_has_encryption_key(dir)) - fscrypt_set_encrypted_dentry(dentry); - fscrypt_set_d_op(dentry); - if (res && res != -ENOKEY) - return ERR_PTR(res); - } + err = fscrypt_prepare_lookup(dir, dentry, flags); + if (err) + return ERR_PTR(err); - if (dentry->d_name.len > EXT4_NAME_LEN) - return ERR_PTR(-ENAMETOOLONG); + if (dentry->d_name.len > EXT4_NAME_LEN) + return ERR_PTR(-ENAMETOOLONG); bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL); if (IS_ERR(bh)) @@ -3108,39 +3098,19 @@ static int ext4_symlink(struct inode *dir, struct inode *inode; int err, len = strlen(symname); int credits; - bool encryption_required; struct fscrypt_str disk_link; - struct fscrypt_symlink_data *sd = NULL; if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb)))) return -EIO; - disk_link.len = len + 1; - disk_link.name = (char *) symname; - - encryption_required = (ext4_encrypted_inode(dir) || - DUMMY_ENCRYPTION_ENABLED(EXT4_SB(dir->i_sb))); - if (encryption_required) { - err = fscrypt_get_encryption_info(dir); - if (err) - return err; - if (!fscrypt_has_encryption_key(dir)) - return -ENOKEY; - disk_link.len = (fscrypt_fname_encrypted_size(dir, len) + - sizeof(struct fscrypt_symlink_data)); - sd = kzalloc(disk_link.len, GFP_KERNEL); - if (!sd) - return -ENOMEM; - } - - if (disk_link.len > dir->i_sb->s_blocksize) { - err = -ENAMETOOLONG; - goto err_free_sd; - } + err = fscrypt_prepare_symlink(dir, symname, len, dir->i_sb->s_blocksize, + &disk_link); + if (err) + return err; err = dquot_initialize(dir); if (err) - goto err_free_sd; + return err; if ((disk_link.len > EXT4_N_BLOCKS * 4)) { /* @@ -3169,27 +3139,18 @@ static int ext4_symlink(struct inode *dir, if (IS_ERR(inode)) { if (handle) ext4_journal_stop(handle); - err = PTR_ERR(inode); - goto err_free_sd; + return PTR_ERR(inode); } - if (encryption_required) { - struct qstr istr; - struct fscrypt_str ostr = - FSTR_INIT(sd->encrypted_path, disk_link.len); - - istr.name = (const unsigned char *) symname; - istr.len = len; - err = fscrypt_fname_usr_to_disk(inode, &istr, &ostr); + if (IS_ENCRYPTED(inode)) { + err = fscrypt_encrypt_symlink(inode, symname, len, &disk_link); if (err) goto err_drop_inode; - sd->len = cpu_to_le16(ostr.len); - disk_link.name = (char *) sd; inode->i_op = &ext4_encrypted_symlink_inode_operations; } if ((disk_link.len > EXT4_N_BLOCKS * 4)) { - if (!encryption_required) + if (!IS_ENCRYPTED(inode)) inode->i_op = &ext4_symlink_inode_operations; inode_nohighmem(inode); ext4_set_aops(inode); @@ -3231,7 +3192,7 @@ static int ext4_symlink(struct inode *dir, } else { /* clear the extent format for fast symlink */ ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS); - if (!encryption_required) { + if (!IS_ENCRYPTED(inode)) { inode->i_op = &ext4_fast_symlink_inode_operations; inode->i_link = (char *)&EXT4_I(inode)->i_data; } @@ -3246,16 +3207,17 @@ static int ext4_symlink(struct inode *dir, if (handle) ext4_journal_stop(handle); - kfree(sd); - return err; + goto out_free_encrypted_link; + err_drop_inode: if (handle) ext4_journal_stop(handle); clear_nlink(inode); unlock_new_inode(inode); iput(inode); -err_free_sd: - kfree(sd); +out_free_encrypted_link: + if (disk_link.name != (unsigned char *)symname) + kfree(disk_link.name); return err; } diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index 9ffa6fad18db..039aa698159a 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -46,6 +46,7 @@ #include <linux/cleancache.h> #include "ext4.h" +#include <trace/events/android_fs.h> static inline bool ext4_bio_encrypted(struct bio *bio) { @@ -56,6 +57,17 @@ static inline bool ext4_bio_encrypted(struct bio *bio) #endif } +static void +ext4_trace_read_completion(struct bio *bio) +{ + struct page *first_page = bio->bi_io_vec[0].bv_page; + + if (first_page != NULL) + trace_android_fs_dataread_end(first_page->mapping->host, + page_offset(first_page), + bio->bi_iter.bi_size); +} + /* * I/O completion handler for multipage BIOs. * @@ -73,11 +85,14 @@ static void mpage_end_io(struct bio *bio) struct bio_vec *bv; int i; + if (trace_android_fs_dataread_start_enabled()) + ext4_trace_read_completion(bio); + if (ext4_bio_encrypted(bio)) { if (bio->bi_status) { fscrypt_release_ctx(bio->bi_private); } else { - fscrypt_decrypt_bio_pages(bio->bi_private, bio); + fscrypt_enqueue_decrypt_bio(bio->bi_private, bio); return; } } @@ -96,6 +111,30 @@ static void mpage_end_io(struct bio *bio) bio_put(bio); } +static void +ext4_submit_bio_read(struct bio *bio) +{ + if (trace_android_fs_dataread_start_enabled()) { + struct page *first_page = bio->bi_io_vec[0].bv_page; + + if (first_page != NULL) { + char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; + + path = android_fstrace_get_pathname(pathbuf, + MAX_TRACE_PATHBUF_LEN, + first_page->mapping->host); + trace_android_fs_dataread_start( + first_page->mapping->host, + page_offset(first_page), + bio->bi_iter.bi_size, + current->pid, + path, + current->comm); + } + } + submit_bio(bio); +} + int ext4_mpage_readpages(struct address_space *mapping, struct list_head *pages, struct page *page, unsigned nr_pages) @@ -236,7 +275,7 @@ int ext4_mpage_readpages(struct address_space *mapping, */ if (bio && (last_block_in_bio != blocks[0] - 1)) { submit_and_realloc: - submit_bio(bio); + ext4_submit_bio_read(bio); bio = NULL; } if (bio == NULL) { @@ -269,14 +308,14 @@ int ext4_mpage_readpages(struct address_space *mapping, if (((map.m_flags & EXT4_MAP_BOUNDARY) && (relative_block == map.m_len)) || (first_hole != blocks_per_page)) { - submit_bio(bio); + ext4_submit_bio_read(bio); bio = NULL; } else last_block_in_bio = blocks[blocks_per_page - 1]; goto next_page; confused: if (bio) { - submit_bio(bio); + ext4_submit_bio_read(bio); bio = NULL; } if (!PageUptodate(page)) @@ -289,6 +328,6 @@ int ext4_mpage_readpages(struct address_space *mapping, } BUG_ON(pages && !list_empty(pages)); if (bio) - submit_bio(bio); + ext4_submit_bio_read(bio); return 0; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ffc985d78137..a0c1c57e6f5f 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1116,9 +1116,7 @@ void ext4_clear_inode(struct inode *inode) jbd2_free_inode(EXT4_I(inode)->jinode); EXT4_I(inode)->jinode = NULL; } -#ifdef CONFIG_EXT4_FS_ENCRYPTION - fscrypt_put_encryption_info(inode, NULL); -#endif + fscrypt_put_encryption_info(inode); } static struct inode *ext4_nfs_get_inode(struct super_block *sb, @@ -1229,7 +1227,8 @@ static int ext4_set_context(struct inode *inode, const void *ctx, size_t len, ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); /* - * Update inode->i_flags - e.g. S_DAX may get disabled + * Update inode->i_flags - S_ENCRYPTED will be enabled, + * S_DAX may be disabled */ ext4_set_inode_flags(inode); } @@ -1254,7 +1253,10 @@ retry: ctx, len, 0); if (!res) { ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT); - /* Update inode->i_flags - e.g. S_DAX may get disabled */ + /* + * Update inode->i_flags - S_ENCRYPTED will be enabled, + * S_DAX may be disabled + */ ext4_set_inode_flags(inode); res = ext4_mark_inode_dirty(handle, inode); if (res) @@ -1274,24 +1276,13 @@ static bool ext4_dummy_context(struct inode *inode) return DUMMY_ENCRYPTION_ENABLED(EXT4_SB(inode->i_sb)); } -static unsigned ext4_max_namelen(struct inode *inode) -{ - return S_ISLNK(inode->i_mode) ? inode->i_sb->s_blocksize : - EXT4_NAME_LEN; -} - static const struct fscrypt_operations ext4_cryptops = { .key_prefix = "ext4:", .get_context = ext4_get_context, .set_context = ext4_set_context, .dummy_context = ext4_dummy_context, - .is_encrypted = ext4_encrypted_inode, .empty_dir = ext4_empty_dir, - .max_namelen = ext4_max_namelen, -}; -#else -static const struct fscrypt_operations ext4_cryptops = { - .is_encrypted = ext4_encrypted_inode, + .max_namelen = EXT4_NAME_LEN, }; #endif @@ -4182,7 +4173,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sb->s_op = &ext4_sops; sb->s_export_op = &ext4_export_ops; sb->s_xattr = ext4_xattr_handlers; +#ifdef CONFIG_EXT4_FS_ENCRYPTION sb->s_cop = &ext4_cryptops; +#endif #ifdef CONFIG_QUOTA sb->dq_op = &ext4_quota_operations; if (ext4_has_feature_quota(sb)) diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c index a2006c9af1d9..dd05af983092 100644 --- a/fs/ext4/symlink.c +++ b/fs/ext4/symlink.c @@ -28,59 +28,28 @@ static const char *ext4_encrypted_get_link(struct dentry *dentry, struct delayed_call *done) { struct page *cpage = NULL; - char *caddr, *paddr = NULL; - struct fscrypt_str cstr, pstr; - struct fscrypt_symlink_data *sd; - int res; - u32 max_size = inode->i_sb->s_blocksize; + const void *caddr; + unsigned int max_size; + const char *paddr; if (!dentry) return ERR_PTR(-ECHILD); - res = fscrypt_get_encryption_info(inode); - if (res) - return ERR_PTR(res); - if (ext4_inode_is_fast_symlink(inode)) { - caddr = (char *) EXT4_I(inode)->i_data; + caddr = EXT4_I(inode)->i_data; max_size = sizeof(EXT4_I(inode)->i_data); } else { cpage = read_mapping_page(inode->i_mapping, 0, NULL); if (IS_ERR(cpage)) return ERR_CAST(cpage); caddr = page_address(cpage); + max_size = inode->i_sb->s_blocksize; } - /* Symlink is encrypted */ - sd = (struct fscrypt_symlink_data *)caddr; - cstr.name = sd->encrypted_path; - cstr.len = le16_to_cpu(sd->len); - if ((cstr.len + sizeof(struct fscrypt_symlink_data) - 1) > max_size) { - /* Symlink data on the disk is corrupted */ - res = -EFSCORRUPTED; - goto errout; - } - - res = fscrypt_fname_alloc_buffer(inode, cstr.len, &pstr); - if (res) - goto errout; - paddr = pstr.name; - - res = fscrypt_fname_disk_to_usr(inode, 0, 0, &cstr, &pstr); - if (res) - goto errout; - - /* Null-terminate the name */ - paddr[pstr.len] = '\0'; + paddr = fscrypt_get_symlink(inode, caddr, max_size, done); if (cpage) put_page(cpage); - set_delayed_call(done, kfree_link, paddr); return paddr; -errout: - if (cpage) - put_page(cpage); - kfree(paddr); - return ERR_PTR(res); } const struct inode_operations ext4_encrypted_symlink_inode_operations = { diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index 5e4860b8bbfc..63e599524085 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/acl.c * @@ -7,10 +8,6 @@ * Portions of this code from linux/fs/ext2/acl.c * * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/f2fs_fs.h> #include "f2fs.h" @@ -53,6 +50,9 @@ static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size) struct f2fs_acl_entry *entry = (struct f2fs_acl_entry *)(hdr + 1); const char *end = value + size; + if (size < sizeof(struct f2fs_acl_header)) + return ERR_PTR(-EINVAL); + if (hdr->a_version != cpu_to_le32(F2FS_ACL_VERSION)) return ERR_PTR(-EINVAL); @@ -160,7 +160,7 @@ static void *f2fs_acl_to_disk(struct f2fs_sb_info *sbi, return (void *)f2fs_acl; fail: - kfree(f2fs_acl); + kvfree(f2fs_acl); return ERR_PTR(-EINVAL); } @@ -190,7 +190,7 @@ static struct posix_acl *__f2fs_get_acl(struct inode *inode, int type, acl = NULL; else acl = ERR_PTR(retval); - kfree(value); + kvfree(value); return acl; } @@ -240,7 +240,7 @@ static int __f2fs_set_acl(struct inode *inode, int type, error = f2fs_setxattr(inode, name_index, "", value, size, ipage, 0); - kfree(value); + kvfree(value); if (!error) set_cached_acl(inode, type, acl); @@ -250,6 +250,9 @@ static int __f2fs_set_acl(struct inode *inode, int type, int f2fs_set_acl(struct inode *inode, struct posix_acl *acl, int type) { + if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) + return -EIO; + return __f2fs_set_acl(inode, type, acl, NULL); } @@ -267,7 +270,7 @@ static struct posix_acl *f2fs_acl_clone(const struct posix_acl *acl, sizeof(struct posix_acl_entry); clone = kmemdup(acl, size, flags); if (clone) - atomic_set(&clone->a_refcount, 1); + refcount_set(&clone->a_refcount, 1); } return clone; } @@ -393,12 +396,16 @@ int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage, error = __f2fs_set_acl(inode, ACL_TYPE_DEFAULT, default_acl, ipage); posix_acl_release(default_acl); + } else { + inode->i_default_acl = NULL; } if (acl) { if (!error) error = __f2fs_set_acl(inode, ACL_TYPE_ACCESS, acl, ipage); posix_acl_release(acl); + } else { + inode->i_acl = NULL; } return error; diff --git a/fs/f2fs/acl.h b/fs/f2fs/acl.h index 2c685185c24d..b96823c59b15 100644 --- a/fs/f2fs/acl.h +++ b/fs/f2fs/acl.h @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/acl.h * @@ -7,10 +8,6 @@ * Portions of this code from linux/fs/ext2/acl.h * * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef __F2FS_ACL_H__ #define __F2FS_ACL_H__ diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 170423ff2721..28739c0034b1 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/checkpoint.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/bio.h> @@ -24,12 +21,12 @@ #include <trace/events/f2fs.h> static struct kmem_cache *ino_entry_slab; -struct kmem_cache *inode_entry_slab; +struct kmem_cache *f2fs_inode_entry_slab; void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io) { + f2fs_build_fault_attr(sbi, 0, 0); set_ckpt_flags(sbi, CP_ERROR_FLAG); - sbi->sb->s_flags |= MS_RDONLY; if (!end_io) f2fs_flush_merged_writes(sbi); } @@ -37,7 +34,7 @@ void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io) /* * We guarantee no failure on the returned page. */ -struct page *grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index) +struct page *f2fs_grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index) { struct address_space *mapping = META_MAPPING(sbi); struct page *page = NULL; @@ -47,7 +44,7 @@ repeat: cond_resched(); goto repeat; } - f2fs_wait_on_page_writeback(page, META, true); + f2fs_wait_on_page_writeback(page, META, true, true); if (!PageUptodate(page)) SetPageUptodate(page); return page; @@ -71,6 +68,7 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index, .encrypted_page = NULL, .is_meta = is_meta, }; + int err; if (unlikely(!is_meta)) fio.op_flags &= ~REQ_META; @@ -85,11 +83,10 @@ repeat: fio.page = page; - if (f2fs_submit_page_bio(&fio)) { - memset(page_address(page), 0, PAGE_SIZE); - f2fs_stop_checkpoint(sbi, false); - f2fs_bug_on(sbi, 1); - return page; + err = f2fs_submit_page_bio(&fio); + if (err) { + f2fs_put_page(page, 1); + return ERR_PTR(err); } lock_page(page); @@ -98,24 +95,37 @@ repeat: goto repeat; } - /* - * if there is any IO error when accessing device, make our filesystem - * readonly and make sure do not write checkpoint with non-uptodate - * meta page. - */ - if (unlikely(!PageUptodate(page))) - f2fs_stop_checkpoint(sbi, false); + if (unlikely(!PageUptodate(page))) { + f2fs_put_page(page, 1); + return ERR_PTR(-EIO); + } out: return page; } -struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index) +struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index) { return __get_meta_page(sbi, index, true); } +struct page *f2fs_get_meta_page_nofail(struct f2fs_sb_info *sbi, pgoff_t index) +{ + struct page *page; + int count = 0; + +retry: + page = __get_meta_page(sbi, index, true); + if (IS_ERR(page)) { + if (PTR_ERR(page) == -EIO && + ++count <= DEFAULT_RETRY_IO_COUNT) + goto retry; + f2fs_stop_checkpoint(sbi, false); + } + return page; +} + /* for POR only */ -struct page *get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index) +struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index) { return __get_meta_page(sbi, index, false); } @@ -167,7 +177,7 @@ bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, /* * Readahead CP/NAT/SIT/SSA pages */ -int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, +int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type, bool sync) { struct page *page; @@ -233,7 +243,7 @@ out: return blkno - start; } -void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index) +void f2fs_ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index) { struct page *page; bool readahead = false; @@ -244,7 +254,7 @@ void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index) f2fs_put_page(page, 0); if (readahead) - ra_meta_pages(sbi, index, BIO_MAX_PAGES, META_POR, true); + f2fs_ra_meta_pages(sbi, index, BIO_MAX_PAGES, META_POR, true); } static int __f2fs_write_meta_page(struct page *page, @@ -255,19 +265,18 @@ static int __f2fs_write_meta_page(struct page *page, trace_f2fs_writepage(page, META); + if (unlikely(f2fs_cp_error(sbi))) + goto redirty_out; if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) goto redirty_out; if (wbc->for_reclaim && page->index < GET_SUM_BLOCK(sbi, 0)) goto redirty_out; - if (unlikely(f2fs_cp_error(sbi))) - goto redirty_out; - write_meta_page(sbi, page, io_type); + f2fs_do_write_meta_page(sbi, page, io_type); dec_page_count(sbi, F2FS_DIRTY_META); if (wbc->for_reclaim) - f2fs_submit_merged_write_cond(sbi, page->mapping->host, - 0, page->index, META); + f2fs_submit_merged_write_cond(sbi, NULL, page, 0, META); unlock_page(page); @@ -297,8 +306,9 @@ static int f2fs_write_meta_pages(struct address_space *mapping, goto skip_write; /* collect a number of dirty meta pages and write together */ - if (wbc->for_kupdate || - get_pages(sbi, F2FS_DIRTY_META) < nr_pages_to_skip(sbi, META)) + if (wbc->sync_mode != WB_SYNC_ALL && + get_pages(sbi, F2FS_DIRTY_META) < + nr_pages_to_skip(sbi, META)) goto skip_write; /* if locked failed, cp will flush dirty pages instead */ @@ -307,7 +317,7 @@ static int f2fs_write_meta_pages(struct address_space *mapping, trace_f2fs_writepages(mapping->host, wbc, META); diff = nr_pages_to_write(sbi, META, wbc); - written = sync_meta_pages(sbi, META, wbc->nr_to_write, FS_META_IO); + written = f2fs_sync_meta_pages(sbi, META, wbc->nr_to_write, FS_META_IO); mutex_unlock(&sbi->cp_mutex); wbc->nr_to_write = max((long)0, wbc->nr_to_write - written - diff); return 0; @@ -318,13 +328,14 @@ skip_write: return 0; } -long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type, +long f2fs_sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type, long nr_to_write, enum iostat_type io_type) { struct address_space *mapping = META_MAPPING(sbi); - pgoff_t index = 0, end = ULONG_MAX, prev = ULONG_MAX; + pgoff_t index = 0, prev = ULONG_MAX; struct pagevec pvec; long nwritten = 0; + int nr_pages; struct writeback_control wbc = { .for_reclaim = 0, }; @@ -334,13 +345,9 @@ long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type, blk_start_plug(&plug); - while (index <= end) { - int i, nr_pages; - nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, - PAGECACHE_TAG_DIRTY, - min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); - if (unlikely(nr_pages == 0)) - break; + while ((nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, + PAGECACHE_TAG_DIRTY))) { + int i; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; @@ -364,9 +371,8 @@ continue_unlock: goto continue_unlock; } - f2fs_wait_on_page_writeback(page, META, true); + f2fs_wait_on_page_writeback(page, META, true, true); - BUG_ON(PageWriteback(page)); if (!clear_page_dirty_for_io(page)) goto continue_unlock; @@ -398,9 +404,9 @@ static int f2fs_set_meta_page_dirty(struct page *page) if (!PageUptodate(page)) SetPageUptodate(page); if (!PageDirty(page)) { - f2fs_set_page_dirty_nobuffers(page); + __set_page_dirty_nobuffers(page); inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_META); - SetPagePrivate(page); + f2fs_set_page_private(page, 0); f2fs_trace_pid(page); return 1; } @@ -418,24 +424,23 @@ const struct address_space_operations f2fs_meta_aops = { #endif }; -static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) +static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, + unsigned int devidx, int type) { struct inode_management *im = &sbi->im[type]; struct ino_entry *e, *tmp; tmp = f2fs_kmem_cache_alloc(ino_entry_slab, GFP_NOFS); -retry: + radix_tree_preload(GFP_NOFS | __GFP_NOFAIL); spin_lock(&im->ino_lock); e = radix_tree_lookup(&im->ino_root, ino); if (!e) { e = tmp; - if (radix_tree_insert(&im->ino_root, ino, e)) { - spin_unlock(&im->ino_lock); - radix_tree_preload_end(); - goto retry; - } + if (unlikely(radix_tree_insert(&im->ino_root, ino, e))) + f2fs_bug_on(sbi, 1); + memset(e, 0, sizeof(struct ino_entry)); e->ino = ino; @@ -443,6 +448,10 @@ retry: if (type != ORPHAN_INO) im->ino_num++; } + + if (type == FLUSH_INO) + f2fs_set_bit(devidx, (char *)&e->dirty_device); + spin_unlock(&im->ino_lock); radix_tree_preload_end(); @@ -468,20 +477,20 @@ static void __remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) spin_unlock(&im->ino_lock); } -void add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) +void f2fs_add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) { /* add new dirty ino entry into list */ - __add_ino_entry(sbi, ino, type); + __add_ino_entry(sbi, ino, 0, type); } -void remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) +void f2fs_remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type) { /* remove dirty ino entry from list */ __remove_ino_entry(sbi, ino, type); } /* mode should be APPEND_INO or UPDATE_INO */ -bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode) +bool f2fs_exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode) { struct inode_management *im = &sbi->im[mode]; struct ino_entry *e; @@ -492,12 +501,12 @@ bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode) return e ? true : false; } -void release_ino_entry(struct f2fs_sb_info *sbi, bool all) +void f2fs_release_ino_entry(struct f2fs_sb_info *sbi, bool all) { struct ino_entry *e, *tmp; int i; - for (i = all ? ORPHAN_INO: APPEND_INO; i <= UPDATE_INO; i++) { + for (i = all ? ORPHAN_INO : APPEND_INO; i < MAX_INO_ENTRY; i++) { struct inode_management *im = &sbi->im[i]; spin_lock(&im->ino_lock); @@ -511,20 +520,40 @@ void release_ino_entry(struct f2fs_sb_info *sbi, bool all) } } -int acquire_orphan_inode(struct f2fs_sb_info *sbi) +void f2fs_set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino, + unsigned int devidx, int type) +{ + __add_ino_entry(sbi, ino, devidx, type); +} + +bool f2fs_is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino, + unsigned int devidx, int type) +{ + struct inode_management *im = &sbi->im[type]; + struct ino_entry *e; + bool is_dirty = false; + + spin_lock(&im->ino_lock); + e = radix_tree_lookup(&im->ino_root, ino); + if (e && f2fs_test_bit(devidx, (char *)&e->dirty_device)) + is_dirty = true; + spin_unlock(&im->ino_lock); + return is_dirty; +} + +int f2fs_acquire_orphan_inode(struct f2fs_sb_info *sbi) { struct inode_management *im = &sbi->im[ORPHAN_INO]; int err = 0; spin_lock(&im->ino_lock); -#ifdef CONFIG_F2FS_FAULT_INJECTION if (time_to_inject(sbi, FAULT_ORPHAN)) { spin_unlock(&im->ino_lock); f2fs_show_injection_info(FAULT_ORPHAN); return -ENOSPC; } -#endif + if (unlikely(im->ino_num >= sbi->max_orphans)) err = -ENOSPC; else @@ -534,7 +563,7 @@ int acquire_orphan_inode(struct f2fs_sb_info *sbi) return err; } -void release_orphan_inode(struct f2fs_sb_info *sbi) +void f2fs_release_orphan_inode(struct f2fs_sb_info *sbi) { struct inode_management *im = &sbi->im[ORPHAN_INO]; @@ -544,14 +573,14 @@ void release_orphan_inode(struct f2fs_sb_info *sbi) spin_unlock(&im->ino_lock); } -void add_orphan_inode(struct inode *inode) +void f2fs_add_orphan_inode(struct inode *inode) { /* add new orphan ino entry into list */ - __add_ino_entry(F2FS_I_SB(inode), inode->i_ino, ORPHAN_INO); - update_inode_page(inode); + __add_ino_entry(F2FS_I_SB(inode), inode->i_ino, 0, ORPHAN_INO); + f2fs_update_inode_page(inode); } -void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) +void f2fs_remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) { /* remove orphan entry from orphan list */ __remove_ino_entry(sbi, ino, ORPHAN_INO); @@ -561,17 +590,7 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) { struct inode *inode; struct node_info ni; - int err = acquire_orphan_inode(sbi); - - if (err) { - set_sbi_flag(sbi, SBI_NEED_FSCK); - f2fs_msg(sbi->sb, KERN_WARNING, - "%s: orphan failed (ino=%x), run fsck to fix.", - __func__, ino); - return err; - } - - __add_ino_entry(sbi, ino, ORPHAN_INO); + int err; inode = f2fs_iget_retry(sbi->sb, ino); if (IS_ERR(inode)) { @@ -583,30 +602,44 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) return PTR_ERR(inode); } + err = dquot_initialize(inode); + if (err) { + iput(inode); + goto err_out; + } + clear_nlink(inode); /* truncate all the data during iput */ iput(inode); - get_node_info(sbi, ino, &ni); + err = f2fs_get_node_info(sbi, ino, &ni); + if (err) + goto err_out; /* ENOMEM was fully retried in f2fs_evict_inode. */ if (ni.blk_addr != NULL_ADDR) { - set_sbi_flag(sbi, SBI_NEED_FSCK); - f2fs_msg(sbi->sb, KERN_WARNING, - "%s: orphan failed (ino=%x) by kernel, retry mount.", - __func__, ino); - return -EIO; + err = -EIO; + goto err_out; } - __remove_ino_entry(sbi, ino, ORPHAN_INO); return 0; + +err_out: + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_msg(sbi->sb, KERN_WARNING, + "%s: orphan failed (ino=%x), run fsck to fix.", + __func__, ino); + return err; } -int recover_orphan_inodes(struct f2fs_sb_info *sbi) +int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi) { block_t start_blk, orphan_blocks, i, j; unsigned int s_flags = sbi->sb->s_flags; int err = 0; +#ifdef CONFIG_QUOTA + int quota_enabled; +#endif if (!is_set_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG)) return 0; @@ -619,19 +652,29 @@ int recover_orphan_inodes(struct f2fs_sb_info *sbi) #ifdef CONFIG_QUOTA /* Needed for iput() to work correctly and not trash data */ sbi->sb->s_flags |= MS_ACTIVE; - /* Turn on quotas so that they are updated correctly */ - f2fs_enable_quota_files(sbi); + + /* + * Turn on quotas which were not enabled for read-only mounts if + * filesystem has quota feature, so that they are updated correctly. + */ + quota_enabled = f2fs_enable_quota_files(sbi, s_flags & MS_RDONLY); #endif start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi); orphan_blocks = __start_sum_addr(sbi) - 1 - __cp_payload(sbi); - ra_meta_pages(sbi, start_blk, orphan_blocks, META_CP, true); + f2fs_ra_meta_pages(sbi, start_blk, orphan_blocks, META_CP, true); for (i = 0; i < orphan_blocks; i++) { - struct page *page = get_meta_page(sbi, start_blk + i); + struct page *page; struct f2fs_orphan_block *orphan_blk; + page = f2fs_get_meta_page(sbi, start_blk + i); + if (IS_ERR(page)) { + err = PTR_ERR(page); + goto out; + } + orphan_blk = (struct f2fs_orphan_block *)page_address(page); for (j = 0; j < le32_to_cpu(orphan_blk->entry_count); j++) { nid_t ino = le32_to_cpu(orphan_blk->ino[j]); @@ -646,9 +689,12 @@ int recover_orphan_inodes(struct f2fs_sb_info *sbi) /* clear Orphan Flag */ clear_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG); out: + set_sbi_flag(sbi, SBI_IS_RECOVERED); + #ifdef CONFIG_QUOTA /* Turn quotas off */ - f2fs_quota_off_umount(sbi->sb); + if (quota_enabled) + f2fs_quota_off_umount(sbi->sb); #endif sbi->sb->s_flags = s_flags; /* Restore MS_RDONLY status */ @@ -678,7 +724,7 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk) /* loop for each orphan inode entry and write them in Jornal block */ list_for_each_entry(orphan, head, list) { if (!page) { - page = grab_meta_page(sbi, start_blk++); + page = f2fs_grab_meta_page(sbi, start_blk++); orphan_blk = (struct f2fs_orphan_block *)page_address(page); memset(orphan_blk, 0, sizeof(*orphan_blk)); @@ -720,7 +766,10 @@ static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr, size_t crc_offset = 0; __u32 crc = 0; - *cp_page = get_meta_page(sbi, cp_addr); + *cp_page = f2fs_get_meta_page(sbi, cp_addr); + if (IS_ERR(*cp_page)) + return PTR_ERR(*cp_page); + *cp_block = (struct f2fs_checkpoint *)page_address(*cp_page); crc_offset = le32_to_cpu((*cp_block)->checksum_offset); @@ -782,7 +831,7 @@ invalid_cp: return NULL; } -int get_valid_checkpoint(struct f2fs_sb_info *sbi) +int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi) { struct f2fs_checkpoint *cp_block; struct f2fs_super_block *fsb = sbi->raw_super; @@ -795,7 +844,8 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi) int i; int err; - sbi->ckpt = kzalloc(cp_blks * blk_size, GFP_KERNEL); + sbi->ckpt = f2fs_kzalloc(sbi, array_size(blk_size, cp_blks), + GFP_KERNEL); if (!sbi->ckpt) return -ENOMEM; /* @@ -833,7 +883,7 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi) sbi->cur_cp_pack = 2; /* Sanity checking of checkpoint */ - if (sanity_check_ckpt(sbi)) { + if (f2fs_sanity_check_ckpt(sbi)) { err = -EFSCORRUPTED; goto free_fail_no_cp; } @@ -849,7 +899,9 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi) void *sit_bitmap_ptr; unsigned char *ckpt = (unsigned char *)sbi->ckpt; - cur_page = get_meta_page(sbi, cp_blk_no + i); + cur_page = f2fs_get_meta_page(sbi, cp_blk_no + i); + if (IS_ERR(cur_page)) + goto free_fail_no_cp; sit_bitmap_ptr = page_address(cur_page); memcpy(ckpt + i * blk_size, sit_bitmap_ptr, blk_size); f2fs_put_page(cur_page, 1); @@ -863,7 +915,7 @@ free_fail_no_cp: f2fs_put_page(cp1, 1); f2fs_put_page(cp2, 1); fail_no_cp: - kfree(sbi->ckpt); + kvfree(sbi->ckpt); return err; } @@ -894,7 +946,7 @@ static void __remove_dirty_inode(struct inode *inode, enum inode_type type) stat_dec_dirty_inode(F2FS_I_SB(inode), type); } -void update_dirty_page(struct inode *inode, struct page *page) +void f2fs_update_dirty_page(struct inode *inode, struct page *page) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE; @@ -909,11 +961,11 @@ void update_dirty_page(struct inode *inode, struct page *page) inode_inc_dirty_pages(inode); spin_unlock(&sbi->inode_lock[type]); - SetPagePrivate(page); + f2fs_set_page_private(page, 0); f2fs_trace_pid(page); } -void remove_dirty_inode(struct inode *inode) +void f2fs_remove_dirty_inode(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE; @@ -930,7 +982,7 @@ void remove_dirty_inode(struct inode *inode) spin_unlock(&sbi->inode_lock[type]); } -int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type) +int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type) { struct list_head *head; struct inode *inode; @@ -971,12 +1023,10 @@ retry: iput(inode); /* We need to give cpu to another writers. */ - if (ino == cur_ino) { - congestion_wait(BLK_RW_ASYNC, HZ/50); + if (ino == cur_ino) cond_resched(); - } else { + else ino = cur_ino; - } } else { /* * We should submit bio, since it exists several @@ -1013,10 +1063,10 @@ int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi) /* it's on eviction */ if (is_inode_flag_set(inode, FI_DIRTY_INODE)) - update_inode_page(inode); + f2fs_update_inode_page(inode); iput(inode); } - }; + } return 0; } @@ -1033,6 +1083,21 @@ static void __prepare_cp_block(struct f2fs_sb_info *sbi) ckpt->next_free_nid = cpu_to_le32(last_nid); } +static bool __need_flush_quota(struct f2fs_sb_info *sbi) +{ + if (!is_journalled_quota(sbi)) + return false; + if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH)) + return false; + if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR)) + return false; + if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_FLUSH)) + return true; + if (get_pages(sbi, F2FS_DIRTY_QDATA)) + return true; + return false; +} + /* * Freeze all the FS-operations for checkpoint. */ @@ -1044,20 +1109,44 @@ static int block_operations(struct f2fs_sb_info *sbi) .for_reclaim = 0, }; struct blk_plug plug; - int err = 0; + int err = 0, cnt = 0; blk_start_plug(&plug); -retry_flush_dents: +retry_flush_quotas: + if (__need_flush_quota(sbi)) { + int locked; + + if (++cnt > DEFAULT_RETRY_QUOTA_FLUSH_COUNT) { + set_sbi_flag(sbi, SBI_QUOTA_SKIP_FLUSH); + f2fs_lock_all(sbi); + goto retry_flush_dents; + } + clear_sbi_flag(sbi, SBI_QUOTA_NEED_FLUSH); + + /* only failed during mount/umount/freeze/quotactl */ + locked = down_read_trylock(&sbi->sb->s_umount); + f2fs_quota_sync(sbi->sb, -1); + if (locked) + up_read(&sbi->sb->s_umount); + } + f2fs_lock_all(sbi); + if (__need_flush_quota(sbi)) { + f2fs_unlock_all(sbi); + cond_resched(); + goto retry_flush_quotas; + } + +retry_flush_dents: /* write all the dirty dentry pages */ if (get_pages(sbi, F2FS_DIRTY_DENTS)) { f2fs_unlock_all(sbi); - err = sync_dirty_inodes(sbi, DIR_INODE); + err = f2fs_sync_dirty_inodes(sbi, DIR_INODE); if (err) goto out; cond_resched(); - goto retry_flush_dents; + goto retry_flush_quotas; } /* @@ -1066,6 +1155,12 @@ retry_flush_dents: */ down_write(&sbi->node_change); + if (__need_flush_quota(sbi)) { + up_write(&sbi->node_change); + f2fs_unlock_all(sbi); + goto retry_flush_quotas; + } + if (get_pages(sbi, F2FS_DIRTY_IMETA)) { up_write(&sbi->node_change); f2fs_unlock_all(sbi); @@ -1073,7 +1168,7 @@ retry_flush_dents: if (err) goto out; cond_resched(); - goto retry_flush_dents; + goto retry_flush_quotas; } retry_flush_nodes: @@ -1081,7 +1176,9 @@ retry_flush_nodes: if (get_pages(sbi, F2FS_DIRTY_NODES)) { up_write(&sbi->node_write); - err = sync_node_pages(sbi, &wbc, false, FS_CP_NODE_IO); + atomic_inc(&sbi->wb_sync_req[NODE]); + err = f2fs_sync_node_pages(sbi, &wbc, false, FS_CP_NODE_IO); + atomic_dec(&sbi->wb_sync_req[NODE]); if (err) { up_write(&sbi->node_change); f2fs_unlock_all(sbi); @@ -1108,7 +1205,7 @@ static void unblock_operations(struct f2fs_sb_info *sbi) f2fs_unlock_all(sbi); } -static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi) +void f2fs_wait_on_all_pages_writeback(struct f2fs_sb_info *sbi) { DEFINE_WAIT(wait); @@ -1118,6 +1215,9 @@ static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi) if (!get_pages(sbi, F2FS_WB_CP_DATA)) break; + if (unlikely(f2fs_cp_error(sbi))) + break; + io_schedule_timeout(5*HZ); } finish_wait(&sbi->cp_wait, &wait); @@ -1159,12 +1259,70 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc) if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) __set_ckpt_flags(ckpt, CP_FSCK_FLAG); + if (is_sbi_flag_set(sbi, SBI_CP_DISABLED)) + __set_ckpt_flags(ckpt, CP_DISABLED_FLAG); + else + __clear_ckpt_flags(ckpt, CP_DISABLED_FLAG); + + if (is_sbi_flag_set(sbi, SBI_CP_DISABLED_QUICK)) + __set_ckpt_flags(ckpt, CP_DISABLED_QUICK_FLAG); + else + __clear_ckpt_flags(ckpt, CP_DISABLED_QUICK_FLAG); + + if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH)) + __set_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG); + /* + * TODO: we count on fsck.f2fs to clear this flag until we figure out + * missing cases which clear it incorrectly. + */ + + if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR)) + __set_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG); + /* set this flag to activate crc|cp_ver for recovery */ __set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG); + __clear_ckpt_flags(ckpt, CP_NOCRC_RECOVERY_FLAG); spin_unlock_irqrestore(&sbi->cp_lock, flags); } +static void commit_checkpoint(struct f2fs_sb_info *sbi, + void *src, block_t blk_addr) +{ + struct writeback_control wbc = { + .for_reclaim = 0, + }; + + /* + * pagevec_lookup_tag and lock_page again will take + * some extra time. Therefore, f2fs_update_meta_pages and + * f2fs_sync_meta_pages are combined in this function. + */ + struct page *page = f2fs_grab_meta_page(sbi, blk_addr); + int err; + + f2fs_wait_on_page_writeback(page, META, true, true); + + memcpy(page_address(page), src, PAGE_SIZE); + + set_page_dirty(page); + if (unlikely(!clear_page_dirty_for_io(page))) + f2fs_bug_on(sbi, 1); + + /* writeout cp pack 2 page */ + err = __f2fs_write_meta_page(page, &wbc, FS_CP_META_IO); + if (unlikely(err && f2fs_cp_error(sbi))) { + f2fs_put_page(page, 1); + return; + } + + f2fs_bug_on(sbi, err); + f2fs_put_page(page, 0); + + /* submit checkpoint (with barrier if NOBARRIER is not set) */ + f2fs_submit_merged_write(sbi, META_FLUSH); +} + static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) { struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); @@ -1178,19 +1336,18 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) struct super_block *sb = sbi->sb; struct curseg_info *seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE); u64 kbytes_written; + int err; /* Flush all the NAT/SIT pages */ - while (get_pages(sbi, F2FS_DIRTY_META)) { - sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO); - if (unlikely(f2fs_cp_error(sbi))) - return -EIO; - } + f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO); + f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_META) && + !f2fs_cp_error(sbi)); /* * modify checkpoint * version number is already updated */ - ckpt->elapsed_time = cpu_to_le64(get_mtime(sbi)); + ckpt->elapsed_time = cpu_to_le64(get_mtime(sbi, true)); ckpt->free_segment_count = cpu_to_le32(free_segments(sbi)); for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) { ckpt->cur_node_segno[i] = @@ -1210,7 +1367,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) } /* 2 cp + n data seg summary + orphan inode blocks */ - data_sum_blocks = npages_for_summary_flush(sbi, false); + data_sum_blocks = f2fs_npages_for_summary_flush(sbi, false); spin_lock_irqsave(&sbi->cp_lock, flags); if (data_sum_blocks < NR_CURSEG_DATA_TYPE) __set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG); @@ -1255,27 +1412,15 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) blk = start_blk + sbi->blocks_per_seg - nm_i->nat_bits_blocks; for (i = 0; i < nm_i->nat_bits_blocks; i++) - update_meta_page(sbi, nm_i->nat_bits + + f2fs_update_meta_page(sbi, nm_i->nat_bits + (i << F2FS_BLKSIZE_BITS), blk + i); - - /* Flush all the NAT BITS pages */ - while (get_pages(sbi, F2FS_DIRTY_META)) { - sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO); - if (unlikely(f2fs_cp_error(sbi))) - return -EIO; - } } - /* need to wait for end_io results */ - wait_on_all_pages_writeback(sbi); - if (unlikely(f2fs_cp_error(sbi))) - return -EIO; - /* write out checkpoint buffer at block 0 */ - update_meta_page(sbi, ckpt, start_blk++); + f2fs_update_meta_page(sbi, ckpt, start_blk++); for (i = 1; i < 1 + cp_payload_blks; i++) - update_meta_page(sbi, (char *)ckpt + i * F2FS_BLKSIZE, + f2fs_update_meta_page(sbi, (char *)ckpt + i * F2FS_BLKSIZE, start_blk++); if (orphan_num) { @@ -1283,7 +1428,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) start_blk += orphan_blocks; } - write_data_summaries(sbi, start_blk); + f2fs_write_data_summaries(sbi, start_blk); start_blk += data_sum_blocks; /* Record write statistics in the hot node summary */ @@ -1294,39 +1439,47 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) seg_i->journal->info.kbytes_written = cpu_to_le64(kbytes_written); if (__remain_node_summaries(cpc->reason)) { - write_node_summaries(sbi, start_blk); + f2fs_write_node_summaries(sbi, start_blk); start_blk += NR_CURSEG_NODE_TYPE; } - /* writeout checkpoint block */ - update_meta_page(sbi, ckpt, start_blk); - - /* wait for previous submitted node/meta pages writeback */ - wait_on_all_pages_writeback(sbi); - - if (unlikely(f2fs_cp_error(sbi))) - return -EIO; - - filemap_fdatawait_range(NODE_MAPPING(sbi), 0, LLONG_MAX); - filemap_fdatawait_range(META_MAPPING(sbi), 0, LLONG_MAX); - /* update user_block_counts */ sbi->last_valid_block_count = sbi->total_valid_block_count; percpu_counter_set(&sbi->alloc_valid_block_count, 0); - /* Here, we only have one bio having CP pack */ - sync_meta_pages(sbi, META_FLUSH, LONG_MAX, FS_CP_META_IO); + /* Here, we have one bio having CP pack except cp pack 2 page */ + f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO); + f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_META) && + !f2fs_cp_error(sbi)); /* wait for previous submitted meta pages writeback */ - wait_on_all_pages_writeback(sbi); + f2fs_wait_on_all_pages_writeback(sbi); + + /* flush all device cache */ + err = f2fs_flush_device_cache(sbi); + if (err) + return err; - release_ino_entry(sbi, false); + /* barrier and flush checkpoint cp pack 2 page if it can */ + commit_checkpoint(sbi, ckpt, start_blk); + f2fs_wait_on_all_pages_writeback(sbi); - if (unlikely(f2fs_cp_error(sbi))) - return -EIO; + /* + * invalidate intermediate page cache borrowed from meta inode + * which are used for migration of encrypted inode's blocks. + */ + if (f2fs_sb_has_encrypt(sbi)) + invalidate_mapping_pages(META_MAPPING(sbi), + MAIN_BLKADDR(sbi), MAX_BLKADDR(sbi) - 1); + + f2fs_release_ino_entry(sbi, false); + + f2fs_reset_fsync_node_info(sbi); clear_sbi_flag(sbi, SBI_IS_DIRTY); clear_sbi_flag(sbi, SBI_NEED_CP); + clear_sbi_flag(sbi, SBI_QUOTA_SKIP_FLUSH); + sbi->unusable_block_count = 0; __set_cp_next_pack(sbi); /* @@ -1339,18 +1492,24 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_DENTS)); - return 0; + return unlikely(f2fs_cp_error(sbi)) ? -EIO : 0; } /* * We guarantee that this checkpoint procedure will not fail. */ -int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) +int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) { struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); unsigned long long ckpt_ver; int err = 0; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + if (cpc->reason != CP_PAUSE) + return 0; + f2fs_msg(sbi->sb, KERN_WARNING, + "Start checkpoint disabled!"); + } mutex_lock(&sbi->cp_mutex); if (!is_sbi_flag_set(sbi, SBI_IS_DIRTY) && @@ -1378,7 +1537,7 @@ int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) /* this is the case of multiple fstrims without any changes */ if (cpc->reason & CP_DISCARD) { - if (!exist_trim_candidates(sbi, cpc)) { + if (!f2fs_exist_trim_candidates(sbi, cpc)) { unblock_operations(sbi); goto out; } @@ -1386,8 +1545,8 @@ int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) if (NM_I(sbi)->dirty_nat_cnt == 0 && SIT_I(sbi)->dirty_sentries == 0 && prefree_segments(sbi) == 0) { - flush_sit_entries(sbi, cpc); - clear_prefree_segments(sbi, cpc); + f2fs_flush_sit_entries(sbi, cpc); + f2fs_clear_prefree_segments(sbi, cpc); unblock_operations(sbi); goto out; } @@ -1402,16 +1561,19 @@ int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) ckpt->checkpoint_ver = cpu_to_le64(++ckpt_ver); /* write cached NAT/SIT entries to NAT/SIT area */ - flush_nat_entries(sbi, cpc); - flush_sit_entries(sbi, cpc); + err = f2fs_flush_nat_entries(sbi, cpc); + if (err) + goto stop; + + f2fs_flush_sit_entries(sbi, cpc); /* unlock all the fs_lock[] in do_checkpoint() */ err = do_checkpoint(sbi, cpc); if (err) - release_discard_addrs(sbi); + f2fs_release_discard_addrs(sbi); else - clear_prefree_segments(sbi, cpc); - + f2fs_clear_prefree_segments(sbi, cpc); +stop: unblock_operations(sbi); stat_inc_cp_count(sbi->stat_info); @@ -1427,7 +1589,7 @@ out: return err; } -void init_ino_entry_info(struct f2fs_sb_info *sbi) +void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi) { int i; @@ -1445,23 +1607,23 @@ void init_ino_entry_info(struct f2fs_sb_info *sbi) F2FS_ORPHANS_PER_BLOCK; } -int __init create_checkpoint_caches(void) +int __init f2fs_create_checkpoint_caches(void) { ino_entry_slab = f2fs_kmem_cache_create("f2fs_ino_entry", sizeof(struct ino_entry)); if (!ino_entry_slab) return -ENOMEM; - inode_entry_slab = f2fs_kmem_cache_create("f2fs_inode_entry", + f2fs_inode_entry_slab = f2fs_kmem_cache_create("f2fs_inode_entry", sizeof(struct inode_entry)); - if (!inode_entry_slab) { + if (!f2fs_inode_entry_slab) { kmem_cache_destroy(ino_entry_slab); return -ENOMEM; } return 0; } -void destroy_checkpoint_caches(void) +void f2fs_destroy_checkpoint_caches(void) { kmem_cache_destroy(ino_entry_slab); - kmem_cache_destroy(inode_entry_slab); + kmem_cache_destroy(f2fs_inode_entry_slab); } diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index afe7dcfff036..157861ed41ef 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/data.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> @@ -19,8 +16,6 @@ #include <linux/bio.h> #include <linux/prefetch.h> #include <linux/uio.h> -#include <linux/mm.h> -#include <linux/memcontrol.h> #include <linux/cleancache.h> #include <linux/sched/signal.h> @@ -29,6 +24,12 @@ #include "segment.h" #include "trace.h" #include <trace/events/f2fs.h> +#include <trace/events/android_fs.h> + +#define NUM_PREALLOC_POST_READ_CTXS 128 + +static struct kmem_cache *bio_post_read_ctx_cache; +static mempool_t *bio_post_read_ctx_pool; static bool __is_cp_guaranteed(struct page *page) { @@ -45,53 +46,139 @@ static bool __is_cp_guaranteed(struct page *page) if (inode->i_ino == F2FS_META_INO(sbi) || inode->i_ino == F2FS_NODE_INO(sbi) || S_ISDIR(inode->i_mode) || + (S_ISREG(inode->i_mode) && + (f2fs_is_atomic_file(inode) || IS_NOQUOTA(inode))) || is_cold_data(page)) return true; return false; } -static void f2fs_read_end_io(struct bio *bio) +static enum count_type __read_io_type(struct page *page) { - struct bio_vec *bvec; - int i; + struct address_space *mapping = page->mapping; -#ifdef CONFIG_F2FS_FAULT_INJECTION - if (time_to_inject(F2FS_P_SB(bio->bi_io_vec->bv_page), FAULT_IO)) { - f2fs_show_injection_info(FAULT_IO); - bio->bi_status = BLK_STS_IOERR; - } -#endif + if (mapping) { + struct inode *inode = mapping->host; + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - if (f2fs_bio_encrypted(bio)) { - if (bio->bi_status) { - fscrypt_release_ctx(bio->bi_private); - } else { - fscrypt_decrypt_bio_pages(bio->bi_private, bio); - return; - } + if (inode->i_ino == F2FS_META_INO(sbi)) + return F2FS_RD_META; + + if (inode->i_ino == F2FS_NODE_INO(sbi)) + return F2FS_RD_NODE; } + return F2FS_RD_DATA; +} - bio_for_each_segment_all(bvec, bio, i) { - struct page *page = bvec->bv_page; +/* postprocessing steps for read bios */ +enum bio_post_read_step { + STEP_INITIAL = 0, + STEP_DECRYPT, +}; - if (!bio->bi_status) { - if (!PageUptodate(page)) - SetPageUptodate(page); - } else { +struct bio_post_read_ctx { + struct bio *bio; + struct work_struct work; + unsigned int cur_step; + unsigned int enabled_steps; +}; + +static void __read_end_io(struct bio *bio) +{ + struct page *page; + struct bio_vec *bv; + int i; + + bio_for_each_segment_all(bv, bio, i) { + page = bv->bv_page; + + /* PG_error was set if any post_read step failed */ + if (bio->bi_status || PageError(page)) { ClearPageUptodate(page); - SetPageError(page); + /* will re-read again later */ + ClearPageError(page); + } else { + SetPageUptodate(page); } + dec_page_count(F2FS_P_SB(page), __read_io_type(page)); unlock_page(page); } + if (bio->bi_private) + mempool_free(bio->bi_private, bio_post_read_ctx_pool); bio_put(bio); } +static void bio_post_read_processing(struct bio_post_read_ctx *ctx); + +static void decrypt_work(struct work_struct *work) +{ + struct bio_post_read_ctx *ctx = + container_of(work, struct bio_post_read_ctx, work); + + fscrypt_decrypt_bio(ctx->bio); + + bio_post_read_processing(ctx); +} + +static void bio_post_read_processing(struct bio_post_read_ctx *ctx) +{ + switch (++ctx->cur_step) { + case STEP_DECRYPT: + if (ctx->enabled_steps & (1 << STEP_DECRYPT)) { + INIT_WORK(&ctx->work, decrypt_work); + fscrypt_enqueue_decrypt_work(&ctx->work); + return; + } + ctx->cur_step++; + /* fall-through */ + default: + __read_end_io(ctx->bio); + } +} + +static bool f2fs_bio_post_read_required(struct bio *bio) +{ + return bio->bi_private && !bio->bi_status; +} + +static void f2fs_read_end_io(struct bio *bio) +{ + struct page *first_page = bio->bi_io_vec[0].bv_page; + + if (time_to_inject(F2FS_P_SB(bio->bi_io_vec->bv_page), FAULT_READ_IO)) { + f2fs_show_injection_info(FAULT_READ_IO); + bio->bi_status = BLK_STS_IOERR; + } + + if (f2fs_bio_post_read_required(bio)) { + struct bio_post_read_ctx *ctx = bio->bi_private; + + ctx->cur_step = STEP_INITIAL; + bio_post_read_processing(ctx); + return; + } + + if (first_page != NULL && + __read_io_type(first_page) == F2FS_RD_DATA) { + trace_android_fs_dataread_end(first_page->mapping->host, + page_offset(first_page), + bio->bi_iter.bi_size); + } + + __read_end_io(bio); +} + static void f2fs_write_end_io(struct bio *bio) { struct f2fs_sb_info *sbi = bio->bi_private; struct bio_vec *bvec; int i; + if (time_to_inject(sbi, FAULT_WRITE_IO)) { + f2fs_show_injection_info(FAULT_WRITE_IO); + bio->bi_status = BLK_STS_IOERR; + } + bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; enum count_type type = WB_DATA_TYPE(page); @@ -111,9 +198,16 @@ static void f2fs_write_end_io(struct bio *bio) if (unlikely(bio->bi_status)) { mapping_set_error(page->mapping, -EIO); - f2fs_stop_checkpoint(sbi, true); + if (type == F2FS_WB_CP_DATA) + f2fs_stop_checkpoint(sbi, true); } + + f2fs_bug_on(sbi, page->mapping == NODE_MAPPING(sbi) && + page->index != nid_of_node(page)); + dec_page_count(sbi, type); + if (f2fs_in_warm_node_list(sbi, page)) + f2fs_del_fsync_node_entry(sbi, page); clear_cold_data(page); end_page_writeback(page); } @@ -174,15 +268,25 @@ static bool __same_bdev(struct f2fs_sb_info *sbi, * Low-level block read/write IO operations. */ static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr, - int npages, bool is_read) + struct writeback_control *wbc, + int npages, bool is_read, + enum page_type type, enum temp_type temp) { struct bio *bio; - bio = f2fs_bio_alloc(npages); + bio = f2fs_bio_alloc(sbi, npages, true); f2fs_target_device(sbi, blk_addr, bio); - bio->bi_end_io = is_read ? f2fs_read_end_io : f2fs_write_end_io; - bio->bi_private = is_read ? NULL : sbi; + if (is_read) { + bio->bi_end_io = f2fs_read_end_io; + bio->bi_private = NULL; + } else { + bio->bi_end_io = f2fs_write_end_io; + bio->bi_private = sbi; + bio->bi_write_hint = f2fs_io_type_to_rw_hint(sbi, type, temp); + } + if (wbc) + wbc_init_bio(wbc, bio); return bio; } @@ -193,13 +297,12 @@ static inline void __submit_bio(struct f2fs_sb_info *sbi, if (!is_read_io(bio_op(bio))) { unsigned int start; - if (f2fs_sb_mounted_blkzoned(sbi->sb) && - current->plug && (type == DATA || type == NODE)) - blk_finish_plug(current->plug); - if (type != DATA && type != NODE) goto submit_io; + if (test_opt(sbi, LFS) && current->plug) + blk_finish_plug(current->plug); + start = bio->bi_iter.bi_size >> F2FS_BLKSIZE_BITS; start %= F2FS_IO_SIZE(sbi); @@ -210,9 +313,10 @@ static inline void __submit_bio(struct f2fs_sb_info *sbi, for (; start < F2FS_IO_SIZE(sbi); start++) { struct page *page = mempool_alloc(sbi->write_io_dummy, - GFP_NOIO | __GFP_ZERO | __GFP_NOFAIL); + GFP_NOIO | __GFP_NOFAIL); f2fs_bug_on(sbi, !page); + zero_user_segment(page, 0, PAGE_SIZE); SetPagePrivate(page); set_page_private(page, (unsigned long)DUMMY_WRITTEN_PAGE); lock_page(page); @@ -234,6 +338,32 @@ submit_io: submit_bio(bio); } +static void __f2fs_submit_read_bio(struct f2fs_sb_info *sbi, + struct bio *bio, enum page_type type) +{ + if (trace_android_fs_dataread_start_enabled() && (type == DATA)) { + struct page *first_page = bio->bi_io_vec[0].bv_page; + + if (first_page != NULL && + __read_io_type(first_page) == F2FS_RD_DATA) { + char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; + + path = android_fstrace_get_pathname(pathbuf, + MAX_TRACE_PATHBUF_LEN, + first_page->mapping->host); + + trace_android_fs_dataread_start( + first_page->mapping->host, + page_offset(first_page), + bio->bi_iter.bi_size, + current->pid, + path, + current->comm); + } + } + __submit_bio(sbi, bio, type); +} + static void __submit_merged_bio(struct f2fs_bio_info *io) { struct f2fs_io_info *fio = &io->fio; @@ -252,8 +382,8 @@ static void __submit_merged_bio(struct f2fs_bio_info *io) io->bio = NULL; } -static bool __has_merged_page(struct f2fs_bio_info *io, - struct inode *inode, nid_t ino, pgoff_t idx) +static bool __has_merged_page(struct f2fs_bio_info *io, struct inode *inode, + struct page *page, nid_t ino) { struct bio_vec *bvec; struct page *target; @@ -262,7 +392,7 @@ static bool __has_merged_page(struct f2fs_bio_info *io, if (!io->bio) return false; - if (!inode && !ino) + if (!inode && !page && !ino) return true; bio_for_each_segment_all(bvec, io->bio, i) { @@ -272,11 +402,10 @@ static bool __has_merged_page(struct f2fs_bio_info *io, else target = fscrypt_control_page(bvec->bv_page); - if (idx != target->index) - continue; - if (inode && inode == target->mapping->host) return true; + if (page && page == target) + return true; if (ino && ino == ino_of_node(target)) return true; } @@ -284,28 +413,6 @@ static bool __has_merged_page(struct f2fs_bio_info *io, return false; } -static bool has_merged_page(struct f2fs_sb_info *sbi, struct inode *inode, - nid_t ino, pgoff_t idx, enum page_type type) -{ - enum page_type btype = PAGE_TYPE_OF_BIO(type); - enum temp_type temp; - struct f2fs_bio_info *io; - bool ret = false; - - for (temp = HOT; temp < NR_TEMP_TYPE; temp++) { - io = sbi->write_io[btype] + temp; - - down_read(&io->io_rwsem); - ret = __has_merged_page(io, inode, ino, idx); - up_read(&io->io_rwsem); - - /* TODO: use HOT temp only for meta pages now. */ - if (ret || btype == META) - break; - } - return ret; -} - static void __f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type, enum temp_type temp) { @@ -327,17 +434,23 @@ static void __f2fs_submit_merged_write(struct f2fs_sb_info *sbi, } static void __submit_merged_write_cond(struct f2fs_sb_info *sbi, - struct inode *inode, nid_t ino, pgoff_t idx, - enum page_type type, bool force) + struct inode *inode, struct page *page, + nid_t ino, enum page_type type, bool force) { enum temp_type temp; - - if (!force && !has_merged_page(sbi, inode, ino, idx, type)) - return; + bool ret = true; for (temp = HOT; temp < NR_TEMP_TYPE; temp++) { + if (!force) { + enum page_type btype = PAGE_TYPE_OF_BIO(type); + struct f2fs_bio_info *io = sbi->write_io[btype] + temp; - __f2fs_submit_merged_write(sbi, type, temp); + down_read(&io->io_rwsem); + ret = __has_merged_page(io, inode, page, ino); + up_read(&io->io_rwsem); + } + if (ret) + __f2fs_submit_merged_write(sbi, type, temp); /* TODO: use HOT temp only for meta pages now. */ if (type >= META) @@ -351,10 +464,10 @@ void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type) } void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi, - struct inode *inode, nid_t ino, pgoff_t idx, - enum page_type type) + struct inode *inode, struct page *page, + nid_t ino, enum page_type type) { - __submit_merged_write_cond(sbi, inode, ino, idx, type, false); + __submit_merged_write_cond(sbi, inode, page, ino, type, false); } void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi) @@ -382,28 +495,32 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) f2fs_trace_ios(fio, 0); /* Allocate a new bio */ - bio = __bio_alloc(fio->sbi, fio->new_blkaddr, 1, is_read_io(fio->op)); + bio = __bio_alloc(fio->sbi, fio->new_blkaddr, fio->io_wbc, + 1, is_read_io(fio->op), fio->type, fio->temp); if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { bio_put(bio); return -EFAULT; } + + if (fio->io_wbc && !is_read_io(fio->op)) + wbc_account_io(fio->io_wbc, page, PAGE_SIZE); + bio_set_op_attrs(bio, fio->op, fio->op_flags); - if (!is_read_io(fio->op)) - inc_page_count(fio->sbi, WB_DATA_TYPE(fio->page)); + inc_page_count(fio->sbi, is_read_io(fio->op) ? + __read_io_type(page): WB_DATA_TYPE(fio->page)); - __submit_bio(fio->sbi, bio, fio->type); + __f2fs_submit_read_bio(fio->sbi, bio, fio->type); return 0; } -int f2fs_submit_page_write(struct f2fs_io_info *fio) +void f2fs_submit_page_write(struct f2fs_io_info *fio) { struct f2fs_sb_info *sbi = fio->sbi; enum page_type btype = PAGE_TYPE_OF_BIO(fio->type); struct f2fs_bio_info *io = sbi->write_io[btype] + fio->temp; struct page *bio_page; - int err = 0; f2fs_bug_on(sbi, is_read_io(fio->op)); @@ -413,7 +530,7 @@ next: spin_lock(&io->io_lock); if (list_empty(&io->io_list)) { spin_unlock(&io->io_lock); - goto out_fail; + goto out; } fio = list_first_entry(&io->io_list, struct f2fs_io_info, list); @@ -427,8 +544,8 @@ next: bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page; - /* set submitted = 1 as a return value */ - fio->submitted = 1; + /* set submitted = true as a return value */ + fio->submitted = true; inc_page_count(sbi, WB_DATA_TYPE(bio_page)); @@ -440,12 +557,13 @@ alloc_new: if (io->bio == NULL) { if ((fio->type == DATA || fio->type == NODE) && fio->new_blkaddr & F2FS_IO_SIZE_MASK(sbi)) { - err = -EAGAIN; dec_page_count(sbi, WB_DATA_TYPE(bio_page)); - goto out_fail; + fio->retry = true; + goto skip; } - io->bio = __bio_alloc(sbi, fio->new_blkaddr, - BIO_MAX_PAGES, false); + io->bio = __bio_alloc(sbi, fio->new_blkaddr, fio->io_wbc, + BIO_MAX_PAGES, false, + fio->type, fio->temp); io->fio = *fio; } @@ -454,47 +572,53 @@ alloc_new: goto alloc_new; } + if (fio->io_wbc) + wbc_account_io(fio->io_wbc, bio_page, PAGE_SIZE); + io->last_block_in_bio = fio->new_blkaddr; f2fs_trace_ios(fio, 0); trace_f2fs_submit_page_write(fio->page, fio); - +skip: if (fio->in_list) goto next; -out_fail: +out: + if (is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN) || + f2fs_is_checkpoint_ready(sbi)) + __submit_merged_bio(io); up_write(&io->io_rwsem); - return err; } static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr, - unsigned nr_pages) + unsigned nr_pages, unsigned op_flag) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct fscrypt_ctx *ctx = NULL; struct bio *bio; + struct bio_post_read_ctx *ctx; + unsigned int post_read_steps = 0; if (!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC)) return ERR_PTR(-EFAULT); - if (f2fs_encrypted_file(inode)) { - ctx = fscrypt_get_ctx(inode, GFP_NOFS); - if (IS_ERR(ctx)) - return ERR_CAST(ctx); - - /* wait the page to be moved by cleaning */ - f2fs_wait_on_block_writeback(sbi, blkaddr); - } - - bio = bio_alloc(GFP_KERNEL, min_t(int, nr_pages, BIO_MAX_PAGES)); - if (!bio) { - if (ctx) - fscrypt_release_ctx(ctx); + bio = f2fs_bio_alloc(sbi, min_t(int, nr_pages, BIO_MAX_PAGES), false); + if (!bio) return ERR_PTR(-ENOMEM); - } f2fs_target_device(sbi, blkaddr, bio); bio->bi_end_io = f2fs_read_end_io; - bio->bi_private = ctx; - bio_set_op_attrs(bio, REQ_OP_READ, 0); + bio_set_op_attrs(bio, REQ_OP_READ, op_flag); + + if (f2fs_encrypted_file(inode)) + post_read_steps |= 1 << STEP_DECRYPT; + if (post_read_steps) { + ctx = mempool_alloc(bio_post_read_ctx_pool, GFP_NOFS); + if (!ctx) { + bio_put(bio); + return ERR_PTR(-ENOMEM); + } + ctx->bio = bio; + ctx->enabled_steps = post_read_steps; + bio->bi_private = ctx; + } return bio; } @@ -503,16 +627,21 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr, static int f2fs_submit_page_read(struct inode *inode, struct page *page, block_t blkaddr) { - struct bio *bio = f2fs_grab_read_bio(inode, blkaddr, 1); + struct bio *bio = f2fs_grab_read_bio(inode, blkaddr, 1, 0); if (IS_ERR(bio)) return PTR_ERR(bio); + /* wait for GCed page writeback via META_MAPPING */ + f2fs_wait_on_block_writeback(inode, blkaddr); + if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { bio_put(bio); return -EFAULT; } - __submit_bio(F2FS_I_SB(inode), bio, DATA); + ClearPageError(page); + inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA); + __f2fs_submit_read_bio(F2FS_I_SB(inode), bio, DATA); return 0; } @@ -536,9 +665,9 @@ static void __set_data_blkaddr(struct dnode_of_data *dn) * ->node_page * update block addresses in the node page */ -void set_data_blkaddr(struct dnode_of_data *dn) +void f2fs_set_data_blkaddr(struct dnode_of_data *dn) { - f2fs_wait_on_page_writeback(dn->node_page, NODE, true); + f2fs_wait_on_page_writeback(dn->node_page, NODE, true, true); __set_data_blkaddr(dn); if (set_page_dirty(dn->node_page)) dn->node_changed = true; @@ -547,12 +676,12 @@ void set_data_blkaddr(struct dnode_of_data *dn) void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr) { dn->data_blkaddr = blkaddr; - set_data_blkaddr(dn); + f2fs_set_data_blkaddr(dn); f2fs_update_extent_cache(dn); } /* dn->ofs_in_node will be returned with up-to-date last block pointer */ -int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count) +int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); int err; @@ -568,7 +697,7 @@ int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count) trace_f2fs_reserve_new_blocks(dn->inode, dn->nid, dn->ofs_in_node, count); - f2fs_wait_on_page_writeback(dn->node_page, NODE, true); + f2fs_wait_on_page_writeback(dn->node_page, NODE, true, true); for (; count > 0; dn->ofs_in_node++) { block_t blkaddr = datablock_addr(dn->inode, @@ -586,12 +715,12 @@ int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count) } /* Should keep dn->ofs_in_node unchanged */ -int reserve_new_block(struct dnode_of_data *dn) +int f2fs_reserve_new_block(struct dnode_of_data *dn) { unsigned int ofs_in_node = dn->ofs_in_node; int ret; - ret = reserve_new_blocks(dn, 1); + ret = f2fs_reserve_new_blocks(dn, 1); dn->ofs_in_node = ofs_in_node; return ret; } @@ -601,12 +730,12 @@ int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index) bool need_put = dn->inode_page ? false : true; int err; - err = get_dnode_of_data(dn, index, ALLOC_NODE); + err = f2fs_get_dnode_of_data(dn, index, ALLOC_NODE); if (err) return err; if (dn->data_blkaddr == NULL_ADDR) - err = reserve_new_block(dn); + err = f2fs_reserve_new_block(dn); if (err || need_put) f2fs_put_dnode(dn); return err; @@ -625,7 +754,7 @@ int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index) return f2fs_reserve_block(dn, index); } -struct page *get_read_data_page(struct inode *inode, pgoff_t index, +struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index, int op_flags, bool for_write) { struct address_space *mapping = inode->i_mapping; @@ -644,7 +773,7 @@ struct page *get_read_data_page(struct inode *inode, pgoff_t index, } set_new_dnode(&dn, inode, NULL, NULL, 0); - err = get_dnode_of_data(&dn, index, LOOKUP_NODE); + err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE); if (err) goto put_err; f2fs_put_dnode(&dn); @@ -663,7 +792,8 @@ got_it: * A new dentry page is allocated but not able to be written, since its * new inode page couldn't be allocated due to -ENOSPC. * In such the case, its blkaddr can be remained as NEW_ADDR. - * see, f2fs_add_link -> get_new_data_page -> init_inode_metadata. + * see, f2fs_add_link -> f2fs_get_new_data_page -> + * f2fs_init_inode_metadata. */ if (dn.data_blkaddr == NEW_ADDR) { zero_user_segment(page, 0, PAGE_SIZE); @@ -683,7 +813,7 @@ put_err: return ERR_PTR(err); } -struct page *find_data_page(struct inode *inode, pgoff_t index) +struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index) { struct address_space *mapping = inode->i_mapping; struct page *page; @@ -693,7 +823,7 @@ struct page *find_data_page(struct inode *inode, pgoff_t index) return page; f2fs_put_page(page, 0); - page = get_read_data_page(inode, index, 0, false); + page = f2fs_get_read_data_page(inode, index, 0, false); if (IS_ERR(page)) return page; @@ -713,13 +843,13 @@ struct page *find_data_page(struct inode *inode, pgoff_t index) * Because, the callers, functions in dir.c and GC, should be able to know * whether this page exists or not. */ -struct page *get_lock_data_page(struct inode *inode, pgoff_t index, +struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index, bool for_write) { struct address_space *mapping = inode->i_mapping; struct page *page; repeat: - page = get_read_data_page(inode, index, 0, for_write); + page = f2fs_get_read_data_page(inode, index, 0, for_write); if (IS_ERR(page)) return page; @@ -745,7 +875,7 @@ repeat: * Note that, ipage is set only by make_empty_dir, and if any error occur, * ipage should be released by this function. */ -struct page *get_new_data_page(struct inode *inode, +struct page *f2fs_get_new_data_page(struct inode *inode, struct page *ipage, pgoff_t index, bool new_i_size) { struct address_space *mapping = inode->i_mapping; @@ -784,7 +914,7 @@ struct page *get_new_data_page(struct inode *inode, /* if ipage exists, blkaddr should be NEW_ADDR */ f2fs_bug_on(F2FS_I_SB(inode), ipage); - page = get_lock_data_page(inode, index, true); + page = f2fs_get_lock_data_page(inode, index, true); if (IS_ERR(page)) return page; } @@ -795,55 +925,64 @@ got_it: return page; } -static int __allocate_data_block(struct dnode_of_data *dn) +static int __allocate_data_block(struct dnode_of_data *dn, int seg_type) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); struct f2fs_summary sum; struct node_info ni; - pgoff_t fofs; + block_t old_blkaddr; blkcnt_t count = 1; int err; if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC))) return -EPERM; + err = f2fs_get_node_info(sbi, dn->nid, &ni); + if (err) + return err; + dn->data_blkaddr = datablock_addr(dn->inode, dn->node_page, dn->ofs_in_node); - if (dn->data_blkaddr == NEW_ADDR) + if (dn->data_blkaddr != NULL_ADDR) goto alloc; if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count)))) return err; alloc: - get_node_info(sbi, dn->nid, &ni); set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version); + old_blkaddr = dn->data_blkaddr; + f2fs_allocate_data_block(sbi, NULL, old_blkaddr, &dn->data_blkaddr, + &sum, seg_type, NULL, false); + if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) + invalidate_mapping_pages(META_MAPPING(sbi), + old_blkaddr, old_blkaddr); + f2fs_set_data_blkaddr(dn); - allocate_data_block(sbi, NULL, dn->data_blkaddr, &dn->data_blkaddr, - &sum, CURSEG_WARM_DATA, NULL, false); - set_data_blkaddr(dn); - - /* update i_size */ - fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) + - dn->ofs_in_node; - if (i_size_read(dn->inode) < ((loff_t)(fofs + 1) << PAGE_SHIFT)) - f2fs_i_size_write(dn->inode, - ((loff_t)(fofs + 1) << PAGE_SHIFT)); + /* + * i_size will be updated by direct_IO. Otherwise, we'll get stale + * data from unwritten block via dio_read. + */ return 0; } -static inline bool __force_buffered_io(struct inode *inode, int rw) -{ - return (f2fs_encrypted_file(inode) || - (rw == WRITE && test_opt(F2FS_I_SB(inode), LFS)) || - F2FS_I_SB(inode)->s_ndevs); -} - int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from) { struct inode *inode = file_inode(iocb->ki_filp); struct f2fs_map_blocks map; + int flag; int err = 0; + bool direct_io = iocb->ki_flags & IOCB_DIRECT; + + /* convert inline data for Direct I/O*/ + if (direct_io) { + err = f2fs_convert_inline_inode(inode); + if (err) + return err; + } + + if (direct_io && allow_outplace_dio(inode, iocb, from)) + return 0; if (is_inode_flag_set(inode, FI_NO_PREALLOC)) return 0; @@ -856,27 +995,38 @@ int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from) map.m_len = 0; map.m_next_pgofs = NULL; + map.m_next_extent = NULL; + map.m_seg_type = NO_CHECK_TYPE; + map.m_may_create = true; - if (iocb->ki_flags & IOCB_DIRECT) { - err = f2fs_convert_inline_inode(inode); - if (err) - return err; - return f2fs_map_blocks(inode, &map, 1, - __force_buffered_io(inode, WRITE) ? - F2FS_GET_BLOCK_PRE_AIO : - F2FS_GET_BLOCK_PRE_DIO); + if (direct_io) { + map.m_seg_type = f2fs_rw_hint_to_seg_type(iocb->ki_hint); + flag = f2fs_force_buffered_io(inode, iocb, from) ? + F2FS_GET_BLOCK_PRE_AIO : + F2FS_GET_BLOCK_PRE_DIO; + goto map_blocks; } if (iocb->ki_pos + iov_iter_count(from) > MAX_INLINE_DATA(inode)) { err = f2fs_convert_inline_inode(inode); if (err) return err; } - if (!f2fs_has_inline_data(inode)) - return f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO); + if (f2fs_has_inline_data(inode)) + return err; + + flag = F2FS_GET_BLOCK_PRE_AIO; + +map_blocks: + err = f2fs_map_blocks(inode, &map, 1, flag); + if (map.m_len > 0 && err == -ENOSPC) { + if (!direct_io) + set_inode_flag(inode, FI_NO_PREALLOC); + err = 0; + } return err; } -static inline void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock) +void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock) { if (flag == F2FS_GET_BLOCK_PRE_AIO) { if (lock) @@ -906,13 +1056,14 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, unsigned int maxblocks = map->m_len; struct dnode_of_data dn; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - int mode = create ? ALLOC_NODE : LOOKUP_NODE; + int mode = map->m_may_create ? ALLOC_NODE : LOOKUP_NODE; pgoff_t pgofs, end_offset, end; int err = 0, ofs = 1; unsigned int ofs_in_node, last_ofs_in_node; blkcnt_t prealloc; struct extent_info ei = {0,0,0}; block_t blkaddr; + unsigned int start_pgofs; if (!maxblocks) return 0; @@ -925,19 +1076,30 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, end = pgofs + maxblocks; if (!create && f2fs_lookup_extent_cache(inode, pgofs, &ei)) { + if (test_opt(sbi, LFS) && flag == F2FS_GET_BLOCK_DIO && + map->m_may_create) + goto next_dnode; + map->m_pblk = ei.blk + pgofs - ei.fofs; map->m_len = min((pgoff_t)maxblocks, ei.fofs + ei.len - pgofs); map->m_flags = F2FS_MAP_MAPPED; + if (map->m_next_extent) + *map->m_next_extent = pgofs + map->m_len; + + /* for hardware encryption, but to avoid potential issue in future */ + if (flag == F2FS_GET_BLOCK_DIO) + f2fs_wait_on_block_writeback_range(inode, + map->m_pblk, map->m_len); goto out; } next_dnode: - if (create) + if (map->m_may_create) __do_map_lock(sbi, flag, true); /* When reading holes, we need its node page */ set_new_dnode(&dn, inode, NULL, NULL, 0); - err = get_dnode_of_data(&dn, pgofs, mode); + err = f2fs_get_dnode_of_data(&dn, pgofs, mode); if (err) { if (flag == F2FS_GET_BLOCK_BMAP) map->m_pblk = 0; @@ -945,11 +1107,15 @@ next_dnode: err = 0; if (map->m_next_pgofs) *map->m_next_pgofs = - get_next_page_offset(&dn, pgofs); + f2fs_get_next_page_offset(&dn, pgofs); + if (map->m_next_extent) + *map->m_next_extent = + f2fs_get_next_page_offset(&dn, pgofs); } goto unlock_out; } + start_pgofs = pgofs; prealloc = 0; last_ofs_in_node = ofs_in_node = dn.ofs_in_node; end_offset = ADDRS_PER_PAGE(dn.node_page, inode); @@ -963,7 +1129,17 @@ next_block: goto sync_out; } - if (!is_valid_data_blkaddr(sbi, blkaddr)) { + if (is_valid_data_blkaddr(sbi, blkaddr)) { + /* use out-place-update for driect IO under LFS mode */ + if (test_opt(sbi, LFS) && flag == F2FS_GET_BLOCK_DIO && + map->m_may_create) { + err = __allocate_data_block(&dn, map->m_seg_type); + if (!err) { + blkaddr = dn.data_blkaddr; + set_inode_flag(inode, FI_APPEND_WRITE); + } + } + } else { if (create) { if (unlikely(f2fs_cp_error(sbi))) { err = -EIO; @@ -975,7 +1151,10 @@ next_block: last_ofs_in_node = dn.ofs_in_node; } } else { - err = __allocate_data_block(&dn); + WARN_ON(flag != F2FS_GET_BLOCK_PRE_DIO && + flag != F2FS_GET_BLOCK_DIO); + err = __allocate_data_block(&dn, + map->m_seg_type); if (!err) set_inode_flag(inode, FI_APPEND_WRITE); } @@ -988,14 +1167,20 @@ next_block: map->m_pblk = 0; goto sync_out; } + if (flag == F2FS_GET_BLOCK_PRECACHE) + goto sync_out; if (flag == F2FS_GET_BLOCK_FIEMAP && blkaddr == NULL_ADDR) { if (map->m_next_pgofs) *map->m_next_pgofs = pgofs + 1; + goto sync_out; } - if (flag != F2FS_GET_BLOCK_FIEMAP || - blkaddr != NEW_ADDR) + if (flag != F2FS_GET_BLOCK_FIEMAP) { + /* for defragment case */ + if (map->m_next_pgofs) + *map->m_next_pgofs = pgofs + 1; goto sync_out; + } } } @@ -1029,7 +1214,7 @@ skip: (pgofs == end || dn.ofs_in_node == end_offset)) { dn.ofs_in_node = ofs_in_node; - err = reserve_new_blocks(&dn, prealloc); + err = f2fs_reserve_new_blocks(&dn, prealloc); if (err) goto sync_out; @@ -1046,18 +1231,45 @@ skip: else if (dn.ofs_in_node < end_offset) goto next_block; + if (flag == F2FS_GET_BLOCK_PRECACHE) { + if (map->m_flags & F2FS_MAP_MAPPED) { + unsigned int ofs = start_pgofs - map->m_lblk; + + f2fs_update_extent_cache_range(&dn, + start_pgofs, map->m_pblk + ofs, + map->m_len - ofs); + } + } + f2fs_put_dnode(&dn); - if (create) { + if (map->m_may_create) { __do_map_lock(sbi, flag, false); f2fs_balance_fs(sbi, dn.node_changed); } goto next_dnode; sync_out: + + /* for hardware encryption, but to avoid potential issue in future */ + if (flag == F2FS_GET_BLOCK_DIO && map->m_flags & F2FS_MAP_MAPPED) + f2fs_wait_on_block_writeback_range(inode, + map->m_pblk, map->m_len); + + if (flag == F2FS_GET_BLOCK_PRECACHE) { + if (map->m_flags & F2FS_MAP_MAPPED) { + unsigned int ofs = start_pgofs - map->m_lblk; + + f2fs_update_extent_cache_range(&dn, + start_pgofs, map->m_pblk + ofs, + map->m_len - ofs); + } + if (map->m_next_extent) + *map->m_next_extent = pgofs + 1; + } f2fs_put_dnode(&dn); unlock_out: - if (create) { + if (map->m_may_create) { __do_map_lock(sbi, flag, false); f2fs_balance_fs(sbi, dn.node_changed); } @@ -1066,9 +1278,35 @@ out: return err; } +bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len) +{ + struct f2fs_map_blocks map; + block_t last_lblk; + int err; + + if (pos + len > i_size_read(inode)) + return false; + + map.m_lblk = F2FS_BYTES_TO_BLK(pos); + map.m_next_pgofs = NULL; + map.m_next_extent = NULL; + map.m_seg_type = NO_CHECK_TYPE; + map.m_may_create = false; + last_lblk = F2FS_BLK_ALIGN(pos + len); + + while (map.m_lblk < last_lblk) { + map.m_len = last_lblk - map.m_lblk; + err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_DEFAULT); + if (err || map.m_len == 0) + return false; + map.m_lblk += map.m_len; + } + return true; +} + static int __get_data_block(struct inode *inode, sector_t iblock, struct buffer_head *bh, int create, int flag, - pgoff_t *next_pgofs) + pgoff_t *next_pgofs, int seg_type, bool may_write) { struct f2fs_map_blocks map; int err; @@ -1076,6 +1314,9 @@ static int __get_data_block(struct inode *inode, sector_t iblock, map.m_lblk = iblock; map.m_len = bh->b_size >> inode->i_blkbits; map.m_next_pgofs = next_pgofs; + map.m_next_extent = NULL; + map.m_seg_type = seg_type; + map.m_may_create = may_write; err = f2fs_map_blocks(inode, &map, create, flag); if (!err) { @@ -1091,14 +1332,26 @@ static int get_data_block(struct inode *inode, sector_t iblock, pgoff_t *next_pgofs) { return __get_data_block(inode, iblock, bh_result, create, - flag, next_pgofs); + flag, next_pgofs, + NO_CHECK_TYPE, create); +} + +static int get_data_block_dio_write(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) +{ + return __get_data_block(inode, iblock, bh_result, create, + F2FS_GET_BLOCK_DIO, NULL, + f2fs_rw_hint_to_seg_type(inode->i_write_hint), + true); } static int get_data_block_dio(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { return __get_data_block(inode, iblock, bh_result, create, - F2FS_GET_BLOCK_DEFAULT, NULL); + F2FS_GET_BLOCK_DIO, NULL, + f2fs_rw_hint_to_seg_type(inode->i_write_hint), + false); } static int get_data_block_bmap(struct inode *inode, sector_t iblock, @@ -1109,7 +1362,8 @@ static int get_data_block_bmap(struct inode *inode, sector_t iblock, return -EFBIG; return __get_data_block(inode, iblock, bh_result, create, - F2FS_GET_BLOCK_BMAP, NULL); + F2FS_GET_BLOCK_BMAP, NULL, + NO_CHECK_TYPE, create); } static inline sector_t logical_to_blk(struct inode *inode, loff_t offset) @@ -1122,6 +1376,76 @@ static inline loff_t blk_to_logical(struct inode *inode, sector_t blk) return (blk << inode->i_blkbits); } +static int f2fs_xattr_fiemap(struct inode *inode, + struct fiemap_extent_info *fieinfo) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct page *page; + struct node_info ni; + __u64 phys = 0, len; + __u32 flags; + nid_t xnid = F2FS_I(inode)->i_xattr_nid; + int err = 0; + + if (f2fs_has_inline_xattr(inode)) { + int offset; + + page = f2fs_grab_cache_page(NODE_MAPPING(sbi), + inode->i_ino, false); + if (!page) + return -ENOMEM; + + err = f2fs_get_node_info(sbi, inode->i_ino, &ni); + if (err) { + f2fs_put_page(page, 1); + return err; + } + + phys = (__u64)blk_to_logical(inode, ni.blk_addr); + offset = offsetof(struct f2fs_inode, i_addr) + + sizeof(__le32) * (DEF_ADDRS_PER_INODE - + get_inline_xattr_addrs(inode)); + + phys += offset; + len = inline_xattr_size(inode); + + f2fs_put_page(page, 1); + + flags = FIEMAP_EXTENT_DATA_INLINE | FIEMAP_EXTENT_NOT_ALIGNED; + + if (!xnid) + flags |= FIEMAP_EXTENT_LAST; + + err = fiemap_fill_next_extent(fieinfo, 0, phys, len, flags); + if (err || err == 1) + return err; + } + + if (xnid) { + page = f2fs_grab_cache_page(NODE_MAPPING(sbi), xnid, false); + if (!page) + return -ENOMEM; + + err = f2fs_get_node_info(sbi, xnid, &ni); + if (err) { + f2fs_put_page(page, 1); + return err; + } + + phys = (__u64)blk_to_logical(inode, ni.blk_addr); + len = inode->i_sb->s_blocksize; + + f2fs_put_page(page, 1); + + flags = FIEMAP_EXTENT_LAST; + } + + if (phys) + err = fiemap_fill_next_extent(fieinfo, 0, phys, len, flags); + + return (err < 0 ? err : 0); +} + int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len) { @@ -1132,18 +1456,29 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u32 flags = 0; int ret = 0; - ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC); + if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) { + ret = f2fs_precache_extents(inode); + if (ret) + return ret; + } + + ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC | FIEMAP_FLAG_XATTR); if (ret) return ret; + inode_lock(inode); + + if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) { + ret = f2fs_xattr_fiemap(inode, fieinfo); + goto out; + } + if (f2fs_has_inline_data(inode)) { ret = f2fs_inline_data_fiemap(inode, fieinfo, start, len); if (ret != -EAGAIN) - return ret; + goto out; } - inode_lock(inode); - if (logical_to_blk(inode, len) == 0) len = blk_to_logical(inode, 1); @@ -1207,13 +1542,17 @@ out: /* * This function was originally taken from fs/mpage.c, and customized for f2fs. * Major change was from block_size == page_size in f2fs by default. + * + * Note that the aops->readpages() function is ONLY used for read-ahead. If + * this function ever deviates from doing just read-ahead, it should either + * use ->readpage() or do the necessary surgery to decouple ->readpages() + * from read-ahead. */ static int f2fs_mpage_readpages(struct address_space *mapping, struct list_head *pages, struct page *page, - unsigned nr_pages) + unsigned nr_pages, bool is_readahead) { struct bio *bio = NULL; - unsigned page_idx; sector_t last_block_in_bio = 0; struct inode *inode = mapping->host; const unsigned blkbits = inode->i_blkbits; @@ -1229,9 +1568,11 @@ static int f2fs_mpage_readpages(struct address_space *mapping, map.m_len = 0; map.m_flags = 0; map.m_next_pgofs = NULL; + map.m_next_extent = NULL; + map.m_seg_type = NO_CHECK_TYPE; + map.m_may_create = false; - for (page_idx = 0; nr_pages; page_idx++, nr_pages--) { - + for (; nr_pages; nr_pages--) { if (pages) { page = list_last_entry(pages, struct page, lru); @@ -1250,6 +1591,9 @@ static int f2fs_mpage_readpages(struct address_space *mapping, if (last_block > last_block_in_file) last_block = last_block_in_file; + /* just zeroing out page which is beyond EOF */ + if (block_in_file >= last_block) + goto zero_out; /* * Map blocks using the previous result first. */ @@ -1262,16 +1606,11 @@ static int f2fs_mpage_readpages(struct address_space *mapping, * Then do more f2fs_map_blocks() calls until we are * done with this page. */ - map.m_flags = 0; + map.m_lblk = block_in_file; + map.m_len = last_block - block_in_file; - if (block_in_file < last_block) { - map.m_lblk = block_in_file; - map.m_len = last_block - block_in_file; - - if (f2fs_map_blocks(inode, &map, 0, - F2FS_GET_BLOCK_DEFAULT)) - goto set_error_page; - } + if (f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_DEFAULT)) + goto set_error_page; got_it: if ((map.m_flags & F2FS_MAP_MAPPED)) { block_nr = map.m_pblk + block_in_file - map.m_lblk; @@ -1286,6 +1625,7 @@ got_it: DATA_GENERIC)) goto set_error_page; } else { +zero_out: zero_user_segment(page, 0, PAGE_SIZE); if (!PageUptodate(page)) SetPageUptodate(page); @@ -1300,20 +1640,29 @@ got_it: if (bio && (last_block_in_bio != block_nr - 1 || !__same_bdev(F2FS_I_SB(inode), block_nr, bio))) { submit_and_realloc: - __submit_bio(F2FS_I_SB(inode), bio, DATA); + __f2fs_submit_read_bio(F2FS_I_SB(inode), bio, DATA); bio = NULL; } if (bio == NULL) { - bio = f2fs_grab_read_bio(inode, block_nr, nr_pages); + bio = f2fs_grab_read_bio(inode, block_nr, nr_pages, + is_readahead ? REQ_RAHEAD : 0); if (IS_ERR(bio)) { bio = NULL; goto set_error_page; } } + /* + * If the page is under writeback, we need to wait for + * its completion to see the correct decrypted data. + */ + f2fs_wait_on_block_writeback(inode, block_nr); + if (bio_add_page(bio, page, blocksize, 0) < blocksize) goto submit_and_realloc; + inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA); + ClearPageError(page); last_block_in_bio = block_nr; goto next_page; set_error_page: @@ -1323,7 +1672,7 @@ set_error_page: goto next_page; confused: if (bio) { - __submit_bio(F2FS_I_SB(inode), bio, DATA); + __f2fs_submit_read_bio(F2FS_I_SB(inode), bio, DATA); bio = NULL; } unlock_page(page); @@ -1333,7 +1682,7 @@ next_page: } BUG_ON(pages && !list_empty(pages)); if (bio) - __submit_bio(F2FS_I_SB(inode), bio, DATA); + __f2fs_submit_read_bio(F2FS_I_SB(inode), bio, DATA); return 0; } @@ -1348,7 +1697,7 @@ static int f2fs_read_data_page(struct file *file, struct page *page) if (f2fs_has_inline_data(inode)) ret = f2fs_read_inline_data(inode, page); if (ret == -EAGAIN) - ret = f2fs_mpage_readpages(page->mapping, NULL, page, 1); + ret = f2fs_mpage_readpages(page->mapping, NULL, page, 1, false); return ret; } @@ -1356,7 +1705,7 @@ static int f2fs_read_data_pages(struct file *file, struct address_space *mapping, struct list_head *pages, unsigned nr_pages) { - struct inode *inode = file->f_mapping->host; + struct inode *inode = mapping->host; struct page *page = list_last_entry(pages, struct page, lru); trace_f2fs_readpages(inode, page, nr_pages); @@ -1365,56 +1714,136 @@ static int f2fs_read_data_pages(struct file *file, if (f2fs_has_inline_data(inode)) return 0; - return f2fs_mpage_readpages(mapping, pages, NULL, nr_pages); + return f2fs_mpage_readpages(mapping, pages, NULL, nr_pages, true); } static int encrypt_one_page(struct f2fs_io_info *fio) { struct inode *inode = fio->page->mapping->host; + struct page *mpage; gfp_t gfp_flags = GFP_NOFS; if (!f2fs_encrypted_file(inode)) return 0; - /* wait for GCed encrypted page writeback */ - f2fs_wait_on_block_writeback(fio->sbi, fio->old_blkaddr); + /* wait for GCed page writeback via META_MAPPING */ + f2fs_wait_on_block_writeback(inode, fio->old_blkaddr); retry_encrypt: fio->encrypted_page = fscrypt_encrypt_page(inode, fio->page, PAGE_SIZE, 0, fio->page->index, gfp_flags); - if (!IS_ERR(fio->encrypted_page)) - return 0; + if (IS_ERR(fio->encrypted_page)) { + /* flush pending IOs and wait for a while in the ENOMEM case */ + if (PTR_ERR(fio->encrypted_page) == -ENOMEM) { + f2fs_flush_merged_writes(fio->sbi); + congestion_wait(BLK_RW_ASYNC, HZ/50); + gfp_flags |= __GFP_NOFAIL; + goto retry_encrypt; + } + return PTR_ERR(fio->encrypted_page); + } - /* flush pending IOs and wait for a while in the ENOMEM case */ - if (PTR_ERR(fio->encrypted_page) == -ENOMEM) { - f2fs_flush_merged_writes(fio->sbi); - congestion_wait(BLK_RW_ASYNC, HZ/50); - gfp_flags |= __GFP_NOFAIL; - goto retry_encrypt; + mpage = find_lock_page(META_MAPPING(fio->sbi), fio->old_blkaddr); + if (mpage) { + if (PageUptodate(mpage)) + memcpy(page_address(mpage), + page_address(fio->encrypted_page), PAGE_SIZE); + f2fs_put_page(mpage, 1); } - return PTR_ERR(fio->encrypted_page); + return 0; +} + +static inline bool check_inplace_update_policy(struct inode *inode, + struct f2fs_io_info *fio) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + unsigned int policy = SM_I(sbi)->ipu_policy; + + if (policy & (0x1 << F2FS_IPU_FORCE)) + return true; + if (policy & (0x1 << F2FS_IPU_SSR) && f2fs_need_SSR(sbi)) + return true; + if (policy & (0x1 << F2FS_IPU_UTIL) && + utilization(sbi) > SM_I(sbi)->min_ipu_util) + return true; + if (policy & (0x1 << F2FS_IPU_SSR_UTIL) && f2fs_need_SSR(sbi) && + utilization(sbi) > SM_I(sbi)->min_ipu_util) + return true; + + /* + * IPU for rewrite async pages + */ + if (policy & (0x1 << F2FS_IPU_ASYNC) && + fio && fio->op == REQ_OP_WRITE && + !(fio->op_flags & REQ_SYNC) && + !f2fs_encrypted_inode(inode)) + return true; + + /* this is only set during fdatasync */ + if (policy & (0x1 << F2FS_IPU_FSYNC) && + is_inode_flag_set(inode, FI_NEED_IPU)) + return true; + + if (unlikely(fio && is_sbi_flag_set(sbi, SBI_CP_DISABLED) && + !f2fs_is_checkpointed_data(sbi, fio->old_blkaddr))) + return true; + + return false; +} + +bool f2fs_should_update_inplace(struct inode *inode, struct f2fs_io_info *fio) +{ + if (f2fs_is_pinned_file(inode)) + return true; + + /* if this is cold file, we should overwrite to avoid fragmentation */ + if (file_is_cold(inode)) + return true; + + return check_inplace_update_policy(inode, fio); +} + +bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + + if (test_opt(sbi, LFS)) + return true; + if (S_ISDIR(inode->i_mode)) + return true; + if (IS_NOQUOTA(inode)) + return true; + if (f2fs_is_atomic_file(inode)) + return true; + if (fio) { + if (is_cold_data(fio->page)) + return true; + if (IS_ATOMIC_WRITTEN_PAGE(fio->page)) + return true; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED) && + f2fs_is_checkpointed_data(sbi, fio->old_blkaddr))) + return true; + } + return false; } static inline bool need_inplace_update(struct f2fs_io_info *fio) { struct inode *inode = fio->page->mapping->host; - if (S_ISDIR(inode->i_mode) || f2fs_is_atomic_file(inode)) - return false; - if (is_cold_data(fio->page)) - return false; - if (IS_ATOMIC_WRITTEN_PAGE(fio->page)) + if (f2fs_should_update_outplace(inode, fio)) return false; - return need_inplace_update_policy(inode, fio); + return f2fs_should_update_inplace(inode, fio); } -int do_write_data_page(struct f2fs_io_info *fio) +int f2fs_do_write_data_page(struct f2fs_io_info *fio) { struct page *page = fio->page; struct inode *inode = page->mapping->host; struct dnode_of_data dn; struct extent_info ei = {0,0,0}; + struct node_info ni; bool ipu_force = false; int err = 0; @@ -1436,7 +1865,7 @@ int do_write_data_page(struct f2fs_io_info *fio) if (fio->need_lock == LOCK_REQ && !f2fs_trylock_op(fio->sbi)) return -EAGAIN; - err = get_dnode_of_data(&dn, page->index, LOOKUP_NODE); + err = f2fs_get_dnode_of_data(&dn, page->index, LOOKUP_NODE); if (err) goto out; @@ -1466,10 +1895,18 @@ got_it: goto out_writepage; set_page_writeback(page); + ClearPageError(page); f2fs_put_dnode(&dn); if (fio->need_lock == LOCK_REQ) f2fs_unlock_op(fio->sbi); - err = rewrite_data_page(fio); + err = f2fs_inplace_write_data(fio); + if (err) { + if (f2fs_encrypted_file(inode)) + fscrypt_pullback_bio_page(&fio->encrypted_page, + true); + if (PageWriteback(page)) + end_page_writeback(page); + } trace_f2fs_do_write_data_page(fio->page, IPU); set_inode_flag(inode, FI_UPDATE_WRITE); return err; @@ -1483,14 +1920,21 @@ got_it: fio->need_lock = LOCK_REQ; } + err = f2fs_get_node_info(fio->sbi, dn.nid, &ni); + if (err) + goto out_writepage; + + fio->version = ni.version; + err = encrypt_one_page(fio); if (err) goto out_writepage; set_page_writeback(page); + ClearPageError(page); /* LFS mode write path */ - write_data_page(&dn, fio); + f2fs_outplace_write_data(&dn, fio); trace_f2fs_do_write_data_page(page, OPU); set_inode_flag(inode, FI_APPEND_WRITE); if (page->index == 0) @@ -1518,6 +1962,7 @@ static int __write_data_page(struct page *page, bool *submitted, int err = 0; struct f2fs_io_info fio = { .sbi = sbi, + .ino = inode->i_ino, .type = DATA, .op = REQ_OP_WRITE, .op_flags = wbc_to_write_flags(wbc), @@ -1527,10 +1972,23 @@ static int __write_data_page(struct page *page, bool *submitted, .submitted = false, .need_lock = LOCK_RETRY, .io_type = io_type, + .io_wbc = wbc, }; trace_f2fs_writepage(page, DATA); + /* we should bypass data pages to proceed the kworkder jobs */ + if (unlikely(f2fs_cp_error(sbi))) { + mapping_set_error(page->mapping, -EIO); + /* + * don't drop any dirty dentry pages for keeping lastest + * directory structure. + */ + if (S_ISDIR(inode->i_mode)) + goto redirty_out; + goto out; + } + if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) goto redirty_out; @@ -1552,19 +2010,13 @@ write: /* we should not write 0'th page having journal header */ if (f2fs_is_volatile_file(inode) && (!page->index || (!wbc->for_reclaim && - available_free_memory(sbi, BASE_CHECK)))) + f2fs_available_free_memory(sbi, BASE_CHECK)))) goto redirty_out; - /* we should bypass data pages to proceed the kworkder jobs */ - if (unlikely(f2fs_cp_error(sbi))) { - mapping_set_error(page->mapping, -EIO); - goto out; - } - /* Dentry blocks are controlled by checkpoint */ if (S_ISDIR(inode->i_mode)) { fio.need_lock = LOCK_DONE; - err = do_write_data_page(&fio); + err = f2fs_do_write_data_page(&fio); goto done; } @@ -1583,14 +2035,21 @@ write: } if (err == -EAGAIN) { - err = do_write_data_page(&fio); + err = f2fs_do_write_data_page(&fio); if (err == -EAGAIN) { fio.need_lock = LOCK_REQ; - err = do_write_data_page(&fio); + err = f2fs_do_write_data_page(&fio); } } - if (F2FS_I(inode)->last_disk_size < psize) - F2FS_I(inode)->last_disk_size = psize; + + if (err) { + file_set_keep_isize(inode); + } else { + down_write(&F2FS_I(inode)->i_sem); + if (F2FS_I(inode)->last_disk_size < psize) + F2FS_I(inode)->last_disk_size = psize; + up_write(&F2FS_I(inode)->i_sem); + } done: if (err && err != -ENOENT) @@ -1604,14 +2063,14 @@ out: } if (wbc->for_reclaim) { - f2fs_submit_merged_write_cond(sbi, inode, 0, page->index, DATA); + f2fs_submit_merged_write_cond(sbi, NULL, page, 0, DATA); clear_inode_flag(inode, FI_HOT_DATA); - remove_dirty_inode(inode); + f2fs_remove_dirty_inode(inode); submitted = NULL; } unlock_page(page); - if (!S_ISDIR(inode->i_mode)) + if (!S_ISDIR(inode->i_mode) && !IS_NOQUOTA(inode)) f2fs_balance_fs(sbi, need_balance_fs); if (unlikely(f2fs_cp_error(sbi))) { @@ -1656,15 +2115,16 @@ static int f2fs_write_cache_pages(struct address_space *mapping, int ret = 0; int done = 0; struct pagevec pvec; + struct f2fs_sb_info *sbi = F2FS_M_SB(mapping); int nr_pages; pgoff_t uninitialized_var(writeback_index); pgoff_t index; pgoff_t end; /* Inclusive */ pgoff_t done_index; - pgoff_t last_idx = ULONG_MAX; int cycled; int range_whole = 0; int tag; + int nwritten = 0; pagevec_init(&pvec, 0); @@ -1700,8 +2160,8 @@ retry: while (!done && (index <= end)) { int i; - nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag, - min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1); + nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end, + tag); if (nr_pages == 0) break; @@ -1709,7 +2169,9 @@ retry: struct page *page = pvec.pages[i]; bool submitted = false; - if (page->index > end) { + /* give a priority to WB_SYNC threads */ + if (atomic_read(&sbi->wb_sync_req[DATA]) && + wbc->sync_mode == WB_SYNC_NONE) { done = 1; break; } @@ -1732,12 +2194,11 @@ continue_unlock: if (PageWriteback(page)) { if (wbc->sync_mode != WB_SYNC_NONE) f2fs_wait_on_page_writeback(page, - DATA, true); + DATA, true, true); else goto continue_unlock; } - BUG_ON(PageWriteback(page)); if (!clear_page_dirty_for_io(page)) goto continue_unlock; @@ -1765,12 +2226,10 @@ continue_unlock: done = 1; break; } else if (submitted) { - last_idx = page->index; + nwritten++; } - /* give a priority to WB_SYNC threads */ - if ((atomic_read(&F2FS_M_SB(mapping)->wb_sync_req) || - --wbc->nr_to_write <= 0) && + if (--wbc->nr_to_write <= 0 && wbc->sync_mode == WB_SYNC_NONE) { done = 1; break; @@ -1789,14 +2248,28 @@ continue_unlock: if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) mapping->writeback_index = done_index; - if (last_idx != ULONG_MAX) + if (nwritten) f2fs_submit_merged_write_cond(F2FS_M_SB(mapping), mapping->host, - 0, last_idx, DATA); + NULL, 0, DATA); return ret; } -int __f2fs_write_data_pages(struct address_space *mapping, +static inline bool __should_serialize_io(struct inode *inode, + struct writeback_control *wbc) +{ + if (!S_ISREG(inode->i_mode)) + return false; + if (IS_NOQUOTA(inode)) + return false; + if (wbc->sync_mode != WB_SYNC_ALL) + return true; + if (get_dirty_pages(inode) >= SM_I(F2FS_I_SB(inode))->min_seq_blocks) + return true; + return false; +} + +static int __f2fs_write_data_pages(struct address_space *mapping, struct writeback_control *wbc, enum iostat_type io_type) { @@ -1804,6 +2277,7 @@ int __f2fs_write_data_pages(struct address_space *mapping, struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct blk_plug plug; int ret; + bool locked = false; /* deal with chardevs and other special file */ if (!mapping->a_ops->writepage) @@ -1817,9 +2291,10 @@ int __f2fs_write_data_pages(struct address_space *mapping, if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) goto skip_write; - if (S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_NONE && + if ((S_ISDIR(inode->i_mode) || IS_NOQUOTA(inode)) && + wbc->sync_mode == WB_SYNC_NONE && get_dirty_pages(inode) < nr_pages_to_skip(sbi, DATA) && - available_free_memory(sbi, DIRTY_DENTS)) + f2fs_available_free_memory(sbi, DIRTY_DENTS)) goto skip_write; /* skip writing during file defragment */ @@ -1830,22 +2305,30 @@ int __f2fs_write_data_pages(struct address_space *mapping, /* to avoid spliting IOs due to mixed WB_SYNC_ALL and WB_SYNC_NONE */ if (wbc->sync_mode == WB_SYNC_ALL) - atomic_inc(&sbi->wb_sync_req); - else if (atomic_read(&sbi->wb_sync_req)) + atomic_inc(&sbi->wb_sync_req[DATA]); + else if (atomic_read(&sbi->wb_sync_req[DATA])) goto skip_write; + if (__should_serialize_io(inode, wbc)) { + mutex_lock(&sbi->writepages); + locked = true; + } + blk_start_plug(&plug); ret = f2fs_write_cache_pages(mapping, wbc, io_type); blk_finish_plug(&plug); + if (locked) + mutex_unlock(&sbi->writepages); + if (wbc->sync_mode == WB_SYNC_ALL) - atomic_dec(&sbi->wb_sync_req); + atomic_dec(&sbi->wb_sync_req[DATA]); /* * if some pages were truncated, we cannot guarantee its mapping->host * to detect pending bios. */ - remove_dirty_inode(inode); + f2fs_remove_dirty_inode(inode); return ret; skip_write: @@ -1870,10 +2353,15 @@ static void f2fs_write_failed(struct address_space *mapping, loff_t to) loff_t i_size = i_size_read(inode); if (to > i_size) { + down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); down_write(&F2FS_I(inode)->i_mmap_sem); + truncate_pagecache(inode, i_size); - truncate_blocks(inode, i_size, true); + if (!IS_NOQUOTA(inode)) + f2fs_truncate_blocks(inode, i_size, true); + up_write(&F2FS_I(inode)->i_mmap_sem); + up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); } } @@ -1911,7 +2399,7 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi, } restart: /* check inline_data */ - ipage = get_node_page(sbi, inode->i_ino); + ipage = f2fs_get_node_page(sbi, inode->i_ino); if (IS_ERR(ipage)) { err = PTR_ERR(ipage); goto unlock_out; @@ -1921,7 +2409,7 @@ restart: if (f2fs_has_inline_data(inode)) { if (pos + len <= MAX_INLINE_DATA(inode)) { - read_inline_data(page, ipage); + f2fs_do_read_inline_data(page, ipage); set_inode_flag(inode, FI_DATA_EXIST); if (inode->i_nlink) set_inline_node(ipage); @@ -1939,7 +2427,7 @@ restart: dn.data_blkaddr = ei.blk + index - ei.fofs; } else { /* hole case */ - err = get_dnode_of_data(&dn, index, LOOKUP_NODE); + err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE); if (err || dn.data_blkaddr == NULL_ADDR) { f2fs_put_dnode(&dn); __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, @@ -1970,12 +2458,34 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping, struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct page *page = NULL; pgoff_t index = ((unsigned long long) pos) >> PAGE_SHIFT; - bool need_balance = false; + bool need_balance = false, drop_atomic = false; block_t blkaddr = NULL_ADDR; int err = 0; + if (trace_android_fs_datawrite_start_enabled()) { + char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; + + path = android_fstrace_get_pathname(pathbuf, + MAX_TRACE_PATHBUF_LEN, + inode); + trace_android_fs_datawrite_start(inode, pos, len, + current->pid, path, + current->comm); + } trace_f2fs_write_begin(inode, pos, len, flags); + err = f2fs_is_checkpoint_ready(sbi); + if (err) + goto fail; + + if ((f2fs_is_atomic_file(inode) && + !f2fs_available_free_memory(sbi, INMEM_PAGES)) || + is_inode_flag_set(inode, FI_ATOMIC_REVOKE_REQUEST)) { + err = -ENOMEM; + drop_atomic = true; + goto fail; + } + /* * We should check this at this moment to avoid deadlock on inode page * and #0 page. The locking rule for inline_data conversion should be: @@ -1991,7 +2501,7 @@ repeat: * Do not use grab_cache_page_write_begin() to avoid deadlock due to * wait_for_stable_page. Will wait that below with our IO control. */ - page = pagecache_get_page(mapping, index, + page = f2fs_pagecache_get_page(mapping, index, FGP_LOCK | FGP_WRITE | FGP_CREAT, GFP_NOFS); if (!page) { err = -ENOMEM; @@ -2005,7 +2515,8 @@ repeat: if (err) goto fail; - if (need_balance && has_not_enough_free_secs(sbi, 0, 0)) { + if (need_balance && !IS_NOQUOTA(inode) && + has_not_enough_free_secs(sbi, 0, 0)) { unlock_page(page); f2fs_balance_fs(sbi, true); lock_page(page); @@ -2016,11 +2527,7 @@ repeat: } } - f2fs_wait_on_page_writeback(page, DATA, false); - - /* wait for GCed encrypted page writeback */ - if (f2fs_encrypted_file(inode)) - f2fs_wait_on_block_writeback(sbi, blkaddr); + f2fs_wait_on_page_writeback(page, DATA, false, true); if (len == PAGE_SIZE || PageUptodate(page)) return 0; @@ -2053,6 +2560,8 @@ repeat: fail: f2fs_put_page(page, 1); f2fs_write_failed(mapping, pos + len); + if (drop_atomic) + f2fs_drop_inmem_pages_all(sbi, false); return err; } @@ -2063,6 +2572,7 @@ static int f2fs_write_end(struct file *file, { struct inode *inode = page->mapping->host; + trace_android_fs_datawrite_end(inode, pos, len); trace_f2fs_write_end(inode, pos, len, copied); /* @@ -2092,48 +2602,164 @@ unlock_out: static int check_direct_IO(struct inode *inode, struct iov_iter *iter, loff_t offset) { - unsigned blocksize_mask = inode->i_sb->s_blocksize - 1; + unsigned i_blkbits = READ_ONCE(inode->i_blkbits); + unsigned blkbits = i_blkbits; + unsigned blocksize_mask = (1 << blkbits) - 1; + unsigned long align = offset | iov_iter_alignment(iter); + struct block_device *bdev = inode->i_sb->s_bdev; + + if (align & blocksize_mask) { + if (bdev) + blkbits = blksize_bits(bdev_logical_block_size(bdev)); + blocksize_mask = (1 << blkbits) - 1; + if (align & blocksize_mask) + return -EINVAL; + return 1; + } + return 0; +} + +static void f2fs_dio_end_io(struct bio *bio) +{ + struct f2fs_private_dio *dio = bio->bi_private; - if (offset & blocksize_mask) - return -EINVAL; + dec_page_count(F2FS_I_SB(dio->inode), + dio->write ? F2FS_DIO_WRITE : F2FS_DIO_READ); - if (iov_iter_alignment(iter) & blocksize_mask) - return -EINVAL; + bio->bi_private = dio->orig_private; + bio->bi_end_io = dio->orig_end_io; - return 0; + kvfree(dio); + + bio_endio(bio); +} + +static void f2fs_dio_submit_bio(struct bio *bio, struct inode *inode, + loff_t file_offset) +{ + struct f2fs_private_dio *dio; + bool write = (bio_op(bio) == REQ_OP_WRITE); + + dio = f2fs_kzalloc(F2FS_I_SB(inode), + sizeof(struct f2fs_private_dio), GFP_NOFS); + if (!dio) + goto out; + + dio->inode = inode; + dio->orig_end_io = bio->bi_end_io; + dio->orig_private = bio->bi_private; + dio->write = write; + + bio->bi_end_io = f2fs_dio_end_io; + bio->bi_private = dio; + + inc_page_count(F2FS_I_SB(inode), + write ? F2FS_DIO_WRITE : F2FS_DIO_READ); + + submit_bio(bio); + return; +out: + bio->bi_status = BLK_STS_IOERR; + bio_endio(bio); } static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct address_space *mapping = iocb->ki_filp->f_mapping; struct inode *inode = mapping->host; + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_inode_info *fi = F2FS_I(inode); size_t count = iov_iter_count(iter); loff_t offset = iocb->ki_pos; int rw = iov_iter_rw(iter); int err; + enum rw_hint hint = iocb->ki_hint; + int whint_mode = F2FS_OPTION(sbi).whint_mode; + bool do_opu; err = check_direct_IO(inode, iter, offset); if (err) - return err; + return err < 0 ? err : 0; - if (__force_buffered_io(inode, rw)) + if (f2fs_force_buffered_io(inode, iocb, iter)) return 0; + do_opu = allow_outplace_dio(inode, iocb, iter); + trace_f2fs_direct_IO_enter(inode, offset, count, rw); - down_read(&F2FS_I(inode)->dio_rwsem[rw]); - err = blockdev_direct_IO(iocb, inode, iter, get_data_block_dio); - up_read(&F2FS_I(inode)->dio_rwsem[rw]); + if (trace_android_fs_dataread_start_enabled() && + (rw == READ)) { + char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; + + path = android_fstrace_get_pathname(pathbuf, + MAX_TRACE_PATHBUF_LEN, + inode); + trace_android_fs_dataread_start(inode, offset, + count, current->pid, path, + current->comm); + } + if (trace_android_fs_datawrite_start_enabled() && + (rw == WRITE)) { + char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; + + path = android_fstrace_get_pathname(pathbuf, + MAX_TRACE_PATHBUF_LEN, + inode); + trace_android_fs_datawrite_start(inode, offset, count, + current->pid, path, + current->comm); + } + if (rw == WRITE && whint_mode == WHINT_MODE_OFF) + iocb->ki_hint = WRITE_LIFE_NOT_SET; + + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!down_read_trylock(&fi->i_gc_rwsem[rw])) { + iocb->ki_hint = hint; + err = -EAGAIN; + goto out; + } + if (do_opu && !down_read_trylock(&fi->i_gc_rwsem[READ])) { + up_read(&fi->i_gc_rwsem[rw]); + iocb->ki_hint = hint; + err = -EAGAIN; + goto out; + } + } else { + down_read(&fi->i_gc_rwsem[rw]); + if (do_opu) + down_read(&fi->i_gc_rwsem[READ]); + } + + err = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, + iter, rw == WRITE ? get_data_block_dio_write : + get_data_block_dio, NULL, f2fs_dio_submit_bio, + DIO_LOCKING | DIO_SKIP_HOLES); + + if (do_opu) + up_read(&fi->i_gc_rwsem[READ]); + + up_read(&fi->i_gc_rwsem[rw]); if (rw == WRITE) { + if (whint_mode == WHINT_MODE_OFF) + iocb->ki_hint = hint; if (err > 0) { f2fs_update_iostat(F2FS_I_SB(inode), APP_DIRECT_IO, err); - set_inode_flag(inode, FI_UPDATE_WRITE); + if (!do_opu) + set_inode_flag(inode, FI_UPDATE_WRITE); } else if (err < 0) { f2fs_write_failed(mapping, offset + count); } } +out: + if (trace_android_fs_dataread_start_enabled() && + (rw == READ)) + trace_android_fs_dataread_end(inode, offset, count); + if (trace_android_fs_datawrite_start_enabled() && + (rw == WRITE)) + trace_android_fs_datawrite_end(inode, offset, count); trace_f2fs_direct_IO_exit(inode, offset, count, rw, err); @@ -2157,18 +2783,16 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset, dec_page_count(sbi, F2FS_DIRTY_NODES); } else { inode_dec_dirty_pages(inode); - remove_dirty_inode(inode); + f2fs_remove_dirty_inode(inode); } } clear_cold_data(page); - /* This is atomic written page, keep Private */ if (IS_ATOMIC_WRITTEN_PAGE(page)) - return drop_inmem_page(inode, page); + return f2fs_drop_inmem_page(inode, page); - set_page_private(page, 0); - ClearPagePrivate(page); + f2fs_clear_page_private(page); } int f2fs_release_page(struct page *page, gfp_t wait) @@ -2182,40 +2806,10 @@ int f2fs_release_page(struct page *page, gfp_t wait) return 0; clear_cold_data(page); - set_page_private(page, 0); - ClearPagePrivate(page); + f2fs_clear_page_private(page); return 1; } -/* - * This was copied from __set_page_dirty_buffers which gives higher performance - * in very high speed storages. (e.g., pmem) - */ -void f2fs_set_page_dirty_nobuffers(struct page *page) -{ - struct address_space *mapping = page->mapping; - unsigned long flags; - - if (unlikely(!mapping)) - return; - - spin_lock(&mapping->private_lock); - lock_page_memcg(page); - SetPageDirty(page); - spin_unlock(&mapping->private_lock); - - spin_lock_irqsave(&mapping->tree_lock, flags); - WARN_ON_ONCE(!PageUptodate(page)); - account_page_dirtied(page, mapping); - radix_tree_tag_set(&mapping->page_tree, - page_index(page), PAGECACHE_TAG_DIRTY); - spin_unlock_irqrestore(&mapping->tree_lock, flags); - unlock_page_memcg(page); - - __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); - return; -} - static int f2fs_set_data_page_dirty(struct page *page) { struct address_space *mapping = page->mapping; @@ -2228,7 +2822,7 @@ static int f2fs_set_data_page_dirty(struct page *page) if (f2fs_is_atomic_file(inode) && !f2fs_is_commit_atomic_write(inode)) { if (!IS_ATOMIC_WRITTEN_PAGE(page)) { - register_inmem_page(inode, page); + f2fs_register_inmem_page(inode, page); return 1; } /* @@ -2239,8 +2833,8 @@ static int f2fs_set_data_page_dirty(struct page *page) } if (!PageDirty(page)) { - f2fs_set_page_dirty_nobuffers(page); - update_dirty_page(inode, page); + __set_page_dirty_nobuffers(page); + f2fs_update_dirty_page(inode, page); return 1; } return 0; @@ -2280,12 +2874,8 @@ int f2fs_migrate_page(struct address_space *mapping, return -EAGAIN; } - /* - * A reference is expected if PagePrivate set when move mapping, - * however F2FS breaks this for maintaining dirty page counts when - * truncating pages. So here adjusting the 'extra_count' make it work. - */ - extra_count = (atomic_written ? 1 : 0) - page_has_private(page); + /* one extra reference was held for atomic_write page */ + extra_count = atomic_written ? 1 : 0; rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode, extra_count); if (rc != MIGRATEPAGE_SUCCESS) { @@ -2306,9 +2896,10 @@ int f2fs_migrate_page(struct address_space *mapping, get_page(newpage); } - if (PagePrivate(page)) - SetPagePrivate(newpage); - set_page_private(newpage, page_private(page)); + if (PagePrivate(page)) { + f2fs_set_page_private(newpage, page_private(page)); + f2fs_clear_page_private(page); + } if (mode != MIGRATE_SYNC_NO_COPY) migrate_page_copy(newpage, page); @@ -2335,3 +2926,38 @@ const struct address_space_operations f2fs_dblock_aops = { .migratepage = f2fs_migrate_page, #endif }; + +void f2fs_clear_radix_tree_dirty_tag(struct page *page) +{ + struct address_space *mapping = page_mapping(page); + unsigned long flags; + + spin_lock_irqsave(&mapping->tree_lock, flags); + radix_tree_tag_clear(&mapping->page_tree, page_index(page), + PAGECACHE_TAG_DIRTY); + spin_unlock_irqrestore(&mapping->tree_lock, flags); +} + +int __init f2fs_init_post_read_processing(void) +{ + bio_post_read_ctx_cache = KMEM_CACHE(bio_post_read_ctx, 0); + if (!bio_post_read_ctx_cache) + goto fail; + bio_post_read_ctx_pool = + mempool_create_slab_pool(NUM_PREALLOC_POST_READ_CTXS, + bio_post_read_ctx_cache); + if (!bio_post_read_ctx_pool) + goto fail_free_cache; + return 0; + +fail_free_cache: + kmem_cache_destroy(bio_post_read_ctx_cache); +fail: + return -ENOMEM; +} + +void __exit f2fs_destroy_post_read_processing(void) +{ + mempool_destroy(bio_post_read_ctx_pool); + kmem_cache_destroy(bio_post_read_ctx_cache); +} diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index 87f449845f5f..d00ba9b711a4 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * f2fs debugging statistics * @@ -5,10 +6,6 @@ * http://www.samsung.com/ * Copyright (c) 2012 Linux Foundation * Copyright (c) 2012 Greg Kroah-Hartman <gregkh@linuxfoundation.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> @@ -45,28 +42,37 @@ static void update_general_status(struct f2fs_sb_info *sbi) si->ndirty_dent = get_pages(sbi, F2FS_DIRTY_DENTS); si->ndirty_meta = get_pages(sbi, F2FS_DIRTY_META); si->ndirty_data = get_pages(sbi, F2FS_DIRTY_DATA); + si->ndirty_qdata = get_pages(sbi, F2FS_DIRTY_QDATA); si->ndirty_imeta = get_pages(sbi, F2FS_DIRTY_IMETA); si->ndirty_dirs = sbi->ndirty_inode[DIR_INODE]; si->ndirty_files = sbi->ndirty_inode[FILE_INODE]; + si->nquota_files = sbi->nquota_files; si->ndirty_all = sbi->ndirty_inode[DIRTY_META]; si->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES); si->aw_cnt = atomic_read(&sbi->aw_cnt); si->vw_cnt = atomic_read(&sbi->vw_cnt); si->max_aw_cnt = atomic_read(&sbi->max_aw_cnt); si->max_vw_cnt = atomic_read(&sbi->max_vw_cnt); + si->nr_dio_read = get_pages(sbi, F2FS_DIO_READ); + si->nr_dio_write = get_pages(sbi, F2FS_DIO_WRITE); si->nr_wb_cp_data = get_pages(sbi, F2FS_WB_CP_DATA); si->nr_wb_data = get_pages(sbi, F2FS_WB_DATA); + si->nr_rd_data = get_pages(sbi, F2FS_RD_DATA); + si->nr_rd_node = get_pages(sbi, F2FS_RD_NODE); + si->nr_rd_meta = get_pages(sbi, F2FS_RD_META); if (SM_I(sbi) && SM_I(sbi)->fcc_info) { si->nr_flushed = atomic_read(&SM_I(sbi)->fcc_info->issued_flush); si->nr_flushing = - atomic_read(&SM_I(sbi)->fcc_info->issing_flush); + atomic_read(&SM_I(sbi)->fcc_info->queued_flush); + si->flush_list_empty = + llist_empty(&SM_I(sbi)->fcc_info->issue_list); } if (SM_I(sbi) && SM_I(sbi)->dcc_info) { si->nr_discarded = atomic_read(&SM_I(sbi)->dcc_info->issued_discard); si->nr_discarding = - atomic_read(&SM_I(sbi)->dcc_info->issing_discard); + atomic_read(&SM_I(sbi)->dcc_info->queued_discard); si->nr_discard_cmd = atomic_read(&SM_I(sbi)->dcc_info->discard_cmd_cnt); si->undiscard_blks = SM_I(sbi)->dcc_info->undiscard_blks; @@ -90,16 +96,22 @@ static void update_general_status(struct f2fs_sb_info *sbi) si->free_secs = free_sections(sbi); si->prefree_count = prefree_segments(sbi); si->dirty_count = dirty_segments(sbi); - si->node_pages = NODE_MAPPING(sbi)->nrpages; - si->meta_pages = META_MAPPING(sbi)->nrpages; + if (sbi->node_inode) + si->node_pages = NODE_MAPPING(sbi)->nrpages; + if (sbi->meta_inode) + si->meta_pages = META_MAPPING(sbi)->nrpages; si->nats = NM_I(sbi)->nat_cnt; si->dirty_nats = NM_I(sbi)->dirty_nat_cnt; si->sits = MAIN_SEGS(sbi); si->dirty_sits = SIT_I(sbi)->dirty_sentries; - si->free_nids = NM_I(sbi)->nid_cnt[FREE_NID_LIST]; + si->free_nids = NM_I(sbi)->nid_cnt[FREE_NID]; si->avail_nids = NM_I(sbi)->available_nids; - si->alloc_nids = NM_I(sbi)->nid_cnt[ALLOC_NID_LIST]; + si->alloc_nids = NM_I(sbi)->nid_cnt[PREALLOC_NID]; si->bg_gc = sbi->bg_gc; + si->io_skip_bggc = sbi->io_skip_bggc; + si->other_skip_bggc = sbi->other_skip_bggc; + si->skipped_atomic_files[BG_GC] = sbi->skipped_atomic_files[BG_GC]; + si->skipped_atomic_files[FG_GC] = sbi->skipped_atomic_files[FG_GC]; si->util_free = (int)(free_user_blocks(sbi) >> sbi->log_blocks_per_seg) * 100 / (int)(sbi->user_block_count >> sbi->log_blocks_per_seg) / 2; @@ -115,6 +127,9 @@ static void update_general_status(struct f2fs_sb_info *sbi) si->curzone[i] = GET_ZONE_FROM_SEC(sbi, si->cursec[i]); } + for (i = META_CP; i < META_MAX; i++) + si->meta_count[i] = atomic_read(&sbi->meta_count[i]); + for (i = 0; i < 2; i++) { si->segment_count[i] = sbi->segment_count[i]; si->block_count[i] = sbi->block_count[i]; @@ -162,7 +177,6 @@ static void update_sit_info(struct f2fs_sb_info *sbi) static void update_mem_info(struct f2fs_sb_info *sbi) { struct f2fs_stat_info *si = F2FS_STAT(sbi); - unsigned npages; int i; if (si->base_mem) @@ -175,7 +189,6 @@ static void update_mem_info(struct f2fs_sb_info *sbi) si->base_mem += sizeof(struct f2fs_sb_info) + sbi->sb->s_blocksize; si->base_mem += 2 * sizeof(struct f2fs_inode_info); si->base_mem += sizeof(*sbi->ckpt); - si->base_mem += sizeof(struct percpu_counter) * NR_COUNT_TYPE; /* build sm */ si->base_mem += sizeof(struct f2fs_sm_info); @@ -185,10 +198,9 @@ static void update_mem_info(struct f2fs_sb_info *sbi) si->base_mem += MAIN_SEGS(sbi) * sizeof(struct seg_entry); si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi)); si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi); - if (f2fs_discard_en(sbi)) - si->base_mem += SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi); + si->base_mem += SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi); si->base_mem += SIT_VBLOCK_MAP_SIZE; - if (sbi->segs_per_sec > 1) + if (__is_large_section(sbi)) si->base_mem += MAIN_SECS(sbi) * sizeof(struct sec_entry); si->base_mem += __bitmap_size(sbi, SIT_BITMAP); @@ -210,7 +222,8 @@ static void update_mem_info(struct f2fs_sb_info *sbi) si->base_mem += sizeof(struct f2fs_nm_info); si->base_mem += __bitmap_size(sbi, NAT_BITMAP); si->base_mem += (NM_I(sbi)->nat_bits_blocks << F2FS_BLKSIZE_BITS); - si->base_mem += NM_I(sbi)->nat_blocks * NAT_ENTRY_BITMAP_SIZE; + si->base_mem += NM_I(sbi)->nat_blocks * + f2fs_bitmap_size(NAT_ENTRY_PER_BLOCK); si->base_mem += NM_I(sbi)->nat_blocks / 8; si->base_mem += NM_I(sbi)->nat_blocks * sizeof(unsigned short); @@ -231,14 +244,14 @@ get_cache: } /* free nids */ - si->cache_mem += (NM_I(sbi)->nid_cnt[FREE_NID_LIST] + - NM_I(sbi)->nid_cnt[ALLOC_NID_LIST]) * + si->cache_mem += (NM_I(sbi)->nid_cnt[FREE_NID] + + NM_I(sbi)->nid_cnt[PREALLOC_NID]) * sizeof(struct free_nid); si->cache_mem += NM_I(sbi)->nat_cnt * sizeof(struct nat_entry); si->cache_mem += NM_I(sbi)->dirty_nat_cnt * sizeof(struct nat_entry_set); si->cache_mem += si->inmem_pages * sizeof(struct inmem_pages); - for (i = 0; i <= ORPHAN_INO; i++) + for (i = 0; i < MAX_INO_ENTRY; i++) si->cache_mem += sbi->im[i].ino_num * sizeof(struct ino_entry); si->cache_mem += atomic_read(&sbi->total_ext_tree) * sizeof(struct extent_tree); @@ -246,10 +259,14 @@ get_cache: sizeof(struct extent_node); si->page_mem = 0; - npages = NODE_MAPPING(sbi)->nrpages; - si->page_mem += (unsigned long long)npages << PAGE_SHIFT; - npages = META_MAPPING(sbi)->nrpages; - si->page_mem += (unsigned long long)npages << PAGE_SHIFT; + if (sbi->node_inode) { + unsigned npages = NODE_MAPPING(sbi)->nrpages; + si->page_mem += (unsigned long long)npages << PAGE_SHIFT; + } + if (sbi->meta_inode) { + unsigned npages = META_MAPPING(sbi)->nrpages; + si->page_mem += (unsigned long long)npages << PAGE_SHIFT; + } } static int stat_show(struct seq_file *s, void *v) @@ -262,9 +279,11 @@ static int stat_show(struct seq_file *s, void *v) list_for_each_entry(si, &f2fs_stat_list, stat_list) { update_general_status(si->sbi); - seq_printf(s, "\n=====[ partition info(%pg). #%d, %s]=====\n", + seq_printf(s, "\n=====[ partition info(%pg). #%d, %s, CP: %s]=====\n", si->sbi->sb->s_bdev, i++, - f2fs_readonly(si->sbi->sb) ? "RO": "RW"); + f2fs_readonly(si->sbi->sb) ? "RO": "RW", + is_set_ckpt_flags(si->sbi, CP_DISABLED_FLAG) ? + "Disabled": (f2fs_cp_error(si->sbi) ? "Error": "Good")); seq_printf(s, "[SB: 1] [CP: 2] [SIT: %d] [NAT: %d] ", si->sit_area_segs, si->nat_area_segs); seq_printf(s, "[SSA: %d] [MAIN: %d", @@ -326,6 +345,13 @@ static int stat_show(struct seq_file *s, void *v) si->prefree_count, si->free_segs, si->free_secs); seq_printf(s, "CP calls: %d (BG: %d)\n", si->cp_count, si->bg_cp_count); + seq_printf(s, " - cp blocks : %u\n", si->meta_count[META_CP]); + seq_printf(s, " - sit blocks : %u\n", + si->meta_count[META_SIT]); + seq_printf(s, " - nat blocks : %u\n", + si->meta_count[META_NAT]); + seq_printf(s, " - ssa blocks : %u\n", + si->meta_count[META_SSA]); seq_printf(s, "GC calls: %d (BG: %d)\n", si->call_count, si->bg_gc); seq_printf(s, " - data segments : %d (%d)\n", @@ -338,6 +364,12 @@ static int stat_show(struct seq_file *s, void *v) si->bg_data_blks); seq_printf(s, " - node blocks : %d (%d)\n", si->node_blks, si->bg_node_blks); + seq_printf(s, "Skipped : atomic write %llu (%llu)\n", + si->skipped_atomic_files[BG_GC] + + si->skipped_atomic_files[FG_GC], + si->skipped_atomic_files[BG_GC]); + seq_printf(s, "BG skip : IO: %u, Other: %u\n", + si->io_skip_bggc, si->other_skip_bggc); seq_puts(s, "\nExtent Cache:\n"); seq_printf(s, " - Hit Count: L1-1:%llu L1-2:%llu L2:%llu\n", si->hit_largest, si->hit_cached, @@ -349,10 +381,15 @@ static int stat_show(struct seq_file *s, void *v) seq_printf(s, " - Inner Struct Count: tree: %d(%d), node: %d\n", si->ext_tree, si->zombie_tree, si->ext_node); seq_puts(s, "\nBalancing F2FS Async:\n"); - seq_printf(s, " - IO (CP: %4d, Data: %4d, Flush: (%4d %4d), " + seq_printf(s, " - DIO (R: %4d, W: %4d)\n", + si->nr_dio_read, si->nr_dio_write); + seq_printf(s, " - IO_R (Data: %4d, Node: %4d, Meta: %4d\n", + si->nr_rd_data, si->nr_rd_node, si->nr_rd_meta); + seq_printf(s, " - IO_W (CP: %4d, Data: %4d, Flush: (%4d %4d %4d), " "Discard: (%4d %4d)) cmd: %4d undiscard:%4u\n", si->nr_wb_cp_data, si->nr_wb_data, si->nr_flushing, si->nr_flushed, + si->flush_list_empty, si->nr_discarding, si->nr_discarded, si->nr_discard_cmd, si->undiscard_blks); seq_printf(s, " - inmem: %4d, atomic IO: %4d (Max. %4d), " @@ -365,6 +402,8 @@ static int stat_show(struct seq_file *s, void *v) si->ndirty_dent, si->ndirty_dirs, si->ndirty_all); seq_printf(s, " - datas: %4d in files:%4d\n", si->ndirty_data, si->ndirty_files); + seq_printf(s, " - quota datas: %4d in quota files:%4d\n", + si->ndirty_qdata, si->nquota_files); seq_printf(s, " - meta: %4d in %4d\n", si->ndirty_meta, si->meta_pages); seq_printf(s, " - imeta: %4d\n", @@ -431,8 +470,9 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi) { struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); struct f2fs_stat_info *si; + int i; - si = kzalloc(sizeof(struct f2fs_stat_info), GFP_KERNEL); + si = f2fs_kzalloc(sbi, sizeof(struct f2fs_stat_info), GFP_KERNEL); if (!si) return -ENOMEM; @@ -456,6 +496,8 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi) atomic_set(&sbi->inline_inode, 0); atomic_set(&sbi->inline_dir, 0); atomic_set(&sbi->inplace_count, 0); + for (i = META_CP; i < META_MAX; i++) + atomic_set(&sbi->meta_count[i], 0); atomic_set(&sbi->aw_cnt, 0); atomic_set(&sbi->vw_cnt, 0); @@ -477,33 +519,19 @@ void f2fs_destroy_stats(struct f2fs_sb_info *sbi) list_del(&si->stat_list); mutex_unlock(&f2fs_stat_mutex); - kfree(si); + kvfree(si); } -int __init f2fs_create_root_stats(void) +void __init f2fs_create_root_stats(void) { - struct dentry *file; - f2fs_debugfs_root = debugfs_create_dir("f2fs", NULL); - if (!f2fs_debugfs_root) - return -ENOMEM; - - file = debugfs_create_file("status", S_IRUGO, f2fs_debugfs_root, - NULL, &stat_fops); - if (!file) { - debugfs_remove(f2fs_debugfs_root); - f2fs_debugfs_root = NULL; - return -ENOMEM; - } - return 0; + debugfs_create_file("status", S_IRUGO, f2fs_debugfs_root, NULL, + &stat_fops); } void f2fs_destroy_root_stats(void) { - if (!f2fs_debugfs_root) - return; - debugfs_remove_recursive(f2fs_debugfs_root); f2fs_debugfs_root = NULL; } diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index ff519f7a8784..d3eafe9e2ed2 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -1,19 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/dir.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> +#include <linux/sched/signal.h> #include "f2fs.h" #include "node.h" #include "acl.h" #include "xattr.h" +#include <trace/events/f2fs.h> static unsigned long dir_blocks(struct inode *inode) { @@ -58,12 +57,12 @@ static unsigned char f2fs_type_by_mode[S_IFMT >> S_SHIFT] = { [S_IFLNK >> S_SHIFT] = F2FS_FT_SYMLINK, }; -void set_de_type(struct f2fs_dir_entry *de, umode_t mode) +static void set_de_type(struct f2fs_dir_entry *de, umode_t mode) { de->file_type = f2fs_type_by_mode[(mode & S_IFMT) >> S_SHIFT]; } -unsigned char get_de_type(struct f2fs_dir_entry *de) +unsigned char f2fs_get_de_type(struct f2fs_dir_entry *de) { if (de->file_type < F2FS_FT_MAX) return f2fs_filetype_table[de->file_type]; @@ -92,19 +91,17 @@ static struct f2fs_dir_entry *find_in_block(struct page *dentry_page, struct f2fs_dir_entry *de; struct f2fs_dentry_ptr d; - dentry_blk = (struct f2fs_dentry_block *)kmap(dentry_page); + dentry_blk = (struct f2fs_dentry_block *)page_address(dentry_page); make_dentry_ptr_block(NULL, &d, dentry_blk); - de = find_target_dentry(fname, namehash, max_slots, &d); + de = f2fs_find_target_dentry(fname, namehash, max_slots, &d); if (de) *res_page = dentry_page; - else - kunmap(dentry_page); return de; } -struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname, +struct f2fs_dir_entry *f2fs_find_target_dentry(struct fscrypt_name *fname, f2fs_hash_t namehash, int *max_slots, struct f2fs_dentry_ptr *d) { @@ -171,7 +168,7 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir, for (; bidx < end_block; bidx++) { /* no need to allocate new dentry pages to all the indices */ - dentry_page = find_data_page(dir, bidx); + dentry_page = f2fs_find_data_page(dir, bidx); if (IS_ERR(dentry_page)) { if (PTR_ERR(dentry_page) == -ENOENT) { room = true; @@ -210,7 +207,7 @@ struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir, if (f2fs_has_inline_dentry(dir)) { *res_page = NULL; - de = find_in_inline_dir(dir, fname, res_page); + de = f2fs_find_in_inline_dir(dir, fname, res_page); goto out; } @@ -285,7 +282,6 @@ ino_t f2fs_inode_by_name(struct inode *dir, const struct qstr *qstr, de = f2fs_find_entry(dir, qstr, page); if (de) { res = le32_to_cpu(de->ino); - f2fs_dentry_kunmap(dir, *page); f2fs_put_page(*page, 0); } @@ -297,10 +293,9 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de, { enum page_type type = f2fs_has_inline_dentry(dir) ? NODE : DATA; lock_page(page); - f2fs_wait_on_page_writeback(page, type, true); + f2fs_wait_on_page_writeback(page, type, true, true); de->ino = cpu_to_le32(inode->i_ino); set_de_type(de, inode->i_mode); - f2fs_dentry_kunmap(dir, page); set_page_dirty(page); dir->i_mtime = dir->i_ctime = current_time(dir); @@ -312,7 +307,7 @@ static void init_dent_inode(const struct qstr *name, struct page *ipage) { struct f2fs_inode *ri; - f2fs_wait_on_page_writeback(ipage, NODE, true); + f2fs_wait_on_page_writeback(ipage, NODE, true, true); /* copy name info. to this inode page */ ri = F2FS_INODE(ipage); @@ -321,7 +316,7 @@ static void init_dent_inode(const struct qstr *name, struct page *ipage) set_page_dirty(ipage); } -void do_make_empty_dir(struct inode *inode, struct inode *parent, +void f2fs_do_make_empty_dir(struct inode *inode, struct inode *parent, struct f2fs_dentry_ptr *d) { struct qstr dot = QSTR_INIT(".", 1); @@ -342,33 +337,32 @@ static int make_empty_dir(struct inode *inode, struct f2fs_dentry_ptr d; if (f2fs_has_inline_dentry(inode)) - return make_empty_inline_dir(inode, parent, page); + return f2fs_make_empty_inline_dir(inode, parent, page); - dentry_page = get_new_data_page(inode, page, 0, true); + dentry_page = f2fs_get_new_data_page(inode, page, 0, true); if (IS_ERR(dentry_page)) return PTR_ERR(dentry_page); - dentry_blk = kmap_atomic(dentry_page); + dentry_blk = page_address(dentry_page); make_dentry_ptr_block(NULL, &d, dentry_blk); - do_make_empty_dir(inode, parent, &d); - - kunmap_atomic(dentry_blk); + f2fs_do_make_empty_dir(inode, parent, &d); set_page_dirty(dentry_page); f2fs_put_page(dentry_page, 1); return 0; } -struct page *init_inode_metadata(struct inode *inode, struct inode *dir, +struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir, const struct qstr *new_name, const struct qstr *orig_name, struct page *dpage) { struct page *page; + int dummy_encrypt = DUMMY_ENCRYPTION_ENABLED(F2FS_I_SB(dir)); int err; if (is_inode_flag_set(inode, FI_NEW_INODE)) { - page = new_inode_page(inode); + page = f2fs_new_inode_page(inode); if (IS_ERR(page)) return page; @@ -391,17 +385,16 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir, if (err) goto put_error; - if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode)) { + if ((f2fs_encrypted_inode(dir) || dummy_encrypt) && + f2fs_may_encrypt(inode)) { err = fscrypt_inherit_context(dir, inode, page, false); if (err) goto put_error; } } else { - page = get_node_page(F2FS_I_SB(dir), inode->i_ino); + page = f2fs_get_node_page(F2FS_I_SB(dir), inode->i_ino); if (IS_ERR(page)) return page; - - set_cold_node(inode, page); } if (new_name) { @@ -422,19 +415,19 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir, * we should remove this inode from orphan list. */ if (inode->i_nlink == 0) - remove_orphan_inode(F2FS_I_SB(dir), inode->i_ino); + f2fs_remove_orphan_inode(F2FS_I_SB(dir), inode->i_ino); f2fs_i_links_write(inode, true); } return page; put_error: clear_nlink(inode); - update_inode(inode, page); + f2fs_update_inode(inode, page); f2fs_put_page(page, 1); return ERR_PTR(err); } -void update_parent_metadata(struct inode *dir, struct inode *inode, +void f2fs_update_parent_metadata(struct inode *dir, struct inode *inode, unsigned int current_depth) { if (inode && is_inode_flag_set(inode, FI_NEW_INODE)) { @@ -452,7 +445,7 @@ void update_parent_metadata(struct inode *dir, struct inode *inode, clear_inode_flag(inode, FI_INC_LINK); } -int room_for_filename(const void *bitmap, int slots, int max_slots) +int f2fs_room_for_filename(const void *bitmap, int slots, int max_slots) { int bit_start = 0; int zero_start, zero_end; @@ -521,12 +514,11 @@ int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name, } start: -#ifdef CONFIG_F2FS_FAULT_INJECTION if (time_to_inject(F2FS_I_SB(dir), FAULT_DIR_DEPTH)) { f2fs_show_injection_info(FAULT_DIR_DEPTH); return -ENOSPC; } -#endif + if (unlikely(current_depth == MAX_DIR_HASH_DEPTH)) return -ENOSPC; @@ -541,17 +533,16 @@ start: (le32_to_cpu(dentry_hash) % nbucket)); for (block = bidx; block <= (bidx + nblock - 1); block++) { - dentry_page = get_new_data_page(dir, NULL, block, true); + dentry_page = f2fs_get_new_data_page(dir, NULL, block, true); if (IS_ERR(dentry_page)) return PTR_ERR(dentry_page); - dentry_blk = kmap(dentry_page); - bit_pos = room_for_filename(&dentry_blk->dentry_bitmap, + dentry_blk = page_address(dentry_page); + bit_pos = f2fs_room_for_filename(&dentry_blk->dentry_bitmap, slots, NR_DENTRY_IN_BLOCK); if (bit_pos < NR_DENTRY_IN_BLOCK) goto add_dentry; - kunmap(dentry_page); f2fs_put_page(dentry_page, 1); } @@ -559,11 +550,11 @@ start: ++level; goto start; add_dentry: - f2fs_wait_on_page_writeback(dentry_page, DATA, true); + f2fs_wait_on_page_writeback(dentry_page, DATA, true, true); if (inode) { down_write(&F2FS_I(inode)->i_sem); - page = init_inode_metadata(inode, dir, new_name, + page = f2fs_init_inode_metadata(inode, dir, new_name, orig_name, NULL); if (IS_ERR(page)) { err = PTR_ERR(page); @@ -581,18 +572,17 @@ add_dentry: f2fs_put_page(page, 1); } - update_parent_metadata(dir, inode, current_depth); + f2fs_update_parent_metadata(dir, inode, current_depth); fail: if (inode) up_write(&F2FS_I(inode)->i_sem); - kunmap(dentry_page); f2fs_put_page(dentry_page, 1); return err; } -int __f2fs_do_add_link(struct inode *dir, struct fscrypt_name *fname, +int f2fs_add_dentry(struct inode *dir, struct fscrypt_name *fname, struct inode *inode, nid_t ino, umode_t mode) { struct qstr new_name; @@ -616,7 +606,7 @@ int __f2fs_do_add_link(struct inode *dir, struct fscrypt_name *fname, * Caller should grab and release a rwsem by calling f2fs_lock_op() and * f2fs_unlock_op(). */ -int __f2fs_add_link(struct inode *dir, const struct qstr *name, +int f2fs_do_add_link(struct inode *dir, const struct qstr *name, struct inode *inode, nid_t ino, umode_t mode) { struct fscrypt_name fname; @@ -640,13 +630,12 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name, F2FS_I(dir)->task = NULL; } if (de) { - f2fs_dentry_kunmap(dir, page); f2fs_put_page(page, 0); err = -EEXIST; } else if (IS_ERR(page)) { err = PTR_ERR(page); } else { - err = __f2fs_do_add_link(dir, &fname, inode, ino, mode); + err = f2fs_add_dentry(dir, &fname, inode, ino, mode); } fscrypt_free_filename(&fname); return err; @@ -658,7 +647,7 @@ int f2fs_do_tmpfile(struct inode *inode, struct inode *dir) int err = 0; down_write(&F2FS_I(inode)->i_sem); - page = init_inode_metadata(inode, dir, NULL, NULL, NULL); + page = f2fs_init_inode_metadata(inode, dir, NULL, NULL, NULL); if (IS_ERR(page)) { err = PTR_ERR(page); goto fail; @@ -666,9 +655,9 @@ int f2fs_do_tmpfile(struct inode *inode, struct inode *dir) f2fs_put_page(page, 1); clear_inode_flag(inode, FI_NEW_INODE); + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); fail: up_write(&F2FS_I(inode)->i_sem); - f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return err; } @@ -690,9 +679,9 @@ void f2fs_drop_nlink(struct inode *dir, struct inode *inode) up_write(&F2FS_I(inode)->i_sem); if (inode->i_nlink == 0) - add_orphan_inode(inode); + f2fs_add_orphan_inode(inode); else - release_orphan_inode(sbi); + f2fs_release_orphan_inode(sbi); } /* @@ -705,17 +694,18 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, struct f2fs_dentry_block *dentry_blk; unsigned int bit_pos; int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len)); - struct address_space *mapping = page_mapping(page); - unsigned long flags; int i; f2fs_update_time(F2FS_I_SB(dir), REQ_TIME); + if (F2FS_OPTION(F2FS_I_SB(dir)).fsync_mode == FSYNC_MODE_STRICT) + f2fs_add_ino_entry(F2FS_I_SB(dir), dir->i_ino, TRANS_DIR_INO); + if (f2fs_has_inline_dentry(dir)) return f2fs_delete_inline_entry(dentry, page, dir, inode); lock_page(page); - f2fs_wait_on_page_writeback(page, DATA, true); + f2fs_wait_on_page_writeback(page, DATA, true, true); dentry_blk = page_address(page); bit_pos = dentry - dentry_blk->dentry; @@ -726,7 +716,6 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap, NR_DENTRY_IN_BLOCK, 0); - kunmap(page); /* kunmap - pair of f2fs_find_entry */ set_page_dirty(page); dir->i_ctime = dir->i_mtime = current_time(dir); @@ -736,18 +725,14 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, f2fs_drop_nlink(dir, inode); if (bit_pos == NR_DENTRY_IN_BLOCK && - !truncate_hole(dir, page->index, page->index + 1)) { - spin_lock_irqsave(&mapping->tree_lock, flags); - radix_tree_tag_clear(&mapping->page_tree, page_index(page), - PAGECACHE_TAG_DIRTY); - spin_unlock_irqrestore(&mapping->tree_lock, flags); - + !f2fs_truncate_hole(dir, page->index, page->index + 1)) { + f2fs_clear_radix_tree_dirty_tag(page); clear_page_dirty_for_io(page); - ClearPagePrivate(page); + f2fs_clear_page_private(page); ClearPageUptodate(page); clear_cold_data(page); inode_dec_dirty_pages(dir); - remove_dirty_inode(dir); + f2fs_remove_dirty_inode(dir); } f2fs_put_page(page, 1); } @@ -764,7 +749,7 @@ bool f2fs_empty_dir(struct inode *dir) return f2fs_empty_inline_dir(dir); for (bidx = 0; bidx < nblock; bidx++) { - dentry_page = get_lock_data_page(dir, bidx, false); + dentry_page = f2fs_get_lock_data_page(dir, bidx, false); if (IS_ERR(dentry_page)) { if (PTR_ERR(dentry_page) == -ENOENT) continue; @@ -772,7 +757,7 @@ bool f2fs_empty_dir(struct inode *dir) return false; } - dentry_blk = kmap_atomic(dentry_page); + dentry_blk = page_address(dentry_page); if (bidx == 0) bit_pos = 2; else @@ -780,7 +765,6 @@ bool f2fs_empty_dir(struct inode *dir) bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap, NR_DENTRY_IN_BLOCK, bit_pos); - kunmap_atomic(dentry_blk); f2fs_put_page(dentry_page, 1); @@ -797,9 +781,16 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, unsigned int bit_pos; struct f2fs_dir_entry *de = NULL; struct fscrypt_str de_name = FSTR_INIT(NULL, 0); + struct f2fs_sb_info *sbi = F2FS_I_SB(d->inode); + struct blk_plug plug; + bool readdir_ra = sbi->readdir_ra == 1; + int err = 0; bit_pos = ((unsigned long)ctx->pos % d->max); + if (readdir_ra) + blk_start_plug(&plug); + while (bit_pos < d->max) { bit_pos = find_next_bit_le(d->bitmap, d->max, bit_pos); if (bit_pos >= d->max) @@ -809,10 +800,14 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, if (de->name_len == 0) { bit_pos++; ctx->pos = start_pos + bit_pos; + printk_ratelimited( + "%s, invalid namelen(0), ino:%u, run fsck to fix.", + KERN_WARNING, le32_to_cpu(de->ino)); + set_sbi_flag(sbi, SBI_NEED_FSCK); continue; } - d_type = get_de_type(de); + d_type = f2fs_get_de_type(de); de_name.name = d->filename[bit_pos]; de_name.len = le16_to_cpu(de->name_len); @@ -821,34 +816,42 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len)); if (unlikely(bit_pos > d->max || le16_to_cpu(de->name_len) > F2FS_NAME_LEN)) { - f2fs_msg(F2FS_I_SB(d->inode)->sb, KERN_WARNING, + f2fs_msg(sbi->sb, KERN_WARNING, "%s: corrupted namelen=%d, run fsck to fix.", __func__, le16_to_cpu(de->name_len)); - set_sbi_flag(F2FS_I_SB(d->inode)->sb->s_fs_info, SBI_NEED_FSCK); - return -EINVAL; + set_sbi_flag(sbi, SBI_NEED_FSCK); + err = -EINVAL; + goto out; } if (f2fs_encrypted_inode(d->inode)) { int save_len = fstr->len; - int err; err = fscrypt_fname_disk_to_usr(d->inode, (u32)de->hash_code, 0, &de_name, fstr); if (err) - return err; + goto out; de_name = *fstr; fstr->len = save_len; } if (!dir_emit(ctx, de_name.name, de_name.len, - le32_to_cpu(de->ino), d_type)) - return 1; + le32_to_cpu(de->ino), d_type)) { + err = 1; + goto out; + } + + if (readdir_ra) + f2fs_ra_node_page(sbi, le32_to_cpu(de->ino)); ctx->pos = start_pos + bit_pos; } - return 0; +out: + if (readdir_ra) + blk_finish_plug(&plug); + return err; } static int f2fs_readdir(struct file *file, struct dir_context *ctx) @@ -858,6 +861,7 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx) struct f2fs_dentry_block *dentry_blk = NULL; struct page *dentry_page = NULL; struct file_ra_state *ra = &file->f_ra; + loff_t start_pos = ctx->pos; unsigned int n = ((unsigned long)ctx->pos / NR_DENTRY_IN_BLOCK); struct f2fs_dentry_ptr d; struct fscrypt_str fstr = FSTR_INIT(NULL, 0); @@ -866,53 +870,60 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx) if (f2fs_encrypted_inode(inode)) { err = fscrypt_get_encryption_info(inode); if (err && err != -ENOKEY) - return err; + goto out; err = fscrypt_fname_alloc_buffer(inode, F2FS_NAME_LEN, &fstr); if (err < 0) - return err; + goto out; } if (f2fs_has_inline_dentry(inode)) { err = f2fs_read_inline_dir(file, ctx, &fstr); - goto out; + goto out_free; } - /* readahead for multi pages of dir */ - if (npages - n > 1 && !ra_has_index(ra, n)) - page_cache_sync_readahead(inode->i_mapping, ra, file, n, + for (; n < npages; n++, ctx->pos = n * NR_DENTRY_IN_BLOCK) { + + /* allow readdir() to be interrupted */ + if (fatal_signal_pending(current)) { + err = -ERESTARTSYS; + goto out_free; + } + cond_resched(); + + /* readahead for multi pages of dir */ + if (npages - n > 1 && !ra_has_index(ra, n)) + page_cache_sync_readahead(inode->i_mapping, ra, file, n, min(npages - n, (pgoff_t)MAX_DIR_RA_PAGES)); - for (; n < npages; n++) { - dentry_page = get_lock_data_page(inode, n, false); + dentry_page = f2fs_find_data_page(inode, n); if (IS_ERR(dentry_page)) { err = PTR_ERR(dentry_page); if (err == -ENOENT) { err = 0; continue; } else { - goto out; + goto out_free; } } - dentry_blk = kmap(dentry_page); + dentry_blk = page_address(dentry_page); make_dentry_ptr_block(inode, &d, dentry_blk); err = f2fs_fill_dentries(ctx, &d, n * NR_DENTRY_IN_BLOCK, &fstr); if (err) { - kunmap(dentry_page); - f2fs_put_page(dentry_page, 1); + f2fs_put_page(dentry_page, 0); break; } - ctx->pos = (n + 1) * NR_DENTRY_IN_BLOCK; - kunmap(dentry_page); - f2fs_put_page(dentry_page, 1); + f2fs_put_page(dentry_page, 0); } -out: +out_free: fscrypt_fname_free_buffer(&fstr); +out: + trace_f2fs_readdir(inode, start_pos, ctx->pos, err); return err < 0 ? err : 0; } diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index aff6c2ed1c02..caf77fe8ac07 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * f2fs extent cache support * @@ -5,10 +6,6 @@ * Copyright (c) 2015 Samsung Electronics * Authors: Jaegeuk Kim <jaegeuk@kernel.org> * Chao Yu <chao2.yu@samsung.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> @@ -30,10 +27,10 @@ static struct rb_entry *__lookup_rb_tree_fast(struct rb_entry *cached_re, return NULL; } -static struct rb_entry *__lookup_rb_tree_slow(struct rb_root *root, +static struct rb_entry *__lookup_rb_tree_slow(struct rb_root_cached *root, unsigned int ofs) { - struct rb_node *node = root->rb_node; + struct rb_node *node = root->rb_root.rb_node; struct rb_entry *re; while (node) { @@ -49,7 +46,7 @@ static struct rb_entry *__lookup_rb_tree_slow(struct rb_root *root, return NULL; } -struct rb_entry *__lookup_rb_tree(struct rb_root *root, +struct rb_entry *f2fs_lookup_rb_tree(struct rb_root_cached *root, struct rb_entry *cached_re, unsigned int ofs) { struct rb_entry *re; @@ -61,23 +58,26 @@ struct rb_entry *__lookup_rb_tree(struct rb_root *root, return re; } -struct rb_node **__lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi, - struct rb_root *root, struct rb_node **parent, - unsigned int ofs) +struct rb_node **f2fs_lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi, + struct rb_root_cached *root, + struct rb_node **parent, + unsigned int ofs, bool *leftmost) { - struct rb_node **p = &root->rb_node; + struct rb_node **p = &root->rb_root.rb_node; struct rb_entry *re; while (*p) { *parent = *p; re = rb_entry(*parent, struct rb_entry, rb_node); - if (ofs < re->ofs) + if (ofs < re->ofs) { p = &(*p)->rb_left; - else if (ofs >= re->ofs + re->len) + } else if (ofs >= re->ofs + re->len) { p = &(*p)->rb_right; - else + *leftmost = false; + } else { f2fs_bug_on(sbi, 1); + } } return p; @@ -92,16 +92,16 @@ struct rb_node **__lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi, * in order to simpfy the insertion after. * tree must stay unchanged between lookup and insertion. */ -struct rb_entry *__lookup_rb_tree_ret(struct rb_root *root, +struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root_cached *root, struct rb_entry *cached_re, unsigned int ofs, struct rb_entry **prev_entry, struct rb_entry **next_entry, struct rb_node ***insert_p, struct rb_node **insert_parent, - bool force) + bool force, bool *leftmost) { - struct rb_node **pnode = &root->rb_node; + struct rb_node **pnode = &root->rb_root.rb_node; struct rb_node *parent = NULL, *tmp_node; struct rb_entry *re = cached_re; @@ -110,7 +110,7 @@ struct rb_entry *__lookup_rb_tree_ret(struct rb_root *root, *prev_entry = NULL; *next_entry = NULL; - if (RB_EMPTY_ROOT(root)) + if (RB_EMPTY_ROOT(&root->rb_root)) return NULL; if (re) { @@ -118,16 +118,22 @@ struct rb_entry *__lookup_rb_tree_ret(struct rb_root *root, goto lookup_neighbors; } + if (leftmost) + *leftmost = true; + while (*pnode) { parent = *pnode; re = rb_entry(*pnode, struct rb_entry, rb_node); - if (ofs < re->ofs) + if (ofs < re->ofs) { pnode = &(*pnode)->rb_left; - else if (ofs >= re->ofs + re->len) + } else if (ofs >= re->ofs + re->len) { pnode = &(*pnode)->rb_right; - else + if (leftmost) + *leftmost = false; + } else { goto lookup_neighbors; + } } *insert_p = pnode; @@ -159,11 +165,11 @@ lookup_neighbors: return re; } -bool __check_rb_tree_consistence(struct f2fs_sb_info *sbi, - struct rb_root *root) +bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi, + struct rb_root_cached *root) { #ifdef CONFIG_F2FS_CHECK_FS - struct rb_node *cur = rb_first(root), *next; + struct rb_node *cur = rb_first_cached(root), *next; struct rb_entry *cur_re, *next_re; if (!cur) @@ -196,7 +202,8 @@ static struct kmem_cache *extent_node_slab; static struct extent_node *__attach_extent_node(struct f2fs_sb_info *sbi, struct extent_tree *et, struct extent_info *ei, - struct rb_node *parent, struct rb_node **p) + struct rb_node *parent, struct rb_node **p, + bool leftmost) { struct extent_node *en; @@ -209,7 +216,7 @@ static struct extent_node *__attach_extent_node(struct f2fs_sb_info *sbi, en->et = et; rb_link_node(&en->rb_node, parent, p); - rb_insert_color(&en->rb_node, &et->root); + rb_insert_color_cached(&en->rb_node, &et->root, leftmost); atomic_inc(&et->node_cnt); atomic_inc(&sbi->total_ext_node); return en; @@ -218,7 +225,7 @@ static struct extent_node *__attach_extent_node(struct f2fs_sb_info *sbi, static void __detach_extent_node(struct f2fs_sb_info *sbi, struct extent_tree *et, struct extent_node *en) { - rb_erase(&en->rb_node, &et->root); + rb_erase_cached(&en->rb_node, &et->root); atomic_dec(&et->node_cnt); atomic_dec(&sbi->total_ext_node); @@ -257,7 +264,7 @@ static struct extent_tree *__grab_extent_tree(struct inode *inode) f2fs_radix_tree_insert(&sbi->extent_tree_root, ino, et); memset(et, 0, sizeof(struct extent_tree)); et->ino = ino; - et->root = RB_ROOT; + et->root = RB_ROOT_CACHED; et->cached_en = NULL; rwlock_init(&et->lock); INIT_LIST_HEAD(&et->list); @@ -278,10 +285,10 @@ static struct extent_tree *__grab_extent_tree(struct inode *inode) static struct extent_node *__init_extent_tree(struct f2fs_sb_info *sbi, struct extent_tree *et, struct extent_info *ei) { - struct rb_node **p = &et->root.rb_node; + struct rb_node **p = &et->root.rb_root.rb_node; struct extent_node *en; - en = __attach_extent_node(sbi, et, ei, NULL, p); + en = __attach_extent_node(sbi, et, ei, NULL, p, true); if (!en) return NULL; @@ -297,7 +304,7 @@ static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi, struct extent_node *en; unsigned int count = atomic_read(&et->node_cnt); - node = rb_first(&et->root); + node = rb_first_cached(&et->root); while (node) { next = rb_next(node); en = rb_entry(node, struct extent_node, rb_node); @@ -308,14 +315,13 @@ static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi, return count - atomic_read(&et->node_cnt); } -static void __drop_largest_extent(struct inode *inode, +static void __drop_largest_extent(struct extent_tree *et, pgoff_t fofs, unsigned int len) { - struct extent_info *largest = &F2FS_I(inode)->extent_tree->largest; - - if (fofs < largest->fofs + largest->len && fofs + len > largest->fofs) { - largest->len = 0; - f2fs_mark_inode_dirty_sync(inode, true); + if (fofs < et->largest.fofs + et->largest.len && + fofs + len > et->largest.fofs) { + et->largest.len = 0; + et->largest_updated = true; } } @@ -390,7 +396,7 @@ static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs, goto out; } - en = (struct extent_node *)__lookup_rb_tree(&et->root, + en = (struct extent_node *)f2fs_lookup_rb_tree(&et->root, (struct rb_entry *)et->cached_en, pgofs); if (!en) goto out; @@ -416,12 +422,11 @@ out: return ret; } -static struct extent_node *__try_merge_extent_node(struct inode *inode, +static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi, struct extent_tree *et, struct extent_info *ei, struct extent_node *prev_ex, struct extent_node *next_ex) { - struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct extent_node *en = NULL; if (prev_ex && __is_back_mergeable(ei, &prev_ex->ei)) { @@ -443,7 +448,7 @@ static struct extent_node *__try_merge_extent_node(struct inode *inode, if (!en) return NULL; - __try_update_largest_extent(inode, et, en); + __try_update_largest_extent(et, en); spin_lock(&sbi->extent_lock); if (!list_empty(&en->list)) { @@ -454,13 +459,13 @@ static struct extent_node *__try_merge_extent_node(struct inode *inode, return en; } -static struct extent_node *__insert_extent_tree(struct inode *inode, +static struct extent_node *__insert_extent_tree(struct f2fs_sb_info *sbi, struct extent_tree *et, struct extent_info *ei, struct rb_node **insert_p, - struct rb_node *insert_parent) + struct rb_node *insert_parent, + bool leftmost) { - struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct rb_node **p = &et->root.rb_node; + struct rb_node **p; struct rb_node *parent = NULL; struct extent_node *en = NULL; @@ -470,13 +475,16 @@ static struct extent_node *__insert_extent_tree(struct inode *inode, goto do_insert; } - p = __lookup_rb_tree_for_insert(sbi, &et->root, &parent, ei->fofs); + leftmost = true; + + p = f2fs_lookup_rb_tree_for_insert(sbi, &et->root, &parent, + ei->fofs, &leftmost); do_insert: - en = __attach_extent_node(sbi, et, ei, parent, p); + en = __attach_extent_node(sbi, et, ei, parent, p, leftmost); if (!en) return NULL; - __try_update_largest_extent(inode, et, en); + __try_update_largest_extent(et, en); /* update in global extent list */ spin_lock(&sbi->extent_lock); @@ -497,6 +505,8 @@ static void f2fs_update_extent_tree_range(struct inode *inode, struct rb_node **insert_p = NULL, *insert_parent = NULL; unsigned int end = fofs + len; unsigned int pos = (unsigned int)fofs; + bool updated = false; + bool leftmost = false; if (!et) return; @@ -517,14 +527,15 @@ static void f2fs_update_extent_tree_range(struct inode *inode, * drop largest extent before lookup, in case it's already * been shrunk from extent tree */ - __drop_largest_extent(inode, fofs, len); + __drop_largest_extent(et, fofs, len); /* 1. lookup first extent node in range [fofs, fofs + len - 1] */ - en = (struct extent_node *)__lookup_rb_tree_ret(&et->root, + en = (struct extent_node *)f2fs_lookup_rb_tree_ret(&et->root, (struct rb_entry *)et->cached_en, fofs, (struct rb_entry **)&prev_en, (struct rb_entry **)&next_en, - &insert_p, &insert_parent, false); + &insert_p, &insert_parent, false, + &leftmost); if (!en) en = next_en; @@ -550,8 +561,8 @@ static void f2fs_update_extent_tree_range(struct inode *inode, set_extent_info(&ei, end, end - dei.fofs + dei.blk, org_end - end); - en1 = __insert_extent_tree(inode, et, &ei, - NULL, NULL); + en1 = __insert_extent_tree(sbi, et, &ei, + NULL, NULL, true); next_en = en1; } else { en->ei.fofs = end; @@ -570,7 +581,7 @@ static void f2fs_update_extent_tree_range(struct inode *inode, } if (parts) - __try_update_largest_extent(inode, et, en); + __try_update_largest_extent(et, en); else __release_extent_node(sbi, et, en); @@ -590,15 +601,16 @@ static void f2fs_update_extent_tree_range(struct inode *inode, if (blkaddr) { set_extent_info(&ei, fofs, blkaddr, len); - if (!__try_merge_extent_node(inode, et, &ei, prev_en, next_en)) - __insert_extent_tree(inode, et, &ei, - insert_p, insert_parent); + if (!__try_merge_extent_node(sbi, et, &ei, prev_en, next_en)) + __insert_extent_tree(sbi, et, &ei, + insert_p, insert_parent, leftmost); /* give up extent_cache, if split and small updates happen */ if (dei.len >= 1 && prev.len < F2FS_MIN_EXTENT_LEN && et->largest.len < F2FS_MIN_EXTENT_LEN) { - __drop_largest_extent(inode, 0, UINT_MAX); + et->largest.len = 0; + et->largest_updated = true; set_inode_flag(inode, FI_NO_EXTENT); } } @@ -606,7 +618,15 @@ static void f2fs_update_extent_tree_range(struct inode *inode, if (is_inode_flag_set(inode, FI_NO_EXTENT)) __free_extent_tree(sbi, et); + if (et->largest_updated) { + et->largest_updated = false; + updated = true; + } + write_unlock(&et->lock); + + if (updated) + f2fs_mark_inode_dirty_sync(inode, true); } unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink) @@ -705,6 +725,7 @@ void f2fs_drop_extent_tree(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct extent_tree *et = F2FS_I(inode)->extent_tree; + bool updated = false; if (!f2fs_may_extent_tree(inode)) return; @@ -713,8 +734,13 @@ void f2fs_drop_extent_tree(struct inode *inode) write_lock(&et->lock); __free_extent_tree(sbi, et); - __drop_largest_extent(inode, 0, UINT_MAX); + if (et->largest.len) { + et->largest.len = 0; + updated = true; + } write_unlock(&et->lock); + if (updated) + f2fs_mark_inode_dirty_sync(inode, true); } void f2fs_destroy_extent_tree(struct inode *inode) @@ -773,7 +799,7 @@ void f2fs_update_extent_cache(struct dnode_of_data *dn) else blkaddr = dn->data_blkaddr; - fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) + + fofs = f2fs_start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) + dn->ofs_in_node; f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, 1); } @@ -788,7 +814,7 @@ void f2fs_update_extent_cache_range(struct dnode_of_data *dn, f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, len); } -void init_extent_cache_info(struct f2fs_sb_info *sbi) +void f2fs_init_extent_cache_info(struct f2fs_sb_info *sbi) { INIT_RADIX_TREE(&sbi->extent_tree_root, GFP_NOIO); mutex_init(&sbi->extent_tree_lock); @@ -800,7 +826,7 @@ void init_extent_cache_info(struct f2fs_sb_info *sbi) atomic_set(&sbi->total_ext_node, 0); } -int __init create_extent_cache(void) +int __init f2fs_create_extent_cache(void) { extent_tree_slab = f2fs_kmem_cache_create("f2fs_extent_tree", sizeof(struct extent_tree)); @@ -815,7 +841,7 @@ int __init create_extent_cache(void) return 0; } -void destroy_extent_cache(void) +void f2fs_destroy_extent_cache(void) { kmem_cache_destroy(extent_node_slab); kmem_cache_destroy(extent_tree_slab); diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 268409cee1c3..0ae019b79e0c 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1,16 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/f2fs.h * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef _LINUX_F2FS_H #define _LINUX_F2FS_H +#include <linux/uio.h> #include <linux/types.h> #include <linux/page-flags.h> #include <linux/buffer_head.h> @@ -19,16 +17,16 @@ #include <linux/magic.h> #include <linux/kobject.h> #include <linux/sched.h> +#include <linux/cred.h> #include <linux/vmalloc.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/quotaops.h> -#ifdef CONFIG_F2FS_FS_ENCRYPTION -#include <linux/fscrypt_supp.h> -#else -#include <linux/fscrypt_notsupp.h> -#endif #include <crypto/hash.h> +#include <linux/overflow.h> + +#define __FS_HAS_ENCRYPTION IS_ENABLED(CONFIG_F2FS_FS_ENCRYPTION) +#include <linux/fscrypt.h> #ifdef CONFIG_F2FS_CHECK_FS #define f2fs_bug_on(sbi, condition) BUG_ON(condition) @@ -42,28 +40,35 @@ } while (0) #endif -#ifdef CONFIG_F2FS_FAULT_INJECTION enum { FAULT_KMALLOC, + FAULT_KVMALLOC, FAULT_PAGE_ALLOC, + FAULT_PAGE_GET, + FAULT_ALLOC_BIO, FAULT_ALLOC_NID, FAULT_ORPHAN, FAULT_BLOCK, FAULT_DIR_DEPTH, FAULT_EVICT_INODE, FAULT_TRUNCATE, - FAULT_IO, + FAULT_READ_IO, FAULT_CHECKPOINT, + FAULT_DISCARD, + FAULT_WRITE_IO, FAULT_MAX, }; +#ifdef CONFIG_F2FS_FAULT_INJECTION +#define F2FS_ALL_FAULT_TYPE ((1 << FAULT_MAX) - 1) + struct f2fs_fault_info { atomic_t inject_ops; unsigned int inject_rate; unsigned int inject_type; }; -extern char *fault_name[FAULT_MAX]; +extern const char *f2fs_fault_name[FAULT_MAX]; #define IS_FAULT_SET(fi, type) ((fi)->inject_type & (1 << (type))) #endif @@ -93,10 +98,14 @@ extern char *fault_name[FAULT_MAX]; #define F2FS_MOUNT_GRPQUOTA 0x00100000 #define F2FS_MOUNT_PRJQUOTA 0x00200000 #define F2FS_MOUNT_QUOTA 0x00400000 +#define F2FS_MOUNT_INLINE_XATTR_SIZE 0x00800000 +#define F2FS_MOUNT_RESERVE_ROOT 0x01000000 +#define F2FS_MOUNT_DISABLE_CHECKPOINT 0x02000000 -#define clear_opt(sbi, option) ((sbi)->mount_opt.opt &= ~F2FS_MOUNT_##option) -#define set_opt(sbi, option) ((sbi)->mount_opt.opt |= F2FS_MOUNT_##option) -#define test_opt(sbi, option) ((sbi)->mount_opt.opt & F2FS_MOUNT_##option) +#define F2FS_OPTION(sbi) ((sbi)->mount_opt) +#define clear_opt(sbi, option) (F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option) +#define set_opt(sbi, option) (F2FS_OPTION(sbi).opt |= F2FS_MOUNT_##option) +#define test_opt(sbi, option) (F2FS_OPTION(sbi).opt & F2FS_MOUNT_##option) #define ver_after(a, b) (typecheck(unsigned long long, a) && \ typecheck(unsigned long long, b) && \ @@ -109,7 +118,26 @@ typedef u32 block_t; /* typedef u32 nid_t; struct f2fs_mount_info { - unsigned int opt; + unsigned int opt; + int write_io_size_bits; /* Write IO size bits */ + block_t root_reserved_blocks; /* root reserved blocks */ + kuid_t s_resuid; /* reserved blocks for uid */ + kgid_t s_resgid; /* reserved blocks for gid */ + int active_logs; /* # of active logs */ + int inline_xattr_size; /* inline xattr size */ +#ifdef CONFIG_F2FS_FAULT_INJECTION + struct f2fs_fault_info fault_info; /* For fault injection */ +#endif +#ifdef CONFIG_QUOTA + /* Names of quota files with journalled quota */ + char *s_qf_names[MAXQUOTAS]; + int s_jquota_fmt; /* Format of quota to use */ +#endif + /* For which write hints are passed down to block layer */ + int whint_mode; + int alloc_mode; /* segment allocation policy */ + int fsync_mode; /* fsync policy */ + bool test_dummy_encryption; /* test dummy encryption */ }; #define F2FS_FEATURE_ENCRYPT 0x0001 @@ -118,13 +146,26 @@ struct f2fs_mount_info { #define F2FS_FEATURE_EXTRA_ATTR 0x0008 #define F2FS_FEATURE_PRJQUOTA 0x0010 #define F2FS_FEATURE_INODE_CHKSUM 0x0020 +#define F2FS_FEATURE_FLEXIBLE_INLINE_XATTR 0x0040 +#define F2FS_FEATURE_QUOTA_INO 0x0080 +#define F2FS_FEATURE_INODE_CRTIME 0x0100 +#define F2FS_FEATURE_LOST_FOUND 0x0200 +#define F2FS_FEATURE_VERITY 0x0400 /* reserved */ +#define F2FS_FEATURE_SB_CHKSUM 0x0800 + +#define __F2FS_HAS_FEATURE(raw_super, mask) \ + ((raw_super->feature & cpu_to_le32(mask)) != 0) +#define F2FS_HAS_FEATURE(sbi, mask) __F2FS_HAS_FEATURE(sbi->raw_super, mask) +#define F2FS_SET_FEATURE(sbi, mask) \ + (sbi->raw_super->feature |= cpu_to_le32(mask)) +#define F2FS_CLEAR_FEATURE(sbi, mask) \ + (sbi->raw_super->feature &= ~cpu_to_le32(mask)) -#define F2FS_HAS_FEATURE(sb, mask) \ - ((F2FS_SB(sb)->raw_super->feature & cpu_to_le32(mask)) != 0) -#define F2FS_SET_FEATURE(sb, mask) \ - (F2FS_SB(sb)->raw_super->feature |= cpu_to_le32(mask)) -#define F2FS_CLEAR_FEATURE(sb, mask) \ - (F2FS_SB(sb)->raw_super->feature &= ~cpu_to_le32(mask)) +/* + * Default values for user and/or group using reserved blocks + */ +#define F2FS_DEF_RESUID 0 +#define F2FS_DEF_RESGID 0 /* * For checkpoint manager @@ -140,25 +181,25 @@ enum { #define CP_RECOVERY 0x00000008 #define CP_DISCARD 0x00000010 #define CP_TRIMMED 0x00000020 +#define CP_PAUSE 0x00000040 -#define DEF_BATCHED_TRIM_SECTIONS 2048 -#define BATCHED_TRIM_SEGMENTS(sbi) \ - (GET_SEG_FROM_SEC(sbi, SM_I(sbi)->trim_sections)) -#define BATCHED_TRIM_BLOCKS(sbi) \ - (BATCHED_TRIM_SEGMENTS(sbi) << (sbi)->log_blocks_per_seg) #define MAX_DISCARD_BLOCKS(sbi) BLKS_PER_SEC(sbi) -#define DISCARD_ISSUE_RATE 8 +#define DEF_MAX_DISCARD_REQUEST 8 /* issue 8 discards per round */ #define DEF_MIN_DISCARD_ISSUE_TIME 50 /* 50 ms, if exists */ +#define DEF_MID_DISCARD_ISSUE_TIME 500 /* 500 ms, if device busy */ #define DEF_MAX_DISCARD_ISSUE_TIME 60000 /* 60 s, if no candidates */ +#define DEF_DISCARD_URGENT_UTIL 80 /* do more discard over 80% */ #define DEF_CP_INTERVAL 60 /* 60 secs */ #define DEF_IDLE_INTERVAL 5 /* 5 secs */ +#define DEF_DISABLE_INTERVAL 5 /* 5 secs */ +#define DEF_DISABLE_QUICK_INTERVAL 1 /* 1 secs */ +#define DEF_UMOUNT_DISCARD_TIMEOUT 5 /* 5 secs */ struct cp_control { int reason; __u64 trim_start; __u64 trim_end; __u64 trim_minlen; - __u64 trimmed; }; /* @@ -169,6 +210,7 @@ enum { META_NAT, META_SIT, META_SSA, + META_MAX, META_POR, DATA_GENERIC, META_GENERIC, @@ -179,12 +221,15 @@ enum { ORPHAN_INO, /* for orphan ino list */ APPEND_INO, /* for append ino list */ UPDATE_INO, /* for update ino list */ + TRANS_DIR_INO, /* for trasactions dir ino list */ + FLUSH_INO, /* for multiple device flushing */ MAX_INO_ENTRY, /* max. list */ }; struct ino_entry { - struct list_head list; /* list head */ - nid_t ino; /* inode number */ + struct list_head list; /* list head */ + nid_t ino; /* inode number */ + unsigned int dirty_device; /* dirty device bitmap */ }; /* for the list of inodes to be GCed */ @@ -193,6 +238,12 @@ struct inode_entry { struct inode *inode; /* vfs inode pointer */ }; +struct fsync_node_entry { + struct list_head list; /* list head */ + struct page *page; /* warm node page pointer */ + unsigned int seq_id; /* sequence id */ +}; + /* for the bitmap indicate blocks to be discarded */ struct discard_entry { struct list_head list; /* list head */ @@ -206,16 +257,13 @@ struct discard_entry { /* max discard pend list number */ #define MAX_PLIST_NUM 512 #define plist_idx(blk_num) ((blk_num) >= MAX_PLIST_NUM ? \ - (MAX_PLIST_NUM - 1) : (blk_num - 1)) - -#define P_ACTIVE 0x01 -#define P_TRIM 0x02 -#define plist_issue(tag) (((tag) & P_ACTIVE) || ((tag) & P_TRIM)) + (MAX_PLIST_NUM - 1) : ((blk_num) - 1)) enum { - D_PREP, - D_SUBMIT, - D_DONE, + D_PREP, /* initial */ + D_PARTIAL, /* partially submitted */ + D_SUBMIT, /* all submitted */ + D_DONE, /* finished */ }; struct discard_info { @@ -240,15 +288,40 @@ struct discard_cmd { struct block_device *bdev; /* bdev */ unsigned short ref; /* reference count */ unsigned char state; /* state */ + unsigned char queued; /* queued discard */ int error; /* bio error */ + spinlock_t lock; /* for state/bio_ref updating */ + unsigned short bio_ref; /* bio reference count */ +}; + +enum { + DPOLICY_BG, + DPOLICY_FORCE, + DPOLICY_FSTRIM, + DPOLICY_UMOUNT, + MAX_DPOLICY, +}; + +struct discard_policy { + int type; /* type of discard */ + unsigned int min_interval; /* used for candidates exist */ + unsigned int mid_interval; /* used for device busy */ + unsigned int max_interval; /* used for candidates not exist */ + unsigned int max_requests; /* # of discards issued per round */ + unsigned int io_aware_gran; /* minimum granularity discard not be aware of I/O */ + bool io_aware; /* issue discard in idle time */ + bool sync; /* submit discard with REQ_SYNC flag */ + bool ordered; /* issue discard by lba order */ + unsigned int granularity; /* discard granularity */ + int timeout; /* discard timeout for put_super */ }; struct discard_cmd_control { struct task_struct *f2fs_issue_discard; /* discard thread */ struct list_head entry_list; /* 4KB discard entry list */ struct list_head pend_list[MAX_PLIST_NUM];/* store pending entries */ - unsigned char pend_list_tag[MAX_PLIST_NUM];/* tag for pending entries */ struct list_head wait_list; /* store on-flushing entries */ + struct list_head fstrim_list; /* in-flight discard from fstrim */ wait_queue_head_t discard_wait_queue; /* waiting queue for wake-up */ unsigned int discard_wake; /* to wake up discard thread */ struct mutex cmd_lock; @@ -256,10 +329,12 @@ struct discard_cmd_control { unsigned int max_discards; /* max. discards to be issued */ unsigned int discard_granularity; /* discard granularity */ unsigned int undiscard_blks; /* # of undiscard blocks */ + unsigned int next_pos; /* next discard position */ atomic_t issued_discard; /* # of issued discard */ - atomic_t issing_discard; /* # of issing discard */ + atomic_t queued_discard; /* # of queued discard */ atomic_t discard_cmd_cnt; /* # of cached cmd count */ - struct rb_root root; /* root of discard rb-tree */ + struct rb_root_cached root; /* root of discard rb-tree */ + bool rbtree_check; /* config for consistence check */ }; /* for the list of fsync inodes, used only during recovery */ @@ -329,6 +404,9 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal, #define F2FS_IOC_GARBAGE_COLLECT_RANGE _IOW(F2FS_IOCTL_MAGIC, 11, \ struct f2fs_gc_range) #define F2FS_IOC_GET_FEATURES _IOR(F2FS_IOCTL_MAGIC, 12, __u32) +#define F2FS_IOC_SET_PIN_FILE _IOW(F2FS_IOCTL_MAGIC, 13, __u32) +#define F2FS_IOC_GET_PIN_FILE _IOR(F2FS_IOCTL_MAGIC, 14, __u32) +#define F2FS_IOC_PRECACHE_EXTENTS _IO(F2FS_IOCTL_MAGIC, 15) #define F2FS_IOC_SET_ENCRYPTION_POLICY FS_IOC_SET_ENCRYPTION_POLICY #define F2FS_IOC_GET_ENCRYPTION_POLICY FS_IOC_GET_ENCRYPTION_POLICY @@ -343,6 +421,7 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal, #define F2FS_GOING_DOWN_METASYNC 0x1 /* going down with metadata */ #define F2FS_GOING_DOWN_NOSYNC 0x2 /* going down */ #define F2FS_GOING_DOWN_METAFLUSH 0x3 /* going down with meta flush */ +#define F2FS_GOING_DOWN_NEED_FSCK 0x4 /* going down to trigger fsck */ #if defined(__KERNEL__) && defined(CONFIG_COMPAT) /* @@ -382,10 +461,11 @@ struct f2fs_flush_device { /* for inline stuff */ #define DEF_INLINE_RESERVED_SIZE 1 static inline int get_extra_isize(struct inode *inode); -#define MAX_INLINE_DATA(inode) (sizeof(__le32) * \ - (CUR_ADDRS_PER_INODE(inode) - \ - DEF_INLINE_RESERVED_SIZE - \ - F2FS_INLINE_XATTR_ADDRS)) +static inline int get_inline_xattr_addrs(struct inode *inode); +#define MAX_INLINE_DATA(inode) (sizeof(__le32) * \ + (CUR_ADDRS_PER_INODE(inode) - \ + get_inline_xattr_addrs(inode) - \ + DEF_INLINE_RESERVED_SIZE)) /* for inline dir */ #define NR_INLINE_DENTRY(inode) (MAX_INLINE_DATA(inode) * BITS_PER_BYTE / \ @@ -417,7 +497,7 @@ static inline void make_dentry_ptr_block(struct inode *inode, d->inode = inode; d->max = NR_DENTRY_IN_BLOCK; d->nr_bitmap = SIZE_OF_DENTRY_BITMAP; - d->bitmap = &t->dentry_bitmap; + d->bitmap = t->dentry_bitmap; d->dentry = t->dentry; d->filename = t->filename; } @@ -454,13 +534,15 @@ enum { */ }; +#define DEFAULT_RETRY_IO_COUNT 8 /* maximum retry read IO count */ + +/* maximum retry quota flush count */ +#define DEFAULT_RETRY_QUOTA_FLUSH_COUNT 8 + #define F2FS_LINK_MAX 0xffffffff /* maximum link count per file */ #define MAX_DIR_RA_PAGES 4 /* maximum ra pages of dir */ -/* vector size for gang look-up from extent cache that consists of radix tree */ -#define EXT_TREE_VEC_SIZE 64 - /* for in-memory extent cache entry */ #define F2FS_MIN_EXTENT_LEN 64 /* minimum extent length */ @@ -480,28 +562,21 @@ struct extent_info { }; struct extent_node { - struct rb_node rb_node; - union { - struct { - unsigned int fofs; - unsigned int len; - u32 blk; - }; - struct extent_info ei; /* extent info */ - - }; + struct rb_node rb_node; /* rb node located in rb-tree */ + struct extent_info ei; /* extent info */ struct list_head list; /* node in global extent list of sbi */ struct extent_tree *et; /* extent tree pointer */ }; struct extent_tree { nid_t ino; /* inode number */ - struct rb_root root; /* root of extent info rb-tree */ + struct rb_root_cached root; /* root of extent info rb-tree */ struct extent_node *cached_en; /* recently accessed extent node */ struct extent_info largest; /* largested extent info */ struct list_head list; /* to be used by sbi->zombie_list */ rwlock_t lock; /* protect extent info rb-tree */ atomic_t node_cnt; /* # of extent node in rb-tree*/ + bool largest_updated; /* largest extent updated */ }; /* @@ -521,6 +596,9 @@ struct f2fs_map_blocks { unsigned int m_len; unsigned int m_flags; pgoff_t *m_next_pgofs; /* point next possible non-hole pgofs */ + pgoff_t *m_next_extent; /* point to next possible extent */ + int m_seg_type; + bool m_may_create; /* indicate it is from write path */ }; /* for flag in get_data_block */ @@ -528,8 +606,10 @@ enum { F2FS_GET_BLOCK_DEFAULT, F2FS_GET_BLOCK_FIEMAP, F2FS_GET_BLOCK_BMAP, + F2FS_GET_BLOCK_DIO, F2FS_GET_BLOCK_PRE_DIO, F2FS_GET_BLOCK_PRE_AIO, + F2FS_GET_BLOCK_PRECACHE, }; /* @@ -540,6 +620,10 @@ enum { #define FADVISE_ENCRYPT_BIT 0x04 #define FADVISE_ENC_NAME_BIT 0x08 #define FADVISE_KEEP_SIZE_BIT 0x10 +#define FADVISE_HOT_BIT 0x20 +#define FADVISE_VERITY_BIT 0x40 /* reserved */ + +#define FADVISE_MODIFIABLE_BITS (FADVISE_COLD_BIT | FADVISE_HOT_BIT) #define file_is_cold(inode) is_file(inode, FADVISE_COLD_BIT) #define file_wrong_pino(inode) is_file(inode, FADVISE_LOST_PINO_BIT) @@ -554,15 +638,26 @@ enum { #define file_set_enc_name(inode) set_file(inode, FADVISE_ENC_NAME_BIT) #define file_keep_isize(inode) is_file(inode, FADVISE_KEEP_SIZE_BIT) #define file_set_keep_isize(inode) set_file(inode, FADVISE_KEEP_SIZE_BIT) +#define file_is_hot(inode) is_file(inode, FADVISE_HOT_BIT) +#define file_set_hot(inode) set_file(inode, FADVISE_HOT_BIT) +#define file_clear_hot(inode) clear_file(inode, FADVISE_HOT_BIT) #define DEF_DIR_LEVEL 0 +enum { + GC_FAILURE_PIN, + GC_FAILURE_ATOMIC, + MAX_GC_FAILURE +}; + struct f2fs_inode_info { struct inode vfs_inode; /* serve a vfs inode */ unsigned long i_flags; /* keep an inode flags for ioctl */ unsigned char i_advise; /* use to give file attribute hints */ unsigned char i_dir_level; /* use for dentry level for large dir */ - unsigned int i_current_depth; /* use only in directory structure */ + unsigned int i_current_depth; /* only for directory depth */ + /* for gc failure statistic */ + unsigned int i_gc_failures[MAX_GC_FAILURE]; unsigned int i_pino; /* parent inode number */ umode_t i_acl_mode; /* keep file acl mode temporarily */ @@ -585,16 +680,22 @@ struct f2fs_inode_info { #endif struct list_head dirty_list; /* dirty list for dirs and files */ struct list_head gdirty_list; /* linked in global dirty list */ + struct list_head inmem_ilist; /* list for inmem inodes */ struct list_head inmem_pages; /* inmemory pages managed by f2fs */ struct task_struct *inmem_task; /* store inmemory task */ struct mutex inmem_lock; /* lock for inmemory pages */ struct extent_tree *extent_tree; /* cached extent_tree entry */ - struct rw_semaphore dio_rwsem[2];/* avoid racing between dio and gc */ + + /* avoid racing between foreground op and gc */ + struct rw_semaphore i_gc_rwsem[2]; struct rw_semaphore i_mmap_sem; struct rw_semaphore i_xattr_sem; /* avoid racing between reading and changing EAs */ int i_extra_isize; /* size of extra space located in i_addr */ kprojid_t i_projid; /* id for project quota */ + int i_inline_xattr_size; /* inline xattr size */ + struct timespec i_crtime; /* inode creation time */ + struct timespec i_disk_time[4]; /* inode disk times */ }; static inline void get_extent_info(struct extent_info *ext, @@ -622,21 +723,22 @@ static inline void set_extent_info(struct extent_info *ei, unsigned int fofs, } static inline bool __is_discard_mergeable(struct discard_info *back, - struct discard_info *front) + struct discard_info *front, unsigned int max_len) { - return back->lstart + back->len == front->lstart; + return (back->lstart + back->len == front->lstart) && + (back->len + front->len <= max_len); } static inline bool __is_discard_back_mergeable(struct discard_info *cur, - struct discard_info *back) + struct discard_info *back, unsigned int max_len) { - return __is_discard_mergeable(back, cur); + return __is_discard_mergeable(back, cur, max_len); } static inline bool __is_discard_front_mergeable(struct discard_info *cur, - struct discard_info *front) + struct discard_info *front, unsigned int max_len) { - return __is_discard_mergeable(cur, front); + return __is_discard_mergeable(cur, front, max_len); } static inline bool __is_extent_mergeable(struct extent_info *back, @@ -659,19 +761,22 @@ static inline bool __is_front_mergeable(struct extent_info *cur, } extern void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync); -static inline void __try_update_largest_extent(struct inode *inode, - struct extent_tree *et, struct extent_node *en) +static inline void __try_update_largest_extent(struct extent_tree *et, + struct extent_node *en) { if (en->ei.len > et->largest.len) { et->largest = en->ei; - f2fs_mark_inode_dirty_sync(inode, true); + et->largest_updated = true; } } -enum nid_list { - FREE_NID_LIST, - ALLOC_NID_LIST, - MAX_NID_LIST, +/* + * For free nid management + */ +enum nid_state { + FREE_NID, /* newly added to free nid list */ + PREALLOC_NID, /* it is preallocated */ + MAX_NID_STATE, }; struct f2fs_nm_info { @@ -688,17 +793,18 @@ struct f2fs_nm_info { struct radix_tree_root nat_set_root;/* root of the nat set cache */ struct rw_semaphore nat_tree_lock; /* protect nat_tree_lock */ struct list_head nat_entries; /* cached nat entry list (clean) */ + spinlock_t nat_list_lock; /* protect clean nat entry list */ unsigned int nat_cnt; /* the # of cached nat entries */ unsigned int dirty_nat_cnt; /* total num of nat entries in set */ unsigned int nat_blocks; /* # of nat blocks */ /* free node ids management */ struct radix_tree_root free_nid_root;/* root of the free_nid cache */ - struct list_head nid_list[MAX_NID_LIST];/* lists for free nids */ - unsigned int nid_cnt[MAX_NID_LIST]; /* the number of free node id */ + struct list_head free_nid_list; /* list for free nids excluding preallocated nids */ + unsigned int nid_cnt[MAX_NID_STATE]; /* the number of free node id */ spinlock_t nid_list_lock; /* protect nid lists ops */ struct mutex build_lock; /* lock for build free nids */ - unsigned char (*free_nid_bitmap)[NAT_ENTRY_BITMAP_SIZE]; + unsigned char **free_nid_bitmap; unsigned char *nat_block_bitmap; unsigned short *free_nid_count; /* free nid count of NAT block */ @@ -773,6 +879,7 @@ enum { struct flush_cmd { struct completion wait; struct llist_node llnode; + nid_t ino; int ret; }; @@ -780,7 +887,7 @@ struct flush_cmd_control { struct task_struct *f2fs_issue_flush; /* flush thread */ wait_queue_head_t flush_wait_queue; /* waiting queue for wake-up */ atomic_t issued_flush; /* # of issued flushes */ - atomic_t issing_flush; /* # of issing flushes */ + atomic_t queued_flush; /* # of queued flushes */ struct llist_head issue_list; /* list for command issue */ struct llist_node *dispatch_list; /* list for command dispatch */ }; @@ -791,6 +898,8 @@ struct f2fs_sm_info { struct dirty_seglist_info *dirty_info; /* dirty segment information */ struct curseg_info *curseg_array; /* active segment information */ + struct rw_semaphore curseg_lock; /* for preventing curseg change */ + block_t seg0_blkaddr; /* block address of 0'th segment */ block_t main_blkaddr; /* start block address of main area */ block_t ssa_blkaddr; /* start block address of SSA area */ @@ -811,7 +920,9 @@ struct f2fs_sm_info { unsigned int ipu_policy; /* in-place-update policy */ unsigned int min_ipu_util; /* in-place-update threshold */ unsigned int min_fsync_blocks; /* threshold for fsync */ + unsigned int min_seq_blocks; /* threshold for sequential blocks */ unsigned int min_hot_blocks; /* threshold for hot block allocation */ + unsigned int min_ssr_sections; /* threshold to trigger SSR allocation */ /* for flush command control */ struct flush_cmd_control *fcc_info; @@ -833,12 +944,18 @@ struct f2fs_sm_info { enum count_type { F2FS_DIRTY_DENTS, F2FS_DIRTY_DATA, + F2FS_DIRTY_QDATA, F2FS_DIRTY_NODES, F2FS_DIRTY_META, F2FS_INMEM_PAGES, F2FS_DIRTY_IMETA, F2FS_WB_CP_DATA, F2FS_WB_DATA, + F2FS_RD_DATA, + F2FS_RD_NODE, + F2FS_RD_META, + F2FS_DIO_WRITE, + F2FS_DIO_READ, NR_COUNT_TYPE, }; @@ -881,6 +998,19 @@ enum need_lock_type { LOCK_RETRY, }; +enum cp_reason_type { + CP_NO_NEEDED, + CP_NON_REGULAR, + CP_HARDLINK, + CP_SB_NEED_CP, + CP_WRONG_PINO, + CP_NO_SPC_ROLL, + CP_NODE_NEED_CP, + CP_FASTBOOT_MODE, + CP_SPEC_LOG_NUM, + CP_RECOVER_DIR, +}; + enum iostat_type { APP_DIRECT_IO, /* app direct IOs */ APP_BUFFERED_IO, /* app buffered IOs */ @@ -900,6 +1030,7 @@ enum iostat_type { struct f2fs_io_info { struct f2fs_sb_info *sbi; /* f2fs_sb_info pointer */ + nid_t ino; /* inode number */ enum page_type type; /* contains DATA/NODE/META/META_FLUSH */ enum temp_type temp; /* contains HOT/WARM/COLD */ int op; /* contains REQ_OP_ */ @@ -913,7 +1044,10 @@ struct f2fs_io_info { int need_lock; /* indicate we need to lock cp_rwsem */ bool in_list; /* indicate fio is in io_list */ bool is_meta; /* indicate borrow meta inode mapping or not */ + bool retry; /* need to reallocate block address */ enum iostat_type io_type; /* io type */ + struct writeback_control *io_wbc; /* writeback control */ + unsigned char version; /* version of the node */ }; #define is_read_io(rw) ((rw) == READ) @@ -945,6 +1079,7 @@ enum inode_type { DIR_INODE, /* for dirty dir inode */ FILE_INODE, /* for dirty regular/symlink inode */ DIRTY_META, /* for all dirtied inode metadata */ + ATOMIC_FILE, /* for all atomic files */ NR_INODE_TYPE, }; @@ -964,20 +1099,64 @@ enum { SBI_POR_DOING, /* recovery is doing or not */ SBI_NEED_SB_WRITE, /* need to recover superblock */ SBI_NEED_CP, /* need to checkpoint */ + SBI_IS_SHUTDOWN, /* shutdown by ioctl */ + SBI_IS_RECOVERED, /* recovered orphan/data */ + SBI_CP_DISABLED, /* CP was disabled last mount */ + SBI_CP_DISABLED_QUICK, /* CP was disabled quickly */ + SBI_QUOTA_NEED_FLUSH, /* need to flush quota info in CP */ + SBI_QUOTA_SKIP_FLUSH, /* skip flushing quota in current CP */ + SBI_QUOTA_NEED_REPAIR, /* quota file may be corrupted */ }; enum { CP_TIME, REQ_TIME, + DISCARD_TIME, + GC_TIME, + DISABLE_TIME, + UMOUNT_DISCARD_TIMEOUT, MAX_TIME, }; +enum { + GC_NORMAL, + GC_IDLE_CB, + GC_IDLE_GREEDY, + GC_URGENT, +}; + +enum { + WHINT_MODE_OFF, /* not pass down write hints */ + WHINT_MODE_USER, /* try to pass down hints given by users */ + WHINT_MODE_FS, /* pass down hints with F2FS policy */ +}; + +enum { + ALLOC_MODE_DEFAULT, /* stay default */ + ALLOC_MODE_REUSE, /* reuse segments as much as possible */ +}; + +enum fsync_mode { + FSYNC_MODE_POSIX, /* fsync follows posix semantics */ + FSYNC_MODE_STRICT, /* fsync behaves in line with ext4 */ + FSYNC_MODE_NOBARRIER, /* fsync behaves nobarrier based on posix */ +}; + +#ifdef CONFIG_F2FS_FS_ENCRYPTION +#define DUMMY_ENCRYPTION_ENABLED(sbi) \ + (unlikely(F2FS_OPTION(sbi).test_dummy_encryption)) +#else +#define DUMMY_ENCRYPTION_ENABLED(sbi) (0) +#endif + struct f2fs_sb_info { struct super_block *sb; /* pointer to VFS super block */ struct proc_dir_entry *s_proc; /* proc entry */ struct f2fs_super_block *raw_super; /* raw super block pointer */ + struct rw_semaphore sb_lock; /* lock for raw super block */ int valid_super_block; /* valid super block no */ unsigned long s_flag; /* flags for sbi */ + struct mutex writepages; /* mutex for writepages() */ #ifdef CONFIG_BLK_DEV_ZONED unsigned int blocks_per_blkz; /* F2FS blocks per zone */ @@ -993,9 +1172,8 @@ struct f2fs_sb_info { /* for bio operations */ struct f2fs_bio_info *write_io[NR_PAGE_TYPE]; /* for write bios */ - struct mutex wio_mutex[NR_PAGE_TYPE - 1][NR_TEMP_TYPE]; - /* bio ordering for NODE/DATA */ - int write_io_size_bits; /* Write IO size bits */ + /* keep migration IO order for LFS mode */ + struct rw_semaphore io_order_lock; mempool_t *write_io_dummy; /* Dummy pages */ /* for checkpoint */ @@ -1013,6 +1191,11 @@ struct f2fs_sb_info { struct inode_management im[MAX_INO_ENTRY]; /* manage inode cache */ + spinlock_t fsync_node_lock; /* for node entry lock */ + struct list_head fsync_node_list; /* node list head */ + unsigned int fsync_seg_id; /* sequence id */ + unsigned int fsync_node_num; /* number of node entries */ + /* for orphan inode, use 0'th array */ unsigned int max_orphans; /* max orphan inodes */ @@ -1045,16 +1228,20 @@ struct f2fs_sb_info { unsigned int total_node_count; /* total node block count */ unsigned int total_valid_node_count; /* valid node block count */ loff_t max_file_blocks; /* max block index of file */ - int active_logs; /* # of active logs */ int dir_level; /* directory level */ + int readdir_ra; /* readahead inode in readdir */ block_t user_block_count; /* # of user blocks */ block_t total_valid_block_count; /* # of valid blocks */ block_t discard_blks; /* discard command candidats */ block_t last_valid_block_count; /* for recovery */ block_t reserved_blocks; /* configurable reserved blocks */ + block_t current_reserved_blocks; /* current reserved blocks */ + + /* Additional tracking for no checkpoint mode */ + block_t unusable_block_count; /* # of blocks saved by last cp */ - u32 s_next_generation; /* for NFS support */ + unsigned int nquota_files; /* # of quota sysfile */ /* # of pages, see count_type */ atomic_t nr_pages[NR_COUNT_TYPE]; @@ -1062,7 +1249,7 @@ struct f2fs_sb_info { struct percpu_counter alloc_valid_block_count; /* writeback control */ - atomic_t wb_sync_req; /* count # of WB_SYNC threads */ + atomic_t wb_sync_req[META]; /* count # of WB_SYNC threads */ /* valid inode count */ struct percpu_counter total_valid_inode_count; @@ -1073,12 +1260,19 @@ struct f2fs_sb_info { struct mutex gc_mutex; /* mutex for GC */ struct f2fs_gc_kthread *gc_thread; /* GC thread */ unsigned int cur_victim_sec; /* current victim section num */ + unsigned int gc_mode; /* current GC state */ + unsigned int next_victim_seg[2]; /* next segment in victim section */ + /* for skip statistic */ + unsigned long long skipped_atomic_files[2]; /* FG_GC and BG_GC */ + unsigned long long skipped_gc_rwsem; /* FG_GC only */ - /* threshold for converting bg victims for fg */ - u64 fggc_threshold; + /* threshold for gc trials on pinned files */ + u64 gc_pin_file_threshold; /* maximum # of trials to find a victim segment for SSR and GC */ unsigned int max_victim_search; + /* migration granularity of garbage collection, unit: segment */ + unsigned int migration_granularity; /* * for stat information. @@ -1086,6 +1280,7 @@ struct f2fs_sb_info { */ #ifdef CONFIG_F2FS_STAT_FS struct f2fs_stat_info *stat_info; /* FS status information */ + atomic_t meta_count[META_MAX]; /* # of meta blocks */ unsigned int segment_count[2]; /* # of allocated segments */ unsigned int block_count[2]; /* # of allocated blocks */ atomic_t inplace_count; /* # of inplace update */ @@ -1101,6 +1296,8 @@ struct f2fs_sb_info { atomic_t max_aw_cnt; /* max # of atomic writes */ atomic_t max_vw_cnt; /* max # of volatile writes */ int bg_gc; /* background gc calls */ + unsigned int io_skip_bggc; /* skip background gc for in-flight IO */ + unsigned int other_skip_bggc; /* skip background gc for other reasons */ unsigned int ndirty_inode[NR_INODE_TYPE]; /* # of dirty inodes */ #endif spinlock_t stat_lock; /* lock for stat operations */ @@ -1118,6 +1315,8 @@ struct f2fs_sb_info { struct list_head s_list; int s_ndevs; /* number of devices */ struct f2fs_dev_info *devs; /* for device list */ + unsigned int dirty_device; /* for checkpoint data flush */ + spinlock_t dev_lock; /* protect dirty_device */ struct mutex umount_mutex; unsigned int shrinker_run_no; @@ -1130,27 +1329,23 @@ struct f2fs_sb_info { /* Precomputed FS UUID checksum for seeding other checksums */ __u32 s_chksum_seed; +}; - /* For fault injection */ -#ifdef CONFIG_F2FS_FAULT_INJECTION - struct f2fs_fault_info fault_info; -#endif - -#ifdef CONFIG_QUOTA - /* Names of quota files with journalled quota */ - char *s_qf_names[MAXQUOTAS]; - int s_jquota_fmt; /* Format of quota to use */ -#endif +struct f2fs_private_dio { + struct inode *inode; + void *orig_private; + bio_end_io_t *orig_end_io; + bool write; }; #ifdef CONFIG_F2FS_FAULT_INJECTION -#define f2fs_show_injection_info(type) \ - printk("%sF2FS-fs : inject %s in %s of %pF\n", \ - KERN_INFO, fault_name[type], \ +#define f2fs_show_injection_info(type) \ + printk_ratelimited("%sF2FS-fs : inject %s in %s of %pF\n", \ + KERN_INFO, f2fs_fault_name[type], \ __func__, __builtin_return_address(0)) static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type) { - struct f2fs_fault_info *ffi = &sbi->fault_info; + struct f2fs_fault_info *ffi = &F2FS_OPTION(sbi).fault_info; if (!ffi->inject_rate) return false; @@ -1165,6 +1360,12 @@ static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type) } return false; } +#else +#define f2fs_show_injection_info(type) do { } while (0) +static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type) +{ + return false; +} #endif /* @@ -1187,59 +1388,42 @@ static inline bool f2fs_is_multi_device(struct f2fs_sb_info *sbi) static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type) { - sbi->last_time[type] = jiffies; + unsigned long now = jiffies; + + sbi->last_time[type] = now; + + /* DISCARD_TIME and GC_TIME are based on REQ_TIME */ + if (type == REQ_TIME) { + sbi->last_time[DISCARD_TIME] = now; + sbi->last_time[GC_TIME] = now; + } } static inline bool f2fs_time_over(struct f2fs_sb_info *sbi, int type) { - struct timespec ts = {sbi->interval_time[type], 0}; - unsigned long interval = timespec_to_jiffies(&ts); + unsigned long interval = sbi->interval_time[type] * HZ; return time_after(jiffies, sbi->last_time[type] + interval); } -static inline bool is_idle(struct f2fs_sb_info *sbi) +static inline unsigned int f2fs_time_to_wait(struct f2fs_sb_info *sbi, + int type) { - struct block_device *bdev = sbi->sb->s_bdev; - struct request_queue *q = bdev_get_queue(bdev); - struct request_list *rl = &q->root_rl; + unsigned long interval = sbi->interval_time[type] * HZ; + unsigned int wait_ms = 0; + long delta; - if (rl->count[BLK_RW_SYNC] || rl->count[BLK_RW_ASYNC]) - return 0; + delta = (sbi->last_time[type] + interval) - jiffies; + if (delta > 0) + wait_ms = jiffies_to_msecs(delta); - return f2fs_time_over(sbi, REQ_TIME); + return wait_ms; } /* * Inline functions */ -static inline u32 f2fs_crc32(struct f2fs_sb_info *sbi, const void *address, - unsigned int length) -{ - SHASH_DESC_ON_STACK(shash, sbi->s_chksum_driver); - u32 *ctx = (u32 *)shash_desc_ctx(shash); - u32 retval; - int err; - - shash->tfm = sbi->s_chksum_driver; - shash->flags = 0; - *ctx = F2FS_SUPER_MAGIC; - - err = crypto_shash_update(shash, address, length); - BUG_ON(err); - - retval = *ctx; - barrier_data(ctx); - return retval; -} - -static inline bool f2fs_crc_valid(struct f2fs_sb_info *sbi, __u32 blk_crc, - void *buf, size_t buf_size) -{ - return f2fs_crc32(sbi, buf, buf_size) == blk_crc; -} - -static inline u32 f2fs_chksum(struct f2fs_sb_info *sbi, u32 crc, +static inline u32 __f2fs_crc32(struct f2fs_sb_info *sbi, u32 crc, const void *address, unsigned int length) { struct { @@ -1260,6 +1444,24 @@ static inline u32 f2fs_chksum(struct f2fs_sb_info *sbi, u32 crc, return *(u32 *)desc.ctx; } +static inline u32 f2fs_crc32(struct f2fs_sb_info *sbi, const void *address, + unsigned int length) +{ + return __f2fs_crc32(sbi, F2FS_SUPER_MAGIC, address, length); +} + +static inline bool f2fs_crc_valid(struct f2fs_sb_info *sbi, __u32 blk_crc, + void *buf, size_t buf_size) +{ + return f2fs_crc32(sbi, buf, buf_size) == blk_crc; +} + +static inline u32 f2fs_chksum(struct f2fs_sb_info *sbi, u32 crc, + const void *address, unsigned int length) +{ + return __f2fs_crc32(sbi, crc, address, length); +} + static inline struct f2fs_inode_info *F2FS_I(struct inode *inode) { return container_of(inode, struct f2fs_inode_info, vfs_inode); @@ -1360,6 +1562,13 @@ static inline unsigned long long cur_cp_version(struct f2fs_checkpoint *cp) return le64_to_cpu(cp->checkpoint_ver); } +static inline unsigned long f2fs_qf_ino(struct super_block *sb, int type) +{ + if (type < F2FS_MAX_QUOTAS) + return le32_to_cpu(F2FS_SB(sb)->raw_super->qf_ino[type]); + return 0; +} + static inline __u64 cur_cp_crc(struct f2fs_checkpoint *cp) { size_t crc_offset = le32_to_cpu(cp->checksum_offset); @@ -1418,12 +1627,16 @@ static inline void disable_nat_bits(struct f2fs_sb_info *sbi, bool lock) { unsigned long flags; - set_sbi_flag(sbi, SBI_NEED_FSCK); + /* + * In order to re-enable nat_bits we need to call fsck.f2fs by + * set_sbi_flag(sbi, SBI_NEED_FSCK). But it may give huge cost, + * so let's rely on regular fsck or unclean shutdown. + */ if (lock) spin_lock_irqsave(&sbi->cp_lock, flags); __clear_ckpt_flags(F2FS_CKPT(sbi), CP_NAT_BITS_FLAG); - kfree(NM_I(sbi)->nat_bits); + kvfree(NM_I(sbi)->nat_bits); NM_I(sbi)->nat_bits = NULL; if (lock) spin_unlock_irqrestore(&sbi->cp_lock, flags); @@ -1499,6 +1712,25 @@ static inline bool f2fs_has_xattr_block(unsigned int ofs) return ofs == XATTR_NODE_OFFSET; } +static inline bool __allow_reserved_blocks(struct f2fs_sb_info *sbi, + struct inode *inode, bool cap) +{ + if (!inode) + return true; + if (!test_opt(sbi, RESERVE_ROOT)) + return false; + if (IS_NOQUOTA(inode)) + return true; + if (uid_eq(F2FS_OPTION(sbi).s_resuid, current_fsuid())) + return true; + if (!gid_eq(F2FS_OPTION(sbi).s_resgid, GLOBAL_ROOT_GID) && + in_group_p(F2FS_OPTION(sbi).s_resgid)) + return true; + if (cap && capable(CAP_SYS_RESOURCE)) + return true; + return false; +} + static inline void f2fs_i_blocks_write(struct inode *, block_t, bool, bool); static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, struct inode *inode, blkcnt_t *count) @@ -1511,13 +1743,12 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, if (ret) return ret; -#ifdef CONFIG_F2FS_FAULT_INJECTION if (time_to_inject(sbi, FAULT_BLOCK)) { f2fs_show_injection_info(FAULT_BLOCK); release = *count; goto enospc; } -#endif + /* * let's increase this in prior to actual block count change in order * for f2fs_sync_file to avoid data races when deciding checkpoint. @@ -1526,26 +1757,36 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, spin_lock(&sbi->stat_lock); sbi->total_valid_block_count += (block_t)(*count); - avail_user_block_count = sbi->user_block_count - sbi->reserved_blocks; + avail_user_block_count = sbi->user_block_count - + sbi->current_reserved_blocks; + + if (!__allow_reserved_blocks(sbi, inode, true)) + avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + avail_user_block_count -= sbi->unusable_block_count; if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) { diff = sbi->total_valid_block_count - avail_user_block_count; + if (diff > *count) + diff = *count; *count -= diff; release = diff; - sbi->total_valid_block_count = avail_user_block_count; + sbi->total_valid_block_count -= diff; if (!*count) { spin_unlock(&sbi->stat_lock); - percpu_counter_sub(&sbi->alloc_valid_block_count, diff); goto enospc; } } spin_unlock(&sbi->stat_lock); - if (release) + if (unlikely(release)) { + percpu_counter_sub(&sbi->alloc_valid_block_count, release); dquot_release_reservation_block(inode, release); + } f2fs_i_blocks_write(inode, *count, true, true); return 0; enospc: + percpu_counter_sub(&sbi->alloc_valid_block_count, release); dquot_release_reservation_block(inode, release); return -ENOSPC; } @@ -1560,6 +1801,10 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi, spin_lock(&sbi->stat_lock); f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count); sbi->total_valid_block_count -= (block_t)count; + if (sbi->reserved_blocks && + sbi->current_reserved_blocks < sbi->reserved_blocks) + sbi->current_reserved_blocks = min(sbi->reserved_blocks, + sbi->current_reserved_blocks + count); spin_unlock(&sbi->stat_lock); if (unlikely(inode->i_blocks < sectors)) { f2fs_msg(sbi->sb, KERN_WARNING, @@ -1577,11 +1822,12 @@ static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type) { atomic_inc(&sbi->nr_pages[count_type]); - if (count_type == F2FS_DIRTY_DATA || count_type == F2FS_INMEM_PAGES || - count_type == F2FS_WB_CP_DATA || count_type == F2FS_WB_DATA) - return; - - set_sbi_flag(sbi, SBI_IS_DIRTY); + if (count_type == F2FS_DIRTY_DENTS || + count_type == F2FS_DIRTY_NODES || + count_type == F2FS_DIRTY_META || + count_type == F2FS_DIRTY_QDATA || + count_type == F2FS_DIRTY_IMETA) + set_sbi_flag(sbi, SBI_IS_DIRTY); } static inline void inode_inc_dirty_pages(struct inode *inode) @@ -1589,6 +1835,8 @@ static inline void inode_inc_dirty_pages(struct inode *inode) atomic_inc(&F2FS_I(inode)->dirty_pages); inc_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ? F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA); + if (IS_NOQUOTA(inode)) + inc_page_count(F2FS_I_SB(inode), F2FS_DIRTY_QDATA); } static inline void dec_page_count(struct f2fs_sb_info *sbi, int count_type) @@ -1605,6 +1853,8 @@ static inline void inode_dec_dirty_pages(struct inode *inode) atomic_dec(&F2FS_I(inode)->dirty_pages); dec_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ? F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA); + if (IS_NOQUOTA(inode)) + dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_QDATA); } static inline s64 get_pages(struct f2fs_sb_info *sbi, int count_type) @@ -1659,6 +1909,12 @@ static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag) struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); int offset; + if (is_set_ckpt_flags(sbi, CP_LARGE_NAT_BITMAP_FLAG)) { + offset = (flag == SIT_BITMAP) ? + le32_to_cpu(ckpt->nat_ver_bitmap_bytesize) : 0; + return &ckpt->sit_nat_version_bitmap + offset; + } + if (__cp_payload(sbi) > 0) { if (flag == NAT_BITMAP) return &ckpt->sit_nat_version_bitmap; @@ -1704,19 +1960,36 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, { block_t valid_block_count; unsigned int valid_node_count; - bool quota = inode && !is_inode; + int err; - if (quota) { - int ret = dquot_reserve_block(inode, 1); - if (ret) - return ret; + if (is_inode) { + if (inode) { + err = dquot_alloc_inode(inode); + if (err) + return err; + } + } else { + err = dquot_reserve_block(inode, 1); + if (err) + return err; + } + + if (time_to_inject(sbi, FAULT_BLOCK)) { + f2fs_show_injection_info(FAULT_BLOCK); + goto enospc; } spin_lock(&sbi->stat_lock); - valid_block_count = sbi->total_valid_block_count + 1; - if (unlikely(valid_block_count + sbi->reserved_blocks > - sbi->user_block_count)) { + valid_block_count = sbi->total_valid_block_count + + sbi->current_reserved_blocks + 1; + + if (!__allow_reserved_blocks(sbi, inode, false)) + valid_block_count += F2FS_OPTION(sbi).root_reserved_blocks; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + valid_block_count += sbi->unusable_block_count; + + if (unlikely(valid_block_count > sbi->user_block_count)) { spin_unlock(&sbi->stat_lock); goto enospc; } @@ -1742,8 +2015,12 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, return 0; enospc: - if (quota) + if (is_inode) { + if (inode) + dquot_free_inode(inode); + } else { dquot_release_reservation_block(inode, 1); + } return -ENOSPC; } @@ -1758,10 +2035,15 @@ static inline void dec_valid_node_count(struct f2fs_sb_info *sbi, sbi->total_valid_node_count--; sbi->total_valid_block_count--; + if (sbi->reserved_blocks && + sbi->current_reserved_blocks < sbi->reserved_blocks) + sbi->current_reserved_blocks++; spin_unlock(&sbi->stat_lock); - if (!is_inode) + if (is_inode) + dquot_free_inode(inode); + else f2fs_i_blocks_write(inode, 1, false, true); } @@ -1788,27 +2070,40 @@ static inline s64 valid_inode_count(struct f2fs_sb_info *sbi) static inline struct page *f2fs_grab_cache_page(struct address_space *mapping, pgoff_t index, bool for_write) { -#ifdef CONFIG_F2FS_FAULT_INJECTION struct page *page; - if (!for_write) - page = find_get_page_flags(mapping, index, - FGP_LOCK | FGP_ACCESSED); - else - page = find_lock_page(mapping, index); - if (page) - return page; + if (IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)) { + if (!for_write) + page = find_get_page_flags(mapping, index, + FGP_LOCK | FGP_ACCESSED); + else + page = find_lock_page(mapping, index); + if (page) + return page; - if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_ALLOC)) { - f2fs_show_injection_info(FAULT_PAGE_ALLOC); - return NULL; + if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_ALLOC)) { + f2fs_show_injection_info(FAULT_PAGE_ALLOC); + return NULL; + } } -#endif + if (!for_write) return grab_cache_page(mapping, index); return grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS); } +static inline struct page *f2fs_pagecache_get_page( + struct address_space *mapping, pgoff_t index, + int fgp_flags, gfp_t gfp_mask) +{ + if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_GET)) { + f2fs_show_injection_info(FAULT_PAGE_GET); + return NULL; + } + + return pagecache_get_page(mapping, index, fgp_flags, gfp_mask); +} + static inline void f2fs_copy_page(struct page *src, struct page *dst) { char *src_kaddr = kmap(src); @@ -1858,15 +2153,44 @@ static inline void *f2fs_kmem_cache_alloc(struct kmem_cache *cachep, return entry; } -static inline struct bio *f2fs_bio_alloc(int npages) +static inline struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, + int npages, bool no_fail) { struct bio *bio; - /* No failure on bio allocation */ - bio = bio_alloc(GFP_NOIO, npages); - if (!bio) - bio = bio_alloc(GFP_NOIO | __GFP_NOFAIL, npages); - return bio; + if (no_fail) { + /* No failure on bio allocation */ + bio = bio_alloc(GFP_NOIO, npages); + if (!bio) + bio = bio_alloc(GFP_NOIO | __GFP_NOFAIL, npages); + return bio; + } + if (time_to_inject(sbi, FAULT_ALLOC_BIO)) { + f2fs_show_injection_info(FAULT_ALLOC_BIO); + return NULL; + } + + return bio_alloc(GFP_KERNEL, npages); +} + +static inline bool is_idle(struct f2fs_sb_info *sbi, int type) +{ + if (get_pages(sbi, F2FS_RD_DATA) || get_pages(sbi, F2FS_RD_NODE) || + get_pages(sbi, F2FS_RD_META) || get_pages(sbi, F2FS_WB_DATA) || + get_pages(sbi, F2FS_WB_CP_DATA) || + get_pages(sbi, F2FS_DIO_READ) || + get_pages(sbi, F2FS_DIO_WRITE)) + return false; + + if (SM_I(sbi) && SM_I(sbi)->dcc_info && + atomic_read(&SM_I(sbi)->dcc_info->queued_discard)) + return false; + + if (SM_I(sbi) && SM_I(sbi)->fcc_info && + atomic_read(&SM_I(sbi)->fcc_info->queued_flush)) + return false; + + return f2fs_time_over(sbi, type); } static inline void f2fs_radix_tree_insert(struct radix_tree_root *root, @@ -1908,11 +2232,11 @@ static inline block_t datablock_addr(struct inode *inode, raw_node = F2FS_NODE(node_page); /* from GC path only */ - if (!inode) { - if (is_inode) + if (is_inode) { + if (!inode) base = offset_in_addr(&raw_node->i); - } else if (f2fs_has_extra_attr(inode) && is_inode) { - base = get_extra_isize(inode); + else if (f2fs_has_extra_attr(inode)) + base = get_extra_isize(inode); } addr_array = blkaddr_in_node(raw_node); @@ -1979,9 +2303,61 @@ static inline void f2fs_change_bit(unsigned int nr, char *addr) *addr ^= mask; } -#define F2FS_REG_FLMASK (~(FS_DIRSYNC_FL | FS_TOPDIR_FL)) -#define F2FS_OTHER_FLMASK (FS_NODUMP_FL | FS_NOATIME_FL) -#define F2FS_FL_INHERITED (FS_PROJINHERIT_FL) +/* + * Inode flags + */ +#define F2FS_SECRM_FL 0x00000001 /* Secure deletion */ +#define F2FS_UNRM_FL 0x00000002 /* Undelete */ +#define F2FS_COMPR_FL 0x00000004 /* Compress file */ +#define F2FS_SYNC_FL 0x00000008 /* Synchronous updates */ +#define F2FS_IMMUTABLE_FL 0x00000010 /* Immutable file */ +#define F2FS_APPEND_FL 0x00000020 /* writes to file may only append */ +#define F2FS_NODUMP_FL 0x00000040 /* do not dump file */ +#define F2FS_NOATIME_FL 0x00000080 /* do not update atime */ +/* Reserved for compression usage... */ +#define F2FS_DIRTY_FL 0x00000100 +#define F2FS_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */ +#define F2FS_NOCOMPR_FL 0x00000400 /* Don't compress */ +#define F2FS_ENCRYPT_FL 0x00000800 /* encrypted file */ +/* End compression flags --- maybe not all used */ +#define F2FS_INDEX_FL 0x00001000 /* hash-indexed directory */ +#define F2FS_IMAGIC_FL 0x00002000 /* AFS directory */ +#define F2FS_JOURNAL_DATA_FL 0x00004000 /* file data should be journaled */ +#define F2FS_NOTAIL_FL 0x00008000 /* file tail should not be merged */ +#define F2FS_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */ +#define F2FS_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/ +#define F2FS_HUGE_FILE_FL 0x00040000 /* Set to each huge file */ +#define F2FS_EXTENTS_FL 0x00080000 /* Inode uses extents */ +#define F2FS_EA_INODE_FL 0x00200000 /* Inode used for large EA */ +#define F2FS_EOFBLOCKS_FL 0x00400000 /* Blocks allocated beyond EOF */ +#define F2FS_NOCOW_FL 0x00800000 /* Do not cow file */ +#define F2FS_INLINE_DATA_FL 0x10000000 /* Inode has inline data. */ +#define F2FS_PROJINHERIT_FL 0x20000000 /* Create with parents projid */ +#define F2FS_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ + +#define F2FS_FL_USER_VISIBLE 0x30CBDFFF /* User visible flags */ +#define F2FS_FL_USER_MODIFIABLE 0x204BC0FF /* User modifiable flags */ + +/* Flags we can manipulate with through F2FS_IOC_FSSETXATTR */ +#define F2FS_FL_XFLAG_VISIBLE (F2FS_SYNC_FL | \ + F2FS_IMMUTABLE_FL | \ + F2FS_APPEND_FL | \ + F2FS_NODUMP_FL | \ + F2FS_NOATIME_FL | \ + F2FS_PROJINHERIT_FL) + +/* Flags that should be inherited by new inodes from their parent. */ +#define F2FS_FL_INHERITED (F2FS_SECRM_FL | F2FS_UNRM_FL | F2FS_COMPR_FL |\ + F2FS_SYNC_FL | F2FS_NODUMP_FL | F2FS_NOATIME_FL |\ + F2FS_NOCOMPR_FL | F2FS_JOURNAL_DATA_FL |\ + F2FS_NOTAIL_FL | F2FS_DIRSYNC_FL |\ + F2FS_PROJINHERIT_FL) + +/* Flags that are appropriate for regular files (all but dir-specific ones). */ +#define F2FS_REG_FLMASK (~(F2FS_DIRSYNC_FL | F2FS_TOPDIR_FL)) + +/* Flags that are appropriate for non-directories/regular files. */ +#define F2FS_OTHER_FLMASK (F2FS_NODUMP_FL | F2FS_NOATIME_FL) static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags) { @@ -2023,6 +2399,8 @@ enum { FI_HOT_DATA, /* indicate file is hot */ FI_EXTRA_ATTR, /* indicate file has extra attribute */ FI_PROJ_INHERIT, /* indicate file inherits projectid */ + FI_PIN_FILE, /* indicate file should not be gced */ + FI_ATOMIC_REVOKE_REQUEST, /* request to drop atomic data */ }; static inline void __mark_inode_dirty_flag(struct inode *inode, @@ -2032,10 +2410,13 @@ static inline void __mark_inode_dirty_flag(struct inode *inode, case FI_INLINE_XATTR: case FI_INLINE_DATA: case FI_INLINE_DENTRY: + case FI_NEW_INODE: if (set) return; + /* fall through */ case FI_DATA_EXIST: case FI_INLINE_DOTS: + case FI_PIN_FILE: f2fs_mark_inode_dirty_sync(inode, true); } } @@ -2116,6 +2497,13 @@ static inline void f2fs_i_depth_write(struct inode *inode, unsigned int depth) f2fs_mark_inode_dirty_sync(inode, true); } +static inline void f2fs_i_gc_failures_write(struct inode *inode, + unsigned int count) +{ + F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN] = count; + f2fs_mark_inode_dirty_sync(inode, true); +} + static inline void f2fs_i_xnid_write(struct inode *inode, nid_t xnid) { F2FS_I(inode)->i_xattr_nid = xnid; @@ -2144,6 +2532,8 @@ static inline void get_inline_info(struct inode *inode, struct f2fs_inode *ri) set_bit(FI_INLINE_DOTS, &fi->flags); if (ri->i_inline & F2FS_EXTRA_ATTR) set_bit(FI_EXTRA_ATTR, &fi->flags); + if (ri->i_inline & F2FS_PIN_FILE) + set_bit(FI_PIN_FILE, &fi->flags); } static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri) @@ -2162,6 +2552,8 @@ static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri) ri->i_inline |= F2FS_INLINE_DOTS; if (is_inode_flag_set(inode, FI_EXTRA_ATTR)) ri->i_inline |= F2FS_EXTRA_ATTR; + if (is_inode_flag_set(inode, FI_PIN_FILE)) + ri->i_inline |= F2FS_PIN_FILE; } static inline int f2fs_has_extra_attr(struct inode *inode) @@ -2176,25 +2568,20 @@ static inline int f2fs_has_inline_xattr(struct inode *inode) static inline unsigned int addrs_per_inode(struct inode *inode) { - if (f2fs_has_inline_xattr(inode)) - return CUR_ADDRS_PER_INODE(inode) - F2FS_INLINE_XATTR_ADDRS; - return CUR_ADDRS_PER_INODE(inode); + return CUR_ADDRS_PER_INODE(inode) - get_inline_xattr_addrs(inode); } -static inline void *inline_xattr_addr(struct page *page) +static inline void *inline_xattr_addr(struct inode *inode, struct page *page) { struct f2fs_inode *ri = F2FS_INODE(page); return (void *)&(ri->i_addr[DEF_ADDRS_PER_INODE - - F2FS_INLINE_XATTR_ADDRS]); + get_inline_xattr_addrs(inode)]); } static inline int inline_xattr_size(struct inode *inode) { - if (f2fs_has_inline_xattr(inode)) - return F2FS_INLINE_XATTR_ADDRS << 2; - else - return 0; + return get_inline_xattr_addrs(inode) * sizeof(__le32); } static inline int f2fs_has_inline_data(struct inode *inode) @@ -2212,6 +2599,11 @@ static inline int f2fs_has_inline_dots(struct inode *inode) return is_inode_flag_set(inode, FI_INLINE_DOTS); } +static inline bool f2fs_is_pinned_file(struct inode *inode) +{ + return is_inode_flag_set(inode, FI_PIN_FILE); +} + static inline bool f2fs_is_atomic_file(struct inode *inode) { return is_inode_flag_set(inode, FI_ATOMIC_FILE); @@ -2250,12 +2642,6 @@ static inline int f2fs_has_inline_dentry(struct inode *inode) return is_inode_flag_set(inode, FI_INLINE_DENTRY); } -static inline void f2fs_dentry_kunmap(struct inode *dir, struct page *page) -{ - if (!f2fs_has_inline_dentry(dir)) - kunmap(page); -} - static inline int is_file(struct inode *inode, int type) { return F2FS_I(inode)->i_advise & type; @@ -2275,9 +2661,10 @@ static inline void clear_file(struct inode *inode, int type) static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync) { + bool ret; + if (dsync) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - bool ret; spin_lock(&sbi->inode_lock[DIRTY_META]); ret = list_empty(&F2FS_I(inode)->gdirty_list); @@ -2286,14 +2673,29 @@ static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync) } if (!is_inode_flag_set(inode, FI_AUTO_RECOVER) || file_keep_isize(inode) || - i_size_read(inode) & PAGE_MASK) + i_size_read(inode) & ~PAGE_MASK) return false; - return F2FS_I(inode)->last_disk_size == i_size_read(inode); + + if (!timespec_equal(F2FS_I(inode)->i_disk_time, &inode->i_atime)) + return false; + if (!timespec_equal(F2FS_I(inode)->i_disk_time + 1, &inode->i_ctime)) + return false; + if (!timespec_equal(F2FS_I(inode)->i_disk_time + 2, &inode->i_mtime)) + return false; + if (!timespec_equal(F2FS_I(inode)->i_disk_time + 3, + &F2FS_I(inode)->i_crtime)) + return false; + + down_read(&F2FS_I(inode)->i_sem); + ret = F2FS_I(inode)->last_disk_size == i_size_read(inode); + up_read(&F2FS_I(inode)->i_sem); + + return ret; } -static inline int f2fs_readonly(struct super_block *sb) +static inline bool f2fs_readonly(struct super_block *sb) { - return sb->s_flags & MS_RDONLY; + return sb_rdonly(sb); } static inline bool f2fs_cp_error(struct f2fs_sb_info *sbi) @@ -2333,13 +2735,41 @@ static inline bool f2fs_may_extent_tree(struct inode *inode) static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi, size_t size, gfp_t flags) { -#ifdef CONFIG_F2FS_FAULT_INJECTION + void *ret; + if (time_to_inject(sbi, FAULT_KMALLOC)) { f2fs_show_injection_info(FAULT_KMALLOC); return NULL; } -#endif - return kmalloc(size, flags); + + ret = kmalloc(size, flags); + if (ret) + return ret; + + return kvmalloc(size, flags); +} + +static inline void *f2fs_kzalloc(struct f2fs_sb_info *sbi, + size_t size, gfp_t flags) +{ + return f2fs_kmalloc(sbi, size, flags | __GFP_ZERO); +} + +static inline void *f2fs_kvmalloc(struct f2fs_sb_info *sbi, + size_t size, gfp_t flags) +{ + if (time_to_inject(sbi, FAULT_KVMALLOC)) { + f2fs_show_injection_info(FAULT_KVMALLOC); + return NULL; + } + + return kvmalloc(size, flags); +} + +static inline void *f2fs_kvzalloc(struct f2fs_sb_info *sbi, + size_t size, gfp_t flags) +{ + return f2fs_kvmalloc(sbi, size, flags | __GFP_ZERO); } static inline int get_extra_isize(struct inode *inode) @@ -2347,7 +2777,12 @@ static inline int get_extra_isize(struct inode *inode) return F2FS_I(inode)->i_extra_isize / sizeof(__le32); } -#define get_inode_mode(i) \ +static inline int get_inline_xattr_addrs(struct inode *inode) +{ + return F2FS_I(inode)->i_inline_xattr_size; +} + +#define f2fs_get_inode_mode(i) \ ((is_inode_flag_set(i, FI_ACL_MODE)) ? \ (F2FS_I(i)->i_acl_mode) : ((i)->i_mode)) @@ -2357,9 +2792,9 @@ static inline int get_extra_isize(struct inode *inode) #define F2FS_OLD_ATTRIBUTE_SIZE (offsetof(struct f2fs_inode, i_addr)) #define F2FS_FITS_IN_INODE(f2fs_inode, extra_isize, field) \ - ((offsetof(typeof(*f2fs_inode), field) + \ + ((offsetof(typeof(*(f2fs_inode)), field) + \ sizeof((f2fs_inode)->field)) \ - <= (F2FS_OLD_ATTRIBUTE_SIZE + extra_isize)) \ + <= (F2FS_OLD_ATTRIBUTE_SIZE + (extra_isize))) \ static inline void f2fs_reset_iostat(struct f2fs_sb_info *sbi) { @@ -2386,8 +2821,10 @@ static inline void f2fs_update_iostat(struct f2fs_sb_info *sbi, spin_unlock(&sbi->iostat_lock); } -#define __is_meta_io(fio) (PAGE_TYPE_OF_BIO(fio->type) == META && \ - (!is_read_io(fio->op) || fio->is_meta)) +#define __is_large_section(sbi) ((sbi)->segs_per_sec > 1) + +#define __is_meta_io(fio) (PAGE_TYPE_OF_BIO((fio)->type) == META && \ + (!is_read_io((fio)->op) || (fio)->is_meta)) bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type); @@ -2418,20 +2855,44 @@ static inline bool is_valid_data_blkaddr(struct f2fs_sb_info *sbi, return true; } +static inline void f2fs_set_page_private(struct page *page, + unsigned long data) +{ + if (PagePrivate(page)) + return; + + get_page(page); + SetPagePrivate(page); + set_page_private(page, data); +} + +static inline void f2fs_clear_page_private(struct page *page) +{ + if (!PagePrivate(page)) + return; + + set_page_private(page, 0); + ClearPagePrivate(page); + f2fs_put_page(page, 0); +} + /* * file.c */ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync); -void truncate_data_blocks(struct dnode_of_data *dn); -int truncate_blocks(struct inode *inode, u64 from, bool lock); +void f2fs_truncate_data_blocks(struct dnode_of_data *dn); +int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock); int f2fs_truncate(struct inode *inode); int f2fs_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags); int f2fs_setattr(struct dentry *dentry, struct iattr *attr); -int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end); -int truncate_data_blocks_range(struct dnode_of_data *dn, int count); +int f2fs_truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end); +void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count); +int f2fs_precache_extents(struct inode *inode); long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg); long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg); +int f2fs_transfer_project_quota(struct inode *inode, kprojid_t kprojid); +int f2fs_pin_file_control(struct inode *inode, bool inc); /* * inode.c @@ -2441,36 +2902,37 @@ bool f2fs_inode_chksum_verify(struct f2fs_sb_info *sbi, struct page *page); void f2fs_inode_chksum_set(struct f2fs_sb_info *sbi, struct page *page); struct inode *f2fs_iget(struct super_block *sb, unsigned long ino); struct inode *f2fs_iget_retry(struct super_block *sb, unsigned long ino); -int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink); -int update_inode(struct inode *inode, struct page *node_page); -int update_inode_page(struct inode *inode); +int f2fs_try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink); +void f2fs_update_inode(struct inode *inode, struct page *node_page); +void f2fs_update_inode_page(struct inode *inode); int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc); void f2fs_evict_inode(struct inode *inode); -void handle_failed_inode(struct inode *inode); +void f2fs_handle_failed_inode(struct inode *inode); /* * namei.c */ +int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name, + bool hot, bool set); struct dentry *f2fs_get_parent(struct dentry *child); /* * dir.c */ -void set_de_type(struct f2fs_dir_entry *de, umode_t mode); -unsigned char get_de_type(struct f2fs_dir_entry *de); -struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname, +unsigned char f2fs_get_de_type(struct f2fs_dir_entry *de); +struct f2fs_dir_entry *f2fs_find_target_dentry(struct fscrypt_name *fname, f2fs_hash_t namehash, int *max_slots, struct f2fs_dentry_ptr *d); int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, unsigned int start_pos, struct fscrypt_str *fstr); -void do_make_empty_dir(struct inode *inode, struct inode *parent, +void f2fs_do_make_empty_dir(struct inode *inode, struct inode *parent, struct f2fs_dentry_ptr *d); -struct page *init_inode_metadata(struct inode *inode, struct inode *dir, +struct page *f2fs_init_inode_metadata(struct inode *inode, struct inode *dir, const struct qstr *new_name, const struct qstr *orig_name, struct page *dpage); -void update_parent_metadata(struct inode *dir, struct inode *inode, +void f2fs_update_parent_metadata(struct inode *dir, struct inode *inode, unsigned int current_depth); -int room_for_filename(const void *bitmap, int slots, int max_slots); +int f2fs_room_for_filename(const void *bitmap, int slots, int max_slots); void f2fs_drop_nlink(struct inode *dir, struct inode *inode); struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir, struct fscrypt_name *fname, struct page **res_page); @@ -2487,9 +2949,9 @@ void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d, int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name, const struct qstr *orig_name, struct inode *inode, nid_t ino, umode_t mode); -int __f2fs_do_add_link(struct inode *dir, struct fscrypt_name *fname, +int f2fs_add_dentry(struct inode *dir, struct fscrypt_name *fname, struct inode *inode, nid_t ino, umode_t mode); -int __f2fs_add_link(struct inode *dir, const struct qstr *name, +int f2fs_do_add_link(struct inode *dir, const struct qstr *name, struct inode *inode, nid_t ino, umode_t mode); void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, struct inode *dir, struct inode *inode); @@ -2498,7 +2960,7 @@ bool f2fs_empty_dir(struct inode *dir); static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode) { - return __f2fs_add_link(d_inode(dentry->d_parent), &dentry->d_name, + return f2fs_do_add_link(d_inode(dentry->d_parent), &dentry->d_name, inode, inode->i_ino, inode->i_mode); } @@ -2507,13 +2969,14 @@ static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode) */ int f2fs_inode_dirtied(struct inode *inode, bool sync); void f2fs_inode_synced(struct inode *inode); -void f2fs_enable_quota_files(struct f2fs_sb_info *sbi); +int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly); +int f2fs_quota_sync(struct super_block *sb, int type); void f2fs_quota_off_umount(struct super_block *sb); int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover); int f2fs_sync_fs(struct super_block *sb, int sync); extern __printf(3, 4) void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...); -int sanity_check_ckpt(struct f2fs_sb_info *sbi); +int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi); /* * hash.c @@ -2527,169 +2990,196 @@ f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info, struct dnode_of_data; struct node_info; -int check_nid_range(struct f2fs_sb_info *sbi, nid_t nid); -bool available_free_memory(struct f2fs_sb_info *sbi, int type); -int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid); -bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid); -bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino); -void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni); -pgoff_t get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs); -int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode); -int truncate_inode_blocks(struct inode *inode, pgoff_t from); -int truncate_xattr_node(struct inode *inode, struct page *page); -int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino); -int remove_inode_page(struct inode *inode); -struct page *new_inode_page(struct inode *inode); -struct page *new_node_page(struct dnode_of_data *dn, unsigned int ofs); -void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid); -struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid); -struct page *get_node_page_ra(struct page *parent, int start); -void move_node_page(struct page *node_page, int gc_type); -int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, - struct writeback_control *wbc, bool atomic); -int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc, +int f2fs_check_nid_range(struct f2fs_sb_info *sbi, nid_t nid); +bool f2fs_available_free_memory(struct f2fs_sb_info *sbi, int type); +bool f2fs_in_warm_node_list(struct f2fs_sb_info *sbi, struct page *page); +void f2fs_init_fsync_node_info(struct f2fs_sb_info *sbi); +void f2fs_del_fsync_node_entry(struct f2fs_sb_info *sbi, struct page *page); +void f2fs_reset_fsync_node_info(struct f2fs_sb_info *sbi); +int f2fs_need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid); +bool f2fs_is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid); +bool f2fs_need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino); +int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid, + struct node_info *ni); +pgoff_t f2fs_get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs); +int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode); +int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from); +int f2fs_truncate_xattr_node(struct inode *inode); +int f2fs_wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, + unsigned int seq_id); +int f2fs_remove_inode_page(struct inode *inode); +struct page *f2fs_new_inode_page(struct inode *inode); +struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs); +void f2fs_ra_node_page(struct f2fs_sb_info *sbi, nid_t nid); +struct page *f2fs_get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid); +struct page *f2fs_get_node_page_ra(struct page *parent, int start); +int f2fs_move_node_page(struct page *node_page, int gc_type); +int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, + struct writeback_control *wbc, bool atomic, + unsigned int *seq_id); +int f2fs_sync_node_pages(struct f2fs_sb_info *sbi, + struct writeback_control *wbc, bool do_balance, enum iostat_type io_type); -void build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount); -bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid); -void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid); -void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid); -int try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink); -void recover_inline_xattr(struct inode *inode, struct page *page); -int recover_xattr_data(struct inode *inode, struct page *page, - block_t blkaddr); -int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page); -int restore_node_summary(struct f2fs_sb_info *sbi, +int f2fs_build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount); +bool f2fs_alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid); +void f2fs_alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid); +void f2fs_alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid); +int f2fs_try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink); +void f2fs_recover_inline_xattr(struct inode *inode, struct page *page); +int f2fs_recover_xattr_data(struct inode *inode, struct page *page); +int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page); +int f2fs_restore_node_summary(struct f2fs_sb_info *sbi, unsigned int segno, struct f2fs_summary_block *sum); -void flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc); -int build_node_manager(struct f2fs_sb_info *sbi); -void destroy_node_manager(struct f2fs_sb_info *sbi); -int __init create_node_manager_caches(void); -void destroy_node_manager_caches(void); +int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc); +int f2fs_build_node_manager(struct f2fs_sb_info *sbi); +void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi); +int __init f2fs_create_node_manager_caches(void); +void f2fs_destroy_node_manager_caches(void); /* * segment.c */ -bool need_SSR(struct f2fs_sb_info *sbi); -void register_inmem_page(struct inode *inode, struct page *page); -void drop_inmem_pages(struct inode *inode); -void drop_inmem_page(struct inode *inode, struct page *page); -int commit_inmem_pages(struct inode *inode); +bool f2fs_need_SSR(struct f2fs_sb_info *sbi); +void f2fs_register_inmem_page(struct inode *inode, struct page *page); +void f2fs_drop_inmem_pages_all(struct f2fs_sb_info *sbi, bool gc_failure); +void f2fs_drop_inmem_pages(struct inode *inode); +void f2fs_drop_inmem_page(struct inode *inode, struct page *page); +int f2fs_commit_inmem_pages(struct inode *inode); void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need); void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi); -int f2fs_issue_flush(struct f2fs_sb_info *sbi); -int create_flush_cmd_control(struct f2fs_sb_info *sbi); -void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free); -void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr); -bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr); -void refresh_sit_entry(struct f2fs_sb_info *sbi, block_t old, block_t new); -void stop_discard_thread(struct f2fs_sb_info *sbi); -void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi, bool umount); -void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc); -void release_discard_addrs(struct f2fs_sb_info *sbi); -int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra); -void allocate_new_segments(struct f2fs_sb_info *sbi); +int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino); +int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi); +int f2fs_flush_device_cache(struct f2fs_sb_info *sbi); +void f2fs_destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free); +void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr); +bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr); +void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi); +void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi); +bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi); +void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi, + struct cp_control *cpc); +void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi); +int f2fs_disable_cp_again(struct f2fs_sb_info *sbi); +void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi); +int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra); +void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi); int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range); -bool exist_trim_candidates(struct f2fs_sb_info *sbi, struct cp_control *cpc); -struct page *get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno); -void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr); -void write_meta_page(struct f2fs_sb_info *sbi, struct page *page, +bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi, + struct cp_control *cpc); +struct page *f2fs_get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno); +void f2fs_update_meta_page(struct f2fs_sb_info *sbi, void *src, + block_t blk_addr); +void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct page *page, enum iostat_type io_type); -void write_node_page(unsigned int nid, struct f2fs_io_info *fio); -void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio); -int rewrite_data_page(struct f2fs_io_info *fio); -void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, +void f2fs_do_write_node_page(unsigned int nid, struct f2fs_io_info *fio); +void f2fs_outplace_write_data(struct dnode_of_data *dn, + struct f2fs_io_info *fio); +int f2fs_inplace_write_data(struct f2fs_io_info *fio); +void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, block_t old_blkaddr, block_t new_blkaddr, bool recover_curseg, bool recover_newaddr); void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn, block_t old_addr, block_t new_addr, unsigned char version, bool recover_curseg, bool recover_newaddr); -void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, +void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, block_t old_blkaddr, block_t *new_blkaddr, struct f2fs_summary *sum, int type, struct f2fs_io_info *fio, bool add_list); void f2fs_wait_on_page_writeback(struct page *page, - enum page_type type, bool ordered); -void f2fs_wait_on_block_writeback(struct f2fs_sb_info *sbi, block_t blkaddr); -void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk); -void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk); -int lookup_journal_in_cursum(struct f2fs_journal *journal, int type, + enum page_type type, bool ordered, bool locked); +void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr); +void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr, + block_t len); +void f2fs_write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk); +void f2fs_write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk); +int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type, unsigned int val, int alloc); -void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc); -int build_segment_manager(struct f2fs_sb_info *sbi); -void destroy_segment_manager(struct f2fs_sb_info *sbi); -int __init create_segment_manager_caches(void); -void destroy_segment_manager_caches(void); +void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc); +int f2fs_build_segment_manager(struct f2fs_sb_info *sbi); +void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi); +int __init f2fs_create_segment_manager_caches(void); +void f2fs_destroy_segment_manager_caches(void); +int f2fs_rw_hint_to_seg_type(enum rw_hint hint); +enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi, + enum page_type type, enum temp_type temp); /* * checkpoint.c */ void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io); -struct page *grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index); -struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index); -struct page *get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index); +struct page *f2fs_grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index); +struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index); +struct page *f2fs_get_meta_page_nofail(struct f2fs_sb_info *sbi, pgoff_t index); +struct page *f2fs_get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index); bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type); -int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, +int f2fs_ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type, bool sync); -void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index); -long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type, +void f2fs_ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index); +long f2fs_sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type, long nr_to_write, enum iostat_type io_type); -void add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type); -void remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type); -void release_ino_entry(struct f2fs_sb_info *sbi, bool all); -bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode); +void f2fs_add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type); +void f2fs_remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type); +void f2fs_release_ino_entry(struct f2fs_sb_info *sbi, bool all); +bool f2fs_exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode); +void f2fs_set_dirty_device(struct f2fs_sb_info *sbi, nid_t ino, + unsigned int devidx, int type); +bool f2fs_is_dirty_device(struct f2fs_sb_info *sbi, nid_t ino, + unsigned int devidx, int type); int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi); -int acquire_orphan_inode(struct f2fs_sb_info *sbi); -void release_orphan_inode(struct f2fs_sb_info *sbi); -void add_orphan_inode(struct inode *inode); -void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino); -int recover_orphan_inodes(struct f2fs_sb_info *sbi); -int get_valid_checkpoint(struct f2fs_sb_info *sbi); -void update_dirty_page(struct inode *inode, struct page *page); -void remove_dirty_inode(struct inode *inode); -int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type); -int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc); -void init_ino_entry_info(struct f2fs_sb_info *sbi); -int __init create_checkpoint_caches(void); -void destroy_checkpoint_caches(void); +int f2fs_acquire_orphan_inode(struct f2fs_sb_info *sbi); +void f2fs_release_orphan_inode(struct f2fs_sb_info *sbi); +void f2fs_add_orphan_inode(struct inode *inode); +void f2fs_remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino); +int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi); +int f2fs_get_valid_checkpoint(struct f2fs_sb_info *sbi); +void f2fs_update_dirty_page(struct inode *inode, struct page *page); +void f2fs_remove_dirty_inode(struct inode *inode); +int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type); +void f2fs_wait_on_all_pages_writeback(struct f2fs_sb_info *sbi); +int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc); +void f2fs_init_ino_entry_info(struct f2fs_sb_info *sbi); +int __init f2fs_create_checkpoint_caches(void); +void f2fs_destroy_checkpoint_caches(void); /* * data.c */ +int f2fs_init_post_read_processing(void); +void f2fs_destroy_post_read_processing(void); void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type); void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi, - struct inode *inode, nid_t ino, pgoff_t idx, - enum page_type type); + struct inode *inode, struct page *page, + nid_t ino, enum page_type type); void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi); int f2fs_submit_page_bio(struct f2fs_io_info *fio); -int f2fs_submit_page_write(struct f2fs_io_info *fio); +void f2fs_submit_page_write(struct f2fs_io_info *fio); struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi, block_t blk_addr, struct bio *bio); int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr); -void set_data_blkaddr(struct dnode_of_data *dn); +void f2fs_set_data_blkaddr(struct dnode_of_data *dn); void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr); -int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count); -int reserve_new_block(struct dnode_of_data *dn); +int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count); +int f2fs_reserve_new_block(struct dnode_of_data *dn); int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index); int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from); int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index); -struct page *get_read_data_page(struct inode *inode, pgoff_t index, +struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index, int op_flags, bool for_write); -struct page *find_data_page(struct inode *inode, pgoff_t index); -struct page *get_lock_data_page(struct inode *inode, pgoff_t index, +struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index); +struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index, bool for_write); -struct page *get_new_data_page(struct inode *inode, +struct page *f2fs_get_new_data_page(struct inode *inode, struct page *ipage, pgoff_t index, bool new_i_size); -int do_write_data_page(struct f2fs_io_info *fio); +int f2fs_do_write_data_page(struct f2fs_io_info *fio); +void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock); int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, int create, int flag); int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len); -void f2fs_set_page_dirty_nobuffers(struct page *page); -int __f2fs_write_data_pages(struct address_space *mapping, - struct writeback_control *wbc, - enum iostat_type io_type); +bool f2fs_should_update_inplace(struct inode *inode, struct f2fs_io_info *fio); +bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio); void f2fs_invalidate_page(struct page *page, unsigned int offset, unsigned int length); int f2fs_release_page(struct page *page, gfp_t wait); @@ -2697,22 +3187,24 @@ int f2fs_release_page(struct page *page, gfp_t wait); int f2fs_migrate_page(struct address_space *mapping, struct page *newpage, struct page *page, enum migrate_mode mode); #endif +bool f2fs_overwrite_io(struct inode *inode, loff_t pos, size_t len); +void f2fs_clear_radix_tree_dirty_tag(struct page *page); /* * gc.c */ -int start_gc_thread(struct f2fs_sb_info *sbi); -void stop_gc_thread(struct f2fs_sb_info *sbi); -block_t start_bidx_of_node(unsigned int node_ofs, struct inode *inode); +int f2fs_start_gc_thread(struct f2fs_sb_info *sbi); +void f2fs_stop_gc_thread(struct f2fs_sb_info *sbi); +block_t f2fs_start_bidx_of_node(unsigned int node_ofs, struct inode *inode); int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background, unsigned int segno); -void build_gc_manager(struct f2fs_sb_info *sbi); +void f2fs_build_gc_manager(struct f2fs_sb_info *sbi); /* * recovery.c */ -int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only); -bool space_for_roll_forward(struct f2fs_sb_info *sbi); +int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only); +bool f2fs_space_for_roll_forward(struct f2fs_sb_info *sbi); /* * debug.c @@ -2726,14 +3218,19 @@ struct f2fs_stat_info { unsigned long long hit_largest, hit_cached, hit_rbtree; unsigned long long hit_total, total_ext; int ext_tree, zombie_tree, ext_node; - int ndirty_node, ndirty_dent, ndirty_meta, ndirty_data, ndirty_imeta; + int ndirty_node, ndirty_dent, ndirty_meta, ndirty_imeta; + int ndirty_data, ndirty_qdata; int inmem_pages; - unsigned int ndirty_dirs, ndirty_files, ndirty_all; + unsigned int ndirty_dirs, ndirty_files, nquota_files, ndirty_all; int nats, dirty_nats, sits, dirty_sits; int free_nids, avail_nids, alloc_nids; int total_count, utilization; int bg_gc, nr_wb_cp_data, nr_wb_data; - int nr_flushing, nr_flushed, nr_discarding, nr_discarded; + int nr_rd_data, nr_rd_node, nr_rd_meta; + int nr_dio_read, nr_dio_write; + unsigned int io_skip_bggc, other_skip_bggc; + int nr_flushing, nr_flushed, flush_list_empty; + int nr_discarding, nr_discarded; int nr_discard_cmd; unsigned int undiscard_blks; int inline_xattr, inline_inode, inline_dir, append, update, orphans; @@ -2748,10 +3245,12 @@ struct f2fs_stat_info { int bg_node_segs, bg_data_segs; int tot_blks, data_blks, node_blks; int bg_data_blks, bg_node_blks; + unsigned long long skipped_atomic_files[2]; int curseg[NR_CURSEG_TYPE]; int cursec[NR_CURSEG_TYPE]; int curzone[NR_CURSEG_TYPE]; + unsigned int meta_count[META_MAX]; unsigned int segment_count[2]; unsigned int block_count[2]; unsigned int inplace_count; @@ -2767,6 +3266,8 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi) #define stat_inc_bg_cp_count(si) ((si)->bg_cp_count++) #define stat_inc_call_count(si) ((si)->call_count++) #define stat_inc_bggc_count(sbi) ((sbi)->bg_gc++) +#define stat_io_skip_bggc_count(sbi) ((sbi)->io_skip_bggc++) +#define stat_other_skip_bggc_count(sbi) ((sbi)->other_skip_bggc++) #define stat_inc_dirty_inode(sbi, type) ((sbi)->ndirty_inode[type]++) #define stat_dec_dirty_inode(sbi, type) ((sbi)->ndirty_inode[type]--) #define stat_inc_total_hit(sbi) (atomic64_inc(&(sbi)->total_hit_ext)) @@ -2803,6 +3304,17 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi) if (f2fs_has_inline_dentry(inode)) \ (atomic_dec(&F2FS_I_SB(inode)->inline_dir)); \ } while (0) +#define stat_inc_meta_count(sbi, blkaddr) \ + do { \ + if (blkaddr < SIT_I(sbi)->sit_base_addr) \ + atomic_inc(&(sbi)->meta_count[META_CP]); \ + else if (blkaddr < NM_I(sbi)->nat_blkaddr) \ + atomic_inc(&(sbi)->meta_count[META_SIT]); \ + else if (blkaddr < SM_I(sbi)->ssa_blkaddr) \ + atomic_inc(&(sbi)->meta_count[META_NAT]); \ + else if (blkaddr < SM_I(sbi)->main_blkaddr) \ + atomic_inc(&(sbi)->meta_count[META_SSA]); \ + } while (0) #define stat_inc_seg_type(sbi, curseg) \ ((sbi)->segment_count[(curseg)->alloc_type]++) #define stat_inc_block_count(sbi, curseg) \ @@ -2865,13 +3377,15 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi) int f2fs_build_stats(struct f2fs_sb_info *sbi); void f2fs_destroy_stats(struct f2fs_sb_info *sbi); -int __init f2fs_create_root_stats(void); +void __init f2fs_create_root_stats(void); void f2fs_destroy_root_stats(void); #else #define stat_inc_cp_count(si) do { } while (0) #define stat_inc_bg_cp_count(si) do { } while (0) #define stat_inc_call_count(si) do { } while (0) #define stat_inc_bggc_count(si) do { } while (0) +#define stat_io_skip_bggc_count(sbi) do { } while (0) +#define stat_other_skip_bggc_count(sbi) do { } while (0) #define stat_inc_dirty_inode(sbi, type) do { } while (0) #define stat_dec_dirty_inode(sbi, type) do { } while (0) #define stat_inc_total_hit(sb) do { } while (0) @@ -2890,6 +3404,7 @@ void f2fs_destroy_root_stats(void); #define stat_inc_volatile_write(inode) do { } while (0) #define stat_dec_volatile_write(inode) do { } while (0) #define stat_update_max_volatile_write(inode) do { } while (0) +#define stat_inc_meta_count(sbi, blkaddr) do { } while (0) #define stat_inc_seg_type(sbi, curseg) do { } while (0) #define stat_inc_block_count(sbi, curseg) do { } while (0) #define stat_inc_inplace_blocks(sbi) do { } while (0) @@ -2900,7 +3415,7 @@ void f2fs_destroy_root_stats(void); static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; } static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { } -static inline int __init f2fs_create_root_stats(void) { return 0; } +static inline void __init f2fs_create_root_stats(void) { } static inline void f2fs_destroy_root_stats(void) { } #endif @@ -2914,29 +3429,31 @@ extern const struct inode_operations f2fs_dir_inode_operations; extern const struct inode_operations f2fs_symlink_inode_operations; extern const struct inode_operations f2fs_encrypted_symlink_inode_operations; extern const struct inode_operations f2fs_special_inode_operations; -extern struct kmem_cache *inode_entry_slab; +extern struct kmem_cache *f2fs_inode_entry_slab; /* * inline.c */ bool f2fs_may_inline_data(struct inode *inode); bool f2fs_may_inline_dentry(struct inode *inode); -void read_inline_data(struct page *page, struct page *ipage); -void truncate_inline_inode(struct inode *inode, struct page *ipage, u64 from); +void f2fs_do_read_inline_data(struct page *page, struct page *ipage); +void f2fs_truncate_inline_inode(struct inode *inode, + struct page *ipage, u64 from); int f2fs_read_inline_data(struct inode *inode, struct page *page); int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page); int f2fs_convert_inline_inode(struct inode *inode); int f2fs_write_inline_data(struct inode *inode, struct page *page); -bool recover_inline_data(struct inode *inode, struct page *npage); -struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir, +bool f2fs_recover_inline_data(struct inode *inode, struct page *npage); +struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir, struct fscrypt_name *fname, struct page **res_page); -int make_empty_inline_dir(struct inode *inode, struct inode *parent, +int f2fs_make_empty_inline_dir(struct inode *inode, struct inode *parent, struct page *ipage); int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name, const struct qstr *orig_name, struct inode *inode, nid_t ino, umode_t mode); -void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page, - struct inode *dir, struct inode *inode); +void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, + struct page *page, struct inode *dir, + struct inode *inode); bool f2fs_empty_inline_dir(struct inode *dir); int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx, struct fscrypt_str *fstr); @@ -2957,18 +3474,19 @@ void f2fs_leave_shrinker(struct f2fs_sb_info *sbi); /* * extent_cache.c */ -struct rb_entry *__lookup_rb_tree(struct rb_root *root, +struct rb_entry *f2fs_lookup_rb_tree(struct rb_root_cached *root, struct rb_entry *cached_re, unsigned int ofs); -struct rb_node **__lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi, - struct rb_root *root, struct rb_node **parent, - unsigned int ofs); -struct rb_entry *__lookup_rb_tree_ret(struct rb_root *root, +struct rb_node **f2fs_lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi, + struct rb_root_cached *root, + struct rb_node **parent, + unsigned int ofs, bool *leftmost); +struct rb_entry *f2fs_lookup_rb_tree_ret(struct rb_root_cached *root, struct rb_entry *cached_re, unsigned int ofs, struct rb_entry **prev_entry, struct rb_entry **next_entry, struct rb_node ***insert_p, struct rb_node **insert_parent, - bool force); -bool __check_rb_tree_consistence(struct f2fs_sb_info *sbi, - struct rb_root *root); + bool force, bool *leftmost); +bool f2fs_check_rb_tree_consistence(struct f2fs_sb_info *sbi, + struct rb_root_cached *root); unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink); bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext); void f2fs_drop_extent_tree(struct inode *inode); @@ -2979,9 +3497,9 @@ bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs, void f2fs_update_extent_cache(struct dnode_of_data *dn); void f2fs_update_extent_cache_range(struct dnode_of_data *dn, pgoff_t fofs, block_t blkaddr, unsigned int len); -void init_extent_cache_info(struct f2fs_sb_info *sbi); -int __init create_extent_cache(void); -void destroy_extent_cache(void); +void f2fs_init_extent_cache_info(struct f2fs_sb_info *sbi); +int __init f2fs_create_extent_cache(void); +void f2fs_destroy_extent_cache(void); /* * sysfs.c @@ -3008,38 +3526,35 @@ static inline void f2fs_set_encrypted_inode(struct inode *inode) { #ifdef CONFIG_F2FS_FS_ENCRYPTION file_set_encrypt(inode); + f2fs_set_inode_flags(inode); #endif } -static inline bool f2fs_bio_encrypted(struct bio *bio) -{ - return bio->bi_private != NULL; -} - -static inline int f2fs_sb_has_crypto(struct super_block *sb) -{ - return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_ENCRYPT); -} - -static inline int f2fs_sb_mounted_blkzoned(struct super_block *sb) -{ - return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_BLKZONED); -} - -static inline int f2fs_sb_has_extra_attr(struct super_block *sb) +/* + * Returns true if the reads of the inode's data need to undergo some + * postprocessing step, like decryption or authenticity verification. + */ +static inline bool f2fs_post_read_required(struct inode *inode) { - return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_EXTRA_ATTR); + return f2fs_encrypted_file(inode); } -static inline int f2fs_sb_has_project_quota(struct super_block *sb) -{ - return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_PRJQUOTA); +#define F2FS_FEATURE_FUNCS(name, flagname) \ +static inline int f2fs_sb_has_##name(struct f2fs_sb_info *sbi) \ +{ \ + return F2FS_HAS_FEATURE(sbi, F2FS_FEATURE_##flagname); \ } -static inline int f2fs_sb_has_inode_chksum(struct super_block *sb) -{ - return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_INODE_CHKSUM); -} +F2FS_FEATURE_FUNCS(encrypt, ENCRYPT); +F2FS_FEATURE_FUNCS(blkzoned, BLKZONED); +F2FS_FEATURE_FUNCS(extra_attr, EXTRA_ATTR); +F2FS_FEATURE_FUNCS(project_quota, PRJQUOTA); +F2FS_FEATURE_FUNCS(inode_chksum, INODE_CHKSUM); +F2FS_FEATURE_FUNCS(flexible_inline_xattr, FLEXIBLE_INLINE_XATTR); +F2FS_FEATURE_FUNCS(quota_ino, QUOTA_INO); +F2FS_FEATURE_FUNCS(inode_crtime, INODE_CRTIME); +F2FS_FEATURE_FUNCS(lost_found, LOST_FOUND); +F2FS_FEATURE_FUNCS(sb_chksum, SB_CHKSUM); #ifdef CONFIG_BLK_DEV_ZONED static inline int get_blkz_type(struct f2fs_sb_info *sbi, @@ -3055,11 +3570,20 @@ static inline int get_blkz_type(struct f2fs_sb_info *sbi, } #endif -static inline bool f2fs_discard_en(struct f2fs_sb_info *sbi) +static inline bool f2fs_hw_should_discard(struct f2fs_sb_info *sbi) { - struct request_queue *q = bdev_get_queue(sbi->sb->s_bdev); + return f2fs_sb_has_blkzoned(sbi); +} - return blk_queue_discard(q) || f2fs_sb_mounted_blkzoned(sbi->sb); +static inline bool f2fs_hw_support_discard(struct f2fs_sb_info *sbi) +{ + return blk_queue_discard(bdev_get_queue(sbi->sb->s_bdev)); +} + +static inline bool f2fs_realtime_discard_enable(struct f2fs_sb_info *sbi) +{ + return (test_opt(sbi, DISCARD) && f2fs_hw_support_discard(sbi)) || + f2fs_hw_should_discard(sbi); } static inline void set_opt_mode(struct f2fs_sb_info *sbi, unsigned int mt) @@ -3084,10 +3608,76 @@ static inline bool f2fs_may_encrypt(struct inode *inode) return (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)); #else - return 0; + return false; #endif } +static inline int block_unaligned_IO(struct inode *inode, + struct kiocb *iocb, struct iov_iter *iter) +{ + unsigned int i_blkbits = READ_ONCE(inode->i_blkbits); + unsigned int blocksize_mask = (1 << i_blkbits) - 1; + loff_t offset = iocb->ki_pos; + unsigned long align = offset | iov_iter_alignment(iter); + + return align & blocksize_mask; +} + +static inline int allow_outplace_dio(struct inode *inode, + struct kiocb *iocb, struct iov_iter *iter) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + int rw = iov_iter_rw(iter); + + return (test_opt(sbi, LFS) && (rw == WRITE) && + !block_unaligned_IO(inode, iocb, iter)); +} + +static inline bool f2fs_force_buffered_io(struct inode *inode, + struct kiocb *iocb, struct iov_iter *iter) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + int rw = iov_iter_rw(iter); + + if (f2fs_post_read_required(inode)) + return true; + if (sbi->s_ndevs) + return true; + /* + * for blkzoned device, fallback direct IO to buffered IO, so + * all IOs can be serialized by log-structured write. + */ + if (f2fs_sb_has_blkzoned(sbi)) + return true; + if (test_opt(sbi, LFS) && (rw == WRITE) && + block_unaligned_IO(inode, iocb, iter)) + return true; + if (is_sbi_flag_set(F2FS_I_SB(inode), SBI_CP_DISABLED)) + return true; + + return false; +} + +#ifdef CONFIG_F2FS_FAULT_INJECTION +extern void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate, + unsigned int type); +#else +#define f2fs_build_fault_attr(sbi, rate, type) do { } while (0) +#endif + +static inline bool is_journalled_quota(struct f2fs_sb_info *sbi) +{ +#ifdef CONFIG_QUOTA + if (f2fs_sb_has_quota_ino(sbi)) + return true; + if (F2FS_OPTION(sbi).s_qf_names[USRQUOTA] || + F2FS_OPTION(sbi).s_qf_names[GRPQUOTA] || + F2FS_OPTION(sbi).s_qf_names[PRJQUOTA]) + return true; +#endif + return false; +} + #endif #define EFSBADCRC EBADMSG /* Bad CRC detected */ diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index d98acc20a38a..1d5a35c80e36 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/file.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> @@ -50,26 +47,18 @@ static int f2fs_vm_page_mkwrite(struct vm_fault *vmf) struct page *page = vmf->page; struct inode *inode = file_inode(vmf->vma->vm_file); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct dnode_of_data dn; + struct dnode_of_data dn = { .node_changed = false }; int err; + if (unlikely(f2fs_cp_error(sbi))) { + err = -EIO; + goto err; + } + sb_start_pagefault(inode->i_sb); f2fs_bug_on(sbi, f2fs_has_inline_data(inode)); - /* block allocation */ - f2fs_lock_op(sbi); - set_new_dnode(&dn, inode, NULL, NULL, 0); - err = f2fs_reserve_block(&dn, page->index); - if (err) { - f2fs_unlock_op(sbi); - goto out; - } - f2fs_put_dnode(&dn); - f2fs_unlock_op(sbi); - - f2fs_balance_fs(sbi, dn.node_changed); - file_update_time(vmf->vma->vm_file); down_read(&F2FS_I(inode)->i_mmap_sem); lock_page(page); @@ -81,16 +70,34 @@ static int f2fs_vm_page_mkwrite(struct vm_fault *vmf) goto out_sem; } + /* block allocation */ + __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true); + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = f2fs_get_block(&dn, page->index); + f2fs_put_dnode(&dn); + __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false); + if (err) { + unlock_page(page); + goto out_sem; + } + + /* fill the page */ + f2fs_wait_on_page_writeback(page, DATA, false, true); + + /* wait for GCed page writeback via META_MAPPING */ + f2fs_wait_on_block_writeback(inode, dn.data_blkaddr); + /* * check to see if the page is mapped already (no holes) */ if (PageMappedToDisk(page)) - goto mapped; + goto out_sem; /* page is wholly or partially inside EOF */ if (((loff_t)(page->index + 1) << PAGE_SHIFT) > i_size_read(inode)) { - unsigned offset; + loff_t offset; + offset = i_size_read(inode) & ~PAGE_MASK; zero_user_segment(page, offset, PAGE_SIZE); } @@ -99,21 +106,16 @@ static int f2fs_vm_page_mkwrite(struct vm_fault *vmf) SetPageUptodate(page); f2fs_update_iostat(sbi, APP_MAPPED_IO, F2FS_BLKSIZE); + f2fs_update_time(sbi, REQ_TIME); trace_f2fs_vm_page_mkwrite(page, DATA); -mapped: - /* fill the page */ - f2fs_wait_on_page_writeback(page, DATA, false); - - /* wait for GCed encrypted page writeback */ - if (f2fs_encrypted_file(inode)) - f2fs_wait_on_block_writeback(sbi, dn.data_blkaddr); - out_sem: up_read(&F2FS_I(inode)->i_mmap_sem); -out: + + f2fs_balance_fs(sbi, dn.node_changed); + sb_end_pagefault(inode->i_sb); - f2fs_update_time(sbi, REQ_TIME); +err: return block_page_mkwrite_return(err); } @@ -138,27 +140,34 @@ static int get_parent_ino(struct inode *inode, nid_t *pino) return 1; } -static inline bool need_do_checkpoint(struct inode *inode) +static inline enum cp_reason_type need_do_checkpoint(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - bool need_cp = false; + enum cp_reason_type cp_reason = CP_NO_NEEDED; - if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1) - need_cp = true; + if (!S_ISREG(inode->i_mode)) + cp_reason = CP_NON_REGULAR; + else if (inode->i_nlink != 1) + cp_reason = CP_HARDLINK; else if (is_sbi_flag_set(sbi, SBI_NEED_CP)) - need_cp = true; + cp_reason = CP_SB_NEED_CP; else if (file_wrong_pino(inode)) - need_cp = true; - else if (!space_for_roll_forward(sbi)) - need_cp = true; - else if (!is_checkpointed_node(sbi, F2FS_I(inode)->i_pino)) - need_cp = true; + cp_reason = CP_WRONG_PINO; + else if (!f2fs_space_for_roll_forward(sbi)) + cp_reason = CP_NO_SPC_ROLL; + else if (!f2fs_is_checkpointed_node(sbi, F2FS_I(inode)->i_pino)) + cp_reason = CP_NODE_NEED_CP; else if (test_opt(sbi, FASTBOOT)) - need_cp = true; - else if (sbi->active_logs == 2) - need_cp = true; + cp_reason = CP_FASTBOOT_MODE; + else if (F2FS_OPTION(sbi).active_logs == 2) + cp_reason = CP_SPEC_LOG_NUM; + else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT && + f2fs_need_dentry_mark(sbi, inode->i_ino) && + f2fs_exist_written_data(sbi, F2FS_I(inode)->i_pino, + TRANS_DIR_INO)) + cp_reason = CP_RECOVER_DIR; - return need_cp; + return cp_reason; } static bool need_inode_page_update(struct f2fs_sb_info *sbi, nid_t ino) @@ -166,7 +175,7 @@ static bool need_inode_page_update(struct f2fs_sb_info *sbi, nid_t ino) struct page *i = find_get_page(NODE_MAPPING(sbi), ino); bool ret = false; /* But we need to avoid that there are some inode updates */ - if ((i && PageDirty(i)) || need_inode_block_update(sbi, ino)) + if ((i && PageDirty(i)) || f2fs_need_inode_block_update(sbi, ino)) ret = true; f2fs_put_page(i, 0); return ret; @@ -193,14 +202,16 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end, struct f2fs_sb_info *sbi = F2FS_I_SB(inode); nid_t ino = inode->i_ino; int ret = 0; - bool need_cp = false; + enum cp_reason_type cp_reason = 0; struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, .nr_to_write = LONG_MAX, .for_reclaim = 0, }; + unsigned int seq_id = 0; - if (unlikely(f2fs_readonly(inode->i_sb))) + if (unlikely(f2fs_readonly(inode->i_sb) || + is_sbi_flag_set(sbi, SBI_CP_DISABLED))) return 0; trace_f2fs_sync_file_enter(inode); @@ -215,7 +226,7 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end, clear_inode_flag(inode, FI_NEED_IPU); if (ret) { - trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret); + trace_f2fs_sync_file_exit(inode, cp_reason, datasync, ret); return ret; } @@ -229,14 +240,14 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end, * if there is no written data, don't waste time to write recovery info. */ if (!is_inode_flag_set(inode, FI_APPEND_WRITE) && - !exist_written_data(sbi, ino, APPEND_INO)) { + !f2fs_exist_written_data(sbi, ino, APPEND_INO)) { /* it may call write_inode just prior to fsync */ if (need_inode_page_update(sbi, ino)) goto go_write; if (is_inode_flag_set(inode, FI_UPDATE_WRITE) || - exist_written_data(sbi, ino, UPDATE_INO)) + f2fs_exist_written_data(sbi, ino, UPDATE_INO)) goto flush_out; goto out; } @@ -246,10 +257,10 @@ go_write: * sudden-power-off. */ down_read(&F2FS_I(inode)->i_sem); - need_cp = need_do_checkpoint(inode); + cp_reason = need_do_checkpoint(inode); up_read(&F2FS_I(inode)->i_sem); - if (need_cp) { + if (cp_reason) { /* all the dirty node pages should be flushed for POR */ ret = f2fs_sync_fs(inode->i_sb, 1); @@ -263,7 +274,9 @@ go_write: goto out; } sync_nodes: - ret = fsync_node_pages(sbi, inode, &wbc, atomic); + atomic_inc(&sbi->wb_sync_req[NODE]); + ret = f2fs_fsync_node_pages(sbi, inode, &wbc, atomic, &seq_id); + atomic_dec(&sbi->wb_sync_req[NODE]); if (ret) goto out; @@ -273,7 +286,7 @@ sync_nodes: goto out; } - if (need_inode_block_update(sbi, ino)) { + if (f2fs_need_inode_block_update(sbi, ino)) { f2fs_mark_inode_dirty_sync(inode, true); f2fs_write_inode(inode, NULL); goto sync_nodes; @@ -288,46 +301,52 @@ sync_nodes: * given fsync mark. */ if (!atomic) { - ret = wait_on_node_pages_writeback(sbi, ino); + ret = f2fs_wait_on_node_pages_writeback(sbi, seq_id); if (ret) goto out; } /* once recovery info is written, don't need to tack this */ - remove_ino_entry(sbi, ino, APPEND_INO); + f2fs_remove_ino_entry(sbi, ino, APPEND_INO); clear_inode_flag(inode, FI_APPEND_WRITE); flush_out: - remove_ino_entry(sbi, ino, UPDATE_INO); - clear_inode_flag(inode, FI_UPDATE_WRITE); - if (!atomic) - ret = f2fs_issue_flush(sbi); + if (!atomic && F2FS_OPTION(sbi).fsync_mode != FSYNC_MODE_NOBARRIER) + ret = f2fs_issue_flush(sbi, inode->i_ino); + if (!ret) { + f2fs_remove_ino_entry(sbi, ino, UPDATE_INO); + clear_inode_flag(inode, FI_UPDATE_WRITE); + f2fs_remove_ino_entry(sbi, ino, FLUSH_INO); + } f2fs_update_time(sbi, REQ_TIME); out: - trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret); + trace_f2fs_sync_file_exit(inode, cp_reason, datasync, ret); f2fs_trace_ios(NULL, 1); return ret; } int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) { + if (unlikely(f2fs_cp_error(F2FS_I_SB(file_inode(file))))) + return -EIO; return f2fs_do_sync_file(file, start, end, datasync, false); } static pgoff_t __get_first_dirty_index(struct address_space *mapping, pgoff_t pgofs, int whence) { - struct pagevec pvec; + struct page *page; int nr_pages; if (whence != SEEK_DATA) return 0; /* find first dirty page index */ - pagevec_init(&pvec, 0); - nr_pages = pagevec_lookup_tag(&pvec, mapping, &pgofs, - PAGECACHE_TAG_DIRTY, 1); - pgofs = nr_pages ? pvec.pages[0]->index : ULONG_MAX; - pagevec_release(&pvec); + nr_pages = find_get_pages_tag(mapping, &pgofs, PAGECACHE_TAG_DIRTY, + 1, &page); + if (!nr_pages) + return ULONG_MAX; + pgofs = page->index; + put_page(page); return pgofs; } @@ -377,13 +396,13 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence) for (; data_ofs < isize; data_ofs = (loff_t)pgofs << PAGE_SHIFT) { set_new_dnode(&dn, inode, NULL, NULL, 0); - err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE); + err = f2fs_get_dnode_of_data(&dn, pgofs, LOOKUP_NODE); if (err && err != -ENOENT) { goto fail; } else if (err == -ENOENT) { /* direct node does not exists */ if (whence == SEEK_DATA) { - pgofs = get_next_page_offset(&dn, pgofs); + pgofs = f2fs_get_next_page_offset(&dn, pgofs); continue; } else { goto found; @@ -397,6 +416,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence) dn.ofs_in_node++, pgofs++, data_ofs = (loff_t)pgofs << PAGE_SHIFT) { block_t blkaddr; + blkaddr = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node); @@ -454,6 +474,9 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma) struct inode *inode = file_inode(file); int err; + if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) + return -EIO; + /* we don't need to use inline_data strictly */ err = f2fs_convert_inline_inode(inode); if (err) @@ -466,26 +489,17 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma) static int f2fs_file_open(struct inode *inode, struct file *filp) { - struct dentry *dir; + int err = fscrypt_file_open(inode, filp); + + if (err) + return err; + + filp->f_mode |= FMODE_NOWAIT; - if (f2fs_encrypted_inode(inode)) { - int ret = fscrypt_get_encryption_info(inode); - if (ret) - return -EACCES; - if (!fscrypt_has_encryption_key(inode)) - return -ENOKEY; - } - dir = dget_parent(file_dentry(filp)); - if (f2fs_encrypted_inode(d_inode(dir)) && - !fscrypt_has_permitted_context(d_inode(dir), inode)) { - dput(dir); - return -EPERM; - } - dput(dir); return dquot_file_open(inode, filp); } -int truncate_data_blocks_range(struct dnode_of_data *dn, int count) +void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); struct f2fs_node *raw_node; @@ -501,17 +515,18 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count) for (; count > 0; count--, addr++, dn->ofs_in_node++) { block_t blkaddr = le32_to_cpu(*addr); + if (blkaddr == NULL_ADDR) continue; dn->data_blkaddr = NULL_ADDR; - set_data_blkaddr(dn); + f2fs_set_data_blkaddr(dn); if (__is_valid_data_blkaddr(blkaddr) && !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC)) continue; - invalidate_blocks(sbi, blkaddr); + f2fs_invalidate_blocks(sbi, blkaddr); if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page)) clear_inode_flag(dn->inode, FI_FIRST_BLOCK_WRITTEN); nr_free++; @@ -523,7 +538,7 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count) * once we invalidate valid blkaddr in range [ofs, ofs + count], * we will invalidate all blkaddr in the whole range. */ - fofs = start_bidx_of_node(ofs_of_node(dn->node_page), + fofs = f2fs_start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) + ofs; f2fs_update_extent_cache_range(dn, fofs, 0, len); dec_valid_block_count(sbi, dn->inode, nr_free); @@ -533,18 +548,17 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count) f2fs_update_time(sbi, REQ_TIME); trace_f2fs_truncate_data_blocks_range(dn->inode, dn->nid, dn->ofs_in_node, nr_free); - return nr_free; } -void truncate_data_blocks(struct dnode_of_data *dn) +void f2fs_truncate_data_blocks(struct dnode_of_data *dn) { - truncate_data_blocks_range(dn, ADDRS_PER_BLOCK); + f2fs_truncate_data_blocks_range(dn, ADDRS_PER_BLOCK); } static int truncate_partial_data_page(struct inode *inode, u64 from, bool cache_only) { - unsigned offset = from & (PAGE_SIZE - 1); + loff_t offset = from & (PAGE_SIZE - 1); pgoff_t index = from >> PAGE_SHIFT; struct address_space *mapping = inode->i_mapping; struct page *page; @@ -560,11 +574,11 @@ static int truncate_partial_data_page(struct inode *inode, u64 from, return 0; } - page = get_lock_data_page(inode, index, true); + page = f2fs_get_lock_data_page(inode, index, true); if (IS_ERR(page)) return PTR_ERR(page) == -ENOENT ? 0 : PTR_ERR(page); truncate_out: - f2fs_wait_on_page_writeback(page, DATA, true); + f2fs_wait_on_page_writeback(page, DATA, true, true); zero_user(page, offset, PAGE_SIZE - offset); /* An encrypted inode should have a key and truncate the last page. */ @@ -575,10 +589,9 @@ truncate_out: return 0; } -int truncate_blocks(struct inode *inode, u64 from, bool lock) +int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - unsigned int blocksize = inode->i_sb->s_blocksize; struct dnode_of_data dn; pgoff_t free_from; int count = 0, err = 0; @@ -587,7 +600,7 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock) trace_f2fs_truncate_blocks_enter(inode, from); - free_from = (pgoff_t)F2FS_BYTES_TO_BLK(from + blocksize - 1); + free_from = (pgoff_t)F2FS_BLK_ALIGN(from); if (free_from >= sbi->max_file_blocks) goto free_partial; @@ -595,21 +608,21 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock) if (lock) f2fs_lock_op(sbi); - ipage = get_node_page(sbi, inode->i_ino); + ipage = f2fs_get_node_page(sbi, inode->i_ino); if (IS_ERR(ipage)) { err = PTR_ERR(ipage); goto out; } if (f2fs_has_inline_data(inode)) { - truncate_inline_inode(inode, ipage, from); + f2fs_truncate_inline_inode(inode, ipage, from); f2fs_put_page(ipage, 1); truncate_page = true; goto out; } set_new_dnode(&dn, inode, ipage, NULL, 0); - err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE_RA); + err = f2fs_get_dnode_of_data(&dn, free_from, LOOKUP_NODE_RA); if (err) { if (err == -ENOENT) goto free_next; @@ -622,13 +635,13 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock) f2fs_bug_on(sbi, count < 0); if (dn.ofs_in_node || IS_INODE(dn.node_page)) { - truncate_data_blocks_range(&dn, count); + f2fs_truncate_data_blocks_range(&dn, count); free_from += count; } f2fs_put_dnode(&dn); free_next: - err = truncate_inode_blocks(inode, free_from); + err = f2fs_truncate_inode_blocks(inode, free_from); out: if (lock) f2fs_unlock_op(sbi); @@ -645,18 +658,20 @@ int f2fs_truncate(struct inode *inode) { int err; + if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) + return -EIO; + if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))) return 0; trace_f2fs_truncate(inode); -#ifdef CONFIG_F2FS_FAULT_INJECTION if (time_to_inject(F2FS_I_SB(inode), FAULT_TRUNCATE)) { f2fs_show_injection_info(FAULT_TRUNCATE); return -EIO; } -#endif + /* we should check inline_data size */ if (!f2fs_may_inline_data(inode)) { err = f2fs_convert_inline_inode(inode); @@ -664,7 +679,7 @@ int f2fs_truncate(struct inode *inode) return err; } - err = truncate_blocks(inode, i_size_read(inode), true); + err = f2fs_truncate_blocks(inode, i_size_read(inode), true); if (err) return err; @@ -678,18 +693,27 @@ int f2fs_getattr(const struct path *path, struct kstat *stat, { struct inode *inode = d_inode(path->dentry); struct f2fs_inode_info *fi = F2FS_I(inode); + struct f2fs_inode *ri; unsigned int flags; - flags = fi->i_flags & (FS_FL_USER_VISIBLE | FS_PROJINHERIT_FL); - if (flags & FS_APPEND_FL) + if (f2fs_has_extra_attr(inode) && + f2fs_sb_has_inode_crtime(F2FS_I_SB(inode)) && + F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_crtime)) { + stat->result_mask |= STATX_BTIME; + stat->btime.tv_sec = fi->i_crtime.tv_sec; + stat->btime.tv_nsec = fi->i_crtime.tv_nsec; + } + + flags = fi->i_flags & F2FS_FL_USER_VISIBLE; + if (flags & F2FS_APPEND_FL) stat->attributes |= STATX_ATTR_APPEND; - if (flags & FS_COMPR_FL) + if (flags & F2FS_COMPR_FL) stat->attributes |= STATX_ATTR_COMPRESSED; if (f2fs_encrypted_inode(inode)) stat->attributes |= STATX_ATTR_ENCRYPTED; - if (flags & FS_IMMUTABLE_FL) + if (flags & F2FS_IMMUTABLE_FL) stat->attributes |= STATX_ATTR_IMMUTABLE; - if (flags & FS_NODUMP_FL) + if (flags & F2FS_NODUMP_FL) stat->attributes |= STATX_ATTR_NODUMP; stat->attributes_mask |= (STATX_ATTR_APPEND | @@ -742,12 +766,18 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); int err; - bool size_changed = false; + + if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) + return -EIO; err = setattr_prepare(dentry, attr); if (err) return err; + err = fscrypt_prepare_setattr(dentry, attr); + if (err) + return err; + if (is_quota_modification(inode, attr)) { err = dquot_initialize(inode); if (err) @@ -757,36 +787,47 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) !uid_eq(attr->ia_uid, inode->i_uid)) || (attr->ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid))) { + f2fs_lock_op(F2FS_I_SB(inode)); err = dquot_transfer(inode, attr); - if (err) + if (err) { + set_sbi_flag(F2FS_I_SB(inode), + SBI_QUOTA_NEED_REPAIR); + f2fs_unlock_op(F2FS_I_SB(inode)); return err; + } + /* + * update uid/gid under lock_op(), so that dquot and inode can + * be updated atomically. + */ + if (attr->ia_valid & ATTR_UID) + inode->i_uid = attr->ia_uid; + if (attr->ia_valid & ATTR_GID) + inode->i_gid = attr->ia_gid; + f2fs_mark_inode_dirty_sync(inode, true); + f2fs_unlock_op(F2FS_I_SB(inode)); } if (attr->ia_valid & ATTR_SIZE) { - if (f2fs_encrypted_inode(inode)) { - err = fscrypt_get_encryption_info(inode); - if (err) - return err; - if (!fscrypt_has_encryption_key(inode)) - return -ENOKEY; - } + bool to_smaller = (attr->ia_size <= i_size_read(inode)); - if (attr->ia_size <= i_size_read(inode)) { - down_write(&F2FS_I(inode)->i_mmap_sem); - truncate_setsize(inode, attr->ia_size); + down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + down_write(&F2FS_I(inode)->i_mmap_sem); + + truncate_setsize(inode, attr->ia_size); + + if (to_smaller) err = f2fs_truncate(inode); - up_write(&F2FS_I(inode)->i_mmap_sem); - if (err) - return err; - } else { - /* - * do not trim all blocks after i_size if target size is - * larger than i_size. - */ - down_write(&F2FS_I(inode)->i_mmap_sem); - truncate_setsize(inode, attr->ia_size); - up_write(&F2FS_I(inode)->i_mmap_sem); + /* + * do not trim all blocks after i_size if target size is + * larger than i_size. + */ + up_write(&F2FS_I(inode)->i_mmap_sem); + up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + if (err) + return err; + + if (!to_smaller) { /* should convert inline inode here */ if (!f2fs_may_inline_data(inode)) { err = f2fs_convert_inline_inode(inode); @@ -796,13 +837,15 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) inode->i_mtime = inode->i_ctime = current_time(inode); } - size_changed = true; + down_write(&F2FS_I(inode)->i_sem); + F2FS_I(inode)->last_disk_size = i_size_read(inode); + up_write(&F2FS_I(inode)->i_sem); } __setattr_copy(inode, attr); if (attr->ia_valid & ATTR_MODE) { - err = posix_acl_chmod(inode, get_inode_mode(inode)); + err = posix_acl_chmod(inode, f2fs_get_inode_mode(inode)); if (err || is_inode_flag_set(inode, FI_ACL_MODE)) { inode->i_mode = F2FS_I(inode)->i_acl_mode; clear_inode_flag(inode, FI_ACL_MODE); @@ -810,7 +853,7 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) } /* file size may changed here */ - f2fs_mark_inode_dirty_sync(inode, size_changed); + f2fs_mark_inode_dirty_sync(inode, true); /* inode change will produce dirty node pages flushed by checkpoint */ f2fs_balance_fs(F2FS_I_SB(inode), true); @@ -841,20 +884,20 @@ static int fill_zero(struct inode *inode, pgoff_t index, f2fs_balance_fs(sbi, true); f2fs_lock_op(sbi); - page = get_new_data_page(inode, NULL, index, false); + page = f2fs_get_new_data_page(inode, NULL, index, false); f2fs_unlock_op(sbi); if (IS_ERR(page)) return PTR_ERR(page); - f2fs_wait_on_page_writeback(page, DATA, true); + f2fs_wait_on_page_writeback(page, DATA, true, true); zero_user(page, start, len); set_page_dirty(page); f2fs_put_page(page, 1); return 0; } -int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end) +int f2fs_truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end) { int err; @@ -863,10 +906,11 @@ int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end) pgoff_t end_offset, count; set_new_dnode(&dn, inode, NULL, NULL, 0); - err = get_dnode_of_data(&dn, pg_start, LOOKUP_NODE); + err = f2fs_get_dnode_of_data(&dn, pg_start, LOOKUP_NODE); if (err) { if (err == -ENOENT) { - pg_start++; + pg_start = f2fs_get_next_page_offset(&dn, + pg_start); continue; } return err; @@ -877,7 +921,7 @@ int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end) f2fs_bug_on(F2FS_I_SB(inode), count == 0 || count > end_offset); - truncate_data_blocks_range(&dn, count); + f2fs_truncate_data_blocks_range(&dn, count); f2fs_put_dnode(&dn); pg_start += count; @@ -928,14 +972,19 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) blk_start = (loff_t)pg_start << PAGE_SHIFT; blk_end = (loff_t)pg_end << PAGE_SHIFT; + + down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); down_write(&F2FS_I(inode)->i_mmap_sem); + truncate_inode_pages_range(mapping, blk_start, blk_end - 1); f2fs_lock_op(sbi); - ret = truncate_hole(inode, pg_start, pg_end); + ret = f2fs_truncate_hole(inode, pg_start, pg_end); f2fs_unlock_op(sbi); + up_write(&F2FS_I(inode)->i_mmap_sem); + up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); } } @@ -951,7 +1000,7 @@ static int __read_out_blkaddrs(struct inode *inode, block_t *blkaddr, next_dnode: set_new_dnode(&dn, inode, NULL, NULL, 0); - ret = get_dnode_of_data(&dn, off, LOOKUP_NODE_RA); + ret = f2fs_get_dnode_of_data(&dn, off, LOOKUP_NODE_RA); if (ret && ret != -ENOENT) { return ret; } else if (ret == -ENOENT) { @@ -968,7 +1017,7 @@ next_dnode: for (i = 0; i < done; i++, blkaddr++, do_replace++, dn.ofs_in_node++) { *blkaddr = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node); - if (!is_checkpointed_data(sbi, *blkaddr)) { + if (!f2fs_is_checkpointed_data(sbi, *blkaddr)) { if (test_opt(sbi, LFS)) { f2fs_put_dnode(&dn); @@ -1001,10 +1050,10 @@ static int __roll_back_blkaddrs(struct inode *inode, block_t *blkaddr, continue; set_new_dnode(&dn, inode, NULL, NULL, 0); - ret = get_dnode_of_data(&dn, off + i, LOOKUP_NODE_RA); + ret = f2fs_get_dnode_of_data(&dn, off + i, LOOKUP_NODE_RA); if (ret) { dec_valid_block_count(sbi, inode, 1); - invalidate_blocks(sbi, *blkaddr); + f2fs_invalidate_blocks(sbi, *blkaddr); } else { f2fs_update_data_blkaddr(&dn, *blkaddr); } @@ -1034,18 +1083,23 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode, pgoff_t ilen; set_new_dnode(&dn, dst_inode, NULL, NULL, 0); - ret = get_dnode_of_data(&dn, dst + i, ALLOC_NODE); + ret = f2fs_get_dnode_of_data(&dn, dst + i, ALLOC_NODE); if (ret) return ret; - get_node_info(sbi, dn.nid, &ni); + ret = f2fs_get_node_info(sbi, dn.nid, &ni); + if (ret) { + f2fs_put_dnode(&dn); + return ret; + } + ilen = min((pgoff_t) ADDRS_PER_PAGE(dn.node_page, dst_inode) - dn.ofs_in_node, len - i); do { dn.data_blkaddr = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node); - truncate_data_blocks_range(&dn, 1); + f2fs_truncate_data_blocks_range(&dn, 1); if (do_replace[i]) { f2fs_i_blocks_write(src_inode, @@ -1068,10 +1122,11 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode, } else { struct page *psrc, *pdst; - psrc = get_lock_data_page(src_inode, src + i, true); + psrc = f2fs_get_lock_data_page(src_inode, + src + i, true); if (IS_ERR(psrc)) return PTR_ERR(psrc); - pdst = get_new_data_page(dst_inode, NULL, dst + i, + pdst = f2fs_get_new_data_page(dst_inode, NULL, dst + i, true); if (IS_ERR(pdst)) { f2fs_put_page(psrc, 1); @@ -1082,7 +1137,8 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode, f2fs_put_page(pdst, 1); f2fs_put_page(psrc, 1); - ret = truncate_hole(src_inode, src + i, src + i + 1); + ret = f2fs_truncate_hole(src_inode, + src + i, src + i + 1); if (ret) return ret; i++; @@ -1103,11 +1159,15 @@ static int __exchange_data_block(struct inode *src_inode, while (len) { olen = min((pgoff_t)4 * ADDRS_PER_BLOCK, len); - src_blkaddr = kvzalloc(sizeof(block_t) * olen, GFP_KERNEL); + src_blkaddr = f2fs_kvzalloc(F2FS_I_SB(src_inode), + array_size(olen, sizeof(block_t)), + GFP_KERNEL); if (!src_blkaddr) return -ENOMEM; - do_replace = kvzalloc(sizeof(int) * olen, GFP_KERNEL); + do_replace = f2fs_kvzalloc(F2FS_I_SB(src_inode), + array_size(olen, sizeof(int)), + GFP_KERNEL); if (!do_replace) { kvfree(src_blkaddr); return -ENOMEM; @@ -1133,31 +1193,39 @@ static int __exchange_data_block(struct inode *src_inode, return 0; roll_back: - __roll_back_blkaddrs(src_inode, src_blkaddr, do_replace, src, len); + __roll_back_blkaddrs(src_inode, src_blkaddr, do_replace, src, olen); kvfree(src_blkaddr); kvfree(do_replace); return ret; } -static int f2fs_do_collapse(struct inode *inode, pgoff_t start, pgoff_t end) +static int f2fs_do_collapse(struct inode *inode, loff_t offset, loff_t len) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); pgoff_t nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE; + pgoff_t start = offset >> PAGE_SHIFT; + pgoff_t end = (offset + len) >> PAGE_SHIFT; int ret; f2fs_balance_fs(sbi, true); - f2fs_lock_op(sbi); - f2fs_drop_extent_tree(inode); + /* avoid gc operation during block exchange */ + down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + down_write(&F2FS_I(inode)->i_mmap_sem); + f2fs_lock_op(sbi); + f2fs_drop_extent_tree(inode); + truncate_pagecache(inode, offset); ret = __exchange_data_block(inode, inode, end, start, nrpages - end, true); f2fs_unlock_op(sbi); + + up_write(&F2FS_I(inode)->i_mmap_sem); + up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); return ret; } static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len) { - pgoff_t pg_start, pg_end; loff_t new_size; int ret; @@ -1172,34 +1240,27 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len) if (ret) return ret; - pg_start = offset >> PAGE_SHIFT; - pg_end = (offset + len) >> PAGE_SHIFT; - - down_write(&F2FS_I(inode)->i_mmap_sem); /* write out all dirty pages from offset */ ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); if (ret) - goto out; - - truncate_pagecache(inode, offset); + return ret; - ret = f2fs_do_collapse(inode, pg_start, pg_end); + ret = f2fs_do_collapse(inode, offset, len); if (ret) - goto out; + return ret; /* write out all moved pages, if possible */ + down_write(&F2FS_I(inode)->i_mmap_sem); filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); truncate_pagecache(inode, offset); new_size = i_size_read(inode) - len; truncate_pagecache(inode, new_size); - ret = truncate_blocks(inode, new_size, true); + ret = f2fs_truncate_blocks(inode, new_size, true); + up_write(&F2FS_I(inode)->i_mmap_sem); if (!ret) f2fs_i_size_write(inode, new_size); - -out: - up_write(&F2FS_I(inode)->i_mmap_sem); return ret; } @@ -1219,7 +1280,7 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start, } dn->ofs_in_node = ofs_in_node; - ret = reserve_new_blocks(dn, count); + ret = f2fs_reserve_new_blocks(dn, count); if (ret) return ret; @@ -1228,7 +1289,7 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start, dn->data_blkaddr = datablock_addr(dn->inode, dn->node_page, dn->ofs_in_node); /* - * reserve_new_blocks will not guarantee entire block + * f2fs_reserve_new_blocks will not guarantee entire block * allocation. */ if (dn->data_blkaddr == NULL_ADDR) { @@ -1236,9 +1297,9 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start, break; } if (dn->data_blkaddr != NEW_ADDR) { - invalidate_blocks(sbi, dn->data_blkaddr); + f2fs_invalidate_blocks(sbi, dn->data_blkaddr); dn->data_blkaddr = NEW_ADDR; - set_data_blkaddr(dn); + f2fs_set_data_blkaddr(dn); } } @@ -1265,12 +1326,9 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, if (ret) return ret; - down_write(&F2FS_I(inode)->i_mmap_sem); ret = filemap_write_and_wait_range(mapping, offset, offset + len - 1); if (ret) - goto out_sem; - - truncate_pagecache_range(inode, offset, offset + len - 1); + return ret; pg_start = ((unsigned long long) offset) >> PAGE_SHIFT; pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT; @@ -1282,7 +1340,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, ret = fill_zero(inode, pg_start, off_start, off_end - off_start); if (ret) - goto out_sem; + return ret; new_size = max_t(loff_t, new_size, offset + len); } else { @@ -1290,7 +1348,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, ret = fill_zero(inode, pg_start++, off_start, PAGE_SIZE - off_start); if (ret) - goto out_sem; + return ret; new_size = max_t(loff_t, new_size, (loff_t)pg_start << PAGE_SHIFT); @@ -1301,12 +1359,21 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, unsigned int end_offset; pgoff_t end; + down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + down_write(&F2FS_I(inode)->i_mmap_sem); + + truncate_pagecache_range(inode, + (loff_t)index << PAGE_SHIFT, + ((loff_t)pg_end << PAGE_SHIFT) - 1); + f2fs_lock_op(sbi); set_new_dnode(&dn, inode, NULL, NULL, 0); - ret = get_dnode_of_data(&dn, index, ALLOC_NODE); + ret = f2fs_get_dnode_of_data(&dn, index, ALLOC_NODE); if (ret) { f2fs_unlock_op(sbi); + up_write(&F2FS_I(inode)->i_mmap_sem); + up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); goto out; } @@ -1315,7 +1382,10 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, ret = f2fs_do_zero_range(&dn, index, end); f2fs_put_dnode(&dn); + f2fs_unlock_op(sbi); + up_write(&F2FS_I(inode)->i_mmap_sem); + up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); f2fs_balance_fs(sbi, dn.node_changed); @@ -1343,9 +1413,6 @@ out: else f2fs_i_size_write(inode, new_size); } -out_sem: - up_write(&F2FS_I(inode)->i_mmap_sem); - return ret; } @@ -1375,22 +1442,26 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) f2fs_balance_fs(sbi, true); down_write(&F2FS_I(inode)->i_mmap_sem); - ret = truncate_blocks(inode, i_size_read(inode), true); + ret = f2fs_truncate_blocks(inode, i_size_read(inode), true); + up_write(&F2FS_I(inode)->i_mmap_sem); if (ret) - goto out; + return ret; /* write out all dirty pages from offset */ ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); if (ret) - goto out; - - truncate_pagecache(inode, offset); + return ret; pg_start = offset >> PAGE_SHIFT; pg_end = (offset + len) >> PAGE_SHIFT; delta = pg_end - pg_start; idx = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE; + /* avoid gc operation during block exchange */ + down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + down_write(&F2FS_I(inode)->i_mmap_sem); + truncate_pagecache(inode, offset); + while (!ret && idx > pg_start) { nr = idx - pg_start; if (nr > delta) @@ -1404,15 +1475,17 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) idx + delta, nr, false); f2fs_unlock_op(sbi); } + up_write(&F2FS_I(inode)->i_mmap_sem); + up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); /* write out all moved pages, if possible */ + down_write(&F2FS_I(inode)->i_mmap_sem); filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); truncate_pagecache(inode, offset); + up_write(&F2FS_I(inode)->i_mmap_sem); if (!ret) f2fs_i_size_write(inode, new_size); -out: - up_write(&F2FS_I(inode)->i_mmap_sem); return ret; } @@ -1420,7 +1493,9 @@ static int expand_inode_data(struct inode *inode, loff_t offset, loff_t len, int mode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct f2fs_map_blocks map = { .m_next_pgofs = NULL }; + struct f2fs_map_blocks map = { .m_next_pgofs = NULL, + .m_next_extent = NULL, .m_seg_type = NO_CHECK_TYPE, + .m_may_create = true }; pgoff_t pg_end; loff_t new_size = i_size_read(inode); loff_t off_end; @@ -1454,14 +1529,18 @@ static int expand_inode_data(struct inode *inode, loff_t offset, last_off = map.m_lblk + map.m_len - 1; /* update new size to the failed position */ - new_size = (last_off == pg_end) ? offset + len: + new_size = (last_off == pg_end) ? offset + len : (loff_t)(last_off + 1) << PAGE_SHIFT; } else { new_size = ((loff_t)pg_end << PAGE_SHIFT) + off_end; } - if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size) - f2fs_i_size_write(inode, new_size); + if (new_size > i_size_read(inode)) { + if (mode & FALLOC_FL_KEEP_SIZE) + file_set_keep_isize(inode); + else + f2fs_i_size_write(inode, new_size); + } return err; } @@ -1472,6 +1551,9 @@ static long f2fs_fallocate(struct file *file, int mode, struct inode *inode = file_inode(file); long ret = 0; + if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) + return -EIO; + /* f2fs only support ->fallocate for regular file */ if (!S_ISREG(inode->i_mode)) return -EINVAL; @@ -1505,8 +1587,6 @@ static long f2fs_fallocate(struct file *file, int mode, if (!ret) { inode->i_mtime = inode->i_ctime = current_time(inode); f2fs_mark_inode_dirty_sync(inode, false); - if (mode & FALLOC_FL_KEEP_SIZE) - file_set_keep_isize(inode); f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); } @@ -1529,13 +1609,13 @@ static int f2fs_release_file(struct inode *inode, struct file *filp) /* some remained atomic pages should discarded */ if (f2fs_is_atomic_file(inode)) - drop_inmem_pages(inode); + f2fs_drop_inmem_pages(inode); if (f2fs_is_volatile_file(inode)) { - clear_inode_flag(inode, FI_VOLATILE_FILE); - stat_dec_volatile_write(inode); set_inode_flag(inode, FI_DROP_CACHE); filemap_fdatawrite(inode->i_mapping); clear_inode_flag(inode, FI_DROP_CACHE); + clear_inode_flag(inode, FI_VOLATILE_FILE); + stat_dec_volatile_write(inode); } return 0; } @@ -1552,7 +1632,7 @@ static int f2fs_file_flush(struct file *file, fl_owner_t id) */ if (f2fs_is_atomic_file(inode) && F2FS_I(inode)->inmem_task == current) - drop_inmem_pages(inode); + f2fs_drop_inmem_pages(inode); return 0; } @@ -1560,8 +1640,17 @@ static int f2fs_ioc_getflags(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_inode_info *fi = F2FS_I(inode); - unsigned int flags = fi->i_flags & - (FS_FL_USER_VISIBLE | FS_PROJINHERIT_FL); + unsigned int flags = fi->i_flags; + + if (f2fs_encrypted_inode(inode)) + flags |= F2FS_ENCRYPT_FL; + if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode)) + flags |= F2FS_INLINE_DATA_FL; + if (is_inode_flag_set(inode, FI_PIN_FILE)) + flags |= F2FS_NOCOW_FL; + + flags &= F2FS_FL_USER_VISIBLE; + return put_user(flags, (int __user *)arg); } @@ -1578,15 +1667,15 @@ static int __f2fs_ioc_setflags(struct inode *inode, unsigned int flags) oldflags = fi->i_flags; - if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) + if ((flags ^ oldflags) & (F2FS_APPEND_FL | F2FS_IMMUTABLE_FL)) if (!capable(CAP_LINUX_IMMUTABLE)) return -EPERM; - flags = flags & (FS_FL_USER_MODIFIABLE | FS_PROJINHERIT_FL); - flags |= oldflags & ~(FS_FL_USER_MODIFIABLE | FS_PROJINHERIT_FL); + flags = flags & F2FS_FL_USER_MODIFIABLE; + flags |= oldflags & ~F2FS_FL_USER_MODIFIABLE; fi->i_flags = flags; - if (fi->i_flags & FS_PROJINHERIT_FL) + if (fi->i_flags & F2FS_PROJINHERIT_FL) set_inode_flag(inode, FI_PROJ_INHERIT); else clear_inode_flag(inode, FI_PROJ_INHERIT); @@ -1646,38 +1735,41 @@ static int f2fs_ioc_start_atomic_write(struct file *filp) inode_lock(inode); - down_write(&F2FS_I(inode)->dio_rwsem[WRITE]); - - if (f2fs_is_atomic_file(inode)) + if (f2fs_is_atomic_file(inode)) { + if (is_inode_flag_set(inode, FI_ATOMIC_REVOKE_REQUEST)) + ret = -EINVAL; goto out; + } ret = f2fs_convert_inline_inode(inode); if (ret) goto out; - set_inode_flag(inode, FI_ATOMIC_FILE); - set_inode_flag(inode, FI_HOT_DATA); - f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); - - if (!get_dirty_pages(inode)) - goto inc_stat; + down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); - f2fs_msg(F2FS_I_SB(inode)->sb, KERN_WARNING, + /* + * Should wait end_io to count F2FS_WB_CP_DATA correctly by + * f2fs_is_atomic_file. + */ + if (get_dirty_pages(inode)) + f2fs_msg(F2FS_I_SB(inode)->sb, KERN_WARNING, "Unexpected flush for atomic writes: ino=%lu, npages=%u", inode->i_ino, get_dirty_pages(inode)); ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX); if (ret) { - clear_inode_flag(inode, FI_ATOMIC_FILE); - clear_inode_flag(inode, FI_HOT_DATA); + up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); goto out; } -inc_stat: + set_inode_flag(inode, FI_ATOMIC_FILE); + clear_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST); + up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); F2FS_I(inode)->inmem_task = current; stat_inc_atomic_write(inode); stat_update_max_atomic_write(inode); out: - up_write(&F2FS_I(inode)->dio_rwsem[WRITE]); inode_unlock(inode); mnt_drop_write_file(filp); return ret; @@ -1695,26 +1787,34 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp) if (ret) return ret; + f2fs_balance_fs(F2FS_I_SB(inode), true); + inode_lock(inode); - if (f2fs_is_volatile_file(inode)) + if (f2fs_is_volatile_file(inode)) { + ret = -EINVAL; goto err_out; + } if (f2fs_is_atomic_file(inode)) { - ret = commit_inmem_pages(inode); + ret = f2fs_commit_inmem_pages(inode); if (ret) goto err_out; ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true); if (!ret) { clear_inode_flag(inode, FI_ATOMIC_FILE); - clear_inode_flag(inode, FI_HOT_DATA); + F2FS_I(inode)->i_gc_failures[GC_FAILURE_ATOMIC] = 0; stat_dec_atomic_write(inode); } } else { ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 1, false); } err_out: + if (is_inode_flag_set(inode, FI_ATOMIC_REVOKE_REQUEST)) { + clear_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST); + ret = -EINVAL; + } inode_unlock(inode); mnt_drop_write_file(filp); return ret; @@ -1799,13 +1899,15 @@ static int f2fs_ioc_abort_volatile_write(struct file *filp) inode_lock(inode); if (f2fs_is_atomic_file(inode)) - drop_inmem_pages(inode); + f2fs_drop_inmem_pages(inode); if (f2fs_is_volatile_file(inode)) { clear_inode_flag(inode, FI_VOLATILE_FILE); stat_dec_volatile_write(inode); ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true); } + clear_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST); + inode_unlock(inode); mnt_drop_write_file(filp); @@ -1836,31 +1938,58 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) switch (in) { case F2FS_GOING_DOWN_FULLSYNC: sb = freeze_bdev(sb->s_bdev); - if (sb && !IS_ERR(sb)) { + if (IS_ERR(sb)) { + ret = PTR_ERR(sb); + goto out; + } + if (sb) { f2fs_stop_checkpoint(sbi, false); + set_sbi_flag(sbi, SBI_IS_SHUTDOWN); thaw_bdev(sb->s_bdev, sb); } break; case F2FS_GOING_DOWN_METASYNC: /* do checkpoint only */ - f2fs_sync_fs(sb, 1); + ret = f2fs_sync_fs(sb, 1); + if (ret) + goto out; f2fs_stop_checkpoint(sbi, false); + set_sbi_flag(sbi, SBI_IS_SHUTDOWN); break; case F2FS_GOING_DOWN_NOSYNC: f2fs_stop_checkpoint(sbi, false); + set_sbi_flag(sbi, SBI_IS_SHUTDOWN); break; case F2FS_GOING_DOWN_METAFLUSH: - sync_meta_pages(sbi, META, LONG_MAX, FS_META_IO); + f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_META_IO); f2fs_stop_checkpoint(sbi, false); + set_sbi_flag(sbi, SBI_IS_SHUTDOWN); break; + case F2FS_GOING_DOWN_NEED_FSCK: + set_sbi_flag(sbi, SBI_NEED_FSCK); + set_sbi_flag(sbi, SBI_CP_DISABLED_QUICK); + set_sbi_flag(sbi, SBI_IS_DIRTY); + /* do checkpoint only */ + ret = f2fs_sync_fs(sb, 1); + goto out; default: ret = -EINVAL; goto out; } + + f2fs_stop_gc_thread(sbi); + f2fs_stop_discard_thread(sbi); + + f2fs_drop_discard_cmd(sbi); + clear_opt(sbi, DISCARD); + f2fs_update_time(sbi, REQ_TIME); out: if (in != F2FS_GOING_DOWN_FULLSYNC) mnt_drop_write_file(filp); + + trace_f2fs_shutdown(sbi, in, ret); + return ret; } @@ -1875,7 +2004,7 @@ static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg) if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!blk_queue_discard(q)) + if (!f2fs_hw_support_discard(F2FS_SB(sb))) return -EOPNOTSUPP; if (copy_from_user(&range, (struct fstrim_range __user *)arg, @@ -1914,6 +2043,9 @@ static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); + if (!f2fs_sb_has_encrypt(F2FS_I_SB(inode))) + return -EOPNOTSUPP; + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return fscrypt_ioctl_set_policy(filp, (const void __user *)arg); @@ -1921,6 +2053,8 @@ static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg) static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg) { + if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp)))) + return -EOPNOTSUPP; return fscrypt_ioctl_get_policy(filp, (void __user *)arg); } @@ -1930,16 +2064,18 @@ static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg) struct f2fs_sb_info *sbi = F2FS_I_SB(inode); int err; - if (!f2fs_sb_has_crypto(inode->i_sb)) + if (!f2fs_sb_has_encrypt(sbi)) return -EOPNOTSUPP; - if (uuid_is_nonzero(sbi->raw_super->encrypt_pw_salt)) - goto got_it; - err = mnt_want_write_file(filp); if (err) return err; + down_write(&sbi->sb_lock); + + if (uuid_is_nonzero(sbi->raw_super->encrypt_pw_salt)) + goto got_it; + /* update superblock with uuid */ generate_random_uuid(sbi->raw_super->encrypt_pw_salt); @@ -1947,15 +2083,16 @@ static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg) if (err) { /* undo new data */ memset(sbi->raw_super->encrypt_pw_salt, 0, 16); - mnt_drop_write_file(filp); - return err; + goto out_err; } - mnt_drop_write_file(filp); got_it: if (copy_to_user((__u8 __user *)arg, sbi->raw_super->encrypt_pw_salt, 16)) - return -EFAULT; - return 0; + err = -EFAULT; +out_err: + up_write(&sbi->sb_lock); + mnt_drop_write_file(filp); + return err; } static int f2fs_ioc_gc(struct file *filp, unsigned long arg) @@ -2011,13 +2148,15 @@ static int f2fs_ioc_gc_range(struct file *filp, unsigned long arg) if (f2fs_readonly(sbi->sb)) return -EROFS; + end = range.start + range.len; + if (range.start < MAIN_BLKADDR(sbi) || end >= MAX_BLKADDR(sbi)) { + return -EINVAL; + } + ret = mnt_want_write_file(filp); if (ret) return ret; - end = range.start + range.len; - if (range.start < MAIN_BLKADDR(sbi) || end >= MAX_BLKADDR(sbi)) - return -EINVAL; do_more: if (!range.sync) { if (!mutex_trylock(&sbi->gc_mutex)) { @@ -2049,6 +2188,12 @@ static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg) if (f2fs_readonly(sbi->sb)) return -EROFS; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + f2fs_msg(sbi->sb, KERN_INFO, + "Skipping Checkpoint. Checkpoints currently disabled."); + return -EINVAL; + } + ret = mnt_want_write_file(filp); if (ret) return ret; @@ -2064,9 +2209,11 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi, struct f2fs_defragment *range) { struct inode *inode = file_inode(filp); - struct f2fs_map_blocks map = { .m_next_pgofs = NULL }; - struct extent_info ei = {0,0,0}; - pgoff_t pg_start, pg_end; + struct f2fs_map_blocks map = { .m_next_extent = NULL, + .m_seg_type = NO_CHECK_TYPE , + .m_may_create = false }; + struct extent_info ei = {0, 0, 0}; + pgoff_t pg_start, pg_end, next_pgofs; unsigned int blk_per_seg = sbi->blocks_per_seg; unsigned int total = 0, sec_num; block_t blk_end = 0; @@ -2074,7 +2221,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi, int err; /* if in-place-update policy is enabled, don't waste time here */ - if (need_inplace_update_policy(inode, NULL)) + if (f2fs_should_update_inplace(inode, NULL)) return -EINVAL; pg_start = range->start >> PAGE_SHIFT; @@ -2100,6 +2247,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi, } map.m_lblk = pg_start; + map.m_next_pgofs = &next_pgofs; /* * lookup mapping info in dnode page cache, skip defragmenting if all @@ -2113,14 +2261,16 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi, goto out; if (!(map.m_flags & F2FS_MAP_FLAGS)) { - map.m_lblk++; + map.m_lblk = next_pgofs; continue; } - if (blk_end && blk_end != map.m_pblk) { + if (blk_end && blk_end != map.m_pblk) fragmented = true; - break; - } + + /* record total count of block that we're going to move */ + total += map.m_len; + blk_end = map.m_pblk + map.m_len; map.m_lblk += map.m_len; @@ -2129,10 +2279,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi, if (!fragmented) goto out; - map.m_lblk = pg_start; - map.m_len = pg_end - pg_start; - - sec_num = (map.m_len + BLKS_PER_SEC(sbi) - 1) / BLKS_PER_SEC(sbi); + sec_num = (total + BLKS_PER_SEC(sbi) - 1) / BLKS_PER_SEC(sbi); /* * make sure there are enough free section for LFS allocation, this can @@ -2144,6 +2291,10 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi, goto out; } + map.m_lblk = pg_start; + map.m_len = pg_end - pg_start; + total = 0; + while (map.m_lblk < pg_end) { pgoff_t idx; int cnt = 0; @@ -2155,7 +2306,7 @@ do_map: goto clear_out; if (!(map.m_flags & F2FS_MAP_FLAGS)) { - map.m_lblk++; + map.m_lblk = next_pgofs; continue; } @@ -2165,7 +2316,7 @@ do_map: while (idx < map.m_lblk + map.m_len && cnt < blk_per_seg) { struct page *page; - page = get_lock_data_page(inode, idx, true); + page = f2fs_get_lock_data_page(inode, idx, true); if (IS_ERR(page)) { err = PTR_ERR(page); goto clear_out; @@ -2277,10 +2428,9 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, inode_lock(src); if (src != dst) { - if (!inode_trylock(dst)) { - ret = -EBUSY; + ret = -EBUSY; + if (!inode_trylock(dst)) goto out; - } } ret = -EINVAL; @@ -2325,6 +2475,14 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, goto out_unlock; f2fs_balance_fs(sbi, true); + + down_write(&F2FS_I(src)->i_gc_rwsem[WRITE]); + if (src != dst) { + ret = -EBUSY; + if (!down_write_trylock(&F2FS_I(dst)->i_gc_rwsem[WRITE])) + goto out_src; + } + f2fs_lock_op(sbi); ret = __exchange_data_block(src, dst, pos_in >> F2FS_BLKSIZE_BITS, pos_out >> F2FS_BLKSIZE_BITS, @@ -2337,6 +2495,11 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, f2fs_i_size_write(dst, dst_osize); } f2fs_unlock_op(sbi); + + if (src != dst) + up_write(&F2FS_I(dst)->i_gc_rwsem[WRITE]); +out_src: + up_write(&F2FS_I(src)->i_gc_rwsem[WRITE]); out_unlock: if (src != dst) inode_unlock(dst); @@ -2403,12 +2566,15 @@ static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg) if (f2fs_readonly(sbi->sb)) return -EROFS; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + return -EINVAL; + if (copy_from_user(&range, (struct f2fs_flush_device __user *)arg, sizeof(range))) return -EFAULT; - if (!f2fs_is_multi_device(sbi) || sbi->s_ndevs - 1 <= range.dev_num || - sbi->segs_per_sec != 1) { + if (sbi->s_ndevs <= 1 || sbi->s_ndevs - 1 <= range.dev_num || + __is_large_section(sbi)) { f2fs_msg(sbi->sb, KERN_WARNING, "Can't flush %u in %d for segs_per_sec %u != 1\n", range.dev_num, sbi->s_ndevs, @@ -2461,18 +2627,33 @@ static int f2fs_ioc_get_features(struct file *filp, unsigned long arg) } #ifdef CONFIG_QUOTA +int f2fs_transfer_project_quota(struct inode *inode, kprojid_t kprojid) +{ + struct dquot *transfer_to[MAXQUOTAS] = {}; + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct super_block *sb = sbi->sb; + int err = 0; + + transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid)); + if (!IS_ERR(transfer_to[PRJQUOTA])) { + err = __dquot_transfer(inode, transfer_to); + if (err) + set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + dqput(transfer_to[PRJQUOTA]); + } + return err; +} + static int f2fs_ioc_setproject(struct file *filp, __u32 projid) { struct inode *inode = file_inode(filp); struct f2fs_inode_info *fi = F2FS_I(inode); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct super_block *sb = sbi->sb; - struct dquot *transfer_to[MAXQUOTAS] = {}; struct page *ipage; kprojid_t kprojid; int err; - if (!f2fs_sb_has_project_quota(sb)) { + if (!f2fs_sb_has_project_quota(sbi)) { if (projid != F2FS_DEF_PROJID) return -EOPNOTSUPP; else @@ -2487,53 +2668,45 @@ static int f2fs_ioc_setproject(struct file *filp, __u32 projid) if (projid_eq(kprojid, F2FS_I(inode)->i_projid)) return 0; - err = mnt_want_write_file(filp); - if (err) - return err; - err = -EPERM; - inode_lock(inode); - /* Is it quota file? Do not allow user to mess with it */ if (IS_NOQUOTA(inode)) - goto out_unlock; + return err; - ipage = get_node_page(sbi, inode->i_ino); - if (IS_ERR(ipage)) { - err = PTR_ERR(ipage); - goto out_unlock; - } + ipage = f2fs_get_node_page(sbi, inode->i_ino); + if (IS_ERR(ipage)) + return PTR_ERR(ipage); if (!F2FS_FITS_IN_INODE(F2FS_INODE(ipage), fi->i_extra_isize, i_projid)) { err = -EOVERFLOW; f2fs_put_page(ipage, 1); - goto out_unlock; + return err; } f2fs_put_page(ipage, 1); err = dquot_initialize(inode); if (err) - goto out_unlock; + return err; - transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid)); - if (!IS_ERR(transfer_to[PRJQUOTA])) { - err = __dquot_transfer(inode, transfer_to); - dqput(transfer_to[PRJQUOTA]); - if (err) - goto out_dirty; - } + f2fs_lock_op(sbi); + err = f2fs_transfer_project_quota(inode, kprojid); + if (err) + goto out_unlock; F2FS_I(inode)->i_projid = kprojid; inode->i_ctime = current_time(inode); -out_dirty: f2fs_mark_inode_dirty_sync(inode, true); out_unlock: - inode_unlock(inode); - mnt_drop_write_file(filp); + f2fs_unlock_op(sbi); return err; } #else +int f2fs_transfer_project_quota(struct inode *inode, kprojid_t kprojid) +{ + return 0; +} + static int f2fs_ioc_setproject(struct file *filp, __u32 projid) { if (projid != F2FS_DEF_PROJID) @@ -2547,17 +2720,17 @@ static inline __u32 f2fs_iflags_to_xflags(unsigned long iflags) { __u32 xflags = 0; - if (iflags & FS_SYNC_FL) + if (iflags & F2FS_SYNC_FL) xflags |= FS_XFLAG_SYNC; - if (iflags & FS_IMMUTABLE_FL) + if (iflags & F2FS_IMMUTABLE_FL) xflags |= FS_XFLAG_IMMUTABLE; - if (iflags & FS_APPEND_FL) + if (iflags & F2FS_APPEND_FL) xflags |= FS_XFLAG_APPEND; - if (iflags & FS_NODUMP_FL) + if (iflags & F2FS_NODUMP_FL) xflags |= FS_XFLAG_NODUMP; - if (iflags & FS_NOATIME_FL) + if (iflags & F2FS_NOATIME_FL) xflags |= FS_XFLAG_NOATIME; - if (iflags & FS_PROJINHERIT_FL) + if (iflags & F2FS_PROJINHERIT_FL) xflags |= FS_XFLAG_PROJINHERIT; return xflags; } @@ -2566,31 +2739,23 @@ static inline __u32 f2fs_iflags_to_xflags(unsigned long iflags) FS_XFLAG_APPEND | FS_XFLAG_NODUMP | \ FS_XFLAG_NOATIME | FS_XFLAG_PROJINHERIT) -/* Flags we can manipulate with through EXT4_IOC_FSSETXATTR */ -#define F2FS_FL_XFLAG_VISIBLE (FS_SYNC_FL | \ - FS_IMMUTABLE_FL | \ - FS_APPEND_FL | \ - FS_NODUMP_FL | \ - FS_NOATIME_FL | \ - FS_PROJINHERIT_FL) - /* Transfer xflags flags to internal */ static inline unsigned long f2fs_xflags_to_iflags(__u32 xflags) { unsigned long iflags = 0; if (xflags & FS_XFLAG_SYNC) - iflags |= FS_SYNC_FL; + iflags |= F2FS_SYNC_FL; if (xflags & FS_XFLAG_IMMUTABLE) - iflags |= FS_IMMUTABLE_FL; + iflags |= F2FS_IMMUTABLE_FL; if (xflags & FS_XFLAG_APPEND) - iflags |= FS_APPEND_FL; + iflags |= F2FS_APPEND_FL; if (xflags & FS_XFLAG_NODUMP) - iflags |= FS_NODUMP_FL; + iflags |= F2FS_NODUMP_FL; if (xflags & FS_XFLAG_NOATIME) - iflags |= FS_NOATIME_FL; + iflags |= F2FS_NOATIME_FL; if (xflags & FS_XFLAG_PROJINHERIT) - iflags |= FS_PROJINHERIT_FL; + iflags |= F2FS_PROJINHERIT_FL; return iflags; } @@ -2603,9 +2768,9 @@ static int f2fs_ioc_fsgetxattr(struct file *filp, unsigned long arg) memset(&fa, 0, sizeof(struct fsxattr)); fa.fsx_xflags = f2fs_iflags_to_xflags(fi->i_flags & - (FS_FL_USER_VISIBLE | FS_PROJINHERIT_FL)); + F2FS_FL_USER_VISIBLE); - if (f2fs_sb_has_project_quota(inode->i_sb)) + if (f2fs_sb_has_project_quota(F2FS_I_SB(inode))) fa.fsx_projid = (__u32)from_kprojid(&init_user_ns, fi->i_projid); @@ -2614,6 +2779,30 @@ static int f2fs_ioc_fsgetxattr(struct file *filp, unsigned long arg) return 0; } +static int f2fs_ioctl_check_project(struct inode *inode, struct fsxattr *fa) +{ + /* + * Project Quota ID state is only allowed to change from within the init + * namespace. Enforce that restriction only if we are trying to change + * the quota ID state. Everything else is allowed in user namespaces. + */ + if (current_user_ns() == &init_user_ns) + return 0; + + if (__kprojid_val(F2FS_I(inode)->i_projid) != fa->fsx_projid) + return -EINVAL; + + if (F2FS_I(inode)->i_flags & F2FS_PROJINHERIT_FL) { + if (!(fa->fsx_xflags & FS_XFLAG_PROJINHERIT)) + return -EINVAL; + } else { + if (fa->fsx_xflags & FS_XFLAG_PROJINHERIT) + return -EINVAL; + } + + return 0; +} + static int f2fs_ioc_fssetxattr(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); @@ -2641,23 +2830,149 @@ static int f2fs_ioc_fssetxattr(struct file *filp, unsigned long arg) return err; inode_lock(inode); + err = f2fs_ioctl_check_project(inode, &fa); + if (err) + goto out; flags = (fi->i_flags & ~F2FS_FL_XFLAG_VISIBLE) | (flags & F2FS_FL_XFLAG_VISIBLE); err = __f2fs_ioc_setflags(inode, flags); - inode_unlock(inode); - mnt_drop_write_file(filp); if (err) - return err; + goto out; err = f2fs_ioc_setproject(filp, fa.fsx_projid); - if (err) - return err; +out: + inode_unlock(inode); + mnt_drop_write_file(filp); + return err; +} +int f2fs_pin_file_control(struct inode *inode, bool inc) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + + /* Use i_gc_failures for normal file as a risk signal. */ + if (inc) + f2fs_i_gc_failures_write(inode, + fi->i_gc_failures[GC_FAILURE_PIN] + 1); + + if (fi->i_gc_failures[GC_FAILURE_PIN] > sbi->gc_pin_file_threshold) { + f2fs_msg(sbi->sb, KERN_WARNING, + "%s: Enable GC = ino %lx after %x GC trials\n", + __func__, inode->i_ino, + fi->i_gc_failures[GC_FAILURE_PIN]); + clear_inode_flag(inode, FI_PIN_FILE); + return -EAGAIN; + } return 0; } +static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + __u32 pin; + int ret = 0; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (get_user(pin, (__u32 __user *)arg)) + return -EFAULT; + + if (!S_ISREG(inode->i_mode)) + return -EINVAL; + + if (f2fs_readonly(F2FS_I_SB(inode)->sb)) + return -EROFS; + + ret = mnt_want_write_file(filp); + if (ret) + return ret; + + inode_lock(inode); + + if (f2fs_should_update_outplace(inode, NULL)) { + ret = -EINVAL; + goto out; + } + + if (!pin) { + clear_inode_flag(inode, FI_PIN_FILE); + f2fs_i_gc_failures_write(inode, 0); + goto done; + } + + if (f2fs_pin_file_control(inode, false)) { + ret = -EAGAIN; + goto out; + } + ret = f2fs_convert_inline_inode(inode); + if (ret) + goto out; + + set_inode_flag(inode, FI_PIN_FILE); + ret = F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN]; +done: + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); +out: + inode_unlock(inode); + mnt_drop_write_file(filp); + return ret; +} + +static int f2fs_ioc_get_pin_file(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + __u32 pin = 0; + + if (is_inode_flag_set(inode, FI_PIN_FILE)) + pin = F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN]; + return put_user(pin, (u32 __user *)arg); +} + +int f2fs_precache_extents(struct inode *inode) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + struct f2fs_map_blocks map; + pgoff_t m_next_extent; + loff_t end; + int err; + + if (is_inode_flag_set(inode, FI_NO_EXTENT)) + return -EOPNOTSUPP; + + map.m_lblk = 0; + map.m_next_pgofs = NULL; + map.m_next_extent = &m_next_extent; + map.m_seg_type = NO_CHECK_TYPE; + map.m_may_create = false; + end = F2FS_I_SB(inode)->max_file_blocks; + + while (map.m_lblk < end) { + map.m_len = end - map.m_lblk; + + down_write(&fi->i_gc_rwsem[WRITE]); + err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_PRECACHE); + up_write(&fi->i_gc_rwsem[WRITE]); + if (err) + return err; + + map.m_lblk = m_next_extent; + } + + return err; +} + +static int f2fs_ioc_precache_extents(struct file *filp, unsigned long arg) +{ + return f2fs_precache_extents(file_inode(filp)); +} + long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { + if (unlikely(f2fs_cp_error(F2FS_I_SB(file_inode(filp))))) + return -EIO; + switch (cmd) { case F2FS_IOC_GETFLAGS: return f2fs_ioc_getflags(filp, arg); @@ -2703,6 +3018,12 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return f2fs_ioc_fsgetxattr(filp, arg); case F2FS_IOC_FSSETXATTR: return f2fs_ioc_fssetxattr(filp, arg); + case F2FS_IOC_GET_PIN_FILE: + return f2fs_ioc_get_pin_file(filp, arg); + case F2FS_IOC_SET_PIN_FILE: + return f2fs_ioc_set_pin_file(filp, arg); + case F2FS_IOC_PRECACHE_EXTENTS: + return f2fs_ioc_precache_extents(filp, arg); default: return -ENOTTY; } @@ -2712,10 +3033,20 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); - struct blk_plug plug; ssize_t ret; - inode_lock(inode); + if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) + return -EIO; + + if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT)) + return -EINVAL; + + if (!inode_trylock(inode)) { + if (iocb->ki_flags & IOCB_NOWAIT) + return -EAGAIN; + inode_lock(inode); + } + ret = generic_write_checks(iocb, from); if (ret > 0) { bool preallocated = false; @@ -2725,18 +3056,31 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) if (iov_iter_fault_in_readable(from, iov_iter_count(from))) set_inode_flag(inode, FI_NO_PREALLOC); - preallocated = true; - target_size = iocb->ki_pos + iov_iter_count(from); + if ((iocb->ki_flags & IOCB_NOWAIT) && + (iocb->ki_flags & IOCB_DIRECT)) { + if (!f2fs_overwrite_io(inode, iocb->ki_pos, + iov_iter_count(from)) || + f2fs_has_inline_data(inode) || + f2fs_force_buffered_io(inode, + iocb, from)) { + clear_inode_flag(inode, + FI_NO_PREALLOC); + inode_unlock(inode); + return -EAGAIN; + } + + } else { + preallocated = true; + target_size = iocb->ki_pos + iov_iter_count(from); - err = f2fs_preallocate_blocks(iocb, from); - if (err) { - clear_inode_flag(inode, FI_NO_PREALLOC); - inode_unlock(inode); - return err; + err = f2fs_preallocate_blocks(iocb, from); + if (err) { + clear_inode_flag(inode, FI_NO_PREALLOC); + inode_unlock(inode); + return err; + } } - blk_start_plug(&plug); ret = __generic_file_write_iter(iocb, from); - blk_finish_plug(&plug); clear_inode_flag(inode, FI_NO_PREALLOC); /* if we couldn't write data, we should deallocate blocks. */ @@ -2784,6 +3128,9 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case F2FS_IOC_GET_FEATURES: case F2FS_IOC_FSGETXATTR: case F2FS_IOC_FSSETXATTR: + case F2FS_IOC_GET_PIN_FILE: + case F2FS_IOC_SET_PIN_FILE: + case F2FS_IOC_PRECACHE_EXTENTS: break; default: return -ENOIOCTLCMD; diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index c2e4c6ce2cf7..d421720cfb17 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/gc.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/module.h> @@ -43,25 +40,28 @@ static int gc_thread_func(void *data) if (gc_th->gc_wake) gc_th->gc_wake = 0; - if (try_to_freeze()) + if (try_to_freeze()) { + stat_other_skip_bggc_count(sbi); continue; + } if (kthread_should_stop()) break; if (sbi->sb->s_writers.frozen >= SB_FREEZE_WRITE) { increase_sleep_time(gc_th, &wait_ms); + stat_other_skip_bggc_count(sbi); continue; } -#ifdef CONFIG_F2FS_FAULT_INJECTION if (time_to_inject(sbi, FAULT_CHECKPOINT)) { f2fs_show_injection_info(FAULT_CHECKPOINT); f2fs_stop_checkpoint(sbi, false); } -#endif - if (!sb_start_write_trylock(sbi->sb)) + if (!sb_start_write_trylock(sbi->sb)) { + stat_other_skip_bggc_count(sbi); continue; + } /* * [GC triggering condition] @@ -76,17 +76,21 @@ static int gc_thread_func(void *data) * invalidated soon after by user update or deletion. * So, I'd like to wait some time to collect dirty segments. */ - if (!mutex_trylock(&sbi->gc_mutex)) - goto next; - - if (gc_th->gc_urgent) { + if (sbi->gc_mode == GC_URGENT) { wait_ms = gc_th->urgent_sleep_time; + mutex_lock(&sbi->gc_mutex); goto do_gc; } - if (!is_idle(sbi)) { + if (!mutex_trylock(&sbi->gc_mutex)) { + stat_other_skip_bggc_count(sbi); + goto next; + } + + if (!is_idle(sbi, GC_TIME)) { increase_sleep_time(gc_th, &wait_ms); mutex_unlock(&sbi->gc_mutex); + stat_io_skip_bggc_count(sbi); goto next; } @@ -113,7 +117,7 @@ next: return 0; } -int start_gc_thread(struct f2fs_sb_info *sbi) +int f2fs_start_gc_thread(struct f2fs_sb_info *sbi) { struct f2fs_gc_kthread *gc_th; dev_t dev = sbi->sb->s_bdev->bd_dev; @@ -130,8 +134,6 @@ int start_gc_thread(struct f2fs_sb_info *sbi) gc_th->max_sleep_time = DEF_GC_THREAD_MAX_SLEEP_TIME; gc_th->no_gc_sleep_time = DEF_GC_THREAD_NOGC_SLEEP_TIME; - gc_th->gc_idle = 0; - gc_th->gc_urgent = 0; gc_th->gc_wake= 0; sbi->gc_thread = gc_th; @@ -140,32 +142,35 @@ int start_gc_thread(struct f2fs_sb_info *sbi) "f2fs_gc-%u:%u", MAJOR(dev), MINOR(dev)); if (IS_ERR(gc_th->f2fs_gc_task)) { err = PTR_ERR(gc_th->f2fs_gc_task); - kfree(gc_th); + kvfree(gc_th); sbi->gc_thread = NULL; } out: return err; } -void stop_gc_thread(struct f2fs_sb_info *sbi) +void f2fs_stop_gc_thread(struct f2fs_sb_info *sbi) { struct f2fs_gc_kthread *gc_th = sbi->gc_thread; if (!gc_th) return; kthread_stop(gc_th->f2fs_gc_task); - kfree(gc_th); + kvfree(gc_th); sbi->gc_thread = NULL; } -static int select_gc_type(struct f2fs_gc_kthread *gc_th, int gc_type) +static int select_gc_type(struct f2fs_sb_info *sbi, int gc_type) { int gc_mode = (gc_type == BG_GC) ? GC_CB : GC_GREEDY; - if (gc_th && gc_th->gc_idle) { - if (gc_th->gc_idle == 1) - gc_mode = GC_CB; - else if (gc_th->gc_idle == 2) - gc_mode = GC_GREEDY; + switch (sbi->gc_mode) { + case GC_IDLE_CB: + gc_mode = GC_CB; + break; + case GC_IDLE_GREEDY: + case GC_URGENT: + gc_mode = GC_GREEDY; + break; } return gc_mode; } @@ -181,14 +186,16 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type, p->max_search = dirty_i->nr_dirty[type]; p->ofs_unit = 1; } else { - p->gc_mode = select_gc_type(sbi->gc_thread, gc_type); + p->gc_mode = select_gc_type(sbi, gc_type); p->dirty_segmap = dirty_i->dirty_segmap[DIRTY]; p->max_search = dirty_i->nr_dirty[DIRTY]; p->ofs_unit = sbi->segs_per_sec; } /* we need to check every dirty segments in the FG_GC case */ - if (gc_type != FG_GC && p->max_search > sbi->max_victim_search) + if (gc_type != FG_GC && + (sbi->gc_mode != GC_URGENT) && + p->max_search > sbi->max_victim_search) p->max_search = sbi->max_victim_search; /* let's select beginning hot/small space first in no_heap mode*/ @@ -226,10 +233,6 @@ static unsigned int check_bg_victims(struct f2fs_sb_info *sbi) for_each_set_bit(secno, dirty_i->victim_secmap, MAIN_SECS(sbi)) { if (sec_usage_check(sbi, secno)) continue; - - if (no_fggc_candidate(sbi, secno)) - continue; - clear_bit(secno, dirty_i->victim_secmap); return GET_SEG_FROM_SEC(sbi, secno); } @@ -268,16 +271,6 @@ static unsigned int get_cb_cost(struct f2fs_sb_info *sbi, unsigned int segno) return UINT_MAX - ((100 * (100 - u) * age) / (100 + u)); } -static unsigned int get_greedy_cost(struct f2fs_sb_info *sbi, - unsigned int segno) -{ - unsigned int valid_blocks = - get_valid_blocks(sbi, segno, true); - - return IS_DATASEG(get_seg_entry(sbi, segno)->type) ? - valid_blocks * 2 : valid_blocks; -} - static inline unsigned int get_gc_cost(struct f2fs_sb_info *sbi, unsigned int segno, struct victim_sel_policy *p) { @@ -286,7 +279,7 @@ static inline unsigned int get_gc_cost(struct f2fs_sb_info *sbi, /* alloc_mode == LFS */ if (p->gc_mode == GC_GREEDY) - return get_greedy_cost(sbi, segno); + return get_valid_blocks(sbi, segno, true); else return get_cb_cost(sbi, segno); } @@ -339,6 +332,22 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi, if (p.max_search == 0) goto out; + if (__is_large_section(sbi) && p.alloc_mode == LFS) { + if (sbi->next_victim_seg[BG_GC] != NULL_SEGNO) { + p.min_segno = sbi->next_victim_seg[BG_GC]; + *result = p.min_segno; + sbi->next_victim_seg[BG_GC] = NULL_SEGNO; + goto got_result; + } + if (gc_type == FG_GC && + sbi->next_victim_seg[FG_GC] != NULL_SEGNO) { + p.min_segno = sbi->next_victim_seg[FG_GC]; + *result = p.min_segno; + sbi->next_victim_seg[FG_GC] = NULL_SEGNO; + goto got_result; + } + } + last_victim = sm->last_victim[p.gc_mode]; if (p.alloc_mode == LFS && gc_type == FG_GC) { p.min_segno = check_bg_victims(sbi); @@ -376,10 +385,11 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi, if (sec_usage_check(sbi, secno)) goto next; - if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap)) + /* Don't touch checkpointed data */ + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED) && + get_ckpt_valid_blocks(sbi, segno))) goto next; - if (gc_type == FG_GC && p.alloc_mode == LFS && - no_fggc_candidate(sbi, secno)) + if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap)) goto next; cost = get_gc_cost(sbi, segno, &p); @@ -400,6 +410,8 @@ next: } if (p.min_segno != NULL_SEGNO) { got_it: + *result = (p.min_segno / p.ofs_unit) * p.ofs_unit; +got_result: if (p.alloc_mode == LFS) { secno = GET_SEC_FROM_SEG(sbi, p.min_segno); if (gc_type == FG_GC) @@ -407,13 +419,13 @@ got_it: else set_bit(secno, dirty_i->victim_secmap); } - *result = (p.min_segno / p.ofs_unit) * p.ofs_unit; + } +out: + if (p.min_segno != NULL_SEGNO) trace_f2fs_get_victim(sbi->sb, type, gc_type, &p, sbi->cur_victim_sec, prefree_segments(sbi), free_segments(sbi)); - } -out: mutex_unlock(&dirty_i->seglist_lock); return (p.min_segno == NULL_SEGNO) ? 0 : 1; @@ -441,7 +453,7 @@ static void add_gc_inode(struct gc_inode_list *gc_list, struct inode *inode) iput(inode); return; } - new_ie = f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS); + new_ie = f2fs_kmem_cache_alloc(f2fs_inode_entry_slab, GFP_NOFS); new_ie->inode = inode; f2fs_radix_tree_insert(&gc_list->iroot, inode->i_ino, new_ie); @@ -455,7 +467,7 @@ static void put_gc_inode(struct gc_inode_list *gc_list) radix_tree_delete(&gc_list->iroot, ie->inode->i_ino); iput(ie->inode); list_del(&ie->list); - kmem_cache_free(inode_entry_slab, ie); + kmem_cache_free(f2fs_inode_entry_slab, ie); } } @@ -466,10 +478,10 @@ static int check_valid_map(struct f2fs_sb_info *sbi, struct seg_entry *sentry; int ret; - mutex_lock(&sit_i->sentry_lock); + down_read(&sit_i->sentry_lock); sentry = get_seg_entry(sbi, segno); ret = f2fs_test_bit(offset, sentry->cur_valid_map); - mutex_unlock(&sit_i->sentry_lock); + up_read(&sit_i->sentry_lock); return ret; } @@ -478,65 +490,81 @@ static int check_valid_map(struct f2fs_sb_info *sbi, * On validity, copy that node with cold status, otherwise (invalid node) * ignore that. */ -static void gc_node_segment(struct f2fs_sb_info *sbi, +static int gc_node_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, unsigned int segno, int gc_type) { struct f2fs_summary *entry; block_t start_addr; int off; int phase = 0; + bool fggc = (gc_type == FG_GC); + int submitted = 0; start_addr = START_BLOCK(sbi, segno); next_step: entry = sum; + if (fggc && phase == 2) + atomic_inc(&sbi->wb_sync_req[NODE]); + for (off = 0; off < sbi->blocks_per_seg; off++, entry++) { nid_t nid = le32_to_cpu(entry->nid); struct page *node_page; struct node_info ni; + int err; /* stop BG_GC if there is not enough free sections. */ if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0)) - return; + return submitted; if (check_valid_map(sbi, segno, off) == 0) continue; if (phase == 0) { - ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), 1, + f2fs_ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), 1, META_NAT, true); continue; } if (phase == 1) { - ra_node_page(sbi, nid); + f2fs_ra_node_page(sbi, nid); continue; } /* phase == 2 */ - node_page = get_node_page(sbi, nid); + node_page = f2fs_get_node_page(sbi, nid); if (IS_ERR(node_page)) continue; - /* block may become invalid during get_node_page */ + /* block may become invalid during f2fs_get_node_page */ if (check_valid_map(sbi, segno, off) == 0) { f2fs_put_page(node_page, 1); continue; } - get_node_info(sbi, nid, &ni); + if (f2fs_get_node_info(sbi, nid, &ni)) { + f2fs_put_page(node_page, 1); + continue; + } + if (ni.blk_addr != start_addr + off) { f2fs_put_page(node_page, 1); continue; } - move_node_page(node_page, gc_type); + err = f2fs_move_node_page(node_page, gc_type); + if (!err && gc_type == FG_GC) + submitted++; stat_inc_node_blk_count(sbi, 1, gc_type); } if (++phase < 3) goto next_step; + + if (fggc) + atomic_dec(&sbi->wb_sync_req[NODE]); + return submitted; } /* @@ -546,7 +574,7 @@ next_step: * as indirect or double indirect node blocks, are given, it must be a caller's * bug. */ -block_t start_bidx_of_node(unsigned int node_ofs, struct inode *inode) +block_t f2fs_start_bidx_of_node(unsigned int node_ofs, struct inode *inode) { unsigned int indirect_blks = 2 * NIDS_PER_BLOCK + 4; unsigned int bidx; @@ -577,11 +605,14 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, nid = le32_to_cpu(sum->nid); ofs_in_node = le16_to_cpu(sum->ofs_in_node); - node_page = get_node_page(sbi, nid); + node_page = f2fs_get_node_page(sbi, nid); if (IS_ERR(node_page)) return false; - get_node_info(sbi, nid, dni); + if (f2fs_get_node_info(sbi, nid, dni)) { + f2fs_put_page(node_page, 1); + return false; + } if (sum->version != dni->version) { f2fs_msg(sbi->sb, KERN_WARNING, @@ -599,47 +630,137 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, return true; } +static int ra_data_block(struct inode *inode, pgoff_t index) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct address_space *mapping = inode->i_mapping; + struct dnode_of_data dn; + struct page *page; + struct extent_info ei = {0, 0, 0}; + struct f2fs_io_info fio = { + .sbi = sbi, + .ino = inode->i_ino, + .type = DATA, + .temp = COLD, + .op = REQ_OP_READ, + .op_flags = 0, + .encrypted_page = NULL, + .in_list = false, + .retry = false, + }; + int err; + + page = f2fs_grab_cache_page(mapping, index, true); + if (!page) + return -ENOMEM; + + if (f2fs_lookup_extent_cache(inode, index, &ei)) { + dn.data_blkaddr = ei.blk + index - ei.fofs; + goto got_it; + } + + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE); + if (err) + goto put_page; + f2fs_put_dnode(&dn); + + if (unlikely(!f2fs_is_valid_blkaddr(sbi, dn.data_blkaddr, + DATA_GENERIC))) { + err = -EFAULT; + goto put_page; + } +got_it: + /* read page */ + fio.page = page; + fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr; + + /* + * don't cache encrypted data into meta inode until previous dirty + * data were writebacked to avoid racing between GC and flush. + */ + f2fs_wait_on_page_writeback(page, DATA, true, true); + + f2fs_wait_on_block_writeback(inode, dn.data_blkaddr); + + fio.encrypted_page = f2fs_pagecache_get_page(META_MAPPING(sbi), + dn.data_blkaddr, + FGP_LOCK | FGP_CREAT, GFP_NOFS); + if (!fio.encrypted_page) { + err = -ENOMEM; + goto put_page; + } + + err = f2fs_submit_page_bio(&fio); + if (err) + goto put_encrypted_page; + f2fs_put_page(fio.encrypted_page, 0); + f2fs_put_page(page, 1); + return 0; +put_encrypted_page: + f2fs_put_page(fio.encrypted_page, 1); +put_page: + f2fs_put_page(page, 1); + return err; +} + /* * Move data block via META_MAPPING while keeping locked data page. * This can be used to move blocks, aka LBAs, directly on disk. */ -static void move_data_block(struct inode *inode, block_t bidx, - unsigned int segno, int off) +static int move_data_block(struct inode *inode, block_t bidx, + int gc_type, unsigned int segno, int off) { struct f2fs_io_info fio = { .sbi = F2FS_I_SB(inode), + .ino = inode->i_ino, .type = DATA, .temp = COLD, .op = REQ_OP_READ, .op_flags = 0, .encrypted_page = NULL, .in_list = false, + .retry = false, }; struct dnode_of_data dn; struct f2fs_summary sum; struct node_info ni; - struct page *page; + struct page *page, *mpage; block_t newaddr; - int err; + int err = 0; + bool lfs_mode = test_opt(fio.sbi, LFS); /* do not read out */ page = f2fs_grab_cache_page(inode->i_mapping, bidx, false); if (!page) - return; + return -ENOMEM; + + if (!check_valid_map(F2FS_I_SB(inode), segno, off)) { + err = -ENOENT; + goto out; + } - if (!check_valid_map(F2FS_I_SB(inode), segno, off)) + if (f2fs_is_atomic_file(inode)) { + F2FS_I(inode)->i_gc_failures[GC_FAILURE_ATOMIC]++; + F2FS_I_SB(inode)->skipped_atomic_files[gc_type]++; + err = -EAGAIN; goto out; + } - if (f2fs_is_atomic_file(inode)) + if (f2fs_is_pinned_file(inode)) { + f2fs_pin_file_control(inode, true); + err = -EAGAIN; goto out; + } set_new_dnode(&dn, inode, NULL, NULL, 0); - err = get_dnode_of_data(&dn, bidx, LOOKUP_NODE); + err = f2fs_get_dnode_of_data(&dn, bidx, LOOKUP_NODE); if (err) goto out; if (unlikely(dn.data_blkaddr == NULL_ADDR)) { ClearPageUptodate(page); + err = -ENOENT; goto put_out; } @@ -647,25 +768,50 @@ static void move_data_block(struct inode *inode, block_t bidx, * don't cache encrypted data into meta inode until previous dirty * data were writebacked to avoid racing between GC and flush. */ - f2fs_wait_on_page_writeback(page, DATA, true); + f2fs_wait_on_page_writeback(page, DATA, true, true); + + f2fs_wait_on_block_writeback(inode, dn.data_blkaddr); + + err = f2fs_get_node_info(fio.sbi, dn.nid, &ni); + if (err) + goto put_out; - get_node_info(fio.sbi, dn.nid, &ni); set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version); /* read page */ fio.page = page; fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr; - allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr, + if (lfs_mode) + down_write(&fio.sbi->io_order_lock); + + f2fs_allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr, &sum, CURSEG_COLD_DATA, NULL, false); - fio.encrypted_page = pagecache_get_page(META_MAPPING(fio.sbi), newaddr, - FGP_LOCK | FGP_CREAT, GFP_NOFS); + fio.encrypted_page = f2fs_pagecache_get_page(META_MAPPING(fio.sbi), + newaddr, FGP_LOCK | FGP_CREAT, GFP_NOFS); if (!fio.encrypted_page) { err = -ENOMEM; goto recover_block; } + mpage = f2fs_pagecache_get_page(META_MAPPING(fio.sbi), + fio.old_blkaddr, FGP_LOCK, GFP_NOFS); + if (mpage) { + bool updated = false; + + if (PageUptodate(mpage)) { + memcpy(page_address(fio.encrypted_page), + page_address(mpage), PAGE_SIZE); + updated = true; + } + f2fs_put_page(mpage, 1); + invalidate_mapping_pages(META_MAPPING(fio.sbi), + fio.old_blkaddr, fio.old_blkaddr); + if (updated) + goto write_page; + } + err = f2fs_submit_page_bio(&fio); if (err) goto put_page_out; @@ -682,21 +828,24 @@ static void move_data_block(struct inode *inode, block_t bidx, goto put_page_out; } +write_page: + f2fs_wait_on_page_writeback(fio.encrypted_page, DATA, true, true); set_page_dirty(fio.encrypted_page); - f2fs_wait_on_page_writeback(fio.encrypted_page, DATA, true); if (clear_page_dirty_for_io(fio.encrypted_page)) dec_page_count(fio.sbi, F2FS_DIRTY_META); set_page_writeback(fio.encrypted_page); + ClearPageError(page); /* allocate block address */ - f2fs_wait_on_page_writeback(dn.node_page, NODE, true); + f2fs_wait_on_page_writeback(dn.node_page, NODE, true, true); fio.op = REQ_OP_WRITE; fio.op_flags = REQ_SYNC; fio.new_blkaddr = newaddr; - err = f2fs_submit_page_write(&fio); - if (err) { + f2fs_submit_page_write(&fio); + if (fio.retry) { + err = -EAGAIN; if (PageWriteback(fio.encrypted_page)) end_page_writeback(fio.encrypted_page); goto put_page_out; @@ -711,38 +860,57 @@ static void move_data_block(struct inode *inode, block_t bidx, put_page_out: f2fs_put_page(fio.encrypted_page, 1); recover_block: + if (lfs_mode) + up_write(&fio.sbi->io_order_lock); if (err) - __f2fs_replace_block(fio.sbi, &sum, newaddr, fio.old_blkaddr, + f2fs_do_replace_block(fio.sbi, &sum, newaddr, fio.old_blkaddr, true, true); put_out: f2fs_put_dnode(&dn); out: f2fs_put_page(page, 1); + return err; } -static void move_data_page(struct inode *inode, block_t bidx, int gc_type, +static int move_data_page(struct inode *inode, block_t bidx, int gc_type, unsigned int segno, int off) { struct page *page; + int err = 0; - page = get_lock_data_page(inode, bidx, true); + page = f2fs_get_lock_data_page(inode, bidx, true); if (IS_ERR(page)) - return; + return PTR_ERR(page); - if (!check_valid_map(F2FS_I_SB(inode), segno, off)) + if (!check_valid_map(F2FS_I_SB(inode), segno, off)) { + err = -ENOENT; goto out; + } - if (f2fs_is_atomic_file(inode)) + if (f2fs_is_atomic_file(inode)) { + F2FS_I(inode)->i_gc_failures[GC_FAILURE_ATOMIC]++; + F2FS_I_SB(inode)->skipped_atomic_files[gc_type]++; + err = -EAGAIN; + goto out; + } + if (f2fs_is_pinned_file(inode)) { + if (gc_type == FG_GC) + f2fs_pin_file_control(inode, true); + err = -EAGAIN; goto out; + } if (gc_type == BG_GC) { - if (PageWriteback(page)) + if (PageWriteback(page)) { + err = -EAGAIN; goto out; + } set_page_dirty(page); set_cold_data(page); } else { struct f2fs_io_info fio = { .sbi = F2FS_I_SB(inode), + .ino = inode->i_ino, .type = DATA, .temp = COLD, .op = REQ_OP_WRITE, @@ -754,19 +922,19 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type, .io_type = FS_GC_DATA_IO, }; bool is_dirty = PageDirty(page); - int err; retry: + f2fs_wait_on_page_writeback(page, DATA, true, true); + set_page_dirty(page); - f2fs_wait_on_page_writeback(page, DATA, true); if (clear_page_dirty_for_io(page)) { inode_dec_dirty_pages(inode); - remove_dirty_inode(inode); + f2fs_remove_dirty_inode(inode); } set_cold_data(page); - err = do_write_data_page(&fio); + err = f2fs_do_write_data_page(&fio); if (err) { clear_cold_data(page); if (err == -ENOMEM) { @@ -779,6 +947,7 @@ retry: } out: f2fs_put_page(page, 1); + return err; } /* @@ -788,7 +957,7 @@ out: * If the parent node is not valid or the data block address is different, * the victim data block is ignored. */ -static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, +static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, struct gc_inode_list *gc_list, unsigned int segno, int gc_type) { struct super_block *sb = sbi->sb; @@ -796,6 +965,7 @@ static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, block_t start_addr; int off; int phase = 0; + int submitted = 0; start_addr = START_BLOCK(sbi, segno); @@ -812,19 +982,19 @@ next_step: /* stop BG_GC if there is not enough free sections. */ if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0)) - return; + return submitted; if (check_valid_map(sbi, segno, off) == 0) continue; if (phase == 0) { - ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), 1, + f2fs_ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), 1, META_NAT, true); continue; } if (phase == 1) { - ra_node_page(sbi, nid); + f2fs_ra_node_page(sbi, nid); continue; } @@ -833,7 +1003,7 @@ next_step: continue; if (phase == 2) { - ra_node_page(sbi, dni.ino); + f2fs_ra_node_page(sbi, dni.ino); continue; } @@ -844,16 +1014,31 @@ next_step: if (IS_ERR(inode) || is_bad_inode(inode)) continue; - /* if encrypted inode, let's go phase 3 */ - if (f2fs_encrypted_file(inode)) { + if (!down_write_trylock( + &F2FS_I(inode)->i_gc_rwsem[WRITE])) { + iput(inode); + sbi->skipped_gc_rwsem++; + continue; + } + + start_bidx = f2fs_start_bidx_of_node(nofs, inode) + + ofs_in_node; + + if (f2fs_post_read_required(inode)) { + int err = ra_data_block(inode, start_bidx); + + up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); + if (err) { + iput(inode); + continue; + } add_gc_inode(gc_list, inode); continue; } - start_bidx = start_bidx_of_node(nofs, inode); - data_page = get_read_data_page(inode, - start_bidx + ofs_in_node, REQ_RAHEAD, - true); + data_page = f2fs_get_read_data_page(inode, + start_bidx, REQ_RAHEAD, true); + up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); if (IS_ERR(data_page)) { iput(inode); continue; @@ -869,13 +1054,15 @@ next_step: if (inode) { struct f2fs_inode_info *fi = F2FS_I(inode); bool locked = false; + int err; if (S_ISREG(inode->i_mode)) { - if (!down_write_trylock(&fi->dio_rwsem[READ])) + if (!down_write_trylock(&fi->i_gc_rwsem[READ])) continue; if (!down_write_trylock( - &fi->dio_rwsem[WRITE])) { - up_write(&fi->dio_rwsem[READ]); + &fi->i_gc_rwsem[WRITE])) { + sbi->skipped_gc_rwsem++; + up_write(&fi->i_gc_rwsem[READ]); continue; } locked = true; @@ -884,17 +1071,22 @@ next_step: inode_dio_wait(inode); } - start_bidx = start_bidx_of_node(nofs, inode) + start_bidx = f2fs_start_bidx_of_node(nofs, inode) + ofs_in_node; - if (f2fs_encrypted_file(inode)) - move_data_block(inode, start_bidx, segno, off); + if (f2fs_post_read_required(inode)) + err = move_data_block(inode, start_bidx, + gc_type, segno, off); else - move_data_page(inode, start_bidx, gc_type, + err = move_data_page(inode, start_bidx, gc_type, segno, off); + if (!err && (gc_type == FG_GC || + f2fs_post_read_required(inode))) + submitted++; + if (locked) { - up_write(&fi->dio_rwsem[WRITE]); - up_write(&fi->dio_rwsem[READ]); + up_write(&fi->i_gc_rwsem[WRITE]); + up_write(&fi->i_gc_rwsem[READ]); } stat_inc_data_blk_count(sbi, 1, gc_type); @@ -903,6 +1095,8 @@ next_step: if (++phase < 5) goto next_step; + + return submitted; } static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim, @@ -911,10 +1105,10 @@ static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim, struct sit_info *sit_i = SIT_I(sbi); int ret; - mutex_lock(&sit_i->sentry_lock); + down_write(&sit_i->sentry_lock); ret = DIRTY_I(sbi)->v_ops->get_victim(sbi, victim, gc_type, NO_CHECK_TYPE, LFS); - mutex_unlock(&sit_i->sentry_lock); + up_write(&sit_i->sentry_lock); return ret; } @@ -927,18 +1121,34 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, struct blk_plug plug; unsigned int segno = start_segno; unsigned int end_segno = start_segno + sbi->segs_per_sec; - int seg_freed = 0; + int seg_freed = 0, migrated = 0; unsigned char type = IS_DATASEG(get_seg_entry(sbi, segno)->type) ? SUM_TYPE_DATA : SUM_TYPE_NODE; + int submitted = 0; + + if (__is_large_section(sbi)) + end_segno = rounddown(end_segno, sbi->segs_per_sec); /* readahead multi ssa blocks those have contiguous address */ - if (sbi->segs_per_sec > 1) - ra_meta_pages(sbi, GET_SUM_BLOCK(sbi, segno), - sbi->segs_per_sec, META_SSA, true); + if (__is_large_section(sbi)) + f2fs_ra_meta_pages(sbi, GET_SUM_BLOCK(sbi, segno), + end_segno - segno, META_SSA, true); /* reference all summary page */ while (segno < end_segno) { - sum_page = get_sum_page(sbi, segno++); + sum_page = f2fs_get_sum_page(sbi, segno++); + if (IS_ERR(sum_page)) { + int err = PTR_ERR(sum_page); + + end_segno = segno - 1; + for (segno = start_segno; segno < end_segno; segno++) { + sum_page = find_get_page(META_MAPPING(sbi), + GET_SUM_BLOCK(sbi, segno)); + f2fs_put_page(sum_page, 0); + f2fs_put_page(sum_page, 0); + } + return err; + } unlock_page(sum_page); } @@ -953,8 +1163,11 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, if (get_valid_blocks(sbi, segno, false) == 0) goto freed; + if (__is_large_section(sbi) && + migrated >= sbi->migration_granularity) + goto skip; if (!PageUptodate(sum_page) || unlikely(f2fs_cp_error(sbi))) - goto next; + goto skip; sum = page_address(sum_page); if (type != GET_SUM_TYPE((&sum->footer))) { @@ -962,21 +1175,22 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, "type [%d, %d] in SSA and SIT", segno, type, GET_SUM_TYPE((&sum->footer))); set_sbi_flag(sbi, SBI_NEED_FSCK); - goto next; + goto skip; } /* * this is to avoid deadlock: * - lock_page(sum_page) - f2fs_replace_block - * - check_valid_map() - mutex_lock(sentry_lock) - * - mutex_lock(sentry_lock) - change_curseg() + * - check_valid_map() - down_write(sentry_lock) + * - down_read(sentry_lock) - change_curseg() * - lock_page(sum_page) */ if (type == SUM_TYPE_NODE) - gc_node_segment(sbi, sum->entries, segno, gc_type); - else - gc_data_segment(sbi, sum->entries, gc_list, segno, + submitted += gc_node_segment(sbi, sum->entries, segno, gc_type); + else + submitted += gc_data_segment(sbi, sum->entries, gc_list, + segno, gc_type); stat_inc_seg_count(sbi, type, gc_type); @@ -984,11 +1198,15 @@ freed: if (gc_type == FG_GC && get_valid_blocks(sbi, segno, false) == 0) seg_freed++; -next: + migrated++; + + if (__is_large_section(sbi) && segno + 1 < end_segno) + sbi->next_victim_seg[gc_type] = segno + 1; +skip: f2fs_put_page(sum_page, 0); } - if (gc_type == FG_GC) + if (submitted) f2fs_submit_merged_write(sbi, (type == SUM_TYPE_NODE) ? NODE : DATA); @@ -1011,6 +1229,9 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, .ilist = LIST_HEAD_INIT(gc_list.ilist), .iroot = RADIX_TREE_INIT(GFP_NOFS), }; + unsigned long long last_skipped = sbi->skipped_atomic_files[FG_GC]; + unsigned long long first_skipped; + unsigned int skipped_round = 0, round = 0; trace_f2fs_gc_begin(sbi->sb, sync, background, get_pages(sbi, F2FS_DIRTY_NODES), @@ -1022,6 +1243,8 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, prefree_segments(sbi)); cpc.reason = __get_cp_reason(sbi); + sbi->skipped_gc_rwsem = 0; + first_skipped = last_skipped; gc_more: if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE))) { ret = -EINVAL; @@ -1038,8 +1261,9 @@ gc_more: * threshold, we can make them free by checkpoint. Then, we * secure free segments which doesn't need fggc any more. */ - if (prefree_segments(sbi)) { - ret = write_checkpoint(sbi, &cpc); + if (prefree_segments(sbi) && + !is_sbi_flag_set(sbi, SBI_CP_DISABLED)) { + ret = f2fs_write_checkpoint(sbi, &cpc); if (ret) goto stop; } @@ -1062,17 +1286,36 @@ gc_more: sec_freed++; total_freed += seg_freed; + if (gc_type == FG_GC) { + if (sbi->skipped_atomic_files[FG_GC] > last_skipped || + sbi->skipped_gc_rwsem) + skipped_round++; + last_skipped = sbi->skipped_atomic_files[FG_GC]; + round++; + } + if (gc_type == FG_GC) sbi->cur_victim_sec = NULL_SEGNO; - if (!sync) { - if (has_not_enough_free_secs(sbi, sec_freed, 0)) { + if (sync) + goto stop; + + if (has_not_enough_free_secs(sbi, sec_freed, 0)) { + if (skipped_round <= MAX_SKIP_GC_COUNT || + skipped_round * 2 < round) { segno = NULL_SEGNO; goto gc_more; } - if (gc_type == FG_GC) - ret = write_checkpoint(sbi, &cpc); + if (first_skipped < last_skipped && + (last_skipped - first_skipped) > + sbi->skipped_gc_rwsem) { + f2fs_drop_inmem_pages_all(sbi, true); + segno = NULL_SEGNO; + goto gc_more; + } + if (gc_type == FG_GC && !is_sbi_flag_set(sbi, SBI_CP_DISABLED)) + ret = f2fs_write_checkpoint(sbi, &cpc); } stop: SIT_I(sbi)->last_victim[ALLOC_NEXT] = 0; @@ -1096,22 +1339,14 @@ stop: return ret; } -void build_gc_manager(struct f2fs_sb_info *sbi) +void f2fs_build_gc_manager(struct f2fs_sb_info *sbi) { - u64 main_count, resv_count, ovp_count; - DIRTY_I(sbi)->v_ops = &default_v_ops; - /* threshold of # of valid blocks in a section for victims of FG_GC */ - main_count = SM_I(sbi)->main_segments << sbi->log_blocks_per_seg; - resv_count = SM_I(sbi)->reserved_segments << sbi->log_blocks_per_seg; - ovp_count = SM_I(sbi)->ovp_segments << sbi->log_blocks_per_seg; - - sbi->fggc_threshold = div64_u64((main_count - ovp_count) * - BLKS_PER_SEC(sbi), (main_count - resv_count)); + sbi->gc_pin_file_threshold = DEF_GC_FAILED_PINNED_FILES; /* give warm/cold data area from slower device */ - if (f2fs_is_multi_device(sbi) && sbi->segs_per_sec == 1) + if (sbi->s_ndevs && !__is_large_section(sbi)) SIT_I(sbi)->last_victim[ALLOC_NEXT] = GET_SEGNO(sbi, FDEV(0).end_blk) + 1; } diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h index 9325191fab2d..bbac9d3787bd 100644 --- a/fs/f2fs/gc.h +++ b/fs/f2fs/gc.h @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/gc.h * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #define GC_THREAD_MIN_WB_PAGES 1 /* * a threshold to determine @@ -20,6 +17,8 @@ #define LIMIT_INVALID_BLOCK 40 /* percentage over total user space */ #define LIMIT_FREE_BLOCK 40 /* percentage over invalid + free space */ +#define DEF_GC_FAILED_PINNED_FILES 2048 + /* Search max. number of dirty segments to select a victim segment */ #define DEF_MAX_VICTIM_SEARCH 4096 /* covers 8GB */ @@ -34,8 +33,6 @@ struct f2fs_gc_kthread { unsigned int no_gc_sleep_time; /* for changing gc mode */ - unsigned int gc_idle; - unsigned int gc_urgent; unsigned int gc_wake; }; diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c index eb2e031ea887..cc82f142f811 100644 --- a/fs/f2fs/hash.c +++ b/fs/f2fs/hash.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/hash.c * @@ -7,10 +8,6 @@ * Portions of this code from linux/fs/ext3/hash.c * * Copyright (C) 2002 by Theodore Ts'o - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/types.h> #include <linux/fs.h> diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 8906f6381b1a..df04b3e24ba4 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -1,11 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/inline.c * Copyright (c) 2013, Intel Corporation * Authors: Huajun Li <huajun.li@intel.com> * Haicheng Li <haicheng.li@intel.com> - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> @@ -13,6 +11,7 @@ #include "f2fs.h" #include "node.h" +#include <trace/events/android_fs.h> bool f2fs_may_inline_data(struct inode *inode) { @@ -25,7 +24,7 @@ bool f2fs_may_inline_data(struct inode *inode) if (i_size_read(inode) > MAX_INLINE_DATA(inode)) return false; - if (f2fs_encrypted_file(inode)) + if (f2fs_post_read_required(inode)) return false; return true; @@ -42,7 +41,7 @@ bool f2fs_may_inline_dentry(struct inode *inode) return true; } -void read_inline_data(struct page *page, struct page *ipage) +void f2fs_do_read_inline_data(struct page *page, struct page *ipage) { struct inode *inode = page->mapping->host; void *src_addr, *dst_addr; @@ -64,7 +63,8 @@ void read_inline_data(struct page *page, struct page *ipage) SetPageUptodate(page); } -void truncate_inline_inode(struct inode *inode, struct page *ipage, u64 from) +void f2fs_truncate_inline_inode(struct inode *inode, + struct page *ipage, u64 from) { void *addr; @@ -73,7 +73,7 @@ void truncate_inline_inode(struct inode *inode, struct page *ipage, u64 from) addr = inline_data_addr(inode, ipage); - f2fs_wait_on_page_writeback(ipage, NODE, true); + f2fs_wait_on_page_writeback(ipage, NODE, true, true); memset(addr + from, 0, MAX_INLINE_DATA(inode) - from); set_page_dirty(ipage); @@ -85,25 +85,42 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page) { struct page *ipage; - ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino); + if (trace_android_fs_dataread_start_enabled()) { + char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; + + path = android_fstrace_get_pathname(pathbuf, + MAX_TRACE_PATHBUF_LEN, + inode); + trace_android_fs_dataread_start(inode, page_offset(page), + PAGE_SIZE, current->pid, + path, current->comm); + } + + ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino); if (IS_ERR(ipage)) { + trace_android_fs_dataread_end(inode, page_offset(page), + PAGE_SIZE); unlock_page(page); return PTR_ERR(ipage); } if (!f2fs_has_inline_data(inode)) { f2fs_put_page(ipage, 1); + trace_android_fs_dataread_end(inode, page_offset(page), + PAGE_SIZE); return -EAGAIN; } if (page->index) zero_user_segment(page, 0, PAGE_SIZE); else - read_inline_data(page, ipage); + f2fs_do_read_inline_data(page, ipage); if (!PageUptodate(page)) SetPageUptodate(page); f2fs_put_page(ipage, 1); + trace_android_fs_dataread_end(inode, page_offset(page), + PAGE_SIZE); unlock_page(page); return 0; } @@ -112,6 +129,7 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page) { struct f2fs_io_info fio = { .sbi = F2FS_I_SB(dn->inode), + .ino = dn->inode->i_ino, .type = DATA, .op = REQ_OP_WRITE, .op_flags = REQ_SYNC | REQ_PRIO, @@ -119,6 +137,7 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page) .encrypted_page = NULL, .io_type = FS_DATA_IO, }; + struct node_info ni; int dirty, err; if (!f2fs_exist_data(dn->inode)) @@ -128,6 +147,14 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page) if (err) return err; + err = f2fs_get_node_info(fio.sbi, dn->nid, &ni); + if (err) { + f2fs_put_dnode(dn); + return err; + } + + fio.version = ni.version; + if (unlikely(dn->data_blkaddr != NEW_ADDR)) { f2fs_put_dnode(dn); set_sbi_flag(fio.sbi, SBI_NEED_FSCK); @@ -140,7 +167,7 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page) f2fs_bug_on(F2FS_P_SB(page), PageWriteback(page)); - read_inline_data(page, dn->inode_page); + f2fs_do_read_inline_data(page, dn->inode_page); set_page_dirty(page); /* clear dirty state */ @@ -148,20 +175,21 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page) /* write data page to try to make data consistent */ set_page_writeback(page); + ClearPageError(page); fio.old_blkaddr = dn->data_blkaddr; set_inode_flag(dn->inode, FI_HOT_DATA); - write_data_page(dn, &fio); - f2fs_wait_on_page_writeback(page, DATA, true); + f2fs_outplace_write_data(dn, &fio); + f2fs_wait_on_page_writeback(page, DATA, true, true); if (dirty) { inode_dec_dirty_pages(dn->inode); - remove_dirty_inode(dn->inode); + f2fs_remove_dirty_inode(dn->inode); } /* this converted inline_data should be recovered. */ set_inode_flag(dn->inode, FI_APPEND_WRITE); /* clear inline data and flag after data writeback */ - truncate_inline_inode(dn->inode, dn->inode_page, 0); + f2fs_truncate_inline_inode(dn->inode, dn->inode_page, 0); clear_inline_node(dn->inode_page); clear_out: stat_dec_inline_inode(dn->inode); @@ -186,7 +214,7 @@ int f2fs_convert_inline_inode(struct inode *inode) f2fs_lock_op(sbi); - ipage = get_node_page(sbi, inode->i_ino); + ipage = f2fs_get_node_page(sbi, inode->i_ino); if (IS_ERR(ipage)) { err = PTR_ERR(ipage); goto out; @@ -212,12 +240,10 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page) { void *src_addr, *dst_addr; struct dnode_of_data dn; - struct address_space *mapping = page_mapping(page); - unsigned long flags; int err; set_new_dnode(&dn, inode, NULL, NULL, 0); - err = get_dnode_of_data(&dn, 0, LOOKUP_NODE); + err = f2fs_get_dnode_of_data(&dn, 0, LOOKUP_NODE); if (err) return err; @@ -228,17 +254,14 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page) f2fs_bug_on(F2FS_I_SB(inode), page->index); - f2fs_wait_on_page_writeback(dn.inode_page, NODE, true); + f2fs_wait_on_page_writeback(dn.inode_page, NODE, true, true); src_addr = kmap_atomic(page); dst_addr = inline_data_addr(inode, dn.inode_page); memcpy(dst_addr, src_addr, MAX_INLINE_DATA(inode)); kunmap_atomic(src_addr); set_page_dirty(dn.inode_page); - spin_lock_irqsave(&mapping->tree_lock, flags); - radix_tree_tag_clear(&mapping->page_tree, page_index(page), - PAGECACHE_TAG_DIRTY); - spin_unlock_irqrestore(&mapping->tree_lock, flags); + f2fs_clear_radix_tree_dirty_tag(page); set_inode_flag(inode, FI_APPEND_WRITE); set_inode_flag(inode, FI_DATA_EXIST); @@ -248,7 +271,7 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page) return 0; } -bool recover_inline_data(struct inode *inode, struct page *npage) +bool f2fs_recover_inline_data(struct inode *inode, struct page *npage) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode *ri = NULL; @@ -269,10 +292,10 @@ bool recover_inline_data(struct inode *inode, struct page *npage) if (f2fs_has_inline_data(inode) && ri && (ri->i_inline & F2FS_INLINE_DATA)) { process_inline: - ipage = get_node_page(sbi, inode->i_ino); + ipage = f2fs_get_node_page(sbi, inode->i_ino); f2fs_bug_on(sbi, IS_ERR(ipage)); - f2fs_wait_on_page_writeback(ipage, NODE, true); + f2fs_wait_on_page_writeback(ipage, NODE, true, true); src_addr = inline_data_addr(inode, npage); dst_addr = inline_data_addr(inode, ipage); @@ -287,20 +310,20 @@ process_inline: } if (f2fs_has_inline_data(inode)) { - ipage = get_node_page(sbi, inode->i_ino); + ipage = f2fs_get_node_page(sbi, inode->i_ino); f2fs_bug_on(sbi, IS_ERR(ipage)); - truncate_inline_inode(inode, ipage, 0); + f2fs_truncate_inline_inode(inode, ipage, 0); clear_inode_flag(inode, FI_INLINE_DATA); f2fs_put_page(ipage, 1); } else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) { - if (truncate_blocks(inode, 0, false)) + if (f2fs_truncate_blocks(inode, 0, false)) return false; goto process_inline; } return false; } -struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir, +struct f2fs_dir_entry *f2fs_find_in_inline_dir(struct inode *dir, struct fscrypt_name *fname, struct page **res_page) { struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb); @@ -311,7 +334,7 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir, void *inline_dentry; f2fs_hash_t namehash; - ipage = get_node_page(sbi, dir->i_ino); + ipage = f2fs_get_node_page(sbi, dir->i_ino); if (IS_ERR(ipage)) { *res_page = ipage; return NULL; @@ -322,7 +345,7 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir, inline_dentry = inline_data_addr(dir, ipage); make_dentry_ptr_inline(dir, &d, inline_dentry); - de = find_target_dentry(fname, namehash, NULL, &d); + de = f2fs_find_target_dentry(fname, namehash, NULL, &d); unlock_page(ipage); if (de) *res_page = ipage; @@ -332,7 +355,7 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir, return de; } -int make_empty_inline_dir(struct inode *inode, struct inode *parent, +int f2fs_make_empty_inline_dir(struct inode *inode, struct inode *parent, struct page *ipage) { struct f2fs_dentry_ptr d; @@ -341,7 +364,7 @@ int make_empty_inline_dir(struct inode *inode, struct inode *parent, inline_dentry = inline_data_addr(inode, ipage); make_dentry_ptr_inline(inode, &d, inline_dentry); - do_make_empty_dir(inode, parent, &d); + f2fs_do_make_empty_dir(inode, parent, &d); set_page_dirty(ipage); @@ -386,10 +409,9 @@ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage, goto out; } - f2fs_wait_on_page_writeback(page, DATA, true); - zero_user_segment(page, MAX_INLINE_DATA(dir), PAGE_SIZE); + f2fs_wait_on_page_writeback(page, DATA, true, true); - dentry_blk = kmap_atomic(page); + dentry_blk = page_address(page); make_dentry_ptr_inline(dir, &src, inline_dentry); make_dentry_ptr_block(dir, &dst, dentry_blk); @@ -406,13 +428,12 @@ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage, memcpy(dst.dentry, src.dentry, SIZE_OF_DIR_ENTRY * src.max); memcpy(dst.filename, src.filename, src.max * F2FS_SLOT_LEN); - kunmap_atomic(dentry_blk); if (!PageUptodate(page)) SetPageUptodate(page); set_page_dirty(page); /* clear inline dir and flag after data writeback */ - truncate_inline_inode(dir, ipage, 0); + f2fs_truncate_inline_inode(dir, ipage, 0); stat_dec_inline_dir(dir); clear_inode_flag(dir, FI_INLINE_DENTRY); @@ -455,7 +476,7 @@ static int f2fs_add_inline_entries(struct inode *dir, void *inline_dentry) new_name.len = le16_to_cpu(de->name_len); ino = le32_to_cpu(de->ino); - fake_mode = get_de_type(de) << S_SHIFT; + fake_mode = f2fs_get_de_type(de) << S_SHIFT; err = f2fs_add_regular_entry(dir, &new_name, NULL, NULL, ino, fake_mode); @@ -467,8 +488,8 @@ static int f2fs_add_inline_entries(struct inode *dir, void *inline_dentry) return 0; punch_dentry_pages: truncate_inode_pages(&dir->i_data, 0); - truncate_blocks(dir, 0, false); - remove_dirty_inode(dir); + f2fs_truncate_blocks(dir, 0, false); + f2fs_remove_dirty_inode(dir); return err; } @@ -486,7 +507,7 @@ static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage, } memcpy(backup_dentry, inline_dentry, MAX_INLINE_DATA(dir)); - truncate_inline_inode(dir, ipage, 0); + f2fs_truncate_inline_inode(dir, ipage, 0); unlock_page(ipage); @@ -498,18 +519,18 @@ static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage, stat_dec_inline_dir(dir); clear_inode_flag(dir, FI_INLINE_DENTRY); - kfree(backup_dentry); + kvfree(backup_dentry); return 0; recover: lock_page(ipage); - f2fs_wait_on_page_writeback(ipage, NODE, true); + f2fs_wait_on_page_writeback(ipage, NODE, true, true); memcpy(inline_dentry, backup_dentry, MAX_INLINE_DATA(dir)); f2fs_i_depth_write(dir, 0); f2fs_i_size_write(dir, MAX_INLINE_DATA(dir)); set_page_dirty(ipage); f2fs_put_page(ipage, 1); - kfree(backup_dentry); + kvfree(backup_dentry); return err; } @@ -536,14 +557,14 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name, struct page *page = NULL; int err = 0; - ipage = get_node_page(sbi, dir->i_ino); + ipage = f2fs_get_node_page(sbi, dir->i_ino); if (IS_ERR(ipage)) return PTR_ERR(ipage); inline_dentry = inline_data_addr(dir, ipage); make_dentry_ptr_inline(dir, &d, inline_dentry); - bit_pos = room_for_filename(d.bitmap, slots, d.max); + bit_pos = f2fs_room_for_filename(d.bitmap, slots, d.max); if (bit_pos >= d.max) { err = f2fs_convert_inline_dir(dir, ipage, inline_dentry); if (err) @@ -554,7 +575,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name, if (inode) { down_write(&F2FS_I(inode)->i_sem); - page = init_inode_metadata(inode, dir, new_name, + page = f2fs_init_inode_metadata(inode, dir, new_name, orig_name, ipage); if (IS_ERR(page)) { err = PTR_ERR(page); @@ -562,7 +583,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name, } } - f2fs_wait_on_page_writeback(ipage, NODE, true); + f2fs_wait_on_page_writeback(ipage, NODE, true, true); name_hash = f2fs_dentry_hash(new_name, NULL); f2fs_update_dentry(ino, mode, &d, new_name, name_hash, bit_pos); @@ -575,7 +596,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name, f2fs_put_page(page, 1); } - update_parent_metadata(dir, inode, 0); + f2fs_update_parent_metadata(dir, inode, 0); fail: if (inode) up_write(&F2FS_I(inode)->i_sem); @@ -594,7 +615,7 @@ void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page, int i; lock_page(page); - f2fs_wait_on_page_writeback(page, NODE, true); + f2fs_wait_on_page_writeback(page, NODE, true, true); inline_dentry = inline_data_addr(dir, page); make_dentry_ptr_inline(dir, &d, inline_dentry); @@ -621,7 +642,7 @@ bool f2fs_empty_inline_dir(struct inode *dir) void *inline_dentry; struct f2fs_dentry_ptr d; - ipage = get_node_page(sbi, dir->i_ino); + ipage = f2fs_get_node_page(sbi, dir->i_ino); if (IS_ERR(ipage)) return false; @@ -652,7 +673,7 @@ int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx, if (ctx->pos == d.max) return 0; - ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino); + ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino); if (IS_ERR(ipage)) return PTR_ERR(ipage); @@ -684,7 +705,7 @@ int f2fs_inline_data_fiemap(struct inode *inode, struct page *ipage; int err = 0; - ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino); + ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino); if (IS_ERR(ipage)) return PTR_ERR(ipage); @@ -700,7 +721,10 @@ int f2fs_inline_data_fiemap(struct inode *inode, ilen = start + len; ilen -= start; - get_node_info(F2FS_I_SB(inode), inode->i_ino, &ni); + err = f2fs_get_node_info(F2FS_I_SB(inode), inode->i_ino, &ni); + if (err) + goto out; + byteaddr = (__u64)ni.blk_addr << inode->i_sb->s_blocksize_bits; byteaddr += (char *)inline_data_addr(inode, ipage) - (char *)F2FS_INODE(ipage); diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index c6d0687f00fe..e9cd54afd14a 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/inode.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> @@ -17,11 +14,15 @@ #include "f2fs.h" #include "node.h" #include "segment.h" +#include "xattr.h" #include <trace/events/f2fs.h> void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync) { + if (is_inode_flag_set(inode, FI_NEW_INODE)) + return; + if (f2fs_inode_dirtied(inode, sync)) return; @@ -33,18 +34,21 @@ void f2fs_set_inode_flags(struct inode *inode) unsigned int flags = F2FS_I(inode)->i_flags; unsigned int new_fl = 0; - if (flags & FS_SYNC_FL) + if (flags & F2FS_SYNC_FL) new_fl |= S_SYNC; - if (flags & FS_APPEND_FL) + if (flags & F2FS_APPEND_FL) new_fl |= S_APPEND; - if (flags & FS_IMMUTABLE_FL) + if (flags & F2FS_IMMUTABLE_FL) new_fl |= S_IMMUTABLE; - if (flags & FS_NOATIME_FL) + if (flags & F2FS_NOATIME_FL) new_fl |= S_NOATIME; - if (flags & FS_DIRSYNC_FL) + if (flags & F2FS_DIRSYNC_FL) new_fl |= S_DIRSYNC; + if (f2fs_encrypted_inode(inode)) + new_fl |= S_ENCRYPTED; inode_set_flags(inode, new_fl, - S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC); + S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC| + S_ENCRYPTED); } static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri) @@ -100,7 +104,7 @@ static void __recover_inline_status(struct inode *inode, struct page *ipage) while (start < end) { if (*start++) { - f2fs_wait_on_page_writeback(ipage, NODE, true); + f2fs_wait_on_page_writeback(ipage, NODE, true, true); set_inode_flag(inode, FI_DATA_EXIST); set_raw_inline(inode, F2FS_INODE(ipage)); @@ -114,15 +118,15 @@ static void __recover_inline_status(struct inode *inode, struct page *ipage) static bool f2fs_enable_inode_chksum(struct f2fs_sb_info *sbi, struct page *page) { struct f2fs_inode *ri = &F2FS_NODE(page)->i; - int extra_isize = le32_to_cpu(ri->i_extra_isize); - if (!f2fs_sb_has_inode_chksum(sbi->sb)) + if (!f2fs_sb_has_inode_chksum(sbi)) return false; - if (!RAW_IS_INODE(F2FS_NODE(page)) || !(ri->i_inline & F2FS_EXTRA_ATTR)) + if (!IS_INODE(page) || !(ri->i_inline & F2FS_EXTRA_ATTR)) return false; - if (!F2FS_FITS_IN_INODE(ri, extra_isize, i_inode_checksum)) + if (!F2FS_FITS_IN_INODE(ri, le16_to_cpu(ri->i_extra_isize), + i_inode_checksum)) return false; return true; @@ -156,8 +160,15 @@ bool f2fs_inode_chksum_verify(struct f2fs_sb_info *sbi, struct page *page) struct f2fs_inode *ri; __u32 provided, calculated; + if (unlikely(is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN))) + return true; + +#ifdef CONFIG_F2FS_CHECK_FS + if (!f2fs_enable_inode_chksum(sbi, page)) +#else if (!f2fs_enable_inode_chksum(sbi, page) || PageDirty(page) || PageWriteback(page)) +#endif return true; ri = &F2FS_NODE(page)->i; @@ -208,8 +219,17 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page) return false; } + if (f2fs_sb_has_flexible_inline_xattr(sbi) + && !f2fs_has_extra_attr(inode)) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_msg(sbi->sb, KERN_WARNING, + "%s: corrupted inode ino=%lx, run fsck to fix.", + __func__, inode->i_ino); + return false; + } + if (f2fs_has_extra_attr(inode) && - !f2fs_sb_has_extra_attr(sbi->sb)) { + !f2fs_sb_has_extra_attr(sbi)) { set_sbi_flag(sbi, SBI_NEED_FSCK); f2fs_msg(sbi->sb, KERN_WARNING, "%s: inode (ino=%lx) is with extra_attr, " @@ -229,6 +249,20 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page) return false; } + if (f2fs_has_extra_attr(inode) && + f2fs_sb_has_flexible_inline_xattr(sbi) && + f2fs_has_inline_xattr(inode) && + (!fi->i_inline_xattr_size || + fi->i_inline_xattr_size > MAX_INLINE_XATTR_SIZE)) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_msg(sbi->sb, KERN_WARNING, + "%s: inode (ino=%lx) has corrupted " + "i_inline_xattr_size: %d, max: %zu", + __func__, inode->i_ino, fi->i_inline_xattr_size, + MAX_INLINE_XATTR_SIZE); + return false; + } + if (F2FS_I(inode)->extent_tree) { struct extent_info *ei = &F2FS_I(inode)->extent_tree->largest; @@ -245,6 +279,26 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page) return false; } } + + if (f2fs_has_inline_data(inode) && + (!S_ISREG(inode->i_mode) && !S_ISLNK(inode->i_mode))) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_msg(sbi->sb, KERN_WARNING, + "%s: inode (ino=%lx, mode=%u) should not have " + "inline_data, run fsck to fix", + __func__, inode->i_ino, inode->i_mode); + return false; + } + + if (f2fs_has_inline_dentry(inode) && !S_ISDIR(inode->i_mode)) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_msg(sbi->sb, KERN_WARNING, + "%s: inode (ino=%lx, mode=%u) should not have " + "inline_dentry, run fsck to fix", + __func__, inode->i_ino, inode->i_mode); + return false; + } + return true; } @@ -258,10 +312,10 @@ static int do_read_inode(struct inode *inode) int err; /* Check if ino is within scope */ - if (check_nid_range(sbi, inode->i_ino)) + if (f2fs_check_nid_range(sbi, inode->i_ino)) return -EINVAL; - node_page = get_node_page(sbi, inode->i_ino); + node_page = f2fs_get_node_page(sbi, inode->i_ino); if (IS_ERR(node_page)) return PTR_ERR(node_page); @@ -281,8 +335,11 @@ static int do_read_inode(struct inode *inode) inode->i_ctime.tv_nsec = le32_to_cpu(ri->i_ctime_nsec); inode->i_mtime.tv_nsec = le32_to_cpu(ri->i_mtime_nsec); inode->i_generation = le32_to_cpu(ri->i_generation); - - fi->i_current_depth = le32_to_cpu(ri->i_current_depth); + if (S_ISDIR(inode->i_mode)) + fi->i_current_depth = le32_to_cpu(ri->i_current_depth); + else if (S_ISREG(inode->i_mode)) + fi->i_gc_failures[GC_FAILURE_PIN] = + le16_to_cpu(ri->i_gc_failures); fi->i_xattr_nid = le32_to_cpu(ri->i_xattr_nid); fi->i_flags = le32_to_cpu(ri->i_flags); fi->flags = 0; @@ -298,6 +355,22 @@ static int do_read_inode(struct inode *inode) fi->i_extra_isize = f2fs_has_extra_attr(inode) ? le16_to_cpu(ri->i_extra_isize) : 0; + if (f2fs_sb_has_flexible_inline_xattr(sbi)) { + fi->i_inline_xattr_size = le16_to_cpu(ri->i_inline_xattr_size); + } else if (f2fs_has_inline_xattr(inode) || + f2fs_has_inline_dentry(inode)) { + fi->i_inline_xattr_size = DEFAULT_INLINE_XATTR_ADDRS; + } else { + + /* + * Previous inline data or directory always reserved 200 bytes + * in inode layout, even if inline_xattr is disabled. In order + * to keep inline_dentry's structure for backward compatibility, + * we get the space back only from inline_data. + */ + fi->i_inline_xattr_size = 0; + } + if (!sanity_check_inode(inode, node_page)) { f2fs_put_page(node_page, 1); return -EFSCORRUPTED; @@ -307,30 +380,48 @@ static int do_read_inode(struct inode *inode) if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode)) __recover_inline_status(inode, node_page); + /* try to recover cold bit for non-dir inode */ + if (!S_ISDIR(inode->i_mode) && !is_cold_node(node_page)) { + set_cold_node(node_page, false); + set_page_dirty(node_page); + } + /* get rdev by using inline_info */ __get_inode_rdev(inode, ri); - err = __written_first_block(sbi, ri); - if (err < 0) { - f2fs_put_page(node_page, 1); - return err; + if (S_ISREG(inode->i_mode)) { + err = __written_first_block(sbi, ri); + if (err < 0) { + f2fs_put_page(node_page, 1); + return err; + } + if (!err) + set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN); } - if (!err) - set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN); - if (!need_inode_block_update(sbi, inode->i_ino)) + if (!f2fs_need_inode_block_update(sbi, inode->i_ino)) fi->last_disk_size = inode->i_size; - if (fi->i_flags & FS_PROJINHERIT_FL) + if (fi->i_flags & F2FS_PROJINHERIT_FL) set_inode_flag(inode, FI_PROJ_INHERIT); - if (f2fs_has_extra_attr(inode) && f2fs_sb_has_project_quota(sbi->sb) && + if (f2fs_has_extra_attr(inode) && f2fs_sb_has_project_quota(sbi) && F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_projid)) i_projid = (projid_t)le32_to_cpu(ri->i_projid); else i_projid = F2FS_DEF_PROJID; fi->i_projid = make_kprojid(&init_user_ns, i_projid); + if (f2fs_has_extra_attr(inode) && f2fs_sb_has_inode_crtime(sbi) && + F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_crtime)) { + fi->i_crtime.tv_sec = le64_to_cpu(ri->i_crtime); + fi->i_crtime.tv_nsec = le32_to_cpu(ri->i_crtime_nsec); + } + + F2FS_I(inode)->i_disk_time[0] = inode->i_atime; + F2FS_I(inode)->i_disk_time[1] = inode->i_ctime; + F2FS_I(inode)->i_disk_time[2] = inode->i_mtime; + F2FS_I(inode)->i_disk_time[3] = F2FS_I(inode)->i_crtime; f2fs_put_page(node_page, 1); stat_inc_inline_xattr(inode); @@ -363,10 +454,10 @@ struct inode *f2fs_iget(struct super_block *sb, unsigned long ino) make_now: if (ino == F2FS_NODE_INO(sbi)) { inode->i_mapping->a_ops = &f2fs_node_aops; - mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO); + mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); } else if (ino == F2FS_META_INO(sbi)) { inode->i_mapping->a_ops = &f2fs_meta_aops; - mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO); + mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); } else if (S_ISREG(inode->i_mode)) { inode->i_op = &f2fs_file_inode_operations; inode->i_fop = &f2fs_file_operations; @@ -375,7 +466,7 @@ make_now: inode->i_op = &f2fs_dir_inode_operations; inode->i_fop = &f2fs_dir_operations; inode->i_mapping->a_ops = &f2fs_dblock_aops; - mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_HIGH_ZERO); + inode_nohighmem(inode); } else if (S_ISLNK(inode->i_mode)) { if (f2fs_encrypted_inode(inode)) inode->i_op = &f2fs_encrypted_symlink_inode_operations; @@ -417,14 +508,15 @@ retry: return inode; } -int update_inode(struct inode *inode, struct page *node_page) +void f2fs_update_inode(struct inode *inode, struct page *node_page) { struct f2fs_inode *ri; struct extent_tree *et = F2FS_I(inode)->extent_tree; - f2fs_inode_synced(inode); + f2fs_wait_on_page_writeback(node_page, NODE, true, true); + set_page_dirty(node_page); - f2fs_wait_on_page_writeback(node_page, NODE, true); + f2fs_inode_synced(inode); ri = F2FS_INODE(node_page); @@ -451,7 +543,12 @@ int update_inode(struct inode *inode, struct page *node_page) ri->i_atime_nsec = cpu_to_le32(inode->i_atime.tv_nsec); ri->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec); ri->i_mtime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec); - ri->i_current_depth = cpu_to_le32(F2FS_I(inode)->i_current_depth); + if (S_ISDIR(inode->i_mode)) + ri->i_current_depth = + cpu_to_le32(F2FS_I(inode)->i_current_depth); + else if (S_ISREG(inode->i_mode)) + ri->i_gc_failures = + cpu_to_le16(F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN]); ri->i_xattr_nid = cpu_to_le32(F2FS_I(inode)->i_xattr_nid); ri->i_flags = cpu_to_le32(F2FS_I(inode)->i_flags); ri->i_pino = cpu_to_le32(F2FS_I(inode)->i_pino); @@ -461,7 +558,11 @@ int update_inode(struct inode *inode, struct page *node_page) if (f2fs_has_extra_attr(inode)) { ri->i_extra_isize = cpu_to_le16(F2FS_I(inode)->i_extra_isize); - if (f2fs_sb_has_project_quota(F2FS_I_SB(inode)->sb) && + if (f2fs_sb_has_flexible_inline_xattr(F2FS_I_SB(inode))) + ri->i_inline_xattr_size = + cpu_to_le16(F2FS_I(inode)->i_inline_xattr_size); + + if (f2fs_sb_has_project_quota(F2FS_I_SB(inode)) && F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize, i_projid)) { projid_t i_projid; @@ -470,25 +571,39 @@ int update_inode(struct inode *inode, struct page *node_page) F2FS_I(inode)->i_projid); ri->i_projid = cpu_to_le32(i_projid); } + + if (f2fs_sb_has_inode_crtime(F2FS_I_SB(inode)) && + F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize, + i_crtime)) { + ri->i_crtime = + cpu_to_le64(F2FS_I(inode)->i_crtime.tv_sec); + ri->i_crtime_nsec = + cpu_to_le32(F2FS_I(inode)->i_crtime.tv_nsec); + } } __set_inode_rdev(inode, ri); - set_cold_node(inode, node_page); /* deleted inode */ if (inode->i_nlink == 0) clear_inline_node(node_page); - return set_page_dirty(node_page); + F2FS_I(inode)->i_disk_time[0] = inode->i_atime; + F2FS_I(inode)->i_disk_time[1] = inode->i_ctime; + F2FS_I(inode)->i_disk_time[2] = inode->i_mtime; + F2FS_I(inode)->i_disk_time[3] = F2FS_I(inode)->i_crtime; + +#ifdef CONFIG_F2FS_CHECK_FS + f2fs_inode_chksum_set(F2FS_I_SB(inode), node_page); +#endif } -int update_inode_page(struct inode *inode) +void f2fs_update_inode_page(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct page *node_page; - int ret = 0; retry: - node_page = get_node_page(sbi, inode->i_ino); + node_page = f2fs_get_node_page(sbi, inode->i_ino); if (IS_ERR(node_page)) { int err = PTR_ERR(node_page); if (err == -ENOMEM) { @@ -497,11 +612,10 @@ retry: } else if (err != -ENOENT) { f2fs_stop_checkpoint(sbi, false); } - return 0; + return; } - ret = update_inode(inode, node_page); + f2fs_update_inode(inode, node_page); f2fs_put_page(node_page, 1); - return ret; } int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc) @@ -515,11 +629,14 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc) if (!is_inode_flag_set(inode, FI_DIRTY_INODE)) return 0; + if (f2fs_is_checkpoint_ready(sbi)) + return -ENOSPC; + /* * We need to balance fs here to prevent from producing dirty node pages * during the urgent cleaning time when runing out of free sections. */ - update_inode_page(inode); + f2fs_update_inode_page(inode); if (wbc && wbc->nr_to_write) f2fs_balance_fs(sbi, true); return 0; @@ -536,7 +653,7 @@ void f2fs_evict_inode(struct inode *inode) /* some remained atomic pages should discarded */ if (f2fs_is_atomic_file(inode)) - drop_inmem_pages(inode); + f2fs_drop_inmem_pages(inode); trace_f2fs_evict_inode(inode); truncate_inode_pages_final(&inode->i_data); @@ -546,17 +663,22 @@ void f2fs_evict_inode(struct inode *inode) goto out_clear; f2fs_bug_on(sbi, get_dirty_pages(inode)); - remove_dirty_inode(inode); + f2fs_remove_dirty_inode(inode); f2fs_destroy_extent_tree(inode); if (inode->i_nlink || is_bad_inode(inode)) goto no_delete; - dquot_initialize(inode); + err = dquot_initialize(inode); + if (err) { + err = 0; + set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + } - remove_ino_entry(sbi, inode->i_ino, APPEND_INO); - remove_ino_entry(sbi, inode->i_ino, UPDATE_INO); + f2fs_remove_ino_entry(sbi, inode->i_ino, APPEND_INO); + f2fs_remove_ino_entry(sbi, inode->i_ino, UPDATE_INO); + f2fs_remove_ino_entry(sbi, inode->i_ino, FLUSH_INO); sb_start_intwrite(inode->i_sb); set_inode_flag(inode, FI_NO_ALLOC); @@ -565,15 +687,14 @@ retry: if (F2FS_HAS_BLOCKS(inode)) err = f2fs_truncate(inode); -#ifdef CONFIG_F2FS_FAULT_INJECTION if (time_to_inject(sbi, FAULT_EVICT_INODE)) { f2fs_show_injection_info(FAULT_EVICT_INODE); err = -EIO; } -#endif + if (!err) { f2fs_lock_op(sbi); - err = remove_inode_page(inode); + err = f2fs_remove_inode_page(inode); f2fs_unlock_op(sbi); if (err == -ENOENT) err = 0; @@ -585,9 +706,10 @@ retry: goto retry; } - if (err) - update_inode_page(inode); - dquot_free_inode(inode); + if (err) { + f2fs_update_inode_page(inode); + set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + } sb_end_intwrite(inode->i_sb); no_delete: dquot_drop(inode); @@ -596,8 +718,11 @@ no_delete: stat_dec_inline_dir(inode); stat_dec_inline_inode(inode); - if (!is_set_ckpt_flags(sbi, CP_ERROR_FLAG)) + if (likely(!is_set_ckpt_flags(sbi, CP_ERROR_FLAG) && + !is_sbi_flag_set(sbi, SBI_CP_DISABLED))) f2fs_bug_on(sbi, is_inode_flag_set(inode, FI_DIRTY_INODE)); + else + f2fs_inode_synced(inode); /* ino == 0, if f2fs_new_inode() was failed t*/ if (inode->i_ino) @@ -607,30 +732,31 @@ no_delete: invalidate_mapping_pages(NODE_MAPPING(sbi), xnid, xnid); if (inode->i_nlink) { if (is_inode_flag_set(inode, FI_APPEND_WRITE)) - add_ino_entry(sbi, inode->i_ino, APPEND_INO); + f2fs_add_ino_entry(sbi, inode->i_ino, APPEND_INO); if (is_inode_flag_set(inode, FI_UPDATE_WRITE)) - add_ino_entry(sbi, inode->i_ino, UPDATE_INO); + f2fs_add_ino_entry(sbi, inode->i_ino, UPDATE_INO); } if (is_inode_flag_set(inode, FI_FREE_NID)) { - alloc_nid_failed(sbi, inode->i_ino); + f2fs_alloc_nid_failed(sbi, inode->i_ino); clear_inode_flag(inode, FI_FREE_NID); } else { /* * If xattr nid is corrupted, we can reach out error condition, - * err & !exist_written_data(sbi, inode->i_ino, ORPHAN_INO)). - * In that case, check_nid_range() is enough to give a clue. + * err & !f2fs_exist_written_data(sbi, inode->i_ino, ORPHAN_INO)). + * In that case, f2fs_check_nid_range() is enough to give a clue. */ } out_clear: - fscrypt_put_encryption_info(inode, NULL); + fscrypt_put_encryption_info(inode); clear_inode(inode); } /* caller should call f2fs_lock_op() */ -void handle_failed_inode(struct inode *inode) +void f2fs_handle_failed_inode(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct node_info ni; + int err; /* * clear nlink of inode in order to release resource of inode @@ -642,7 +768,7 @@ void handle_failed_inode(struct inode *inode) * we must call this to avoid inode being remained as dirty, resulting * in a panic when flushing dirty inodes in gdirty_list. */ - update_inode_page(inode); + f2fs_update_inode_page(inode); f2fs_inode_synced(inode); /* don't make bad inode, since it becomes a regular file. */ @@ -653,22 +779,29 @@ void handle_failed_inode(struct inode *inode) * so we can prevent losing this orphan when encoutering checkpoint * and following suddenly power-off. */ - get_node_info(sbi, inode->i_ino, &ni); + err = f2fs_get_node_info(sbi, inode->i_ino, &ni); + if (err) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_msg(sbi->sb, KERN_WARNING, + "May loss orphan inode, run fsck to fix."); + goto out; + } if (ni.blk_addr != NULL_ADDR) { - int err = acquire_orphan_inode(sbi); + err = f2fs_acquire_orphan_inode(sbi); if (err) { set_sbi_flag(sbi, SBI_NEED_FSCK); f2fs_msg(sbi->sb, KERN_WARNING, "Too many orphan inodes, run fsck to fix."); } else { - add_orphan_inode(inode); + f2fs_add_orphan_inode(inode); } - alloc_nid_done(sbi, inode->i_ino); + f2fs_alloc_nid_done(sbi, inode->i_ino); } else { set_inode_flag(inode, FI_FREE_NID); } +out: f2fs_unlock_op(sbi); /* iput will drop the inode object */ diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index b13383948fca..4a1503631f70 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -1,24 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/namei.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> #include <linux/pagemap.h> #include <linux/sched.h> #include <linux/ctype.h> +#include <linux/random.h> #include <linux/dcache.h> #include <linux/namei.h> #include <linux/quotaops.h> #include "f2fs.h" #include "node.h" +#include "segment.h" #include "xattr.h" #include "acl.h" #include <trace/events/f2fs.h> @@ -29,6 +28,7 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) nid_t ino; struct inode *inode; bool nid_free = false; + int xattr_size = 0; int err; inode = new_inode(dir->i_sb); @@ -36,7 +36,7 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) return ERR_PTR(-ENOMEM); f2fs_lock_op(sbi); - if (!alloc_nid(sbi, &ino)) { + if (!f2fs_alloc_nid(sbi, &ino)) { f2fs_unlock_op(sbi); err = -ENOSPC; goto fail; @@ -49,8 +49,12 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) inode->i_ino = ino; inode->i_blocks = 0; - inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); - inode->i_generation = sbi->s_next_generation++; + inode->i_mtime = inode->i_atime = inode->i_ctime = + F2FS_I(inode)->i_crtime = current_time(inode); + inode->i_generation = prandom_u32(); + + if (S_ISDIR(inode->i_mode)) + F2FS_I(inode)->i_current_depth = 1; err = insert_inode_locked(inode); if (err) { @@ -58,8 +62,8 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) goto fail; } - if (f2fs_sb_has_project_quota(sbi->sb) && - (F2FS_I(dir)->i_flags & FS_PROJINHERIT_FL)) + if (f2fs_sb_has_project_quota(sbi) && + (F2FS_I(dir)->i_flags & F2FS_PROJINHERIT_FL)) F2FS_I(inode)->i_projid = F2FS_I(dir)->i_projid; else F2FS_I(inode)->i_projid = make_kprojid(&init_user_ns, @@ -69,28 +73,37 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) if (err) goto fail_drop; - err = dquot_alloc_inode(inode); - if (err) - goto fail_drop; + set_inode_flag(inode, FI_NEW_INODE); /* If the directory encrypted, then we should encrypt the inode. */ - if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode)) + if ((f2fs_encrypted_inode(dir) || DUMMY_ENCRYPTION_ENABLED(sbi)) && + f2fs_may_encrypt(inode)) f2fs_set_encrypted_inode(inode); - set_inode_flag(inode, FI_NEW_INODE); - - if (f2fs_sb_has_extra_attr(sbi->sb)) { + if (f2fs_sb_has_extra_attr(sbi)) { set_inode_flag(inode, FI_EXTRA_ATTR); F2FS_I(inode)->i_extra_isize = F2FS_TOTAL_EXTRA_ATTR_SIZE; } if (test_opt(sbi, INLINE_XATTR)) set_inode_flag(inode, FI_INLINE_XATTR); + if (test_opt(sbi, INLINE_DATA) && f2fs_may_inline_data(inode)) set_inode_flag(inode, FI_INLINE_DATA); if (f2fs_may_inline_dentry(inode)) set_inode_flag(inode, FI_INLINE_DENTRY); + if (f2fs_sb_has_flexible_inline_xattr(sbi)) { + f2fs_bug_on(sbi, !f2fs_has_extra_attr(inode)); + if (f2fs_has_inline_xattr(inode)) + xattr_size = F2FS_OPTION(sbi).inline_xattr_size; + /* Otherwise, will be 0 */ + } else if (f2fs_has_inline_xattr(inode) || + f2fs_has_inline_dentry(inode)) { + xattr_size = DEFAULT_INLINE_XATTR_ADDRS; + } + F2FS_I(inode)->i_inline_xattr_size = xattr_size; + f2fs_init_extent_tree(inode, NULL); stat_inc_inline_xattr(inode); @@ -101,11 +114,13 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) f2fs_mask_flags(mode, F2FS_I(dir)->i_flags & F2FS_FL_INHERITED); if (S_ISDIR(inode->i_mode)) - F2FS_I(inode)->i_flags |= FS_INDEX_FL; + F2FS_I(inode)->i_flags |= F2FS_INDEX_FL; - if (F2FS_I(inode)->i_flags & FS_PROJINHERIT_FL) + if (F2FS_I(inode)->i_flags & F2FS_PROJINHERIT_FL) set_inode_flag(inode, FI_PROJ_INHERIT); + f2fs_set_inode_flags(inode); + trace_f2fs_new_inode(inode, 0); return inode; @@ -128,7 +143,7 @@ fail_drop: return ERR_PTR(err); } -static int is_multimedia_file(const unsigned char *s, const char *sub) +static int is_extension_exist(const unsigned char *s, const char *sub) { size_t slen = strlen(s); size_t sublen = strlen(sub); @@ -154,19 +169,97 @@ static int is_multimedia_file(const unsigned char *s, const char *sub) /* * Set multimedia files as cold files for hot/cold data separation */ -static inline void set_cold_files(struct f2fs_sb_info *sbi, struct inode *inode, +static inline void set_file_temperature(struct f2fs_sb_info *sbi, struct inode *inode, const unsigned char *name) { - int i; - __u8 (*extlist)[8] = sbi->raw_super->extension_list; + __u8 (*extlist)[F2FS_EXTENSION_LEN] = sbi->raw_super->extension_list; + int i, cold_count, hot_count; + + down_read(&sbi->sb_lock); + + cold_count = le32_to_cpu(sbi->raw_super->extension_count); + hot_count = sbi->raw_super->hot_ext_count; - int count = le32_to_cpu(sbi->raw_super->extension_count); - for (i = 0; i < count; i++) { - if (is_multimedia_file(name, extlist[i])) { - file_set_cold(inode); + for (i = 0; i < cold_count + hot_count; i++) { + if (is_extension_exist(name, extlist[i])) break; - } } + + up_read(&sbi->sb_lock); + + if (i == cold_count + hot_count) + return; + + if (i < cold_count) + file_set_cold(inode); + else + file_set_hot(inode); +} + +int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name, + bool hot, bool set) +{ + __u8 (*extlist)[F2FS_EXTENSION_LEN] = sbi->raw_super->extension_list; + int cold_count = le32_to_cpu(sbi->raw_super->extension_count); + int hot_count = sbi->raw_super->hot_ext_count; + int total_count = cold_count + hot_count; + int start, count; + int i; + + if (set) { + if (total_count == F2FS_MAX_EXTENSION) + return -EINVAL; + } else { + if (!hot && !cold_count) + return -EINVAL; + if (hot && !hot_count) + return -EINVAL; + } + + if (hot) { + start = cold_count; + count = total_count; + } else { + start = 0; + count = cold_count; + } + + for (i = start; i < count; i++) { + if (strcmp(name, extlist[i])) + continue; + + if (set) + return -EINVAL; + + memcpy(extlist[i], extlist[i + 1], + F2FS_EXTENSION_LEN * (total_count - i - 1)); + memset(extlist[total_count - 1], 0, F2FS_EXTENSION_LEN); + if (hot) + sbi->raw_super->hot_ext_count = hot_count - 1; + else + sbi->raw_super->extension_count = + cpu_to_le32(cold_count - 1); + return 0; + } + + if (!set) + return -EINVAL; + + if (hot) { + memcpy(extlist[count], name, strlen(name)); + sbi->raw_super->hot_ext_count = hot_count + 1; + } else { + char buf[F2FS_MAX_EXTENSION][F2FS_EXTENSION_LEN]; + + memcpy(buf, &extlist[cold_count], + F2FS_EXTENSION_LEN * hot_count); + memset(extlist[cold_count], 0, F2FS_EXTENSION_LEN); + memcpy(extlist[cold_count], name, strlen(name)); + memcpy(&extlist[cold_count + 1], buf, + F2FS_EXTENSION_LEN * hot_count); + sbi->raw_super->extension_count = cpu_to_le32(cold_count + 1); + } + return 0; } static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode, @@ -177,6 +270,12 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode, nid_t ino = 0; int err; + if (unlikely(f2fs_cp_error(sbi))) + return -EIO; + err = f2fs_is_checkpoint_ready(sbi); + if (err) + return err; + err = dquot_initialize(dir); if (err) return err; @@ -186,7 +285,7 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode, return PTR_ERR(inode); if (!test_opt(sbi, DISABLE_EXT_IDENTIFY)) - set_cold_files(sbi, inode, dentry->d_name.name); + set_file_temperature(sbi, inode, dentry->d_name.name); inode->i_op = &f2fs_file_inode_operations; inode->i_fop = &f2fs_file_operations; @@ -199,7 +298,7 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode, goto out; f2fs_unlock_op(sbi); - alloc_nid_done(sbi, ino); + f2fs_alloc_nid_done(sbi, ino); d_instantiate_new(dentry, inode); @@ -209,7 +308,7 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode, f2fs_balance_fs(sbi, true); return 0; out: - handle_failed_inode(inode); + f2fs_handle_failed_inode(inode); return err; } @@ -220,9 +319,15 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir, struct f2fs_sb_info *sbi = F2FS_I_SB(dir); int err; - if (f2fs_encrypted_inode(dir) && - !fscrypt_has_permitted_context(dir, inode)) - return -EPERM; + if (unlikely(f2fs_cp_error(sbi))) + return -EIO; + err = f2fs_is_checkpoint_ready(sbi); + if (err) + return err; + + err = fscrypt_prepare_link(old_dentry, dir, dentry); + if (err) + return err; if (is_inode_flag_set(dir, FI_PROJ_INHERIT) && (!projid_eq(F2FS_I(dir)->i_projid, @@ -296,26 +401,23 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino) de = f2fs_find_entry(dir, &dot, &page); if (de) { - f2fs_dentry_kunmap(dir, page); f2fs_put_page(page, 0); } else if (IS_ERR(page)) { err = PTR_ERR(page); goto out; } else { - err = __f2fs_add_link(dir, &dot, NULL, dir->i_ino, S_IFDIR); + err = f2fs_do_add_link(dir, &dot, NULL, dir->i_ino, S_IFDIR); if (err) goto out; } de = f2fs_find_entry(dir, &dotdot, &page); - if (de) { - f2fs_dentry_kunmap(dir, page); + if (de) f2fs_put_page(page, 0); - } else if (IS_ERR(page)) { + else if (IS_ERR(page)) err = PTR_ERR(page); - } else { - err = __f2fs_add_link(dir, &dotdot, NULL, pino, S_IFDIR); - } + else + err = f2fs_do_add_link(dir, &dotdot, NULL, pino, S_IFDIR); out: if (!err) clear_inode_flag(dir, FI_INLINE_DOTS); @@ -330,53 +432,50 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry, struct inode *inode = NULL; struct f2fs_dir_entry *de; struct page *page; - nid_t ino; + struct dentry *new; + nid_t ino = -1; int err = 0; unsigned int root_ino = F2FS_ROOT_INO(F2FS_I_SB(dir)); - if (f2fs_encrypted_inode(dir)) { - int res = fscrypt_get_encryption_info(dir); + trace_f2fs_lookup_start(dir, dentry, flags); - /* - * DCACHE_ENCRYPTED_WITH_KEY is set if the dentry is - * created while the directory was encrypted and we - * don't have access to the key. - */ - if (fscrypt_has_encryption_key(dir)) - fscrypt_set_encrypted_dentry(dentry); - fscrypt_set_d_op(dentry); - if (res && res != -ENOKEY) - return ERR_PTR(res); - } + err = fscrypt_prepare_lookup(dir, dentry, flags); + if (err) + goto out; - if (dentry->d_name.len > F2FS_NAME_LEN) - return ERR_PTR(-ENAMETOOLONG); + if (dentry->d_name.len > F2FS_NAME_LEN) { + err = -ENAMETOOLONG; + goto out; + } de = f2fs_find_entry(dir, &dentry->d_name, &page); if (!de) { - if (IS_ERR(page)) - return (struct dentry *)page; - return d_splice_alias(inode, dentry); + if (IS_ERR(page)) { + err = PTR_ERR(page); + goto out; + } + goto out_splice; } ino = le32_to_cpu(de->ino); - f2fs_dentry_kunmap(dir, page); f2fs_put_page(page, 0); inode = f2fs_iget(dir->i_sb, ino); - if (IS_ERR(inode)) - return ERR_CAST(inode); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + goto out; + } if ((dir->i_ino == root_ino) && f2fs_has_inline_dots(dir)) { err = __recover_dot_dentries(dir, root_ino); if (err) - goto err_out; + goto out_iput; } if (f2fs_has_inline_dots(inode)) { err = __recover_dot_dentries(inode, dir->i_ino); if (err) - goto err_out; + goto out_iput; } if (f2fs_encrypted_inode(dir) && (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) && @@ -385,12 +484,18 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry, "Inconsistent encryption contexts: %lu/%lu", dir->i_ino, inode->i_ino); err = -EPERM; - goto err_out; + goto out_iput; } - return d_splice_alias(inode, dentry); - -err_out: +out_splice: + new = d_splice_alias(inode, dentry); + if (IS_ERR(new)) + err = PTR_ERR(new); + trace_f2fs_lookup_end(dir, dentry, ino, err); + return new; +out_iput: iput(inode); +out: + trace_f2fs_lookup_end(dir, dentry, ino, err); return ERR_PTR(err); } @@ -404,9 +509,15 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry) trace_f2fs_unlink_enter(dir, dentry); + if (unlikely(f2fs_cp_error(sbi))) + return -EIO; + err = dquot_initialize(dir); if (err) return err; + err = dquot_initialize(inode); + if (err) + return err; de = f2fs_find_entry(dir, &dentry->d_name, &page); if (!de) { @@ -418,10 +529,9 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry) f2fs_balance_fs(sbi, true); f2fs_lock_op(sbi); - err = acquire_orphan_inode(sbi); + err = f2fs_acquire_orphan_inode(sbi); if (err) { f2fs_unlock_op(sbi); - f2fs_dentry_kunmap(dir, page); f2fs_put_page(page, 0); goto fail; } @@ -455,24 +565,19 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry, struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct inode *inode; size_t len = strlen(symname); - struct fscrypt_str disk_link = FSTR_INIT((char *)symname, len + 1); - struct fscrypt_symlink_data *sd = NULL; + struct fscrypt_str disk_link; int err; - if (f2fs_encrypted_inode(dir)) { - err = fscrypt_get_encryption_info(dir); - if (err) - return err; - - if (!fscrypt_has_encryption_key(dir)) - return -ENOKEY; - - disk_link.len = (fscrypt_fname_encrypted_size(dir, len) + - sizeof(struct fscrypt_symlink_data)); - } + if (unlikely(f2fs_cp_error(sbi))) + return -EIO; + err = f2fs_is_checkpoint_ready(sbi); + if (err) + return err; - if (disk_link.len > dir->i_sb->s_blocksize) - return -ENAMETOOLONG; + err = fscrypt_prepare_symlink(dir, symname, len, dir->i_sb->s_blocksize, + &disk_link); + if (err) + return err; err = dquot_initialize(dir); if (err) @@ -482,7 +587,7 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry, if (IS_ERR(inode)) return PTR_ERR(inode); - if (f2fs_encrypted_inode(inode)) + if (IS_ENCRYPTED(inode)) inode->i_op = &f2fs_encrypted_symlink_inode_operations; else inode->i_op = &f2fs_symlink_inode_operations; @@ -492,38 +597,13 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry, f2fs_lock_op(sbi); err = f2fs_add_link(dentry, inode); if (err) - goto out; + goto out_f2fs_handle_failed_inode; f2fs_unlock_op(sbi); - alloc_nid_done(sbi, inode->i_ino); + f2fs_alloc_nid_done(sbi, inode->i_ino); - if (f2fs_encrypted_inode(inode)) { - struct qstr istr = QSTR_INIT(symname, len); - struct fscrypt_str ostr; - - sd = kzalloc(disk_link.len, GFP_NOFS); - if (!sd) { - err = -ENOMEM; - goto err_out; - } - - err = fscrypt_get_encryption_info(inode); - if (err) - goto err_out; - - if (!fscrypt_has_encryption_key(inode)) { - err = -ENOKEY; - goto err_out; - } - - ostr.name = sd->encrypted_path; - ostr.len = disk_link.len; - err = fscrypt_fname_usr_to_disk(inode, &istr, &ostr); - if (err) - goto err_out; - - sd->len = cpu_to_le16(ostr.len); - disk_link.name = (char *)sd; - } + err = fscrypt_encrypt_symlink(inode, symname, len, &disk_link); + if (err) + goto err_out; err = page_symlink(inode, disk_link.name, disk_link.len); @@ -549,12 +629,14 @@ err_out: f2fs_unlink(dir, dentry); } - kfree(sd); - f2fs_balance_fs(sbi, true); - return err; -out: - handle_failed_inode(inode); + goto out_free_encrypted_link; + +out_f2fs_handle_failed_inode: + f2fs_handle_failed_inode(inode); +out_free_encrypted_link: + if (disk_link.name != (unsigned char *)symname) + kvfree(disk_link.name); return err; } @@ -564,6 +646,9 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) struct inode *inode; int err; + if (unlikely(f2fs_cp_error(sbi))) + return -EIO; + err = dquot_initialize(dir); if (err) return err; @@ -575,7 +660,7 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) inode->i_op = &f2fs_dir_inode_operations; inode->i_fop = &f2fs_dir_operations; inode->i_mapping->a_ops = &f2fs_dblock_aops; - mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_HIGH_ZERO); + inode_nohighmem(inode); set_inode_flag(inode, FI_INC_LINK); f2fs_lock_op(sbi); @@ -584,7 +669,7 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) goto out_fail; f2fs_unlock_op(sbi); - alloc_nid_done(sbi, inode->i_ino); + f2fs_alloc_nid_done(sbi, inode->i_ino); d_instantiate_new(dentry, inode); @@ -596,7 +681,7 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) out_fail: clear_inode_flag(inode, FI_INC_LINK); - handle_failed_inode(inode); + f2fs_handle_failed_inode(inode); return err; } @@ -615,6 +700,12 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry, struct inode *inode; int err = 0; + if (unlikely(f2fs_cp_error(sbi))) + return -EIO; + err = f2fs_is_checkpoint_ready(sbi); + if (err) + return err; + err = dquot_initialize(dir); if (err) return err; @@ -632,7 +723,7 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry, goto out; f2fs_unlock_op(sbi); - alloc_nid_done(sbi, inode->i_ino); + f2fs_alloc_nid_done(sbi, inode->i_ino); d_instantiate_new(dentry, inode); @@ -642,7 +733,7 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry, f2fs_balance_fs(sbi, true); return 0; out: - handle_failed_inode(inode); + f2fs_handle_failed_inode(inode); return err; } @@ -671,7 +762,7 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry, } f2fs_lock_op(sbi); - err = acquire_orphan_inode(sbi); + err = f2fs_acquire_orphan_inode(sbi); if (err) goto out; @@ -683,8 +774,8 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry, * add this non-linked tmpfile to orphan list, in this way we could * remove all unused data of tmpfile after abnormal power-off. */ - add_orphan_inode(inode); - alloc_nid_done(sbi, inode->i_ino); + f2fs_add_orphan_inode(inode); + f2fs_alloc_nid_done(sbi, inode->i_ino); if (whiteout) { f2fs_i_links_write(inode, false); @@ -700,15 +791,20 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry, return 0; release_out: - release_orphan_inode(sbi); + f2fs_release_orphan_inode(sbi); out: - handle_failed_inode(inode); + f2fs_handle_failed_inode(inode); return err; } static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) { - if (f2fs_encrypted_inode(dir)) { + struct f2fs_sb_info *sbi = F2FS_I_SB(dir); + + if (unlikely(f2fs_cp_error(sbi))) + return -EIO; + + if (f2fs_encrypted_inode(dir) || DUMMY_ENCRYPTION_ENABLED(sbi)) { int err = fscrypt_get_encryption_info(dir); if (err) return err; @@ -719,6 +815,9 @@ static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) static int f2fs_create_whiteout(struct inode *dir, struct inode **whiteout) { + if (unlikely(f2fs_cp_error(F2FS_I_SB(dir)))) + return -EIO; + return __f2fs_tmpfile(dir, NULL, S_IFCHR | WHITEOUT_MODE, whiteout); } @@ -736,19 +835,13 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, struct f2fs_dir_entry *old_entry; struct f2fs_dir_entry *new_entry; bool is_old_inline = f2fs_has_inline_dentry(old_dir); - int err = -ENOENT; - - if ((f2fs_encrypted_inode(old_dir) && - !fscrypt_has_encryption_key(old_dir)) || - (f2fs_encrypted_inode(new_dir) && - !fscrypt_has_encryption_key(new_dir))) - return -ENOKEY; + int err; - if ((old_dir != new_dir) && f2fs_encrypted_inode(new_dir) && - !fscrypt_has_permitted_context(new_dir, old_inode)) { - err = -EPERM; - goto out; - } + if (unlikely(f2fs_cp_error(sbi))) + return -EIO; + err = f2fs_is_checkpoint_ready(sbi); + if (err) + return err; if (is_inode_flag_set(new_dir, FI_PROJ_INHERIT) && (!projid_eq(F2FS_I(new_dir)->i_projid, @@ -763,6 +856,13 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, if (err) goto out; + if (new_inode) { + err = dquot_initialize(new_inode); + if (err) + goto out; + } + + err = -ENOENT; old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page); if (!old_entry) { if (IS_ERR(old_page)) @@ -804,7 +904,7 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, f2fs_lock_op(sbi); - err = acquire_orphan_inode(sbi); + err = f2fs_acquire_orphan_inode(sbi); if (err) goto put_out_dir; @@ -818,9 +918,9 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, up_write(&F2FS_I(new_inode)->i_sem); if (!new_inode->i_nlink) - add_orphan_inode(new_inode); + f2fs_add_orphan_inode(new_inode); else - release_orphan_inode(sbi); + f2fs_release_orphan_inode(sbi); } else { f2fs_balance_fs(sbi, true); @@ -882,38 +982,39 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, } if (old_dir_entry) { - if (old_dir != new_dir && !whiteout) { + if (old_dir != new_dir && !whiteout) f2fs_set_link(old_inode, old_dir_entry, old_dir_page, new_dir); - } else { - f2fs_dentry_kunmap(old_inode, old_dir_page); + else f2fs_put_page(old_dir_page, 0); - } f2fs_i_links_write(old_dir, false); } + if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT) { + f2fs_add_ino_entry(sbi, new_dir->i_ino, TRANS_DIR_INO); + if (S_ISDIR(old_inode->i_mode)) + f2fs_add_ino_entry(sbi, old_inode->i_ino, + TRANS_DIR_INO); + } f2fs_unlock_op(sbi); if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir)) f2fs_sync_fs(sbi->sb, 1); + + f2fs_update_time(sbi, REQ_TIME); return 0; put_out_dir: f2fs_unlock_op(sbi); - if (new_page) { - f2fs_dentry_kunmap(new_dir, new_page); + if (new_page) f2fs_put_page(new_page, 0); - } out_whiteout: if (whiteout) iput(whiteout); out_dir: - if (old_dir_entry) { - f2fs_dentry_kunmap(old_inode, old_dir_page); + if (old_dir_entry) f2fs_put_page(old_dir_page, 0); - } out_old: - f2fs_dentry_kunmap(old_dir, old_page); f2fs_put_page(old_page, 0); out: return err; @@ -930,19 +1031,13 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, struct f2fs_dir_entry *old_dir_entry = NULL, *new_dir_entry = NULL; struct f2fs_dir_entry *old_entry, *new_entry; int old_nlink = 0, new_nlink = 0; - int err = -ENOENT; - - if ((f2fs_encrypted_inode(old_dir) && - !fscrypt_has_encryption_key(old_dir)) || - (f2fs_encrypted_inode(new_dir) && - !fscrypt_has_encryption_key(new_dir))) - return -ENOKEY; + int err; - if ((f2fs_encrypted_inode(old_dir) || f2fs_encrypted_inode(new_dir)) && - (old_dir != new_dir) && - (!fscrypt_has_permitted_context(new_dir, old_inode) || - !fscrypt_has_permitted_context(old_dir, new_inode))) - return -EPERM; + if (unlikely(f2fs_cp_error(sbi))) + return -EIO; + err = f2fs_is_checkpoint_ready(sbi); + if (err) + return err; if ((is_inode_flag_set(new_dir, FI_PROJ_INHERIT) && !projid_eq(F2FS_I(new_dir)->i_projid, @@ -960,6 +1055,7 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, if (err) goto out; + err = -ENOENT; old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page); if (!old_entry) { if (IS_ERR(old_page)) @@ -1062,26 +1158,29 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, } f2fs_mark_inode_dirty_sync(new_dir, false); + if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT) { + f2fs_add_ino_entry(sbi, old_dir->i_ino, TRANS_DIR_INO); + f2fs_add_ino_entry(sbi, new_dir->i_ino, TRANS_DIR_INO); + } + f2fs_unlock_op(sbi); if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir)) f2fs_sync_fs(sbi->sb, 1); + + f2fs_update_time(sbi, REQ_TIME); return 0; out_new_dir: if (new_dir_entry) { - f2fs_dentry_kunmap(new_inode, new_dir_page); f2fs_put_page(new_dir_page, 0); } out_old_dir: if (old_dir_entry) { - f2fs_dentry_kunmap(old_inode, old_dir_page); f2fs_put_page(old_dir_page, 0); } out_new: - f2fs_dentry_kunmap(new_dir, new_page); f2fs_put_page(new_page, 0); out_old: - f2fs_dentry_kunmap(old_dir, old_page); f2fs_put_page(old_page, 0); out: return err; @@ -1091,9 +1190,16 @@ static int f2fs_rename2(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { + int err; + if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) return -EINVAL; + err = fscrypt_prepare_rename(old_dir, old_dentry, new_dir, new_dentry, + flags); + if (err) + return err; + if (flags & RENAME_EXCHANGE) { return f2fs_cross_rename(old_dir, old_dentry, new_dir, new_dentry); @@ -1109,68 +1215,20 @@ static const char *f2fs_encrypted_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { - struct page *cpage = NULL; - char *caddr, *paddr = NULL; - struct fscrypt_str cstr = FSTR_INIT(NULL, 0); - struct fscrypt_str pstr = FSTR_INIT(NULL, 0); - struct fscrypt_symlink_data *sd; - u32 max_size = inode->i_sb->s_blocksize; - int res; + struct page *page; + const char *target; if (!dentry) return ERR_PTR(-ECHILD); - res = fscrypt_get_encryption_info(inode); - if (res) - return ERR_PTR(res); - - cpage = read_mapping_page(inode->i_mapping, 0, NULL); - if (IS_ERR(cpage)) - return ERR_CAST(cpage); - caddr = page_address(cpage); - - /* Symlink is encrypted */ - sd = (struct fscrypt_symlink_data *)caddr; - cstr.name = sd->encrypted_path; - cstr.len = le16_to_cpu(sd->len); - - /* this is broken symlink case */ - if (unlikely(cstr.len == 0)) { - res = -ENOENT; - goto errout; - } - - if ((cstr.len + sizeof(struct fscrypt_symlink_data) - 1) > max_size) { - /* Symlink data on the disk is corrupted */ - res = -EIO; - goto errout; - } - res = fscrypt_fname_alloc_buffer(inode, cstr.len, &pstr); - if (res) - goto errout; - - res = fscrypt_fname_disk_to_usr(inode, 0, 0, &cstr, &pstr); - if (res) - goto errout; - - /* this is broken symlink case */ - if (unlikely(pstr.name[0] == 0)) { - res = -ENOENT; - goto errout; - } - - paddr = pstr.name; - - /* Null-terminate the name */ - paddr[pstr.len] = '\0'; + page = read_mapping_page(inode->i_mapping, 0, NULL); + if (IS_ERR(page)) + return ERR_CAST(page); - put_page(cpage); - set_delayed_call(done, kfree_link, paddr); - return paddr; -errout: - fscrypt_fname_free_buffer(&pstr); - put_page(cpage); - return ERR_PTR(res); + target = fscrypt_get_symlink(inode, page_address(page), + inode->i_sb->s_blocksize, done); + put_page(page); + return target; } const struct inode_operations f2fs_encrypted_symlink_inode_operations = { diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index e7b8e2b35e22..94c3cf7f3162 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/node.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> @@ -23,16 +20,17 @@ #include "trace.h" #include <trace/events/f2fs.h> -#define on_build_free_nids(nmi) mutex_is_locked(&(nm_i)->build_lock) +#define on_f2fs_build_free_nids(nmi) mutex_is_locked(&(nm_i)->build_lock) static struct kmem_cache *nat_entry_slab; static struct kmem_cache *free_nid_slab; static struct kmem_cache *nat_entry_set_slab; +static struct kmem_cache *fsync_node_entry_slab; /* * Check whether the given nid is within node id range. */ -int check_nid_range(struct f2fs_sb_info *sbi, nid_t nid) +int f2fs_check_nid_range(struct f2fs_sb_info *sbi, nid_t nid) { if (unlikely(nid < F2FS_ROOT_INO(sbi) || nid >= NM_I(sbi)->max_nid)) { set_sbi_flag(sbi, SBI_NEED_FSCK); @@ -44,7 +42,7 @@ int check_nid_range(struct f2fs_sb_info *sbi, nid_t nid) return 0; } -bool available_free_memory(struct f2fs_sb_info *sbi, int type) +bool f2fs_available_free_memory(struct f2fs_sb_info *sbi, int type) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct sysinfo val; @@ -61,7 +59,7 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type) * give 25%, 25%, 50%, 50%, 50% memory for each components respectively */ if (type == FREE_NIDS) { - mem_size = (nm_i->nid_cnt[FREE_NID_LIST] * + mem_size = (nm_i->nid_cnt[FREE_NID] * sizeof(struct free_nid)) >> PAGE_SHIFT; res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2); } else if (type == NAT_ENTRIES) { @@ -78,7 +76,7 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type) } else if (type == INO_ENTRIES) { int i; - for (i = 0; i <= UPDATE_INO; i++) + for (i = 0; i < MAX_INO_ENTRY; i++) mem_size += sbi->im[i].ino_num * sizeof(struct ino_entry); mem_size >>= PAGE_SHIFT; @@ -89,6 +87,10 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type) atomic_read(&sbi->total_ext_node) * sizeof(struct extent_node)) >> PAGE_SHIFT; res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1); + } else if (type == INMEM_PAGES) { + /* it allows 20% / total_ram for inmemory pages */ + mem_size = get_pages(sbi, F2FS_INMEM_PAGES); + res = mem_size < (val.totalram / 5); } else { if (!sbi->sb->s_bdi->wb.dirty_exceeded) return true; @@ -98,44 +100,35 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type) static void clear_node_page_dirty(struct page *page) { - struct address_space *mapping = page->mapping; - unsigned int long flags; - if (PageDirty(page)) { - spin_lock_irqsave(&mapping->tree_lock, flags); - radix_tree_tag_clear(&mapping->page_tree, - page_index(page), - PAGECACHE_TAG_DIRTY); - spin_unlock_irqrestore(&mapping->tree_lock, flags); - + f2fs_clear_radix_tree_dirty_tag(page); clear_page_dirty_for_io(page); - dec_page_count(F2FS_M_SB(mapping), F2FS_DIRTY_NODES); + dec_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES); } ClearPageUptodate(page); } static struct page *get_current_nat_page(struct f2fs_sb_info *sbi, nid_t nid) { - pgoff_t index = current_nat_addr(sbi, nid); - return get_meta_page(sbi, index); + return f2fs_get_meta_page_nofail(sbi, current_nat_addr(sbi, nid)); } static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid) { struct page *src_page; struct page *dst_page; - pgoff_t src_off; pgoff_t dst_off; void *src_addr; void *dst_addr; struct f2fs_nm_info *nm_i = NM_I(sbi); - src_off = current_nat_addr(sbi, nid); - dst_off = next_nat_addr(sbi, src_off); + dst_off = next_nat_addr(sbi, current_nat_addr(sbi, nid)); /* get current nat block page with lock */ - src_page = get_meta_page(sbi, src_off); - dst_page = grab_meta_page(sbi, dst_off); + src_page = get_current_nat_page(sbi, nid); + if (IS_ERR(src_page)) + return src_page; + dst_page = f2fs_grab_meta_page(sbi, dst_off); f2fs_bug_on(sbi, PageDirty(src_page)); src_addr = page_address(src_page); @@ -149,9 +142,61 @@ static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid) return dst_page; } +static struct nat_entry *__alloc_nat_entry(nid_t nid, bool no_fail) +{ + struct nat_entry *new; + + if (no_fail) + new = f2fs_kmem_cache_alloc(nat_entry_slab, GFP_F2FS_ZERO); + else + new = kmem_cache_alloc(nat_entry_slab, GFP_F2FS_ZERO); + if (new) { + nat_set_nid(new, nid); + nat_reset_flag(new); + } + return new; +} + +static void __free_nat_entry(struct nat_entry *e) +{ + kmem_cache_free(nat_entry_slab, e); +} + +/* must be locked by nat_tree_lock */ +static struct nat_entry *__init_nat_entry(struct f2fs_nm_info *nm_i, + struct nat_entry *ne, struct f2fs_nat_entry *raw_ne, bool no_fail) +{ + if (no_fail) + f2fs_radix_tree_insert(&nm_i->nat_root, nat_get_nid(ne), ne); + else if (radix_tree_insert(&nm_i->nat_root, nat_get_nid(ne), ne)) + return NULL; + + if (raw_ne) + node_info_from_raw_nat(&ne->ni, raw_ne); + + spin_lock(&nm_i->nat_list_lock); + list_add_tail(&ne->list, &nm_i->nat_entries); + spin_unlock(&nm_i->nat_list_lock); + + nm_i->nat_cnt++; + return ne; +} + static struct nat_entry *__lookup_nat_cache(struct f2fs_nm_info *nm_i, nid_t n) { - return radix_tree_lookup(&nm_i->nat_root, n); + struct nat_entry *ne; + + ne = radix_tree_lookup(&nm_i->nat_root, n); + + /* for recent accessed nat entry, move it to tail of lru list */ + if (ne && !get_nat_flag(ne, IS_DIRTY)) { + spin_lock(&nm_i->nat_list_lock); + if (!list_empty(&ne->list)) + list_move_tail(&ne->list, &nm_i->nat_entries); + spin_unlock(&nm_i->nat_list_lock); + } + + return ne; } static unsigned int __gang_lookup_nat_cache(struct f2fs_nm_info *nm_i, @@ -162,14 +207,13 @@ static unsigned int __gang_lookup_nat_cache(struct f2fs_nm_info *nm_i, static void __del_from_nat_cache(struct f2fs_nm_info *nm_i, struct nat_entry *e) { - list_del(&e->list); radix_tree_delete(&nm_i->nat_root, nat_get_nid(e)); nm_i->nat_cnt--; - kmem_cache_free(nat_entry_slab, e); + __free_nat_entry(e); } -static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i, - struct nat_entry *ne) +static struct nat_entry_set *__grab_nat_entry_set(struct f2fs_nm_info *nm_i, + struct nat_entry *ne) { nid_t set = NAT_BLOCK_OFFSET(ne->ni.nid); struct nat_entry_set *head; @@ -184,24 +228,50 @@ static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i, head->entry_cnt = 0; f2fs_radix_tree_insert(&nm_i->nat_set_root, set, head); } + return head; +} + +static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i, + struct nat_entry *ne) +{ + struct nat_entry_set *head; + bool new_ne = nat_get_blkaddr(ne) == NEW_ADDR; + + if (!new_ne) + head = __grab_nat_entry_set(nm_i, ne); + + /* + * update entry_cnt in below condition: + * 1. update NEW_ADDR to valid block address; + * 2. update old block address to new one; + */ + if (!new_ne && (get_nat_flag(ne, IS_PREALLOC) || + !get_nat_flag(ne, IS_DIRTY))) + head->entry_cnt++; + + set_nat_flag(ne, IS_PREALLOC, new_ne); if (get_nat_flag(ne, IS_DIRTY)) goto refresh_list; nm_i->dirty_nat_cnt++; - head->entry_cnt++; set_nat_flag(ne, IS_DIRTY, true); refresh_list: - if (nat_get_blkaddr(ne) == NEW_ADDR) + spin_lock(&nm_i->nat_list_lock); + if (new_ne) list_del_init(&ne->list); else list_move_tail(&ne->list, &head->entry_list); + spin_unlock(&nm_i->nat_list_lock); } static void __clear_nat_cache_dirty(struct f2fs_nm_info *nm_i, struct nat_entry_set *set, struct nat_entry *ne) { + spin_lock(&nm_i->nat_list_lock); list_move_tail(&ne->list, &nm_i->nat_entries); + spin_unlock(&nm_i->nat_list_lock); + set_nat_flag(ne, IS_DIRTY, false); set->entry_cnt--; nm_i->dirty_nat_cnt--; @@ -214,7 +284,73 @@ static unsigned int __gang_lookup_nat_set(struct f2fs_nm_info *nm_i, start, nr); } -int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid) +bool f2fs_in_warm_node_list(struct f2fs_sb_info *sbi, struct page *page) +{ + return NODE_MAPPING(sbi) == page->mapping && + IS_DNODE(page) && is_cold_node(page); +} + +void f2fs_init_fsync_node_info(struct f2fs_sb_info *sbi) +{ + spin_lock_init(&sbi->fsync_node_lock); + INIT_LIST_HEAD(&sbi->fsync_node_list); + sbi->fsync_seg_id = 0; + sbi->fsync_node_num = 0; +} + +static unsigned int f2fs_add_fsync_node_entry(struct f2fs_sb_info *sbi, + struct page *page) +{ + struct fsync_node_entry *fn; + unsigned long flags; + unsigned int seq_id; + + fn = f2fs_kmem_cache_alloc(fsync_node_entry_slab, GFP_NOFS); + + get_page(page); + fn->page = page; + INIT_LIST_HEAD(&fn->list); + + spin_lock_irqsave(&sbi->fsync_node_lock, flags); + list_add_tail(&fn->list, &sbi->fsync_node_list); + fn->seq_id = sbi->fsync_seg_id++; + seq_id = fn->seq_id; + sbi->fsync_node_num++; + spin_unlock_irqrestore(&sbi->fsync_node_lock, flags); + + return seq_id; +} + +void f2fs_del_fsync_node_entry(struct f2fs_sb_info *sbi, struct page *page) +{ + struct fsync_node_entry *fn; + unsigned long flags; + + spin_lock_irqsave(&sbi->fsync_node_lock, flags); + list_for_each_entry(fn, &sbi->fsync_node_list, list) { + if (fn->page == page) { + list_del(&fn->list); + sbi->fsync_node_num--; + spin_unlock_irqrestore(&sbi->fsync_node_lock, flags); + kmem_cache_free(fsync_node_entry_slab, fn); + put_page(page); + return; + } + } + spin_unlock_irqrestore(&sbi->fsync_node_lock, flags); + f2fs_bug_on(sbi, 1); +} + +void f2fs_reset_fsync_node_info(struct f2fs_sb_info *sbi) +{ + unsigned long flags; + + spin_lock_irqsave(&sbi->fsync_node_lock, flags); + sbi->fsync_seg_id = 0; + spin_unlock_irqrestore(&sbi->fsync_node_lock, flags); +} + +int f2fs_need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; @@ -231,7 +367,7 @@ int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid) return need; } -bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid) +bool f2fs_is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; @@ -245,7 +381,7 @@ bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid) return is_cp; } -bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino) +bool f2fs_need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; @@ -261,49 +397,29 @@ bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino) return need_update; } -static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid, - bool no_fail) -{ - struct nat_entry *new; - - if (no_fail) { - new = f2fs_kmem_cache_alloc(nat_entry_slab, GFP_NOFS); - f2fs_radix_tree_insert(&nm_i->nat_root, nid, new); - } else { - new = kmem_cache_alloc(nat_entry_slab, GFP_NOFS); - if (!new) - return NULL; - if (radix_tree_insert(&nm_i->nat_root, nid, new)) { - kmem_cache_free(nat_entry_slab, new); - return NULL; - } - } - - memset(new, 0, sizeof(struct nat_entry)); - nat_set_nid(new, nid); - nat_reset_flag(new); - list_add_tail(&new->list, &nm_i->nat_entries); - nm_i->nat_cnt++; - return new; -} - +/* must be locked by nat_tree_lock */ static void cache_nat_entry(struct f2fs_sb_info *sbi, nid_t nid, struct f2fs_nat_entry *ne) { struct f2fs_nm_info *nm_i = NM_I(sbi); - struct nat_entry *e; + struct nat_entry *new, *e; + + new = __alloc_nat_entry(nid, false); + if (!new) + return; + down_write(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, nid); - if (!e) { - e = grab_nat_entry(nm_i, nid, false); - if (e) - node_info_from_raw_nat(&e->ni, ne); - } else { + if (!e) + e = __init_nat_entry(nm_i, new, ne, false); + else f2fs_bug_on(sbi, nat_get_ino(e) != le32_to_cpu(ne->ino) || nat_get_blkaddr(e) != le32_to_cpu(ne->block_addr) || nat_get_version(e) != ne->version); - } + up_write(&nm_i->nat_tree_lock); + if (e != new) + __free_nat_entry(new); } static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, @@ -311,11 +427,12 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, { struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; + struct nat_entry *new = __alloc_nat_entry(ni->nid, true); down_write(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, ni->nid); if (!e) { - e = grab_nat_entry(nm_i, ni->nid, true); + e = __init_nat_entry(nm_i, new, NULL, true); copy_node_info(&e->ni, ni); f2fs_bug_on(sbi, ni->blk_addr == NEW_ADDR); } else if (new_blkaddr == NEW_ADDR) { @@ -327,6 +444,9 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, copy_node_info(&e->ni, ni); f2fs_bug_on(sbi, ni->blk_addr != NULL_ADDR); } + /* let's free early to reduce memory consumption */ + if (e != new) + __free_nat_entry(new); /* sanity check */ f2fs_bug_on(sbi, nat_get_blkaddr(e) != ni->blk_addr); @@ -341,10 +461,6 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, if (nat_get_blkaddr(e) != NEW_ADDR && new_blkaddr == NULL_ADDR) { unsigned char version = nat_get_version(e); nat_set_version(e, inc_node_version(version)); - - /* in order to reuse the nid */ - if (nm_i->next_scan_nid > ni->nid) - nm_i->next_scan_nid = ni->nid; } /* change address */ @@ -364,7 +480,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, up_write(&nm_i->nat_tree_lock); } -int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) +int f2fs_try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) { struct f2fs_nm_info *nm_i = NM_I(sbi); int nr = nr_shrink; @@ -372,13 +488,25 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) if (!down_write_trylock(&nm_i->nat_tree_lock)) return 0; - while (nr_shrink && !list_empty(&nm_i->nat_entries)) { + spin_lock(&nm_i->nat_list_lock); + while (nr_shrink) { struct nat_entry *ne; + + if (list_empty(&nm_i->nat_entries)) + break; + ne = list_first_entry(&nm_i->nat_entries, struct nat_entry, list); + list_del(&ne->list); + spin_unlock(&nm_i->nat_list_lock); + __del_from_nat_cache(nm_i, ne); nr_shrink--; + + spin_lock(&nm_i->nat_list_lock); } + spin_unlock(&nm_i->nat_list_lock); + up_write(&nm_i->nat_tree_lock); return nr - nr_shrink; } @@ -386,7 +514,8 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) /* * This function always returns success */ -void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) +int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid, + struct node_info *ni) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); @@ -409,14 +538,14 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) ni->blk_addr = nat_get_blkaddr(e); ni->version = nat_get_version(e); up_read(&nm_i->nat_tree_lock); - return; + return 0; } memset(&ne, 0, sizeof(struct f2fs_nat_entry)); /* Check current segment summary */ down_read(&curseg->journal_rwsem); - i = lookup_journal_in_cursum(journal, NAT_JOURNAL, nid, 0); + i = f2fs_lookup_journal_in_cursum(journal, NAT_JOURNAL, nid, 0); if (i >= 0) { ne = nat_in_journal(journal, i); node_info_from_raw_nat(ni, &ne); @@ -431,22 +560,24 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) index = current_nat_addr(sbi, nid); up_read(&nm_i->nat_tree_lock); - page = get_meta_page(sbi, index); + page = f2fs_get_meta_page(sbi, index); + if (IS_ERR(page)) + return PTR_ERR(page); + nat_blk = (struct f2fs_nat_block *)page_address(page); ne = nat_blk->entries[nid - start_nid]; node_info_from_raw_nat(ni, &ne); f2fs_put_page(page, 1); cache: /* cache nat entry */ - down_write(&nm_i->nat_tree_lock); cache_nat_entry(sbi, nid, &ne); - up_write(&nm_i->nat_tree_lock); + return 0; } /* * readahead MAX_RA_NODE number of node pages. */ -static void ra_node_pages(struct page *parent, int start, int n) +static void f2fs_ra_node_pages(struct page *parent, int start, int n) { struct f2fs_sb_info *sbi = F2FS_P_SB(parent); struct blk_plug plug; @@ -460,13 +591,13 @@ static void ra_node_pages(struct page *parent, int start, int n) end = min(end, NIDS_PER_BLOCK); for (i = start; i < end; i++) { nid = get_nid(parent, i, false); - ra_node_page(sbi, nid); + f2fs_ra_node_page(sbi, nid); } blk_finish_plug(&plug); } -pgoff_t get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs) +pgoff_t f2fs_get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs) { const long direct_index = ADDRS_PER_INODE(dn->inode); const long direct_blks = ADDRS_PER_BLOCK; @@ -581,7 +712,7 @@ got: * f2fs_unlock_op() only if ro is not set RDONLY_NODE. * In the case of RDONLY_NODE, we don't need to care about mutex. */ -int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) +int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); struct page *npage[4]; @@ -600,7 +731,7 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) npage[0] = dn->inode_page; if (!npage[0]) { - npage[0] = get_node_page(sbi, nids[0]); + npage[0] = f2fs_get_node_page(sbi, nids[0]); if (IS_ERR(npage[0])) return PTR_ERR(npage[0]); } @@ -624,24 +755,24 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) if (!nids[i] && mode == ALLOC_NODE) { /* alloc new node */ - if (!alloc_nid(sbi, &(nids[i]))) { + if (!f2fs_alloc_nid(sbi, &(nids[i]))) { err = -ENOSPC; goto release_pages; } dn->nid = nids[i]; - npage[i] = new_node_page(dn, noffset[i]); + npage[i] = f2fs_new_node_page(dn, noffset[i]); if (IS_ERR(npage[i])) { - alloc_nid_failed(sbi, nids[i]); + f2fs_alloc_nid_failed(sbi, nids[i]); err = PTR_ERR(npage[i]); goto release_pages; } set_nid(parent, offset[i - 1], nids[i], i == 1); - alloc_nid_done(sbi, nids[i]); + f2fs_alloc_nid_done(sbi, nids[i]); done = true; } else if (mode == LOOKUP_NODE_RA && i == level && level > 1) { - npage[i] = get_node_page_ra(parent, offset[i - 1]); + npage[i] = f2fs_get_node_page_ra(parent, offset[i - 1]); if (IS_ERR(npage[i])) { err = PTR_ERR(npage[i]); goto release_pages; @@ -656,7 +787,7 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) } if (!done) { - npage[i] = get_node_page(sbi, nids[i]); + npage[i] = f2fs_get_node_page(sbi, nids[i]); if (IS_ERR(npage[i])) { err = PTR_ERR(npage[i]); f2fs_put_page(npage[0], 0); @@ -690,22 +821,24 @@ release_out: return err; } -static void truncate_node(struct dnode_of_data *dn) +static int truncate_node(struct dnode_of_data *dn) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); struct node_info ni; + int err; pgoff_t index; - get_node_info(sbi, dn->nid, &ni); - f2fs_bug_on(sbi, ni.blk_addr == NULL_ADDR); + err = f2fs_get_node_info(sbi, dn->nid, &ni); + if (err) + return err; /* Deallocate node address */ - invalidate_blocks(sbi, ni.blk_addr); + f2fs_invalidate_blocks(sbi, ni.blk_addr); dec_valid_node_count(sbi, dn->inode, dn->nid == dn->inode->i_ino); set_node_addr(sbi, &ni, NULL_ADDR, false); if (dn->nid == dn->inode->i_ino) { - remove_orphan_inode(sbi, dn->nid); + f2fs_remove_orphan_inode(sbi, dn->nid); dec_valid_inode_count(sbi); f2fs_inode_synced(dn->inode); } @@ -721,17 +854,20 @@ static void truncate_node(struct dnode_of_data *dn) dn->node_page = NULL; trace_f2fs_truncate_node(dn->inode, dn->nid, ni.blk_addr); + + return 0; } static int truncate_dnode(struct dnode_of_data *dn) { struct page *page; + int err; if (dn->nid == 0) return 1; /* get direct node */ - page = get_node_page(F2FS_I_SB(dn->inode), dn->nid); + page = f2fs_get_node_page(F2FS_I_SB(dn->inode), dn->nid); if (IS_ERR(page) && PTR_ERR(page) == -ENOENT) return 1; else if (IS_ERR(page)) @@ -740,8 +876,11 @@ static int truncate_dnode(struct dnode_of_data *dn) /* Make dnode_of_data for parameter */ dn->node_page = page; dn->ofs_in_node = 0; - truncate_data_blocks(dn); - truncate_node(dn); + f2fs_truncate_data_blocks(dn); + err = truncate_node(dn); + if (err) + return err; + return 1; } @@ -761,13 +900,13 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs, trace_f2fs_truncate_nodes_enter(dn->inode, dn->nid, dn->data_blkaddr); - page = get_node_page(F2FS_I_SB(dn->inode), dn->nid); + page = f2fs_get_node_page(F2FS_I_SB(dn->inode), dn->nid); if (IS_ERR(page)) { trace_f2fs_truncate_nodes_exit(dn->inode, PTR_ERR(page)); return PTR_ERR(page); } - ra_node_pages(page, ofs, NIDS_PER_BLOCK); + f2fs_ra_node_pages(page, ofs, NIDS_PER_BLOCK); rn = F2FS_NODE(page); if (depth < 3) { @@ -806,7 +945,9 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs, if (!ofs) { /* remove current indirect node */ dn->node_page = page; - truncate_node(dn); + ret = truncate_node(dn); + if (ret) + goto out_err; freed++; } else { f2fs_put_page(page, 1); @@ -837,7 +978,7 @@ static int truncate_partial_nodes(struct dnode_of_data *dn, /* get indirect nodes in the path */ for (i = 0; i < idx + 1; i++) { /* reference count'll be increased */ - pages[i] = get_node_page(F2FS_I_SB(dn->inode), nid[i]); + pages[i] = f2fs_get_node_page(F2FS_I_SB(dn->inode), nid[i]); if (IS_ERR(pages[i])) { err = PTR_ERR(pages[i]); idx = i - 1; @@ -846,7 +987,7 @@ static int truncate_partial_nodes(struct dnode_of_data *dn, nid[i + 1] = get_nid(pages[i], offset[i + 1], false); } - ra_node_pages(pages[idx], offset[idx + 1], NIDS_PER_BLOCK); + f2fs_ra_node_pages(pages[idx], offset[idx + 1], NIDS_PER_BLOCK); /* free direct nodes linked to a partial indirect node */ for (i = offset[idx + 1]; i < NIDS_PER_BLOCK; i++) { @@ -864,7 +1005,9 @@ static int truncate_partial_nodes(struct dnode_of_data *dn, if (offset[idx + 1] == 0) { dn->node_page = pages[idx]; dn->nid = nid[idx]; - truncate_node(dn); + err = truncate_node(dn); + if (err) + goto fail; } else { f2fs_put_page(pages[idx], 1); } @@ -883,7 +1026,7 @@ fail: /* * All the block addresses of data and nodes should be nullified. */ -int truncate_inode_blocks(struct inode *inode, pgoff_t from) +int f2fs_truncate_inode_blocks(struct inode *inode, pgoff_t from) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); int err = 0, cont = 1; @@ -899,7 +1042,7 @@ int truncate_inode_blocks(struct inode *inode, pgoff_t from) if (level < 0) return level; - page = get_node_page(sbi, inode->i_ino); + page = f2fs_get_node_page(sbi, inode->i_ino); if (IS_ERR(page)) { trace_f2fs_truncate_inode_blocks_exit(inode, PTR_ERR(page)); return PTR_ERR(page); @@ -963,7 +1106,7 @@ skip_partial: ri->i_nid[offset[0] - NODE_DIR1_BLOCK]) { lock_page(page); BUG_ON(page->mapping != NODE_MAPPING(sbi)); - f2fs_wait_on_page_writeback(page, NODE, true); + f2fs_wait_on_page_writeback(page, NODE, true, true); ri->i_nid[offset[0] - NODE_DIR1_BLOCK] = 0; set_page_dirty(page); unlock_page(page); @@ -978,27 +1121,31 @@ fail: return err > 0 ? 0 : err; } -int truncate_xattr_node(struct inode *inode, struct page *page) +/* caller must lock inode page */ +int f2fs_truncate_xattr_node(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); nid_t nid = F2FS_I(inode)->i_xattr_nid; struct dnode_of_data dn; struct page *npage; + int err; if (!nid) return 0; - npage = get_node_page(sbi, nid); + npage = f2fs_get_node_page(sbi, nid); if (IS_ERR(npage)) return PTR_ERR(npage); - f2fs_i_xnid_write(inode, 0); + set_new_dnode(&dn, inode, NULL, npage, nid); + err = truncate_node(&dn); + if (err) { + f2fs_put_page(npage, 1); + return err; + } - set_new_dnode(&dn, inode, page, npage, nid); + f2fs_i_xnid_write(inode, 0); - if (page) - dn.inode_page_locked = true; - truncate_node(&dn); return 0; } @@ -1006,17 +1153,17 @@ int truncate_xattr_node(struct inode *inode, struct page *page) * Caller should grab and release a rwsem by calling f2fs_lock_op() and * f2fs_unlock_op(). */ -int remove_inode_page(struct inode *inode) +int f2fs_remove_inode_page(struct inode *inode) { struct dnode_of_data dn; int err; set_new_dnode(&dn, inode, NULL, NULL, inode->i_ino); - err = get_dnode_of_data(&dn, 0, LOOKUP_NODE); + err = f2fs_get_dnode_of_data(&dn, 0, LOOKUP_NODE); if (err) return err; - err = truncate_xattr_node(inode, dn.inode_page); + err = f2fs_truncate_xattr_node(inode); if (err) { f2fs_put_dnode(&dn); return err; @@ -1025,18 +1172,26 @@ int remove_inode_page(struct inode *inode) /* remove potential inline_data blocks */ if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) - truncate_data_blocks_range(&dn, 1); + f2fs_truncate_data_blocks_range(&dn, 1); /* 0 is possible, after f2fs_new_inode() has failed */ + if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) { + f2fs_put_dnode(&dn); + return -EIO; + } f2fs_bug_on(F2FS_I_SB(inode), inode->i_blocks != 0 && inode->i_blocks != 8); /* will put inode & node pages */ - truncate_node(&dn); + err = truncate_node(&dn); + if (err) { + f2fs_put_dnode(&dn); + return err; + } return 0; } -struct page *new_inode_page(struct inode *inode) +struct page *f2fs_new_inode_page(struct inode *inode) { struct dnode_of_data dn; @@ -1044,10 +1199,10 @@ struct page *new_inode_page(struct inode *inode) set_new_dnode(&dn, inode, NULL, NULL, inode->i_ino); /* caller should f2fs_put_page(page, 1); */ - return new_node_page(&dn, 0); + return f2fs_new_node_page(&dn, 0); } -struct page *new_node_page(struct dnode_of_data *dn, unsigned int ofs) +struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); struct node_info new_ni; @@ -1065,7 +1220,11 @@ struct page *new_node_page(struct dnode_of_data *dn, unsigned int ofs) goto fail; #ifdef CONFIG_F2FS_CHECK_FS - get_node_info(sbi, dn->nid, &new_ni); + err = f2fs_get_node_info(sbi, dn->nid, &new_ni); + if (err) { + dec_valid_node_count(sbi, dn->inode, !ofs); + goto fail; + } f2fs_bug_on(sbi, new_ni.blk_addr != NULL_ADDR); #endif new_ni.nid = dn->nid; @@ -1075,9 +1234,9 @@ struct page *new_node_page(struct dnode_of_data *dn, unsigned int ofs) new_ni.version = 0; set_node_addr(sbi, &new_ni, NEW_ADDR, false); - f2fs_wait_on_page_writeback(page, NODE, true); + f2fs_wait_on_page_writeback(page, NODE, true, true); fill_node_footer(page, dn->nid, dn->inode->i_ino, ofs, true); - set_cold_node(dn->inode, page); + set_cold_node(page, S_ISDIR(dn->inode->i_mode)); if (!PageUptodate(page)) SetPageUptodate(page); if (set_page_dirty(page)) @@ -1113,13 +1272,21 @@ static int read_node_page(struct page *page, int op_flags) .page = page, .encrypted_page = NULL, }; + int err; - if (PageUptodate(page)) + if (PageUptodate(page)) { +#ifdef CONFIG_F2FS_CHECK_FS + f2fs_bug_on(sbi, !f2fs_inode_chksum_verify(sbi, page)); +#endif return LOCKED_PAGE; + } - get_node_info(sbi, page->index, &ni); + err = f2fs_get_node_info(sbi, page->index, &ni); + if (err) + return err; - if (unlikely(ni.blk_addr == NULL_ADDR)) { + if (unlikely(ni.blk_addr == NULL_ADDR) || + is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN)) { ClearPageUptodate(page); return -ENOENT; } @@ -1131,14 +1298,14 @@ static int read_node_page(struct page *page, int op_flags) /* * Readahead a node page */ -void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid) +void f2fs_ra_node_page(struct f2fs_sb_info *sbi, nid_t nid) { struct page *apage; int err; if (!nid) return; - if (check_nid_range(sbi, nid)) + if (f2fs_check_nid_range(sbi, nid)) return; rcu_read_lock(); @@ -1163,7 +1330,7 @@ static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid, if (!nid) return ERR_PTR(-ENOENT); - if (check_nid_range(sbi, nid)) + if (f2fs_check_nid_range(sbi, nid)) return ERR_PTR(-EINVAL); repeat: page = f2fs_grab_cache_page(NODE_MAPPING(sbi), nid, false); @@ -1180,7 +1347,7 @@ repeat: } if (parent) - ra_node_pages(parent, start + 1, MAX_RA_NODE); + f2fs_ra_node_pages(parent, start + 1, MAX_RA_NODE); lock_page(page); @@ -1214,12 +1381,12 @@ out_err: return page; } -struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid) +struct page *f2fs_get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid) { return __get_node_page(sbi, nid, NULL, 0); } -struct page *get_node_page_ra(struct page *parent, int start) +struct page *f2fs_get_node_page_ra(struct page *parent, int start) { struct f2fs_sb_info *sbi = F2FS_P_SB(parent); nid_t nid = get_nid(parent, start, false); @@ -1238,7 +1405,8 @@ static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino) if (!inode) return; - page = pagecache_get_page(inode->i_mapping, 0, FGP_LOCK|FGP_NOWAIT, 0); + page = f2fs_pagecache_get_page(inode->i_mapping, 0, + FGP_LOCK|FGP_NOWAIT, 0); if (!page) goto iput_out; @@ -1253,7 +1421,7 @@ static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino) ret = f2fs_write_inline_data(inode, page); inode_dec_dirty_pages(inode); - remove_dirty_inode(inode); + f2fs_remove_dirty_inode(inode); if (ret) set_page_dirty(page); page_out: @@ -1262,54 +1430,19 @@ iput_out: iput(inode); } -void move_node_page(struct page *node_page, int gc_type) -{ - if (gc_type == FG_GC) { - struct f2fs_sb_info *sbi = F2FS_P_SB(node_page); - struct writeback_control wbc = { - .sync_mode = WB_SYNC_ALL, - .nr_to_write = 1, - .for_reclaim = 0, - }; - - set_page_dirty(node_page); - f2fs_wait_on_page_writeback(node_page, NODE, true); - - f2fs_bug_on(sbi, PageWriteback(node_page)); - if (!clear_page_dirty_for_io(node_page)) - goto out_page; - - if (NODE_MAPPING(sbi)->a_ops->writepage(node_page, &wbc)) - unlock_page(node_page); - goto release_page; - } else { - /* set page dirty and write it */ - if (!PageWriteback(node_page)) - set_page_dirty(node_page); - } -out_page: - unlock_page(node_page); -release_page: - f2fs_put_page(node_page, 0); -} - static struct page *last_fsync_dnode(struct f2fs_sb_info *sbi, nid_t ino) { - pgoff_t index, end; + pgoff_t index; struct pagevec pvec; struct page *last_page = NULL; + int nr_pages; pagevec_init(&pvec, 0); index = 0; - end = ULONG_MAX; - - while (index <= end) { - int i, nr_pages; - nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index, - PAGECACHE_TAG_DIRTY, - min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); - if (nr_pages == 0) - break; + + while ((nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index, + PAGECACHE_TAG_DIRTY))) { + int i; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; @@ -1355,13 +1488,14 @@ continue_unlock: static int __write_node_page(struct page *page, bool atomic, bool *submitted, struct writeback_control *wbc, bool do_balance, - enum iostat_type io_type) + enum iostat_type io_type, unsigned int *seq_id) { struct f2fs_sb_info *sbi = F2FS_P_SB(page); nid_t nid; struct node_info ni; struct f2fs_io_info fio = { .sbi = sbi, + .ino = ino_of_node(page), .type = NODE, .op = REQ_OP_WRITE, .op_flags = wbc_to_write_flags(wbc), @@ -1369,19 +1503,29 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted, .encrypted_page = NULL, .submitted = false, .io_type = io_type, + .io_wbc = wbc, }; + unsigned int seq; trace_f2fs_writepage(page, NODE); + if (unlikely(f2fs_cp_error(sbi))) + goto redirty_out; + if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) goto redirty_out; - if (unlikely(f2fs_cp_error(sbi))) + + if (wbc->sync_mode == WB_SYNC_NONE && + IS_DNODE(page) && is_cold_node(page)) goto redirty_out; /* get old block addr of this node page */ nid = nid_of_node(page); f2fs_bug_on(sbi, page->index != nid); + if (f2fs_get_node_info(sbi, nid, &ni)) + goto redirty_out; + if (wbc->for_reclaim) { if (!down_read_trylock(&sbi->node_write)) goto redirty_out; @@ -1389,8 +1533,6 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted, down_read(&sbi->node_write); } - get_node_info(sbi, nid, &ni); - /* This page is already truncated */ if (unlikely(ni.blk_addr == NULL_ADDR)) { ClearPageUptodate(page); @@ -1410,15 +1552,22 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted, fio.op_flags |= REQ_PREFLUSH | REQ_FUA; set_page_writeback(page); + ClearPageError(page); + + if (f2fs_in_warm_node_list(sbi, page)) { + seq = f2fs_add_fsync_node_entry(sbi, page); + if (seq_id) + *seq_id = seq; + } + fio.old_blkaddr = ni.blk_addr; - write_node_page(nid, &fio); + f2fs_do_write_node_page(nid, &fio); set_node_addr(sbi, &ni, fio.new_blkaddr, is_fsync_dnode(page)); dec_page_count(sbi, F2FS_DIRTY_NODES); up_read(&sbi->node_write); if (wbc->for_reclaim) { - f2fs_submit_merged_write_cond(sbi, page->mapping->host, 0, - page->index, NODE); + f2fs_submit_merged_write_cond(sbi, NULL, page, 0, NODE); submitted = NULL; } @@ -1440,22 +1589,63 @@ redirty_out: return AOP_WRITEPAGE_ACTIVATE; } +int f2fs_move_node_page(struct page *node_page, int gc_type) +{ + int err = 0; + + if (gc_type == FG_GC) { + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = 1, + .for_reclaim = 0, + }; + + f2fs_wait_on_page_writeback(node_page, NODE, true, true); + + set_page_dirty(node_page); + + if (!clear_page_dirty_for_io(node_page)) { + err = -EAGAIN; + goto out_page; + } + + if (__write_node_page(node_page, false, NULL, + &wbc, false, FS_GC_NODE_IO, NULL)) { + err = -EAGAIN; + unlock_page(node_page); + } + goto release_page; + } else { + /* set page dirty and write it */ + if (!PageWriteback(node_page)) + set_page_dirty(node_page); + } +out_page: + unlock_page(node_page); +release_page: + f2fs_put_page(node_page, 0); + return err; +} + static int f2fs_write_node_page(struct page *page, struct writeback_control *wbc) { - return __write_node_page(page, false, NULL, wbc, false, FS_NODE_IO); + return __write_node_page(page, false, NULL, wbc, false, + FS_NODE_IO, NULL); } -int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, - struct writeback_control *wbc, bool atomic) +int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, + struct writeback_control *wbc, bool atomic, + unsigned int *seq_id) { - pgoff_t index, end; - pgoff_t last_idx = ULONG_MAX; + pgoff_t index; struct pagevec pvec; int ret = 0; struct page *last_page = NULL; bool marked = false; nid_t ino = inode->i_ino; + int nr_pages; + int nwritten = 0; if (atomic) { last_page = last_fsync_dnode(sbi, ino); @@ -1465,15 +1655,10 @@ int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, retry: pagevec_init(&pvec, 0); index = 0; - end = ULONG_MAX; - - while (index <= end) { - int i, nr_pages; - nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index, - PAGECACHE_TAG_DIRTY, - min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); - if (nr_pages == 0) - break; + + while ((nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index, + PAGECACHE_TAG_DIRTY))) { + int i; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; @@ -1506,8 +1691,7 @@ continue_unlock: goto continue_unlock; } - f2fs_wait_on_page_writeback(page, NODE, true); - BUG_ON(PageWriteback(page)); + f2fs_wait_on_page_writeback(page, NODE, true, true); set_fsync_mark(page, 0); set_dentry_mark(page, 0); @@ -1517,9 +1701,9 @@ continue_unlock: if (IS_INODE(page)) { if (is_inode_flag_set(inode, FI_DIRTY_INODE)) - update_inode(inode, page); + f2fs_update_inode(inode, page); set_dentry_mark(page, - need_dentry_mark(sbi, ino)); + f2fs_need_dentry_mark(sbi, ino)); } /* may be written by other thread */ if (!PageDirty(page)) @@ -1532,13 +1716,13 @@ continue_unlock: ret = __write_node_page(page, atomic && page == last_page, &submitted, wbc, true, - FS_NODE_IO); + FS_NODE_IO, seq_id); if (ret) { unlock_page(page); f2fs_put_page(last_page, 0); break; } else if (submitted) { - last_idx = page->index; + nwritten++; } if (page == last_page) { @@ -1558,48 +1742,46 @@ continue_unlock: "Retry to write fsync mark: ino=%u, idx=%lx", ino, last_page->index); lock_page(last_page); - f2fs_wait_on_page_writeback(last_page, NODE, true); + f2fs_wait_on_page_writeback(last_page, NODE, true, true); set_page_dirty(last_page); unlock_page(last_page); goto retry; } out: - if (last_idx != ULONG_MAX) - f2fs_submit_merged_write_cond(sbi, NULL, ino, last_idx, NODE); + if (nwritten) + f2fs_submit_merged_write_cond(sbi, NULL, NULL, ino, NODE); return ret ? -EIO: 0; } -int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc, +int f2fs_sync_node_pages(struct f2fs_sb_info *sbi, + struct writeback_control *wbc, bool do_balance, enum iostat_type io_type) { - pgoff_t index, end; + pgoff_t index; struct pagevec pvec; int step = 0; int nwritten = 0; int ret = 0; + int nr_pages, done = 0; pagevec_init(&pvec, 0); next_step: index = 0; - end = ULONG_MAX; - - while (index <= end) { - int i, nr_pages; - nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index, - PAGECACHE_TAG_DIRTY, - min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); - if (nr_pages == 0) - break; + + while (!done && (nr_pages = pagevec_lookup_tag(&pvec, + NODE_MAPPING(sbi), &index, PAGECACHE_TAG_DIRTY))) { + int i; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; bool submitted = false; - if (unlikely(f2fs_cp_error(sbi))) { - pagevec_release(&pvec); - ret = -EIO; - goto out; + /* give a priority to WB_SYNC threads */ + if (atomic_read(&sbi->wb_sync_req[NODE]) && + wbc->sync_mode == WB_SYNC_NONE) { + done = 1; + break; } /* @@ -1641,9 +1823,8 @@ continue_unlock: goto lock_node; } - f2fs_wait_on_page_writeback(page, NODE, true); + f2fs_wait_on_page_writeback(page, NODE, true, true); - BUG_ON(PageWriteback(page)); if (!clear_page_dirty_for_io(page)) goto continue_unlock; @@ -1651,7 +1832,7 @@ continue_unlock: set_dentry_mark(page, 0); ret = __write_node_page(page, false, &submitted, - wbc, do_balance, io_type); + wbc, do_balance, io_type, NULL); if (ret) unlock_page(page); else if (submitted) @@ -1670,51 +1851,60 @@ continue_unlock: } if (step < 2) { + if (wbc->sync_mode == WB_SYNC_NONE && step == 1) + goto out; step++; goto next_step; } out: if (nwritten) f2fs_submit_merged_write(sbi, NODE); + + if (unlikely(f2fs_cp_error(sbi))) + return -EIO; return ret; } -int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino) +int f2fs_wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, + unsigned int seq_id) { - pgoff_t index = 0, end = ULONG_MAX; - struct pagevec pvec; + struct fsync_node_entry *fn; + struct page *page; + struct list_head *head = &sbi->fsync_node_list; + unsigned long flags; + unsigned int cur_seq_id = 0; int ret2, ret = 0; - pagevec_init(&pvec, 0); - - while (index <= end) { - int i, nr_pages; - nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index, - PAGECACHE_TAG_WRITEBACK, - min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); - if (nr_pages == 0) + while (seq_id && cur_seq_id < seq_id) { + spin_lock_irqsave(&sbi->fsync_node_lock, flags); + if (list_empty(head)) { + spin_unlock_irqrestore(&sbi->fsync_node_lock, flags); break; + } + fn = list_first_entry(head, struct fsync_node_entry, list); + if (fn->seq_id > seq_id) { + spin_unlock_irqrestore(&sbi->fsync_node_lock, flags); + break; + } + cur_seq_id = fn->seq_id; + page = fn->page; + get_page(page); + spin_unlock_irqrestore(&sbi->fsync_node_lock, flags); - for (i = 0; i < nr_pages; i++) { - struct page *page = pvec.pages[i]; + f2fs_wait_on_page_writeback(page, NODE, true, false); + if (TestClearPageError(page)) + ret = -EIO; - /* until radix tree lookup accepts end_index */ - if (unlikely(page->index > end)) - continue; + put_page(page); - if (ino && ino_of_node(page) == ino) { - f2fs_wait_on_page_writeback(page, NODE, true); - if (TestClearPageError(page)) - ret = -EIO; - } - } - pagevec_release(&pvec); - cond_resched(); + if (ret) + break; } ret2 = filemap_check_errors(NODE_MAPPING(sbi)); if (!ret) ret = ret2; + return ret; } @@ -1732,17 +1922,26 @@ static int f2fs_write_node_pages(struct address_space *mapping, f2fs_balance_fs_bg(sbi); /* collect a number of dirty node pages and write together */ - if (get_pages(sbi, F2FS_DIRTY_NODES) < nr_pages_to_skip(sbi, NODE)) + if (wbc->sync_mode != WB_SYNC_ALL && + get_pages(sbi, F2FS_DIRTY_NODES) < + nr_pages_to_skip(sbi, NODE)) + goto skip_write; + + if (wbc->sync_mode == WB_SYNC_ALL) + atomic_inc(&sbi->wb_sync_req[NODE]); + else if (atomic_read(&sbi->wb_sync_req[NODE])) goto skip_write; trace_f2fs_writepages(mapping->host, wbc, NODE); diff = nr_pages_to_write(sbi, NODE, wbc); - wbc->sync_mode = WB_SYNC_NONE; blk_start_plug(&plug); - sync_node_pages(sbi, wbc, true, FS_NODE_IO); + f2fs_sync_node_pages(sbi, wbc, true, FS_NODE_IO); blk_finish_plug(&plug); wbc->nr_to_write = max((long)0, wbc->nr_to_write - diff); + + if (wbc->sync_mode == WB_SYNC_ALL) + atomic_dec(&sbi->wb_sync_req[NODE]); return 0; skip_write: @@ -1757,10 +1956,14 @@ static int f2fs_set_node_page_dirty(struct page *page) if (!PageUptodate(page)) SetPageUptodate(page); +#ifdef CONFIG_F2FS_CHECK_FS + if (IS_INODE(page)) + f2fs_inode_chksum_set(F2FS_P_SB(page), page); +#endif if (!PageDirty(page)) { - f2fs_set_page_dirty_nobuffers(page); + __set_page_dirty_nobuffers(page); inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES); - SetPagePrivate(page); + f2fs_set_page_private(page, 0); f2fs_trace_pid(page); return 1; } @@ -1787,39 +1990,83 @@ static struct free_nid *__lookup_free_nid_list(struct f2fs_nm_info *nm_i, return radix_tree_lookup(&nm_i->free_nid_root, n); } -static int __insert_nid_to_list(struct f2fs_sb_info *sbi, - struct free_nid *i, enum nid_list list, bool new) +static int __insert_free_nid(struct f2fs_sb_info *sbi, + struct free_nid *i, enum nid_state state) { struct f2fs_nm_info *nm_i = NM_I(sbi); - if (new) { - int err = radix_tree_insert(&nm_i->free_nid_root, i->nid, i); - if (err) - return err; - } + int err = radix_tree_insert(&nm_i->free_nid_root, i->nid, i); + if (err) + return err; - f2fs_bug_on(sbi, list == FREE_NID_LIST ? i->state != NID_NEW : - i->state != NID_ALLOC); - nm_i->nid_cnt[list]++; - list_add_tail(&i->list, &nm_i->nid_list[list]); + f2fs_bug_on(sbi, state != i->state); + nm_i->nid_cnt[state]++; + if (state == FREE_NID) + list_add_tail(&i->list, &nm_i->free_nid_list); return 0; } -static void __remove_nid_from_list(struct f2fs_sb_info *sbi, - struct free_nid *i, enum nid_list list, bool reuse) +static void __remove_free_nid(struct f2fs_sb_info *sbi, + struct free_nid *i, enum nid_state state) { struct f2fs_nm_info *nm_i = NM_I(sbi); - f2fs_bug_on(sbi, list == FREE_NID_LIST ? i->state != NID_NEW : - i->state != NID_ALLOC); - nm_i->nid_cnt[list]--; - list_del(&i->list); - if (!reuse) - radix_tree_delete(&nm_i->free_nid_root, i->nid); + f2fs_bug_on(sbi, state != i->state); + nm_i->nid_cnt[state]--; + if (state == FREE_NID) + list_del(&i->list); + radix_tree_delete(&nm_i->free_nid_root, i->nid); +} + +static void __move_free_nid(struct f2fs_sb_info *sbi, struct free_nid *i, + enum nid_state org_state, enum nid_state dst_state) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + + f2fs_bug_on(sbi, org_state != i->state); + i->state = dst_state; + nm_i->nid_cnt[org_state]--; + nm_i->nid_cnt[dst_state]++; + + switch (dst_state) { + case PREALLOC_NID: + list_del(&i->list); + break; + case FREE_NID: + list_add_tail(&i->list, &nm_i->free_nid_list); + break; + default: + BUG_ON(1); + } +} + +static void update_free_nid_bitmap(struct f2fs_sb_info *sbi, nid_t nid, + bool set, bool build) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); + unsigned int nat_ofs = NAT_BLOCK_OFFSET(nid); + unsigned int nid_ofs = nid - START_NID(nid); + + if (!test_bit_le(nat_ofs, nm_i->nat_block_bitmap)) + return; + + if (set) { + if (test_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs])) + return; + __set_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]); + nm_i->free_nid_count[nat_ofs]++; + } else { + if (!test_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs])) + return; + __clear_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]); + if (!build) + nm_i->free_nid_count[nat_ofs]--; + } } /* return if the nid is recognized as free */ -static bool add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build) +static bool add_free_nid(struct f2fs_sb_info *sbi, + nid_t nid, bool build, bool update) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i, *e; @@ -1833,10 +2080,9 @@ static bool add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build) i = f2fs_kmem_cache_alloc(free_nid_slab, GFP_NOFS); i->nid = nid; - i->state = NID_NEW; + i->state = FREE_NID; - if (radix_tree_preload(GFP_NOFS)) - goto err; + radix_tree_preload(GFP_NOFS | __GFP_NOFAIL); spin_lock(&nm_i->nid_list_lock); @@ -1845,22 +2091,22 @@ static bool add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build) * Thread A Thread B * - f2fs_create * - f2fs_new_inode - * - alloc_nid - * - __insert_nid_to_list(ALLOC_NID_LIST) + * - f2fs_alloc_nid + * - __insert_nid_to_list(PREALLOC_NID) * - f2fs_balance_fs_bg - * - build_free_nids - * - __build_free_nids + * - f2fs_build_free_nids + * - __f2fs_build_free_nids * - scan_nat_page * - add_free_nid * - __lookup_nat_cache * - f2fs_add_link - * - init_inode_metadata - * - new_inode_page - * - new_node_page + * - f2fs_init_inode_metadata + * - f2fs_new_inode_page + * - f2fs_new_node_page * - set_node_addr - * - alloc_nid_done - * - __remove_nid_from_list(ALLOC_NID_LIST) - * - __insert_nid_to_list(FREE_NID_LIST) + * - f2fs_alloc_nid_done + * - __remove_nid_from_list(PREALLOC_NID) + * - __insert_nid_to_list(FREE_NID) */ ne = __lookup_nat_cache(nm_i, nid); if (ne && (!get_nat_flag(ne, IS_CHECKPOINTED) || @@ -1869,17 +2115,22 @@ static bool add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build) e = __lookup_free_nid_list(nm_i, nid); if (e) { - if (e->state == NID_NEW) + if (e->state == FREE_NID) ret = true; goto err_out; } } ret = true; - err = __insert_nid_to_list(sbi, i, FREE_NID_LIST, true); + err = __insert_free_nid(sbi, i, FREE_NID); err_out: + if (update) { + update_free_nid_bitmap(sbi, nid, ret, build); + if (!build) + nm_i->available_nids++; + } spin_unlock(&nm_i->nid_list_lock); radix_tree_preload_end(); -err: + if (err) kmem_cache_free(free_nid_slab, i); return ret; @@ -1893,8 +2144,8 @@ static void remove_free_nid(struct f2fs_sb_info *sbi, nid_t nid) spin_lock(&nm_i->nid_list_lock); i = __lookup_free_nid_list(nm_i, nid); - if (i && i->state == NID_NEW) { - __remove_nid_from_list(sbi, i, FREE_NID_LIST, false); + if (i && i->state == FREE_NID) { + __remove_free_nid(sbi, i, FREE_NID); need_free = true; } spin_unlock(&nm_i->nid_list_lock); @@ -1903,28 +2154,7 @@ static void remove_free_nid(struct f2fs_sb_info *sbi, nid_t nid) kmem_cache_free(free_nid_slab, i); } -static void update_free_nid_bitmap(struct f2fs_sb_info *sbi, nid_t nid, - bool set, bool build) -{ - struct f2fs_nm_info *nm_i = NM_I(sbi); - unsigned int nat_ofs = NAT_BLOCK_OFFSET(nid); - unsigned int nid_ofs = nid - START_NID(nid); - - if (!test_bit_le(nat_ofs, nm_i->nat_block_bitmap)) - return; - - if (set) - __set_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]); - else - __clear_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]); - - if (set) - nm_i->free_nid_count[nat_ofs]++; - else if (!build) - nm_i->free_nid_count[nat_ofs]--; -} - -static void scan_nat_page(struct f2fs_sb_info *sbi, +static int scan_nat_page(struct f2fs_sb_info *sbi, struct page *nat_page, nid_t start_nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); @@ -1933,35 +2163,57 @@ static void scan_nat_page(struct f2fs_sb_info *sbi, unsigned int nat_ofs = NAT_BLOCK_OFFSET(start_nid); int i; - if (test_bit_le(nat_ofs, nm_i->nat_block_bitmap)) - return; - __set_bit_le(nat_ofs, nm_i->nat_block_bitmap); i = start_nid % NAT_ENTRY_PER_BLOCK; for (; i < NAT_ENTRY_PER_BLOCK; i++, start_nid++) { - bool freed = false; - if (unlikely(start_nid >= nm_i->max_nid)) break; blk_addr = le32_to_cpu(nat_blk->entries[i].block_addr); - f2fs_bug_on(sbi, blk_addr == NEW_ADDR); - if (blk_addr == NULL_ADDR) - freed = add_free_nid(sbi, start_nid, true); - spin_lock(&NM_I(sbi)->nid_list_lock); - update_free_nid_bitmap(sbi, start_nid, freed, true); - spin_unlock(&NM_I(sbi)->nid_list_lock); + + if (blk_addr == NEW_ADDR) + return -EINVAL; + + if (blk_addr == NULL_ADDR) { + add_free_nid(sbi, start_nid, true, true); + } else { + spin_lock(&NM_I(sbi)->nid_list_lock); + update_free_nid_bitmap(sbi, start_nid, false, true); + spin_unlock(&NM_I(sbi)->nid_list_lock); + } } + + return 0; } -static void scan_free_nid_bits(struct f2fs_sb_info *sbi) +static void scan_curseg_cache(struct f2fs_sb_info *sbi) { - struct f2fs_nm_info *nm_i = NM_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); struct f2fs_journal *journal = curseg->journal; + int i; + + down_read(&curseg->journal_rwsem); + for (i = 0; i < nats_in_cursum(journal); i++) { + block_t addr; + nid_t nid; + + addr = le32_to_cpu(nat_in_journal(journal, i).block_addr); + nid = le32_to_cpu(nid_in_journal(journal, i)); + if (addr == NULL_ADDR) + add_free_nid(sbi, nid, true, false); + else + remove_free_nid(sbi, nid); + } + up_read(&curseg->journal_rwsem); +} + +static void scan_free_nid_bits(struct f2fs_sb_info *sbi) +{ + struct f2fs_nm_info *nm_i = NM_I(sbi); unsigned int i, idx; + nid_t nid; down_read(&nm_i->nat_tree_lock); @@ -1971,72 +2223,75 @@ static void scan_free_nid_bits(struct f2fs_sb_info *sbi) if (!nm_i->free_nid_count[i]) continue; for (idx = 0; idx < NAT_ENTRY_PER_BLOCK; idx++) { - nid_t nid; - - if (!test_bit_le(idx, nm_i->free_nid_bitmap[i])) - continue; + idx = find_next_bit_le(nm_i->free_nid_bitmap[i], + NAT_ENTRY_PER_BLOCK, idx); + if (idx >= NAT_ENTRY_PER_BLOCK) + break; nid = i * NAT_ENTRY_PER_BLOCK + idx; - add_free_nid(sbi, nid, true); + add_free_nid(sbi, nid, true, false); - if (nm_i->nid_cnt[FREE_NID_LIST] >= MAX_FREE_NIDS) + if (nm_i->nid_cnt[FREE_NID] >= MAX_FREE_NIDS) goto out; } } out: - down_read(&curseg->journal_rwsem); - for (i = 0; i < nats_in_cursum(journal); i++) { - block_t addr; - nid_t nid; + scan_curseg_cache(sbi); - addr = le32_to_cpu(nat_in_journal(journal, i).block_addr); - nid = le32_to_cpu(nid_in_journal(journal, i)); - if (addr == NULL_ADDR) - add_free_nid(sbi, nid, true); - else - remove_free_nid(sbi, nid); - } - up_read(&curseg->journal_rwsem); up_read(&nm_i->nat_tree_lock); } -static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount) +static int __f2fs_build_free_nids(struct f2fs_sb_info *sbi, + bool sync, bool mount) { struct f2fs_nm_info *nm_i = NM_I(sbi); - struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); - struct f2fs_journal *journal = curseg->journal; - int i = 0; + int i = 0, ret; nid_t nid = nm_i->next_scan_nid; if (unlikely(nid >= nm_i->max_nid)) nid = 0; /* Enough entries */ - if (nm_i->nid_cnt[FREE_NID_LIST] >= NAT_ENTRY_PER_BLOCK) - return; + if (nm_i->nid_cnt[FREE_NID] >= NAT_ENTRY_PER_BLOCK) + return 0; - if (!sync && !available_free_memory(sbi, FREE_NIDS)) - return; + if (!sync && !f2fs_available_free_memory(sbi, FREE_NIDS)) + return 0; if (!mount) { /* try to find free nids in free_nid_bitmap */ scan_free_nid_bits(sbi); - if (nm_i->nid_cnt[FREE_NID_LIST]) - return; + if (nm_i->nid_cnt[FREE_NID] >= NAT_ENTRY_PER_BLOCK) + return 0; } /* readahead nat pages to be scanned */ - ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES, + f2fs_ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES, META_NAT, true); down_read(&nm_i->nat_tree_lock); while (1) { - struct page *page = get_current_nat_page(sbi, nid); + if (!test_bit_le(NAT_BLOCK_OFFSET(nid), + nm_i->nat_block_bitmap)) { + struct page *page = get_current_nat_page(sbi, nid); + + if (IS_ERR(page)) { + ret = PTR_ERR(page); + } else { + ret = scan_nat_page(sbi, page, nid); + f2fs_put_page(page, 1); + } - scan_nat_page(sbi, page, nid); - f2fs_put_page(page, 1); + if (ret) { + up_read(&nm_i->nat_tree_lock); + f2fs_bug_on(sbi, !mount); + f2fs_msg(sbi->sb, KERN_ERR, + "NAT is corrupt, run fsck to fix it"); + return ret; + } + } nid += (NAT_ENTRY_PER_BLOCK - (nid % NAT_ENTRY_PER_BLOCK)); if (unlikely(nid >= nm_i->max_nid)) @@ -2050,29 +2305,25 @@ static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount) nm_i->next_scan_nid = nid; /* find free nids from current sum_pages */ - down_read(&curseg->journal_rwsem); - for (i = 0; i < nats_in_cursum(journal); i++) { - block_t addr; + scan_curseg_cache(sbi); - addr = le32_to_cpu(nat_in_journal(journal, i).block_addr); - nid = le32_to_cpu(nid_in_journal(journal, i)); - if (addr == NULL_ADDR) - add_free_nid(sbi, nid, true); - else - remove_free_nid(sbi, nid); - } - up_read(&curseg->journal_rwsem); up_read(&nm_i->nat_tree_lock); - ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid), + f2fs_ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid), nm_i->ra_nid_pages, META_NAT, false); + + return 0; } -void build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount) +int f2fs_build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount) { + int ret; + mutex_lock(&NM_I(sbi)->build_lock); - __build_free_nids(sbi, sync, mount); + ret = __f2fs_build_free_nids(sbi, sync, mount); mutex_unlock(&NM_I(sbi)->build_lock); + + return ret; } /* @@ -2080,17 +2331,16 @@ void build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount) * from second parameter of this function. * The returned nid could be used ino as well as nid when inode is created. */ -bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid) +bool f2fs_alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i = NULL; retry: -#ifdef CONFIG_F2FS_FAULT_INJECTION if (time_to_inject(sbi, FAULT_ALLOC_NID)) { f2fs_show_injection_info(FAULT_ALLOC_NID); return false; } -#endif + spin_lock(&nm_i->nid_list_lock); if (unlikely(nm_i->available_nids == 0)) { @@ -2098,16 +2348,14 @@ retry: return false; } - /* We should not use stale free nids created by build_free_nids */ - if (nm_i->nid_cnt[FREE_NID_LIST] && !on_build_free_nids(nm_i)) { - f2fs_bug_on(sbi, list_empty(&nm_i->nid_list[FREE_NID_LIST])); - i = list_first_entry(&nm_i->nid_list[FREE_NID_LIST], + /* We should not use stale free nids created by f2fs_build_free_nids */ + if (nm_i->nid_cnt[FREE_NID] && !on_f2fs_build_free_nids(nm_i)) { + f2fs_bug_on(sbi, list_empty(&nm_i->free_nid_list)); + i = list_first_entry(&nm_i->free_nid_list, struct free_nid, list); *nid = i->nid; - __remove_nid_from_list(sbi, i, FREE_NID_LIST, true); - i->state = NID_ALLOC; - __insert_nid_to_list(sbi, i, ALLOC_NID_LIST, false); + __move_free_nid(sbi, i, FREE_NID, PREALLOC_NID); nm_i->available_nids--; update_free_nid_bitmap(sbi, *nid, false, false); @@ -2118,14 +2366,15 @@ retry: spin_unlock(&nm_i->nid_list_lock); /* Let's scan nat pages and its caches to get free nids */ - build_free_nids(sbi, true, false); - goto retry; + if (!f2fs_build_free_nids(sbi, true, false)) + goto retry; + return false; } /* - * alloc_nid() should be called prior to this function. + * f2fs_alloc_nid() should be called prior to this function. */ -void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid) +void f2fs_alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i; @@ -2133,16 +2382,16 @@ void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid) spin_lock(&nm_i->nid_list_lock); i = __lookup_free_nid_list(nm_i, nid); f2fs_bug_on(sbi, !i); - __remove_nid_from_list(sbi, i, ALLOC_NID_LIST, false); + __remove_free_nid(sbi, i, PREALLOC_NID); spin_unlock(&nm_i->nid_list_lock); kmem_cache_free(free_nid_slab, i); } /* - * alloc_nid() should be called prior to this function. + * f2fs_alloc_nid() should be called prior to this function. */ -void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid) +void f2fs_alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i; @@ -2155,13 +2404,11 @@ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid) i = __lookup_free_nid_list(nm_i, nid); f2fs_bug_on(sbi, !i); - if (!available_free_memory(sbi, FREE_NIDS)) { - __remove_nid_from_list(sbi, i, ALLOC_NID_LIST, false); + if (!f2fs_available_free_memory(sbi, FREE_NIDS)) { + __remove_free_nid(sbi, i, PREALLOC_NID); need_free = true; } else { - __remove_nid_from_list(sbi, i, ALLOC_NID_LIST, true); - i->state = NID_NEW; - __insert_nid_to_list(sbi, i, FREE_NID_LIST, false); + __move_free_nid(sbi, i, PREALLOC_NID, FREE_NID); } nm_i->available_nids++; @@ -2174,26 +2421,25 @@ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid) kmem_cache_free(free_nid_slab, i); } -int try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink) +int f2fs_try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i, *next; int nr = nr_shrink; - if (nm_i->nid_cnt[FREE_NID_LIST] <= MAX_FREE_NIDS) + if (nm_i->nid_cnt[FREE_NID] <= MAX_FREE_NIDS) return 0; if (!mutex_trylock(&nm_i->build_lock)) return 0; spin_lock(&nm_i->nid_list_lock); - list_for_each_entry_safe(i, next, &nm_i->nid_list[FREE_NID_LIST], - list) { + list_for_each_entry_safe(i, next, &nm_i->free_nid_list, list) { if (nr_shrink <= 0 || - nm_i->nid_cnt[FREE_NID_LIST] <= MAX_FREE_NIDS) + nm_i->nid_cnt[FREE_NID] <= MAX_FREE_NIDS) break; - __remove_nid_from_list(sbi, i, FREE_NID_LIST, false); + __remove_free_nid(sbi, i, FREE_NID); kmem_cache_free(free_nid_slab, i); nr_shrink--; } @@ -2203,34 +2449,36 @@ int try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink) return nr - nr_shrink; } -void recover_inline_xattr(struct inode *inode, struct page *page) +void f2fs_recover_inline_xattr(struct inode *inode, struct page *page) { void *src_addr, *dst_addr; size_t inline_size; struct page *ipage; struct f2fs_inode *ri; - ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino); + ipage = f2fs_get_node_page(F2FS_I_SB(inode), inode->i_ino); f2fs_bug_on(F2FS_I_SB(inode), IS_ERR(ipage)); ri = F2FS_INODE(page); - if (!(ri->i_inline & F2FS_INLINE_XATTR)) { + if (ri->i_inline & F2FS_INLINE_XATTR) { + set_inode_flag(inode, FI_INLINE_XATTR); + } else { clear_inode_flag(inode, FI_INLINE_XATTR); goto update_inode; } - dst_addr = inline_xattr_addr(ipage); - src_addr = inline_xattr_addr(page); + dst_addr = inline_xattr_addr(inode, ipage); + src_addr = inline_xattr_addr(inode, page); inline_size = inline_xattr_size(inode); - f2fs_wait_on_page_writeback(ipage, NODE, true); + f2fs_wait_on_page_writeback(ipage, NODE, true, true); memcpy(dst_addr, src_addr, inline_size); update_inode: - update_inode(inode, ipage); + f2fs_update_inode(inode, ipage); f2fs_put_page(ipage, 1); } -int recover_xattr_data(struct inode *inode, struct page *page, block_t blkaddr) +int f2fs_recover_xattr_data(struct inode *inode, struct page *page) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); nid_t prev_xnid = F2FS_I(inode)->i_xattr_nid; @@ -2238,31 +2486,34 @@ int recover_xattr_data(struct inode *inode, struct page *page, block_t blkaddr) struct dnode_of_data dn; struct node_info ni; struct page *xpage; + int err; if (!prev_xnid) goto recover_xnid; /* 1: invalidate the previous xattr nid */ - get_node_info(sbi, prev_xnid, &ni); - f2fs_bug_on(sbi, ni.blk_addr == NULL_ADDR); - invalidate_blocks(sbi, ni.blk_addr); + err = f2fs_get_node_info(sbi, prev_xnid, &ni); + if (err) + return err; + + f2fs_invalidate_blocks(sbi, ni.blk_addr); dec_valid_node_count(sbi, inode, false); set_node_addr(sbi, &ni, NULL_ADDR, false); recover_xnid: /* 2: update xattr nid in inode */ - if (!alloc_nid(sbi, &new_xnid)) + if (!f2fs_alloc_nid(sbi, &new_xnid)) return -ENOSPC; set_new_dnode(&dn, inode, NULL, NULL, new_xnid); - xpage = new_node_page(&dn, XATTR_NODE_OFFSET); + xpage = f2fs_new_node_page(&dn, XATTR_NODE_OFFSET); if (IS_ERR(xpage)) { - alloc_nid_failed(sbi, new_xnid); + f2fs_alloc_nid_failed(sbi, new_xnid); return PTR_ERR(xpage); } - alloc_nid_done(sbi, new_xnid); - update_inode_page(inode); + f2fs_alloc_nid_done(sbi, new_xnid); + f2fs_update_inode_page(inode); /* 3: update and set xattr node page dirty */ memcpy(F2FS_NODE(xpage), F2FS_NODE(page), VALID_XATTR_BLOCK_SIZE); @@ -2273,14 +2524,17 @@ recover_xnid: return 0; } -int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page) +int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page) { struct f2fs_inode *src, *dst; nid_t ino = ino_of_node(page); struct node_info old_ni, new_ni; struct page *ipage; + int err; - get_node_info(sbi, ino, &old_ni); + err = f2fs_get_node_info(sbi, ino, &old_ni); + if (err) + return err; if (unlikely(old_ni.blk_addr != NULL_ADDR)) return -EINVAL; @@ -2297,6 +2551,7 @@ retry: if (!PageUptodate(ipage)) SetPageUptodate(ipage); fill_node_footer(ipage, ino, ino, 0, true); + set_cold_node(ipage, false); src = F2FS_INODE(page); dst = F2FS_INODE(ipage); @@ -2309,10 +2564,23 @@ retry: dst->i_inline = src->i_inline & (F2FS_INLINE_XATTR | F2FS_EXTRA_ATTR); if (dst->i_inline & F2FS_EXTRA_ATTR) { dst->i_extra_isize = src->i_extra_isize; - if (f2fs_sb_has_project_quota(sbi->sb) && + + if (f2fs_sb_has_flexible_inline_xattr(sbi) && + F2FS_FITS_IN_INODE(src, le16_to_cpu(src->i_extra_isize), + i_inline_xattr_size)) + dst->i_inline_xattr_size = src->i_inline_xattr_size; + + if (f2fs_sb_has_project_quota(sbi) && F2FS_FITS_IN_INODE(src, le16_to_cpu(src->i_extra_isize), i_projid)) dst->i_projid = src->i_projid; + + if (f2fs_sb_has_inode_crtime(sbi) && + F2FS_FITS_IN_INODE(src, le16_to_cpu(src->i_extra_isize), + i_crtime_nsec)) { + dst->i_crtime = src->i_crtime; + dst->i_crtime_nsec = src->i_crtime_nsec; + } } new_ni = old_ni; @@ -2327,7 +2595,7 @@ retry: return 0; } -int restore_node_summary(struct f2fs_sb_info *sbi, +int f2fs_restore_node_summary(struct f2fs_sb_info *sbi, unsigned int segno, struct f2fs_summary_block *sum) { struct f2fs_node *rn; @@ -2344,10 +2612,13 @@ int restore_node_summary(struct f2fs_sb_info *sbi, nrpages = min(last_offset - i, BIO_MAX_PAGES); /* readahead node pages */ - ra_meta_pages(sbi, addr, nrpages, META_POR, true); + f2fs_ra_meta_pages(sbi, addr, nrpages, META_POR, true); for (idx = addr; idx < addr + nrpages; idx++) { - struct page *page = get_tmp_page(sbi, idx); + struct page *page = f2fs_get_tmp_page(sbi, idx); + + if (IS_ERR(page)) + return PTR_ERR(page); rn = F2FS_NODE(page); sum_entry->nid = rn->footer.nid; @@ -2380,8 +2651,8 @@ static void remove_nats_in_journal(struct f2fs_sb_info *sbi) ne = __lookup_nat_cache(nm_i, nid); if (!ne) { - ne = grab_nat_entry(nm_i, nid, true); - node_info_from_raw_nat(&ne->ni, &raw_ne); + ne = __alloc_nat_entry(nid, true); + __init_nat_entry(nm_i, ne, &raw_ne, true); } /* @@ -2427,15 +2698,17 @@ static void __update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid, unsigned int nat_index = start_nid / NAT_ENTRY_PER_BLOCK; struct f2fs_nat_block *nat_blk = page_address(page); int valid = 0; - int i; + int i = 0; if (!enabled_nat_bits(sbi, NULL)) return; - for (i = 0; i < NAT_ENTRY_PER_BLOCK; i++) { - if (start_nid == 0 && i == 0) - valid++; - if (nat_blk->entries[i].block_addr) + if (nat_index == 0) { + valid = 1; + i = 1; + } + for (; i < NAT_ENTRY_PER_BLOCK; i++) { + if (nat_blk->entries[i].block_addr != NULL_ADDR) valid++; } if (valid == 0) { @@ -2451,7 +2724,7 @@ static void __update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid, __clear_bit_le(nat_index, nm_i->full_nat_bits); } -static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, +static int __flush_nat_entry_set(struct f2fs_sb_info *sbi, struct nat_entry_set *set, struct cp_control *cpc) { struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); @@ -2475,6 +2748,9 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, down_write(&curseg->journal_rwsem); } else { page = get_next_nat_page(sbi, start_nid); + if (IS_ERR(page)) + return PTR_ERR(page); + nat_blk = page_address(page); f2fs_bug_on(sbi, !nat_blk); } @@ -2488,7 +2764,7 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, f2fs_bug_on(sbi, nat_get_blkaddr(ne) == NEW_ADDR); if (to_journal) { - offset = lookup_journal_in_cursum(journal, + offset = f2fs_lookup_journal_in_cursum(journal, NAT_JOURNAL, nid, 1); f2fs_bug_on(sbi, offset < 0); raw_ne = &nat_in_journal(journal, offset); @@ -2500,11 +2776,7 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, nat_reset_flag(ne); __clear_nat_cache_dirty(NM_I(sbi), set, ne); if (nat_get_blkaddr(ne) == NULL_ADDR) { - add_free_nid(sbi, nid, false); - spin_lock(&NM_I(sbi)->nid_list_lock); - NM_I(sbi)->available_nids++; - update_free_nid_bitmap(sbi, nid, true, false); - spin_unlock(&NM_I(sbi)->nid_list_lock); + add_free_nid(sbi, nid, false, true); } else { spin_lock(&NM_I(sbi)->nid_list_lock); update_free_nid_bitmap(sbi, nid, false, false); @@ -2524,12 +2796,13 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, radix_tree_delete(&NM_I(sbi)->nat_set_root, set->set); kmem_cache_free(nat_entry_set_slab, set); } + return 0; } /* * This function is called during the checkpointing process. */ -void flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) +int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); @@ -2539,9 +2812,17 @@ void flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) unsigned int found; nid_t set_idx = 0; LIST_HEAD(sets); + int err = 0; + + /* during unmount, let's flush nat_bits before checking dirty_nat_cnt */ + if (enabled_nat_bits(sbi, cpc)) { + down_write(&nm_i->nat_tree_lock); + remove_nats_in_journal(sbi); + up_write(&nm_i->nat_tree_lock); + } if (!nm_i->dirty_nat_cnt) - return; + return 0; down_write(&nm_i->nat_tree_lock); @@ -2564,11 +2845,16 @@ void flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) } /* flush dirty nats in nat entry set */ - list_for_each_entry_safe(set, tmp, &sets, set_list) - __flush_nat_entry_set(sbi, set, cpc); + list_for_each_entry_safe(set, tmp, &sets, set_list) { + err = __flush_nat_entry_set(sbi, set, cpc); + if (err) + break; + } up_write(&nm_i->nat_tree_lock); /* Allow dirty nats by node block allocation in write_begin */ + + return err; } static int __get_nat_bitmaps(struct f2fs_sb_info *sbi) @@ -2583,17 +2869,20 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi) if (!enabled_nat_bits(sbi, NULL)) return 0; - nm_i->nat_bits_blocks = F2FS_BYTES_TO_BLK((nat_bits_bytes << 1) + 8 + - F2FS_BLKSIZE - 1); - nm_i->nat_bits = kzalloc(nm_i->nat_bits_blocks << F2FS_BLKSIZE_BITS, - GFP_KERNEL); + nm_i->nat_bits_blocks = F2FS_BLK_ALIGN((nat_bits_bytes << 1) + 8); + nm_i->nat_bits = f2fs_kzalloc(sbi, + nm_i->nat_bits_blocks << F2FS_BLKSIZE_BITS, GFP_KERNEL); if (!nm_i->nat_bits) return -ENOMEM; nat_bits_addr = __start_cp_addr(sbi) + sbi->blocks_per_seg - nm_i->nat_bits_blocks; for (i = 0; i < nm_i->nat_bits_blocks; i++) { - struct page *page = get_meta_page(sbi, nat_bits_addr++); + struct page *page; + + page = f2fs_get_meta_page(sbi, nat_bits_addr++); + if (IS_ERR(page)) + return PTR_ERR(page); memcpy(nm_i->nat_bits + (i << F2FS_BLKSIZE_BITS), page_address(page), F2FS_BLKSIZE); @@ -2630,7 +2919,7 @@ static inline void load_free_nid_bitmap(struct f2fs_sb_info *sbi) __set_bit_le(i, nm_i->nat_block_bitmap); nid = i * NAT_ENTRY_PER_BLOCK; - last_nid = (i + 1) * NAT_ENTRY_PER_BLOCK; + last_nid = nid + NAT_ENTRY_PER_BLOCK; spin_lock(&NM_I(sbi)->nid_list_lock); for (; nid < last_nid; nid++) @@ -2664,20 +2953,20 @@ static int init_node_manager(struct f2fs_sb_info *sbi) /* not used nids: 0, node, meta, (and root counted as valid node) */ nm_i->available_nids = nm_i->max_nid - sbi->total_valid_node_count - - F2FS_RESERVED_NODE_NUM; - nm_i->nid_cnt[FREE_NID_LIST] = 0; - nm_i->nid_cnt[ALLOC_NID_LIST] = 0; + sbi->nquota_files - F2FS_RESERVED_NODE_NUM; + nm_i->nid_cnt[FREE_NID] = 0; + nm_i->nid_cnt[PREALLOC_NID] = 0; nm_i->nat_cnt = 0; nm_i->ram_thresh = DEF_RAM_THRESHOLD; nm_i->ra_nid_pages = DEF_RA_NID_PAGES; nm_i->dirty_nats_ratio = DEF_DIRTY_NAT_RATIO_THRESHOLD; INIT_RADIX_TREE(&nm_i->free_nid_root, GFP_ATOMIC); - INIT_LIST_HEAD(&nm_i->nid_list[FREE_NID_LIST]); - INIT_LIST_HEAD(&nm_i->nid_list[ALLOC_NID_LIST]); + INIT_LIST_HEAD(&nm_i->free_nid_list); INIT_RADIX_TREE(&nm_i->nat_root, GFP_NOIO); INIT_RADIX_TREE(&nm_i->nat_set_root, GFP_NOIO); INIT_LIST_HEAD(&nm_i->nat_entries); + spin_lock_init(&nm_i->nat_list_lock); mutex_init(&nm_i->build_lock); spin_lock_init(&nm_i->nid_list_lock); @@ -2711,29 +3000,42 @@ static int init_node_manager(struct f2fs_sb_info *sbi) static int init_free_nid_cache(struct f2fs_sb_info *sbi) { struct f2fs_nm_info *nm_i = NM_I(sbi); + int i; - nm_i->free_nid_bitmap = kvzalloc(nm_i->nat_blocks * - NAT_ENTRY_BITMAP_SIZE, GFP_KERNEL); + nm_i->free_nid_bitmap = + f2fs_kzalloc(sbi, array_size(sizeof(unsigned char *), + nm_i->nat_blocks), + GFP_KERNEL); if (!nm_i->free_nid_bitmap) return -ENOMEM; - nm_i->nat_block_bitmap = kvzalloc(nm_i->nat_blocks / 8, + for (i = 0; i < nm_i->nat_blocks; i++) { + nm_i->free_nid_bitmap[i] = f2fs_kvzalloc(sbi, + f2fs_bitmap_size(NAT_ENTRY_PER_BLOCK), GFP_KERNEL); + if (!nm_i->free_nid_bitmap[i]) + return -ENOMEM; + } + + nm_i->nat_block_bitmap = f2fs_kvzalloc(sbi, nm_i->nat_blocks / 8, GFP_KERNEL); if (!nm_i->nat_block_bitmap) return -ENOMEM; - nm_i->free_nid_count = kvzalloc(nm_i->nat_blocks * - sizeof(unsigned short), GFP_KERNEL); + nm_i->free_nid_count = + f2fs_kvzalloc(sbi, array_size(sizeof(unsigned short), + nm_i->nat_blocks), + GFP_KERNEL); if (!nm_i->free_nid_count) return -ENOMEM; return 0; } -int build_node_manager(struct f2fs_sb_info *sbi) +int f2fs_build_node_manager(struct f2fs_sb_info *sbi) { int err; - sbi->nm_info = kzalloc(sizeof(struct f2fs_nm_info), GFP_KERNEL); + sbi->nm_info = f2fs_kzalloc(sbi, sizeof(struct f2fs_nm_info), + GFP_KERNEL); if (!sbi->nm_info) return -ENOMEM; @@ -2748,11 +3050,10 @@ int build_node_manager(struct f2fs_sb_info *sbi) /* load free nid status from nat_bits table */ load_free_nid_bitmap(sbi); - build_free_nids(sbi, true, true); - return 0; + return f2fs_build_free_nids(sbi, true, true); } -void destroy_node_manager(struct f2fs_sb_info *sbi) +void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i, *next_i; @@ -2766,16 +3067,15 @@ void destroy_node_manager(struct f2fs_sb_info *sbi) /* destroy free nid list */ spin_lock(&nm_i->nid_list_lock); - list_for_each_entry_safe(i, next_i, &nm_i->nid_list[FREE_NID_LIST], - list) { - __remove_nid_from_list(sbi, i, FREE_NID_LIST, false); + list_for_each_entry_safe(i, next_i, &nm_i->free_nid_list, list) { + __remove_free_nid(sbi, i, FREE_NID); spin_unlock(&nm_i->nid_list_lock); kmem_cache_free(free_nid_slab, i); spin_lock(&nm_i->nid_list_lock); } - f2fs_bug_on(sbi, nm_i->nid_cnt[FREE_NID_LIST]); - f2fs_bug_on(sbi, nm_i->nid_cnt[ALLOC_NID_LIST]); - f2fs_bug_on(sbi, !list_empty(&nm_i->nid_list[ALLOC_NID_LIST])); + f2fs_bug_on(sbi, nm_i->nid_cnt[FREE_NID]); + f2fs_bug_on(sbi, nm_i->nid_cnt[PREALLOC_NID]); + f2fs_bug_on(sbi, !list_empty(&nm_i->free_nid_list)); spin_unlock(&nm_i->nid_list_lock); /* destroy nat cache */ @@ -2785,8 +3085,13 @@ void destroy_node_manager(struct f2fs_sb_info *sbi) unsigned idx; nid = nat_get_nid(natvec[found - 1]) + 1; - for (idx = 0; idx < found; idx++) + for (idx = 0; idx < found; idx++) { + spin_lock(&nm_i->nat_list_lock); + list_del(&natvec[idx]->list); + spin_unlock(&nm_i->nat_list_lock); + __del_from_nat_cache(nm_i, natvec[idx]); + } } f2fs_bug_on(sbi, nm_i->nat_cnt); @@ -2807,19 +3112,25 @@ void destroy_node_manager(struct f2fs_sb_info *sbi) up_write(&nm_i->nat_tree_lock); kvfree(nm_i->nat_block_bitmap); - kvfree(nm_i->free_nid_bitmap); + if (nm_i->free_nid_bitmap) { + int i; + + for (i = 0; i < nm_i->nat_blocks; i++) + kvfree(nm_i->free_nid_bitmap[i]); + kvfree(nm_i->free_nid_bitmap); + } kvfree(nm_i->free_nid_count); - kfree(nm_i->nat_bitmap); - kfree(nm_i->nat_bits); + kvfree(nm_i->nat_bitmap); + kvfree(nm_i->nat_bits); #ifdef CONFIG_F2FS_CHECK_FS - kfree(nm_i->nat_bitmap_mir); + kvfree(nm_i->nat_bitmap_mir); #endif sbi->nm_info = NULL; - kfree(nm_i); + kvfree(nm_i); } -int __init create_node_manager_caches(void) +int __init f2fs_create_node_manager_caches(void) { nat_entry_slab = f2fs_kmem_cache_create("nat_entry", sizeof(struct nat_entry)); @@ -2835,8 +3146,15 @@ int __init create_node_manager_caches(void) sizeof(struct nat_entry_set)); if (!nat_entry_set_slab) goto destroy_free_nid; + + fsync_node_entry_slab = f2fs_kmem_cache_create("fsync_node_entry", + sizeof(struct fsync_node_entry)); + if (!fsync_node_entry_slab) + goto destroy_nat_entry_set; return 0; +destroy_nat_entry_set: + kmem_cache_destroy(nat_entry_set_slab); destroy_free_nid: kmem_cache_destroy(free_nid_slab); destroy_nat_entry: @@ -2845,8 +3163,9 @@ fail: return -ENOMEM; } -void destroy_node_manager_caches(void) +void f2fs_destroy_node_manager_caches(void) { + kmem_cache_destroy(fsync_node_entry_slab); kmem_cache_destroy(nat_entry_set_slab); kmem_cache_destroy(free_nid_slab); kmem_cache_destroy(nat_entry_slab); diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h index bb53e9955ff2..e05af5df5648 100644 --- a/fs/f2fs/node.h +++ b/fs/f2fs/node.h @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/node.h * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ /* start node id of a node block dedicated to the given node id */ #define START_NID(nid) (((nid) / NAT_ENTRY_PER_BLOCK) * NAT_ENTRY_PER_BLOCK) @@ -44,6 +41,7 @@ enum { HAS_FSYNCED_INODE, /* is the inode fsynced before? */ HAS_LAST_FSYNC, /* has the latest node fsync mark? */ IS_DIRTY, /* this nat entry is dirty? */ + IS_PREALLOC, /* nat entry is preallocated */ }; /* @@ -134,12 +132,18 @@ static inline bool excess_cached_nats(struct f2fs_sb_info *sbi) return NM_I(sbi)->nat_cnt >= DEF_NAT_CACHE_THRESHOLD; } +static inline bool excess_dirty_nodes(struct f2fs_sb_info *sbi) +{ + return get_pages(sbi, F2FS_DIRTY_NODES) >= sbi->blocks_per_seg * 8; +} + enum mem_type { FREE_NIDS, /* indicates the free nid list */ NAT_ENTRIES, /* indicates the cached nat entry */ DIRTY_DENTS, /* indicates dirty dentry pages */ INO_ENTRIES, /* indicates inode entries */ EXTENT_CACHE, /* indicates extent cache */ + INMEM_PAGES, /* indicates inmemory pages */ BASE_CHECK, /* check kernel status */ }; @@ -150,18 +154,10 @@ struct nat_entry_set { unsigned int entry_cnt; /* the # of nat entries in set */ }; -/* - * For free nid mangement - */ -enum nid_state { - NID_NEW, /* newly added to free nid list */ - NID_ALLOC /* it is allocated */ -}; - struct free_nid { struct list_head list; /* for free node id list */ nid_t nid; /* node id */ - int state; /* in use or not: NID_NEW or NID_ALLOC */ + int state; /* in use or not: FREE_NID or PREALLOC_NID */ }; static inline void next_free_nid(struct f2fs_sb_info *sbi, nid_t *nid) @@ -170,12 +166,11 @@ static inline void next_free_nid(struct f2fs_sb_info *sbi, nid_t *nid) struct free_nid *fnid; spin_lock(&nm_i->nid_list_lock); - if (nm_i->nid_cnt[FREE_NID_LIST] <= 0) { + if (nm_i->nid_cnt[FREE_NID] <= 0) { spin_unlock(&nm_i->nid_list_lock); return; } - fnid = list_first_entry(&nm_i->nid_list[FREE_NID_LIST], - struct free_nid, list); + fnid = list_first_entry(&nm_i->free_nid_list, struct free_nid, list); *nid = fnid->nid; spin_unlock(&nm_i->nid_list_lock); } @@ -313,6 +308,10 @@ static inline bool is_recoverable_dnode(struct page *page) struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page)); __u64 cp_ver = cur_cp_version(ckpt); + /* Don't care crc part, if fsck.f2fs sets it. */ + if (__is_set_ckpt_flags(ckpt, CP_NOCRC_RECOVERY_FLAG)) + return (cp_ver << 32) == (cpver_of_node(page) << 32); + if (__is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG)) cp_ver |= (cur_cp_crc(ckpt) << 32); @@ -362,7 +361,7 @@ static inline int set_nid(struct page *p, int off, nid_t nid, bool i) { struct f2fs_node *rn = F2FS_NODE(p); - f2fs_wait_on_page_writeback(p, NODE, true); + f2fs_wait_on_page_writeback(p, NODE, true, true); if (i) rn->i.i_nid[off - NODE_DIR1_BLOCK] = cpu_to_le32(nid); @@ -426,12 +425,12 @@ static inline void clear_inline_node(struct page *page) ClearPageChecked(page); } -static inline void set_cold_node(struct inode *inode, struct page *page) +static inline void set_cold_node(struct page *page, bool is_dir) { struct f2fs_node *rn = F2FS_NODE(page); unsigned int flag = le32_to_cpu(rn->footer.flag); - if (S_ISDIR(inode->i_mode)) + if (is_dir) flag &= ~(0x1 << COLD_BIT_SHIFT); else flag |= (0x1 << COLD_BIT_SHIFT); @@ -447,6 +446,10 @@ static inline void set_mark(struct page *page, int mark, int type) else flag &= ~(0x1 << type); rn->footer.flag = cpu_to_le32(flag); + +#ifdef CONFIG_F2FS_CHECK_FS + f2fs_inode_chksum_set(F2FS_P_SB(page), page); +#endif } #define set_dentry_mark(page, mark) set_mark(page, mark, DENT_BIT_SHIFT) #define set_fsync_mark(page, mark) set_mark(page, mark, FSYNC_BIT_SHIFT) diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 2eef266b656b..9af5c7b962e3 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/recovery.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> @@ -47,7 +44,7 @@ static struct kmem_cache *fsync_entry_slab; -bool space_for_roll_forward(struct f2fs_sb_info *sbi) +bool f2fs_space_for_roll_forward(struct f2fs_sb_info *sbi) { s64 nalloc = percpu_counter_sum_positive(&sbi->alloc_valid_block_count); @@ -99,8 +96,12 @@ err_out: return ERR_PTR(err); } -static void del_fsync_inode(struct fsync_inode_entry *entry) +static void del_fsync_inode(struct fsync_inode_entry *entry, int drop) { + if (drop) { + /* inode should not be recovered, drop it */ + f2fs_inode_synced(entry->inode); + } iput(entry->inode); list_del(&entry->list); kmem_cache_free(fsync_entry_slab, entry); @@ -144,7 +145,7 @@ static int recover_dentry(struct inode *inode, struct page *ipage, retry: de = __f2fs_find_entry(dir, &fname, &page); if (de && inode->i_ino == le32_to_cpu(de->ino)) - goto out_unmap_put; + goto out_put; if (de) { einode = f2fs_iget_retry(inode->i_sb, le32_to_cpu(de->ino)); @@ -153,19 +154,19 @@ retry: err = PTR_ERR(einode); if (err == -ENOENT) err = -EEXIST; - goto out_unmap_put; + goto out_put; } err = dquot_initialize(einode); if (err) { iput(einode); - goto out_unmap_put; + goto out_put; } - err = acquire_orphan_inode(F2FS_I_SB(inode)); + err = f2fs_acquire_orphan_inode(F2FS_I_SB(inode)); if (err) { iput(einode); - goto out_unmap_put; + goto out_put; } f2fs_delete_entry(de, page, dir, einode); iput(einode); @@ -173,15 +174,14 @@ retry: } else if (IS_ERR(page)) { err = PTR_ERR(page); } else { - err = __f2fs_do_add_link(dir, &fname, inode, + err = f2fs_add_dentry(dir, &fname, inode, inode->i_ino, inode->i_mode); } if (err == -ENOMEM) goto retry; goto out; -out_unmap_put: - f2fs_dentry_kunmap(dir, page); +out_put: f2fs_put_page(page, 0); out: if (file_enc_name(inode)) @@ -195,24 +195,77 @@ out: return err; } -static void recover_inode(struct inode *inode, struct page *page) +static int recover_quota_data(struct inode *inode, struct page *page) +{ + struct f2fs_inode *raw = F2FS_INODE(page); + struct iattr attr; + uid_t i_uid = le32_to_cpu(raw->i_uid); + gid_t i_gid = le32_to_cpu(raw->i_gid); + int err; + + memset(&attr, 0, sizeof(attr)); + + attr.ia_uid = make_kuid(inode->i_sb->s_user_ns, i_uid); + attr.ia_gid = make_kgid(inode->i_sb->s_user_ns, i_gid); + + if (!uid_eq(attr.ia_uid, inode->i_uid)) + attr.ia_valid |= ATTR_UID; + if (!gid_eq(attr.ia_gid, inode->i_gid)) + attr.ia_valid |= ATTR_GID; + + if (!attr.ia_valid) + return 0; + + err = dquot_transfer(inode, &attr); + if (err) + set_sbi_flag(F2FS_I_SB(inode), SBI_QUOTA_NEED_REPAIR); + return err; +} + +static void recover_inline_flags(struct inode *inode, struct f2fs_inode *ri) +{ + if (ri->i_inline & F2FS_PIN_FILE) + set_inode_flag(inode, FI_PIN_FILE); + else + clear_inode_flag(inode, FI_PIN_FILE); + if (ri->i_inline & F2FS_DATA_EXIST) + set_inode_flag(inode, FI_DATA_EXIST); + else + clear_inode_flag(inode, FI_DATA_EXIST); +} + +static int recover_inode(struct inode *inode, struct page *page) { struct f2fs_inode *raw = F2FS_INODE(page); char *name; + int err; inode->i_mode = le16_to_cpu(raw->i_mode); + + err = recover_quota_data(inode, page); + if (err) + return err; + i_uid_write(inode, le32_to_cpu(raw->i_uid)); i_gid_write(inode, le32_to_cpu(raw->i_gid)); if (raw->i_inline & F2FS_EXTRA_ATTR) { - if (f2fs_sb_has_project_quota(F2FS_I_SB(inode)->sb) && + if (f2fs_sb_has_project_quota(F2FS_I_SB(inode)) && F2FS_FITS_IN_INODE(raw, le16_to_cpu(raw->i_extra_isize), i_projid)) { projid_t i_projid; + kprojid_t kprojid; i_projid = (projid_t)le32_to_cpu(raw->i_projid); - F2FS_I(inode)->i_projid = - make_kprojid(&init_user_ns, i_projid); + kprojid = make_kprojid(&init_user_ns, i_projid); + + if (!projid_eq(kprojid, F2FS_I(inode)->i_projid)) { + err = f2fs_transfer_project_quota(inode, + kprojid); + if (err) + return err; + F2FS_I(inode)->i_projid = kprojid; + } } } @@ -226,6 +279,11 @@ static void recover_inode(struct inode *inode, struct page *page) F2FS_I(inode)->i_advise = raw->i_advise; F2FS_I(inode)->i_flags = le32_to_cpu(raw->i_flags); + f2fs_set_inode_flags(inode); + F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN] = + le16_to_cpu(raw->i_gc_failures); + + recover_inline_flags(inode, raw); f2fs_mark_inode_dirty_sync(inode, true); @@ -234,8 +292,10 @@ static void recover_inode(struct inode *inode, struct page *page) else name = F2FS_INODE(page)->i_name; - f2fs_msg(inode->i_sb, KERN_NOTICE, "recover_inode: ino = %x, name = %s", - ino_of_node(page), name); + f2fs_msg(inode->i_sb, KERN_NOTICE, + "recover_inode: ino = %x, name = %s, inline = %x", + ino_of_node(page), name, raw->i_inline); + return 0; } static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, @@ -244,6 +304,9 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, struct curseg_info *curseg; struct page *page = NULL; block_t blkaddr; + unsigned int loop_cnt = 0; + unsigned int free_blocks = MAIN_SEGS(sbi) * sbi->blocks_per_seg - + valid_user_blocks(sbi); int err = 0; /* get node pages in the current segment */ @@ -256,7 +319,11 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, if (!f2fs_is_valid_blkaddr(sbi, blkaddr, META_POR)) return 0; - page = get_tmp_page(sbi, blkaddr); + page = f2fs_get_tmp_page(sbi, blkaddr); + if (IS_ERR(page)) { + err = PTR_ERR(page); + break; + } if (!is_recoverable_dnode(page)) break; @@ -270,7 +337,7 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, if (!check_only && IS_INODE(page) && is_dent_dnode(page)) { - err = recover_inode_page(sbi, page); + err = f2fs_recover_inode_page(sbi, page); if (err) break; quota_inode = true; @@ -296,22 +363,33 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, if (IS_INODE(page) && is_dent_dnode(page)) entry->last_dentry = blkaddr; next: + /* sanity check in order to detect looped node chain */ + if (++loop_cnt >= free_blocks || + blkaddr == next_blkaddr_of_node(page)) { + f2fs_msg(sbi->sb, KERN_NOTICE, + "%s: detect looped node chain, " + "blkaddr:%u, next:%u", + __func__, blkaddr, next_blkaddr_of_node(page)); + err = -EINVAL; + break; + } + /* check next segment */ blkaddr = next_blkaddr_of_node(page); f2fs_put_page(page, 1); - ra_meta_pages_cond(sbi, blkaddr); + f2fs_ra_meta_pages_cond(sbi, blkaddr); } f2fs_put_page(page, 1); return err; } -static void destroy_fsync_dnodes(struct list_head *head) +static void destroy_fsync_dnodes(struct list_head *head, int drop) { struct fsync_inode_entry *entry, *tmp; list_for_each_entry_safe(entry, tmp, head, list) - del_fsync_inode(entry); + del_fsync_inode(entry, drop); } static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi, @@ -343,7 +421,9 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi, } } - sum_page = get_sum_page(sbi, segno); + sum_page = f2fs_get_sum_page(sbi, segno); + if (IS_ERR(sum_page)) + return PTR_ERR(sum_page); sum_node = (struct f2fs_summary_block *)page_address(sum_page); sum = sum_node->entries[blkoff]; f2fs_put_page(sum_page, 1); @@ -363,7 +443,7 @@ got_it: } /* Get the node page */ - node_page = get_node_page(sbi, nid); + node_page = f2fs_get_node_page(sbi, nid); if (IS_ERR(node_page)) return PTR_ERR(node_page); @@ -388,7 +468,8 @@ got_it: inode = dn->inode; } - bidx = start_bidx_of_node(offset, inode) + le16_to_cpu(sum.ofs_in_node); + bidx = f2fs_start_bidx_of_node(offset, inode) + + le16_to_cpu(sum.ofs_in_node); /* * if inode page is locked, unlock temporarily, but its reference @@ -398,11 +479,11 @@ got_it: unlock_page(dn->inode_page); set_new_dnode(&tdn, inode, NULL, NULL, 0); - if (get_dnode_of_data(&tdn, bidx, LOOKUP_NODE)) + if (f2fs_get_dnode_of_data(&tdn, bidx, LOOKUP_NODE)) goto out; if (tdn.data_blkaddr == blkaddr) - truncate_data_blocks_range(&tdn, 1); + f2fs_truncate_data_blocks_range(&tdn, 1); f2fs_put_dnode(&tdn); out: @@ -415,14 +496,14 @@ out: truncate_out: if (datablock_addr(tdn.inode, tdn.node_page, tdn.ofs_in_node) == blkaddr) - truncate_data_blocks_range(&tdn, 1); + f2fs_truncate_data_blocks_range(&tdn, 1); if (dn->inode->i_ino == nid && !dn->inode_page_locked) unlock_page(dn->inode_page); return 0; } static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, - struct page *page, block_t blkaddr) + struct page *page) { struct dnode_of_data dn; struct node_info ni; @@ -431,25 +512,25 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, /* step 1: recover xattr */ if (IS_INODE(page)) { - recover_inline_xattr(inode, page); + f2fs_recover_inline_xattr(inode, page); } else if (f2fs_has_xattr_block(ofs_of_node(page))) { - err = recover_xattr_data(inode, page, blkaddr); + err = f2fs_recover_xattr_data(inode, page); if (!err) recovered++; goto out; } /* step 2: recover inline data */ - if (recover_inline_data(inode, page)) + if (f2fs_recover_inline_data(inode, page)) goto out; /* step 3: recover data indices */ - start = start_bidx_of_node(ofs_of_node(page), inode); + start = f2fs_start_bidx_of_node(ofs_of_node(page), inode); end = start + ADDRS_PER_PAGE(page, inode); set_new_dnode(&dn, inode, NULL, NULL, 0); retry_dn: - err = get_dnode_of_data(&dn, start, ALLOC_NODE); + err = f2fs_get_dnode_of_data(&dn, start, ALLOC_NODE); if (err) { if (err == -ENOMEM) { congestion_wait(BLK_RW_ASYNC, HZ/50); @@ -458,9 +539,12 @@ retry_dn: goto out; } - f2fs_wait_on_page_writeback(dn.node_page, NODE, true); + f2fs_wait_on_page_writeback(dn.node_page, NODE, true, true); + + err = f2fs_get_node_info(sbi, dn.nid, &ni); + if (err) + goto err; - get_node_info(sbi, dn.nid, &ni); f2fs_bug_on(sbi, ni.ino != ino_of_node(page)); if (ofs_of_node(dn.node_page) != ofs_of_node(page)) { @@ -484,7 +568,7 @@ retry_dn: /* dest is invalid, just invalidate src block */ if (dest == NULL_ADDR) { - truncate_data_blocks_range(&dn, 1); + f2fs_truncate_data_blocks_range(&dn, 1); continue; } @@ -498,8 +582,8 @@ retry_dn: * and then reserve one new block in dnode page. */ if (dest == NEW_ADDR) { - truncate_data_blocks_range(&dn, 1); - reserve_new_block(&dn); + f2fs_truncate_data_blocks_range(&dn, 1); + f2fs_reserve_new_block(&dn); continue; } @@ -507,11 +591,10 @@ retry_dn: if (f2fs_is_valid_blkaddr(sbi, dest, META_POR)) { if (src == NULL_ADDR) { - err = reserve_new_block(&dn); -#ifdef CONFIG_F2FS_FAULT_INJECTION - while (err) - err = reserve_new_block(&dn); -#endif + err = f2fs_reserve_new_block(&dn); + while (err && + IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)) + err = f2fs_reserve_new_block(&dn); /* We should not get -ENOSPC */ f2fs_bug_on(sbi, err); if (err) @@ -551,7 +634,7 @@ out: } static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list, - struct list_head *dir_list) + struct list_head *tmp_inode_list, struct list_head *dir_list) { struct curseg_info *curseg; struct page *page = NULL; @@ -568,9 +651,13 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list, if (!f2fs_is_valid_blkaddr(sbi, blkaddr, META_POR)) break; - ra_meta_pages_cond(sbi, blkaddr); + f2fs_ra_meta_pages_cond(sbi, blkaddr); - page = get_tmp_page(sbi, blkaddr); + page = f2fs_get_tmp_page(sbi, blkaddr); + if (IS_ERR(page)) { + err = PTR_ERR(page); + break; + } if (!is_recoverable_dnode(page)) { f2fs_put_page(page, 1); @@ -585,8 +672,11 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list, * In this case, we can lose the latest inode(x). * So, call recover_inode for the inode update. */ - if (IS_INODE(page)) - recover_inode(entry->inode, page); + if (IS_INODE(page)) { + err = recover_inode(entry->inode, page); + if (err) + break; + } if (entry->last_dentry == blkaddr) { err = recover_dentry(entry->inode, page, dir_list); if (err) { @@ -594,35 +684,39 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list, break; } } - err = do_recover_data(sbi, entry->inode, page, blkaddr); + err = do_recover_data(sbi, entry->inode, page); if (err) { f2fs_put_page(page, 1); break; } if (entry->blkaddr == blkaddr) - del_fsync_inode(entry); + list_move_tail(&entry->list, tmp_inode_list); next: /* check next segment */ blkaddr = next_blkaddr_of_node(page); f2fs_put_page(page, 1); } if (!err) - allocate_new_segments(sbi); + f2fs_allocate_new_segments(sbi); return err; } -int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) +int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) { - struct list_head inode_list; + struct list_head inode_list, tmp_inode_list; struct list_head dir_list; int err; int ret = 0; unsigned long s_flags = sbi->sb->s_flags; bool need_writecp = false; +#ifdef CONFIG_QUOTA + int quota_enabled; +#endif if (s_flags & MS_RDONLY) { - f2fs_msg(sbi->sb, KERN_INFO, "orphan cleanup on readonly fs"); + f2fs_msg(sbi->sb, KERN_INFO, + "recover fsync data on readonly fs"); sbi->sb->s_flags &= ~MS_RDONLY; } @@ -630,7 +724,7 @@ int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) /* Needed for iput() to work correctly and not trash data */ sbi->sb->s_flags |= MS_ACTIVE; /* Turn on quotas so that they are updated correctly */ - f2fs_enable_quota_files(sbi); + quota_enabled = f2fs_enable_quota_files(sbi, s_flags & MS_RDONLY); #endif fsync_entry_slab = f2fs_kmem_cache_create("f2fs_fsync_inode_entry", @@ -641,6 +735,7 @@ int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) } INIT_LIST_HEAD(&inode_list); + INIT_LIST_HEAD(&tmp_inode_list); INIT_LIST_HEAD(&dir_list); /* prevent checkpoint */ @@ -659,11 +754,16 @@ int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) need_writecp = true; /* step #2: recover data */ - err = recover_data(sbi, &inode_list, &dir_list); + err = recover_data(sbi, &inode_list, &tmp_inode_list, &dir_list); if (!err) f2fs_bug_on(sbi, !list_empty(&inode_list)); + else { + /* restore s_flags to let iput() trash data */ + sbi->sb->s_flags = s_flags; + } skip: - destroy_fsync_dnodes(&inode_list); + destroy_fsync_dnodes(&inode_list, err); + destroy_fsync_dnodes(&tmp_inode_list, err); /* truncate meta pages to be used by the recovery */ truncate_inode_pages_range(META_MAPPING(sbi), @@ -672,26 +772,31 @@ skip: if (err) { truncate_inode_pages_final(NODE_MAPPING(sbi)); truncate_inode_pages_final(META_MAPPING(sbi)); + } else { + clear_sbi_flag(sbi, SBI_POR_DOING); } - - clear_sbi_flag(sbi, SBI_POR_DOING); mutex_unlock(&sbi->cp_mutex); /* let's drop all the directory inodes for clean checkpoint */ - destroy_fsync_dnodes(&dir_list); + destroy_fsync_dnodes(&dir_list, err); + + if (need_writecp) { + set_sbi_flag(sbi, SBI_IS_RECOVERED); - if (!err && need_writecp) { - struct cp_control cpc = { - .reason = CP_RECOVERY, - }; - err = write_checkpoint(sbi, &cpc); + if (!err) { + struct cp_control cpc = { + .reason = CP_RECOVERY, + }; + err = f2fs_write_checkpoint(sbi, &cpc); + } } kmem_cache_destroy(fsync_entry_slab); out: #ifdef CONFIG_QUOTA /* Turn quotas off */ - f2fs_quota_off_umount(sbi->sb); + if (quota_enabled) + f2fs_quota_off_umount(sbi->sb); #endif sbi->sb->s_flags = s_flags; /* Restore MS_RDONLY status */ diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 2cd0d126ef8f..5a61cf42ef74 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/segment.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> @@ -169,7 +166,7 @@ found: return result - size + __reverse_ffz(tmp); } -bool need_SSR(struct f2fs_sb_info *sbi) +bool f2fs_need_SSR(struct f2fs_sb_info *sbi) { int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES); int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS); @@ -177,22 +174,24 @@ bool need_SSR(struct f2fs_sb_info *sbi) if (test_opt(sbi, LFS)) return false; - if (sbi->gc_thread && sbi->gc_thread->gc_urgent) + if (sbi->gc_mode == GC_URGENT) + return true; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) return true; return free_sections(sbi) <= (node_secs + 2 * dent_secs + imeta_secs + - 2 * reserved_sections(sbi)); + SM_I(sbi)->min_ssr_sections + reserved_sections(sbi)); } -void register_inmem_page(struct inode *inode, struct page *page) +void f2fs_register_inmem_page(struct inode *inode, struct page *page) { + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); struct inmem_pages *new; f2fs_trace_pid(page); - set_page_private(page, (unsigned long)ATOMIC_WRITTEN_PAGE); - SetPagePrivate(page); + f2fs_set_page_private(page, (unsigned long)ATOMIC_WRITTEN_PAGE); new = f2fs_kmem_cache_alloc(inmem_entry_slab, GFP_NOFS); @@ -204,6 +203,10 @@ void register_inmem_page(struct inode *inode, struct page *page) mutex_lock(&fi->inmem_lock); get_page(page); list_add_tail(&new->list, &fi->inmem_pages); + spin_lock(&sbi->inode_lock[ATOMIC_FILE]); + if (list_empty(&fi->inmem_ilist)) + list_add_tail(&fi->inmem_ilist, &sbi->inode_list[ATOMIC_FILE]); + spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); inc_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES); mutex_unlock(&fi->inmem_lock); @@ -211,7 +214,8 @@ void register_inmem_page(struct inode *inode, struct page *page) } static int __revoke_inmem_pages(struct inode *inode, - struct list_head *head, bool drop, bool recover) + struct list_head *head, bool drop, bool recover, + bool trylock) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct inmem_pages *cur, *tmp; @@ -223,9 +227,18 @@ static int __revoke_inmem_pages(struct inode *inode, if (drop) trace_f2fs_commit_inmem_page(page, INMEM_DROP); - lock_page(page); + if (trylock) { + /* + * to avoid deadlock in between page lock and + * inmem_lock. + */ + if (!trylock_page(page)) + continue; + } else { + lock_page(page); + } - f2fs_wait_on_page_writeback(page, DATA, true); + f2fs_wait_on_page_writeback(page, DATA, true, true); if (recover) { struct dnode_of_data dn; @@ -234,7 +247,8 @@ static int __revoke_inmem_pages(struct inode *inode, trace_f2fs_commit_inmem_page(page, INMEM_REVOKE); retry: set_new_dnode(&dn, inode, NULL, NULL, 0); - err = get_dnode_of_data(&dn, page->index, LOOKUP_NODE); + err = f2fs_get_dnode_of_data(&dn, page->index, + LOOKUP_NODE); if (err) { if (err == -ENOMEM) { congestion_wait(BLK_RW_ASYNC, HZ/50); @@ -244,8 +258,18 @@ retry: err = -EAGAIN; goto next; } - get_node_info(sbi, dn.nid, &ni); - f2fs_replace_block(sbi, &dn, dn.data_blkaddr, + + err = f2fs_get_node_info(sbi, dn.nid, &ni); + if (err) { + f2fs_put_dnode(&dn); + return err; + } + + if (cur->old_addr == NEW_ADDR) { + f2fs_invalidate_blocks(sbi, dn.data_blkaddr); + f2fs_update_data_blkaddr(&dn, NEW_ADDR); + } else + f2fs_replace_block(sbi, &dn, dn.data_blkaddr, cur->old_addr, ni.version, true, true); f2fs_put_dnode(&dn); } @@ -255,8 +279,7 @@ next: ClearPageUptodate(page); clear_cold_data(page); } - set_page_private(page, 0); - ClearPagePrivate(page); + f2fs_clear_page_private(page); f2fs_put_page(page, 1); list_del(&cur->list); @@ -266,20 +289,63 @@ next: return err; } -void drop_inmem_pages(struct inode *inode) +void f2fs_drop_inmem_pages_all(struct f2fs_sb_info *sbi, bool gc_failure) { + struct list_head *head = &sbi->inode_list[ATOMIC_FILE]; + struct inode *inode; + struct f2fs_inode_info *fi; +next: + spin_lock(&sbi->inode_lock[ATOMIC_FILE]); + if (list_empty(head)) { + spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); + return; + } + fi = list_first_entry(head, struct f2fs_inode_info, inmem_ilist); + inode = igrab(&fi->vfs_inode); + spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); + + if (inode) { + if (gc_failure) { + if (fi->i_gc_failures[GC_FAILURE_ATOMIC]) + goto drop; + goto skip; + } +drop: + set_inode_flag(inode, FI_ATOMIC_REVOKE_REQUEST); + f2fs_drop_inmem_pages(inode); + iput(inode); + } +skip: + congestion_wait(BLK_RW_ASYNC, HZ/50); + cond_resched(); + goto next; +} + +void f2fs_drop_inmem_pages(struct inode *inode) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); - mutex_lock(&fi->inmem_lock); - __revoke_inmem_pages(inode, &fi->inmem_pages, true, false); - mutex_unlock(&fi->inmem_lock); + while (!list_empty(&fi->inmem_pages)) { + mutex_lock(&fi->inmem_lock); + __revoke_inmem_pages(inode, &fi->inmem_pages, + true, false, true); + + if (list_empty(&fi->inmem_pages)) { + spin_lock(&sbi->inode_lock[ATOMIC_FILE]); + if (!list_empty(&fi->inmem_ilist)) + list_del_init(&fi->inmem_ilist); + spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); + } + mutex_unlock(&fi->inmem_lock); + } clear_inode_flag(inode, FI_ATOMIC_FILE); - clear_inode_flag(inode, FI_HOT_DATA); + fi->i_gc_failures[GC_FAILURE_ATOMIC] = 0; stat_dec_atomic_write(inode); } -void drop_inmem_page(struct inode *inode, struct page *page) +void f2fs_drop_inmem_page(struct inode *inode, struct page *page) { struct f2fs_inode_info *fi = F2FS_I(inode); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); @@ -294,7 +360,7 @@ void drop_inmem_page(struct inode *inode, struct page *page) break; } - f2fs_bug_on(sbi, !cur || cur->page != page); + f2fs_bug_on(sbi, list_empty(head) || cur->page != page); list_del(&cur->list); mutex_unlock(&fi->inmem_lock); @@ -302,29 +368,31 @@ void drop_inmem_page(struct inode *inode, struct page *page) kmem_cache_free(inmem_entry_slab, cur); ClearPageUptodate(page); - set_page_private(page, 0); - ClearPagePrivate(page); + f2fs_clear_page_private(page); f2fs_put_page(page, 0); trace_f2fs_commit_inmem_page(page, INMEM_INVALIDATE); } -static int __commit_inmem_pages(struct inode *inode, - struct list_head *revoke_list) +static int __f2fs_commit_inmem_pages(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); struct inmem_pages *cur, *tmp; struct f2fs_io_info fio = { .sbi = sbi, + .ino = inode->i_ino, .type = DATA, .op = REQ_OP_WRITE, .op_flags = REQ_SYNC | REQ_PRIO, .io_type = FS_DATA_IO, }; - pgoff_t last_idx = ULONG_MAX; + struct list_head revoke_list; + bool submit_bio = false; int err = 0; + INIT_LIST_HEAD(&revoke_list); + list_for_each_entry_safe(cur, tmp, &fi->inmem_pages, list) { struct page *page = cur->page; @@ -332,18 +400,19 @@ static int __commit_inmem_pages(struct inode *inode, if (page->mapping == inode->i_mapping) { trace_f2fs_commit_inmem_page(page, INMEM); + f2fs_wait_on_page_writeback(page, DATA, true, true); + set_page_dirty(page); - f2fs_wait_on_page_writeback(page, DATA, true); if (clear_page_dirty_for_io(page)) { inode_dec_dirty_pages(inode); - remove_dirty_inode(inode); + f2fs_remove_dirty_inode(inode); } retry: fio.page = page; fio.old_blkaddr = NULL_ADDR; fio.encrypted_page = NULL; fio.need_lock = LOCK_DONE; - err = do_write_data_page(&fio); + err = f2fs_do_write_data_page(&fio); if (err) { if (err == -ENOMEM) { congestion_wait(BLK_RW_ASYNC, HZ/50); @@ -355,58 +424,65 @@ retry: } /* record old blkaddr for revoking */ cur->old_addr = fio.old_blkaddr; - last_idx = page->index; + submit_bio = true; } unlock_page(page); - list_move_tail(&cur->list, revoke_list); + list_move_tail(&cur->list, &revoke_list); } - if (last_idx != ULONG_MAX) - f2fs_submit_merged_write_cond(sbi, inode, 0, last_idx, DATA); + if (submit_bio) + f2fs_submit_merged_write_cond(sbi, inode, NULL, 0, DATA); - if (!err) - __revoke_inmem_pages(inode, revoke_list, false, false); + if (err) { + /* + * try to revoke all committed pages, but still we could fail + * due to no memory or other reason, if that happened, EAGAIN + * will be returned, which means in such case, transaction is + * already not integrity, caller should use journal to do the + * recovery or rewrite & commit last transaction. For other + * error number, revoking was done by filesystem itself. + */ + err = __revoke_inmem_pages(inode, &revoke_list, + false, true, false); + + /* drop all uncommitted pages */ + __revoke_inmem_pages(inode, &fi->inmem_pages, + true, false, false); + } else { + __revoke_inmem_pages(inode, &revoke_list, + false, false, false); + } return err; } -int commit_inmem_pages(struct inode *inode) +int f2fs_commit_inmem_pages(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); - struct list_head revoke_list; int err; - INIT_LIST_HEAD(&revoke_list); f2fs_balance_fs(sbi, true); - f2fs_lock_op(sbi); + down_write(&fi->i_gc_rwsem[WRITE]); + + f2fs_lock_op(sbi); set_inode_flag(inode, FI_ATOMIC_COMMIT); mutex_lock(&fi->inmem_lock); - err = __commit_inmem_pages(inode, &revoke_list); - if (err) { - int ret; - /* - * try to revoke all committed pages, but still we could fail - * due to no memory or other reason, if that happened, EAGAIN - * will be returned, which means in such case, transaction is - * already not integrity, caller should use journal to do the - * recovery or rewrite & commit last transaction. For other - * error number, revoking was done by filesystem itself. - */ - ret = __revoke_inmem_pages(inode, &revoke_list, false, true); - if (ret) - err = ret; + err = __f2fs_commit_inmem_pages(inode); - /* drop all uncommitted pages */ - __revoke_inmem_pages(inode, &fi->inmem_pages, true, false); - } + spin_lock(&sbi->inode_lock[ATOMIC_FILE]); + if (!list_empty(&fi->inmem_ilist)) + list_del_init(&fi->inmem_ilist); + spin_unlock(&sbi->inode_lock[ATOMIC_FILE]); mutex_unlock(&fi->inmem_lock); clear_inode_flag(inode, FI_ATOMIC_COMMIT); f2fs_unlock_op(sbi); + up_write(&fi->i_gc_rwsem[WRITE]); + return err; } @@ -416,17 +492,18 @@ int commit_inmem_pages(struct inode *inode) */ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need) { -#ifdef CONFIG_F2FS_FAULT_INJECTION if (time_to_inject(sbi, FAULT_CHECKPOINT)) { f2fs_show_injection_info(FAULT_CHECKPOINT); f2fs_stop_checkpoint(sbi, false); } -#endif /* balance_fs_bg is able to be pending */ if (need && excess_cached_nats(sbi)) f2fs_balance_fs_bg(sbi); + if (f2fs_is_checkpoint_ready(sbi)) + return; + /* * We should do GC or end up with checkpoint, if there are so many dirty * dir/node pages without enough free segments. @@ -443,32 +520,34 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi) return; /* try to shrink extent cache when there is no enough memory */ - if (!available_free_memory(sbi, EXTENT_CACHE)) + if (!f2fs_available_free_memory(sbi, EXTENT_CACHE)) f2fs_shrink_extent_tree(sbi, EXTENT_CACHE_SHRINK_NUMBER); /* check the # of cached NAT entries */ - if (!available_free_memory(sbi, NAT_ENTRIES)) - try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK); + if (!f2fs_available_free_memory(sbi, NAT_ENTRIES)) + f2fs_try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK); - if (!available_free_memory(sbi, FREE_NIDS)) - try_to_free_nids(sbi, MAX_FREE_NIDS); + if (!f2fs_available_free_memory(sbi, FREE_NIDS)) + f2fs_try_to_free_nids(sbi, MAX_FREE_NIDS); else - build_free_nids(sbi, false, false); + f2fs_build_free_nids(sbi, false, false); - if (!is_idle(sbi) && !excess_dirty_nats(sbi)) + if (!is_idle(sbi, REQ_TIME) && + (!excess_dirty_nats(sbi) && !excess_dirty_nodes(sbi))) return; /* checkpoint is the only way to shrink partial cached entries */ - if (!available_free_memory(sbi, NAT_ENTRIES) || - !available_free_memory(sbi, INO_ENTRIES) || + if (!f2fs_available_free_memory(sbi, NAT_ENTRIES) || + !f2fs_available_free_memory(sbi, INO_ENTRIES) || excess_prefree_segs(sbi) || excess_dirty_nats(sbi) || + excess_dirty_nodes(sbi) || f2fs_time_over(sbi, CP_TIME)) { if (test_opt(sbi, DATA_FLUSH)) { struct blk_plug plug; blk_start_plug(&plug); - sync_dirty_inodes(sbi, FILE_INODE); + f2fs_sync_dirty_inodes(sbi, FILE_INODE); blk_finish_plug(&plug); } f2fs_sync_fs(sbi->sb, true); @@ -479,9 +558,13 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi) static int __submit_flush_wait(struct f2fs_sb_info *sbi, struct block_device *bdev) { - struct bio *bio = f2fs_bio_alloc(0); + struct bio *bio; int ret; + bio = f2fs_bio_alloc(sbi, 0, false); + if (!bio) + return -ENOMEM; + bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH; bio_set_dev(bio, bdev); ret = submit_bio_wait(bio); @@ -492,15 +575,17 @@ static int __submit_flush_wait(struct f2fs_sb_info *sbi, return ret; } -static int submit_flush_wait(struct f2fs_sb_info *sbi) +static int submit_flush_wait(struct f2fs_sb_info *sbi, nid_t ino) { - int ret = __submit_flush_wait(sbi, sbi->sb->s_bdev); + int ret = 0; int i; - if (!f2fs_is_multi_device(sbi) || ret) - return ret; + if (!sbi->s_ndevs) + return __submit_flush_wait(sbi, sbi->sb->s_bdev); - for (i = 1; i < sbi->s_ndevs; i++) { + for (i = 0; i < sbi->s_ndevs; i++) { + if (!f2fs_is_dirty_device(sbi, ino, i, FLUSH_INO)) + continue; ret = __submit_flush_wait(sbi, FDEV(i).bdev); if (ret) break; @@ -526,7 +611,9 @@ repeat: fcc->dispatch_list = llist_del_all(&fcc->issue_list); fcc->dispatch_list = llist_reverse_order(fcc->dispatch_list); - ret = submit_flush_wait(sbi); + cmd = llist_entry(fcc->dispatch_list, struct flush_cmd, llnode); + + ret = submit_flush_wait(sbi, cmd->ino); atomic_inc(&fcc->issued_flush); llist_for_each_entry_safe(cmd, next, @@ -544,7 +631,7 @@ repeat: goto repeat; } -int f2fs_issue_flush(struct f2fs_sb_info *sbi) +int f2fs_issue_flush(struct f2fs_sb_info *sbi, nid_t ino) { struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info; struct flush_cmd cmd; @@ -554,19 +641,22 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi) return 0; if (!test_opt(sbi, FLUSH_MERGE)) { - ret = submit_flush_wait(sbi); + atomic_inc(&fcc->queued_flush); + ret = submit_flush_wait(sbi, ino); + atomic_dec(&fcc->queued_flush); atomic_inc(&fcc->issued_flush); return ret; } - if (atomic_inc_return(&fcc->issing_flush) == 1) { - ret = submit_flush_wait(sbi); - atomic_dec(&fcc->issing_flush); + if (atomic_inc_return(&fcc->queued_flush) == 1 || sbi->s_ndevs > 1) { + ret = submit_flush_wait(sbi, ino); + atomic_dec(&fcc->queued_flush); atomic_inc(&fcc->issued_flush); return ret; } + cmd.ino = ino; init_completion(&cmd.wait); llist_add(&cmd.llnode, &fcc->issue_list); @@ -579,23 +669,23 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi) if (fcc->f2fs_issue_flush) { wait_for_completion(&cmd.wait); - atomic_dec(&fcc->issing_flush); + atomic_dec(&fcc->queued_flush); } else { struct llist_node *list; list = llist_del_all(&fcc->issue_list); if (!list) { wait_for_completion(&cmd.wait); - atomic_dec(&fcc->issing_flush); + atomic_dec(&fcc->queued_flush); } else { struct flush_cmd *tmp, *next; - ret = submit_flush_wait(sbi); + ret = submit_flush_wait(sbi, ino); llist_for_each_entry_safe(tmp, next, list, llnode) { if (tmp == &cmd) { cmd.ret = ret; - atomic_dec(&fcc->issing_flush); + atomic_dec(&fcc->queued_flush); continue; } tmp->ret = ret; @@ -607,7 +697,7 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi) return cmd.ret; } -int create_flush_cmd_control(struct f2fs_sb_info *sbi) +int f2fs_create_flush_cmd_control(struct f2fs_sb_info *sbi) { dev_t dev = sbi->sb->s_bdev->bd_dev; struct flush_cmd_control *fcc; @@ -620,11 +710,11 @@ int create_flush_cmd_control(struct f2fs_sb_info *sbi) goto init_thread; } - fcc = kzalloc(sizeof(struct flush_cmd_control), GFP_KERNEL); + fcc = f2fs_kzalloc(sbi, sizeof(struct flush_cmd_control), GFP_KERNEL); if (!fcc) return -ENOMEM; atomic_set(&fcc->issued_flush, 0); - atomic_set(&fcc->issing_flush, 0); + atomic_set(&fcc->queued_flush, 0); init_waitqueue_head(&fcc->flush_wait_queue); init_llist_head(&fcc->issue_list); SM_I(sbi)->fcc_info = fcc; @@ -636,7 +726,7 @@ init_thread: "f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev)); if (IS_ERR(fcc->f2fs_issue_flush)) { err = PTR_ERR(fcc->f2fs_issue_flush); - kfree(fcc); + kvfree(fcc); SM_I(sbi)->fcc_info = NULL; return err; } @@ -644,7 +734,7 @@ init_thread: return err; } -void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free) +void f2fs_destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free) { struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info; @@ -655,11 +745,33 @@ void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free) kthread_stop(flush_thread); } if (free) { - kfree(fcc); + kvfree(fcc); SM_I(sbi)->fcc_info = NULL; } } +int f2fs_flush_device_cache(struct f2fs_sb_info *sbi) +{ + int ret = 0, i; + + if (!sbi->s_ndevs) + return 0; + + for (i = 1; i < sbi->s_ndevs; i++) { + if (!f2fs_test_bit(i, (char *)&sbi->dirty_device)) + continue; + ret = __submit_flush_wait(sbi, FDEV(i).bdev); + if (ret) + break; + + spin_lock(&sbi->dev_lock); + f2fs_clear_bit(i, (char *)&sbi->dirty_device); + spin_unlock(&sbi->dev_lock); + } + + return ret; +} + static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno, enum dirty_type dirty_type) { @@ -714,7 +826,7 @@ static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno, static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); - unsigned short valid_blocks; + unsigned short valid_blocks, ckpt_valid_blocks; if (segno == NULL_SEGNO || IS_CURSEG(sbi, segno)) return; @@ -722,8 +834,10 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno) mutex_lock(&dirty_i->seglist_lock); valid_blocks = get_valid_blocks(sbi, segno, false); + ckpt_valid_blocks = get_ckpt_valid_blocks(sbi, segno); - if (valid_blocks == 0) { + if (valid_blocks == 0 && (!is_sbi_flag_set(sbi, SBI_CP_DISABLED) || + ckpt_valid_blocks == sbi->blocks_per_seg)) { __locate_dirty_segment(sbi, segno, PRE); __remove_dirty_segment(sbi, segno, DIRTY); } else if (valid_blocks < sbi->blocks_per_seg) { @@ -736,6 +850,69 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno) mutex_unlock(&dirty_i->seglist_lock); } +/* This moves currently empty dirty blocks to prefree. Must hold seglist_lock */ +void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + unsigned int segno; + + mutex_lock(&dirty_i->seglist_lock); + for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) { + if (get_valid_blocks(sbi, segno, false)) + continue; + if (IS_CURSEG(sbi, segno)) + continue; + __locate_dirty_segment(sbi, segno, PRE); + __remove_dirty_segment(sbi, segno, DIRTY); + } + mutex_unlock(&dirty_i->seglist_lock); +} + +int f2fs_disable_cp_again(struct f2fs_sb_info *sbi) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + block_t ovp = overprovision_segments(sbi) << sbi->log_blocks_per_seg; + block_t holes[2] = {0, 0}; /* DATA and NODE */ + struct seg_entry *se; + unsigned int segno; + + mutex_lock(&dirty_i->seglist_lock); + for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) { + se = get_seg_entry(sbi, segno); + if (IS_NODESEG(se->type)) + holes[NODE] += sbi->blocks_per_seg - se->valid_blocks; + else + holes[DATA] += sbi->blocks_per_seg - se->valid_blocks; + } + mutex_unlock(&dirty_i->seglist_lock); + + if (holes[DATA] > ovp || holes[NODE] > ovp) + return -EAGAIN; + if (is_sbi_flag_set(sbi, SBI_CP_DISABLED_QUICK) && + dirty_segments(sbi) > overprovision_segments(sbi)) + return -EAGAIN; + return 0; +} + +/* This is only used by SBI_CP_DISABLED */ +static unsigned int get_free_segment(struct f2fs_sb_info *sbi) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + unsigned int segno = 0; + + mutex_lock(&dirty_i->seglist_lock); + for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) { + if (get_valid_blocks(sbi, segno, false)) + continue; + if (get_ckpt_valid_blocks(sbi, segno)) + continue; + mutex_unlock(&dirty_i->seglist_lock); + return segno; + } + mutex_unlock(&dirty_i->seglist_lock); + return NULL_SEGNO; +} + static struct discard_cmd *__create_discard_cmd(struct f2fs_sb_info *sbi, struct block_device *bdev, block_t lstart, block_t start, block_t len) @@ -756,9 +933,12 @@ static struct discard_cmd *__create_discard_cmd(struct f2fs_sb_info *sbi, dc->len = len; dc->ref = 0; dc->state = D_PREP; + dc->queued = 0; dc->error = 0; init_completion(&dc->wait); list_add_tail(&dc->list, pend_list); + spin_lock_init(&dc->lock); + dc->bio_ref = 0; atomic_inc(&dcc->discard_cmd_cnt); dcc->undiscard_blks += len; @@ -768,7 +948,8 @@ static struct discard_cmd *__create_discard_cmd(struct f2fs_sb_info *sbi, static struct discard_cmd *__attach_discard_cmd(struct f2fs_sb_info *sbi, struct block_device *bdev, block_t lstart, block_t start, block_t len, - struct rb_node *parent, struct rb_node **p) + struct rb_node *parent, struct rb_node **p, + bool leftmost) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct discard_cmd *dc; @@ -776,7 +957,7 @@ static struct discard_cmd *__attach_discard_cmd(struct f2fs_sb_info *sbi, dc = __create_discard_cmd(sbi, bdev, lstart, start, len); rb_link_node(&dc->rb_node, parent, p); - rb_insert_color(&dc->rb_node, &dcc->root); + rb_insert_color_cached(&dc->rb_node, &dcc->root, leftmost); return dc; } @@ -785,10 +966,10 @@ static void __detach_discard_cmd(struct discard_cmd_control *dcc, struct discard_cmd *dc) { if (dc->state == D_DONE) - atomic_dec(&dcc->issing_discard); + atomic_sub(dc->queued, &dcc->queued_discard); list_del(&dc->list); - rb_erase(&dc->rb_node, &dcc->root); + rb_erase_cached(&dc->rb_node, &dcc->root); dcc->undiscard_blks -= dc->len; kmem_cache_free(discard_cmd_slab, dc); @@ -800,6 +981,16 @@ static void __remove_discard_cmd(struct f2fs_sb_info *sbi, struct discard_cmd *dc) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; + unsigned long flags; + + trace_f2fs_remove_discard(dc->bdev, dc->start, dc->len); + + spin_lock_irqsave(&dc->lock, flags); + if (dc->bio_ref) { + spin_unlock_irqrestore(&dc->lock, flags); + return; + } + spin_unlock_irqrestore(&dc->lock, flags); f2fs_bug_on(sbi, dc->ref); @@ -807,23 +998,30 @@ static void __remove_discard_cmd(struct f2fs_sb_info *sbi, dc->error = 0; if (dc->error) - f2fs_msg(sbi->sb, KERN_INFO, - "Issue discard(%u, %u, %u) failed, ret: %d", - dc->lstart, dc->start, dc->len, dc->error); + printk_ratelimited( + "%sF2FS-fs: Issue discard(%u, %u, %u) failed, ret: %d", + KERN_INFO, dc->lstart, dc->start, dc->len, dc->error); __detach_discard_cmd(dcc, dc); } static void f2fs_submit_discard_endio(struct bio *bio) { struct discard_cmd *dc = (struct discard_cmd *)bio->bi_private; + unsigned long flags; dc->error = blk_status_to_errno(bio->bi_status); - dc->state = D_DONE; - complete_all(&dc->wait); + + spin_lock_irqsave(&dc->lock, flags); + dc->bio_ref--; + if (!dc->bio_ref && dc->state == D_SUBMIT) { + dc->state = D_DONE; + complete_all(&dc->wait); + } + spin_unlock_irqrestore(&dc->lock, flags); bio_put(bio); } -void __check_sit_bitmap(struct f2fs_sb_info *sbi, +static void __check_sit_bitmap(struct f2fs_sb_info *sbi, block_t start, block_t end) { #ifdef CONFIG_F2FS_CHECK_FS @@ -850,40 +1048,155 @@ void __check_sit_bitmap(struct f2fs_sb_info *sbi, #endif } +static void __init_discard_policy(struct f2fs_sb_info *sbi, + struct discard_policy *dpolicy, + int discard_type, unsigned int granularity) +{ + /* common policy */ + dpolicy->type = discard_type; + dpolicy->sync = true; + dpolicy->ordered = false; + dpolicy->granularity = granularity; + + dpolicy->max_requests = DEF_MAX_DISCARD_REQUEST; + dpolicy->io_aware_gran = MAX_PLIST_NUM; + dpolicy->timeout = 0; + + if (discard_type == DPOLICY_BG) { + dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME; + dpolicy->mid_interval = DEF_MID_DISCARD_ISSUE_TIME; + dpolicy->max_interval = DEF_MAX_DISCARD_ISSUE_TIME; + dpolicy->io_aware = true; + dpolicy->sync = false; + dpolicy->ordered = true; + if (utilization(sbi) > DEF_DISCARD_URGENT_UTIL) { + dpolicy->granularity = 1; + dpolicy->max_interval = DEF_MIN_DISCARD_ISSUE_TIME; + } + } else if (discard_type == DPOLICY_FORCE) { + dpolicy->min_interval = DEF_MIN_DISCARD_ISSUE_TIME; + dpolicy->mid_interval = DEF_MID_DISCARD_ISSUE_TIME; + dpolicy->max_interval = DEF_MAX_DISCARD_ISSUE_TIME; + dpolicy->io_aware = false; + } else if (discard_type == DPOLICY_FSTRIM) { + dpolicy->io_aware = false; + } else if (discard_type == DPOLICY_UMOUNT) { + dpolicy->max_requests = UINT_MAX; + dpolicy->io_aware = false; + /* we need to issue all to keep CP_TRIMMED_FLAG */ + dpolicy->granularity = 1; + } +} + +static void __update_discard_tree_range(struct f2fs_sb_info *sbi, + struct block_device *bdev, block_t lstart, + block_t start, block_t len); /* this function is copied from blkdev_issue_discard from block/blk-lib.c */ -static void __submit_discard_cmd(struct f2fs_sb_info *sbi, - struct discard_cmd *dc) -{ +static int __submit_discard_cmd(struct f2fs_sb_info *sbi, + struct discard_policy *dpolicy, + struct discard_cmd *dc, + unsigned int *issued) +{ + struct block_device *bdev = dc->bdev; + struct request_queue *q = bdev_get_queue(bdev); + unsigned int max_discard_blocks = + SECTOR_TO_BLOCK(q->limits.max_discard_sectors); struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; - struct bio *bio = NULL; + struct list_head *wait_list = (dpolicy->type == DPOLICY_FSTRIM) ? + &(dcc->fstrim_list) : &(dcc->wait_list); + int flag = dpolicy->sync ? REQ_SYNC : 0; + block_t lstart, start, len, total_len; + int err = 0; if (dc->state != D_PREP) - return; + return 0; + + if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) + return 0; - trace_f2fs_issue_discard(dc->bdev, dc->start, dc->len); + trace_f2fs_issue_discard(bdev, dc->start, dc->len); - dc->error = __blkdev_issue_discard(dc->bdev, - SECTOR_FROM_BLOCK(dc->start), - SECTOR_FROM_BLOCK(dc->len), - GFP_NOFS, 0, &bio); - if (!dc->error) { - /* should keep before submission to avoid D_DONE right away */ - dc->state = D_SUBMIT; - atomic_inc(&dcc->issued_discard); - atomic_inc(&dcc->issing_discard); - if (bio) { - bio->bi_private = dc; - bio->bi_end_io = f2fs_submit_discard_endio; - bio->bi_opf |= REQ_SYNC; - submit_bio(bio); - list_move_tail(&dc->list, &dcc->wait_list); - __check_sit_bitmap(sbi, dc->start, dc->start + dc->len); + lstart = dc->lstart; + start = dc->start; + len = dc->len; + total_len = len; - f2fs_update_iostat(sbi, FS_DISCARD, 1); + dc->len = 0; + + while (total_len && *issued < dpolicy->max_requests && !err) { + struct bio *bio = NULL; + unsigned long flags; + bool last = true; + + if (len > max_discard_blocks) { + len = max_discard_blocks; + last = false; } - } else { - __remove_discard_cmd(sbi, dc); + + (*issued)++; + if (*issued == dpolicy->max_requests) + last = true; + + dc->len += len; + + if (time_to_inject(sbi, FAULT_DISCARD)) { + f2fs_show_injection_info(FAULT_DISCARD); + err = -EIO; + goto submit; + } + err = __blkdev_issue_discard(bdev, + SECTOR_FROM_BLOCK(start), + SECTOR_FROM_BLOCK(len), + GFP_NOFS, 0, &bio); +submit: + if (err) { + spin_lock_irqsave(&dc->lock, flags); + if (dc->state == D_PARTIAL) + dc->state = D_SUBMIT; + spin_unlock_irqrestore(&dc->lock, flags); + + break; + } + + f2fs_bug_on(sbi, !bio); + + /* + * should keep before submission to avoid D_DONE + * right away + */ + spin_lock_irqsave(&dc->lock, flags); + if (last) + dc->state = D_SUBMIT; + else + dc->state = D_PARTIAL; + dc->bio_ref++; + spin_unlock_irqrestore(&dc->lock, flags); + + atomic_inc(&dcc->queued_discard); + dc->queued++; + list_move_tail(&dc->list, wait_list); + + /* sanity check on discard range */ + __check_sit_bitmap(sbi, lstart, lstart + len); + + bio->bi_private = dc; + bio->bi_end_io = f2fs_submit_discard_endio; + bio->bi_opf |= flag; + submit_bio(bio); + + atomic_inc(&dcc->issued_discard); + + f2fs_update_iostat(sbi, FS_DISCARD, 1); + + lstart += len; + start += len; + total_len -= len; + len = total_len; } + + if (!err && len) + __update_discard_tree_range(sbi, bdev, lstart, start, len); + return err; } static struct discard_cmd *__insert_discard_tree(struct f2fs_sb_info *sbi, @@ -893,9 +1206,10 @@ static struct discard_cmd *__insert_discard_tree(struct f2fs_sb_info *sbi, struct rb_node *insert_parent) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; - struct rb_node **p = &dcc->root.rb_node; + struct rb_node **p; struct rb_node *parent = NULL; struct discard_cmd *dc = NULL; + bool leftmost = true; if (insert_p && insert_parent) { parent = insert_parent; @@ -903,9 +1217,11 @@ static struct discard_cmd *__insert_discard_tree(struct f2fs_sb_info *sbi, goto do_insert; } - p = __lookup_rb_tree_for_insert(sbi, &dcc->root, &parent, lstart); + p = f2fs_lookup_rb_tree_for_insert(sbi, &dcc->root, &parent, + lstart, &leftmost); do_insert: - dc = __attach_discard_cmd(sbi, bdev, lstart, start, len, parent, p); + dc = __attach_discard_cmd(sbi, bdev, lstart, start, len, parent, + p, leftmost); if (!dc) return NULL; @@ -964,15 +1280,16 @@ static void __update_discard_tree_range(struct f2fs_sb_info *sbi, struct discard_cmd *dc; struct discard_info di = {0}; struct rb_node **insert_p = NULL, *insert_parent = NULL; + struct request_queue *q = bdev_get_queue(bdev); + unsigned int max_discard_blocks = + SECTOR_TO_BLOCK(q->limits.max_discard_sectors); block_t end = lstart + len; - mutex_lock(&dcc->cmd_lock); - - dc = (struct discard_cmd *)__lookup_rb_tree_ret(&dcc->root, + dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root, NULL, lstart, (struct rb_entry **)&prev_dc, (struct rb_entry **)&next_dc, - &insert_p, &insert_parent, true); + &insert_p, &insert_parent, true, NULL); if (dc) prev_dc = dc; @@ -1007,7 +1324,8 @@ static void __update_discard_tree_range(struct f2fs_sb_info *sbi, if (prev_dc && prev_dc->state == D_PREP && prev_dc->bdev == bdev && - __is_discard_back_mergeable(&di, &prev_dc->di)) { + __is_discard_back_mergeable(&di, &prev_dc->di, + max_discard_blocks)) { prev_dc->di.len += di.len; dcc->undiscard_blks += di.len; __relocate_discard_cmd(dcc, prev_dc); @@ -1018,7 +1336,8 @@ static void __update_discard_tree_range(struct f2fs_sb_info *sbi, if (next_dc && next_dc->state == D_PREP && next_dc->bdev == bdev && - __is_discard_front_mergeable(&di, &next_dc->di)) { + __is_discard_front_mergeable(&di, &next_dc->di, + max_discard_blocks)) { next_dc->di.lstart = di.lstart; next_dc->di.len += di.len; next_dc->di.start = di.start; @@ -1041,8 +1360,6 @@ static void __update_discard_tree_range(struct f2fs_sb_info *sbi, node = rb_next(&prev_dc->rb_node); next_dc = rb_entry_safe(node, struct discard_cmd, rb_node); } - - mutex_unlock(&dcc->cmd_lock); } static int __queue_discard_cmd(struct f2fs_sb_info *sbi, @@ -1057,62 +1374,126 @@ static int __queue_discard_cmd(struct f2fs_sb_info *sbi, blkstart -= FDEV(devi).start_blk; } + mutex_lock(&SM_I(sbi)->dcc_info->cmd_lock); __update_discard_tree_range(sbi, bdev, lblkstart, blkstart, blklen); + mutex_unlock(&SM_I(sbi)->dcc_info->cmd_lock); return 0; } -static int __issue_discard_cmd(struct f2fs_sb_info *sbi, bool issue_cond) +static unsigned int __issue_discard_cmd_orderly(struct f2fs_sb_info *sbi, + struct discard_policy *dpolicy) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; - struct list_head *pend_list; - struct discard_cmd *dc, *tmp; + struct discard_cmd *prev_dc = NULL, *next_dc = NULL; + struct rb_node **insert_p = NULL, *insert_parent = NULL; + struct discard_cmd *dc; struct blk_plug plug; - int iter = 0, issued = 0; - int i; + unsigned int pos = dcc->next_pos; + unsigned int issued = 0; bool io_interrupted = false; mutex_lock(&dcc->cmd_lock); - f2fs_bug_on(sbi, - !__check_rb_tree_consistence(sbi, &dcc->root)); + dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root, + NULL, pos, + (struct rb_entry **)&prev_dc, + (struct rb_entry **)&next_dc, + &insert_p, &insert_parent, true, NULL); + if (!dc) + dc = next_dc; + blk_start_plug(&plug); - for (i = MAX_PLIST_NUM - 1; - i >= 0 && plist_issue(dcc->pend_list_tag[i]); i--) { - pend_list = &dcc->pend_list[i]; - list_for_each_entry_safe(dc, tmp, pend_list, list) { - f2fs_bug_on(sbi, dc->state != D_PREP); - /* Hurry up to finish fstrim */ - if (dcc->pend_list_tag[i] & P_TRIM) { - __submit_discard_cmd(sbi, dc); - issued++; + while (dc) { + struct rb_node *node; + int err = 0; - if (fatal_signal_pending(current)) - break; - continue; - } + if (dc->state != D_PREP) + goto next; - if (!issue_cond) { - __submit_discard_cmd(sbi, dc); - issued++; - continue; - } + if (dpolicy->io_aware && !is_idle(sbi, DISCARD_TIME)) { + io_interrupted = true; + break; + } - if (is_idle(sbi)) { - __submit_discard_cmd(sbi, dc); - issued++; - } else { + dcc->next_pos = dc->lstart + dc->len; + err = __submit_discard_cmd(sbi, dpolicy, dc, &issued); + + if (issued >= dpolicy->max_requests) + break; +next: + node = rb_next(&dc->rb_node); + if (err) + __remove_discard_cmd(sbi, dc); + dc = rb_entry_safe(node, struct discard_cmd, rb_node); + } + + blk_finish_plug(&plug); + + if (!dc) + dcc->next_pos = 0; + + mutex_unlock(&dcc->cmd_lock); + + if (!issued && io_interrupted) + issued = -1; + + return issued; +} + +static int __issue_discard_cmd(struct f2fs_sb_info *sbi, + struct discard_policy *dpolicy) +{ + struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; + struct list_head *pend_list; + struct discard_cmd *dc, *tmp; + struct blk_plug plug; + int i, issued = 0; + bool io_interrupted = false; + + if (dpolicy->timeout != 0) + f2fs_update_time(sbi, dpolicy->timeout); + + for (i = MAX_PLIST_NUM - 1; i >= 0; i--) { + if (dpolicy->timeout != 0 && + f2fs_time_over(sbi, dpolicy->timeout)) + break; + + if (i + 1 < dpolicy->granularity) + break; + + if (i < DEFAULT_DISCARD_GRANULARITY && dpolicy->ordered) + return __issue_discard_cmd_orderly(sbi, dpolicy); + + pend_list = &dcc->pend_list[i]; + + mutex_lock(&dcc->cmd_lock); + if (list_empty(pend_list)) + goto next; + if (unlikely(dcc->rbtree_check)) + f2fs_bug_on(sbi, !f2fs_check_rb_tree_consistence(sbi, + &dcc->root)); + blk_start_plug(&plug); + list_for_each_entry_safe(dc, tmp, pend_list, list) { + f2fs_bug_on(sbi, dc->state != D_PREP); + + if (dpolicy->io_aware && i < dpolicy->io_aware_gran && + !is_idle(sbi, DISCARD_TIME)) { io_interrupted = true; + break; } - if (++iter >= DISCARD_ISSUE_RATE) - goto out; + __submit_discard_cmd(sbi, dpolicy, dc, &issued); + + if (issued >= dpolicy->max_requests) + break; } - if (list_empty(pend_list) && dcc->pend_list_tag[i] & P_TRIM) - dcc->pend_list_tag[i] &= (~P_TRIM); + blk_finish_plug(&plug); +next: + mutex_unlock(&dcc->cmd_lock); + + if (issued >= dpolicy->max_requests || io_interrupted) + break; } -out: - blk_finish_plug(&plug); - mutex_unlock(&dcc->cmd_lock); if (!issued && io_interrupted) issued = -1; @@ -1120,12 +1501,13 @@ out: return issued; } -static void __drop_discard_cmd(struct f2fs_sb_info *sbi) +static bool __drop_discard_cmd(struct f2fs_sb_info *sbi) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct list_head *pend_list; struct discard_cmd *dc, *tmp; int i; + bool dropped = false; mutex_lock(&dcc->cmd_lock); for (i = MAX_PLIST_NUM - 1; i >= 0; i--) { @@ -1133,39 +1515,63 @@ static void __drop_discard_cmd(struct f2fs_sb_info *sbi) list_for_each_entry_safe(dc, tmp, pend_list, list) { f2fs_bug_on(sbi, dc->state != D_PREP); __remove_discard_cmd(sbi, dc); + dropped = true; } } mutex_unlock(&dcc->cmd_lock); + + return dropped; +} + +void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi) +{ + __drop_discard_cmd(sbi); } -static void __wait_one_discard_bio(struct f2fs_sb_info *sbi, +static unsigned int __wait_one_discard_bio(struct f2fs_sb_info *sbi, struct discard_cmd *dc) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; + unsigned int len = 0; wait_for_completion_io(&dc->wait); mutex_lock(&dcc->cmd_lock); f2fs_bug_on(sbi, dc->state != D_DONE); dc->ref--; - if (!dc->ref) + if (!dc->ref) { + if (!dc->error) + len = dc->len; __remove_discard_cmd(sbi, dc); + } mutex_unlock(&dcc->cmd_lock); + + return len; } -static void __wait_discard_cmd(struct f2fs_sb_info *sbi, bool wait_cond) +static unsigned int __wait_discard_cmd_range(struct f2fs_sb_info *sbi, + struct discard_policy *dpolicy, + block_t start, block_t end) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; - struct list_head *wait_list = &(dcc->wait_list); + struct list_head *wait_list = (dpolicy->type == DPOLICY_FSTRIM) ? + &(dcc->fstrim_list) : &(dcc->wait_list); struct discard_cmd *dc, *tmp; bool need_wait; + unsigned int trimmed = 0; next: need_wait = false; mutex_lock(&dcc->cmd_lock); list_for_each_entry_safe(dc, tmp, wait_list, list) { - if (!wait_cond || (dc->state == D_DONE && !dc->ref)) { + if (dc->lstart + dc->len <= start || end <= dc->lstart) + continue; + if (dc->len < dpolicy->granularity) + continue; + if (dc->state == D_DONE && !dc->ref) { wait_for_completion_io(&dc->wait); + if (!dc->error) + trimmed += dc->len; __remove_discard_cmd(sbi, dc); } else { dc->ref++; @@ -1176,20 +1582,41 @@ next: mutex_unlock(&dcc->cmd_lock); if (need_wait) { - __wait_one_discard_bio(sbi, dc); + trimmed += __wait_one_discard_bio(sbi, dc); goto next; } + + return trimmed; +} + +static unsigned int __wait_all_discard_cmd(struct f2fs_sb_info *sbi, + struct discard_policy *dpolicy) +{ + struct discard_policy dp; + unsigned int discard_blks; + + if (dpolicy) + return __wait_discard_cmd_range(sbi, dpolicy, 0, UINT_MAX); + + /* wait all */ + __init_discard_policy(sbi, &dp, DPOLICY_FSTRIM, 1); + discard_blks = __wait_discard_cmd_range(sbi, &dp, 0, UINT_MAX); + __init_discard_policy(sbi, &dp, DPOLICY_UMOUNT, 1); + discard_blks += __wait_discard_cmd_range(sbi, &dp, 0, UINT_MAX); + + return discard_blks; } /* This should be covered by global mutex, &sit_i->sentry_lock */ -void f2fs_wait_discard_bio(struct f2fs_sb_info *sbi, block_t blkaddr) +static void f2fs_wait_discard_bio(struct f2fs_sb_info *sbi, block_t blkaddr) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct discard_cmd *dc; bool need_wait = false; mutex_lock(&dcc->cmd_lock); - dc = (struct discard_cmd *)__lookup_rb_tree(&dcc->root, NULL, blkaddr); + dc = (struct discard_cmd *)f2fs_lookup_rb_tree(&dcc->root, + NULL, blkaddr); if (dc) { if (dc->state == D_PREP) { __punch_discard_cmd(sbi, dc, blkaddr); @@ -1204,7 +1631,7 @@ void f2fs_wait_discard_bio(struct f2fs_sb_info *sbi, block_t blkaddr) __wait_one_discard_bio(sbi, dc); } -void stop_discard_thread(struct f2fs_sb_info *sbi) +void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; @@ -1216,23 +1643,24 @@ void stop_discard_thread(struct f2fs_sb_info *sbi) } } -/* This comes from f2fs_put_super and f2fs_trim_fs */ -void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi, bool umount) -{ - __issue_discard_cmd(sbi, false); - __drop_discard_cmd(sbi); - __wait_discard_cmd(sbi, !umount); -} - -static void mark_discard_range_all(struct f2fs_sb_info *sbi) +/* This comes from f2fs_put_super */ +bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; - int i; + struct discard_policy dpolicy; + bool dropped; - mutex_lock(&dcc->cmd_lock); - for (i = 0; i < MAX_PLIST_NUM; i++) - dcc->pend_list_tag[i] |= P_TRIM; - mutex_unlock(&dcc->cmd_lock); + __init_discard_policy(sbi, &dpolicy, DPOLICY_UMOUNT, + dcc->discard_granularity); + dpolicy.timeout = UMOUNT_DISCARD_TIMEOUT; + __issue_discard_cmd(sbi, &dpolicy); + dropped = __drop_discard_cmd(sbi); + + /* just to make sure there is no pending discard commands */ + __wait_all_discard_cmd(sbi, NULL); + + f2fs_bug_on(sbi, atomic_read(&dcc->discard_cmd_cnt)); + return dropped; } static int issue_discard_thread(void *data) @@ -1240,35 +1668,54 @@ static int issue_discard_thread(void *data) struct f2fs_sb_info *sbi = data; struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; wait_queue_head_t *q = &dcc->discard_wait_queue; + struct discard_policy dpolicy; unsigned int wait_ms = DEF_MIN_DISCARD_ISSUE_TIME; int issued; set_freezable(); do { + __init_discard_policy(sbi, &dpolicy, DPOLICY_BG, + dcc->discard_granularity); + wait_event_interruptible_timeout(*q, kthread_should_stop() || freezing(current) || dcc->discard_wake, msecs_to_jiffies(wait_ms)); + + if (dcc->discard_wake) + dcc->discard_wake = 0; + + /* clean up pending candidates before going to sleep */ + if (atomic_read(&dcc->queued_discard)) + __wait_all_discard_cmd(sbi, NULL); + if (try_to_freeze()) continue; + if (f2fs_readonly(sbi->sb)) + continue; if (kthread_should_stop()) return 0; - - if (dcc->discard_wake) { - dcc->discard_wake = 0; - if (sbi->gc_thread && sbi->gc_thread->gc_urgent) - mark_discard_range_all(sbi); + if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) { + wait_ms = dpolicy.max_interval; + continue; } + if (sbi->gc_mode == GC_URGENT) + __init_discard_policy(sbi, &dpolicy, DPOLICY_FORCE, 1); + sb_start_intwrite(sbi->sb); - issued = __issue_discard_cmd(sbi, true); - if (issued) { - __wait_discard_cmd(sbi, true); - wait_ms = DEF_MIN_DISCARD_ISSUE_TIME; + issued = __issue_discard_cmd(sbi, &dpolicy); + if (issued > 0) { + __wait_all_discard_cmd(sbi, &dpolicy); + wait_ms = dpolicy.min_interval; + } else if (issued == -1){ + wait_ms = f2fs_time_to_wait(sbi, DISCARD_TIME); + if (!wait_ms) + wait_ms = dpolicy.mid_interval; } else { - wait_ms = DEF_MAX_DISCARD_ISSUE_TIME; + wait_ms = dpolicy.max_interval; } sb_end_intwrite(sbi->sb); @@ -1328,7 +1775,7 @@ static int __issue_discard_async(struct f2fs_sb_info *sbi, struct block_device *bdev, block_t blkstart, block_t blklen) { #ifdef CONFIG_BLK_DEV_ZONED - if (f2fs_sb_mounted_blkzoned(sbi->sb) && + if (f2fs_sb_has_blkzoned(sbi) && bdev_zoned_model(bdev) != BLK_ZONED_NONE) return __f2fs_issue_discard_zone(sbi, bdev, blkstart, blklen); #endif @@ -1391,11 +1838,11 @@ static bool add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc, struct list_head *head = &SM_I(sbi)->dcc_info->entry_list; int i; - if (se->valid_blocks == max_blocks || !f2fs_discard_en(sbi)) + if (se->valid_blocks == max_blocks || !f2fs_hw_support_discard(sbi)) return false; if (!force) { - if (!test_opt(sbi, DISCARD) || !se->valid_blocks || + if (!f2fs_realtime_discard_enable(sbi) || !se->valid_blocks || SM_I(sbi)->dcc_info->nr_discards >= SM_I(sbi)->dcc_info->max_discards) return false; @@ -1435,20 +1882,24 @@ static bool add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc, return false; } -void release_discard_addrs(struct f2fs_sb_info *sbi) +static void release_discard_addr(struct discard_entry *entry) +{ + list_del(&entry->list); + kmem_cache_free(discard_entry_slab, entry); +} + +void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi) { struct list_head *head = &(SM_I(sbi)->dcc_info->entry_list); struct discard_entry *entry, *this; /* drop caches */ - list_for_each_entry_safe(entry, this, head, list) { - list_del(&entry->list); - kmem_cache_free(discard_entry_slab, entry); - } + list_for_each_entry_safe(entry, this, head, list) + release_discard_addr(entry); } /* - * Should call clear_prefree_segments after checkpoint is done. + * Should call f2fs_clear_prefree_segments after checkpoint is done. */ static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi) { @@ -1461,7 +1912,8 @@ static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi) mutex_unlock(&dirty_i->seglist_lock); } -void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc) +void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi, + struct cp_control *cpc) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct list_head *head = &dcc->entry_list; @@ -1471,30 +1923,39 @@ void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc) unsigned int start = 0, end = -1; unsigned int secno, start_segno; bool force = (cpc->reason & CP_DISCARD); + bool need_align = test_opt(sbi, LFS) && __is_large_section(sbi); mutex_lock(&dirty_i->seglist_lock); while (1) { int i; + + if (need_align && end != -1) + end--; start = find_next_bit(prefree_map, MAIN_SEGS(sbi), end + 1); if (start >= MAIN_SEGS(sbi)) break; end = find_next_zero_bit(prefree_map, MAIN_SEGS(sbi), start + 1); - for (i = start; i < end; i++) - clear_bit(i, prefree_map); + if (need_align) { + start = rounddown(start, sbi->segs_per_sec); + end = roundup(end, sbi->segs_per_sec); + } - dirty_i->nr_dirty[PRE] -= end - start; + for (i = start; i < end; i++) { + if (test_and_clear_bit(i, prefree_map)) + dirty_i->nr_dirty[PRE]--; + } - if (!test_opt(sbi, DISCARD)) + if (!f2fs_realtime_discard_enable(sbi)) continue; if (force && start >= cpc->trim_start && (end - 1) <= cpc->trim_end) continue; - if (!test_opt(sbi, LFS) || sbi->segs_per_sec == 1) { + if (!test_opt(sbi, LFS) || !__is_large_section(sbi)) { f2fs_issue_discard(sbi, START_BLOCK(sbi, start), (end - start) << sbi->log_blocks_per_seg); continue; @@ -1526,13 +1987,12 @@ find_next: sbi->blocks_per_seg, cur_pos); len = next_pos - cur_pos; - if (f2fs_sb_mounted_blkzoned(sbi->sb) || + if (f2fs_sb_has_blkzoned(sbi) || (force && len < cpc->trim_minlen)) goto skip; f2fs_issue_discard(sbi, entry->start_blkaddr + cur_pos, len); - cpc->trimmed += len; total_len += len; } else { next_pos = find_next_bit_le(entry->discard_map, @@ -1545,9 +2005,8 @@ skip: if (cur_pos < sbi->blocks_per_seg) goto find_next; - list_del(&entry->list); + release_discard_addr(entry); dcc->nr_discards -= total_len; - kmem_cache_free(discard_entry_slab, entry); } wake_up_discard_thread(sbi, false); @@ -1564,26 +2023,26 @@ static int create_discard_cmd_control(struct f2fs_sb_info *sbi) goto init_thread; } - dcc = kzalloc(sizeof(struct discard_cmd_control), GFP_KERNEL); + dcc = f2fs_kzalloc(sbi, sizeof(struct discard_cmd_control), GFP_KERNEL); if (!dcc) return -ENOMEM; dcc->discard_granularity = DEFAULT_DISCARD_GRANULARITY; INIT_LIST_HEAD(&dcc->entry_list); - for (i = 0; i < MAX_PLIST_NUM; i++) { + for (i = 0; i < MAX_PLIST_NUM; i++) INIT_LIST_HEAD(&dcc->pend_list[i]); - if (i >= dcc->discard_granularity - 1) - dcc->pend_list_tag[i] |= P_ACTIVE; - } INIT_LIST_HEAD(&dcc->wait_list); + INIT_LIST_HEAD(&dcc->fstrim_list); mutex_init(&dcc->cmd_lock); atomic_set(&dcc->issued_discard, 0); - atomic_set(&dcc->issing_discard, 0); + atomic_set(&dcc->queued_discard, 0); atomic_set(&dcc->discard_cmd_cnt, 0); dcc->nr_discards = 0; dcc->max_discards = MAIN_SEGS(sbi) << sbi->log_blocks_per_seg; dcc->undiscard_blks = 0; - dcc->root = RB_ROOT; + dcc->next_pos = 0; + dcc->root = RB_ROOT_CACHED; + dcc->rbtree_check = false; init_waitqueue_head(&dcc->discard_wait_queue); SM_I(sbi)->dcc_info = dcc; @@ -1592,7 +2051,7 @@ init_thread: "f2fs_discard-%u:%u", MAJOR(dev), MINOR(dev)); if (IS_ERR(dcc->f2fs_issue_discard)) { err = PTR_ERR(dcc->f2fs_issue_discard); - kfree(dcc); + kvfree(dcc); SM_I(sbi)->dcc_info = NULL; return err; } @@ -1607,9 +2066,9 @@ static void destroy_discard_cmd_control(struct f2fs_sb_info *sbi) if (!dcc) return; - stop_discard_thread(sbi); + f2fs_stop_discard_thread(sbi); - kfree(dcc); + kvfree(dcc); SM_I(sbi)->dcc_info = NULL; } @@ -1654,8 +2113,9 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) (new_vblocks > sbi->blocks_per_seg))); se->valid_blocks = new_vblocks; - se->mtime = get_mtime(sbi); - SIT_I(sbi)->max_mtime = se->mtime; + se->mtime = get_mtime(sbi, false); + if (se->mtime > SIT_I(sbi)->max_mtime) + SIT_I(sbi)->max_mtime = se->mtime; /* Update valid block bitmap */ if (del > 0) { @@ -1678,12 +2138,12 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) del = 0; } - if (f2fs_discard_en(sbi) && - !f2fs_test_and_set_bit(offset, se->discard_map)) + if (!f2fs_test_and_set_bit(offset, se->discard_map)) sbi->discard_blks--; /* don't overwrite by SSR to keep node chain */ - if (se->type == CURSEG_WARM_NODE) { + if (IS_NODESEG(se->type) && + !is_sbi_flag_set(sbi, SBI_CP_DISABLED)) { if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map)) se->ckpt_valid_blocks++; } @@ -1705,10 +2165,18 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) f2fs_bug_on(sbi, 1); se->valid_blocks++; del = 0; + } else if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + /* + * If checkpoints are off, we must not reuse data that + * was used in the previous checkpoint. If it was used + * before, we must track that to know how much space we + * really have. + */ + if (f2fs_test_bit(offset, se->ckpt_valid_map)) + sbi->unusable_block_count++; } - if (f2fs_discard_en(sbi) && - f2fs_test_and_clear_bit(offset, se->discard_map)) + if (f2fs_test_and_clear_bit(offset, se->discard_map)) sbi->discard_blks++; } if (!f2fs_test_bit(offset, se->ckpt_valid_map)) @@ -1719,21 +2187,11 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) /* update total number of valid blocks to be written in ckpt area */ SIT_I(sbi)->written_valid_blocks += del; - if (sbi->segs_per_sec > 1) + if (__is_large_section(sbi)) get_sec_entry(sbi, segno)->valid_blocks += del; } -void refresh_sit_entry(struct f2fs_sb_info *sbi, block_t old, block_t new) -{ - update_sit_entry(sbi, new, 1); - if (GET_SEGNO(sbi, old) != NULL_SEGNO) - update_sit_entry(sbi, old, -1); - - locate_dirty_segment(sbi, GET_SEGNO(sbi, old)); - locate_dirty_segment(sbi, GET_SEGNO(sbi, new)); -} - -void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr) +void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr) { unsigned int segno = GET_SEGNO(sbi, addr); struct sit_info *sit_i = SIT_I(sbi); @@ -1742,18 +2200,20 @@ void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr) if (addr == NEW_ADDR) return; + invalidate_mapping_pages(META_MAPPING(sbi), addr, addr); + /* add it into sit main buffer */ - mutex_lock(&sit_i->sentry_lock); + down_write(&sit_i->sentry_lock); update_sit_entry(sbi, addr, -1); /* add it into dirty seglist */ locate_dirty_segment(sbi, segno); - mutex_unlock(&sit_i->sentry_lock); + up_write(&sit_i->sentry_lock); } -bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr) +bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr) { struct sit_info *sit_i = SIT_I(sbi); unsigned int segno, offset; @@ -1763,7 +2223,7 @@ bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr) if (!is_valid_data_blkaddr(sbi, blkaddr)) return true; - mutex_lock(&sit_i->sentry_lock); + down_read(&sit_i->sentry_lock); segno = GET_SEGNO(sbi, blkaddr); se = get_seg_entry(sbi, segno); @@ -1772,7 +2232,7 @@ bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr) if (f2fs_test_bit(offset, se->ckpt_valid_map)) is_cp = true; - mutex_unlock(&sit_i->sentry_lock); + up_read(&sit_i->sentry_lock); return is_cp; } @@ -1792,7 +2252,7 @@ static void __add_sum_entry(struct f2fs_sb_info *sbi, int type, /* * Calculate the number of current summary pages for writing */ -int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra) +int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra) { int valid_sum_count = 0; int i, sum_in_page; @@ -1822,20 +2282,17 @@ int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra) /* * Caller should put this summary page */ -struct page *get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno) +struct page *f2fs_get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno) { - return get_meta_page(sbi, GET_SUM_BLOCK(sbi, segno)); + return f2fs_get_meta_page_nofail(sbi, GET_SUM_BLOCK(sbi, segno)); } -void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr) +void f2fs_update_meta_page(struct f2fs_sb_info *sbi, + void *src, block_t blk_addr) { - struct page *page = grab_meta_page(sbi, blk_addr); - void *dst = page_address(page); + struct page *page = f2fs_grab_meta_page(sbi, blk_addr); - if (src) - memcpy(dst, src, PAGE_SIZE); - else - memset(dst, 0, PAGE_SIZE); + memcpy(page_address(page), src, PAGE_SIZE); set_page_dirty(page); f2fs_put_page(page, 1); } @@ -1843,18 +2300,19 @@ void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr) static void write_sum_page(struct f2fs_sb_info *sbi, struct f2fs_summary_block *sum_blk, block_t blk_addr) { - update_meta_page(sbi, (void *)sum_blk, blk_addr); + f2fs_update_meta_page(sbi, (void *)sum_blk, blk_addr); } static void write_current_sum_page(struct f2fs_sb_info *sbi, int type, block_t blk_addr) { struct curseg_info *curseg = CURSEG_I(sbi, type); - struct page *page = grab_meta_page(sbi, blk_addr); + struct page *page = f2fs_grab_meta_page(sbi, blk_addr); struct f2fs_summary_block *src = curseg->sum_blk; struct f2fs_summary_block *dst; dst = (struct f2fs_summary_block *)page_address(page); + memset(dst, 0, PAGE_SIZE); mutex_lock(&curseg->curseg_mutex); @@ -1934,7 +2392,6 @@ find_other_zone: } secno = left_start; skip_left: - hint = secno; segno = GET_SEG_FROM_SEC(sbi, secno); zoneno = GET_ZONE_FROM_SEC(sbi, secno); @@ -1996,15 +2453,23 @@ static void reset_curseg(struct f2fs_sb_info *sbi, int type, int modified) static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type) { /* if segs_per_sec is large than 1, we need to keep original policy. */ - if (sbi->segs_per_sec != 1) + if (__is_large_section(sbi)) return CURSEG_I(sbi, type)->segno; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + return 0; + if (test_opt(sbi, NOHEAP) && (type == CURSEG_HOT_DATA || IS_NODESEG(type))) return 0; if (SIT_I(sbi)->last_victim[ALLOC_NEXT]) return SIT_I(sbi)->last_victim[ALLOC_NEXT]; + + /* find segments from 0 to reuse freed segments */ + if (F2FS_OPTION(sbi).alloc_mode == ALLOC_MODE_REUSE) + return 0; + return CURSEG_I(sbi, type)->segno; } @@ -2090,7 +2555,8 @@ static void change_curseg(struct f2fs_sb_info *sbi, int type) curseg->alloc_type = SSR; __next_free_blkoff(sbi, curseg, 0); - sum_page = get_sum_page(sbi, new_segno); + sum_page = f2fs_get_sum_page(sbi, new_segno); + f2fs_bug_on(sbi, IS_ERR(sum_page)); sum_node = (struct f2fs_summary_block *)page_address(sum_page); memcpy(curseg->sum_blk, sum_node, SUM_ENTRY_SIZE); f2fs_put_page(sum_page, 1); @@ -2104,7 +2570,7 @@ static int get_ssr_segment(struct f2fs_sb_info *sbi, int type) int i, cnt; bool reversed = false; - /* need_SSR() already forces to do this */ + /* f2fs_need_SSR() already forces to do this */ if (v_ops->get_victim(sbi, &segno, BG_GC, type, SSR)) { curseg->next_segno = segno; return 1; @@ -2137,6 +2603,15 @@ static int get_ssr_segment(struct f2fs_sb_info *sbi, int type) return 1; } } + + /* find valid_blocks=0 in dirty list */ + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + segno = get_free_segment(sbi); + if (segno != NULL_SEGNO) { + curseg->next_segno = segno; + return 1; + } + } return 0; } @@ -2154,9 +2629,10 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi, else if (!is_set_ckpt_flags(sbi, CP_CRC_RECOVERY_FLAG) && type == CURSEG_WARM_NODE) new_curseg(sbi, type, false); - else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type)) + else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type) && + likely(!is_sbi_flag_set(sbi, SBI_CP_DISABLED))) new_curseg(sbi, type, false); - else if (need_SSR(sbi) && get_ssr_segment(sbi, type)) + else if (f2fs_need_SSR(sbi) && get_ssr_segment(sbi, type)) change_curseg(sbi, type); else new_curseg(sbi, type, false); @@ -2164,98 +2640,187 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi, stat_inc_seg_type(sbi, curseg); } -void allocate_new_segments(struct f2fs_sb_info *sbi) +void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi) { struct curseg_info *curseg; unsigned int old_segno; int i; + down_write(&SIT_I(sbi)->sentry_lock); + for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) { curseg = CURSEG_I(sbi, i); old_segno = curseg->segno; SIT_I(sbi)->s_ops->allocate_segment(sbi, i, true); locate_dirty_segment(sbi, old_segno); } + + up_write(&SIT_I(sbi)->sentry_lock); } static const struct segment_allocation default_salloc_ops = { .allocate_segment = allocate_segment_by_default, }; -bool exist_trim_candidates(struct f2fs_sb_info *sbi, struct cp_control *cpc) +bool f2fs_exist_trim_candidates(struct f2fs_sb_info *sbi, + struct cp_control *cpc) { __u64 trim_start = cpc->trim_start; bool has_candidate = false; - mutex_lock(&SIT_I(sbi)->sentry_lock); + down_write(&SIT_I(sbi)->sentry_lock); for (; cpc->trim_start <= cpc->trim_end; cpc->trim_start++) { if (add_discard_addrs(sbi, cpc, true)) { has_candidate = true; break; } } - mutex_unlock(&SIT_I(sbi)->sentry_lock); + up_write(&SIT_I(sbi)->sentry_lock); cpc->trim_start = trim_start; return has_candidate; } +static unsigned int __issue_discard_cmd_range(struct f2fs_sb_info *sbi, + struct discard_policy *dpolicy, + unsigned int start, unsigned int end) +{ + struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; + struct discard_cmd *prev_dc = NULL, *next_dc = NULL; + struct rb_node **insert_p = NULL, *insert_parent = NULL; + struct discard_cmd *dc; + struct blk_plug plug; + int issued; + unsigned int trimmed = 0; + +next: + issued = 0; + + mutex_lock(&dcc->cmd_lock); + if (unlikely(dcc->rbtree_check)) + f2fs_bug_on(sbi, !f2fs_check_rb_tree_consistence(sbi, + &dcc->root)); + + dc = (struct discard_cmd *)f2fs_lookup_rb_tree_ret(&dcc->root, + NULL, start, + (struct rb_entry **)&prev_dc, + (struct rb_entry **)&next_dc, + &insert_p, &insert_parent, true, NULL); + if (!dc) + dc = next_dc; + + blk_start_plug(&plug); + + while (dc && dc->lstart <= end) { + struct rb_node *node; + int err = 0; + + if (dc->len < dpolicy->granularity) + goto skip; + + if (dc->state != D_PREP) { + list_move_tail(&dc->list, &dcc->fstrim_list); + goto skip; + } + + err = __submit_discard_cmd(sbi, dpolicy, dc, &issued); + + if (issued >= dpolicy->max_requests) { + start = dc->lstart + dc->len; + + if (err) + __remove_discard_cmd(sbi, dc); + + blk_finish_plug(&plug); + mutex_unlock(&dcc->cmd_lock); + trimmed += __wait_all_discard_cmd(sbi, NULL); + congestion_wait(BLK_RW_ASYNC, HZ/50); + goto next; + } +skip: + node = rb_next(&dc->rb_node); + if (err) + __remove_discard_cmd(sbi, dc); + dc = rb_entry_safe(node, struct discard_cmd, rb_node); + + if (fatal_signal_pending(current)) + break; + } + + blk_finish_plug(&plug); + mutex_unlock(&dcc->cmd_lock); + + return trimmed; +} + int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range) { __u64 start = F2FS_BYTES_TO_BLK(range->start); __u64 end = start + F2FS_BYTES_TO_BLK(range->len) - 1; unsigned int start_segno, end_segno; + block_t start_block, end_block; struct cp_control cpc; + struct discard_policy dpolicy; + unsigned long long trimmed = 0; int err = 0; + bool need_align = test_opt(sbi, LFS) && __is_large_section(sbi); if (start >= MAX_BLKADDR(sbi) || range->len < sbi->blocksize) return -EINVAL; - cpc.trimmed = 0; - if (end <= MAIN_BLKADDR(sbi)) + if (end < MAIN_BLKADDR(sbi)) goto out; if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) { f2fs_msg(sbi->sb, KERN_WARNING, "Found FS corruption, run fsck to fix."); - err = -EFSCORRUPTED; - goto out; + return -EFSCORRUPTED; } /* start/end segment number in main_area */ start_segno = (start <= MAIN_BLKADDR(sbi)) ? 0 : GET_SEGNO(sbi, start); end_segno = (end >= MAX_BLKADDR(sbi)) ? MAIN_SEGS(sbi) - 1 : GET_SEGNO(sbi, end); + if (need_align) { + start_segno = rounddown(start_segno, sbi->segs_per_sec); + end_segno = roundup(end_segno + 1, sbi->segs_per_sec) - 1; + } + cpc.reason = CP_DISCARD; cpc.trim_minlen = max_t(__u64, 1, F2FS_BYTES_TO_BLK(range->minlen)); + cpc.trim_start = start_segno; + cpc.trim_end = end_segno; - /* do checkpoint to issue discard commands safely */ - for (; start_segno <= end_segno; start_segno = cpc.trim_end + 1) { - cpc.trim_start = start_segno; + if (sbi->discard_blks == 0) + goto out; - if (sbi->discard_blks == 0) - break; - else if (sbi->discard_blks < BATCHED_TRIM_BLOCKS(sbi)) - cpc.trim_end = end_segno; - else - cpc.trim_end = min_t(unsigned int, - rounddown(start_segno + - BATCHED_TRIM_SEGMENTS(sbi), - sbi->segs_per_sec) - 1, end_segno); + mutex_lock(&sbi->gc_mutex); + err = f2fs_write_checkpoint(sbi, &cpc); + mutex_unlock(&sbi->gc_mutex); + if (err) + goto out; - mutex_lock(&sbi->gc_mutex); - err = write_checkpoint(sbi, &cpc); - mutex_unlock(&sbi->gc_mutex); - if (err) - break; + /* + * We filed discard candidates, but actually we don't need to wait for + * all of them, since they'll be issued in idle time along with runtime + * discard option. User configuration looks like using runtime discard + * or periodic fstrim instead of it. + */ + if (f2fs_realtime_discard_enable(sbi)) + goto out; - schedule(); - } - /* It's time to issue all the filed discards */ - mark_discard_range_all(sbi); - f2fs_wait_discard_bios(sbi, false); + start_block = START_BLOCK(sbi, start_segno); + end_block = START_BLOCK(sbi, end_segno + 1); + + __init_discard_policy(sbi, &dpolicy, DPOLICY_FSTRIM, cpc.trim_minlen); + trimmed = __issue_discard_cmd_range(sbi, &dpolicy, + start_block, end_block); + + trimmed += __wait_discard_cmd_range(sbi, &dpolicy, + start_block, end_block); out: - range->len = F2FS_BLK_TO_BYTES(cpc.trimmed); + if (!err) + range->len = F2FS_BLK_TO_BYTES(trimmed); return err; } @@ -2267,6 +2832,113 @@ static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type) return false; } +int f2fs_rw_hint_to_seg_type(enum rw_hint hint) +{ + switch (hint) { + case WRITE_LIFE_SHORT: + return CURSEG_HOT_DATA; + case WRITE_LIFE_EXTREME: + return CURSEG_COLD_DATA; + default: + return CURSEG_WARM_DATA; + } +} + +/* This returns write hints for each segment type. This hints will be + * passed down to block layer. There are mapping tables which depend on + * the mount option 'whint_mode'. + * + * 1) whint_mode=off. F2FS only passes down WRITE_LIFE_NOT_SET. + * + * 2) whint_mode=user-based. F2FS tries to pass down hints given by users. + * + * User F2FS Block + * ---- ---- ----- + * META WRITE_LIFE_NOT_SET + * HOT_NODE " + * WARM_NODE " + * COLD_NODE " + * ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME + * extension list " " + * + * -- buffered io + * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME + * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT + * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET + * WRITE_LIFE_NONE " " + * WRITE_LIFE_MEDIUM " " + * WRITE_LIFE_LONG " " + * + * -- direct io + * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME + * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT + * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET + * WRITE_LIFE_NONE " WRITE_LIFE_NONE + * WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM + * WRITE_LIFE_LONG " WRITE_LIFE_LONG + * + * 3) whint_mode=fs-based. F2FS passes down hints with its policy. + * + * User F2FS Block + * ---- ---- ----- + * META WRITE_LIFE_MEDIUM; + * HOT_NODE WRITE_LIFE_NOT_SET + * WARM_NODE " + * COLD_NODE WRITE_LIFE_NONE + * ioctl(COLD) COLD_DATA WRITE_LIFE_EXTREME + * extension list " " + * + * -- buffered io + * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME + * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT + * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_LONG + * WRITE_LIFE_NONE " " + * WRITE_LIFE_MEDIUM " " + * WRITE_LIFE_LONG " " + * + * -- direct io + * WRITE_LIFE_EXTREME COLD_DATA WRITE_LIFE_EXTREME + * WRITE_LIFE_SHORT HOT_DATA WRITE_LIFE_SHORT + * WRITE_LIFE_NOT_SET WARM_DATA WRITE_LIFE_NOT_SET + * WRITE_LIFE_NONE " WRITE_LIFE_NONE + * WRITE_LIFE_MEDIUM " WRITE_LIFE_MEDIUM + * WRITE_LIFE_LONG " WRITE_LIFE_LONG + */ + +enum rw_hint f2fs_io_type_to_rw_hint(struct f2fs_sb_info *sbi, + enum page_type type, enum temp_type temp) +{ + if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_USER) { + if (type == DATA) { + if (temp == WARM) + return WRITE_LIFE_NOT_SET; + else if (temp == HOT) + return WRITE_LIFE_SHORT; + else if (temp == COLD) + return WRITE_LIFE_EXTREME; + } else { + return WRITE_LIFE_NOT_SET; + } + } else if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_FS) { + if (type == DATA) { + if (temp == WARM) + return WRITE_LIFE_LONG; + else if (temp == HOT) + return WRITE_LIFE_SHORT; + else if (temp == COLD) + return WRITE_LIFE_EXTREME; + } else if (type == NODE) { + if (temp == WARM || temp == HOT) + return WRITE_LIFE_NOT_SET; + else if (temp == COLD) + return WRITE_LIFE_NONE; + } else if (type == META) { + return WRITE_LIFE_MEDIUM; + } + } + return WRITE_LIFE_NOT_SET; +} + static int __get_segment_type_2(struct f2fs_io_info *fio) { if (fio->type == DATA) @@ -2299,9 +2971,12 @@ static int __get_segment_type_6(struct f2fs_io_info *fio) if (is_cold_data(fio->page) || file_is_cold(inode)) return CURSEG_COLD_DATA; - if (is_inode_flag_set(inode, FI_HOT_DATA)) + if (file_is_hot(inode) || + is_inode_flag_set(inode, FI_HOT_DATA) || + f2fs_is_atomic_file(inode) || + f2fs_is_volatile_file(inode)) return CURSEG_HOT_DATA; - return CURSEG_WARM_DATA; + return f2fs_rw_hint_to_seg_type(inode->i_write_hint); } else { if (IS_DNODE(fio->page)) return is_cold_node(fio->page) ? CURSEG_WARM_NODE : @@ -2314,7 +2989,7 @@ static int __get_segment_type(struct f2fs_io_info *fio) { int type = 0; - switch (fio->sbi->active_logs) { + switch (F2FS_OPTION(fio->sbi).active_logs) { case 2: type = __get_segment_type_2(fio); break; @@ -2337,7 +3012,7 @@ static int __get_segment_type(struct f2fs_io_info *fio) return type; } -void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, +void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, block_t old_blkaddr, block_t *new_blkaddr, struct f2fs_summary *sum, int type, struct f2fs_io_info *fio, bool add_list) @@ -2345,8 +3020,10 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, struct sit_info *sit_i = SIT_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, type); + down_read(&SM_I(sbi)->curseg_lock); + mutex_lock(&curseg->curseg_mutex); - mutex_lock(&sit_i->sentry_lock); + down_write(&sit_i->sentry_lock); *new_blkaddr = NEXT_FREE_BLKADDR(sbi, curseg); @@ -2363,15 +3040,26 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, stat_inc_block_count(sbi, curseg); + /* + * SIT information should be updated before segment allocation, + * since SSR needs latest valid block information. + */ + update_sit_entry(sbi, *new_blkaddr, 1); + if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) + update_sit_entry(sbi, old_blkaddr, -1); + if (!__has_curseg_space(sbi, type)) sit_i->s_ops->allocate_segment(sbi, type, false); + /* - * SIT information should be updated after segment allocation, - * since we need to keep dirty segments precisely under SSR. + * segment dirty status should be updated after segment allocation, + * so we just need to update status only one time after previous + * segment being closed. */ - refresh_sit_entry(sbi, old_blkaddr, *new_blkaddr); + locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr)); + locate_dirty_segment(sbi, GET_SEGNO(sbi, *new_blkaddr)); - mutex_unlock(&sit_i->sentry_lock); + up_write(&sit_i->sentry_lock); if (page && IS_NODESEG(type)) { fill_node_footer_blkaddr(page, NEXT_FREE_BLKADDR(sbi, curseg)); @@ -2384,6 +3072,7 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, INIT_LIST_HEAD(&fio->list); fio->in_list = true; + fio->retry = false; io = sbi->write_io[fio->type] + fio->temp; spin_lock(&io->io_lock); list_add_tail(&fio->list, &io->io_list); @@ -2391,31 +3080,65 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, } mutex_unlock(&curseg->curseg_mutex); + + up_read(&SM_I(sbi)->curseg_lock); +} + +static void update_device_state(struct f2fs_io_info *fio) +{ + struct f2fs_sb_info *sbi = fio->sbi; + unsigned int devidx; + + if (!sbi->s_ndevs) + return; + + devidx = f2fs_target_device_index(sbi, fio->new_blkaddr); + + /* update device state for fsync */ + f2fs_set_dirty_device(sbi, fio->ino, devidx, FLUSH_INO); + + /* update device state for checkpoint */ + if (!f2fs_test_bit(devidx, (char *)&sbi->dirty_device)) { + spin_lock(&sbi->dev_lock); + f2fs_set_bit(devidx, (char *)&sbi->dirty_device); + spin_unlock(&sbi->dev_lock); + } } static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio) { int type = __get_segment_type(fio); - int err; + bool keep_order = (test_opt(fio->sbi, LFS) && type == CURSEG_COLD_DATA); + if (keep_order) + down_read(&fio->sbi->io_order_lock); reallocate: - allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr, + f2fs_allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr, &fio->new_blkaddr, sum, type, fio, true); + if (GET_SEGNO(fio->sbi, fio->old_blkaddr) != NULL_SEGNO) + invalidate_mapping_pages(META_MAPPING(fio->sbi), + fio->old_blkaddr, fio->old_blkaddr); /* writeout dirty page into bdev */ - err = f2fs_submit_page_write(fio); - if (err == -EAGAIN) { + f2fs_submit_page_write(fio); + if (fio->retry) { fio->old_blkaddr = fio->new_blkaddr; goto reallocate; } + + update_device_state(fio); + + if (keep_order) + up_read(&fio->sbi->io_order_lock); } -void write_meta_page(struct f2fs_sb_info *sbi, struct page *page, +void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct page *page, enum iostat_type io_type) { struct f2fs_io_info fio = { .sbi = sbi, .type = META, + .temp = HOT, .op = REQ_OP_WRITE, .op_flags = REQ_SYNC | REQ_META | REQ_PRIO, .old_blkaddr = page->index, @@ -2429,12 +3152,14 @@ void write_meta_page(struct f2fs_sb_info *sbi, struct page *page, fio.op_flags &= ~REQ_META; set_page_writeback(page); + ClearPageError(page); f2fs_submit_page_write(&fio); + stat_inc_meta_count(sbi, page->index); f2fs_update_iostat(sbi, io_type, F2FS_BLKSIZE); } -void write_node_page(unsigned int nid, struct f2fs_io_info *fio) +void f2fs_do_write_node_page(unsigned int nid, struct f2fs_io_info *fio) { struct f2fs_summary sum; @@ -2444,36 +3169,56 @@ void write_node_page(unsigned int nid, struct f2fs_io_info *fio) f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE); } -void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio) +void f2fs_outplace_write_data(struct dnode_of_data *dn, + struct f2fs_io_info *fio) { struct f2fs_sb_info *sbi = fio->sbi; struct f2fs_summary sum; - struct node_info ni; f2fs_bug_on(sbi, dn->data_blkaddr == NULL_ADDR); - get_node_info(sbi, dn->nid, &ni); - set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version); + set_summary(&sum, dn->nid, dn->ofs_in_node, fio->version); do_write_page(&sum, fio); f2fs_update_data_blkaddr(dn, fio->new_blkaddr); f2fs_update_iostat(sbi, fio->io_type, F2FS_BLKSIZE); } -int rewrite_data_page(struct f2fs_io_info *fio) +int f2fs_inplace_write_data(struct f2fs_io_info *fio) { int err; + struct f2fs_sb_info *sbi = fio->sbi; fio->new_blkaddr = fio->old_blkaddr; + /* i/o temperature is needed for passing down write hints */ + __get_segment_type(fio); + + f2fs_bug_on(sbi, !IS_DATASEG(get_seg_entry(sbi, + GET_SEGNO(sbi, fio->new_blkaddr))->type)); + stat_inc_inplace_blocks(fio->sbi); err = f2fs_submit_page_bio(fio); - - f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE); + if (!err) { + update_device_state(fio); + f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE); + } return err; } -void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, +static inline int __f2fs_get_curseg(struct f2fs_sb_info *sbi, + unsigned int segno) +{ + int i; + + for (i = CURSEG_HOT_DATA; i < NO_CHECK_TYPE; i++) { + if (CURSEG_I(sbi, i)->segno == segno) + break; + } + return i; +} + +void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, block_t old_blkaddr, block_t new_blkaddr, bool recover_curseg, bool recover_newaddr) { @@ -2488,6 +3233,8 @@ void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, se = get_seg_entry(sbi, segno); type = se->type; + down_write(&SM_I(sbi)->curseg_lock); + if (!recover_curseg) { /* for recovery flow */ if (se->valid_blocks == 0 && !IS_CURSEG(sbi, segno)) { @@ -2497,14 +3244,20 @@ void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, type = CURSEG_WARM_DATA; } } else { - if (!IS_CURSEG(sbi, segno)) + if (IS_CURSEG(sbi, segno)) { + /* se->type is volatile as SSR allocation */ + type = __f2fs_get_curseg(sbi, segno); + f2fs_bug_on(sbi, type == NO_CHECK_TYPE); + } else { type = CURSEG_WARM_DATA; + } } + f2fs_bug_on(sbi, !IS_DATASEG(type)); curseg = CURSEG_I(sbi, type); mutex_lock(&curseg->curseg_mutex); - mutex_lock(&sit_i->sentry_lock); + down_write(&sit_i->sentry_lock); old_cursegno = curseg->segno; old_blkoff = curseg->next_blkoff; @@ -2520,8 +3273,11 @@ void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, if (!recover_curseg || recover_newaddr) update_sit_entry(sbi, new_blkaddr, 1); - if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) + if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) { + invalidate_mapping_pages(META_MAPPING(sbi), + old_blkaddr, old_blkaddr); update_sit_entry(sbi, old_blkaddr, -1); + } locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr)); locate_dirty_segment(sbi, GET_SEGNO(sbi, new_blkaddr)); @@ -2536,8 +3292,9 @@ void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, curseg->next_blkoff = old_blkoff; } - mutex_unlock(&sit_i->sentry_lock); + up_write(&sit_i->sentry_lock); mutex_unlock(&curseg->curseg_mutex); + up_write(&SM_I(sbi)->curseg_lock); } void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn, @@ -2549,41 +3306,55 @@ void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn, set_summary(&sum, dn->nid, dn->ofs_in_node, version); - __f2fs_replace_block(sbi, &sum, old_addr, new_addr, + f2fs_do_replace_block(sbi, &sum, old_addr, new_addr, recover_curseg, recover_newaddr); f2fs_update_data_blkaddr(dn, new_addr); } void f2fs_wait_on_page_writeback(struct page *page, - enum page_type type, bool ordered) + enum page_type type, bool ordered, bool locked) { if (PageWriteback(page)) { struct f2fs_sb_info *sbi = F2FS_P_SB(page); - f2fs_submit_merged_write_cond(sbi, page->mapping->host, - 0, page->index, type); - if (ordered) + f2fs_submit_merged_write_cond(sbi, NULL, page, 0, type); + if (ordered) { wait_on_page_writeback(page); - else + f2fs_bug_on(sbi, locked && PageWriteback(page)); + } else { wait_for_stable_page(page); + } } } -void f2fs_wait_on_block_writeback(struct f2fs_sb_info *sbi, block_t blkaddr) +void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr) { + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct page *cpage; + if (!f2fs_post_read_required(inode)) + return; + if (!is_valid_data_blkaddr(sbi, blkaddr)) return; cpage = find_lock_page(META_MAPPING(sbi), blkaddr); if (cpage) { - f2fs_wait_on_page_writeback(cpage, DATA, true); + f2fs_wait_on_page_writeback(cpage, DATA, true, true); f2fs_put_page(cpage, 1); } } +void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr, + block_t len) +{ + block_t i; + + for (i = 0; i < len; i++) + f2fs_wait_on_block_writeback(inode, blkaddr + i); +} + static int read_compacted_summaries(struct f2fs_sb_info *sbi) { struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); @@ -2595,7 +3366,9 @@ static int read_compacted_summaries(struct f2fs_sb_info *sbi) start = start_sum_block(sbi); - page = get_meta_page(sbi, start++); + page = f2fs_get_meta_page(sbi, start++); + if (IS_ERR(page)) + return PTR_ERR(page); kaddr = (unsigned char *)page_address(page); /* Step 1: restore nat cache */ @@ -2635,7 +3408,9 @@ static int read_compacted_summaries(struct f2fs_sb_info *sbi) f2fs_put_page(page, 1); page = NULL; - page = get_meta_page(sbi, start++); + page = f2fs_get_meta_page(sbi, start++); + if (IS_ERR(page)) + return PTR_ERR(page); kaddr = (unsigned char *)page_address(page); offset = 0; } @@ -2653,6 +3428,7 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type) unsigned short blk_off; unsigned int segno = 0; block_t blk_addr = 0; + int err = 0; /* get segment number and block addr */ if (IS_DATASEG(type)) { @@ -2675,7 +3451,9 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type) blk_addr = GET_SUM_BLOCK(sbi, segno); } - new = get_meta_page(sbi, blk_addr); + new = f2fs_get_meta_page(sbi, blk_addr); + if (IS_ERR(new)) + return PTR_ERR(new); sum = (struct f2fs_summary_block *)page_address(new); if (IS_NODESEG(type)) { @@ -2687,13 +3465,9 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type) ns->ofs_in_node = 0; } } else { - int err; - - err = restore_node_summary(sbi, segno, sum); - if (err) { - f2fs_put_page(new, 1); - return err; - } + err = f2fs_restore_node_summary(sbi, segno, sum); + if (err) + goto out; } } @@ -2713,8 +3487,9 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type) curseg->alloc_type = ckpt->alloc_type[type]; curseg->next_blkoff = blk_off; mutex_unlock(&curseg->curseg_mutex); +out: f2fs_put_page(new, 1); - return 0; + return err; } static int restore_curseg_summaries(struct f2fs_sb_info *sbi) @@ -2725,20 +3500,21 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi) int err; if (is_set_ckpt_flags(sbi, CP_COMPACT_SUM_FLAG)) { - int npages = npages_for_summary_flush(sbi, true); + int npages = f2fs_npages_for_summary_flush(sbi, true); if (npages >= 2) - ra_meta_pages(sbi, start_sum_block(sbi), npages, + f2fs_ra_meta_pages(sbi, start_sum_block(sbi), npages, META_CP, true); /* restore for compacted data summary */ - if (read_compacted_summaries(sbi)) - return -EINVAL; + err = read_compacted_summaries(sbi); + if (err) + return err; type = CURSEG_HOT_NODE; } if (__exist_node_summaries(sbi)) - ra_meta_pages(sbi, sum_blk_addr(sbi, NR_CURSEG_TYPE, type), + f2fs_ra_meta_pages(sbi, sum_blk_addr(sbi, NR_CURSEG_TYPE, type), NR_CURSEG_TYPE - type, META_CP, true); for (; type <= CURSEG_COLD_NODE; type++) { @@ -2764,8 +3540,9 @@ static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr) int written_size = 0; int i, j; - page = grab_meta_page(sbi, blkaddr++); + page = f2fs_grab_meta_page(sbi, blkaddr++); kaddr = (unsigned char *)page_address(page); + memset(kaddr, 0, PAGE_SIZE); /* Step 1: write nat cache */ seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA); @@ -2788,8 +3565,9 @@ static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr) for (j = 0; j < blkoff; j++) { if (!page) { - page = grab_meta_page(sbi, blkaddr++); + page = f2fs_grab_meta_page(sbi, blkaddr++); kaddr = (unsigned char *)page_address(page); + memset(kaddr, 0, PAGE_SIZE); written_size = 0; } summary = (struct f2fs_summary *)(kaddr + written_size); @@ -2824,7 +3602,7 @@ static void write_normal_summaries(struct f2fs_sb_info *sbi, write_current_sum_page(sbi, i, blkaddr + (i - type)); } -void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk) +void f2fs_write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk) { if (is_set_ckpt_flags(sbi, CP_COMPACT_SUM_FLAG)) write_compacted_summaries(sbi, start_blk); @@ -2832,12 +3610,12 @@ void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk) write_normal_summaries(sbi, start_blk, CURSEG_HOT_DATA); } -void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk) +void f2fs_write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk) { write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE); } -int lookup_journal_in_cursum(struct f2fs_journal *journal, int type, +int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type, unsigned int val, int alloc) { int i; @@ -2862,35 +3640,26 @@ int lookup_journal_in_cursum(struct f2fs_journal *journal, int type, static struct page *get_current_sit_page(struct f2fs_sb_info *sbi, unsigned int segno) { - return get_meta_page(sbi, current_sit_addr(sbi, segno)); + return f2fs_get_meta_page_nofail(sbi, current_sit_addr(sbi, segno)); } static struct page *get_next_sit_page(struct f2fs_sb_info *sbi, unsigned int start) { struct sit_info *sit_i = SIT_I(sbi); - struct page *src_page, *dst_page; + struct page *page; pgoff_t src_off, dst_off; - void *src_addr, *dst_addr; src_off = current_sit_addr(sbi, start); dst_off = next_sit_addr(sbi, src_off); - /* get current sit block page without lock */ - src_page = get_meta_page(sbi, src_off); - dst_page = grab_meta_page(sbi, dst_off); - f2fs_bug_on(sbi, PageDirty(src_page)); - - src_addr = page_address(src_page); - dst_addr = page_address(dst_page); - memcpy(dst_addr, src_addr, PAGE_SIZE); - - set_page_dirty(dst_page); - f2fs_put_page(src_page, 1); + page = f2fs_grab_meta_page(sbi, dst_off); + seg_info_to_sit_page(sbi, page, start); + set_page_dirty(page); set_to_next_sit(sit_i, start); - return dst_page; + return page; } static struct sit_entry_set *grab_sit_entry_set(void) @@ -2980,7 +3749,7 @@ static void remove_sits_in_journal(struct f2fs_sb_info *sbi) * CP calls this function, which flushes SIT entries including sit_journal, * and moves prefree segs to free segs. */ -void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) +void f2fs_flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) { struct sit_info *sit_i = SIT_I(sbi); unsigned long *bitmap = sit_i->dirty_sentries_bitmap; @@ -2991,7 +3760,7 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) bool to_journal = true; struct seg_entry *se; - mutex_lock(&sit_i->sentry_lock); + down_write(&sit_i->sentry_lock); if (!sit_i->dirty_sentries) goto out; @@ -3039,6 +3808,11 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) int offset, sit_offset; se = get_seg_entry(sbi, segno); +#ifdef CONFIG_F2FS_CHECK_FS + if (memcmp(se->cur_valid_map, se->cur_valid_map_mir, + SIT_VBLOCK_MAP_SIZE)) + f2fs_bug_on(sbi, 1); +#endif /* add discard candidates */ if (!(cpc->reason & CP_DISCARD)) { @@ -3047,17 +3821,21 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) } if (to_journal) { - offset = lookup_journal_in_cursum(journal, + offset = f2fs_lookup_journal_in_cursum(journal, SIT_JOURNAL, segno, 1); f2fs_bug_on(sbi, offset < 0); segno_in_journal(journal, offset) = cpu_to_le32(segno); seg_info_to_raw_sit(se, &sit_in_journal(journal, offset)); + check_block_count(sbi, segno, + &sit_in_journal(journal, offset)); } else { sit_offset = SIT_ENTRY_OFFSET(sit_i, segno); seg_info_to_raw_sit(se, &raw_sit->entries[sit_offset]); + check_block_count(sbi, segno, + &raw_sit->entries[sit_offset]); } __clear_bit(segno, bitmap); @@ -3085,7 +3863,7 @@ out: cpc->trim_start = trim_start; } - mutex_unlock(&sit_i->sentry_lock); + up_write(&sit_i->sentry_lock); set_prefree_as_free_segments(sbi); } @@ -3099,53 +3877,57 @@ static int build_sit_info(struct f2fs_sb_info *sbi) unsigned int bitmap_size; /* allocate memory for SIT information */ - sit_i = kzalloc(sizeof(struct sit_info), GFP_KERNEL); + sit_i = f2fs_kzalloc(sbi, sizeof(struct sit_info), GFP_KERNEL); if (!sit_i) return -ENOMEM; SM_I(sbi)->sit_info = sit_i; - sit_i->sentries = kvzalloc(MAIN_SEGS(sbi) * - sizeof(struct seg_entry), GFP_KERNEL); + sit_i->sentries = + f2fs_kvzalloc(sbi, array_size(sizeof(struct seg_entry), + MAIN_SEGS(sbi)), + GFP_KERNEL); if (!sit_i->sentries) return -ENOMEM; bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi)); - sit_i->dirty_sentries_bitmap = kvzalloc(bitmap_size, GFP_KERNEL); + sit_i->dirty_sentries_bitmap = f2fs_kvzalloc(sbi, bitmap_size, + GFP_KERNEL); if (!sit_i->dirty_sentries_bitmap) return -ENOMEM; for (start = 0; start < MAIN_SEGS(sbi); start++) { sit_i->sentries[start].cur_valid_map - = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); + = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); sit_i->sentries[start].ckpt_valid_map - = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); + = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); if (!sit_i->sentries[start].cur_valid_map || !sit_i->sentries[start].ckpt_valid_map) return -ENOMEM; #ifdef CONFIG_F2FS_CHECK_FS sit_i->sentries[start].cur_valid_map_mir - = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); + = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); if (!sit_i->sentries[start].cur_valid_map_mir) return -ENOMEM; #endif - if (f2fs_discard_en(sbi)) { - sit_i->sentries[start].discard_map - = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); - if (!sit_i->sentries[start].discard_map) - return -ENOMEM; - } + sit_i->sentries[start].discard_map + = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, + GFP_KERNEL); + if (!sit_i->sentries[start].discard_map) + return -ENOMEM; } - sit_i->tmp_map = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); + sit_i->tmp_map = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); if (!sit_i->tmp_map) return -ENOMEM; - if (sbi->segs_per_sec > 1) { - sit_i->sec_entries = kvzalloc(MAIN_SECS(sbi) * - sizeof(struct sec_entry), GFP_KERNEL); + if (__is_large_section(sbi)) { + sit_i->sec_entries = + f2fs_kvzalloc(sbi, array_size(sizeof(struct sec_entry), + MAIN_SECS(sbi)), + GFP_KERNEL); if (!sit_i->sec_entries) return -ENOMEM; } @@ -3178,7 +3960,7 @@ static int build_sit_info(struct f2fs_sb_info *sbi) sit_i->sents_per_block = SIT_ENTRY_PER_BLOCK; sit_i->elapsed_time = le64_to_cpu(sbi->ckpt->elapsed_time); sit_i->mounted_time = ktime_get_real_seconds(); - mutex_init(&sit_i->sentry_lock); + init_rwsem(&sit_i->sentry_lock); return 0; } @@ -3188,19 +3970,19 @@ static int build_free_segmap(struct f2fs_sb_info *sbi) unsigned int bitmap_size, sec_bitmap_size; /* allocate memory for free segmap information */ - free_i = kzalloc(sizeof(struct free_segmap_info), GFP_KERNEL); + free_i = f2fs_kzalloc(sbi, sizeof(struct free_segmap_info), GFP_KERNEL); if (!free_i) return -ENOMEM; SM_I(sbi)->free_info = free_i; bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi)); - free_i->free_segmap = kvmalloc(bitmap_size, GFP_KERNEL); + free_i->free_segmap = f2fs_kvmalloc(sbi, bitmap_size, GFP_KERNEL); if (!free_i->free_segmap) return -ENOMEM; sec_bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi)); - free_i->free_secmap = kvmalloc(sec_bitmap_size, GFP_KERNEL); + free_i->free_secmap = f2fs_kvmalloc(sbi, sec_bitmap_size, GFP_KERNEL); if (!free_i->free_secmap) return -ENOMEM; @@ -3221,7 +4003,8 @@ static int build_curseg(struct f2fs_sb_info *sbi) struct curseg_info *array; int i; - array = kcalloc(NR_CURSEG_TYPE, sizeof(*array), GFP_KERNEL); + array = f2fs_kzalloc(sbi, array_size(NR_CURSEG_TYPE, sizeof(*array)), + GFP_KERNEL); if (!array) return -ENOMEM; @@ -3229,12 +4012,12 @@ static int build_curseg(struct f2fs_sb_info *sbi) for (i = 0; i < NR_CURSEG_TYPE; i++) { mutex_init(&array[i].curseg_mutex); - array[i].sum_blk = kzalloc(PAGE_SIZE, GFP_KERNEL); + array[i].sum_blk = f2fs_kzalloc(sbi, PAGE_SIZE, GFP_KERNEL); if (!array[i].sum_blk) return -ENOMEM; init_rwsem(&array[i].journal_rwsem); - array[i].journal = kzalloc(sizeof(struct f2fs_journal), - GFP_KERNEL); + array[i].journal = f2fs_kzalloc(sbi, + sizeof(struct f2fs_journal), GFP_KERNEL); if (!array[i].journal) return -ENOMEM; array[i].segno = NULL_SEGNO; @@ -3257,7 +4040,7 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) block_t total_node_blocks = 0; do { - readed = ra_meta_pages(sbi, start_blk, BIO_MAX_PAGES, + readed = f2fs_ra_meta_pages(sbi, start_blk, BIO_MAX_PAGES, META_SIT, true); start = start_blk * sit_i->sents_per_block; @@ -3269,6 +4052,8 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) se = &sit_i->sentries[start]; page = get_current_sit_page(sbi, start); + if (IS_ERR(page)) + return PTR_ERR(page); sit_blk = (struct f2fs_sit_block *)page_address(page); sit = sit_blk->entries[SIT_ENTRY_OFFSET(sit_i, start)]; f2fs_put_page(page, 1); @@ -3281,21 +4066,19 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) total_node_blocks += se->valid_blocks; /* build discard map only one time */ - if (f2fs_discard_en(sbi)) { - if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) { - memset(se->discard_map, 0xff, - SIT_VBLOCK_MAP_SIZE); - } else { - memcpy(se->discard_map, - se->cur_valid_map, - SIT_VBLOCK_MAP_SIZE); - sbi->discard_blks += - sbi->blocks_per_seg - - se->valid_blocks; - } + if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) { + memset(se->discard_map, 0xff, + SIT_VBLOCK_MAP_SIZE); + } else { + memcpy(se->discard_map, + se->cur_valid_map, + SIT_VBLOCK_MAP_SIZE); + sbi->discard_blks += + sbi->blocks_per_seg - + se->valid_blocks; } - if (sbi->segs_per_sec > 1) + if (__is_large_section(sbi)) get_sec_entry(sbi, start)->valid_blocks += se->valid_blocks; } @@ -3330,21 +4113,21 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) if (IS_NODESEG(se->type)) total_node_blocks += se->valid_blocks; - if (f2fs_discard_en(sbi)) { - if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) { - memset(se->discard_map, 0xff, - SIT_VBLOCK_MAP_SIZE); - } else { - memcpy(se->discard_map, se->cur_valid_map, - SIT_VBLOCK_MAP_SIZE); - sbi->discard_blks += old_valid_blocks - - se->valid_blocks; - } + if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) { + memset(se->discard_map, 0xff, SIT_VBLOCK_MAP_SIZE); + } else { + memcpy(se->discard_map, se->cur_valid_map, + SIT_VBLOCK_MAP_SIZE); + sbi->discard_blks += old_valid_blocks; + sbi->discard_blks -= se->valid_blocks; } - if (sbi->segs_per_sec > 1) + if (__is_large_section(sbi)) { get_sec_entry(sbi, start)->valid_blocks += - se->valid_blocks - old_valid_blocks; + se->valid_blocks; + get_sec_entry(sbi, start)->valid_blocks -= + old_valid_blocks; + } } up_read(&curseg->journal_rwsem); @@ -3411,7 +4194,7 @@ static int init_victim_secmap(struct f2fs_sb_info *sbi) struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); unsigned int bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi)); - dirty_i->victim_secmap = kvzalloc(bitmap_size, GFP_KERNEL); + dirty_i->victim_secmap = f2fs_kvzalloc(sbi, bitmap_size, GFP_KERNEL); if (!dirty_i->victim_secmap) return -ENOMEM; return 0; @@ -3423,7 +4206,8 @@ static int build_dirty_segmap(struct f2fs_sb_info *sbi) unsigned int bitmap_size, i; /* allocate memory for dirty segments list information */ - dirty_i = kzalloc(sizeof(struct dirty_seglist_info), GFP_KERNEL); + dirty_i = f2fs_kzalloc(sbi, sizeof(struct dirty_seglist_info), + GFP_KERNEL); if (!dirty_i) return -ENOMEM; @@ -3433,7 +4217,8 @@ static int build_dirty_segmap(struct f2fs_sb_info *sbi) bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi)); for (i = 0; i < NR_DIRTY_TYPE; i++) { - dirty_i->dirty_segmap[i] = kvzalloc(bitmap_size, GFP_KERNEL); + dirty_i->dirty_segmap[i] = f2fs_kvzalloc(sbi, bitmap_size, + GFP_KERNEL); if (!dirty_i->dirty_segmap[i]) return -ENOMEM; } @@ -3485,9 +4270,9 @@ static void init_min_max_mtime(struct f2fs_sb_info *sbi) struct sit_info *sit_i = SIT_I(sbi); unsigned int segno; - mutex_lock(&sit_i->sentry_lock); + down_write(&sit_i->sentry_lock); - sit_i->min_mtime = LLONG_MAX; + sit_i->min_mtime = ULLONG_MAX; for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) { unsigned int i; @@ -3501,18 +4286,18 @@ static void init_min_max_mtime(struct f2fs_sb_info *sbi) if (sit_i->min_mtime > mtime) sit_i->min_mtime = mtime; } - sit_i->max_mtime = get_mtime(sbi); - mutex_unlock(&sit_i->sentry_lock); + sit_i->max_mtime = get_mtime(sbi, false); + up_write(&sit_i->sentry_lock); } -int build_segment_manager(struct f2fs_sb_info *sbi) +int f2fs_build_segment_manager(struct f2fs_sb_info *sbi) { struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); struct f2fs_sm_info *sm_info; int err; - sm_info = kzalloc(sizeof(struct f2fs_sm_info), GFP_KERNEL); + sm_info = f2fs_kzalloc(sbi, sizeof(struct f2fs_sm_info), GFP_KERNEL); if (!sm_info) return -ENOMEM; @@ -3534,14 +4319,16 @@ int build_segment_manager(struct f2fs_sb_info *sbi) sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC; sm_info->min_ipu_util = DEF_MIN_IPU_UTIL; sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS; + sm_info->min_seq_blocks = sbi->blocks_per_seg * sbi->segs_per_sec; sm_info->min_hot_blocks = DEF_MIN_HOT_BLOCKS; - - sm_info->trim_sections = DEF_BATCHED_TRIM_SECTIONS; + sm_info->min_ssr_sections = reserved_sections(sbi); INIT_LIST_HEAD(&sm_info->sit_entry_set); + init_rwsem(&sm_info->curseg_lock); + if (!f2fs_readonly(sbi->sb)) { - err = create_flush_cmd_control(sbi); + err = f2fs_create_flush_cmd_control(sbi); if (err) return err; } @@ -3609,7 +4396,7 @@ static void destroy_dirty_segmap(struct f2fs_sb_info *sbi) destroy_victim_secmap(sbi); SM_I(sbi)->dirty_info = NULL; - kfree(dirty_i); + kvfree(dirty_i); } static void destroy_curseg(struct f2fs_sb_info *sbi) @@ -3621,10 +4408,10 @@ static void destroy_curseg(struct f2fs_sb_info *sbi) return; SM_I(sbi)->curseg_array = NULL; for (i = 0; i < NR_CURSEG_TYPE; i++) { - kfree(array[i].sum_blk); - kfree(array[i].journal); + kvfree(array[i].sum_blk); + kvfree(array[i].journal); } - kfree(array); + kvfree(array); } static void destroy_free_segmap(struct f2fs_sb_info *sbi) @@ -3635,7 +4422,7 @@ static void destroy_free_segmap(struct f2fs_sb_info *sbi) SM_I(sbi)->free_info = NULL; kvfree(free_i->free_segmap); kvfree(free_i->free_secmap); - kfree(free_i); + kvfree(free_i); } static void destroy_sit_info(struct f2fs_sb_info *sbi) @@ -3648,45 +4435,45 @@ static void destroy_sit_info(struct f2fs_sb_info *sbi) if (sit_i->sentries) { for (start = 0; start < MAIN_SEGS(sbi); start++) { - kfree(sit_i->sentries[start].cur_valid_map); + kvfree(sit_i->sentries[start].cur_valid_map); #ifdef CONFIG_F2FS_CHECK_FS - kfree(sit_i->sentries[start].cur_valid_map_mir); + kvfree(sit_i->sentries[start].cur_valid_map_mir); #endif - kfree(sit_i->sentries[start].ckpt_valid_map); - kfree(sit_i->sentries[start].discard_map); + kvfree(sit_i->sentries[start].ckpt_valid_map); + kvfree(sit_i->sentries[start].discard_map); } } - kfree(sit_i->tmp_map); + kvfree(sit_i->tmp_map); kvfree(sit_i->sentries); kvfree(sit_i->sec_entries); kvfree(sit_i->dirty_sentries_bitmap); SM_I(sbi)->sit_info = NULL; - kfree(sit_i->sit_bitmap); + kvfree(sit_i->sit_bitmap); #ifdef CONFIG_F2FS_CHECK_FS - kfree(sit_i->sit_bitmap_mir); + kvfree(sit_i->sit_bitmap_mir); #endif - kfree(sit_i); + kvfree(sit_i); } -void destroy_segment_manager(struct f2fs_sb_info *sbi) +void f2fs_destroy_segment_manager(struct f2fs_sb_info *sbi) { struct f2fs_sm_info *sm_info = SM_I(sbi); if (!sm_info) return; - destroy_flush_cmd_control(sbi, true); + f2fs_destroy_flush_cmd_control(sbi, true); destroy_discard_cmd_control(sbi); destroy_dirty_segmap(sbi); destroy_curseg(sbi); destroy_free_segmap(sbi); destroy_sit_info(sbi); sbi->sm_info = NULL; - kfree(sm_info); + kvfree(sm_info); } -int __init create_segment_manager_caches(void) +int __init f2fs_create_segment_manager_caches(void) { discard_entry_slab = f2fs_kmem_cache_create("discard_entry", sizeof(struct discard_entry)); @@ -3719,7 +4506,7 @@ fail: return -ENOMEM; } -void destroy_segment_manager_caches(void) +void f2fs_destroy_segment_manager_caches(void) { kmem_cache_destroy(sit_entry_set_slab); kmem_cache_destroy(discard_cmd_slab); diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 0d46e936d54e..c08202f4f988 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/segment.h * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/blkdev.h> #include <linux/backing-dev.h> @@ -215,6 +212,8 @@ struct segment_allocation { #define IS_DUMMY_WRITTEN_PAGE(page) \ (page_private(page) == (unsigned long)DUMMY_WRITTEN_PAGE) +#define MAX_SKIP_GC_COUNT 16 + struct inmem_pages { struct list_head list; struct page *page; @@ -237,7 +236,7 @@ struct sit_info { unsigned long *dirty_sentries_bitmap; /* bitmap for dirty sentries */ unsigned int dirty_sentries; /* # of dirty sentries */ unsigned int sents_per_block; /* # of SIT entries per block */ - struct mutex sentry_lock; /* to protect SIT cache */ + struct rw_semaphore sentry_lock; /* to protect SIT cache */ struct seg_entry *sentries; /* SIT segment-level cache */ struct sec_entry *sec_entries; /* SIT section-level cache */ @@ -334,12 +333,18 @@ static inline unsigned int get_valid_blocks(struct f2fs_sb_info *sbi, * In order to get # of valid blocks in a section instantly from many * segments, f2fs manages two counting structures separately. */ - if (use_section && sbi->segs_per_sec > 1) + if (use_section && __is_large_section(sbi)) return get_sec_entry(sbi, segno)->valid_blocks; else return get_seg_entry(sbi, segno)->valid_blocks; } +static inline unsigned int get_ckpt_valid_blocks(struct f2fs_sb_info *sbi, + unsigned int segno) +{ + return get_seg_entry(sbi, segno)->ckpt_valid_blocks; +} + static inline void seg_info_from_raw_sit(struct seg_entry *se, struct f2fs_sit_entry *rs) { @@ -354,16 +359,42 @@ static inline void seg_info_from_raw_sit(struct seg_entry *se, se->mtime = le64_to_cpu(rs->mtime); } -static inline void seg_info_to_raw_sit(struct seg_entry *se, +static inline void __seg_info_to_raw_sit(struct seg_entry *se, struct f2fs_sit_entry *rs) { unsigned short raw_vblocks = (se->type << SIT_VBLOCKS_SHIFT) | se->valid_blocks; rs->vblocks = cpu_to_le16(raw_vblocks); memcpy(rs->valid_map, se->cur_valid_map, SIT_VBLOCK_MAP_SIZE); + rs->mtime = cpu_to_le64(se->mtime); +} + +static inline void seg_info_to_sit_page(struct f2fs_sb_info *sbi, + struct page *page, unsigned int start) +{ + struct f2fs_sit_block *raw_sit; + struct seg_entry *se; + struct f2fs_sit_entry *rs; + unsigned int end = min(start + SIT_ENTRY_PER_BLOCK, + (unsigned long)MAIN_SEGS(sbi)); + int i; + + raw_sit = (struct f2fs_sit_block *)page_address(page); + memset(raw_sit, 0, PAGE_SIZE); + for (i = 0; i < end - start; i++) { + rs = &raw_sit->entries[i]; + se = get_seg_entry(sbi, start + i); + __seg_info_to_raw_sit(se, rs); + } +} + +static inline void seg_info_to_raw_sit(struct seg_entry *se, + struct f2fs_sit_entry *rs) +{ + __seg_info_to_raw_sit(se, rs); + memcpy(se->ckpt_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE); se->ckpt_valid_blocks = se->valid_blocks; - rs->mtime = cpu_to_le64(se->mtime); } static inline unsigned int find_next_inuse(struct free_segmap_info *free_i, @@ -506,6 +537,33 @@ static inline int reserved_sections(struct f2fs_sb_info *sbi) return GET_SEC_FROM_SEG(sbi, (unsigned int)reserved_segments(sbi)); } +static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi) +{ + unsigned int node_blocks = get_pages(sbi, F2FS_DIRTY_NODES) + + get_pages(sbi, F2FS_DIRTY_DENTS); + unsigned int dent_blocks = get_pages(sbi, F2FS_DIRTY_DENTS); + unsigned int segno, left_blocks; + int i; + + /* check current node segment */ + for (i = CURSEG_HOT_NODE; i <= CURSEG_COLD_NODE; i++) { + segno = CURSEG_I(sbi, i)->segno; + left_blocks = sbi->blocks_per_seg - + get_seg_entry(sbi, segno)->ckpt_valid_blocks; + + if (node_blocks > left_blocks) + return false; + } + + /* check current data segment */ + segno = CURSEG_I(sbi, CURSEG_HOT_DATA)->segno; + left_blocks = sbi->blocks_per_seg - + get_seg_entry(sbi, segno)->ckpt_valid_blocks; + if (dent_blocks > left_blocks) + return false; + return true; +} + static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, int freed, int needed) { @@ -516,11 +574,23 @@ static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) return false; + if (free_sections(sbi) + freed == reserved_sections(sbi) + needed && + has_curseg_enough_space(sbi)) + return false; return (free_sections(sbi) + freed) <= (node_secs + 2 * dent_secs + imeta_secs + reserved_sections(sbi) + needed); } +static inline int f2fs_is_checkpoint_ready(struct f2fs_sb_info *sbi) +{ + if (likely(!is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + return 0; + if (likely(!has_not_enough_free_secs(sbi, 0, 0))) + return 0; + return -ENOSPC; +} + static inline bool excess_prefree_segs(struct f2fs_sb_info *sbi) { return prefree_segments(sbi) > SM_I(sbi)->rec_prefree_segments; @@ -550,6 +620,8 @@ static inline int utilization(struct f2fs_sb_info *sbi) #define DEF_MIN_FSYNC_BLOCKS 8 #define DEF_MIN_HOT_BLOCKS 16 +#define SMALL_VOLUME_SEGMENTS (16 * 512) /* 16GB */ + enum { F2FS_IPU_FORCE, F2FS_IPU_SSR, @@ -559,47 +631,6 @@ enum { F2FS_IPU_ASYNC, }; -static inline bool need_inplace_update_policy(struct inode *inode, - struct f2fs_io_info *fio) -{ - struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - unsigned int policy = SM_I(sbi)->ipu_policy; - - if (test_opt(sbi, LFS)) - return false; - - /* if this is cold file, we should overwrite to avoid fragmentation */ - if (file_is_cold(inode)) - return true; - - if (policy & (0x1 << F2FS_IPU_FORCE)) - return true; - if (policy & (0x1 << F2FS_IPU_SSR) && need_SSR(sbi)) - return true; - if (policy & (0x1 << F2FS_IPU_UTIL) && - utilization(sbi) > SM_I(sbi)->min_ipu_util) - return true; - if (policy & (0x1 << F2FS_IPU_SSR_UTIL) && need_SSR(sbi) && - utilization(sbi) > SM_I(sbi)->min_ipu_util) - return true; - - /* - * IPU for rewrite async pages - */ - if (policy & (0x1 << F2FS_IPU_ASYNC) && - fio && fio->op == REQ_OP_WRITE && - !(fio->op_flags & REQ_SYNC) && - !f2fs_encrypted_inode(inode)) - return true; - - /* this is only set during fdatasync */ - if (policy & (0x1 << F2FS_IPU_FSYNC) && - is_inode_flag_set(inode, FI_NEED_IPU)) - return true; - - return false; -} - static inline unsigned int curseg_segno(struct f2fs_sb_info *sbi, int type) { @@ -725,12 +756,23 @@ static inline void set_to_next_sit(struct sit_info *sit_i, unsigned int start) #endif } -static inline unsigned long long get_mtime(struct f2fs_sb_info *sbi) +static inline unsigned long long get_mtime(struct f2fs_sb_info *sbi, + bool base_time) { struct sit_info *sit_i = SIT_I(sbi); - time64_t now = ktime_get_real_seconds(); + time64_t diff, now = ktime_get_real_seconds(); + + if (now >= sit_i->mounted_time) + return sit_i->elapsed_time + now - sit_i->mounted_time; - return sit_i->elapsed_time + now - sit_i->mounted_time; + /* system time is set to the past */ + if (!base_time) { + diff = sit_i->mounted_time - now; + if (sit_i->elapsed_time >= diff) + return sit_i->elapsed_time - diff; + return 0; + } + return sit_i->elapsed_time; } static inline void set_summary(struct f2fs_summary *sum, nid_t nid, @@ -754,15 +796,6 @@ static inline block_t sum_blk_addr(struct f2fs_sb_info *sbi, int base, int type) - (base + 1) + type; } -static inline bool no_fggc_candidate(struct f2fs_sb_info *sbi, - unsigned int secno) -{ - if (get_valid_blocks(sbi, GET_SEG_FROM_SEC(sbi, secno), true) >= - sbi->fggc_threshold) - return true; - return false; -} - static inline bool sec_usage_check(struct f2fs_sb_info *sbi, unsigned int secno) { if (IS_CURSEC(sbi, secno) || (sbi->cur_victim_sec == secno)) @@ -822,15 +855,16 @@ static inline void wake_up_discard_thread(struct f2fs_sb_info *sbi, bool force) goto wake_up; mutex_lock(&dcc->cmd_lock); - for (i = MAX_PLIST_NUM - 1; - i >= 0 && plist_issue(dcc->pend_list_tag[i]); i--) { + for (i = MAX_PLIST_NUM - 1; i >= 0; i--) { + if (i + 1 < dcc->discard_granularity) + break; if (!list_empty(&dcc->pend_list[i])) { wakeup = true; break; } } mutex_unlock(&dcc->cmd_lock); - if (!wakeup) + if (!wakeup || !is_idle(sbi, DISCARD_TIME)) return; wake_up: dcc->discard_wake = 1; diff --git a/fs/f2fs/shrinker.c b/fs/f2fs/shrinker.c index ec71d2e29a15..a467aca29cfe 100644 --- a/fs/f2fs/shrinker.c +++ b/fs/f2fs/shrinker.c @@ -1,13 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 /* * f2fs shrinker support * the basic infra was copied from fs/ubifs/shrinker.c * * Copyright (c) 2015 Motorola Mobility * Copyright (c) 2015 Jaegeuk Kim <jaegeuk@kernel.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> @@ -28,7 +25,7 @@ static unsigned long __count_nat_entries(struct f2fs_sb_info *sbi) static unsigned long __count_free_nids(struct f2fs_sb_info *sbi) { - long count = NM_I(sbi)->nid_cnt[FREE_NID_LIST] - MAX_FREE_NIDS; + long count = NM_I(sbi)->nid_cnt[FREE_NID] - MAX_FREE_NIDS; return count > 0 ? count : 0; } @@ -109,11 +106,11 @@ unsigned long f2fs_shrink_scan(struct shrinker *shrink, /* shrink clean nat cache entries */ if (freed < nr) - freed += try_to_free_nats(sbi, nr - freed); + freed += f2fs_try_to_free_nats(sbi, nr - freed); /* shrink free nids cache entries */ if (freed < nr) - freed += try_to_free_nids(sbi, nr - freed); + freed += f2fs_try_to_free_nids(sbi, nr - freed); spin_lock(&f2fs_list_lock); p = p->next; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 89319c352406..b5c115e6f294 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/super.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/module.h> #include <linux/init.h> @@ -41,31 +38,39 @@ static struct kmem_cache *f2fs_inode_cachep; #ifdef CONFIG_F2FS_FAULT_INJECTION -char *fault_name[FAULT_MAX] = { +const char *f2fs_fault_name[FAULT_MAX] = { [FAULT_KMALLOC] = "kmalloc", + [FAULT_KVMALLOC] = "kvmalloc", [FAULT_PAGE_ALLOC] = "page alloc", + [FAULT_PAGE_GET] = "page get", + [FAULT_ALLOC_BIO] = "alloc bio", [FAULT_ALLOC_NID] = "alloc nid", [FAULT_ORPHAN] = "orphan", [FAULT_BLOCK] = "no more block", [FAULT_DIR_DEPTH] = "too big dir depth", [FAULT_EVICT_INODE] = "evict_inode fail", [FAULT_TRUNCATE] = "truncate fail", - [FAULT_IO] = "IO error", + [FAULT_READ_IO] = "read IO error", [FAULT_CHECKPOINT] = "checkpoint error", + [FAULT_DISCARD] = "discard error", + [FAULT_WRITE_IO] = "write IO error", }; -static void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, - unsigned int rate) +void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate, + unsigned int type) { - struct f2fs_fault_info *ffi = &sbi->fault_info; + struct f2fs_fault_info *ffi = &F2FS_OPTION(sbi).fault_info; if (rate) { atomic_set(&ffi->inject_ops, 0); ffi->inject_rate = rate; - ffi->inject_type = (1 << FAULT_MAX) - 1; - } else { - memset(ffi, 0, sizeof(struct f2fs_fault_info)); } + + if (type) + ffi->inject_type = type; + + if (!rate && !type) + memset(ffi, 0, sizeof(struct f2fs_fault_info)); } #endif @@ -92,6 +97,7 @@ enum { Opt_disable_ext_identify, Opt_inline_xattr, Opt_noinline_xattr, + Opt_inline_xattr_size, Opt_inline_data, Opt_inline_dentry, Opt_noinline_dentry, @@ -103,9 +109,13 @@ enum { Opt_noextent_cache, Opt_noinline_data, Opt_data_flush, + Opt_reserve_root, + Opt_resgid, + Opt_resuid, Opt_mode, Opt_io_size_bits, Opt_fault_injection, + Opt_fault_type, Opt_lazytime, Opt_nolazytime, Opt_quota, @@ -122,6 +132,11 @@ enum { Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, + Opt_whint, + Opt_alloc, + Opt_fsync, + Opt_test_dummy_encryption, + Opt_checkpoint, Opt_err, }; @@ -141,6 +156,7 @@ static match_table_t f2fs_tokens = { {Opt_disable_ext_identify, "disable_ext_identify"}, {Opt_inline_xattr, "inline_xattr"}, {Opt_noinline_xattr, "noinline_xattr"}, + {Opt_inline_xattr_size, "inline_xattr_size=%u"}, {Opt_inline_data, "inline_data"}, {Opt_inline_dentry, "inline_dentry"}, {Opt_noinline_dentry, "noinline_dentry"}, @@ -152,9 +168,13 @@ static match_table_t f2fs_tokens = { {Opt_noextent_cache, "noextent_cache"}, {Opt_noinline_data, "noinline_data"}, {Opt_data_flush, "data_flush"}, + {Opt_reserve_root, "reserve_root=%u"}, + {Opt_resgid, "resgid=%u"}, + {Opt_resuid, "resuid=%u"}, {Opt_mode, "mode=%s"}, {Opt_io_size_bits, "io_bits=%u"}, {Opt_fault_injection, "fault_injection=%u"}, + {Opt_fault_type, "fault_type=%u"}, {Opt_lazytime, "lazytime"}, {Opt_nolazytime, "nolazytime"}, {Opt_quota, "quota"}, @@ -171,6 +191,11 @@ static match_table_t f2fs_tokens = { {Opt_jqfmt_vfsold, "jqfmt=vfsold"}, {Opt_jqfmt_vfsv0, "jqfmt=vfsv0"}, {Opt_jqfmt_vfsv1, "jqfmt=vfsv1"}, + {Opt_whint, "whint_mode=%s"}, + {Opt_alloc, "alloc_mode=%s"}, + {Opt_fsync, "fsync_mode=%s"}, + {Opt_test_dummy_encryption, "test_dummy_encryption"}, + {Opt_checkpoint, "checkpoint=%s"}, {Opt_err, NULL}, }; @@ -182,10 +207,35 @@ void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...) va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; - printk_ratelimited("%sF2FS-fs (%s): %pV\n", level, sb->s_id, &vaf); + printk("%sF2FS-fs (%s): %pV\n", level, sb->s_id, &vaf); va_end(args); } +static inline void limit_reserve_root(struct f2fs_sb_info *sbi) +{ + block_t limit = (sbi->user_block_count << 1) / 1000; + + /* limit is 0.2% */ + if (test_opt(sbi, RESERVE_ROOT) && + F2FS_OPTION(sbi).root_reserved_blocks > limit) { + F2FS_OPTION(sbi).root_reserved_blocks = limit; + f2fs_msg(sbi->sb, KERN_INFO, + "Reduce reserved blocks for root = %u", + F2FS_OPTION(sbi).root_reserved_blocks); + } + if (!test_opt(sbi, RESERVE_ROOT) && + (!uid_eq(F2FS_OPTION(sbi).s_resuid, + make_kuid(&init_user_ns, F2FS_DEF_RESUID)) || + !gid_eq(F2FS_OPTION(sbi).s_resgid, + make_kgid(&init_user_ns, F2FS_DEF_RESGID)))) + f2fs_msg(sbi->sb, KERN_INFO, + "Ignore s_resuid=%u, s_resgid=%u w/o reserve_root", + from_kuid_munged(&init_user_ns, + F2FS_OPTION(sbi).s_resuid), + from_kgid_munged(&init_user_ns, + F2FS_OPTION(sbi).s_resgid)); +} + static void init_once(void *foo) { struct f2fs_inode_info *fi = (struct f2fs_inode_info *) foo; @@ -203,20 +253,26 @@ static int f2fs_set_qf_name(struct super_block *sb, int qtype, char *qname; int ret = -EINVAL; - if (sb_any_quota_loaded(sb) && !sbi->s_qf_names[qtype]) { + if (sb_any_quota_loaded(sb) && !F2FS_OPTION(sbi).s_qf_names[qtype]) { f2fs_msg(sb, KERN_ERR, "Cannot change journaled " "quota options when quota turned on"); return -EINVAL; } + if (f2fs_sb_has_quota_ino(sbi)) { + f2fs_msg(sb, KERN_INFO, + "QUOTA feature is enabled, so ignore qf_name"); + return 0; + } + qname = match_strdup(args); if (!qname) { f2fs_msg(sb, KERN_ERR, "Not enough memory for storing quotafile name"); - return -EINVAL; + return -ENOMEM; } - if (sbi->s_qf_names[qtype]) { - if (strcmp(sbi->s_qf_names[qtype], qname) == 0) + if (F2FS_OPTION(sbi).s_qf_names[qtype]) { + if (strcmp(F2FS_OPTION(sbi).s_qf_names[qtype], qname) == 0) ret = 0; else f2fs_msg(sb, KERN_ERR, @@ -229,11 +285,11 @@ static int f2fs_set_qf_name(struct super_block *sb, int qtype, "quotafile must be on filesystem root"); goto errout; } - sbi->s_qf_names[qtype] = qname; + F2FS_OPTION(sbi).s_qf_names[qtype] = qname; set_opt(sbi, QUOTA); return 0; errout: - kfree(qname); + kvfree(qname); return ret; } @@ -241,13 +297,13 @@ static int f2fs_clear_qf_name(struct super_block *sb, int qtype) { struct f2fs_sb_info *sbi = F2FS_SB(sb); - if (sb_any_quota_loaded(sb) && sbi->s_qf_names[qtype]) { + if (sb_any_quota_loaded(sb) && F2FS_OPTION(sbi).s_qf_names[qtype]) { f2fs_msg(sb, KERN_ERR, "Cannot change journaled quota options" " when quota turned on"); return -EINVAL; } - kfree(sbi->s_qf_names[qtype]); - sbi->s_qf_names[qtype] = NULL; + kvfree(F2FS_OPTION(sbi).s_qf_names[qtype]); + F2FS_OPTION(sbi).s_qf_names[qtype] = NULL; return 0; } @@ -258,20 +314,24 @@ static int f2fs_check_quota_options(struct f2fs_sb_info *sbi) * 'grpquota' mount options are allowed even without quota feature * to support legacy quotas in quota files. */ - if (test_opt(sbi, PRJQUOTA) && !f2fs_sb_has_project_quota(sbi->sb)) { + if (test_opt(sbi, PRJQUOTA) && !f2fs_sb_has_project_quota(sbi)) { f2fs_msg(sbi->sb, KERN_ERR, "Project quota feature not enabled. " "Cannot enable project quota enforcement."); return -1; } - if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA] || - sbi->s_qf_names[PRJQUOTA]) { - if (test_opt(sbi, USRQUOTA) && sbi->s_qf_names[USRQUOTA]) + if (F2FS_OPTION(sbi).s_qf_names[USRQUOTA] || + F2FS_OPTION(sbi).s_qf_names[GRPQUOTA] || + F2FS_OPTION(sbi).s_qf_names[PRJQUOTA]) { + if (test_opt(sbi, USRQUOTA) && + F2FS_OPTION(sbi).s_qf_names[USRQUOTA]) clear_opt(sbi, USRQUOTA); - if (test_opt(sbi, GRPQUOTA) && sbi->s_qf_names[GRPQUOTA]) + if (test_opt(sbi, GRPQUOTA) && + F2FS_OPTION(sbi).s_qf_names[GRPQUOTA]) clear_opt(sbi, GRPQUOTA); - if (test_opt(sbi, PRJQUOTA) && sbi->s_qf_names[PRJQUOTA]) + if (test_opt(sbi, PRJQUOTA) && + F2FS_OPTION(sbi).s_qf_names[PRJQUOTA]) clear_opt(sbi, PRJQUOTA); if (test_opt(sbi, GRPQUOTA) || test_opt(sbi, USRQUOTA) || @@ -281,12 +341,18 @@ static int f2fs_check_quota_options(struct f2fs_sb_info *sbi) return -1; } - if (!sbi->s_jquota_fmt) { + if (!F2FS_OPTION(sbi).s_jquota_fmt) { f2fs_msg(sbi->sb, KERN_ERR, "journaled quota format " "not specified"); return -1; } } + + if (f2fs_sb_has_quota_ino(sbi) && F2FS_OPTION(sbi).s_jquota_fmt) { + f2fs_msg(sbi->sb, KERN_INFO, + "QUOTA feature is enabled, so ignore jquota_fmt"); + F2FS_OPTION(sbi).s_jquota_fmt = 0; + } return 0; } #endif @@ -294,10 +360,11 @@ static int f2fs_check_quota_options(struct f2fs_sb_info *sbi) static int parse_options(struct super_block *sb, char *options) { struct f2fs_sb_info *sbi = F2FS_SB(sb); - struct request_queue *q; substring_t args[MAX_OPT_ARGS]; char *p, *name; int arg = 0; + kuid_t uid; + kgid_t gid; #ifdef CONFIG_QUOTA int ret; #endif @@ -332,10 +399,10 @@ static int parse_options(struct super_block *sb, char *options) set_opt(sbi, BG_GC); set_opt(sbi, FORCE_FG_GC); } else { - kfree(name); + kvfree(name); return -EINVAL; } - kfree(name); + kvfree(name); break; case Opt_disable_roll_forward: set_opt(sbi, DISABLE_ROLL_FORWARD); @@ -347,17 +414,10 @@ static int parse_options(struct super_block *sb, char *options) return -EINVAL; break; case Opt_discard: - q = bdev_get_queue(sb->s_bdev); - if (blk_queue_discard(q)) { - set_opt(sbi, DISCARD); - } else if (!f2fs_sb_mounted_blkzoned(sb)) { - f2fs_msg(sb, KERN_WARNING, - "mounting with \"discard\" option, but " - "the device does not support discard"); - } + set_opt(sbi, DISCARD); break; case Opt_nodiscard: - if (f2fs_sb_mounted_blkzoned(sb)) { + if (f2fs_sb_has_blkzoned(sbi)) { f2fs_msg(sb, KERN_WARNING, "discard is required for zoned block devices"); return -EINVAL; @@ -383,6 +443,12 @@ static int parse_options(struct super_block *sb, char *options) case Opt_noinline_xattr: clear_opt(sbi, INLINE_XATTR); break; + case Opt_inline_xattr_size: + if (args->from && match_int(args, &arg)) + return -EINVAL; + set_opt(sbi, INLINE_XATTR_SIZE); + F2FS_OPTION(sbi).inline_xattr_size = arg; + break; #else case Opt_user_xattr: f2fs_msg(sb, KERN_INFO, @@ -421,7 +487,7 @@ static int parse_options(struct super_block *sb, char *options) return -EINVAL; if (arg != 2 && arg != 4 && arg != NR_CURSEG_TYPE) return -EINVAL; - sbi->active_logs = arg; + F2FS_OPTION(sbi).active_logs = arg; break; case Opt_disable_ext_identify: set_opt(sbi, DISABLE_EXT_IDENTIFY); @@ -459,6 +525,40 @@ static int parse_options(struct super_block *sb, char *options) case Opt_data_flush: set_opt(sbi, DATA_FLUSH); break; + case Opt_reserve_root: + if (args->from && match_int(args, &arg)) + return -EINVAL; + if (test_opt(sbi, RESERVE_ROOT)) { + f2fs_msg(sb, KERN_INFO, + "Preserve previous reserve_root=%u", + F2FS_OPTION(sbi).root_reserved_blocks); + } else { + F2FS_OPTION(sbi).root_reserved_blocks = arg; + set_opt(sbi, RESERVE_ROOT); + } + break; + case Opt_resuid: + if (args->from && match_int(args, &arg)) + return -EINVAL; + uid = make_kuid(current_user_ns(), arg); + if (!uid_valid(uid)) { + f2fs_msg(sb, KERN_ERR, + "Invalid uid value %d", arg); + return -EINVAL; + } + F2FS_OPTION(sbi).s_resuid = uid; + break; + case Opt_resgid: + if (args->from && match_int(args, &arg)) + return -EINVAL; + gid = make_kgid(current_user_ns(), arg); + if (!gid_valid(gid)) { + f2fs_msg(sb, KERN_ERR, + "Invalid gid value %d", arg); + return -EINVAL; + } + F2FS_OPTION(sbi).s_resgid = gid; + break; case Opt_mode: name = match_strdup(&args[0]); @@ -466,11 +566,11 @@ static int parse_options(struct super_block *sb, char *options) return -ENOMEM; if (strlen(name) == 8 && !strncmp(name, "adaptive", 8)) { - if (f2fs_sb_mounted_blkzoned(sb)) { + if (f2fs_sb_has_blkzoned(sbi)) { f2fs_msg(sb, KERN_WARNING, "adaptive mode is not allowed with " "zoned block device feature"); - kfree(name); + kvfree(name); return -EINVAL; } set_opt_mode(sbi, F2FS_MOUNT_ADAPTIVE); @@ -478,33 +578,47 @@ static int parse_options(struct super_block *sb, char *options) !strncmp(name, "lfs", 3)) { set_opt_mode(sbi, F2FS_MOUNT_LFS); } else { - kfree(name); + kvfree(name); return -EINVAL; } - kfree(name); + kvfree(name); break; case Opt_io_size_bits: if (args->from && match_int(args, &arg)) return -EINVAL; - if (arg > __ilog2_u32(BIO_MAX_PAGES)) { + if (arg <= 0 || arg > __ilog2_u32(BIO_MAX_PAGES)) { f2fs_msg(sb, KERN_WARNING, "Not support %d, larger than %d", 1 << arg, BIO_MAX_PAGES); return -EINVAL; } - sbi->write_io_size_bits = arg; + F2FS_OPTION(sbi).write_io_size_bits = arg; break; +#ifdef CONFIG_F2FS_FAULT_INJECTION case Opt_fault_injection: if (args->from && match_int(args, &arg)) return -EINVAL; -#ifdef CONFIG_F2FS_FAULT_INJECTION - f2fs_build_fault_attr(sbi, arg); + f2fs_build_fault_attr(sbi, arg, F2FS_ALL_FAULT_TYPE); set_opt(sbi, FAULT_INJECTION); + break; + + case Opt_fault_type: + if (args->from && match_int(args, &arg)) + return -EINVAL; + f2fs_build_fault_attr(sbi, 0, arg); + set_opt(sbi, FAULT_INJECTION); + break; #else + case Opt_fault_injection: f2fs_msg(sb, KERN_INFO, - "FAULT_INJECTION was not selected"); -#endif + "fault_injection options not supported"); + break; + + case Opt_fault_type: + f2fs_msg(sb, KERN_INFO, + "fault_type options not supported"); break; +#endif case Opt_lazytime: sb->s_flags |= MS_LAZYTIME; break; @@ -553,13 +667,13 @@ static int parse_options(struct super_block *sb, char *options) return ret; break; case Opt_jqfmt_vfsold: - sbi->s_jquota_fmt = QFMT_VFS_OLD; + F2FS_OPTION(sbi).s_jquota_fmt = QFMT_VFS_OLD; break; case Opt_jqfmt_vfsv0: - sbi->s_jquota_fmt = QFMT_VFS_V0; + F2FS_OPTION(sbi).s_jquota_fmt = QFMT_VFS_V0; break; case Opt_jqfmt_vfsv1: - sbi->s_jquota_fmt = QFMT_VFS_V1; + F2FS_OPTION(sbi).s_jquota_fmt = QFMT_VFS_V1; break; case Opt_noquota: clear_opt(sbi, QUOTA); @@ -586,6 +700,94 @@ static int parse_options(struct super_block *sb, char *options) "quota operations not supported"); break; #endif + case Opt_whint: + name = match_strdup(&args[0]); + if (!name) + return -ENOMEM; + if (strlen(name) == 10 && + !strncmp(name, "user-based", 10)) { + F2FS_OPTION(sbi).whint_mode = WHINT_MODE_USER; + } else if (strlen(name) == 3 && + !strncmp(name, "off", 3)) { + F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF; + } else if (strlen(name) == 8 && + !strncmp(name, "fs-based", 8)) { + F2FS_OPTION(sbi).whint_mode = WHINT_MODE_FS; + } else { + kvfree(name); + return -EINVAL; + } + kvfree(name); + break; + case Opt_alloc: + name = match_strdup(&args[0]); + if (!name) + return -ENOMEM; + + if (strlen(name) == 7 && + !strncmp(name, "default", 7)) { + F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_DEFAULT; + } else if (strlen(name) == 5 && + !strncmp(name, "reuse", 5)) { + F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_REUSE; + } else { + kvfree(name); + return -EINVAL; + } + kvfree(name); + break; + case Opt_fsync: + name = match_strdup(&args[0]); + if (!name) + return -ENOMEM; + if (strlen(name) == 5 && + !strncmp(name, "posix", 5)) { + F2FS_OPTION(sbi).fsync_mode = FSYNC_MODE_POSIX; + } else if (strlen(name) == 6 && + !strncmp(name, "strict", 6)) { + F2FS_OPTION(sbi).fsync_mode = FSYNC_MODE_STRICT; + } else if (strlen(name) == 9 && + !strncmp(name, "nobarrier", 9)) { + F2FS_OPTION(sbi).fsync_mode = + FSYNC_MODE_NOBARRIER; + } else { + kvfree(name); + return -EINVAL; + } + kvfree(name); + break; + case Opt_test_dummy_encryption: +#ifdef CONFIG_F2FS_FS_ENCRYPTION + if (!f2fs_sb_has_encrypt(sbi)) { + f2fs_msg(sb, KERN_ERR, "Encrypt feature is off"); + return -EINVAL; + } + + F2FS_OPTION(sbi).test_dummy_encryption = true; + f2fs_msg(sb, KERN_INFO, + "Test dummy encryption mode enabled"); +#else + f2fs_msg(sb, KERN_INFO, + "Test dummy encryption mount option ignored"); +#endif + break; + case Opt_checkpoint: + name = match_strdup(&args[0]); + if (!name) + return -ENOMEM; + + if (strlen(name) == 6 && + !strncmp(name, "enable", 6)) { + clear_opt(sbi, DISABLE_CHECKPOINT); + } else if (strlen(name) == 7 && + !strncmp(name, "disable", 7)) { + set_opt(sbi, DISABLE_CHECKPOINT); + } else { + kvfree(name); + return -EINVAL; + } + kvfree(name); + break; default: f2fs_msg(sb, KERN_ERR, "Unrecognized mount option \"%s\" or missing value", @@ -596,6 +798,19 @@ static int parse_options(struct super_block *sb, char *options) #ifdef CONFIG_QUOTA if (f2fs_check_quota_options(sbi)) return -EINVAL; +#else + if (f2fs_sb_has_quota_ino(sbi) && !f2fs_readonly(sbi->sb)) { + f2fs_msg(sbi->sb, KERN_INFO, + "Filesystem with quota feature cannot be mounted RDWR " + "without CONFIG_QUOTA"); + return -EINVAL; + } + if (f2fs_sb_has_project_quota(sbi) && !f2fs_readonly(sbi->sb)) { + f2fs_msg(sb, KERN_ERR, + "Filesystem with project quota feature cannot be " + "mounted RDWR without CONFIG_QUOTA"); + return -EINVAL; + } #endif if (F2FS_IO_SIZE_BITS(sbi) && !test_opt(sbi, LFS)) { @@ -604,6 +819,47 @@ static int parse_options(struct super_block *sb, char *options) F2FS_IO_SIZE_KB(sbi)); return -EINVAL; } + + if (test_opt(sbi, INLINE_XATTR_SIZE)) { + int min_size, max_size; + + if (!f2fs_sb_has_extra_attr(sbi) || + !f2fs_sb_has_flexible_inline_xattr(sbi)) { + f2fs_msg(sb, KERN_ERR, + "extra_attr or flexible_inline_xattr " + "feature is off"); + return -EINVAL; + } + if (!test_opt(sbi, INLINE_XATTR)) { + f2fs_msg(sb, KERN_ERR, + "inline_xattr_size option should be " + "set with inline_xattr option"); + return -EINVAL; + } + + min_size = sizeof(struct f2fs_xattr_header) / sizeof(__le32); + max_size = MAX_INLINE_XATTR_SIZE; + + if (F2FS_OPTION(sbi).inline_xattr_size < min_size || + F2FS_OPTION(sbi).inline_xattr_size > max_size) { + f2fs_msg(sb, KERN_ERR, + "inline xattr size is out of range: %d ~ %d", + min_size, max_size); + return -EINVAL; + } + } + + if (test_opt(sbi, DISABLE_CHECKPOINT) && test_opt(sbi, LFS)) { + f2fs_msg(sb, KERN_ERR, + "LFS not compatible with checkpoint=disable\n"); + return -EINVAL; + } + + /* Not pass down write hints if the number of active logs is lesser + * than NR_CURSEG_TYPE. + */ + if (F2FS_OPTION(sbi).active_logs != NR_CURSEG_TYPE) + F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF; return 0; } @@ -618,24 +874,18 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb) init_once((void *) fi); /* Initialize f2fs-specific inode info */ - fi->vfs_inode.i_version = 1; atomic_set(&fi->dirty_pages, 0); - fi->i_current_depth = 1; - fi->i_advise = 0; init_rwsem(&fi->i_sem); INIT_LIST_HEAD(&fi->dirty_list); INIT_LIST_HEAD(&fi->gdirty_list); + INIT_LIST_HEAD(&fi->inmem_ilist); INIT_LIST_HEAD(&fi->inmem_pages); mutex_init(&fi->inmem_lock); - init_rwsem(&fi->dio_rwsem[READ]); - init_rwsem(&fi->dio_rwsem[WRITE]); + init_rwsem(&fi->i_gc_rwsem[READ]); + init_rwsem(&fi->i_gc_rwsem[WRITE]); init_rwsem(&fi->i_mmap_sem); init_rwsem(&fi->i_xattr_sem); -#ifdef CONFIG_QUOTA - memset(&fi->i_dquot, 0, sizeof(fi->i_dquot)); - fi->i_reserved_quota = 0; -#endif /* Will be used by directory only */ fi->i_dir_level = F2FS_SB(sb)->dir_level; @@ -660,7 +910,7 @@ static int f2fs_drop_inode(struct inode *inode) /* some remained atomic pages should discarded */ if (f2fs_is_atomic_file(inode)) - drop_inmem_pages(inode); + f2fs_drop_inmem_pages(inode); /* should remain fi->extent_tree for writepage */ f2fs_destroy_extent_node(inode); @@ -668,12 +918,15 @@ static int f2fs_drop_inode(struct inode *inode) sb_start_intwrite(inode->i_sb); f2fs_i_size_write(inode, 0); + f2fs_submit_merged_write_cond(F2FS_I_SB(inode), + inode, NULL, 0, DATA); + truncate_inode_pages_final(inode->i_mapping); + if (F2FS_HAS_BLOCKS(inode)) f2fs_truncate(inode); sb_end_intwrite(inode->i_sb); - fscrypt_put_encryption_info(inode, NULL); spin_lock(&inode->i_lock); atomic_dec(&inode->i_count); } @@ -771,16 +1024,17 @@ static void destroy_device_list(struct f2fs_sb_info *sbi) for (i = 0; i < sbi->s_ndevs; i++) { blkdev_put(FDEV(i).bdev, FMODE_EXCL); #ifdef CONFIG_BLK_DEV_ZONED - kfree(FDEV(i).blkz_type); + kvfree(FDEV(i).blkz_type); #endif } - kfree(sbi->devs); + kvfree(sbi->devs); } static void f2fs_put_super(struct super_block *sb) { struct f2fs_sb_info *sbi = F2FS_SB(sb); int i; + bool dropped; f2fs_quota_off_umount(sb); @@ -792,32 +1046,30 @@ static void f2fs_put_super(struct super_block *sb) * But, the previous checkpoint was not done by umount, it needs to do * clean checkpoint again. */ - if (is_sbi_flag_set(sbi, SBI_IS_DIRTY) || - !is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) { + if ((is_sbi_flag_set(sbi, SBI_IS_DIRTY) || + !is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG))) { struct cp_control cpc = { .reason = CP_UMOUNT, }; - write_checkpoint(sbi, &cpc); + f2fs_write_checkpoint(sbi, &cpc); } /* be sure to wait for any on-going discard commands */ - f2fs_wait_discard_bios(sbi, true); + dropped = f2fs_issue_discard_timeout(sbi); - if (f2fs_discard_en(sbi) && !sbi->discard_blks) { + if ((f2fs_hw_support_discard(sbi) || f2fs_hw_should_discard(sbi)) && + !sbi->discard_blks && !dropped) { struct cp_control cpc = { .reason = CP_UMOUNT | CP_TRIMMED, }; - write_checkpoint(sbi, &cpc); + f2fs_write_checkpoint(sbi, &cpc); } - /* write_checkpoint can update stat informaion */ - f2fs_destroy_stats(sbi); - /* * normally superblock is clean, so we need to release this. * In addition, EIO will skip do checkpoint, we need this as well. */ - release_ino_entry(sbi, true); + f2fs_release_ino_entry(sbi, true); f2fs_leave_shrinker(sbi); mutex_unlock(&sbi->umount_mutex); @@ -825,32 +1077,45 @@ static void f2fs_put_super(struct super_block *sb) /* our cp_error case, we can wait for any writeback page */ f2fs_flush_merged_writes(sbi); + f2fs_wait_on_all_pages_writeback(sbi); + + f2fs_bug_on(sbi, sbi->fsync_node_num); + iput(sbi->node_inode); + sbi->node_inode = NULL; + iput(sbi->meta_inode); + sbi->meta_inode = NULL; + + /* + * iput() can update stat information, if f2fs_write_checkpoint() + * above failed with error. + */ + f2fs_destroy_stats(sbi); /* destroy f2fs internal modules */ - destroy_node_manager(sbi); - destroy_segment_manager(sbi); + f2fs_destroy_node_manager(sbi); + f2fs_destroy_segment_manager(sbi); - kfree(sbi->ckpt); + kvfree(sbi->ckpt); f2fs_unregister_sysfs(sbi); sb->s_fs_info = NULL; if (sbi->s_chksum_driver) crypto_free_shash(sbi->s_chksum_driver); - kfree(sbi->raw_super); + kvfree(sbi->raw_super); destroy_device_list(sbi); mempool_destroy(sbi->write_io_dummy); #ifdef CONFIG_QUOTA for (i = 0; i < MAXQUOTAS; i++) - kfree(sbi->s_qf_names[i]); + kvfree(F2FS_OPTION(sbi).s_qf_names[i]); #endif destroy_percpu_info(sbi); for (i = 0; i < NR_PAGE_TYPE; i++) - kfree(sbi->write_io[i]); - kfree(sbi); + kvfree(sbi->write_io[i]); + kvfree(sbi); } int f2fs_sync_fs(struct super_block *sb, int sync) @@ -858,6 +1123,11 @@ int f2fs_sync_fs(struct super_block *sb, int sync) struct f2fs_sb_info *sbi = F2FS_SB(sb); int err = 0; + if (unlikely(f2fs_cp_error(sbi))) + return 0; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + return 0; + trace_f2fs_sync_fs(sb, sync); if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) @@ -869,7 +1139,7 @@ int f2fs_sync_fs(struct super_block *sb, int sync) cpc.reason = __get_cp_reason(sbi); mutex_lock(&sbi->gc_mutex); - err = write_checkpoint(sbi, &cpc); + err = f2fs_write_checkpoint(sbi, &cpc); mutex_unlock(&sbi->gc_mutex); } f2fs_trace_ios(NULL, 1); @@ -910,7 +1180,7 @@ static int f2fs_statfs_project(struct super_block *sb, dquot = dqget(sb, qid); if (IS_ERR(dquot)) return PTR_ERR(dquot); - spin_lock(&dq_data_lock); + spin_lock(&dquot->dq_dqb_lock); limit = min_not_zero(dquot->dq_dqb.dqb_bsoftlimit, dquot->dq_dqb.dqb_bhardlimit); @@ -936,7 +1206,7 @@ static int f2fs_statfs_project(struct super_block *sb, (buf->f_files - dquot->dq_dqb.dqb_curinodes) : 0; } - spin_unlock(&dq_data_lock); + spin_unlock(&dquot->dq_dqb_lock); dqput(dquot); return 0; } @@ -947,22 +1217,31 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf) struct super_block *sb = dentry->d_sb; struct f2fs_sb_info *sbi = F2FS_SB(sb); u64 id = huge_encode_dev(sb->s_bdev->bd_dev); - block_t total_count, user_block_count, start_count, ovp_count; + block_t total_count, user_block_count, start_count; u64 avail_node_count; total_count = le64_to_cpu(sbi->raw_super->block_count); user_block_count = sbi->user_block_count; start_count = le32_to_cpu(sbi->raw_super->segment0_blkaddr); - ovp_count = SM_I(sbi)->ovp_segments << sbi->log_blocks_per_seg; buf->f_type = F2FS_SUPER_MAGIC; buf->f_bsize = sbi->blocksize; buf->f_blocks = total_count - start_count; - buf->f_bfree = user_block_count - valid_user_blocks(sbi) + ovp_count; - buf->f_bavail = user_block_count - valid_user_blocks(sbi) - - sbi->reserved_blocks; + buf->f_bfree = user_block_count - valid_user_blocks(sbi) - + sbi->current_reserved_blocks; + if (unlikely(buf->f_bfree <= sbi->unusable_block_count)) + buf->f_bfree = 0; + else + buf->f_bfree -= sbi->unusable_block_count; + + if (buf->f_bfree > F2FS_OPTION(sbi).root_reserved_blocks) + buf->f_bavail = buf->f_bfree - + F2FS_OPTION(sbi).root_reserved_blocks; + else + buf->f_bavail = 0; - avail_node_count = sbi->total_node_count - F2FS_RESERVED_NODE_NUM; + avail_node_count = sbi->total_node_count - sbi->nquota_files - + F2FS_RESERVED_NODE_NUM; if (avail_node_count > user_block_count) { buf->f_files = user_block_count; @@ -992,10 +1271,10 @@ static inline void f2fs_show_quota_options(struct seq_file *seq, #ifdef CONFIG_QUOTA struct f2fs_sb_info *sbi = F2FS_SB(sb); - if (sbi->s_jquota_fmt) { + if (F2FS_OPTION(sbi).s_jquota_fmt) { char *fmtname = ""; - switch (sbi->s_jquota_fmt) { + switch (F2FS_OPTION(sbi).s_jquota_fmt) { case QFMT_VFS_OLD: fmtname = "vfsold"; break; @@ -1009,14 +1288,17 @@ static inline void f2fs_show_quota_options(struct seq_file *seq, seq_printf(seq, ",jqfmt=%s", fmtname); } - if (sbi->s_qf_names[USRQUOTA]) - seq_show_option(seq, "usrjquota", sbi->s_qf_names[USRQUOTA]); + if (F2FS_OPTION(sbi).s_qf_names[USRQUOTA]) + seq_show_option(seq, "usrjquota", + F2FS_OPTION(sbi).s_qf_names[USRQUOTA]); - if (sbi->s_qf_names[GRPQUOTA]) - seq_show_option(seq, "grpjquota", sbi->s_qf_names[GRPQUOTA]); + if (F2FS_OPTION(sbi).s_qf_names[GRPQUOTA]) + seq_show_option(seq, "grpjquota", + F2FS_OPTION(sbi).s_qf_names[GRPQUOTA]); - if (sbi->s_qf_names[PRJQUOTA]) - seq_show_option(seq, "prjjquota", sbi->s_qf_names[PRJQUOTA]); + if (F2FS_OPTION(sbi).s_qf_names[PRJQUOTA]) + seq_show_option(seq, "prjjquota", + F2FS_OPTION(sbi).s_qf_names[PRJQUOTA]); #endif } @@ -1049,6 +1331,9 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",inline_xattr"); else seq_puts(seq, ",noinline_xattr"); + if (test_opt(sbi, INLINE_XATTR_SIZE)) + seq_printf(seq, ",inline_xattr_size=%u", + F2FS_OPTION(sbi).inline_xattr_size); #endif #ifdef CONFIG_F2FS_FS_POSIX_ACL if (test_opt(sbi, POSIX_ACL)) @@ -1084,13 +1369,24 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, "adaptive"); else if (test_opt(sbi, LFS)) seq_puts(seq, "lfs"); - seq_printf(seq, ",active_logs=%u", sbi->active_logs); + seq_printf(seq, ",active_logs=%u", F2FS_OPTION(sbi).active_logs); + if (test_opt(sbi, RESERVE_ROOT)) + seq_printf(seq, ",reserve_root=%u,resuid=%u,resgid=%u", + F2FS_OPTION(sbi).root_reserved_blocks, + from_kuid_munged(&init_user_ns, + F2FS_OPTION(sbi).s_resuid), + from_kgid_munged(&init_user_ns, + F2FS_OPTION(sbi).s_resgid)); if (F2FS_IO_SIZE_BITS(sbi)) - seq_printf(seq, ",io_size=%uKB", F2FS_IO_SIZE_KB(sbi)); + seq_printf(seq, ",io_bits=%u", + F2FS_OPTION(sbi).write_io_size_bits); #ifdef CONFIG_F2FS_FAULT_INJECTION - if (test_opt(sbi, FAULT_INJECTION)) + if (test_opt(sbi, FAULT_INJECTION)) { seq_printf(seq, ",fault_injection=%u", - sbi->fault_info.inject_rate); + F2FS_OPTION(sbi).fault_info.inject_rate); + seq_printf(seq, ",fault_type=%u", + F2FS_OPTION(sbi).fault_info.inject_type); + } #endif #ifdef CONFIG_QUOTA if (test_opt(sbi, QUOTA)) @@ -1103,14 +1399,43 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",prjquota"); #endif f2fs_show_quota_options(seq, sbi->sb); + if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_USER) + seq_printf(seq, ",whint_mode=%s", "user-based"); + else if (F2FS_OPTION(sbi).whint_mode == WHINT_MODE_FS) + seq_printf(seq, ",whint_mode=%s", "fs-based"); +#ifdef CONFIG_F2FS_FS_ENCRYPTION + if (F2FS_OPTION(sbi).test_dummy_encryption) + seq_puts(seq, ",test_dummy_encryption"); +#endif + if (F2FS_OPTION(sbi).alloc_mode == ALLOC_MODE_DEFAULT) + seq_printf(seq, ",alloc_mode=%s", "default"); + else if (F2FS_OPTION(sbi).alloc_mode == ALLOC_MODE_REUSE) + seq_printf(seq, ",alloc_mode=%s", "reuse"); + + if (test_opt(sbi, DISABLE_CHECKPOINT)) + seq_puts(seq, ",checkpoint=disable"); + + if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_POSIX) + seq_printf(seq, ",fsync_mode=%s", "posix"); + else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT) + seq_printf(seq, ",fsync_mode=%s", "strict"); + else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_NOBARRIER) + seq_printf(seq, ",fsync_mode=%s", "nobarrier"); return 0; } static void default_options(struct f2fs_sb_info *sbi) { /* init some FS parameters */ - sbi->active_logs = NR_CURSEG_TYPE; + F2FS_OPTION(sbi).active_logs = NR_CURSEG_TYPE; + F2FS_OPTION(sbi).inline_xattr_size = DEFAULT_INLINE_XATTR_ADDRS; + F2FS_OPTION(sbi).whint_mode = WHINT_MODE_OFF; + F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_DEFAULT; + F2FS_OPTION(sbi).fsync_mode = FSYNC_MODE_POSIX; + F2FS_OPTION(sbi).test_dummy_encryption = false; + F2FS_OPTION(sbi).s_resuid = make_kuid(&init_user_ns, F2FS_DEF_RESUID); + F2FS_OPTION(sbi).s_resgid = make_kgid(&init_user_ns, F2FS_DEF_RESGID); set_opt(sbi, BG_GC); set_opt(sbi, INLINE_XATTR); @@ -1119,13 +1444,13 @@ static void default_options(struct f2fs_sb_info *sbi) set_opt(sbi, EXTENT_CACHE); set_opt(sbi, NOHEAP); sbi->sb->s_flags |= MS_LAZYTIME; + clear_opt(sbi, DISABLE_CHECKPOINT); set_opt(sbi, FLUSH_MERGE); - if (f2fs_sb_mounted_blkzoned(sbi->sb)) { + set_opt(sbi, DISCARD); + if (f2fs_sb_has_blkzoned(sbi)) set_opt_mode(sbi, F2FS_MOUNT_LFS); - set_opt(sbi, DISCARD); - } else { + else set_opt_mode(sbi, F2FS_MOUNT_ADAPTIVE); - } #ifdef CONFIG_F2FS_FS_XATTR set_opt(sbi, XATTR_USER); @@ -1134,9 +1459,73 @@ static void default_options(struct f2fs_sb_info *sbi) set_opt(sbi, POSIX_ACL); #endif -#ifdef CONFIG_F2FS_FAULT_INJECTION - f2fs_build_fault_attr(sbi, 0); + f2fs_build_fault_attr(sbi, 0, 0); +} + +#ifdef CONFIG_QUOTA +static int f2fs_enable_quotas(struct super_block *sb); #endif + +static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) +{ + unsigned int s_flags = sbi->sb->s_flags; + struct cp_control cpc; + int err = 0; + int ret; + + if (s_flags & SB_RDONLY) { + f2fs_msg(sbi->sb, KERN_ERR, + "checkpoint=disable on readonly fs"); + return -EINVAL; + } + sbi->sb->s_flags |= SB_ACTIVE; + + f2fs_update_time(sbi, DISABLE_TIME); + + while (!f2fs_time_over(sbi, DISABLE_TIME)) { + mutex_lock(&sbi->gc_mutex); + err = f2fs_gc(sbi, true, false, NULL_SEGNO); + if (err == -ENODATA) { + err = 0; + break; + } + if (err && err != -EAGAIN) + break; + } + + ret = sync_filesystem(sbi->sb); + if (ret || err) { + err = ret ? ret: err; + goto restore_flag; + } + + if (f2fs_disable_cp_again(sbi)) { + err = -EAGAIN; + goto restore_flag; + } + + mutex_lock(&sbi->gc_mutex); + cpc.reason = CP_PAUSE; + set_sbi_flag(sbi, SBI_CP_DISABLED); + f2fs_write_checkpoint(sbi, &cpc); + + sbi->unusable_block_count = 0; + mutex_unlock(&sbi->gc_mutex); +restore_flag: + sbi->sb->s_flags = s_flags; /* Restore MS_RDONLY status */ + return err; +} + +static void f2fs_enable_checkpoint(struct f2fs_sb_info *sbi) +{ + mutex_lock(&sbi->gc_mutex); + f2fs_dirty_to_prefree(sbi); + + clear_sbi_flag(sbi, SBI_CP_DISABLED); + set_sbi_flag(sbi, SBI_IS_DIRTY); + mutex_unlock(&sbi->gc_mutex); + + f2fs_sync_fs(sbi->sb, 1); } static int f2fs_remount(struct super_block *sb, int *flags, char *data) @@ -1144,16 +1533,13 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) struct f2fs_sb_info *sbi = F2FS_SB(sb); struct f2fs_mount_info org_mount_opt; unsigned long old_sb_flags; - int err, active_logs; + int err; bool need_restart_gc = false; bool need_stop_gc = false; bool no_extent_cache = !test_opt(sbi, EXTENT_CACHE); -#ifdef CONFIG_F2FS_FAULT_INJECTION - struct f2fs_fault_info ffi = sbi->fault_info; -#endif + bool disable_checkpoint = test_opt(sbi, DISABLE_CHECKPOINT); + bool checkpoint_changed; #ifdef CONFIG_QUOTA - int s_jquota_fmt; - char *s_qf_names[MAXQUOTAS]; int i, j; #endif @@ -1163,21 +1549,21 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) */ org_mount_opt = sbi->mount_opt; old_sb_flags = sb->s_flags; - active_logs = sbi->active_logs; #ifdef CONFIG_QUOTA - s_jquota_fmt = sbi->s_jquota_fmt; + org_mount_opt.s_jquota_fmt = F2FS_OPTION(sbi).s_jquota_fmt; for (i = 0; i < MAXQUOTAS; i++) { - if (sbi->s_qf_names[i]) { - s_qf_names[i] = kstrdup(sbi->s_qf_names[i], - GFP_KERNEL); - if (!s_qf_names[i]) { + if (F2FS_OPTION(sbi).s_qf_names[i]) { + org_mount_opt.s_qf_names[i] = + kstrdup(F2FS_OPTION(sbi).s_qf_names[i], + GFP_KERNEL); + if (!org_mount_opt.s_qf_names[i]) { for (j = 0; j < i; j++) - kfree(s_qf_names[j]); + kvfree(org_mount_opt.s_qf_names[j]); return -ENOMEM; } } else { - s_qf_names[i] = NULL; + org_mount_opt.s_qf_names[i] = NULL; } } #endif @@ -1197,6 +1583,8 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) err = parse_options(sb, data); if (err) goto restore_opts; + checkpoint_changed = + disable_checkpoint != test_opt(sbi, DISABLE_CHECKPOINT); /* * Previous and new state of filesystem is RO, @@ -1205,16 +1593,23 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) if (f2fs_readonly(sb) && (*flags & MS_RDONLY)) goto skip; +#ifdef CONFIG_QUOTA if (!f2fs_readonly(sb) && (*flags & MS_RDONLY)) { err = dquot_suspend(sb, -1); if (err < 0) goto restore_opts; - } else { + } else if (f2fs_readonly(sb) && !(*flags & SB_RDONLY)) { /* dquot_resume needs RW */ sb->s_flags &= ~MS_RDONLY; - dquot_resume(sb, -1); + if (sb_any_quota_suspended(sb)) { + dquot_resume(sb, -1); + } else if (f2fs_sb_has_quota_ino(sbi)) { + err = f2fs_enable_quotas(sb); + if (err) + goto restore_opts; + } } - +#endif /* disallow enable/disable extent_cache dynamically */ if (no_extent_cache == !!test_opt(sbi, EXTENT_CACHE)) { err = -EINVAL; @@ -1223,6 +1618,13 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) goto restore_opts; } + if ((*flags & SB_RDONLY) && test_opt(sbi, DISABLE_CHECKPOINT)) { + err = -EINVAL; + f2fs_msg(sbi->sb, KERN_WARNING, + "disabling checkpoint not compatible with read-only"); + goto restore_opts; + } + /* * We stop the GC thread if FS is mounted as RO * or if background_gc = off is passed in mount @@ -1230,17 +1632,18 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) */ if ((*flags & MS_RDONLY) || !test_opt(sbi, BG_GC)) { if (sbi->gc_thread) { - stop_gc_thread(sbi); + f2fs_stop_gc_thread(sbi); need_restart_gc = true; } } else if (!sbi->gc_thread) { - err = start_gc_thread(sbi); + err = f2fs_start_gc_thread(sbi); if (err) goto restore_opts; need_stop_gc = true; } - if (*flags & MS_RDONLY) { + if (*flags & MS_RDONLY || + F2FS_OPTION(sbi).whint_mode != org_mount_opt.whint_mode) { writeback_inodes_sb(sb, WB_REASON_SYNC); sync_inodes_sb(sb); @@ -1250,15 +1653,25 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) clear_sbi_flag(sbi, SBI_IS_CLOSE); } + if (checkpoint_changed) { + if (test_opt(sbi, DISABLE_CHECKPOINT)) { + err = f2fs_disable_checkpoint(sbi); + if (err) + goto restore_gc; + } else { + f2fs_enable_checkpoint(sbi); + } + } + /* * We stop issue flush thread if FS is mounted as RO * or if flush_merge is not passed in mount option. */ if ((*flags & MS_RDONLY) || !test_opt(sbi, FLUSH_MERGE)) { clear_opt(sbi, FLUSH_MERGE); - destroy_flush_cmd_control(sbi, false); + f2fs_destroy_flush_cmd_control(sbi, false); } else { - err = create_flush_cmd_control(sbi); + err = f2fs_create_flush_cmd_control(sbi); if (err) goto restore_gc; } @@ -1266,35 +1679,33 @@ skip: #ifdef CONFIG_QUOTA /* Release old quota file names */ for (i = 0; i < MAXQUOTAS; i++) - kfree(s_qf_names[i]); + kvfree(org_mount_opt.s_qf_names[i]); #endif /* Update the POSIXACL Flag */ sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | (test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0); + limit_reserve_root(sbi); + *flags = (*flags & ~SB_LAZYTIME) | (sb->s_flags & SB_LAZYTIME); return 0; restore_gc: if (need_restart_gc) { - if (start_gc_thread(sbi)) + if (f2fs_start_gc_thread(sbi)) f2fs_msg(sbi->sb, KERN_WARNING, "background gc thread has stopped"); } else if (need_stop_gc) { - stop_gc_thread(sbi); + f2fs_stop_gc_thread(sbi); } restore_opts: #ifdef CONFIG_QUOTA - sbi->s_jquota_fmt = s_jquota_fmt; + F2FS_OPTION(sbi).s_jquota_fmt = org_mount_opt.s_jquota_fmt; for (i = 0; i < MAXQUOTAS; i++) { - kfree(sbi->s_qf_names[i]); - sbi->s_qf_names[i] = s_qf_names[i]; + kvfree(F2FS_OPTION(sbi).s_qf_names[i]); + F2FS_OPTION(sbi).s_qf_names[i] = org_mount_opt.s_qf_names[i]; } #endif sbi->mount_opt = org_mount_opt; - sbi->active_logs = active_logs; sb->s_flags = old_sb_flags; -#ifdef CONFIG_F2FS_FAULT_INJECTION - sbi->fault_info = ffi; -#endif return err; } @@ -1322,9 +1733,15 @@ static ssize_t f2fs_quota_read(struct super_block *sb, int type, char *data, while (toread > 0) { tocopy = min_t(unsigned long, sb->s_blocksize - offset, toread); repeat: - page = read_mapping_page(mapping, blkidx, NULL); - if (IS_ERR(page)) + page = read_cache_page_gfp(mapping, blkidx, GFP_NOFS); + if (IS_ERR(page)) { + if (PTR_ERR(page) == -ENOMEM) { + congestion_wait(BLK_RW_ASYNC, HZ/50); + goto repeat; + } + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); return PTR_ERR(page); + } lock_page(page); @@ -1334,6 +1751,7 @@ repeat: } if (unlikely(!PageUptodate(page))) { f2fs_put_page(page, 1); + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); return -EIO; } @@ -1367,11 +1785,17 @@ static ssize_t f2fs_quota_write(struct super_block *sb, int type, while (towrite > 0) { tocopy = min_t(unsigned long, sb->s_blocksize - offset, towrite); - +retry: err = a_ops->write_begin(NULL, mapping, off, tocopy, 0, &page, NULL); - if (unlikely(err)) + if (unlikely(err)) { + if (err == -ENOMEM) { + congestion_wait(BLK_RW_ASYNC, HZ/50); + goto retry; + } + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); break; + } kaddr = kmap_atomic(page); memcpy(kaddr + offset, data, tocopy); @@ -1388,8 +1812,7 @@ static ssize_t f2fs_quota_write(struct super_block *sb, int type, } if (len == towrite) - return 0; - inode->i_version++; + return err; inode->i_mtime = inode->i_ctime = current_time(inode); f2fs_mark_inode_dirty_sync(inode, false); return len - towrite; @@ -1407,54 +1830,157 @@ static qsize_t *f2fs_get_reserved_space(struct inode *inode) static int f2fs_quota_on_mount(struct f2fs_sb_info *sbi, int type) { - return dquot_quota_on_mount(sbi->sb, sbi->s_qf_names[type], - sbi->s_jquota_fmt, type); + if (is_set_ckpt_flags(sbi, CP_QUOTA_NEED_FSCK_FLAG)) { + f2fs_msg(sbi->sb, KERN_ERR, + "quota sysfile may be corrupted, skip loading it"); + return 0; + } + + return dquot_quota_on_mount(sbi->sb, F2FS_OPTION(sbi).s_qf_names[type], + F2FS_OPTION(sbi).s_jquota_fmt, type); } -void f2fs_enable_quota_files(struct f2fs_sb_info *sbi) +int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly) { - int i, ret; + int enabled = 0; + int i, err; + + if (f2fs_sb_has_quota_ino(sbi) && rdonly) { + err = f2fs_enable_quotas(sbi->sb); + if (err) { + f2fs_msg(sbi->sb, KERN_ERR, + "Cannot turn on quota_ino: %d", err); + return 0; + } + return 1; + } for (i = 0; i < MAXQUOTAS; i++) { - if (sbi->s_qf_names[i]) { - ret = f2fs_quota_on_mount(sbi, i); - if (ret < 0) - f2fs_msg(sbi->sb, KERN_ERR, - "Cannot turn on journaled " - "quota: error %d", ret); + if (F2FS_OPTION(sbi).s_qf_names[i]) { + err = f2fs_quota_on_mount(sbi, i); + if (!err) { + enabled = 1; + continue; + } + f2fs_msg(sbi->sb, KERN_ERR, + "Cannot turn on quotas: %d on %d", err, i); } } + return enabled; +} + +static int f2fs_quota_enable(struct super_block *sb, int type, int format_id, + unsigned int flags) +{ + struct inode *qf_inode; + unsigned long qf_inum; + int err; + + BUG_ON(!f2fs_sb_has_quota_ino(F2FS_SB(sb))); + + qf_inum = f2fs_qf_ino(sb, type); + if (!qf_inum) + return -EPERM; + + qf_inode = f2fs_iget(sb, qf_inum); + if (IS_ERR(qf_inode)) { + f2fs_msg(sb, KERN_ERR, + "Bad quota inode %u:%lu", type, qf_inum); + return PTR_ERR(qf_inode); + } + + /* Don't account quota for quota files to avoid recursion */ + qf_inode->i_flags |= S_NOQUOTA; + err = dquot_enable(qf_inode, type, format_id, flags); + iput(qf_inode); + return err; } -static int f2fs_quota_sync(struct super_block *sb, int type) +static int f2fs_enable_quotas(struct super_block *sb) { + int type, err = 0; + unsigned long qf_inum; + bool quota_mopt[MAXQUOTAS] = { + test_opt(F2FS_SB(sb), USRQUOTA), + test_opt(F2FS_SB(sb), GRPQUOTA), + test_opt(F2FS_SB(sb), PRJQUOTA), + }; + + if (is_set_ckpt_flags(F2FS_SB(sb), CP_QUOTA_NEED_FSCK_FLAG)) { + f2fs_msg(sb, KERN_ERR, + "quota file may be corrupted, skip loading it"); + return 0; + } + + sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE; + + for (type = 0; type < MAXQUOTAS; type++) { + qf_inum = f2fs_qf_ino(sb, type); + if (qf_inum) { + err = f2fs_quota_enable(sb, type, QFMT_VFS_V1, + DQUOT_USAGE_ENABLED | + (quota_mopt[type] ? DQUOT_LIMITS_ENABLED : 0)); + if (err) { + f2fs_msg(sb, KERN_ERR, + "Failed to enable quota tracking " + "(type=%d, err=%d). Please run " + "fsck to fix.", type, err); + for (type--; type >= 0; type--) + dquot_quota_off(sb, type); + set_sbi_flag(F2FS_SB(sb), + SBI_QUOTA_NEED_REPAIR); + return err; + } + } + } + return 0; +} + +int f2fs_quota_sync(struct super_block *sb, int type) +{ + struct f2fs_sb_info *sbi = F2FS_SB(sb); struct quota_info *dqopt = sb_dqopt(sb); int cnt; int ret; ret = dquot_writeback_dquots(sb, type); if (ret) - return ret; + goto out; /* * Now when everything is written we can discard the pagecache so * that userspace sees the changes. */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { + struct address_space *mapping; + if (type != -1 && cnt != type) continue; if (!sb_has_quota_active(sb, cnt)) continue; - ret = filemap_write_and_wait(dqopt->files[cnt]->i_mapping); + mapping = dqopt->files[cnt]->i_mapping; + + ret = filemap_fdatawrite(mapping); + if (ret) + goto out; + + /* if we are using journalled quota */ + if (is_journalled_quota(sbi)) + continue; + + ret = filemap_fdatawait(mapping); if (ret) - return ret; + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); inode_lock(dqopt->files[cnt]); truncate_inode_pages(&dqopt->files[cnt]->i_data, 0); inode_unlock(dqopt->files[cnt]); } - return 0; +out: + if (ret) + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); + return ret; } static int f2fs_quota_on(struct super_block *sb, int type, int format_id, @@ -1474,9 +2000,8 @@ static int f2fs_quota_on(struct super_block *sb, int type, int format_id, inode = d_inode(path->dentry); inode_lock(inode); - F2FS_I(inode)->i_flags |= FS_NOATIME_FL | FS_IMMUTABLE_FL; - inode_set_flags(inode, S_NOATIME | S_IMMUTABLE, - S_NOATIME | S_IMMUTABLE); + F2FS_I(inode)->i_flags |= F2FS_NOATIME_FL | F2FS_IMMUTABLE_FL; + f2fs_set_inode_flags(inode); inode_unlock(inode); f2fs_mark_inode_dirty_sync(inode, false); @@ -1496,12 +2021,12 @@ static int f2fs_quota_off(struct super_block *sb, int type) goto out_put; err = dquot_quota_off(sb, type); - if (err) + if (err || f2fs_sb_has_quota_ino(F2FS_SB(sb))) goto out_put; inode_lock(inode); - F2FS_I(inode)->i_flags &= ~(FS_NOATIME_FL | FS_IMMUTABLE_FL); - inode_set_flags(inode, 0, S_NOATIME | S_IMMUTABLE); + F2FS_I(inode)->i_flags &= ~(F2FS_NOATIME_FL | F2FS_IMMUTABLE_FL); + f2fs_set_inode_flags(inode); inode_unlock(inode); f2fs_mark_inode_dirty_sync(inode, false); out_put: @@ -1523,7 +2048,7 @@ void f2fs_quota_off_umount(struct super_block *sb) "Fail to turn off disk quota " "(type: %d, err: %d, ret:%d), Please " "run fsck to fix it.", type, err, ret); - set_sbi_flag(F2FS_SB(sb), SBI_NEED_FSCK); + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); } } /* @@ -1534,7 +2059,75 @@ void f2fs_quota_off_umount(struct super_block *sb) sync_filesystem(sb); } -int f2fs_get_projid(struct inode *inode, kprojid_t *projid) +static void f2fs_truncate_quota_inode_pages(struct super_block *sb) +{ + struct quota_info *dqopt = sb_dqopt(sb); + int type; + + for (type = 0; type < MAXQUOTAS; type++) { + if (!dqopt->files[type]) + continue; + f2fs_inode_synced(dqopt->files[type]); + } +} + +static int f2fs_dquot_commit(struct dquot *dquot) +{ + int ret; + + ret = dquot_commit(dquot); + if (ret < 0) + set_sbi_flag(F2FS_SB(dquot->dq_sb), SBI_QUOTA_NEED_REPAIR); + return ret; +} + +static int f2fs_dquot_acquire(struct dquot *dquot) +{ + int ret; + + ret = dquot_acquire(dquot); + if (ret < 0) + set_sbi_flag(F2FS_SB(dquot->dq_sb), SBI_QUOTA_NEED_REPAIR); + + return ret; +} + +static int f2fs_dquot_release(struct dquot *dquot) +{ + int ret; + + ret = dquot_release(dquot); + if (ret < 0) + set_sbi_flag(F2FS_SB(dquot->dq_sb), SBI_QUOTA_NEED_REPAIR); + return ret; +} + +static int f2fs_dquot_mark_dquot_dirty(struct dquot *dquot) +{ + struct super_block *sb = dquot->dq_sb; + struct f2fs_sb_info *sbi = F2FS_SB(sb); + int ret; + + ret = dquot_mark_dquot_dirty(dquot); + + /* if we are using journalled quota */ + if (is_journalled_quota(sbi)) + set_sbi_flag(sbi, SBI_QUOTA_NEED_FLUSH); + + return ret; +} + +static int f2fs_dquot_commit_info(struct super_block *sb, int type) +{ + int ret; + + ret = dquot_commit_info(sb, type); + if (ret < 0) + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); + return ret; +} + +static int f2fs_get_projid(struct inode *inode, kprojid_t *projid) { *projid = F2FS_I(inode)->i_projid; return 0; @@ -1542,11 +2135,11 @@ int f2fs_get_projid(struct inode *inode, kprojid_t *projid) static const struct dquot_operations f2fs_quota_operations = { .get_reserved_space = f2fs_get_reserved_space, - .write_dquot = dquot_commit, - .acquire_dquot = dquot_acquire, - .release_dquot = dquot_release, - .mark_dirty = dquot_mark_dquot_dirty, - .write_info = dquot_commit_info, + .write_dquot = f2fs_dquot_commit, + .acquire_dquot = f2fs_dquot_acquire, + .release_dquot = f2fs_dquot_release, + .mark_dirty = f2fs_dquot_mark_dquot_dirty, + .write_info = f2fs_dquot_commit_info, .alloc_dquot = dquot_alloc, .destroy_dquot = dquot_destroy, .get_projid = f2fs_get_projid, @@ -1564,6 +2157,11 @@ static const struct quotactl_ops f2fs_quotactl_ops = { .get_nextdqblk = dquot_get_next_dqblk, }; #else +int f2fs_quota_sync(struct super_block *sb, int type) +{ + return 0; +} + void f2fs_quota_off_umount(struct super_block *sb) { } @@ -1601,28 +2199,35 @@ static int f2fs_get_context(struct inode *inode, void *ctx, size_t len) static int f2fs_set_context(struct inode *inode, const void *ctx, size_t len, void *fs_data) { + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + + /* + * Encrypting the root directory is not allowed because fsck + * expects lost+found directory to exist and remain unencrypted + * if LOST_FOUND feature is enabled. + * + */ + if (f2fs_sb_has_lost_found(sbi) && + inode->i_ino == F2FS_ROOT_INO(sbi)) + return -EPERM; + return f2fs_setxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION, F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len, fs_data, XATTR_CREATE); } -static unsigned f2fs_max_namelen(struct inode *inode) +static bool f2fs_dummy_context(struct inode *inode) { - return S_ISLNK(inode->i_mode) ? - inode->i_sb->s_blocksize : F2FS_NAME_LEN; + return DUMMY_ENCRYPTION_ENABLED(F2FS_I_SB(inode)); } static const struct fscrypt_operations f2fs_cryptops = { .key_prefix = "f2fs:", .get_context = f2fs_get_context, .set_context = f2fs_set_context, - .is_encrypted = f2fs_encrypted_inode, + .dummy_context = f2fs_dummy_context, .empty_dir = f2fs_empty_dir, - .max_namelen = f2fs_max_namelen, -}; -#else -static const struct fscrypt_operations f2fs_cryptops = { - .is_encrypted = f2fs_encrypted_inode, + .max_namelen = F2FS_NAME_LEN, }; #endif @@ -1632,7 +2237,7 @@ static struct inode *f2fs_nfs_get_inode(struct super_block *sb, struct f2fs_sb_info *sbi = F2FS_SB(sb); struct inode *inode; - if (check_nid_range(sbi, ino)) + if (f2fs_check_nid_range(sbi, ino)) return ERR_PTR(-ESTALE); /* @@ -1678,7 +2283,7 @@ static loff_t max_file_blocks(void) /* * note: previously, result is equal to (DEF_ADDRS_PER_INODE - - * F2FS_INLINE_XATTR_ADDRS), but now f2fs try to reserve more + * DEFAULT_INLINE_XATTR_ADDRS), but now f2fs try to reserve more * space in inode.i_addr, it will be more safe to reassign * result as zero. */ @@ -1703,7 +2308,6 @@ static int __f2fs_commit_super(struct buffer_head *bh, lock_buffer(bh); if (super) memcpy(bh->b_data + F2FS_SUPER_OFFSET, super, sizeof(*super)); - set_buffer_uptodate(bh); set_buffer_dirty(bh); unlock_buffer(bh); @@ -1822,6 +2426,26 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, (bh->b_data + F2FS_SUPER_OFFSET); struct super_block *sb = sbi->sb; unsigned int blocksize; + size_t crc_offset = 0; + __u32 crc = 0; + + /* Check checksum_offset and crc in superblock */ + if (__F2FS_HAS_FEATURE(raw_super, F2FS_FEATURE_SB_CHKSUM)) { + crc_offset = le32_to_cpu(raw_super->checksum_offset); + if (crc_offset != + offsetof(struct f2fs_super_block, crc)) { + f2fs_msg(sb, KERN_INFO, + "Invalid SB checksum offset: %zu", + crc_offset); + return 1; + } + crc = le32_to_cpu(raw_super->crc); + if (!f2fs_crc_valid(sbi, crc, raw_super, crc_offset)) { + f2fs_msg(sb, KERN_INFO, + "Invalid SB checksum value: %u", crc); + return 1; + } + } if (le32_to_cpu(raw_super->magic) != F2FS_SUPER_MAGIC) { f2fs_msg(sb, KERN_INFO, @@ -1919,10 +2543,14 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, secs_per_zone, total_sections); return -EFSCORRUPTED; } - if (le32_to_cpu(raw_super->extension_count) > F2FS_MAX_EXTENSION) { + if (le32_to_cpu(raw_super->extension_count) > F2FS_MAX_EXTENSION || + raw_super->hot_ext_count > F2FS_MAX_EXTENSION || + (le32_to_cpu(raw_super->extension_count) + + raw_super->hot_ext_count) > F2FS_MAX_EXTENSION) { f2fs_msg(sb, KERN_INFO, - "Corrupted extension count (%u > %u)", + "Corrupted extension count (%u + %u > %u)", le32_to_cpu(raw_super->extension_count), + raw_super->hot_ext_count, F2FS_MAX_EXTENSION); return -EFSCORRUPTED; } @@ -1955,7 +2583,7 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, return 0; } -int sanity_check_ckpt(struct f2fs_sb_info *sbi) +int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi) { unsigned int total, fsmeta; struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); @@ -2080,7 +2708,7 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi) static void init_sb_info(struct f2fs_sb_info *sbi) { struct f2fs_super_block *raw_super = sbi->raw_super; - int i, j; + int i; sbi->log_sectors_per_block = le32_to_cpu(raw_super->log_sectors_per_block); @@ -2098,24 +2726,36 @@ static void init_sb_info(struct f2fs_sb_info *sbi) sbi->node_ino_num = le32_to_cpu(raw_super->node_ino); sbi->meta_ino_num = le32_to_cpu(raw_super->meta_ino); sbi->cur_victim_sec = NULL_SECNO; + sbi->next_victim_seg[BG_GC] = NULL_SEGNO; + sbi->next_victim_seg[FG_GC] = NULL_SEGNO; sbi->max_victim_search = DEF_MAX_VICTIM_SEARCH; + sbi->migration_granularity = sbi->segs_per_sec; sbi->dir_level = DEF_DIR_LEVEL; sbi->interval_time[CP_TIME] = DEF_CP_INTERVAL; sbi->interval_time[REQ_TIME] = DEF_IDLE_INTERVAL; + sbi->interval_time[DISCARD_TIME] = DEF_IDLE_INTERVAL; + sbi->interval_time[GC_TIME] = DEF_IDLE_INTERVAL; + sbi->interval_time[DISABLE_TIME] = DEF_DISABLE_INTERVAL; + sbi->interval_time[UMOUNT_DISCARD_TIMEOUT] = + DEF_UMOUNT_DISCARD_TIMEOUT; clear_sbi_flag(sbi, SBI_NEED_FSCK); for (i = 0; i < NR_COUNT_TYPE; i++) atomic_set(&sbi->nr_pages[i], 0); - atomic_set(&sbi->wb_sync_req, 0); + for (i = 0; i < META; i++) + atomic_set(&sbi->wb_sync_req[i], 0); INIT_LIST_HEAD(&sbi->s_list); mutex_init(&sbi->umount_mutex); - for (i = 0; i < NR_PAGE_TYPE - 1; i++) - for (j = HOT; j < NR_TEMP_TYPE; j++) - mutex_init(&sbi->wio_mutex[i][j]); + init_rwsem(&sbi->io_order_lock); spin_lock_init(&sbi->cp_lock); + + sbi->dirty_device = 0; + spin_lock_init(&sbi->dev_lock); + + init_rwsem(&sbi->sb_lock); } static int init_percpu_info(struct f2fs_sb_info *sbi) @@ -2145,7 +2785,7 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi) unsigned int n = 0; int err = -EIO; - if (!f2fs_sb_mounted_blkzoned(sbi->sb)) + if (!f2fs_sb_has_blkzoned(sbi)) return 0; if (sbi->blocks_per_blkz && sbi->blocks_per_blkz != @@ -2161,14 +2801,17 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi) if (nr_sectors & (bdev_zone_sectors(bdev) - 1)) FDEV(devi).nr_blkz++; - FDEV(devi).blkz_type = kmalloc(FDEV(devi).nr_blkz, GFP_KERNEL); + FDEV(devi).blkz_type = f2fs_kmalloc(sbi, FDEV(devi).nr_blkz, + GFP_KERNEL); if (!FDEV(devi).blkz_type) return -ENOMEM; #define F2FS_REPORT_NR_ZONES 4096 - zones = kcalloc(F2FS_REPORT_NR_ZONES, sizeof(struct blk_zone), - GFP_KERNEL); + zones = f2fs_kzalloc(sbi, + array_size(F2FS_REPORT_NR_ZONES, + sizeof(struct blk_zone)), + GFP_KERNEL); if (!zones) return -ENOMEM; @@ -2193,7 +2836,7 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi) } } - kfree(zones); + kvfree(zones); return err; } @@ -2253,7 +2896,7 @@ static int read_raw_super_block(struct f2fs_sb_info *sbi, /* No valid superblock */ if (!*raw_super) - kfree(super); + kvfree(super); else err = 0; @@ -2263,6 +2906,7 @@ static int read_raw_super_block(struct f2fs_sb_info *sbi, int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover) { struct buffer_head *bh; + __u32 crc = 0; int err; if ((recover && f2fs_readonly(sbi->sb)) || @@ -2271,8 +2915,15 @@ int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover) return -EROFS; } + /* we should update superblock crc here */ + if (!recover && f2fs_sb_has_sb_chksum(sbi)) { + crc = f2fs_crc32(sbi, F2FS_RAW_SUPER(sbi), + offsetof(struct f2fs_super_block, crc)); + F2FS_RAW_SUPER(sbi)->crc = cpu_to_le32(crc); + } + /* write back-up superblock first */ - bh = sb_getblk(sbi->sb, sbi->valid_super_block ? 0: 1); + bh = sb_bread(sbi->sb, sbi->valid_super_block ? 0 : 1); if (!bh) return -EIO; err = __f2fs_commit_super(bh, F2FS_RAW_SUPER(sbi)); @@ -2283,7 +2934,7 @@ int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover) return err; /* write current valid superblock */ - bh = sb_getblk(sbi->sb, sbi->valid_super_block); + bh = sb_bread(sbi->sb, sbi->valid_super_block); if (!bh) return -EIO; err = __f2fs_commit_super(bh, F2FS_RAW_SUPER(sbi)); @@ -2308,8 +2959,10 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) * Initialize multiple devices information, or single * zoned block device information. */ - sbi->devs = kcalloc(max_devices, sizeof(struct f2fs_dev_info), - GFP_KERNEL); + sbi->devs = f2fs_kzalloc(sbi, + array_size(max_devices, + sizeof(struct f2fs_dev_info)), + GFP_KERNEL); if (!sbi->devs) return -ENOMEM; @@ -2351,7 +3004,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) #ifdef CONFIG_BLK_DEV_ZONED if (bdev_zoned_model(FDEV(i).bdev) == BLK_ZONED_HM && - !f2fs_sb_mounted_blkzoned(sbi->sb)) { + !f2fs_sb_has_blkzoned(sbi)) { f2fs_msg(sbi->sb, KERN_ERR, "Zoned block device feature not enabled\n"); return -EINVAL; @@ -2385,16 +3038,31 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) return 0; } +static void f2fs_tuning_parameters(struct f2fs_sb_info *sbi) +{ + struct f2fs_sm_info *sm_i = SM_I(sbi); + + /* adjust parameters according to the volume size */ + if (sm_i->main_segments <= SMALL_VOLUME_SEGMENTS) { + F2FS_OPTION(sbi).alloc_mode = ALLOC_MODE_REUSE; + sm_i->dcc_info->discard_granularity = 1; + sm_i->ipu_policy = 1 << F2FS_IPU_FORCE; + } + + sbi->readdir_ra = 1; +} + static int f2fs_fill_super(struct super_block *sb, void *data, int silent) { struct f2fs_sb_info *sbi; struct f2fs_super_block *raw_super; struct inode *root; int err; - bool retry = true, need_fsck = false; + bool skip_recovery = false, need_fsck = false; char *options = NULL; int recovery, i, valid_super_block; struct curseg_info *seg_i; + int retry_cnt = 1; try_onemore: err = -EINVAL; @@ -2433,7 +3101,7 @@ try_onemore: sbi->raw_super = raw_super; /* precompute checksum seed for metadata */ - if (f2fs_sb_has_inode_chksum(sb)) + if (f2fs_sb_has_inode_chksum(sbi)) sbi->s_chksum_seed = f2fs_chksum(sbi, ~0, raw_super->uuid, sizeof(raw_super->uuid)); @@ -2443,7 +3111,7 @@ try_onemore: * devices, but mandatory for host-managed zoned block devices. */ #ifndef CONFIG_BLK_DEV_ZONED - if (f2fs_sb_mounted_blkzoned(sb)) { + if (f2fs_sb_has_blkzoned(sbi)) { f2fs_msg(sb, KERN_ERR, "Zoned block device support is not enabled\n"); err = -EOPNOTSUPP; @@ -2466,16 +3134,27 @@ try_onemore: sb->s_maxbytes = sbi->max_file_blocks << le32_to_cpu(raw_super->log_blocksize); sb->s_max_links = F2FS_LINK_MAX; - get_random_bytes(&sbi->s_next_generation, sizeof(u32)); #ifdef CONFIG_QUOTA sb->dq_op = &f2fs_quota_operations; - sb->s_qcop = &f2fs_quotactl_ops; + if (f2fs_sb_has_quota_ino(sbi)) + sb->s_qcop = &dquot_quotactl_sysfile_ops; + else + sb->s_qcop = &f2fs_quotactl_ops; sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ; + + if (f2fs_sb_has_quota_ino(sbi)) { + for (i = 0; i < MAXQUOTAS; i++) { + if (f2fs_qf_ino(sbi->sb, i)) + sbi->nquota_files++; + } + } #endif sb->s_op = &f2fs_sops; +#ifdef CONFIG_F2FS_FS_ENCRYPTION sb->s_cop = &f2fs_cryptops; +#endif sb->s_xattr = f2fs_xattr_handlers; sb->s_export_op = &f2fs_export_ops; sb->s_magic = F2FS_SUPER_MAGIC; @@ -2483,10 +3162,12 @@ try_onemore: sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | (test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0); memcpy(&sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid)); + sb->s_iflags |= SB_I_CGROUPWB; /* init f2fs-specific super block info */ sbi->valid_super_block = valid_super_block; mutex_init(&sbi->gc_mutex); + mutex_init(&sbi->writepages); mutex_init(&sbi->cp_mutex); init_rwsem(&sbi->node_write); init_rwsem(&sbi->node_change); @@ -2503,11 +3184,14 @@ try_onemore: int n = (i == META) ? 1: NR_TEMP_TYPE; int j; - sbi->write_io[i] = kmalloc(n * sizeof(struct f2fs_bio_info), - GFP_KERNEL); + sbi->write_io[i] = + f2fs_kmalloc(sbi, + array_size(n, + sizeof(struct f2fs_bio_info)), + GFP_KERNEL); if (!sbi->write_io[i]) { err = -ENOMEM; - goto free_options; + goto free_bio_info; } for (j = HOT; j < n; j++) { @@ -2525,14 +3209,14 @@ try_onemore: err = init_percpu_info(sbi); if (err) - goto free_options; + goto free_bio_info; if (F2FS_IO_SIZE(sbi) > 1) { sbi->write_io_dummy = mempool_create_page_pool(2 * (F2FS_IO_SIZE(sbi) - 1), 0); if (!sbi->write_io_dummy) { err = -ENOMEM; - goto free_options; + goto free_percpu; } } @@ -2544,12 +3228,19 @@ try_onemore: goto free_io_dummy; } - err = get_valid_checkpoint(sbi); + err = f2fs_get_valid_checkpoint(sbi); if (err) { f2fs_msg(sb, KERN_ERR, "Failed to get valid F2FS checkpoint"); goto free_meta_inode; } + if (__is_set_ckpt_flags(F2FS_CKPT(sbi), CP_QUOTA_NEED_FSCK_FLAG)) + set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + if (__is_set_ckpt_flags(F2FS_CKPT(sbi), CP_DISABLED_QUICK_FLAG)) { + set_sbi_flag(sbi, SBI_CP_DISABLED_QUICK); + sbi->interval_time[DISABLE_TIME] = DEF_DISABLE_QUICK_INTERVAL; + } + /* Initialize device list */ err = f2fs_scan_devices(sbi); if (err) { @@ -2566,24 +3257,28 @@ try_onemore: le64_to_cpu(sbi->ckpt->valid_block_count); sbi->last_valid_block_count = sbi->total_valid_block_count; sbi->reserved_blocks = 0; + sbi->current_reserved_blocks = 0; + limit_reserve_root(sbi); for (i = 0; i < NR_INODE_TYPE; i++) { INIT_LIST_HEAD(&sbi->inode_list[i]); spin_lock_init(&sbi->inode_lock[i]); } - init_extent_cache_info(sbi); + f2fs_init_extent_cache_info(sbi); + + f2fs_init_ino_entry_info(sbi); - init_ino_entry_info(sbi); + f2fs_init_fsync_node_info(sbi); /* setup f2fs internal modules */ - err = build_segment_manager(sbi); + err = f2fs_build_segment_manager(sbi); if (err) { f2fs_msg(sb, KERN_ERR, "Failed to initialize F2FS segment manager"); goto free_sm; } - err = build_node_manager(sbi); + err = f2fs_build_node_manager(sbi); if (err) { f2fs_msg(sb, KERN_ERR, "Failed to initialize F2FS node manager"); @@ -2601,22 +3296,20 @@ try_onemore: sbi->kbytes_written = le64_to_cpu(seg_i->journal->info.kbytes_written); - build_gc_manager(sbi); + f2fs_build_gc_manager(sbi); + + err = f2fs_build_stats(sbi); + if (err) + goto free_nm; /* get an inode for node space */ sbi->node_inode = f2fs_iget(sb, F2FS_NODE_INO(sbi)); if (IS_ERR(sbi->node_inode)) { f2fs_msg(sb, KERN_ERR, "Failed to read node inode"); err = PTR_ERR(sbi->node_inode); - goto free_nm; + goto free_stats; } - f2fs_join_shrinker(sbi); - - err = f2fs_build_stats(sbi); - if (err) - goto free_nm; - /* read root inode and dentry */ root = f2fs_iget(sb, F2FS_ROOT_INO(sbi)); if (IS_ERR(root)) { @@ -2624,7 +3317,8 @@ try_onemore: err = PTR_ERR(root); goto free_node_inode; } - if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) { + if (!S_ISDIR(root->i_mode) || !root->i_blocks || + !root->i_size || !root->i_nlink) { iput(root); err = -EINVAL; goto free_node_inode; @@ -2633,17 +3327,29 @@ try_onemore: sb->s_root = d_make_root(root); /* allocate root dentry */ if (!sb->s_root) { err = -ENOMEM; - goto free_root_inode; + goto free_node_inode; } err = f2fs_register_sysfs(sbi); if (err) goto free_root_inode; +#ifdef CONFIG_QUOTA + /* Enable quota usage during mount */ + if (f2fs_sb_has_quota_ino(sbi) && !f2fs_readonly(sb)) { + err = f2fs_enable_quotas(sb); + if (err) + f2fs_msg(sb, KERN_ERR, + "Cannot turn on quotas: error %d", err); + } +#endif /* if there are nt orphan nodes free them */ - err = recover_orphan_inodes(sbi); + err = f2fs_recover_orphan_inodes(sbi); if (err) - goto free_sysfs; + goto free_meta; + + if (unlikely(is_set_ckpt_flags(sbi, CP_DISABLED_FLAG))) + goto reset_checkpoint; /* recover fsynced data */ if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) { @@ -2660,41 +3366,51 @@ try_onemore: if (need_fsck) set_sbi_flag(sbi, SBI_NEED_FSCK); - if (!retry) - goto skip_recovery; + if (skip_recovery) + goto reset_checkpoint; - err = recover_fsync_data(sbi, false); + err = f2fs_recover_fsync_data(sbi, false); if (err < 0) { + if (err != -ENOMEM) + skip_recovery = true; need_fsck = true; f2fs_msg(sb, KERN_ERR, "Cannot recover all fsync data errno=%d", err); goto free_meta; } } else { - err = recover_fsync_data(sbi, true); + err = f2fs_recover_fsync_data(sbi, true); if (!f2fs_readonly(sb) && err > 0) { err = -EINVAL; f2fs_msg(sb, KERN_ERR, "Need to recover fsync data"); - goto free_sysfs; + goto free_meta; } } -skip_recovery: - /* recover_fsync_data() cleared this already */ +reset_checkpoint: + /* f2fs_recover_fsync_data() cleared this already */ clear_sbi_flag(sbi, SBI_POR_DOING); + if (test_opt(sbi, DISABLE_CHECKPOINT)) { + err = f2fs_disable_checkpoint(sbi); + if (err) + goto sync_free_meta; + } else if (is_set_ckpt_flags(sbi, CP_DISABLED_FLAG)) { + f2fs_enable_checkpoint(sbi); + } + /* * If filesystem is not mounted as read-only then * do start the gc_thread. */ if (test_opt(sbi, BG_GC) && !f2fs_readonly(sb)) { /* After POR, we can run background GC thread.*/ - err = start_gc_thread(sbi); + err = f2fs_start_gc_thread(sbi); if (err) - goto free_meta; + goto sync_free_meta; } - kfree(options); + kvfree(options); /* recover broken superblock */ if (recovery) { @@ -2704,65 +3420,82 @@ skip_recovery: sbi->valid_super_block ? 1 : 2, err); } + f2fs_join_shrinker(sbi); + + f2fs_tuning_parameters(sbi); + f2fs_msg(sbi->sb, KERN_NOTICE, "Mounted with checkpoint version = %llx", cur_cp_version(F2FS_CKPT(sbi))); f2fs_update_time(sbi, CP_TIME); f2fs_update_time(sbi, REQ_TIME); + clear_sbi_flag(sbi, SBI_CP_DISABLED_QUICK); return 0; +sync_free_meta: + /* safe to flush all the data */ + sync_filesystem(sbi->sb); + retry_cnt = 0; + free_meta: - f2fs_sync_inode_meta(sbi); +#ifdef CONFIG_QUOTA + f2fs_truncate_quota_inode_pages(sb); + if (f2fs_sb_has_quota_ino(sbi) && !f2fs_readonly(sb)) + f2fs_quota_off_umount(sbi->sb); +#endif /* - * Some dirty meta pages can be produced by recover_orphan_inodes() + * Some dirty meta pages can be produced by f2fs_recover_orphan_inodes() * failed by EIO. Then, iput(node_inode) can trigger balance_fs_bg() - * followed by write_checkpoint() through f2fs_write_node_pages(), which - * falls into an infinite loop in sync_meta_pages(). + * followed by f2fs_write_checkpoint() through f2fs_write_node_pages(), which + * falls into an infinite loop in f2fs_sync_meta_pages(). */ truncate_inode_pages_final(META_MAPPING(sbi)); -free_sysfs: + /* evict some inodes being cached by GC */ + evict_inodes(sb); f2fs_unregister_sysfs(sbi); free_root_inode: dput(sb->s_root); sb->s_root = NULL; free_node_inode: + f2fs_release_ino_entry(sbi, true); truncate_inode_pages_final(NODE_MAPPING(sbi)); - mutex_lock(&sbi->umount_mutex); - release_ino_entry(sbi, true); - f2fs_leave_shrinker(sbi); iput(sbi->node_inode); - mutex_unlock(&sbi->umount_mutex); + sbi->node_inode = NULL; +free_stats: f2fs_destroy_stats(sbi); free_nm: - destroy_node_manager(sbi); + f2fs_destroy_node_manager(sbi); free_sm: - destroy_segment_manager(sbi); + f2fs_destroy_segment_manager(sbi); free_devices: destroy_device_list(sbi); - kfree(sbi->ckpt); + kvfree(sbi->ckpt); free_meta_inode: make_bad_inode(sbi->meta_inode); iput(sbi->meta_inode); + sbi->meta_inode = NULL; free_io_dummy: mempool_destroy(sbi->write_io_dummy); -free_options: - for (i = 0; i < NR_PAGE_TYPE; i++) - kfree(sbi->write_io[i]); +free_percpu: destroy_percpu_info(sbi); +free_bio_info: + for (i = 0; i < NR_PAGE_TYPE; i++) + kvfree(sbi->write_io[i]); +free_options: #ifdef CONFIG_QUOTA for (i = 0; i < MAXQUOTAS; i++) - kfree(sbi->s_qf_names[i]); + kvfree(F2FS_OPTION(sbi).s_qf_names[i]); #endif - kfree(options); + kvfree(options); free_sb_buf: - kfree(raw_super); + kvfree(raw_super); free_sbi: if (sbi->s_chksum_driver) crypto_free_shash(sbi->s_chksum_driver); - kfree(sbi); + kvfree(sbi); /* give only one another chance */ - if (retry) { - retry = false; + if (retry_cnt > 0 && skip_recovery) { + retry_cnt--; shrink_dcache_sb(sb); goto try_onemore; } @@ -2778,9 +3511,22 @@ static struct dentry *f2fs_mount(struct file_system_type *fs_type, int flags, static void kill_f2fs_super(struct super_block *sb) { if (sb->s_root) { - set_sbi_flag(F2FS_SB(sb), SBI_IS_CLOSE); - stop_gc_thread(F2FS_SB(sb)); - stop_discard_thread(F2FS_SB(sb)); + struct f2fs_sb_info *sbi = F2FS_SB(sb); + + set_sbi_flag(sbi, SBI_IS_CLOSE); + f2fs_stop_gc_thread(sbi); + f2fs_stop_discard_thread(sbi); + + if (is_sbi_flag_set(sbi, SBI_IS_DIRTY) || + !is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) { + struct cp_control cpc = { + .reason = CP_UMOUNT, + }; + f2fs_write_checkpoint(sbi, &cpc); + } + + if (is_sbi_flag_set(sbi, SBI_IS_RECOVERED) && f2fs_readonly(sb)) + sb->s_flags &= ~SB_RDONLY; } kill_block_super(sb); } @@ -2829,16 +3575,16 @@ static int __init init_f2fs_fs(void) err = init_inodecache(); if (err) goto fail; - err = create_node_manager_caches(); + err = f2fs_create_node_manager_caches(); if (err) goto free_inodecache; - err = create_segment_manager_caches(); + err = f2fs_create_segment_manager_caches(); if (err) goto free_node_manager_caches; - err = create_checkpoint_caches(); + err = f2fs_create_checkpoint_caches(); if (err) goto free_segment_manager_caches; - err = create_extent_cache(); + err = f2fs_create_extent_cache(); if (err) goto free_checkpoint_caches; err = f2fs_init_sysfs(); @@ -2850,25 +3596,27 @@ static int __init init_f2fs_fs(void) err = register_filesystem(&f2fs_fs_type); if (err) goto free_shrinker; - err = f2fs_create_root_stats(); + f2fs_create_root_stats(); + err = f2fs_init_post_read_processing(); if (err) - goto free_filesystem; + goto free_root_stats; return 0; -free_filesystem: +free_root_stats: + f2fs_destroy_root_stats(); unregister_filesystem(&f2fs_fs_type); free_shrinker: unregister_shrinker(&f2fs_shrinker_info); free_sysfs: f2fs_exit_sysfs(); free_extent_cache: - destroy_extent_cache(); + f2fs_destroy_extent_cache(); free_checkpoint_caches: - destroy_checkpoint_caches(); + f2fs_destroy_checkpoint_caches(); free_segment_manager_caches: - destroy_segment_manager_caches(); + f2fs_destroy_segment_manager_caches(); free_node_manager_caches: - destroy_node_manager_caches(); + f2fs_destroy_node_manager_caches(); free_inodecache: destroy_inodecache(); fail: @@ -2877,14 +3625,15 @@ fail: static void __exit exit_f2fs_fs(void) { + f2fs_destroy_post_read_processing(); f2fs_destroy_root_stats(); unregister_filesystem(&f2fs_fs_type); unregister_shrinker(&f2fs_shrinker_info); f2fs_exit_sysfs(); - destroy_extent_cache(); - destroy_checkpoint_caches(); - destroy_segment_manager_caches(); - destroy_node_manager_caches(); + f2fs_destroy_extent_cache(); + f2fs_destroy_checkpoint_caches(); + f2fs_destroy_segment_manager_caches(); + f2fs_destroy_node_manager_caches(); destroy_inodecache(); f2fs_destroy_trace_ios(); } diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index a55919eec035..15dc128b83dd 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -1,13 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 /* * f2fs sysfs interface * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ * Copyright (c) 2017 Chao Yu <chao@kernel.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/compiler.h> #include <linux/proc_fs.h> @@ -31,7 +28,7 @@ enum { FAULT_INFO_RATE, /* struct f2fs_fault_info */ FAULT_INFO_TYPE, /* struct f2fs_fault_info */ #endif - RESERVED_BLOCKS, + RESERVED_BLOCKS, /* struct f2fs_sb_info */ }; struct f2fs_attr { @@ -59,11 +56,18 @@ static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type) #ifdef CONFIG_F2FS_FAULT_INJECTION else if (struct_type == FAULT_INFO_RATE || struct_type == FAULT_INFO_TYPE) - return (unsigned char *)&sbi->fault_info; + return (unsigned char *)&F2FS_OPTION(sbi).fault_info; #endif return NULL; } +static ssize_t dirty_segments_show(struct f2fs_attr *a, + struct f2fs_sb_info *sbi, char *buf) +{ + return snprintf(buf, PAGE_SIZE, "%llu\n", + (unsigned long long)(dirty_segments(sbi))); +} + static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { @@ -86,25 +90,46 @@ static ssize_t features_show(struct f2fs_attr *a, if (!sb->s_bdev->bd_part) return snprintf(buf, PAGE_SIZE, "0\n"); - if (f2fs_sb_has_crypto(sb)) + if (f2fs_sb_has_encrypt(sbi)) len += snprintf(buf, PAGE_SIZE - len, "%s", "encryption"); - if (f2fs_sb_mounted_blkzoned(sb)) + if (f2fs_sb_has_blkzoned(sbi)) len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", len ? ", " : "", "blkzoned"); - if (f2fs_sb_has_extra_attr(sb)) + if (f2fs_sb_has_extra_attr(sbi)) len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", len ? ", " : "", "extra_attr"); - if (f2fs_sb_has_project_quota(sb)) + if (f2fs_sb_has_project_quota(sbi)) len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", len ? ", " : "", "projquota"); - if (f2fs_sb_has_inode_chksum(sb)) + if (f2fs_sb_has_inode_chksum(sbi)) len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", len ? ", " : "", "inode_checksum"); + if (f2fs_sb_has_flexible_inline_xattr(sbi)) + len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", + len ? ", " : "", "flexible_inline_xattr"); + if (f2fs_sb_has_quota_ino(sbi)) + len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", + len ? ", " : "", "quota_ino"); + if (f2fs_sb_has_inode_crtime(sbi)) + len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", + len ? ", " : "", "inode_crtime"); + if (f2fs_sb_has_lost_found(sbi)) + len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", + len ? ", " : "", "lost_found"); + if (f2fs_sb_has_sb_chksum(sbi)) + len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", + len ? ", " : "", "sb_checksum"); len += snprintf(buf + len, PAGE_SIZE - len, "\n"); return len; } +static ssize_t current_reserved_blocks_show(struct f2fs_attr *a, + struct f2fs_sb_info *sbi, char *buf) +{ + return snprintf(buf, PAGE_SIZE, "%u\n", sbi->current_reserved_blocks); +} + static ssize_t f2fs_sbi_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { @@ -115,12 +140,33 @@ static ssize_t f2fs_sbi_show(struct f2fs_attr *a, if (!ptr) return -EINVAL; + if (!strcmp(a->attr.name, "extension_list")) { + __u8 (*extlist)[F2FS_EXTENSION_LEN] = + sbi->raw_super->extension_list; + int cold_count = le32_to_cpu(sbi->raw_super->extension_count); + int hot_count = sbi->raw_super->hot_ext_count; + int len = 0, i; + + len += snprintf(buf + len, PAGE_SIZE - len, + "cold file extension:\n"); + for (i = 0; i < cold_count; i++) + len += snprintf(buf + len, PAGE_SIZE - len, "%s\n", + extlist[i]); + + len += snprintf(buf + len, PAGE_SIZE - len, + "hot file extension:\n"); + for (i = cold_count; i < cold_count + hot_count; i++) + len += snprintf(buf + len, PAGE_SIZE - len, "%s\n", + extlist[i]); + return len; + } + ui = (unsigned int *)(ptr + a->offset); return snprintf(buf, PAGE_SIZE, "%u\n", *ui); } -static ssize_t f2fs_sbi_store(struct f2fs_attr *a, +static ssize_t __sbi_store(struct f2fs_attr *a, struct f2fs_sb_info *sbi, const char *buf, size_t count) { @@ -133,6 +179,41 @@ static ssize_t f2fs_sbi_store(struct f2fs_attr *a, if (!ptr) return -EINVAL; + if (!strcmp(a->attr.name, "extension_list")) { + const char *name = strim((char *)buf); + bool set = true, hot; + + if (!strncmp(name, "[h]", 3)) + hot = true; + else if (!strncmp(name, "[c]", 3)) + hot = false; + else + return -EINVAL; + + name += 3; + + if (*name == '!') { + name++; + set = false; + } + + if (strlen(name) >= F2FS_EXTENSION_LEN) + return -EINVAL; + + down_write(&sbi->sb_lock); + + ret = f2fs_update_extension_list(sbi, name, hot, set); + if (ret) + goto out; + + ret = f2fs_commit_super(sbi, false); + if (ret) + f2fs_update_extension_list(sbi, name, hot, !set); +out: + up_write(&sbi->sb_lock); + return ret ? ret : count; + } + ui = (unsigned int *)(ptr + a->offset); ret = kstrtoul(skip_spaces(buf), 0, &t); @@ -141,54 +222,96 @@ static ssize_t f2fs_sbi_store(struct f2fs_attr *a, #ifdef CONFIG_F2FS_FAULT_INJECTION if (a->struct_type == FAULT_INFO_TYPE && t >= (1 << FAULT_MAX)) return -EINVAL; + if (a->struct_type == FAULT_INFO_RATE && t >= UINT_MAX) + return -EINVAL; #endif if (a->struct_type == RESERVED_BLOCKS) { spin_lock(&sbi->stat_lock); - if ((unsigned long)sbi->total_valid_block_count + t > - (unsigned long)sbi->user_block_count) { + if (t > (unsigned long)(sbi->user_block_count - + F2FS_OPTION(sbi).root_reserved_blocks)) { spin_unlock(&sbi->stat_lock); return -EINVAL; } *ui = t; + sbi->current_reserved_blocks = min(sbi->reserved_blocks, + sbi->user_block_count - valid_user_blocks(sbi)); spin_unlock(&sbi->stat_lock); return count; } if (!strcmp(a->attr.name, "discard_granularity")) { - struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; - int i; - if (t == 0 || t > MAX_PLIST_NUM) return -EINVAL; if (t == *ui) return count; + *ui = t; + return count; + } - mutex_lock(&dcc->cmd_lock); - for (i = 0; i < MAX_PLIST_NUM; i++) { - if (i >= t - 1) - dcc->pend_list_tag[i] |= P_ACTIVE; - else - dcc->pend_list_tag[i] &= (~P_ACTIVE); - } - mutex_unlock(&dcc->cmd_lock); + if (!strcmp(a->attr.name, "migration_granularity")) { + if (t == 0 || t > sbi->segs_per_sec) + return -EINVAL; + } - *ui = t; + if (!strcmp(a->attr.name, "trim_sections")) + return -EINVAL; + + if (!strcmp(a->attr.name, "gc_urgent")) { + if (t >= 1) { + sbi->gc_mode = GC_URGENT; + if (sbi->gc_thread) { + sbi->gc_thread->gc_wake = 1; + wake_up_interruptible_all( + &sbi->gc_thread->gc_wait_queue_head); + wake_up_discard_thread(sbi, true); + } + } else { + sbi->gc_mode = GC_NORMAL; + } + return count; + } + if (!strcmp(a->attr.name, "gc_idle")) { + if (t == GC_IDLE_CB) + sbi->gc_mode = GC_IDLE_CB; + else if (t == GC_IDLE_GREEDY) + sbi->gc_mode = GC_IDLE_GREEDY; + else + sbi->gc_mode = GC_NORMAL; return count; } - *ui = t; - if (!strcmp(a->attr.name, "iostat_enable") && *ui == 0) - f2fs_reset_iostat(sbi); - if (!strcmp(a->attr.name, "gc_urgent") && t == 1 && sbi->gc_thread) { - sbi->gc_thread->gc_wake = 1; - wake_up_interruptible_all(&sbi->gc_thread->gc_wait_queue_head); - wake_up_discard_thread(sbi, true); + if (!strcmp(a->attr.name, "iostat_enable")) { + sbi->iostat_enable = !!t; + if (!sbi->iostat_enable) + f2fs_reset_iostat(sbi); + return count; } + *ui = (unsigned int)t; + return count; } +static ssize_t f2fs_sbi_store(struct f2fs_attr *a, + struct f2fs_sb_info *sbi, + const char *buf, size_t count) +{ + ssize_t ret; + bool gc_entry = (!strcmp(a->attr.name, "gc_urgent") || + a->struct_type == GC_THREAD); + + if (gc_entry) { + if (!down_read_trylock(&sbi->sb->s_umount)) + return -EAGAIN; + } + ret = __sbi_store(a, sbi, buf, count); + if (gc_entry) + up_read(&sbi->sb->s_umount); + + return ret; +} + static ssize_t f2fs_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { @@ -223,6 +346,11 @@ enum feat_id { FEAT_EXTRA_ATTR, FEAT_PROJECT_QUOTA, FEAT_INODE_CHECKSUM, + FEAT_FLEXIBLE_INLINE_XATTR, + FEAT_QUOTA_INO, + FEAT_INODE_CRTIME, + FEAT_LOST_FOUND, + FEAT_SB_CHECKSUM, }; static ssize_t f2fs_feature_show(struct f2fs_attr *a, @@ -235,6 +363,11 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a, case FEAT_EXTRA_ATTR: case FEAT_PROJECT_QUOTA: case FEAT_INODE_CHECKSUM: + case FEAT_FLEXIBLE_INLINE_XATTR: + case FEAT_QUOTA_INO: + case FEAT_INODE_CRTIME: + case FEAT_LOST_FOUND: + case FEAT_SB_CHECKSUM: return snprintf(buf, PAGE_SIZE, "supported\n"); } return 0; @@ -269,8 +402,8 @@ F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_urgent_sleep_time, F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_min_sleep_time, min_sleep_time); F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_max_sleep_time, max_sleep_time); F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time); -F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_idle, gc_idle); -F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_urgent, gc_urgent); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_idle, gc_mode); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_urgent, gc_mode); F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments); F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, max_small_discards, max_discards); F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, discard_granularity, discard_granularity); @@ -279,21 +412,34 @@ F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, batched_trim_sections, trim_sections); F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy); F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util); F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks); +F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_seq_blocks, min_seq_blocks); F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_hot_blocks, min_hot_blocks); +F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ssr_sections, min_ssr_sections); F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh); F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ra_nid_pages, ra_nid_pages); F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, dirty_nats_ratio, dirty_nats_ratio); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, migration_granularity, migration_granularity); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, interval_time[CP_TIME]); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, idle_interval, interval_time[REQ_TIME]); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, discard_idle_interval, + interval_time[DISCARD_TIME]); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_idle_interval, interval_time[GC_TIME]); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, + umount_discard_timeout, interval_time[UMOUNT_DISCARD_TIMEOUT]); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, iostat_enable, iostat_enable); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, readdir_ra, readdir_ra); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_pin_file_thresh, gc_pin_file_threshold); +F2FS_RW_ATTR(F2FS_SBI, f2fs_super_block, extension_list, extension_list); #ifdef CONFIG_F2FS_FAULT_INJECTION F2FS_RW_ATTR(FAULT_INFO_RATE, f2fs_fault_info, inject_rate, inject_rate); F2FS_RW_ATTR(FAULT_INFO_TYPE, f2fs_fault_info, inject_type, inject_type); #endif +F2FS_GENERAL_RO_ATTR(dirty_segments); F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes); F2FS_GENERAL_RO_ATTR(features); +F2FS_GENERAL_RO_ATTR(current_reserved_blocks); #ifdef CONFIG_F2FS_FS_ENCRYPTION F2FS_FEATURE_RO_ATTR(encryption, FEAT_CRYPTO); @@ -305,6 +451,11 @@ F2FS_FEATURE_RO_ATTR(atomic_write, FEAT_ATOMIC_WRITE); F2FS_FEATURE_RO_ATTR(extra_attr, FEAT_EXTRA_ATTR); F2FS_FEATURE_RO_ATTR(project_quota, FEAT_PROJECT_QUOTA); F2FS_FEATURE_RO_ATTR(inode_checksum, FEAT_INODE_CHECKSUM); +F2FS_FEATURE_RO_ATTR(flexible_inline_xattr, FEAT_FLEXIBLE_INLINE_XATTR); +F2FS_FEATURE_RO_ATTR(quota_ino, FEAT_QUOTA_INO); +F2FS_FEATURE_RO_ATTR(inode_crtime, FEAT_INODE_CRTIME); +F2FS_FEATURE_RO_ATTR(lost_found, FEAT_LOST_FOUND); +F2FS_FEATURE_RO_ATTR(sb_checksum, FEAT_SB_CHECKSUM); #define ATTR_LIST(name) (&f2fs_attr_##name.attr) static struct attribute *f2fs_attrs[] = { @@ -321,22 +472,33 @@ static struct attribute *f2fs_attrs[] = { ATTR_LIST(ipu_policy), ATTR_LIST(min_ipu_util), ATTR_LIST(min_fsync_blocks), + ATTR_LIST(min_seq_blocks), ATTR_LIST(min_hot_blocks), + ATTR_LIST(min_ssr_sections), ATTR_LIST(max_victim_search), + ATTR_LIST(migration_granularity), ATTR_LIST(dir_level), ATTR_LIST(ram_thresh), ATTR_LIST(ra_nid_pages), ATTR_LIST(dirty_nats_ratio), ATTR_LIST(cp_interval), ATTR_LIST(idle_interval), + ATTR_LIST(discard_idle_interval), + ATTR_LIST(gc_idle_interval), + ATTR_LIST(umount_discard_timeout), ATTR_LIST(iostat_enable), + ATTR_LIST(readdir_ra), + ATTR_LIST(gc_pin_file_thresh), + ATTR_LIST(extension_list), #ifdef CONFIG_F2FS_FAULT_INJECTION ATTR_LIST(inject_rate), ATTR_LIST(inject_type), #endif + ATTR_LIST(dirty_segments), ATTR_LIST(lifetime_write_kbytes), ATTR_LIST(features), ATTR_LIST(reserved_blocks), + ATTR_LIST(current_reserved_blocks), NULL, }; @@ -351,6 +513,11 @@ static struct attribute *f2fs_feat_attrs[] = { ATTR_LIST(extra_attr), ATTR_LIST(project_quota), ATTR_LIST(inode_checksum), + ATTR_LIST(flexible_inline_xattr), + ATTR_LIST(quota_ino), + ATTR_LIST(inode_crtime), + ATTR_LIST(lost_found), + ATTR_LIST(sb_checksum), NULL, }; @@ -478,6 +645,28 @@ static int __maybe_unused iostat_info_seq_show(struct seq_file *seq, return 0; } +static int __maybe_unused victim_bits_seq_show(struct seq_file *seq, + void *offset) +{ + struct super_block *sb = seq->private; + struct f2fs_sb_info *sbi = F2FS_SB(sb); + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + int i; + + seq_puts(seq, "format: victim_secmap bitmaps\n"); + + for (i = 0; i < MAIN_SECS(sbi); i++) { + if ((i % 10) == 0) + seq_printf(seq, "%-10d", i); + seq_printf(seq, "%d", test_bit(i, dirty_i->victim_secmap) ? 1 : 0); + if ((i % 10) == 9 || i == (MAIN_SECS(sbi) - 1)) + seq_putc(seq, '\n'); + else + seq_putc(seq, ' '); + } + return 0; +} + #define F2FS_PROC_FILE_DEF(_name) \ static int _name##_open_fs(struct inode *inode, struct file *file) \ { \ @@ -494,6 +683,7 @@ static const struct file_operations f2fs_seq_##_name##_fops = { \ F2FS_PROC_FILE_DEF(segment_info); F2FS_PROC_FILE_DEF(segment_bits); F2FS_PROC_FILE_DEF(iostat_info); +F2FS_PROC_FILE_DEF(victim_bits); int __init f2fs_init_sysfs(void) { @@ -549,6 +739,8 @@ int f2fs_register_sysfs(struct f2fs_sb_info *sbi) &f2fs_seq_segment_bits_fops, sb); proc_create_data("iostat_info", S_IRUGO, sbi->s_proc, &f2fs_seq_iostat_info_fops, sb); + proc_create_data("victim_bits", S_IRUGO, sbi->s_proc, + &f2fs_seq_victim_bits_fops, sb); } return 0; } @@ -559,6 +751,7 @@ void f2fs_unregister_sysfs(struct f2fs_sb_info *sbi) remove_proc_entry("iostat_info", sbi->s_proc); remove_proc_entry("segment_info", sbi->s_proc); remove_proc_entry("segment_bits", sbi->s_proc); + remove_proc_entry("victim_bits", sbi->s_proc); remove_proc_entry(sbi->sb->s_id, f2fs_proc_root); } kobject_del(&sbi->s_kobj); diff --git a/fs/f2fs/trace.c b/fs/f2fs/trace.c index 8ac1851a21c0..d0ab533a9ce8 100644 --- a/fs/f2fs/trace.c +++ b/fs/f2fs/trace.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * f2fs IO tracer * * Copyright (c) 2014 Motorola Mobility * Copyright (c) 2014 Jaegeuk Kim <jaegeuk@kernel.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> diff --git a/fs/f2fs/trace.h b/fs/f2fs/trace.h index 67db24ac1e85..e8075fc5b228 100644 --- a/fs/f2fs/trace.h +++ b/fs/f2fs/trace.h @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * f2fs IO tracer * * Copyright (c) 2014 Motorola Mobility * Copyright (c) 2014 Jaegeuk Kim <jaegeuk@kernel.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef __F2FS_TRACE_H__ #define __F2FS_TRACE_H__ diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 89c975126d4e..50fe20a03101 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/xattr.c * @@ -13,10 +14,6 @@ * suggestion of Luka Renko <luka.renko@hermes.si>. * xattr consolidation Copyright (c) 2004 James Morris <jmorris@redhat.com>, * Red Hat Inc. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/rwsem.h> #include <linux/f2fs_fs.h> @@ -37,9 +34,6 @@ static int f2fs_xattr_generic_get(const struct xattr_handler *handler, return -EOPNOTSUPP; break; case F2FS_XATTR_INDEX_TRUSTED: - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - break; case F2FS_XATTR_INDEX_SECURITY: break; default: @@ -62,9 +56,6 @@ static int f2fs_xattr_generic_set(const struct xattr_handler *handler, return -EOPNOTSUPP; break; case F2FS_XATTR_INDEX_TRUSTED: - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - break; case F2FS_XATTR_INDEX_SECURITY: break; default: @@ -100,12 +91,22 @@ static int f2fs_xattr_advise_set(const struct xattr_handler *handler, const char *name, const void *value, size_t size, int flags) { + unsigned char old_advise = F2FS_I(inode)->i_advise; + unsigned char new_advise; + if (!inode_owner_or_capable(inode)) return -EPERM; if (value == NULL) return -EINVAL; - F2FS_I(inode)->i_advise |= *(char *)value; + new_advise = *(char *)value; + if (new_advise & ~FADVISE_MODIFIABLE_BITS) + return -EINVAL; + + new_advise = new_advise & FADVISE_MODIFIABLE_BITS; + new_advise |= old_advise & ~FADVISE_MODIFIABLE_BITS; + + F2FS_I(inode)->i_advise = new_advise; f2fs_mark_inode_dirty_sync(inode, true); return 0; } @@ -222,17 +223,17 @@ static struct f2fs_xattr_entry *__find_xattr(void *base_addr, return entry; } -static struct f2fs_xattr_entry *__find_inline_xattr(void *base_addr, - void **last_addr, int index, - size_t len, const char *name) +static struct f2fs_xattr_entry *__find_inline_xattr(struct inode *inode, + void *base_addr, void **last_addr, int index, + size_t len, const char *name) { struct f2fs_xattr_entry *entry; - unsigned int inline_size = F2FS_INLINE_XATTR_ADDRS << 2; + unsigned int inline_size = inline_xattr_size(inode); + void *max_addr = base_addr + inline_size; list_for_each_xattr(entry, base_addr) { - if ((void *)entry + sizeof(__u32) > base_addr + inline_size || - (void *)XATTR_NEXT_ENTRY(entry) + sizeof(__u32) > - base_addr + inline_size) { + if ((void *)entry + sizeof(__u32) > max_addr || + (void *)XATTR_NEXT_ENTRY(entry) > max_addr) { *last_addr = entry; return NULL; } @@ -243,6 +244,13 @@ static struct f2fs_xattr_entry *__find_inline_xattr(void *base_addr, if (!memcmp(entry->e_name, name, len)) break; } + + /* inline xattr header or entry across max inline xattr size */ + if (IS_XATTR_LAST_ENTRY(entry) && + (void *)entry + sizeof(__u32) > max_addr) { + *last_addr = entry; + return NULL; + } return entry; } @@ -255,13 +263,13 @@ static int read_inline_xattr(struct inode *inode, struct page *ipage, void *inline_addr; if (ipage) { - inline_addr = inline_xattr_addr(ipage); + inline_addr = inline_xattr_addr(inode, ipage); } else { - page = get_node_page(sbi, inode->i_ino); + page = f2fs_get_node_page(sbi, inode->i_ino); if (IS_ERR(page)) return PTR_ERR(page); - inline_addr = inline_xattr_addr(page); + inline_addr = inline_xattr_addr(inode, page); } memcpy(txattr_addr, inline_addr, inline_size); f2fs_put_page(page, 1); @@ -278,7 +286,7 @@ static int read_xattr_block(struct inode *inode, void *txattr_addr) void *xattr_addr; /* The inode already has an extended attribute block. */ - xpage = get_node_page(sbi, xnid); + xpage = f2fs_get_node_page(sbi, xnid); if (IS_ERR(xpage)) return PTR_ERR(xpage); @@ -304,7 +312,7 @@ static int lookup_all_xattrs(struct inode *inode, struct page *ipage, return -ENODATA; *base_size = XATTR_SIZE(xnid, inode) + XATTR_PADDING_SIZE; - txattr_addr = kzalloc(*base_size, GFP_F2FS_ZERO); + txattr_addr = f2fs_kzalloc(F2FS_I_SB(inode), *base_size, GFP_NOFS); if (!txattr_addr) return -ENOMEM; @@ -316,7 +324,7 @@ static int lookup_all_xattrs(struct inode *inode, struct page *ipage, if (err) goto out; - *xe = __find_inline_xattr(txattr_addr, &last_addr, + *xe = __find_inline_xattr(inode, txattr_addr, &last_addr, index, len, name); if (*xe) { *base_size = inline_size; @@ -350,7 +358,7 @@ check: *base_addr = txattr_addr; return 0; out: - kzfree(txattr_addr); + kvfree(txattr_addr); return err; } @@ -364,8 +372,8 @@ static int read_all_xattrs(struct inode *inode, struct page *ipage, void *txattr_addr; int err; - txattr_addr = kzalloc(inline_size + size + XATTR_PADDING_SIZE, - GFP_F2FS_ZERO); + txattr_addr = f2fs_kzalloc(F2FS_I_SB(inode), + inline_size + size + XATTR_PADDING_SIZE, GFP_NOFS); if (!txattr_addr) return -ENOMEM; @@ -393,7 +401,7 @@ static int read_all_xattrs(struct inode *inode, struct page *ipage, *base_addr = txattr_addr; return 0; fail: - kzfree(txattr_addr); + kvfree(txattr_addr); return err; } @@ -402,70 +410,81 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize, { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); size_t inline_size = inline_xattr_size(inode); + struct page *in_page = NULL; void *xattr_addr; + void *inline_addr = NULL; struct page *xpage; nid_t new_nid = 0; - int err; + int err = 0; if (hsize > inline_size && !F2FS_I(inode)->i_xattr_nid) - if (!alloc_nid(sbi, &new_nid)) + if (!f2fs_alloc_nid(sbi, &new_nid)) return -ENOSPC; /* write to inline xattr */ if (inline_size) { - struct page *page = NULL; - void *inline_addr; - if (ipage) { - inline_addr = inline_xattr_addr(ipage); - f2fs_wait_on_page_writeback(ipage, NODE, true); - set_page_dirty(ipage); + inline_addr = inline_xattr_addr(inode, ipage); } else { - page = get_node_page(sbi, inode->i_ino); - if (IS_ERR(page)) { - alloc_nid_failed(sbi, new_nid); - return PTR_ERR(page); + in_page = f2fs_get_node_page(sbi, inode->i_ino); + if (IS_ERR(in_page)) { + f2fs_alloc_nid_failed(sbi, new_nid); + return PTR_ERR(in_page); } - inline_addr = inline_xattr_addr(page); - f2fs_wait_on_page_writeback(page, NODE, true); + inline_addr = inline_xattr_addr(inode, in_page); } - memcpy(inline_addr, txattr_addr, inline_size); - f2fs_put_page(page, 1); + f2fs_wait_on_page_writeback(ipage ? ipage : in_page, + NODE, true, true); /* no need to use xattr node block */ if (hsize <= inline_size) { - err = truncate_xattr_node(inode, ipage); - alloc_nid_failed(sbi, new_nid); - return err; + err = f2fs_truncate_xattr_node(inode); + f2fs_alloc_nid_failed(sbi, new_nid); + if (err) { + f2fs_put_page(in_page, 1); + return err; + } + memcpy(inline_addr, txattr_addr, inline_size); + set_page_dirty(ipage ? ipage : in_page); + goto in_page_out; } } /* write to xattr node block */ if (F2FS_I(inode)->i_xattr_nid) { - xpage = get_node_page(sbi, F2FS_I(inode)->i_xattr_nid); + xpage = f2fs_get_node_page(sbi, F2FS_I(inode)->i_xattr_nid); if (IS_ERR(xpage)) { - alloc_nid_failed(sbi, new_nid); - return PTR_ERR(xpage); + err = PTR_ERR(xpage); + f2fs_alloc_nid_failed(sbi, new_nid); + goto in_page_out; } f2fs_bug_on(sbi, new_nid); - f2fs_wait_on_page_writeback(xpage, NODE, true); + f2fs_wait_on_page_writeback(xpage, NODE, true, true); } else { struct dnode_of_data dn; set_new_dnode(&dn, inode, NULL, NULL, new_nid); - xpage = new_node_page(&dn, XATTR_NODE_OFFSET); + xpage = f2fs_new_node_page(&dn, XATTR_NODE_OFFSET); if (IS_ERR(xpage)) { - alloc_nid_failed(sbi, new_nid); - return PTR_ERR(xpage); + err = PTR_ERR(xpage); + f2fs_alloc_nid_failed(sbi, new_nid); + goto in_page_out; } - alloc_nid_done(sbi, new_nid); + f2fs_alloc_nid_done(sbi, new_nid); } - xattr_addr = page_address(xpage); + + if (inline_size) + memcpy(inline_addr, txattr_addr, inline_size); memcpy(xattr_addr, txattr_addr + inline_size, VALID_XATTR_BLOCK_SIZE); + + if (inline_size) + set_page_dirty(ipage ? ipage : in_page); set_page_dirty(xpage); - f2fs_put_page(xpage, 1); - return 0; + f2fs_put_page(xpage, 1); +in_page_out: + f2fs_put_page(in_page, 1); + return err; } int f2fs_getxattr(struct inode *inode, int index, const char *name, @@ -509,7 +528,7 @@ int f2fs_getxattr(struct inode *inode, int index, const char *name, } error = size; out: - kzfree(base_addr); + kvfree(base_addr); return error; } @@ -550,7 +569,7 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) if (!handler || (handler->list && !handler->list(dentry))) continue; - prefix = handler->prefix ?: handler->name; + prefix = xattr_prefix(handler); prefix_len = strlen(prefix); size = prefix_len + entry->e_name_len + 1; if (buffer) { @@ -568,7 +587,7 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) } error = buffer_size - rest; cleanup: - kzfree(base_addr); + kvfree(base_addr); return error; } @@ -628,7 +647,7 @@ static int __f2fs_setxattr(struct inode *inode, int index, goto exit; } - if (f2fs_xattr_value_same(here, value, size)) + if (value && f2fs_xattr_value_same(here, value, size)) goto exit; } else if ((flags & XATTR_REPLACE)) { error = -ENODATA; @@ -706,7 +725,7 @@ static int __f2fs_setxattr(struct inode *inode, int index, if (!error && S_ISDIR(inode->i_mode)) set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_CP); exit: - kzfree(base_addr); + kvfree(base_addr); return error; } @@ -717,7 +736,11 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name, struct f2fs_sb_info *sbi = F2FS_I_SB(inode); int err; - /* this case is only from init_inode_metadata */ + err = dquot_initialize(inode); + if (err) + return err; + + /* this case is only from f2fs_init_inode_metadata */ if (ipage) return __f2fs_setxattr(inode, index, name, value, size, ipage, flags); diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h index 2a4ecaf338ea..a90920e2f949 100644 --- a/fs/f2fs/xattr.h +++ b/fs/f2fs/xattr.h @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/xattr.h * @@ -9,10 +10,6 @@ * On-disk format of extended attributes for the ext2 filesystem. * * (C) 2001 Andreas Gruenbacher, <a.gruenbacher@computer.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef __F2FS_XATTR_H__ #define __F2FS_XATTR_H__ @@ -83,6 +80,12 @@ struct f2fs_xattr_entry { sizeof(struct f2fs_xattr_header) - \ sizeof(struct f2fs_xattr_entry)) +#define MAX_INLINE_XATTR_SIZE \ + (DEF_ADDRS_PER_INODE - \ + F2FS_TOTAL_EXTRA_ATTR_SIZE / sizeof(__le32) - \ + DEF_INLINE_RESERVED_SIZE - \ + MIN_INLINE_DENTRY_SIZE / sizeof(__le32)) + /* * On-disk structure of f2fs_xattr * We use inline xattrs space + 1 block for xattr. diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index fe907ff91eeb..9d391bae3325 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -2160,7 +2160,7 @@ void __mark_inode_dirty(struct inode *inode, int flags) (dirtytime && (inode->i_state & I_DIRTY_INODE))) return; - if (unlikely(block_dump)) + if (unlikely(block_dump > 1)) block_dump___mark_inode_dirty(inode); spin_lock(&inode->i_lock); diff --git a/fs/fs_struct.c b/fs/fs_struct.c index be0250788b73..987c95b950f6 100644 --- a/fs/fs_struct.c +++ b/fs/fs_struct.c @@ -45,6 +45,7 @@ void set_fs_pwd(struct fs_struct *fs, const struct path *path) if (old_pwd.dentry) path_put(&old_pwd); } +EXPORT_SYMBOL(set_fs_pwd); static inline int replace_path(struct path *p, const struct path *old, const struct path *new) { @@ -90,6 +91,7 @@ void free_fs_struct(struct fs_struct *fs) path_put(&fs->pwd); kmem_cache_free(fs_cachep, fs); } +EXPORT_SYMBOL(free_fs_struct); void exit_fs(struct task_struct *tsk) { @@ -128,6 +130,7 @@ struct fs_struct *copy_fs_struct(struct fs_struct *old) } return fs; } +EXPORT_SYMBOL_GPL(copy_fs_struct); int unshare_fs_struct(void) { diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index f580695b7bb9..bfd6353ef7fa 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -14,6 +14,7 @@ #include <linux/sched/signal.h> #include <linux/uio.h> #include <linux/miscdevice.h> +#include <linux/namei.h> #include <linux/pagemap.h> #include <linux/file.h> #include <linux/slab.h> @@ -21,6 +22,7 @@ #include <linux/swap.h> #include <linux/splice.h> #include <linux/sched.h> +#include <linux/freezer.h> MODULE_ALIAS_MISCDEV(FUSE_MINOR); MODULE_ALIAS("devname:fuse"); @@ -475,7 +477,9 @@ static void request_wait_answer(struct fuse_conn *fc, struct fuse_req *req) * Either request is already in userspace, or it was forced. * Wait it out. */ - wait_event(req->waitq, test_bit(FR_FINISHED, &req->flags)); + while (!test_bit(FR_FINISHED, &req->flags)) + wait_event_freezable(req->waitq, + test_bit(FR_FINISHED, &req->flags)); } static void __fuse_request_send(struct fuse_conn *fc, struct fuse_req *req) @@ -1916,6 +1920,12 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud, cs->move_pages = 0; err = copy_out_args(cs, &req->out, nbytes); + if (req->in.h.opcode == FUSE_CANONICAL_PATH) { + char *path = (char *)req->out.args[0].value; + + path[req->out.args[0].size - 1] = 0; + req->out.h.error = kern_path(path, 0, req->canonical_path); + } fuse_copy_finish(cs); spin_lock(&fpq->lock); diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 4d95a416fc36..d84819c9174c 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -263,6 +263,50 @@ invalid: goto out; } +/* + * Get the canonical path. Since we must translate to a path, this must be done + * in the context of the userspace daemon, however, the userspace daemon cannot + * look up paths on its own. Instead, we handle the lookup as a special case + * inside of the write request. + */ +static void fuse_dentry_canonical_path(const struct path *path, struct path *canonical_path) { + struct inode *inode = path->dentry->d_inode; + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_req *req; + int err; + char *path_name; + + req = fuse_get_req(fc, 1); + err = PTR_ERR(req); + if (IS_ERR(req)) + goto default_path; + + path_name = (char*)__get_free_page(GFP_KERNEL); + if (!path_name) { + fuse_put_request(fc, req); + goto default_path; + } + + req->in.h.opcode = FUSE_CANONICAL_PATH; + req->in.h.nodeid = get_node_id(inode); + req->in.numargs = 0; + req->out.numargs = 1; + req->out.args[0].size = PATH_MAX; + req->out.args[0].value = path_name; + req->canonical_path = canonical_path; + req->out.argvar = 1; + fuse_request_send(fc, req); + err = req->out.h.error; + fuse_put_request(fc, req); + free_page((unsigned long)path_name); + if (!err) + return; +default_path: + canonical_path->dentry = path->dentry; + canonical_path->mnt = path->mnt; + path_get(canonical_path); +} + static int invalid_nodeid(u64 nodeid) { return !nodeid || nodeid == FUSE_ROOT_ID; @@ -285,11 +329,13 @@ const struct dentry_operations fuse_dentry_operations = { .d_revalidate = fuse_dentry_revalidate, .d_init = fuse_dentry_init, .d_release = fuse_dentry_release, + .d_canonical_path = fuse_dentry_canonical_path, }; const struct dentry_operations fuse_root_dentry_operations = { .d_init = fuse_dentry_init, .d_release = fuse_dentry_release, + .d_canonical_path = fuse_dentry_canonical_path, }; int fuse_valid_type(int m) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 4238939af2fe..25458a78d24f 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -845,9 +845,9 @@ struct fuse_fill_data { unsigned nr_pages; }; -static int fuse_readpages_fill(void *_data, struct page *page) +static int fuse_readpages_fill(struct file *_data, struct page *page) { - struct fuse_fill_data *data = _data; + struct fuse_fill_data *data = (struct fuse_fill_data *)_data; struct fuse_req *req = data->req; struct inode *inode = data->inode; struct fuse_conn *fc = get_fuse_conn(inode); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 338aa5e266d6..74bae9703ee6 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -370,6 +370,9 @@ struct fuse_req { /** Inode used in the request or NULL */ struct inode *inode; + /** Path used for completing d_canonical_path */ + struct path *canonical_path; + /** AIO control block */ struct fuse_io_priv *io; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index ffb61787d77a..97138986f02b 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -31,7 +31,7 @@ static struct kmem_cache *fuse_inode_cachep; struct list_head fuse_conn_list; DEFINE_MUTEX(fuse_mutex); -static int set_global_limit(const char *val, struct kernel_param *kp); +static int set_global_limit(const char *val, const struct kernel_param *kp); unsigned max_user_bgreq; module_param_call(max_user_bgreq, set_global_limit, param_get_uint, @@ -826,7 +826,7 @@ static void sanitize_global_limit(unsigned *limit) *limit = (1 << 16) - 1; } -static int set_global_limit(const char *val, struct kernel_param *kp) +static int set_global_limit(const char *val, const struct kernel_param *kp) { int rv; diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 68ed06962537..ec3147ec0cd3 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -280,22 +280,6 @@ static int gfs2_write_jdata_pagevec(struct address_space *mapping, for(i = 0; i < nr_pages; i++) { struct page *page = pvec->pages[i]; - /* - * At this point, the page may be truncated or - * invalidated (changing page->mapping to NULL), or - * even swizzled back from swapper_space to tmpfs file - * mapping. However, page->index will not change - * because we have a reference on the page. - */ - if (page->index > end) { - /* - * can't be range_cyclic (1st pass) because - * end == -1 in that case. - */ - ret = 1; - break; - } - *done_index = page->index; lock_page(page); @@ -413,8 +397,8 @@ retry: tag_pages_for_writeback(mapping, index, end); done_index = index; while (!done && (index <= end)) { - nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag, - min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); + nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end, + tag); if (nr_pages == 0) break; @@ -523,7 +507,7 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct page *page) * */ -static int __gfs2_readpage(void *file, struct page *page) +static int __gfs2_readpage(struct file *file, struct page *page) { struct gfs2_inode *ip = GFS2_I(page->mapping->host); struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host); diff --git a/fs/inode.c b/fs/inode.c index 17172b616d22..e23b561dc880 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1802,7 +1802,7 @@ int dentry_needs_remove_privs(struct dentry *dentry) return mask; } -static int __remove_privs(struct dentry *dentry, int kill) +static int __remove_privs(struct vfsmount *mnt, struct dentry *dentry, int kill) { struct iattr newattrs; @@ -1811,7 +1811,7 @@ static int __remove_privs(struct dentry *dentry, int kill) * Note we call this on write, so notify_change will not * encounter any conflicting delegations: */ - return notify_change(dentry, &newattrs, NULL); + return notify_change2(mnt, dentry, &newattrs, NULL); } /* @@ -1838,7 +1838,7 @@ int file_remove_privs(struct file *file) if (kill < 0) return kill; if (kill) - error = __remove_privs(dentry, kill); + error = __remove_privs(file->f_path.mnt, dentry, kill); if (!error) inode_has_no_xattr(inode); diff --git a/fs/internal.h b/fs/internal.h index 48cee21b4f14..b4338451c1e4 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -90,9 +90,11 @@ extern struct file *get_empty_filp(void); * super.c */ extern int do_remount_sb(struct super_block *, int, void *, int); +extern int do_remount_sb2(struct vfsmount *, struct super_block *, int, + void *, int); extern bool trylock_super(struct super_block *sb); extern struct dentry *mount_fs(struct file_system_type *, - int, const char *, void *); + int, const char *, struct vfsmount *, void *); extern struct super_block *user_get_super(dev_t); /* diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index d8f49c412f50..d5b3cd692b29 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -832,26 +832,35 @@ void kernfs_drain_open_files(struct kernfs_node *kn) * to see if it supports poll (Neither 'poll' nor 'select' return * an appropriate error code). When in doubt, set a suitable timeout value. */ +unsigned int kernfs_generic_poll(struct kernfs_open_file *of, poll_table *wait) +{ + struct kernfs_node *kn = kernfs_dentry_node(of->file->f_path.dentry); + struct kernfs_open_node *on = kn->attr.open; + + poll_wait(of->file, &on->poll, wait); + + if (of->event != atomic_read(&on->event)) + return DEFAULT_POLLMASK|POLLERR|POLLPRI; + + return DEFAULT_POLLMASK; +} + static unsigned int kernfs_fop_poll(struct file *filp, poll_table *wait) { struct kernfs_open_file *of = kernfs_of(filp); struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry); - struct kernfs_open_node *on = kn->attr.open; + unsigned int ret; if (!kernfs_get_active(kn)) - goto trigger; + return DEFAULT_POLLMASK|POLLERR|POLLPRI; - poll_wait(filp, &on->poll, wait); + if (kn->attr.ops->poll) + ret = kn->attr.ops->poll(of, wait); + else + ret = kernfs_generic_poll(of, wait); kernfs_put_active(kn); - - if (of->event != atomic_read(&on->event)) - goto trigger; - - return DEFAULT_POLLMASK; - - trigger: - return DEFAULT_POLLMASK|POLLERR|POLLPRI; + return ret; } static void kernfs_notify_workfn(struct work_struct *work) diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 809cbccbad28..da2825a45ce8 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -614,7 +614,7 @@ static struct ctl_table nlm_sysctl_root[] = { */ #define param_set_min_max(name, type, which_strtol, min, max) \ -static int param_set_##name(const char *val, struct kernel_param *kp) \ +static int param_set_##name(const char *val, const struct kernel_param *kp) \ { \ char *endp; \ __typeof__(type) num = which_strtol(val, &endp, 0); \ diff --git a/fs/mpage.c b/fs/mpage.c index b7e7f570733a..93e3cf7bf27c 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -32,6 +32,14 @@ #include <linux/cleancache.h> #include "internal.h" +#define CREATE_TRACE_POINTS +#include <trace/events/android_fs.h> + +EXPORT_TRACEPOINT_SYMBOL(android_fs_datawrite_start); +EXPORT_TRACEPOINT_SYMBOL(android_fs_datawrite_end); +EXPORT_TRACEPOINT_SYMBOL(android_fs_dataread_start); +EXPORT_TRACEPOINT_SYMBOL(android_fs_dataread_end); + /* * I/O completion handler for multipage BIOs. * @@ -49,6 +57,16 @@ static void mpage_end_io(struct bio *bio) struct bio_vec *bv; int i; + if (trace_android_fs_dataread_end_enabled() && + (bio_data_dir(bio) == READ)) { + struct page *first_page = bio->bi_io_vec[0].bv_page; + + if (first_page != NULL) + trace_android_fs_dataread_end(first_page->mapping->host, + page_offset(first_page), + bio->bi_iter.bi_size); + } + bio_for_each_segment_all(bv, bio, i) { struct page *page = bv->bv_page; page_endio(page, op_is_write(bio_op(bio)), @@ -60,6 +78,24 @@ static void mpage_end_io(struct bio *bio) static struct bio *mpage_bio_submit(int op, int op_flags, struct bio *bio) { + if (trace_android_fs_dataread_start_enabled() && (op == REQ_OP_READ)) { + struct page *first_page = bio->bi_io_vec[0].bv_page; + + if (first_page != NULL) { + char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; + + path = android_fstrace_get_pathname(pathbuf, + MAX_TRACE_PATHBUF_LEN, + first_page->mapping->host); + trace_android_fs_dataread_start( + first_page->mapping->host, + page_offset(first_page), + bio->bi_iter.bi_size, + current->pid, + path, + current->comm); + } + } bio->bi_end_io = mpage_end_io; bio_set_op_attrs(bio, op, op_flags); guard_bio_eod(op, bio); diff --git a/fs/namei.c b/fs/namei.c index c5ebe33984f4..6c7beeeb95b3 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -377,9 +377,11 @@ EXPORT_SYMBOL(generic_permission); * flag in inode->i_opflags, that says "this has not special * permission function, use the fast case". */ -static inline int do_inode_permission(struct inode *inode, int mask) +static inline int do_inode_permission(struct vfsmount *mnt, struct inode *inode, int mask) { if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) { + if (likely(mnt && inode->i_op->permission2)) + return inode->i_op->permission2(mnt, inode, mask); if (likely(inode->i_op->permission)) return inode->i_op->permission(inode, mask); @@ -403,7 +405,7 @@ static inline int do_inode_permission(struct inode *inode, int mask) * This does not check for a read-only file system. You probably want * inode_permission(). */ -int __inode_permission(struct inode *inode, int mask) +int __inode_permission2(struct vfsmount *mnt, struct inode *inode, int mask) { int retval; @@ -423,7 +425,7 @@ int __inode_permission(struct inode *inode, int mask) return -EACCES; } - retval = do_inode_permission(inode, mask); + retval = do_inode_permission(mnt, inode, mask); if (retval) return retval; @@ -431,7 +433,14 @@ int __inode_permission(struct inode *inode, int mask) if (retval) return retval; - return security_inode_permission(inode, mask); + retval = security_inode_permission(inode, mask); + return retval; +} +EXPORT_SYMBOL(__inode_permission2); + +int __inode_permission(struct inode *inode, int mask) +{ + return __inode_permission2(NULL, inode, mask); } EXPORT_SYMBOL(__inode_permission); @@ -466,14 +475,20 @@ static int sb_permission(struct super_block *sb, struct inode *inode, int mask) * * When checking for MAY_APPEND, MAY_WRITE must also be set in @mask. */ -int inode_permission(struct inode *inode, int mask) +int inode_permission2(struct vfsmount *mnt, struct inode *inode, int mask) { int retval; retval = sb_permission(inode->i_sb, inode, mask); if (retval) return retval; - return __inode_permission(inode, mask); + return __inode_permission2(mnt, inode, mask); +} +EXPORT_SYMBOL(inode_permission2); + +int inode_permission(struct inode *inode, int mask) +{ + return inode_permission2(NULL, inode, mask); } EXPORT_SYMBOL(inode_permission); @@ -1708,13 +1723,13 @@ out: static inline int may_lookup(struct nameidata *nd) { if (nd->flags & LOOKUP_RCU) { - int err = inode_permission(nd->inode, MAY_EXEC|MAY_NOT_BLOCK); + int err = inode_permission2(nd->path.mnt, nd->inode, MAY_EXEC|MAY_NOT_BLOCK); if (err != -ECHILD) return err; if (unlazy_walk(nd)) return -ECHILD; } - return inode_permission(nd->inode, MAY_EXEC); + return inode_permission2(nd->path.mnt, nd->inode, MAY_EXEC); } static inline int handle_dots(struct nameidata *nd, int type) @@ -2490,6 +2505,7 @@ EXPORT_SYMBOL(vfs_path_lookup); /** * lookup_one_len - filesystem helper to lookup single pathname component * @name: pathname component to lookup + * @mnt: mount we are looking up on * @base: base directory to lookup from * @len: maximum length @len should be interpreted to * @@ -2498,7 +2514,7 @@ EXPORT_SYMBOL(vfs_path_lookup); * * The caller must hold base->i_mutex. */ -struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) +struct dentry *lookup_one_len2(const char *name, struct vfsmount *mnt, struct dentry *base, int len) { struct qstr this; unsigned int c; @@ -2532,12 +2548,18 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) return ERR_PTR(err); } - err = inode_permission(base->d_inode, MAY_EXEC); + err = inode_permission2(mnt, base->d_inode, MAY_EXEC); if (err) return ERR_PTR(err); return __lookup_hash(&this, base, 0); } +EXPORT_SYMBOL(lookup_one_len2); + +struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) +{ + return lookup_one_len2(name, NULL, base, len); +} EXPORT_SYMBOL(lookup_one_len); /** @@ -2815,7 +2837,7 @@ EXPORT_SYMBOL(__check_sticky); * 11. We don't allow removal of NFS sillyrenamed files; it's handled by * nfs_async_unlink(). */ -static int may_delete(struct inode *dir, struct dentry *victim, bool isdir) +static int may_delete(struct vfsmount *mnt, struct inode *dir, struct dentry *victim, bool isdir) { struct inode *inode = d_backing_inode(victim); int error; @@ -2827,7 +2849,7 @@ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir) BUG_ON(victim->d_parent->d_inode != dir); audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE); - error = inode_permission(dir, MAY_WRITE | MAY_EXEC); + error = inode_permission2(mnt, dir, MAY_WRITE | MAY_EXEC); if (error) return error; if (IS_APPEND(dir)) @@ -2859,7 +2881,7 @@ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir) * 4. We should have write and exec permissions on dir * 5. We can't do it if dir is immutable (done in permission()) */ -static inline int may_create(struct inode *dir, struct dentry *child) +static inline int may_create(struct vfsmount *mnt, struct inode *dir, struct dentry *child) { struct user_namespace *s_user_ns; audit_inode_child(dir, child, AUDIT_TYPE_CHILD_CREATE); @@ -2871,7 +2893,7 @@ static inline int may_create(struct inode *dir, struct dentry *child) if (!kuid_has_mapping(s_user_ns, current_fsuid()) || !kgid_has_mapping(s_user_ns, current_fsgid())) return -EOVERFLOW; - return inode_permission(dir, MAY_WRITE | MAY_EXEC); + return inode_permission2(mnt, dir, MAY_WRITE | MAY_EXEC); } /* @@ -2918,10 +2940,10 @@ void unlock_rename(struct dentry *p1, struct dentry *p2) } EXPORT_SYMBOL(unlock_rename); -int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, - bool want_excl) +int vfs_create2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry, + umode_t mode, bool want_excl) { - int error = may_create(dir, dentry); + int error = may_create(mnt, dir, dentry); if (error) return error; @@ -2937,6 +2959,13 @@ int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, fsnotify_create(dir, dentry); return error; } +EXPORT_SYMBOL(vfs_create2); + +int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, + bool want_excl) +{ + return vfs_create2(NULL, dir, dentry, mode, want_excl); +} EXPORT_SYMBOL(vfs_create); bool may_open_dev(const struct path *path) @@ -2948,6 +2977,7 @@ bool may_open_dev(const struct path *path) static int may_open(const struct path *path, int acc_mode, int flag) { struct dentry *dentry = path->dentry; + struct vfsmount *mnt = path->mnt; struct inode *inode = dentry->d_inode; int error; @@ -2972,7 +3002,7 @@ static int may_open(const struct path *path, int acc_mode, int flag) break; } - error = inode_permission(inode, MAY_OPEN | acc_mode); + error = inode_permission2(mnt, inode, MAY_OPEN | acc_mode); if (error) return error; @@ -3007,7 +3037,7 @@ static int handle_truncate(struct file *filp) if (!error) error = security_path_truncate(path); if (!error) { - error = do_truncate(path->dentry, 0, + error = do_truncate2(path->mnt, path->dentry, 0, ATTR_MTIME|ATTR_CTIME|ATTR_OPEN, filp); } @@ -3034,7 +3064,7 @@ static int may_o_create(const struct path *dir, struct dentry *dentry, umode_t m !kgid_has_mapping(s_user_ns, current_fsgid())) return -EOVERFLOW; - error = inode_permission(dir->dentry->d_inode, MAY_WRITE | MAY_EXEC); + error = inode_permission2(dir->mnt, dir->dentry->d_inode, MAY_WRITE | MAY_EXEC); if (error) return error; @@ -3455,7 +3485,8 @@ struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag) int error; /* we want directory to be writable */ - error = inode_permission(dir, MAY_WRITE | MAY_EXEC); + error = inode_permission2(ERR_PTR(-EOPNOTSUPP), dir, + MAY_WRITE | MAY_EXEC); if (error) goto out_err; error = -EOPNOTSUPP; @@ -3733,9 +3764,9 @@ inline struct dentry *user_path_create(int dfd, const char __user *pathname, } EXPORT_SYMBOL(user_path_create); -int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) +int vfs_mknod2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { - int error = may_create(dir, dentry); + int error = may_create(mnt, dir, dentry); if (error) return error; @@ -3759,6 +3790,12 @@ int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) fsnotify_create(dir, dentry); return error; } +EXPORT_SYMBOL(vfs_mknod2); + +int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) +{ + return vfs_mknod2(NULL, dir, dentry, mode, dev); +} EXPORT_SYMBOL(vfs_mknod); static int may_mknod(umode_t mode) @@ -3801,12 +3838,12 @@ retry: goto out; switch (mode & S_IFMT) { case 0: case S_IFREG: - error = vfs_create(path.dentry->d_inode,dentry,mode,true); + error = vfs_create2(path.mnt, path.dentry->d_inode,dentry,mode,true); if (!error) ima_post_path_mknod(dentry); break; case S_IFCHR: case S_IFBLK: - error = vfs_mknod(path.dentry->d_inode,dentry,mode, + error = vfs_mknod2(path.mnt, path.dentry->d_inode,dentry,mode, new_decode_dev(dev)); break; case S_IFIFO: case S_IFSOCK: @@ -3827,9 +3864,9 @@ SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, d return sys_mknodat(AT_FDCWD, filename, mode, dev); } -int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +int vfs_mkdir2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry, umode_t mode) { - int error = may_create(dir, dentry); + int error = may_create(mnt, dir, dentry); unsigned max_links = dir->i_sb->s_max_links; if (error) @@ -3851,6 +3888,12 @@ int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) fsnotify_mkdir(dir, dentry); return error; } +EXPORT_SYMBOL(vfs_mkdir2); + +int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + return vfs_mkdir2(NULL, dir, dentry, mode); +} EXPORT_SYMBOL(vfs_mkdir); SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode) @@ -3869,7 +3912,7 @@ retry: mode &= ~current_umask(); error = security_path_mkdir(&path, dentry, mode); if (!error) - error = vfs_mkdir(path.dentry->d_inode, dentry, mode); + error = vfs_mkdir2(path.mnt, path.dentry->d_inode, dentry, mode); done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; @@ -3883,9 +3926,9 @@ SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode) return sys_mkdirat(AT_FDCWD, pathname, mode); } -int vfs_rmdir(struct inode *dir, struct dentry *dentry) +int vfs_rmdir2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry) { - int error = may_delete(dir, dentry, 1); + int error = may_delete(mnt, dir, dentry, 1); if (error) return error; @@ -3920,6 +3963,12 @@ out: d_delete(dentry); return error; } +EXPORT_SYMBOL(vfs_rmdir2); + +int vfs_rmdir(struct inode *dir, struct dentry *dentry) +{ + return vfs_rmdir2(NULL, dir, dentry); +} EXPORT_SYMBOL(vfs_rmdir); static long do_rmdir(int dfd, const char __user *pathname) @@ -3965,7 +4014,7 @@ retry: error = security_path_rmdir(&path, dentry); if (error) goto exit3; - error = vfs_rmdir(path.dentry->d_inode, dentry); + error = vfs_rmdir2(path.mnt, path.dentry->d_inode, dentry); exit3: dput(dentry); exit2: @@ -4004,10 +4053,10 @@ SYSCALL_DEFINE1(rmdir, const char __user *, pathname) * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. */ -int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegated_inode) +int vfs_unlink2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry, struct inode **delegated_inode) { struct inode *target = dentry->d_inode; - int error = may_delete(dir, dentry, 0); + int error = may_delete(mnt, dir, dentry, 0); if (error) return error; @@ -4042,6 +4091,12 @@ out: return error; } +EXPORT_SYMBOL(vfs_unlink2); + +int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegated_inode) +{ + return vfs_unlink2(NULL, dir, dentry, delegated_inode); +} EXPORT_SYMBOL(vfs_unlink); /* @@ -4089,7 +4144,7 @@ retry_deleg: error = security_path_unlink(&path, dentry); if (error) goto exit2; - error = vfs_unlink(path.dentry->d_inode, dentry, &delegated_inode); + error = vfs_unlink2(path.mnt, path.dentry->d_inode, dentry, &delegated_inode); exit2: dput(dentry); } @@ -4139,9 +4194,9 @@ SYSCALL_DEFINE1(unlink, const char __user *, pathname) return do_unlinkat(AT_FDCWD, pathname); } -int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname) +int vfs_symlink2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry, const char *oldname) { - int error = may_create(dir, dentry); + int error = may_create(mnt, dir, dentry); if (error) return error; @@ -4158,6 +4213,12 @@ int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname) fsnotify_create(dir, dentry); return error; } +EXPORT_SYMBOL(vfs_symlink2); + +int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname) +{ + return vfs_symlink2(NULL, dir, dentry, oldname); +} EXPORT_SYMBOL(vfs_symlink); SYSCALL_DEFINE3(symlinkat, const char __user *, oldname, @@ -4180,7 +4241,7 @@ retry: error = security_path_symlink(&path, dentry, from->name); if (!error) - error = vfs_symlink(path.dentry->d_inode, dentry, from->name); + error = vfs_symlink2(path.mnt, path.dentry->d_inode, dentry, from->name); done_path_create(&path, dentry); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; @@ -4215,7 +4276,7 @@ SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newn * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. */ -int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode) +int vfs_link2(struct vfsmount *mnt, struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode) { struct inode *inode = old_dentry->d_inode; unsigned max_links = dir->i_sb->s_max_links; @@ -4224,7 +4285,7 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de if (!inode) return -ENOENT; - error = may_create(dir, new_dentry); + error = may_create(mnt, dir, new_dentry); if (error) return error; @@ -4274,6 +4335,12 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de fsnotify_link(dir, inode, new_dentry); return error; } +EXPORT_SYMBOL(vfs_link2); + +int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode) +{ + return vfs_link2(NULL, old_dentry, dir, new_dentry, delegated_inode); +} EXPORT_SYMBOL(vfs_link); /* @@ -4329,7 +4396,7 @@ retry: error = security_path_link(old_path.dentry, &new_path, new_dentry); if (error) goto out_dput; - error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry, &delegated_inode); + error = vfs_link2(old_path.mnt, old_path.dentry, new_path.dentry->d_inode, new_dentry, &delegated_inode); out_dput: done_path_create(&new_path, new_dentry); if (delegated_inode) { @@ -4405,7 +4472,8 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname * ->i_mutex on parents, which works but leads to some truly excessive * locking]. */ -int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, +int vfs_rename2(struct vfsmount *mnt, + struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, struct inode **delegated_inode, unsigned int flags) { @@ -4420,19 +4488,19 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (source == target) return 0; - error = may_delete(old_dir, old_dentry, is_dir); + error = may_delete(mnt, old_dir, old_dentry, is_dir); if (error) return error; if (!target) { - error = may_create(new_dir, new_dentry); + error = may_create(mnt, new_dir, new_dentry); } else { new_is_dir = d_is_dir(new_dentry); if (!(flags & RENAME_EXCHANGE)) - error = may_delete(new_dir, new_dentry, is_dir); + error = may_delete(mnt, new_dir, new_dentry, is_dir); else - error = may_delete(new_dir, new_dentry, new_is_dir); + error = may_delete(mnt, new_dir, new_dentry, new_is_dir); } if (error) return error; @@ -4446,12 +4514,12 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, */ if (new_dir != old_dir) { if (is_dir) { - error = inode_permission(source, MAY_WRITE); + error = inode_permission2(mnt, source, MAY_WRITE); if (error) return error; } if ((flags & RENAME_EXCHANGE) && new_is_dir) { - error = inode_permission(target, MAY_WRITE); + error = inode_permission2(mnt, target, MAY_WRITE); if (error) return error; } @@ -4528,6 +4596,14 @@ out: return error; } +EXPORT_SYMBOL(vfs_rename2); + +int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, + struct inode **delegated_inode, unsigned int flags) +{ + return vfs_rename2(NULL, old_dir, old_dentry, new_dir, new_dentry, delegated_inode, flags); +} EXPORT_SYMBOL(vfs_rename); SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname, @@ -4641,7 +4717,7 @@ retry_deleg: &new_path, new_dentry, flags); if (error) goto exit5; - error = vfs_rename(old_path.dentry->d_inode, old_dentry, + error = vfs_rename2(old_path.mnt, old_path.dentry->d_inode, old_dentry, new_path.dentry->d_inode, new_dentry, &delegated_inode, flags); exit5: @@ -4686,7 +4762,7 @@ SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newna int vfs_whiteout(struct inode *dir, struct dentry *dentry) { - int error = may_create(dir, dentry); + int error = may_create(NULL, dir, dentry); if (error) return error; diff --git a/fs/namespace.c b/fs/namespace.c index c8acc60c456d..15eceaa585ac 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -226,6 +226,7 @@ static struct mount *alloc_vfsmnt(const char *name) mnt->mnt_count = 1; mnt->mnt_writers = 0; #endif + mnt->mnt.data = NULL; INIT_HLIST_NODE(&mnt->mnt_hash); INIT_LIST_HEAD(&mnt->mnt_child); @@ -637,6 +638,7 @@ int sb_prepare_remount_readonly(struct super_block *sb) static void free_vfsmnt(struct mount *mnt) { + kfree(mnt->mnt.data); kfree_const(mnt->mnt_devname); #ifdef CONFIG_SMP free_percpu(mnt->mnt_pcp); @@ -1040,10 +1042,18 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void if (!mnt) return ERR_PTR(-ENOMEM); + if (type->alloc_mnt_data) { + mnt->mnt.data = type->alloc_mnt_data(); + if (!mnt->mnt.data) { + mnt_free_id(mnt); + free_vfsmnt(mnt); + return ERR_PTR(-ENOMEM); + } + } if (flags & SB_KERNMOUNT) mnt->mnt.mnt_flags = MNT_INTERNAL; - root = mount_fs(type, flags, name, data); + root = mount_fs(type, flags, name, &mnt->mnt, data); if (IS_ERR(root)) { mnt_free_id(mnt); free_vfsmnt(mnt); @@ -1087,6 +1097,14 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root, if (!mnt) return ERR_PTR(-ENOMEM); + if (sb->s_op->clone_mnt_data) { + mnt->mnt.data = sb->s_op->clone_mnt_data(old->mnt.data); + if (!mnt->mnt.data) { + err = -ENOMEM; + goto out_free; + } + } + if (flag & (CL_SLAVE | CL_PRIVATE | CL_SHARED_TO_SLAVE)) mnt->mnt_group_id = 0; /* not a peer of original */ else @@ -2366,8 +2384,14 @@ static int do_remount(struct path *path, int ms_flags, int sb_flags, err = change_mount_flags(path->mnt, ms_flags); else if (!capable(CAP_SYS_ADMIN)) err = -EPERM; - else - err = do_remount_sb(sb, sb_flags, data, 0); + else { + err = do_remount_sb2(path->mnt, sb, sb_flags, data, 0); + namespace_lock(); + lock_mount_hash(); + propagate_remount(mnt); + unlock_mount_hash(); + namespace_unlock(); + } if (!err) { lock_mount_hash(); mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK; diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 673d89bb817e..7dba2594421e 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -683,8 +683,9 @@ out: * We only need to convert from xdr once so future lookups are much simpler */ static -int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page) +int nfs_readdir_filler(struct file *file, struct page* page) { + nfs_readdir_descriptor_t *desc = (nfs_readdir_descriptor_t *)file; struct inode *inode = file_inode(desc->file); int ret; @@ -716,7 +717,7 @@ static struct page *get_cache_page(nfs_readdir_descriptor_t *desc) { return read_cache_page(desc->file->f_mapping, - desc->page_index, (filler_t *)nfs_readdir_filler, desc); + desc->page_index, nfs_readdir_filler, desc); } /* diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 09d5c282f50e..afd447ac457e 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -354,7 +354,7 @@ struct nfs_readdesc { }; static int -readpage_async_filler(void *data, struct page *page) +readpage_async_filler(struct file *data, struct page *page) { struct nfs_readdesc *desc = (struct nfs_readdesc *)data; struct nfs_page *new; diff --git a/fs/nfs/symlink.c b/fs/nfs/symlink.c index 06eb44b47885..220d5ba2bd9b 100644 --- a/fs/nfs/symlink.c +++ b/fs/nfs/symlink.c @@ -26,8 +26,9 @@ * and straight-forward than readdir caching. */ -static int nfs_symlink_filler(struct inode *inode, struct page *page) +static int nfs_symlink_filler(struct file *file, struct page *page) { + struct inode *inode = (struct inode *)file; int error; error = NFS_PROTO(inode)->readlink(inode, page, 0, PAGE_SIZE); @@ -66,7 +67,7 @@ static const char *nfs_get_link(struct dentry *dentry, if (err) return err; page = read_cache_page(&inode->i_data, 0, - (filler_t *)nfs_symlink_filler, inode); + nfs_symlink_filler, inode); if (IS_ERR(page)) return ERR_CAST(page); } diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 06ffa135dfa6..35989c7bb065 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -2158,8 +2158,8 @@ static void nilfs_btree_lookup_dirty_buffers(struct nilfs_bmap *btree, pagevec_init(&pvec, 0); - while (pagevec_lookup_tag(&pvec, btcache, &index, PAGECACHE_TAG_DIRTY, - PAGEVEC_SIZE)) { + while (pagevec_lookup_tag(&pvec, btcache, &index, + PAGECACHE_TAG_DIRTY)) { for (i = 0; i < pagevec_count(&pvec); i++) { bh = head = page_buffers(pvec.pages[i]); do { diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index 8616c46d33da..1c16726915c1 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -257,8 +257,7 @@ int nilfs_copy_dirty_pages(struct address_space *dmap, pagevec_init(&pvec, 0); repeat: - if (!pagevec_lookup_tag(&pvec, smap, &index, PAGECACHE_TAG_DIRTY, - PAGEVEC_SIZE)) + if (!pagevec_lookup_tag(&pvec, smap, &index, PAGECACHE_TAG_DIRTY)) return 0; for (i = 0; i < pagevec_count(&pvec); i++) { @@ -376,8 +375,8 @@ void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent) pagevec_init(&pvec, 0); - while (pagevec_lookup_tag(&pvec, mapping, &index, PAGECACHE_TAG_DIRTY, - PAGEVEC_SIZE)) { + while (pagevec_lookup_tag(&pvec, mapping, &index, + PAGECACHE_TAG_DIRTY)) { for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 5d1e5832690e..3ac4b2b72593 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -711,18 +711,14 @@ static size_t nilfs_lookup_dirty_data_buffers(struct inode *inode, pagevec_init(&pvec, 0); repeat: if (unlikely(index > last) || - !pagevec_lookup_tag(&pvec, mapping, &index, PAGECACHE_TAG_DIRTY, - min_t(pgoff_t, last - index, - PAGEVEC_SIZE - 1) + 1)) + !pagevec_lookup_range_tag(&pvec, mapping, &index, last, + PAGECACHE_TAG_DIRTY)) return ndirties; for (i = 0; i < pagevec_count(&pvec); i++) { struct buffer_head *bh, *head; struct page *page = pvec.pages[i]; - if (unlikely(page->index > last)) - break; - lock_page(page); if (!page_has_buffers(page)) create_empty_buffers(page, i_blocksize(inode), 0); @@ -759,8 +755,8 @@ static void nilfs_lookup_dirty_node_buffers(struct inode *inode, pagevec_init(&pvec, 0); - while (pagevec_lookup_tag(&pvec, mapping, &index, PAGECACHE_TAG_DIRTY, - PAGEVEC_SIZE)) { + while (pagevec_lookup_tag(&pvec, mapping, &index, + PAGECACHE_TAG_DIRTY)) { for (i = 0; i < pagevec_count(&pvec); i++) { bh = head = page_buffers(pvec.pages[i]); do { diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 9752e7270e61..685e39e7b452 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -495,7 +495,7 @@ static int fanotify_find_path(int dfd, const char __user *filename, } /* you can only watch an inode if you have read permissions on it */ - ret = inode_permission(path->dentry->d_inode, MAY_READ); + ret = inode_permission2(path->mnt, path->dentry->d_inode, MAY_READ); if (ret) path_put(path); out: diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 7cc7d3fb1862..5c3caeaf0502 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -335,7 +335,7 @@ static int inotify_find_inode(const char __user *dirname, struct path *path, uns if (error) return error; /* you can only watch an inode if you have read permissions on it */ - error = inode_permission(path->dentry->d_inode, MAY_READ); + error = inode_permission2(path->mnt, path->dentry->d_inode, MAY_READ); if (error) path_put(path); return error; @@ -671,6 +671,8 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname, struct fsnotify_group *group; struct inode *inode; struct path path; + struct path alteredpath; + struct path *canonical_path = &path; struct fd f; int ret; unsigned flags = 0; @@ -710,13 +712,22 @@ SYSCALL_DEFINE3(inotify_add_watch, int, fd, const char __user *, pathname, if (ret) goto fput_and_out; + /* support stacked filesystems */ + if(path.dentry && path.dentry->d_op) { + if (path.dentry->d_op->d_canonical_path) { + path.dentry->d_op->d_canonical_path(&path, &alteredpath); + canonical_path = &alteredpath; + path_put(&path); + } + } + /* inode held in place by reference to path; group by fget on fd */ - inode = path.dentry->d_inode; + inode = canonical_path->dentry->d_inode; group = f.file->private_data; /* create/update an inode mark */ ret = inotify_update_watch(group, inode, mask); - path_put(&path); + path_put(canonical_path); fput_and_out: fdput(f); return ret; diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index 9ab9e1892b5f..988137de08f5 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -88,13 +88,13 @@ struct workqueue_struct *user_dlm_worker; */ #define DLMFS_CAPABILITIES "bast stackglue" static int param_set_dlmfs_capabilities(const char *val, - struct kernel_param *kp) + const struct kernel_param *kp) { printk(KERN_ERR "%s: readonly parameter\n", kp->name); return -EINVAL; } static int param_get_dlmfs_capabilities(char *buffer, - struct kernel_param *kp) + const struct kernel_param *kp) { return strlcpy(buffer, DLMFS_CAPABILITIES, strlen(DLMFS_CAPABILITIES) + 1); diff --git a/fs/open.c b/fs/open.c index 49fd070be0ec..3b62683fe332 100644 --- a/fs/open.c +++ b/fs/open.c @@ -34,8 +34,8 @@ #include "internal.h" -int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs, - struct file *filp) +int do_truncate2(struct vfsmount *mnt, struct dentry *dentry, loff_t length, + unsigned int time_attrs, struct file *filp) { int ret; struct iattr newattrs; @@ -60,18 +60,25 @@ int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs, inode_lock(dentry->d_inode); /* Note any delegations or leases have already been broken: */ - ret = notify_change(dentry, &newattrs, NULL); + ret = notify_change2(mnt, dentry, &newattrs, NULL); inode_unlock(dentry->d_inode); return ret; } +int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs, + struct file *filp) +{ + return do_truncate2(NULL, dentry, length, time_attrs, filp); +} long vfs_truncate(const struct path *path, loff_t length) { struct inode *inode; + struct vfsmount *mnt; struct dentry *upperdentry; long error; inode = path->dentry->d_inode; + mnt = path->mnt; /* For directories it's -EISDIR, for other non-regulars - -EINVAL */ if (S_ISDIR(inode->i_mode)) @@ -83,7 +90,7 @@ long vfs_truncate(const struct path *path, loff_t length) if (error) goto out; - error = inode_permission(inode, MAY_WRITE); + error = inode_permission2(mnt, inode, MAY_WRITE); if (error) goto mnt_drop_write_and_out; @@ -117,7 +124,7 @@ long vfs_truncate(const struct path *path, loff_t length) if (!error) error = security_path_truncate(path); if (!error) - error = do_truncate(path->dentry, length, 0, NULL); + error = do_truncate2(mnt, path->dentry, length, 0, NULL); put_write_and_out: put_write_access(upperdentry->d_inode); @@ -166,6 +173,7 @@ static long do_sys_ftruncate(unsigned int fd, loff_t length, int small) { struct inode *inode; struct dentry *dentry; + struct vfsmount *mnt; struct fd f; int error; @@ -182,6 +190,7 @@ static long do_sys_ftruncate(unsigned int fd, loff_t length, int small) small = 0; dentry = f.file->f_path.dentry; + mnt = f.file->f_path.mnt; inode = dentry->d_inode; error = -EINVAL; if (!S_ISREG(inode->i_mode) || !(f.file->f_mode & FMODE_WRITE)) @@ -202,7 +211,7 @@ static long do_sys_ftruncate(unsigned int fd, loff_t length, int small) if (!error) error = security_path_truncate(&f.file->f_path); if (!error) - error = do_truncate(dentry, length, ATTR_MTIME|ATTR_CTIME, f.file); + error = do_truncate2(mnt, dentry, length, ATTR_MTIME|ATTR_CTIME, f.file); sb_end_write(inode->i_sb); out_putf: fdput(f); @@ -356,6 +365,7 @@ SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode) struct cred *override_cred; struct path path; struct inode *inode; + struct vfsmount *mnt; int res; unsigned int lookup_flags = LOOKUP_FOLLOW; @@ -405,6 +415,7 @@ retry: goto out; inode = d_backing_inode(path.dentry); + mnt = path.mnt; if ((mode & MAY_EXEC) && S_ISREG(inode->i_mode)) { /* @@ -416,7 +427,7 @@ retry: goto out_path_release; } - res = inode_permission(inode, mode | MAY_ACCESS); + res = inode_permission2(mnt, inode, mode | MAY_ACCESS); /* SuS v2 requires we report a read only fs too */ if (res || !(mode & S_IWOTH) || special_file(inode->i_mode)) goto out_path_release; @@ -460,7 +471,7 @@ retry: if (error) goto out; - error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR); + error = inode_permission2(path.mnt, path.dentry->d_inode, MAY_EXEC | MAY_CHDIR); if (error) goto dput_and_out; @@ -489,7 +500,8 @@ SYSCALL_DEFINE1(fchdir, unsigned int, fd) if (!d_can_lookup(f.file->f_path.dentry)) goto out_putf; - error = inode_permission(file_inode(f.file), MAY_EXEC | MAY_CHDIR); + error = inode_permission2(f.file->f_path.mnt, file_inode(f.file), + MAY_EXEC | MAY_CHDIR); if (!error) set_fs_pwd(current->fs, &f.file->f_path); out_putf: @@ -508,7 +520,7 @@ retry: if (error) goto out; - error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR); + error = inode_permission2(path.mnt, path.dentry->d_inode, MAY_EXEC | MAY_CHDIR); if (error) goto dput_and_out; @@ -548,7 +560,7 @@ retry_deleg: goto out_unlock; newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO); newattrs.ia_valid = ATTR_MODE | ATTR_CTIME; - error = notify_change(path->dentry, &newattrs, &delegated_inode); + error = notify_change2(path->mnt, path->dentry, &newattrs, &delegated_inode); out_unlock: inode_unlock(inode); if (delegated_inode) { @@ -628,7 +640,7 @@ retry_deleg: inode_lock(inode); error = security_path_chown(path, uid, gid); if (!error) - error = notify_change(path->dentry, &newattrs, &delegated_inode); + error = notify_change2(path->mnt, path->dentry, &newattrs, &delegated_inode); inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index b97fc1df6212..4a2603841d77 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -687,7 +687,7 @@ int ovl_copy_up_flags(struct dentry *dentry, int flags) dput(parent); dput(next); } - revert_creds(old_cred); + ovl_revert_creds(old_cred); return err; } diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 8c561703275a..b075fc2fbbfe 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -469,7 +469,7 @@ static int ovl_create_or_link(struct dentry *dentry, struct inode *inode, bool origin) { int err; - const struct cred *old_cred; + const struct cred *old_cred, *hold_cred = NULL; struct cred *override_cred; struct dentry *parent = dentry->d_parent; @@ -496,14 +496,15 @@ static int ovl_create_or_link(struct dentry *dentry, struct inode *inode, override_cred->fsgid = inode->i_gid; if (!hardlink) { err = security_dentry_create_files_as(dentry, - attr->mode, &dentry->d_name, old_cred, + attr->mode, &dentry->d_name, + old_cred ? old_cred : current_cred(), override_cred); if (err) { put_cred(override_cred); goto out_revert_creds; } } - put_cred(override_creds(override_cred)); + hold_cred = override_creds(override_cred); put_cred(override_cred); if (!ovl_dentry_is_whiteout(dentry)) @@ -514,7 +515,9 @@ static int ovl_create_or_link(struct dentry *dentry, struct inode *inode, hardlink); } out_revert_creds: - revert_creds(old_cred); + ovl_revert_creds(old_cred ?: hold_cred); + if (old_cred && hold_cred) + put_cred(hold_cred); if (!err) { struct inode *realinode = d_inode(ovl_dentry_upper(dentry)); @@ -773,7 +776,7 @@ static int ovl_do_remove(struct dentry *dentry, bool is_dir) err = ovl_remove_upper(dentry, is_dir); else err = ovl_remove_and_whiteout(dentry, is_dir); - revert_creds(old_cred); + ovl_revert_creds(old_cred); if (!err) { if (is_dir) clear_nlink(dentry->d_inode); @@ -1089,7 +1092,7 @@ out_dput_old: out_unlock: unlock_rename(new_upperdir, old_upperdir); out_revert_creds: - revert_creds(old_cred); + ovl_revert_creds(old_cred); ovl_nlink_end(new, locked); out_drop_write: ovl_drop_write(old); diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 30a1c7fc8c75..ce48ed6ba052 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -49,7 +49,7 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr) inode_lock(upperdentry->d_inode); old_cred = ovl_override_creds(dentry->d_sb); err = notify_change(upperdentry, attr, NULL); - revert_creds(old_cred); + ovl_revert_creds(old_cred); if (!err) ovl_copyattr(upperdentry->d_inode, dentry->d_inode); inode_unlock(upperdentry->d_inode); @@ -142,7 +142,7 @@ int ovl_getattr(const struct path *path, struct kstat *stat, stat->nlink = dentry->d_inode->i_nlink; out: - revert_creds(old_cred); + ovl_revert_creds(old_cred); return err; } @@ -176,7 +176,7 @@ int ovl_permission(struct inode *inode, int mask) mask |= MAY_READ; } err = inode_permission(realinode, mask); - revert_creds(old_cred); + ovl_revert_creds(old_cred); return err; } @@ -193,7 +193,7 @@ static const char *ovl_get_link(struct dentry *dentry, old_cred = ovl_override_creds(dentry->d_sb); p = vfs_get_link(ovl_dentry_real(dentry), done); - revert_creds(old_cred); + ovl_revert_creds(old_cred); return p; } @@ -236,7 +236,7 @@ int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name, WARN_ON(flags != XATTR_REPLACE); err = vfs_removexattr(realdentry, name); } - revert_creds(old_cred); + ovl_revert_creds(old_cred); out_drop_write: ovl_drop_write(dentry); @@ -244,6 +244,21 @@ out: return err; } +int __ovl_xattr_get(struct dentry *dentry, struct inode *inode, + const char *name, void *value, size_t size) +{ + ssize_t res; + const struct cred *old_cred; + struct dentry *realdentry = + ovl_i_dentry_upper(inode) ?: ovl_dentry_lower(dentry); + + old_cred = ovl_override_creds(dentry->d_sb); + res = __vfs_getxattr(realdentry, d_inode(realdentry), name, value, + size); + ovl_revert_creds(old_cred); + return res; +} + int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name, void *value, size_t size) { @@ -254,7 +269,7 @@ int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name, old_cred = ovl_override_creds(dentry->d_sb); res = vfs_getxattr(realdentry, name, value, size); - revert_creds(old_cred); + ovl_revert_creds(old_cred); return res; } @@ -279,7 +294,7 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) old_cred = ovl_override_creds(dentry->d_sb); res = vfs_listxattr(realdentry, list, size); - revert_creds(old_cred); + ovl_revert_creds(old_cred); if (res <= 0 || size == 0) return res; @@ -314,7 +329,7 @@ struct posix_acl *ovl_get_acl(struct inode *inode, int type) old_cred = ovl_override_creds(inode->i_sb); acl = get_acl(realinode, type); - revert_creds(old_cred); + ovl_revert_creds(old_cred); return acl; } @@ -524,12 +539,13 @@ unsigned int ovl_get_nlink(struct dentry *lowerdentry, int nlink_diff; int nlink; char buf[13]; - int err; + ssize_t err; if (!lowerdentry || !upperdentry || d_inode(lowerdentry)->i_nlink == 1) return fallback; - err = vfs_getxattr(upperdentry, OVL_XATTR_NLINK, &buf, sizeof(buf) - 1); + err = ovl_vfs_getxattr(upperdentry, OVL_XATTR_NLINK, + &buf, sizeof(buf) - 1); if (err < 0) goto fail; @@ -551,7 +567,7 @@ unsigned int ovl_get_nlink(struct dentry *lowerdentry, return nlink; fail: - pr_warn_ratelimited("overlayfs: failed to get index nlink (%pd2, err=%i)\n", + pr_warn_ratelimited("overlayfs: failed to get index nlink (%pd2, err=%zi)\n", upperdentry, err); return fallback; } diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index 8442f9839c90..6071196a7b63 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -29,10 +29,10 @@ struct ovl_lookup_data { static int ovl_check_redirect(struct dentry *dentry, struct ovl_lookup_data *d, size_t prelen, const char *post) { - int res; + ssize_t res; char *s, *next, *buf = NULL; - res = vfs_getxattr(dentry, OVL_XATTR_REDIRECT, NULL, 0); + res = ovl_vfs_getxattr(dentry, OVL_XATTR_REDIRECT, NULL, 0); if (res < 0) { if (res == -ENODATA || res == -EOPNOTSUPP) return 0; @@ -45,7 +45,7 @@ static int ovl_check_redirect(struct dentry *dentry, struct ovl_lookup_data *d, if (res == 0) goto invalid; - res = vfs_getxattr(dentry, OVL_XATTR_REDIRECT, buf, res); + res = ovl_vfs_getxattr(dentry, OVL_XATTR_REDIRECT, buf, res); if (res < 0) goto fail; if (res == 0) @@ -85,7 +85,7 @@ err_free: kfree(buf); return 0; fail: - pr_warn_ratelimited("overlayfs: failed to get redirect (%i)\n", res); + pr_warn_ratelimited("overlayfs: failed to get redirect (%zi)\n", res); goto err_free; invalid: pr_warn_ratelimited("overlayfs: invalid redirect (%s)\n", buf); @@ -99,10 +99,10 @@ static int ovl_acceptable(void *ctx, struct dentry *dentry) static struct ovl_fh *ovl_get_origin_fh(struct dentry *dentry) { - int res; + ssize_t res; struct ovl_fh *fh = NULL; - res = vfs_getxattr(dentry, OVL_XATTR_ORIGIN, NULL, 0); + res = ovl_vfs_getxattr(dentry, OVL_XATTR_ORIGIN, NULL, 0); if (res < 0) { if (res == -ENODATA || res == -EOPNOTSUPP) return NULL; @@ -116,7 +116,7 @@ static struct ovl_fh *ovl_get_origin_fh(struct dentry *dentry) if (!fh) return ERR_PTR(-ENOMEM); - res = vfs_getxattr(dentry, OVL_XATTR_ORIGIN, fh, res); + res = ovl_vfs_getxattr(dentry, OVL_XATTR_ORIGIN, fh, res); if (res < 0) goto fail; @@ -142,10 +142,11 @@ out: return NULL; fail: - pr_warn_ratelimited("overlayfs: failed to get origin (%i)\n", res); + pr_warn_ratelimited("overlayfs: failed to get origin (%zi)\n", res); goto out; invalid: - pr_warn_ratelimited("overlayfs: invalid origin (%*phN)\n", res, fh); + pr_warn_ratelimited("overlayfs: invalid origin (%*phN)\n", + (int)res, fh); goto out; } @@ -730,7 +731,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, ovl_set_flag(OVL_INDEX, inode); } - revert_creds(old_cred); + ovl_revert_creds(old_cred); dput(index); kfree(stack); kfree(d.redirect); @@ -751,7 +752,7 @@ out_put_upper: kfree(upperredirect); out: kfree(d.redirect); - revert_creds(old_cred); + ovl_revert_creds(old_cred); return ERR_PTR(err); } diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index e1e743005583..fdf83a10a9d3 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -187,6 +187,9 @@ int ovl_want_write(struct dentry *dentry); void ovl_drop_write(struct dentry *dentry); struct dentry *ovl_workdir(struct dentry *dentry); const struct cred *ovl_override_creds(struct super_block *sb); +void ovl_revert_creds(const struct cred *oldcred); +ssize_t ovl_vfs_getxattr(struct dentry *dentry, const char *name, void *buf, + size_t size); struct super_block *ovl_same_sb(struct super_block *sb); bool ovl_can_decode_fh(struct super_block *sb); struct dentry *ovl_indexdir(struct super_block *sb); @@ -279,6 +282,8 @@ int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name, const void *value, size_t size, int flags); int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name, void *value, size_t size); +int __ovl_xattr_get(struct dentry *dentry, struct inode *inode, + const char *name, void *value, size_t size); ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size); struct posix_acl *ovl_get_acl(struct inode *inode, int type); int ovl_open_maybe_copy_up(struct dentry *dentry, unsigned int file_flags); diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h index 36b49bd09264..27a6325d3af2 100644 --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -15,6 +15,7 @@ struct ovl_config { bool default_permissions; bool redirect_dir; bool index; + bool override_creds; }; /* private information held for overlayfs's superblock */ diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index 1d4f9997236f..b00f1a9d21ad 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -283,7 +283,7 @@ static int ovl_check_whiteouts(struct dentry *dir, struct ovl_readdir_data *rdd) } inode_unlock(dir->d_inode); } - revert_creds(old_cred); + ovl_revert_creds(old_cred); return err; } diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index ba20393d60ef..01cd5a2cbe35 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -39,6 +39,11 @@ module_param_named(index, ovl_index_def, bool, 0644); MODULE_PARM_DESC(ovl_index_def, "Default to on or off for the inodes index feature"); +static bool __read_mostly ovl_override_creds_def = true; +module_param_named(override_creds, ovl_override_creds_def, bool, 0644); +MODULE_PARM_DESC(ovl_override_creds_def, + "Use mounter's credentials for accesses"); + static void ovl_dentry_release(struct dentry *dentry) { struct ovl_entry *oe = dentry->d_fsdata; @@ -318,6 +323,9 @@ static int ovl_show_options(struct seq_file *m, struct dentry *dentry) if (ufs->config.index != ovl_index_def) seq_printf(m, ",index=%s", ufs->config.index ? "on" : "off"); + if (ufs->config.override_creds != ovl_override_creds_def) + seq_show_option(m, "override_creds", + ufs->config.override_creds ? "on" : "off"); return 0; } @@ -351,6 +359,8 @@ enum { OPT_REDIRECT_DIR_OFF, OPT_INDEX_ON, OPT_INDEX_OFF, + OPT_OVERRIDE_CREDS_ON, + OPT_OVERRIDE_CREDS_OFF, OPT_ERR, }; @@ -363,6 +373,8 @@ static const match_table_t ovl_tokens = { {OPT_REDIRECT_DIR_OFF, "redirect_dir=off"}, {OPT_INDEX_ON, "index=on"}, {OPT_INDEX_OFF, "index=off"}, + {OPT_OVERRIDE_CREDS_ON, "override_creds=on"}, + {OPT_OVERRIDE_CREDS_OFF, "override_creds=off"}, {OPT_ERR, NULL} }; @@ -393,6 +405,7 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config) { char *p; + config->override_creds = ovl_override_creds_def; while ((p = ovl_next_opt(&opt)) != NULL) { int token; substring_t args[MAX_OPT_ARGS]; @@ -443,6 +456,14 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config) config->index = false; break; + case OPT_OVERRIDE_CREDS_ON: + config->override_creds = true; + break; + + case OPT_OVERRIDE_CREDS_OFF: + config->override_creds = false; + break; + default: pr_err("overlayfs: unrecognized mount option \"%s\" or missing value\n", p); return -EINVAL; @@ -713,6 +734,14 @@ ovl_posix_acl_xattr_get(const struct xattr_handler *handler, } static int __maybe_unused +__ovl_posix_acl_xattr_get(const struct xattr_handler *handler, + struct dentry *dentry, struct inode *inode, + const char *name, void *buffer, size_t size) +{ + return __ovl_xattr_get(dentry, inode, handler->name, buffer, size); +} + +static int __maybe_unused ovl_posix_acl_xattr_set(const struct xattr_handler *handler, struct dentry *dentry, struct inode *inode, const char *name, const void *value, @@ -792,6 +821,13 @@ static int ovl_other_xattr_get(const struct xattr_handler *handler, return ovl_xattr_get(dentry, inode, name, buffer, size); } +static int __ovl_other_xattr_get(const struct xattr_handler *handler, + struct dentry *dentry, struct inode *inode, + const char *name, void *buffer, size_t size) +{ + return __ovl_xattr_get(dentry, inode, name, buffer, size); +} + static int ovl_other_xattr_set(const struct xattr_handler *handler, struct dentry *dentry, struct inode *inode, const char *name, const void *value, @@ -805,6 +841,7 @@ ovl_posix_acl_access_xattr_handler = { .name = XATTR_NAME_POSIX_ACL_ACCESS, .flags = ACL_TYPE_ACCESS, .get = ovl_posix_acl_xattr_get, + .__get = __ovl_posix_acl_xattr_get, .set = ovl_posix_acl_xattr_set, }; @@ -813,6 +850,7 @@ ovl_posix_acl_default_xattr_handler = { .name = XATTR_NAME_POSIX_ACL_DEFAULT, .flags = ACL_TYPE_DEFAULT, .get = ovl_posix_acl_xattr_get, + .__get = __ovl_posix_acl_xattr_get, .set = ovl_posix_acl_xattr_set, }; @@ -825,6 +863,7 @@ static const struct xattr_handler ovl_own_xattr_handler = { static const struct xattr_handler ovl_other_xattr_handler = { .prefix = "", /* catch all */ .get = ovl_other_xattr_get, + .__get = __ovl_other_xattr_get, .set = ovl_other_xattr_set, }; @@ -1157,7 +1196,6 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) ovl_dentry_lower(root_dentry)); sb->s_root = root_dentry; - return 0; out_free_oe: diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index afdc2533ce74..e2244c134c9c 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -41,9 +41,23 @@ const struct cred *ovl_override_creds(struct super_block *sb) { struct ovl_fs *ofs = sb->s_fs_info; + if (!ofs->config.override_creds) + return NULL; return override_creds(ofs->creator_cred); } +void ovl_revert_creds(const struct cred *old_cred) +{ + if (old_cred) + revert_creds(old_cred); +} + +ssize_t ovl_vfs_getxattr(struct dentry *dentry, const char *name, void *buf, + size_t size) +{ + return __vfs_getxattr(dentry, d_inode(dentry), name, buf, size); +} + struct super_block *ovl_same_sb(struct super_block *sb) { struct ovl_fs *ofs = sb->s_fs_info; @@ -331,13 +345,13 @@ void ovl_copy_up_end(struct dentry *dentry) bool ovl_check_dir_xattr(struct dentry *dentry, const char *name) { - int res; + ssize_t res; char val; if (!d_is_dir(dentry)) return false; - res = vfs_getxattr(dentry, name, &val, 1); + res = ovl_vfs_getxattr(dentry, name, &val, 1); if (res == 1 && val == 'y') return true; @@ -535,7 +549,7 @@ int ovl_nlink_start(struct dentry *dentry, bool *locked) * value relative to the upper inode nlink in an upper inode xattr. */ err = ovl_set_nlink_upper(dentry); - revert_creds(old_cred); + ovl_revert_creds(old_cred); out: if (err) @@ -555,7 +569,7 @@ void ovl_nlink_end(struct dentry *dentry, bool locked) old_cred = ovl_override_creds(dentry->d_sb); ovl_cleanup_index(dentry); - revert_creds(old_cred); + ovl_revert_creds(old_cred); } mutex_unlock(&OVL_I(d_inode(dentry))->lock); diff --git a/fs/pnode.c b/fs/pnode.c index 7910ae91f17e..1fc2e47d1308 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -606,3 +606,19 @@ int propagate_umount(struct list_head *list) return 0; } + +void propagate_remount(struct mount *mnt) +{ + struct mount *parent = mnt->mnt_parent; + struct mount *p = mnt, *m; + struct super_block *sb = mnt->mnt.mnt_sb; + + if (!sb->s_op->copy_mnt_data) + return; + for (p = propagation_next(parent, parent); p; + p = propagation_next(p, parent)) { + m = __lookup_mnt(&p->mnt, mnt->mnt_mountpoint); + if (m) + sb->s_op->copy_mnt_data(m->mnt.data, mnt->mnt.data); + } +} diff --git a/fs/pnode.h b/fs/pnode.h index dc87e65becd2..a9a6576540ad 100644 --- a/fs/pnode.h +++ b/fs/pnode.h @@ -44,6 +44,7 @@ int propagate_mnt(struct mount *, struct mountpoint *, struct mount *, int propagate_umount(struct list_head *); int propagate_mount_busy(struct mount *, int); void propagate_mount_unlock(struct mount *); +void propagate_remount(struct mount *); void mnt_release_group_id(struct mount *); int get_dominating_id(struct mount *mnt, const struct path *root); unsigned int mnt_get_count(struct mount *mnt); diff --git a/fs/posix_acl.c b/fs/posix_acl.c index eebf5f6cf6d5..2fd0fde16fe1 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -43,7 +43,7 @@ struct posix_acl *get_cached_acl(struct inode *inode, int type) rcu_read_lock(); acl = rcu_dereference(*p); if (!acl || is_uncached_acl(acl) || - atomic_inc_not_zero(&acl->a_refcount)) + refcount_inc_not_zero(&acl->a_refcount)) break; rcu_read_unlock(); cpu_relax(); @@ -164,7 +164,7 @@ EXPORT_SYMBOL(get_acl); void posix_acl_init(struct posix_acl *acl, int count) { - atomic_set(&acl->a_refcount, 1); + refcount_set(&acl->a_refcount, 1); acl->a_count = count; } EXPORT_SYMBOL(posix_acl_init); @@ -197,7 +197,7 @@ posix_acl_clone(const struct posix_acl *acl, gfp_t flags) sizeof(struct posix_acl_entry); clone = kmemdup(acl, size, flags); if (clone) - atomic_set(&clone->a_refcount, 1); + refcount_set(&clone->a_refcount, 1); } return clone; } diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig index 1ade1206bb89..08dce22afec1 100644 --- a/fs/proc/Kconfig +++ b/fs/proc/Kconfig @@ -81,3 +81,10 @@ config PROC_CHILDREN Say Y if you are running any user-space software which takes benefit from this interface. For example, rkt is such a piece of software. + +config PROC_UID + bool "Include /proc/uid/ files" + default y + depends on PROC_FS && RT_MUTEXES + help + Provides aggregated per-uid information under /proc/uid. diff --git a/fs/proc/Makefile b/fs/proc/Makefile index f7456c4e7d0f..d8dcb188db6d 100644 --- a/fs/proc/Makefile +++ b/fs/proc/Makefile @@ -26,6 +26,7 @@ proc-y += softirqs.o proc-y += namespaces.o proc-y += self.o proc-y += thread_self.o +proc-$(CONFIG_PROC_UID) += uid.o proc-$(CONFIG_PROC_SYSCTL) += proc_sysctl.o proc-$(CONFIG_NET) += proc_net.o proc-$(CONFIG_PROC_KCORE) += kcore.o diff --git a/fs/proc/base.c b/fs/proc/base.c index 64695dcf89f3..3b593d1bafaf 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -93,6 +93,7 @@ #include <linux/sched/stat.h> #include <linux/flex_array.h> #include <linux/posix-timers.h> +#include <linux/cpufreq_times.h> #ifdef CONFIG_HARDWALL #include <asm/hardwall.h> #endif @@ -3032,6 +3033,9 @@ static const struct pid_entry tgid_base_stuff[] = { #ifdef CONFIG_LIVEPATCH ONE("patch_state", S_IRUSR, proc_pid_patch_state), #endif +#ifdef CONFIG_CPU_FREQ_TIMES + ONE("time_in_state", 0444, proc_time_in_state_show), +#endif }; static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx) @@ -3419,6 +3423,9 @@ static const struct pid_entry tid_base_stuff[] = { #ifdef CONFIG_LIVEPATCH ONE("patch_state", S_IRUSR, proc_pid_patch_state), #endif +#ifdef CONFIG_CPU_FREQ_TIMES + ONE("time_in_state", 0444, proc_time_in_state_show), +#endif }; static int proc_tid_base_readdir(struct file *file, struct dir_context *ctx) diff --git a/fs/proc/inode.c b/fs/proc/inode.c index d8e1249adb18..a6632f5c6cb8 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -472,17 +472,12 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) return inode; } -int proc_fill_super(struct super_block *s, void *data, int silent) +int proc_fill_super(struct super_block *s) { - struct pid_namespace *ns = get_pid_ns(s->s_fs_info); struct inode *root_inode; int ret; - if (!proc_parse_options(data, ns)) - return -EINVAL; - - /* User space would break if executables or devices appear on proc */ - s->s_iflags |= SB_I_USERNS_VISIBLE | SB_I_NOEXEC | SB_I_NODEV; + s->s_iflags |= SB_I_USERNS_VISIBLE | SB_I_NODEV; s->s_flags |= MS_NODIRATIME | MS_NOSUID | MS_NOEXEC; s->s_blocksize = 1024; s->s_blocksize_bits = 10; diff --git a/fs/proc/internal.h b/fs/proc/internal.h index a34195e92b20..02e0d9e9b3fe 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -203,7 +203,7 @@ extern const struct inode_operations proc_pid_link_inode_operations; extern void proc_init_inodecache(void); void set_proc_pid_nlink(void); extern struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry *); -extern int proc_fill_super(struct super_block *, void *data, int flags); +extern int proc_fill_super(struct super_block *); extern void proc_entry_rundown(struct proc_dir_entry *); /* @@ -249,6 +249,15 @@ static inline void proc_sys_evict_inode(struct inode *inode, #endif /* + * uid.c + */ +#ifdef CONFIG_PROC_UID +extern int proc_uid_init(void); +#else +static inline void proc_uid_init(void) { } +#endif + +/* * proc_tty.c */ #ifdef CONFIG_TTY @@ -261,7 +270,6 @@ static inline void proc_tty_init(void) {} * root.c */ extern struct proc_dir_entry proc_root; -extern int proc_parse_options(char *options, struct pid_namespace *pid); extern void proc_self_init(void); extern int proc_remount(struct super_block *, int *, char *); diff --git a/fs/proc/loadavg.c b/fs/proc/loadavg.c index 9bc5c58c00ee..b3c0475f88de 100644 --- a/fs/proc/loadavg.c +++ b/fs/proc/loadavg.c @@ -10,9 +10,6 @@ #include <linux/seqlock.h> #include <linux/time.h> -#define LOAD_INT(x) ((x) >> FSHIFT) -#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) - static int loadavg_proc_show(struct seq_file *m, void *v) { unsigned long avnrun[3]; diff --git a/fs/proc/root.c b/fs/proc/root.c index 4e42aba97f2e..ef6840c64e95 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -26,6 +26,21 @@ #include "internal.h" +static int proc_test_super(struct super_block *sb, void *data) +{ + return sb->s_fs_info == data; +} + +static int proc_set_super(struct super_block *sb, void *data) +{ + int err = set_anon_super(sb, NULL); + if (!err) { + struct pid_namespace *ns = (struct pid_namespace *)data; + sb->s_fs_info = get_pid_ns(ns); + } + return err; +} + enum { Opt_gid, Opt_hidepid, Opt_err, }; @@ -36,7 +51,7 @@ static const match_table_t tokens = { {Opt_err, NULL}, }; -int proc_parse_options(char *options, struct pid_namespace *pid) +static int proc_parse_options(char *options, struct pid_namespace *pid) { char *p; substring_t args[MAX_OPT_ARGS]; @@ -89,16 +104,45 @@ int proc_remount(struct super_block *sb, int *flags, char *data) static struct dentry *proc_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { + int err; + struct super_block *sb; struct pid_namespace *ns; + char *options; if (flags & MS_KERNMOUNT) { - ns = data; - data = NULL; + ns = (struct pid_namespace *)data; + options = NULL; } else { ns = task_active_pid_ns(current); + options = data; + + /* Does the mounter have privilege over the pid namespace? */ + if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); } - return mount_ns(fs_type, flags, data, ns, ns->user_ns, proc_fill_super); + sb = sget(fs_type, proc_test_super, proc_set_super, flags, ns); + if (IS_ERR(sb)) + return ERR_CAST(sb); + + if (!proc_parse_options(options, ns)) { + deactivate_locked_super(sb); + return ERR_PTR(-EINVAL); + } + + if (!sb->s_root) { + err = proc_fill_super(sb); + if (err) { + deactivate_locked_super(sb); + return ERR_PTR(err); + } + + sb->s_flags |= MS_ACTIVE; + /* User space would break if executables appear on proc */ + sb->s_iflags |= SB_I_NOEXEC; + } + + return dget(sb->s_root); } static void proc_kill_sb(struct super_block *sb) @@ -136,7 +180,7 @@ void __init proc_root_init(void) proc_symlink("mounts", NULL, "self/mounts"); proc_net_init(); - + proc_uid_init(); #ifdef CONFIG_SYSVIPC proc_mkdir("sysvipc", NULL); #endif diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 309d24118f9a..5b346eb97a93 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -130,6 +130,56 @@ static void release_task_mempolicy(struct proc_maps_private *priv) } #endif +static void seq_print_vma_name(struct seq_file *m, struct vm_area_struct *vma) +{ + const char __user *name = vma_get_anon_name(vma); + struct mm_struct *mm = vma->vm_mm; + + unsigned long page_start_vaddr; + unsigned long page_offset; + unsigned long num_pages; + unsigned long max_len = NAME_MAX; + int i; + + page_start_vaddr = (unsigned long)name & PAGE_MASK; + page_offset = (unsigned long)name - page_start_vaddr; + num_pages = DIV_ROUND_UP(page_offset + max_len, PAGE_SIZE); + + seq_puts(m, "[anon:"); + + for (i = 0; i < num_pages; i++) { + int len; + int write_len; + const char *kaddr; + long pages_pinned; + struct page *page; + + pages_pinned = get_user_pages_remote(current, mm, + page_start_vaddr, 1, 0, &page, NULL, NULL); + if (pages_pinned < 1) { + seq_puts(m, "<fault>]"); + return; + } + + kaddr = (const char *)kmap(page); + len = min(max_len, PAGE_SIZE - page_offset); + write_len = strnlen(kaddr + page_offset, len); + seq_write(m, kaddr + page_offset, write_len); + kunmap(page); + put_page(page); + + /* if strnlen hit a null terminator then we're done */ + if (write_len != len) + break; + + max_len -= len; + page_offset = 0; + page_start_vaddr += PAGE_SIZE; + } + + seq_putc(m, ']'); +} + static void vma_stop(struct proc_maps_private *priv) { struct mm_struct *mm = priv->mm; @@ -349,8 +399,15 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid) goto done; } - if (is_stack(vma)) + if (is_stack(vma)) { name = "[stack]"; + goto done; + } + + if (vma_get_anon_name(vma)) { + seq_pad(m, ' '); + seq_print_vma_name(m, vma); + } } done: @@ -806,6 +863,11 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) if (!rollup_mode) { show_map_vma(m, vma, is_pid); + if (vma_get_anon_name(vma)) { + seq_puts(m, "Name: "); + seq_print_vma_name(m, vma); + seq_putc(m, '\n'); + } } else if (last_vma) { show_vma_header_prefix( m, mss->first_vma_start, vma->vm_end, 0, 0, 0, 0); diff --git a/fs/proc/uid.c b/fs/proc/uid.c new file mode 100644 index 000000000000..6a096d25109d --- /dev/null +++ b/fs/proc/uid.c @@ -0,0 +1,295 @@ +/* + * /proc/uid support + */ + +#include <linux/cpufreq_times.h> +#include <linux/fs.h> +#include <linux/hashtable.h> +#include <linux/init.h> +#include <linux/proc_fs.h> +#include <linux/rtmutex.h> +#include <linux/sched.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include "internal.h" + +static struct proc_dir_entry *proc_uid; + +#define UID_HASH_BITS 10 + +static DECLARE_HASHTABLE(proc_uid_hash_table, UID_HASH_BITS); + +/* + * use rt_mutex here to avoid priority inversion between high-priority readers + * of these files and tasks calling proc_register_uid(). + */ +static DEFINE_RT_MUTEX(proc_uid_lock); /* proc_uid_hash_table */ + +struct uid_hash_entry { + uid_t uid; + struct hlist_node hash; +}; + +/* Caller must hold proc_uid_lock */ +static bool uid_hash_entry_exists_locked(uid_t uid) +{ + struct uid_hash_entry *entry; + + hash_for_each_possible(proc_uid_hash_table, entry, hash, uid) { + if (entry->uid == uid) + return true; + } + return false; +} + +void proc_register_uid(kuid_t kuid) +{ + struct uid_hash_entry *entry; + bool exists; + uid_t uid = from_kuid_munged(current_user_ns(), kuid); + + rt_mutex_lock(&proc_uid_lock); + exists = uid_hash_entry_exists_locked(uid); + rt_mutex_unlock(&proc_uid_lock); + if (exists) + return; + + entry = kzalloc(sizeof(struct uid_hash_entry), GFP_KERNEL); + if (!entry) + return; + entry->uid = uid; + + rt_mutex_lock(&proc_uid_lock); + if (uid_hash_entry_exists_locked(uid)) + kfree(entry); + else + hash_add(proc_uid_hash_table, &entry->hash, uid); + rt_mutex_unlock(&proc_uid_lock); +} + +struct uid_entry { + const char *name; + int len; + umode_t mode; + const struct inode_operations *iop; + const struct file_operations *fop; +}; + +#define NOD(NAME, MODE, IOP, FOP) { \ + .name = (NAME), \ + .len = sizeof(NAME) - 1, \ + .mode = MODE, \ + .iop = IOP, \ + .fop = FOP, \ +} + +#ifdef CONFIG_CPU_FREQ_TIMES +static const struct file_operations proc_uid_time_in_state_operations = { + .open = single_uid_time_in_state_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; +#endif + +static const struct uid_entry uid_base_stuff[] = { +#ifdef CONFIG_CPU_FREQ_TIMES + NOD("time_in_state", 0444, NULL, &proc_uid_time_in_state_operations), +#endif +}; + +static const struct inode_operations proc_uid_def_inode_operations = { + .setattr = proc_setattr, +}; + +static struct inode *proc_uid_make_inode(struct super_block *sb, kuid_t kuid) +{ + struct inode *inode; + + inode = new_inode(sb); + if (!inode) + return NULL; + + inode->i_ino = get_next_ino(); + inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); + inode->i_op = &proc_uid_def_inode_operations; + inode->i_uid = kuid; + + return inode; +} + +static int proc_uident_instantiate(struct inode *dir, struct dentry *dentry, + struct task_struct *unused, const void *ptr) +{ + const struct uid_entry *u = ptr; + struct inode *inode; + + inode = proc_uid_make_inode(dir->i_sb, dir->i_uid); + if (!inode) + return -ENOENT; + + inode->i_mode = u->mode; + if (S_ISDIR(inode->i_mode)) + set_nlink(inode, 2); + if (u->iop) + inode->i_op = u->iop; + if (u->fop) + inode->i_fop = u->fop; + d_add(dentry, inode); + return 0; +} + +static struct dentry *proc_uid_base_lookup(struct inode *dir, + struct dentry *dentry, + unsigned int flags) +{ + const struct uid_entry *u, *last; + unsigned int nents = ARRAY_SIZE(uid_base_stuff); + + if (nents == 0) + return ERR_PTR(-ENOENT); + + last = &uid_base_stuff[nents - 1]; + for (u = uid_base_stuff; u <= last; u++) { + if (u->len != dentry->d_name.len) + continue; + if (!memcmp(dentry->d_name.name, u->name, u->len)) + break; + } + if (u > last) + return ERR_PTR(-ENOENT); + + return ERR_PTR(proc_uident_instantiate(dir, dentry, NULL, u)); +} + +static int proc_uid_base_readdir(struct file *file, struct dir_context *ctx) +{ + unsigned int nents = ARRAY_SIZE(uid_base_stuff); + const struct uid_entry *u; + + if (!dir_emit_dots(file, ctx)) + return 0; + + if (ctx->pos >= nents + 2) + return 0; + + for (u = uid_base_stuff + (ctx->pos - 2); + u < uid_base_stuff + nents; u++) { + if (!proc_fill_cache(file, ctx, u->name, u->len, + proc_uident_instantiate, NULL, u)) + break; + ctx->pos++; + } + + return 0; +} + +static const struct inode_operations proc_uid_base_inode_operations = { + .lookup = proc_uid_base_lookup, + .setattr = proc_setattr, +}; + +static const struct file_operations proc_uid_base_operations = { + .read = generic_read_dir, + .iterate = proc_uid_base_readdir, + .llseek = default_llseek, +}; + +static int proc_uid_instantiate(struct inode *dir, struct dentry *dentry, + struct task_struct *unused, const void *ptr) +{ + unsigned int i, len; + nlink_t nlinks; + kuid_t *kuid = (kuid_t *)ptr; + struct inode *inode = proc_uid_make_inode(dir->i_sb, *kuid); + + if (!inode) + return -ENOENT; + + inode->i_mode = S_IFDIR | 0555; + inode->i_op = &proc_uid_base_inode_operations; + inode->i_fop = &proc_uid_base_operations; + inode->i_flags |= S_IMMUTABLE; + + nlinks = 2; + len = ARRAY_SIZE(uid_base_stuff); + for (i = 0; i < len; ++i) { + if (S_ISDIR(uid_base_stuff[i].mode)) + ++nlinks; + } + set_nlink(inode, nlinks); + + d_add(dentry, inode); + + return 0; +} + +static int proc_uid_readdir(struct file *file, struct dir_context *ctx) +{ + int last_shown, i; + unsigned long bkt; + struct uid_hash_entry *entry; + + if (!dir_emit_dots(file, ctx)) + return 0; + + i = 0; + last_shown = ctx->pos - 2; + rt_mutex_lock(&proc_uid_lock); + hash_for_each(proc_uid_hash_table, bkt, entry, hash) { + int len; + char buf[PROC_NUMBUF]; + + if (i < last_shown) + continue; + len = snprintf(buf, sizeof(buf), "%u", entry->uid); + if (!proc_fill_cache(file, ctx, buf, len, + proc_uid_instantiate, NULL, &entry->uid)) + break; + i++; + ctx->pos++; + } + rt_mutex_unlock(&proc_uid_lock); + return 0; +} + +static struct dentry *proc_uid_lookup(struct inode *dir, struct dentry *dentry, + unsigned int flags) +{ + int result = -ENOENT; + + uid_t uid = name_to_int(&dentry->d_name); + bool uid_exists; + + rt_mutex_lock(&proc_uid_lock); + uid_exists = uid_hash_entry_exists_locked(uid); + rt_mutex_unlock(&proc_uid_lock); + if (uid_exists) { + kuid_t kuid = make_kuid(current_user_ns(), uid); + + result = proc_uid_instantiate(dir, dentry, NULL, &kuid); + } + return ERR_PTR(result); +} + +static const struct file_operations proc_uid_operations = { + .read = generic_read_dir, + .iterate = proc_uid_readdir, + .llseek = default_llseek, +}; + +static const struct inode_operations proc_uid_inode_operations = { + .lookup = proc_uid_lookup, + .setattr = proc_setattr, +}; + +int __init proc_uid_init(void) +{ + proc_uid = proc_mkdir("uid", NULL); + if (!proc_uid) + return -ENOMEM; + proc_uid->proc_iops = &proc_uid_inode_operations; + proc_uid->proc_fops = &proc_uid_operations; + + return 0; +} diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c index 7626ee11b06c..b859aaeecb27 100644 --- a/fs/proc_namespace.c +++ b/fs/proc_namespace.c @@ -121,7 +121,9 @@ static int show_vfsmnt(struct seq_file *m, struct vfsmount *mnt) if (err) goto out; show_mnt_opts(m, mnt); - if (sb->s_op->show_options) + if (sb->s_op->show_options2) + err = sb->s_op->show_options2(mnt, m, mnt_path.dentry); + else if (sb->s_op->show_options) err = sb->s_op->show_options(m, mnt_path.dentry); seq_puts(m, " 0 0\n"); out: @@ -183,7 +185,9 @@ static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt) err = show_sb_opts(m, sb); if (err) goto out; - if (sb->s_op->show_options) + if (sb->s_op->show_options2) { + err = sb->s_op->show_options2(mnt, m, mnt->mnt_root); + } else if (sb->s_op->show_options) err = sb->s_op->show_options(m, mnt->mnt_root); seq_putc(m, '\n'); out: diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 11c7a171c0a1..8291b5b6e370 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -718,6 +718,12 @@ static int ramoops_parse_dt(struct platform_device *pdev, return 0; } +void notrace ramoops_console_write_buf(const char *buf, size_t size) +{ + struct ramoops_context *cxt = &oops_cxt; + persistent_ram_write(cxt->cprz, buf, size); +} + static int ramoops_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; diff --git a/fs/read_write.c b/fs/read_write.c index e8136a72c13f..0da6e4f19d7f 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -455,6 +455,8 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) return ret; } +EXPORT_SYMBOL(vfs_read); + static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos) { struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = len }; @@ -553,6 +555,8 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_ return ret; } +EXPORT_SYMBOL(vfs_write); + static inline loff_t file_pos_read(struct file *file) { return file->f_mode & FMODE_STREAM ? 0 : file->f_pos; diff --git a/fs/sdcardfs/Kconfig b/fs/sdcardfs/Kconfig new file mode 100644 index 000000000000..a1c103316ac7 --- /dev/null +++ b/fs/sdcardfs/Kconfig @@ -0,0 +1,13 @@ +config SDCARD_FS + tristate "sdcard file system" + depends on CONFIGFS_FS + default n + help + Sdcardfs is based on Wrapfs file system. + +config SDCARD_FS_FADV_NOACTIVE + bool "sdcardfs fadvise noactive support" + depends on FADV_NOACTIVE + default y + help + Sdcardfs supports fadvise noactive mode. diff --git a/fs/sdcardfs/Makefile b/fs/sdcardfs/Makefile new file mode 100644 index 000000000000..b84fbb2b45a4 --- /dev/null +++ b/fs/sdcardfs/Makefile @@ -0,0 +1,7 @@ +SDCARDFS_VERSION="0.1" + +EXTRA_CFLAGS += -DSDCARDFS_VERSION=\"$(SDCARDFS_VERSION)\" + +obj-$(CONFIG_SDCARD_FS) += sdcardfs.o + +sdcardfs-y := dentry.o file.o inode.o main.o super.o lookup.o mmap.o packagelist.o derived_perm.o diff --git a/fs/sdcardfs/dentry.c b/fs/sdcardfs/dentry.c new file mode 100644 index 000000000000..cb573f1efbfc --- /dev/null +++ b/fs/sdcardfs/dentry.c @@ -0,0 +1,196 @@ +/* + * fs/sdcardfs/dentry.c + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#include "sdcardfs.h" +#include "linux/ctype.h" + +/* + * returns: -ERRNO if error (returned to user) + * 0: tell VFS to invalidate dentry + * 1: dentry is valid + */ +static int sdcardfs_d_revalidate(struct dentry *dentry, unsigned int flags) +{ + int err = 1; + struct path parent_lower_path, lower_path; + struct dentry *parent_dentry = NULL; + struct dentry *parent_lower_dentry = NULL; + struct dentry *lower_cur_parent_dentry = NULL; + struct dentry *lower_dentry = NULL; + struct inode *inode; + struct sdcardfs_inode_data *data; + + if (flags & LOOKUP_RCU) + return -ECHILD; + + spin_lock(&dentry->d_lock); + if (IS_ROOT(dentry)) { + spin_unlock(&dentry->d_lock); + return 1; + } + spin_unlock(&dentry->d_lock); + + /* check uninitialized obb_dentry and + * whether the base obbpath has been changed or not + */ + if (is_obbpath_invalid(dentry)) { + return 0; + } + + parent_dentry = dget_parent(dentry); + sdcardfs_get_lower_path(parent_dentry, &parent_lower_path); + sdcardfs_get_real_lower(dentry, &lower_path); + parent_lower_dentry = parent_lower_path.dentry; + lower_dentry = lower_path.dentry; + lower_cur_parent_dentry = dget_parent(lower_dentry); + + if ((lower_dentry->d_flags & DCACHE_OP_REVALIDATE)) { + err = lower_dentry->d_op->d_revalidate(lower_dentry, flags); + if (err == 0) { + goto out; + } + } + + spin_lock(&lower_dentry->d_lock); + if (d_unhashed(lower_dentry)) { + spin_unlock(&lower_dentry->d_lock); + err = 0; + goto out; + } + spin_unlock(&lower_dentry->d_lock); + + if (parent_lower_dentry != lower_cur_parent_dentry) { + err = 0; + goto out; + } + + if (dentry < lower_dentry) { + spin_lock(&dentry->d_lock); + spin_lock_nested(&lower_dentry->d_lock, DENTRY_D_LOCK_NESTED); + } else { + spin_lock(&lower_dentry->d_lock); + spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); + } + + if (!qstr_case_eq(&dentry->d_name, &lower_dentry->d_name)) { + err = 0; + } + + if (dentry < lower_dentry) { + spin_unlock(&lower_dentry->d_lock); + spin_unlock(&dentry->d_lock); + } else { + spin_unlock(&dentry->d_lock); + spin_unlock(&lower_dentry->d_lock); + } + if (!err) + goto out; + + /* If our top's inode is gone, we may be out of date */ + inode = igrab(d_inode(dentry)); + if (inode) { + data = top_data_get(SDCARDFS_I(inode)); + if (!data || data->abandoned) { + err = 0; + } + if (data) + data_put(data); + iput(inode); + } + +out: + dput(parent_dentry); + dput(lower_cur_parent_dentry); + sdcardfs_put_lower_path(parent_dentry, &parent_lower_path); + sdcardfs_put_real_lower(dentry, &lower_path); + return err; +} + +/* 1 = delete, 0 = cache */ +static int sdcardfs_d_delete(const struct dentry *d) +{ + return SDCARDFS_SB(d->d_sb)->options.nocache ? 1 : 0; +} + +static void sdcardfs_d_release(struct dentry *dentry) +{ + if (!dentry || !dentry->d_fsdata) + return; + /* release and reset the lower paths */ + if (has_graft_path(dentry)) + sdcardfs_put_reset_orig_path(dentry); + sdcardfs_put_reset_lower_path(dentry); + free_dentry_private_data(dentry); +} + +static int sdcardfs_hash_ci(const struct dentry *dentry, + struct qstr *qstr) +{ + /* + * This function is copy of vfat_hashi. + * FIXME Should we support national language? + * Refer to vfat_hashi() + * struct nls_table *t = MSDOS_SB(dentry->d_sb)->nls_io; + */ + const unsigned char *name; + unsigned int len; + unsigned long hash; + + name = qstr->name; + len = qstr->len; + + hash = init_name_hash(dentry); + while (len--) + hash = partial_name_hash(tolower(*name++), hash); + qstr->hash = end_name_hash(hash); + + return 0; +} + +/* + * Case insensitive compare of two vfat names. + */ +static int sdcardfs_cmp_ci(const struct dentry *dentry, + unsigned int len, const char *str, const struct qstr *name) +{ + /* FIXME Should we support national language? */ + + if (name->len == len) { + if (str_n_case_eq(name->name, str, len)) + return 0; + } + return 1; +} + +static void sdcardfs_canonical_path(const struct path *path, + struct path *actual_path) +{ + sdcardfs_get_real_lower(path->dentry, actual_path); +} + +const struct dentry_operations sdcardfs_ci_dops = { + .d_revalidate = sdcardfs_d_revalidate, + .d_delete = sdcardfs_d_delete, + .d_release = sdcardfs_d_release, + .d_hash = sdcardfs_hash_ci, + .d_compare = sdcardfs_cmp_ci, + .d_canonical_path = sdcardfs_canonical_path, +}; + diff --git a/fs/sdcardfs/derived_perm.c b/fs/sdcardfs/derived_perm.c new file mode 100644 index 000000000000..78a669c8a4d6 --- /dev/null +++ b/fs/sdcardfs/derived_perm.c @@ -0,0 +1,477 @@ +/* + * fs/sdcardfs/derived_perm.c + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#include "sdcardfs.h" + +/* copy derived state from parent inode */ +static void inherit_derived_state(struct inode *parent, struct inode *child) +{ + struct sdcardfs_inode_info *pi = SDCARDFS_I(parent); + struct sdcardfs_inode_info *ci = SDCARDFS_I(child); + + ci->data->perm = PERM_INHERIT; + ci->data->userid = pi->data->userid; + ci->data->d_uid = pi->data->d_uid; + ci->data->under_android = pi->data->under_android; + ci->data->under_cache = pi->data->under_cache; + ci->data->under_obb = pi->data->under_obb; +} + +/* helper function for derived state */ +void setup_derived_state(struct inode *inode, perm_t perm, userid_t userid, + uid_t uid) +{ + struct sdcardfs_inode_info *info = SDCARDFS_I(inode); + + info->data->perm = perm; + info->data->userid = userid; + info->data->d_uid = uid; + info->data->under_android = false; + info->data->under_cache = false; + info->data->under_obb = false; +} + +/* While renaming, there is a point where we want the path from dentry, + * but the name from newdentry + */ +void get_derived_permission_new(struct dentry *parent, struct dentry *dentry, + const struct qstr *name) +{ + struct sdcardfs_inode_info *info = SDCARDFS_I(d_inode(dentry)); + struct sdcardfs_inode_info *parent_info = SDCARDFS_I(d_inode(parent)); + struct sdcardfs_inode_data *parent_data = parent_info->data; + appid_t appid; + unsigned long user_num; + int err; + struct qstr q_Android = QSTR_LITERAL("Android"); + struct qstr q_data = QSTR_LITERAL("data"); + struct qstr q_sandbox = QSTR_LITERAL("sandbox"); + struct qstr q_obb = QSTR_LITERAL("obb"); + struct qstr q_media = QSTR_LITERAL("media"); + struct qstr q_cache = QSTR_LITERAL("cache"); + + /* By default, each inode inherits from its parent. + * the properties are maintained on its private fields + * because the inode attributes will be modified with that of + * its lower inode. + * These values are used by our custom permission call instead + * of using the inode permissions. + */ + + inherit_derived_state(d_inode(parent), d_inode(dentry)); + + /* Files don't get special labels */ + if (!S_ISDIR(d_inode(dentry)->i_mode)) { + set_top(info, parent_info); + return; + } + /* Derive custom permissions based on parent and current node */ + switch (parent_data->perm) { + case PERM_INHERIT: + case PERM_ANDROID_PACKAGE_CACHE: + set_top(info, parent_info); + break; + case PERM_PRE_ROOT: + /* Legacy internal layout places users at top level */ + info->data->perm = PERM_ROOT; + err = kstrtoul(name->name, 10, &user_num); + if (err) + info->data->userid = 0; + else + info->data->userid = user_num; + break; + case PERM_ROOT: + /* Assume masked off by default. */ + if (qstr_case_eq(name, &q_Android)) { + /* App-specific directories inside; let anyone traverse */ + info->data->perm = PERM_ANDROID; + info->data->under_android = true; + } else { + set_top(info, parent_info); + } + break; + case PERM_ANDROID: + if (qstr_case_eq(name, &q_data)) { + /* App-specific directories inside; let anyone traverse */ + info->data->perm = PERM_ANDROID_DATA; + } else if (qstr_case_eq(name, &q_sandbox)) { + /* App-specific directories inside; let anyone traverse */ + info->data->perm = PERM_ANDROID_DATA; + } else if (qstr_case_eq(name, &q_obb)) { + /* App-specific directories inside; let anyone traverse */ + info->data->perm = PERM_ANDROID_OBB; + info->data->under_obb = true; + /* Single OBB directory is always shared */ + } else if (qstr_case_eq(name, &q_media)) { + /* App-specific directories inside; let anyone traverse */ + info->data->perm = PERM_ANDROID_MEDIA; + } else { + set_top(info, parent_info); + } + break; + case PERM_ANDROID_OBB: + case PERM_ANDROID_DATA: + case PERM_ANDROID_MEDIA: + info->data->perm = PERM_ANDROID_PACKAGE; + appid = get_appid(name->name); + if (appid != 0 && !is_excluded(name->name, parent_data->userid)) + info->data->d_uid = + multiuser_get_uid(parent_data->userid, appid); + break; + case PERM_ANDROID_PACKAGE: + if (qstr_case_eq(name, &q_cache)) { + info->data->perm = PERM_ANDROID_PACKAGE_CACHE; + info->data->under_cache = true; + } + set_top(info, parent_info); + break; + } +} + +void get_derived_permission(struct dentry *parent, struct dentry *dentry) +{ + get_derived_permission_new(parent, dentry, &dentry->d_name); +} + +static appid_t get_type(const char *name) +{ + const char *ext = strrchr(name, '.'); + appid_t id; + + if (ext && ext[0]) { + ext = &ext[1]; + id = get_ext_gid(ext); + return id?:AID_MEDIA_RW; + } + return AID_MEDIA_RW; +} + +void fixup_lower_ownership(struct dentry *dentry, const char *name) +{ + struct path path; + struct inode *inode; + struct inode *delegated_inode = NULL; + int error; + struct sdcardfs_inode_info *info; + struct sdcardfs_inode_data *info_d; + struct sdcardfs_inode_data *info_top; + perm_t perm; + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + uid_t uid = sbi->options.fs_low_uid; + gid_t gid = sbi->options.fs_low_gid; + struct iattr newattrs; + + if (!sbi->options.gid_derivation) + return; + + info = SDCARDFS_I(d_inode(dentry)); + info_d = info->data; + perm = info_d->perm; + if (info_d->under_obb) { + perm = PERM_ANDROID_OBB; + } else if (info_d->under_cache) { + perm = PERM_ANDROID_PACKAGE_CACHE; + } else if (perm == PERM_INHERIT) { + info_top = top_data_get(info); + perm = info_top->perm; + data_put(info_top); + } + + switch (perm) { + case PERM_ROOT: + case PERM_ANDROID: + case PERM_ANDROID_DATA: + case PERM_ANDROID_MEDIA: + case PERM_ANDROID_PACKAGE: + case PERM_ANDROID_PACKAGE_CACHE: + uid = multiuser_get_uid(info_d->userid, uid); + break; + case PERM_ANDROID_OBB: + uid = AID_MEDIA_OBB; + break; + case PERM_PRE_ROOT: + default: + break; + } + switch (perm) { + case PERM_ROOT: + case PERM_ANDROID: + case PERM_ANDROID_DATA: + case PERM_ANDROID_MEDIA: + if (S_ISDIR(d_inode(dentry)->i_mode)) + gid = multiuser_get_uid(info_d->userid, AID_MEDIA_RW); + else + gid = multiuser_get_uid(info_d->userid, get_type(name)); + break; + case PERM_ANDROID_OBB: + gid = AID_MEDIA_OBB; + break; + case PERM_ANDROID_PACKAGE: + if (uid_is_app(info_d->d_uid)) + gid = multiuser_get_ext_gid(info_d->d_uid); + else + gid = multiuser_get_uid(info_d->userid, AID_MEDIA_RW); + break; + case PERM_ANDROID_PACKAGE_CACHE: + if (uid_is_app(info_d->d_uid)) + gid = multiuser_get_ext_cache_gid(info_d->d_uid); + else + gid = multiuser_get_uid(info_d->userid, AID_MEDIA_RW); + break; + case PERM_PRE_ROOT: + default: + break; + } + + sdcardfs_get_lower_path(dentry, &path); + inode = d_inode(path.dentry); + if (d_inode(path.dentry)->i_gid.val != gid || d_inode(path.dentry)->i_uid.val != uid) { +retry_deleg: + newattrs.ia_valid = ATTR_GID | ATTR_UID | ATTR_FORCE; + newattrs.ia_uid = make_kuid(current_user_ns(), uid); + newattrs.ia_gid = make_kgid(current_user_ns(), gid); + if (!S_ISDIR(inode->i_mode)) + newattrs.ia_valid |= + ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV; + inode_lock(inode); + error = security_path_chown(&path, newattrs.ia_uid, newattrs.ia_gid); + if (!error) + error = notify_change2(path.mnt, path.dentry, &newattrs, &delegated_inode); + inode_unlock(inode); + if (delegated_inode) { + error = break_deleg_wait(&delegated_inode); + if (!error) + goto retry_deleg; + } + if (error) + pr_debug("sdcardfs: Failed to touch up lower fs gid/uid for %s\n", name); + } + sdcardfs_put_lower_path(dentry, &path); +} + +static int descendant_may_need_fixup(struct sdcardfs_inode_data *data, + struct limit_search *limit) +{ + if (data->perm == PERM_ROOT) + return (limit->flags & BY_USERID) ? + data->userid == limit->userid : 1; + if (data->perm == PERM_PRE_ROOT || data->perm == PERM_ANDROID) + return 1; + return 0; +} + +static int needs_fixup(perm_t perm) +{ + if (perm == PERM_ANDROID_DATA || perm == PERM_ANDROID_OBB + || perm == PERM_ANDROID_MEDIA) + return 1; + return 0; +} + +static void __fixup_perms_recursive(struct dentry *dentry, struct limit_search *limit, int depth) +{ + struct dentry *child; + struct sdcardfs_inode_info *info; + + /* + * All paths will terminate their recursion on hitting PERM_ANDROID_OBB, + * PERM_ANDROID_MEDIA, or PERM_ANDROID_DATA. This happens at a depth of + * at most 3. + */ + WARN(depth > 3, "%s: Max expected depth exceeded!\n", __func__); + spin_lock_nested(&dentry->d_lock, depth); + if (!d_inode(dentry)) { + spin_unlock(&dentry->d_lock); + return; + } + info = SDCARDFS_I(d_inode(dentry)); + + if (needs_fixup(info->data->perm)) { + list_for_each_entry(child, &dentry->d_subdirs, d_child) { + spin_lock_nested(&child->d_lock, depth + 1); + if (!(limit->flags & BY_NAME) || qstr_case_eq(&child->d_name, &limit->name)) { + if (d_inode(child)) { + get_derived_permission(dentry, child); + fixup_tmp_permissions(d_inode(child)); + spin_unlock(&child->d_lock); + break; + } + } + spin_unlock(&child->d_lock); + } + } else if (descendant_may_need_fixup(info->data, limit)) { + list_for_each_entry(child, &dentry->d_subdirs, d_child) { + __fixup_perms_recursive(child, limit, depth + 1); + } + } + spin_unlock(&dentry->d_lock); +} + +void fixup_perms_recursive(struct dentry *dentry, struct limit_search *limit) +{ + __fixup_perms_recursive(dentry, limit, 0); +} + +/* main function for updating derived permission */ +inline void update_derived_permission_lock(struct dentry *dentry) +{ + struct dentry *parent; + + if (!dentry || !d_inode(dentry)) { + pr_err("sdcardfs: %s: invalid dentry\n", __func__); + return; + } + /* FIXME: + * 1. need to check whether the dentry is updated or not + * 2. remove the root dentry update + */ + if (!IS_ROOT(dentry)) { + parent = dget_parent(dentry); + if (parent) { + get_derived_permission(parent, dentry); + dput(parent); + } + } + fixup_tmp_permissions(d_inode(dentry)); +} + +int need_graft_path(struct dentry *dentry) +{ + int ret = 0; + struct dentry *parent = dget_parent(dentry); + struct sdcardfs_inode_info *parent_info = SDCARDFS_I(d_inode(parent)); + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + struct qstr obb = QSTR_LITERAL("obb"); + + if (!sbi->options.unshared_obb && + parent_info->data->perm == PERM_ANDROID && + qstr_case_eq(&dentry->d_name, &obb)) { + + /* /Android/obb is the base obbpath of DERIVED_UNIFIED */ + if (!(sbi->options.multiuser == false + && parent_info->data->userid == 0)) { + ret = 1; + } + } + dput(parent); + return ret; +} + +int is_obbpath_invalid(struct dentry *dent) +{ + int ret = 0; + struct sdcardfs_dentry_info *di = SDCARDFS_D(dent); + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dent->d_sb); + char *path_buf, *obbpath_s; + int need_put = 0; + struct path lower_path; + + /* check the base obbpath has been changed. + * this routine can check an uninitialized obb dentry as well. + * regarding the uninitialized obb, refer to the sdcardfs_mkdir() + */ + spin_lock(&di->lock); + if (di->orig_path.dentry) { + if (!di->lower_path.dentry) { + ret = 1; + } else { + path_get(&di->lower_path); + + path_buf = kmalloc(PATH_MAX, GFP_ATOMIC); + if (!path_buf) { + ret = 1; + pr_err("sdcardfs: fail to allocate path_buf in %s.\n", __func__); + } else { + obbpath_s = d_path(&di->lower_path, path_buf, PATH_MAX); + if (d_unhashed(di->lower_path.dentry) || + !str_case_eq(sbi->obbpath_s, obbpath_s)) { + ret = 1; + } + kfree(path_buf); + } + + pathcpy(&lower_path, &di->lower_path); + need_put = 1; + } + } + spin_unlock(&di->lock); + if (need_put) + path_put(&lower_path); + return ret; +} + +int is_base_obbpath(struct dentry *dentry) +{ + int ret = 0; + struct dentry *parent = dget_parent(dentry); + struct sdcardfs_inode_info *parent_info = SDCARDFS_I(d_inode(parent)); + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + struct qstr q_obb = QSTR_LITERAL("obb"); + + spin_lock(&SDCARDFS_D(dentry)->lock); + if (sbi->options.multiuser) { + if (parent_info->data->perm == PERM_PRE_ROOT && + qstr_case_eq(&dentry->d_name, &q_obb)) { + ret = 1; + } + } else if (parent_info->data->perm == PERM_ANDROID && + qstr_case_eq(&dentry->d_name, &q_obb)) { + ret = 1; + } + spin_unlock(&SDCARDFS_D(dentry)->lock); + return ret; +} + +/* The lower_path will be stored to the dentry's orig_path + * and the base obbpath will be copyed to the lower_path variable. + * if an error returned, there's no change in the lower_path + * returns: -ERRNO if error (0: no error) + */ +int setup_obb_dentry(struct dentry *dentry, struct path *lower_path) +{ + int err = 0; + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + struct path obbpath; + + /* A local obb dentry must have its own orig_path to support rmdir + * and mkdir of itself. Usually, we expect that the sbi->obbpath + * is avaiable on this stage. + */ + sdcardfs_set_orig_path(dentry, lower_path); + + err = kern_path(sbi->obbpath_s, + LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &obbpath); + + if (!err) { + /* the obbpath base has been found */ + pathcpy(lower_path, &obbpath); + } else { + /* if the sbi->obbpath is not available, we can optionally + * setup the lower_path with its orig_path. + * but, the current implementation just returns an error + * because the sdcard daemon also regards this case as + * a lookup fail. + */ + pr_info("sdcardfs: the sbi->obbpath is not available\n"); + } + return err; +} + + diff --git a/fs/sdcardfs/file.c b/fs/sdcardfs/file.c new file mode 100644 index 000000000000..271c4c4cb760 --- /dev/null +++ b/fs/sdcardfs/file.c @@ -0,0 +1,467 @@ +/* + * fs/sdcardfs/file.c + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#include "sdcardfs.h" +#ifdef CONFIG_SDCARD_FS_FADV_NOACTIVE +#include <linux/backing-dev.h> +#endif + +static ssize_t sdcardfs_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + int err; + struct file *lower_file; + struct dentry *dentry = file->f_path.dentry; +#ifdef CONFIG_SDCARD_FS_FADV_NOACTIVE + struct backing_dev_info *bdi; +#endif + + lower_file = sdcardfs_lower_file(file); + +#ifdef CONFIG_SDCARD_FS_FADV_NOACTIVE + if (file->f_mode & FMODE_NOACTIVE) { + if (!(lower_file->f_mode & FMODE_NOACTIVE)) { + bdi = lower_file->f_mapping->backing_dev_info; + lower_file->f_ra.ra_pages = bdi->ra_pages * 2; + spin_lock(&lower_file->f_lock); + lower_file->f_mode |= FMODE_NOACTIVE; + spin_unlock(&lower_file->f_lock); + } + } +#endif + + err = vfs_read(lower_file, buf, count, ppos); + /* update our inode atime upon a successful lower read */ + if (err >= 0) + fsstack_copy_attr_atime(d_inode(dentry), + file_inode(lower_file)); + + return err; +} + +static ssize_t sdcardfs_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + int err; + struct file *lower_file; + struct dentry *dentry = file->f_path.dentry; + struct inode *inode = d_inode(dentry); + + /* check disk space */ + if (!check_min_free_space(dentry, count, 0)) { + pr_err("No minimum free space.\n"); + return -ENOSPC; + } + + lower_file = sdcardfs_lower_file(file); + err = vfs_write(lower_file, buf, count, ppos); + /* update our inode times+sizes upon a successful lower write */ + if (err >= 0) { + if (sizeof(loff_t) > sizeof(long)) + inode_lock(inode); + fsstack_copy_inode_size(inode, file_inode(lower_file)); + fsstack_copy_attr_times(inode, file_inode(lower_file)); + if (sizeof(loff_t) > sizeof(long)) + inode_unlock(inode); + } + + return err; +} + +static int sdcardfs_readdir(struct file *file, struct dir_context *ctx) +{ + int err; + struct file *lower_file = NULL; + struct dentry *dentry = file->f_path.dentry; + + lower_file = sdcardfs_lower_file(file); + + lower_file->f_pos = file->f_pos; + err = iterate_dir(lower_file, ctx); + file->f_pos = lower_file->f_pos; + if (err >= 0) /* copy the atime */ + fsstack_copy_attr_atime(d_inode(dentry), + file_inode(lower_file)); + return err; +} + +static long sdcardfs_unlocked_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + long err = -ENOTTY; + struct file *lower_file; + const struct cred *saved_cred = NULL; + struct dentry *dentry = file->f_path.dentry; + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + + lower_file = sdcardfs_lower_file(file); + + /* XXX: use vfs_ioctl if/when VFS exports it */ + if (!lower_file || !lower_file->f_op) + goto out; + + /* save current_cred and override it */ + saved_cred = override_fsids(sbi, SDCARDFS_I(file_inode(file))->data); + if (!saved_cred) { + err = -ENOMEM; + goto out; + } + + if (lower_file->f_op->unlocked_ioctl) + err = lower_file->f_op->unlocked_ioctl(lower_file, cmd, arg); + + /* some ioctls can change inode attributes (EXT2_IOC_SETFLAGS) */ + if (!err) + sdcardfs_copy_and_fix_attrs(file_inode(file), + file_inode(lower_file)); + revert_fsids(saved_cred); +out: + return err; +} + +#ifdef CONFIG_COMPAT +static long sdcardfs_compat_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + long err = -ENOTTY; + struct file *lower_file; + const struct cred *saved_cred = NULL; + struct dentry *dentry = file->f_path.dentry; + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + + lower_file = sdcardfs_lower_file(file); + + /* XXX: use vfs_ioctl if/when VFS exports it */ + if (!lower_file || !lower_file->f_op) + goto out; + + /* save current_cred and override it */ + saved_cred = override_fsids(sbi, SDCARDFS_I(file_inode(file))->data); + if (!saved_cred) { + err = -ENOMEM; + goto out; + } + + if (lower_file->f_op->compat_ioctl) + err = lower_file->f_op->compat_ioctl(lower_file, cmd, arg); + + revert_fsids(saved_cred); +out: + return err; +} +#endif + +static int sdcardfs_mmap(struct file *file, struct vm_area_struct *vma) +{ + int err = 0; + bool willwrite; + struct file *lower_file; + const struct vm_operations_struct *saved_vm_ops = NULL; + + /* this might be deferred to mmap's writepage */ + willwrite = ((vma->vm_flags | VM_SHARED | VM_WRITE) == vma->vm_flags); + + /* + * File systems which do not implement ->writepage may use + * generic_file_readonly_mmap as their ->mmap op. If you call + * generic_file_readonly_mmap with VM_WRITE, you'd get an -EINVAL. + * But we cannot call the lower ->mmap op, so we can't tell that + * writeable mappings won't work. Therefore, our only choice is to + * check if the lower file system supports the ->writepage, and if + * not, return EINVAL (the same error that + * generic_file_readonly_mmap returns in that case). + */ + lower_file = sdcardfs_lower_file(file); + if (willwrite && !lower_file->f_mapping->a_ops->writepage) { + err = -EINVAL; + pr_err("sdcardfs: lower file system does not support writeable mmap\n"); + goto out; + } + + /* + * find and save lower vm_ops. + * + * XXX: the VFS should have a cleaner way of finding the lower vm_ops + */ + if (!SDCARDFS_F(file)->lower_vm_ops) { + err = lower_file->f_op->mmap(lower_file, vma); + if (err) { + pr_err("sdcardfs: lower mmap failed %d\n", err); + goto out; + } + saved_vm_ops = vma->vm_ops; /* save: came from lower ->mmap */ + } + + /* + * Next 3 lines are all I need from generic_file_mmap. I definitely + * don't want its test for ->readpage which returns -ENOEXEC. + */ + file_accessed(file); + vma->vm_ops = &sdcardfs_vm_ops; + + file->f_mapping->a_ops = &sdcardfs_aops; /* set our aops */ + if (!SDCARDFS_F(file)->lower_vm_ops) /* save for our ->fault */ + SDCARDFS_F(file)->lower_vm_ops = saved_vm_ops; + vma->vm_private_data = file; + get_file(lower_file); + vma->vm_file = lower_file; + +out: + return err; +} + +static int sdcardfs_open(struct inode *inode, struct file *file) +{ + int err = 0; + struct file *lower_file = NULL; + struct path lower_path; + struct dentry *dentry = file->f_path.dentry; + struct dentry *parent = dget_parent(dentry); + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + const struct cred *saved_cred = NULL; + + /* don't open unhashed/deleted files */ + if (d_unhashed(dentry)) { + err = -ENOENT; + goto out_err; + } + + if (!check_caller_access_to_name(d_inode(parent), &dentry->d_name)) { + err = -EACCES; + goto out_err; + } + + /* save current_cred and override it */ + saved_cred = override_fsids(sbi, SDCARDFS_I(inode)->data); + if (!saved_cred) { + err = -ENOMEM; + goto out_err; + } + + file->private_data = + kzalloc(sizeof(struct sdcardfs_file_info), GFP_KERNEL); + if (!SDCARDFS_F(file)) { + err = -ENOMEM; + goto out_revert_cred; + } + + /* open lower object and link sdcardfs's file struct to lower's */ + sdcardfs_get_lower_path(file->f_path.dentry, &lower_path); + lower_file = dentry_open(&lower_path, file->f_flags, current_cred()); + path_put(&lower_path); + if (IS_ERR(lower_file)) { + err = PTR_ERR(lower_file); + lower_file = sdcardfs_lower_file(file); + if (lower_file) { + sdcardfs_set_lower_file(file, NULL); + fput(lower_file); /* fput calls dput for lower_dentry */ + } + } else { + sdcardfs_set_lower_file(file, lower_file); + } + + if (err) + kfree(SDCARDFS_F(file)); + else + sdcardfs_copy_and_fix_attrs(inode, sdcardfs_lower_inode(inode)); + +out_revert_cred: + revert_fsids(saved_cred); +out_err: + dput(parent); + return err; +} + +static int sdcardfs_flush(struct file *file, fl_owner_t id) +{ + int err = 0; + struct file *lower_file = NULL; + + lower_file = sdcardfs_lower_file(file); + if (lower_file && lower_file->f_op && lower_file->f_op->flush) { + filemap_write_and_wait(file->f_mapping); + err = lower_file->f_op->flush(lower_file, id); + } + + return err; +} + +/* release all lower object references & free the file info structure */ +static int sdcardfs_file_release(struct inode *inode, struct file *file) +{ + struct file *lower_file; + + lower_file = sdcardfs_lower_file(file); + if (lower_file) { + sdcardfs_set_lower_file(file, NULL); + fput(lower_file); + } + + kfree(SDCARDFS_F(file)); + return 0; +} + +static int sdcardfs_fsync(struct file *file, loff_t start, loff_t end, + int datasync) +{ + int err; + struct file *lower_file; + struct path lower_path; + struct dentry *dentry = file->f_path.dentry; + + err = __generic_file_fsync(file, start, end, datasync); + if (err) + goto out; + + lower_file = sdcardfs_lower_file(file); + sdcardfs_get_lower_path(dentry, &lower_path); + err = vfs_fsync_range(lower_file, start, end, datasync); + sdcardfs_put_lower_path(dentry, &lower_path); +out: + return err; +} + +static int sdcardfs_fasync(int fd, struct file *file, int flag) +{ + int err = 0; + struct file *lower_file = NULL; + + lower_file = sdcardfs_lower_file(file); + if (lower_file->f_op && lower_file->f_op->fasync) + err = lower_file->f_op->fasync(fd, lower_file, flag); + + return err; +} + +/* + * Sdcardfs cannot use generic_file_llseek as ->llseek, because it would + * only set the offset of the upper file. So we have to implement our + * own method to set both the upper and lower file offsets + * consistently. + */ +static loff_t sdcardfs_file_llseek(struct file *file, loff_t offset, int whence) +{ + int err; + struct file *lower_file; + + err = generic_file_llseek(file, offset, whence); + if (err < 0) + goto out; + + lower_file = sdcardfs_lower_file(file); + err = generic_file_llseek(lower_file, offset, whence); + +out: + return err; +} + +/* + * Sdcardfs read_iter, redirect modified iocb to lower read_iter + */ +ssize_t sdcardfs_read_iter(struct kiocb *iocb, struct iov_iter *iter) +{ + int err; + struct file *file = iocb->ki_filp, *lower_file; + + lower_file = sdcardfs_lower_file(file); + if (!lower_file->f_op->read_iter) { + err = -EINVAL; + goto out; + } + + get_file(lower_file); /* prevent lower_file from being released */ + iocb->ki_filp = lower_file; + err = lower_file->f_op->read_iter(iocb, iter); + iocb->ki_filp = file; + fput(lower_file); + /* update upper inode atime as needed */ + if (err >= 0 || err == -EIOCBQUEUED) + fsstack_copy_attr_atime(file->f_path.dentry->d_inode, + file_inode(lower_file)); +out: + return err; +} + +/* + * Sdcardfs write_iter, redirect modified iocb to lower write_iter + */ +ssize_t sdcardfs_write_iter(struct kiocb *iocb, struct iov_iter *iter) +{ + int err; + struct file *file = iocb->ki_filp, *lower_file; + struct inode *inode = file->f_path.dentry->d_inode; + + lower_file = sdcardfs_lower_file(file); + if (!lower_file->f_op->write_iter) { + err = -EINVAL; + goto out; + } + + get_file(lower_file); /* prevent lower_file from being released */ + iocb->ki_filp = lower_file; + err = lower_file->f_op->write_iter(iocb, iter); + iocb->ki_filp = file; + fput(lower_file); + /* update upper inode times/sizes as needed */ + if (err >= 0 || err == -EIOCBQUEUED) { + if (sizeof(loff_t) > sizeof(long)) + inode_lock(inode); + fsstack_copy_inode_size(inode, file_inode(lower_file)); + fsstack_copy_attr_times(inode, file_inode(lower_file)); + if (sizeof(loff_t) > sizeof(long)) + inode_unlock(inode); + } +out: + return err; +} + +const struct file_operations sdcardfs_main_fops = { + .llseek = generic_file_llseek, + .read = sdcardfs_read, + .write = sdcardfs_write, + .unlocked_ioctl = sdcardfs_unlocked_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = sdcardfs_compat_ioctl, +#endif + .mmap = sdcardfs_mmap, + .open = sdcardfs_open, + .flush = sdcardfs_flush, + .release = sdcardfs_file_release, + .fsync = sdcardfs_fsync, + .fasync = sdcardfs_fasync, + .read_iter = sdcardfs_read_iter, + .write_iter = sdcardfs_write_iter, +}; + +/* trimmed directory options */ +const struct file_operations sdcardfs_dir_fops = { + .llseek = sdcardfs_file_llseek, + .read = generic_read_dir, + .iterate = sdcardfs_readdir, + .unlocked_ioctl = sdcardfs_unlocked_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = sdcardfs_compat_ioctl, +#endif + .open = sdcardfs_open, + .release = sdcardfs_file_release, + .flush = sdcardfs_flush, + .fsync = sdcardfs_fsync, + .fasync = sdcardfs_fasync, +}; diff --git a/fs/sdcardfs/inode.c b/fs/sdcardfs/inode.c new file mode 100644 index 000000000000..4dd681e0d59d --- /dev/null +++ b/fs/sdcardfs/inode.c @@ -0,0 +1,821 @@ +/* + * fs/sdcardfs/inode.c + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#include "sdcardfs.h" +#include <linux/fs_struct.h> +#include <linux/ratelimit.h> +#include <linux/sched/task.h> + +const struct cred *override_fsids(struct sdcardfs_sb_info *sbi, + struct sdcardfs_inode_data *data) +{ + struct cred *cred; + const struct cred *old_cred; + uid_t uid; + + cred = prepare_creds(); + if (!cred) + return NULL; + + if (sbi->options.gid_derivation) { + if (data->under_obb) + uid = AID_MEDIA_OBB; + else + uid = multiuser_get_uid(data->userid, sbi->options.fs_low_uid); + } else { + uid = sbi->options.fs_low_uid; + } + cred->fsuid = make_kuid(&init_user_ns, uid); + cred->fsgid = make_kgid(&init_user_ns, sbi->options.fs_low_gid); + + old_cred = override_creds(cred); + + return old_cred; +} + +void revert_fsids(const struct cred *old_cred) +{ + const struct cred *cur_cred; + + cur_cred = current->cred; + revert_creds(old_cred); + put_cred(cur_cred); +} + +static int sdcardfs_create(struct inode *dir, struct dentry *dentry, + umode_t mode, bool want_excl) +{ + int err; + struct dentry *lower_dentry; + struct vfsmount *lower_dentry_mnt; + struct dentry *lower_parent_dentry = NULL; + struct path lower_path; + const struct cred *saved_cred = NULL; + struct fs_struct *saved_fs; + struct fs_struct *copied_fs; + + if (!check_caller_access_to_name(dir, &dentry->d_name)) { + err = -EACCES; + goto out_eacces; + } + + /* save current_cred and override it */ + saved_cred = override_fsids(SDCARDFS_SB(dir->i_sb), + SDCARDFS_I(dir)->data); + if (!saved_cred) + return -ENOMEM; + + sdcardfs_get_lower_path(dentry, &lower_path); + lower_dentry = lower_path.dentry; + lower_dentry_mnt = lower_path.mnt; + lower_parent_dentry = lock_parent(lower_dentry); + + /* set last 16bytes of mode field to 0664 */ + mode = (mode & S_IFMT) | 00664; + + /* temporarily change umask for lower fs write */ + saved_fs = current->fs; + copied_fs = copy_fs_struct(current->fs); + if (!copied_fs) { + err = -ENOMEM; + goto out_unlock; + } + copied_fs->umask = 0; + task_lock(current); + current->fs = copied_fs; + task_unlock(current); + + err = vfs_create2(lower_dentry_mnt, d_inode(lower_parent_dentry), lower_dentry, mode, want_excl); + if (err) + goto out; + + err = sdcardfs_interpose(dentry, dir->i_sb, &lower_path, + SDCARDFS_I(dir)->data->userid); + if (err) + goto out; + fsstack_copy_attr_times(dir, sdcardfs_lower_inode(dir)); + fsstack_copy_inode_size(dir, d_inode(lower_parent_dentry)); + fixup_lower_ownership(dentry, dentry->d_name.name); + +out: + task_lock(current); + current->fs = saved_fs; + task_unlock(current); + free_fs_struct(copied_fs); +out_unlock: + unlock_dir(lower_parent_dentry); + sdcardfs_put_lower_path(dentry, &lower_path); + revert_fsids(saved_cred); +out_eacces: + return err; +} + +static int sdcardfs_unlink(struct inode *dir, struct dentry *dentry) +{ + int err; + struct dentry *lower_dentry; + struct vfsmount *lower_mnt; + struct inode *lower_dir_inode = sdcardfs_lower_inode(dir); + struct dentry *lower_dir_dentry; + struct path lower_path; + const struct cred *saved_cred = NULL; + + if (!check_caller_access_to_name(dir, &dentry->d_name)) { + err = -EACCES; + goto out_eacces; + } + + /* save current_cred and override it */ + saved_cred = override_fsids(SDCARDFS_SB(dir->i_sb), + SDCARDFS_I(dir)->data); + if (!saved_cred) + return -ENOMEM; + + sdcardfs_get_lower_path(dentry, &lower_path); + lower_dentry = lower_path.dentry; + lower_mnt = lower_path.mnt; + dget(lower_dentry); + lower_dir_dentry = lock_parent(lower_dentry); + + err = vfs_unlink2(lower_mnt, lower_dir_inode, lower_dentry, NULL); + + /* + * Note: unlinking on top of NFS can cause silly-renamed files. + * Trying to delete such files results in EBUSY from NFS + * below. Silly-renamed files will get deleted by NFS later on, so + * we just need to detect them here and treat such EBUSY errors as + * if the upper file was successfully deleted. + */ + if (err == -EBUSY && lower_dentry->d_flags & DCACHE_NFSFS_RENAMED) + err = 0; + if (err) + goto out; + fsstack_copy_attr_times(dir, lower_dir_inode); + fsstack_copy_inode_size(dir, lower_dir_inode); + set_nlink(d_inode(dentry), + sdcardfs_lower_inode(d_inode(dentry))->i_nlink); + d_inode(dentry)->i_ctime = dir->i_ctime; + d_drop(dentry); /* this is needed, else LTP fails (VFS won't do it) */ +out: + unlock_dir(lower_dir_dentry); + dput(lower_dentry); + sdcardfs_put_lower_path(dentry, &lower_path); + revert_fsids(saved_cred); +out_eacces: + return err; +} + +static int touch(char *abs_path, mode_t mode) +{ + struct file *filp = filp_open(abs_path, O_RDWR|O_CREAT|O_EXCL|O_NOFOLLOW, mode); + + if (IS_ERR(filp)) { + if (PTR_ERR(filp) == -EEXIST) { + return 0; + } else { + pr_err("sdcardfs: failed to open(%s): %ld\n", + abs_path, PTR_ERR(filp)); + return PTR_ERR(filp); + } + } + filp_close(filp, current->files); + return 0; +} + +static int sdcardfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + int err; + int make_nomedia_in_obb = 0; + struct dentry *lower_dentry; + struct vfsmount *lower_mnt; + struct dentry *lower_parent_dentry = NULL; + struct dentry *parent_dentry = NULL; + struct path lower_path; + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + const struct cred *saved_cred = NULL; + struct sdcardfs_inode_data *pd = SDCARDFS_I(dir)->data; + int touch_err = 0; + struct fs_struct *saved_fs; + struct fs_struct *copied_fs; + struct qstr q_obb = QSTR_LITERAL("obb"); + struct qstr q_data = QSTR_LITERAL("data"); + + if (!check_caller_access_to_name(dir, &dentry->d_name)) { + err = -EACCES; + goto out_eacces; + } + + /* save current_cred and override it */ + saved_cred = override_fsids(SDCARDFS_SB(dir->i_sb), + SDCARDFS_I(dir)->data); + if (!saved_cred) + return -ENOMEM; + + /* check disk space */ + parent_dentry = dget_parent(dentry); + if (!check_min_free_space(parent_dentry, 0, 1)) { + pr_err("sdcardfs: No minimum free space.\n"); + err = -ENOSPC; + dput(parent_dentry); + goto out_revert; + } + dput(parent_dentry); + + /* the lower_dentry is negative here */ + sdcardfs_get_lower_path(dentry, &lower_path); + lower_dentry = lower_path.dentry; + lower_mnt = lower_path.mnt; + lower_parent_dentry = lock_parent(lower_dentry); + + /* set last 16bytes of mode field to 0775 */ + mode = (mode & S_IFMT) | 00775; + + /* temporarily change umask for lower fs write */ + saved_fs = current->fs; + copied_fs = copy_fs_struct(current->fs); + if (!copied_fs) { + err = -ENOMEM; + unlock_dir(lower_parent_dentry); + goto out_unlock; + } + copied_fs->umask = 0; + task_lock(current); + current->fs = copied_fs; + task_unlock(current); + + err = vfs_mkdir2(lower_mnt, d_inode(lower_parent_dentry), lower_dentry, mode); + + if (err) { + unlock_dir(lower_parent_dentry); + goto out; + } + + /* if it is a local obb dentry, setup it with the base obbpath */ + if (need_graft_path(dentry)) { + + err = setup_obb_dentry(dentry, &lower_path); + if (err) { + /* if the sbi->obbpath is not available, the lower_path won't be + * changed by setup_obb_dentry() but the lower path is saved to + * its orig_path. this dentry will be revalidated later. + * but now, the lower_path should be NULL + */ + sdcardfs_put_reset_lower_path(dentry); + + /* the newly created lower path which saved to its orig_path or + * the lower_path is the base obbpath. + * therefore, an additional path_get is required + */ + path_get(&lower_path); + } else + make_nomedia_in_obb = 1; + } + + err = sdcardfs_interpose(dentry, dir->i_sb, &lower_path, pd->userid); + if (err) { + unlock_dir(lower_parent_dentry); + goto out; + } + + fsstack_copy_attr_times(dir, sdcardfs_lower_inode(dir)); + fsstack_copy_inode_size(dir, d_inode(lower_parent_dentry)); + /* update number of links on parent directory */ + set_nlink(dir, sdcardfs_lower_inode(dir)->i_nlink); + fixup_lower_ownership(dentry, dentry->d_name.name); + unlock_dir(lower_parent_dentry); + if ((!sbi->options.multiuser) && (qstr_case_eq(&dentry->d_name, &q_obb)) + && (pd->perm == PERM_ANDROID) && (pd->userid == 0)) + make_nomedia_in_obb = 1; + + /* When creating /Android/data and /Android/obb, mark them as .nomedia */ + if (make_nomedia_in_obb || + ((pd->perm == PERM_ANDROID) + && (qstr_case_eq(&dentry->d_name, &q_data)))) { + revert_fsids(saved_cred); + saved_cred = override_fsids(sbi, + SDCARDFS_I(d_inode(dentry))->data); + if (!saved_cred) { + pr_err("sdcardfs: failed to set up .nomedia in %s: %d\n", + lower_path.dentry->d_name.name, + -ENOMEM); + goto out; + } + set_fs_pwd(current->fs, &lower_path); + touch_err = touch(".nomedia", 0664); + if (touch_err) { + pr_err("sdcardfs: failed to create .nomedia in %s: %d\n", + lower_path.dentry->d_name.name, + touch_err); + goto out; + } + } +out: + task_lock(current); + current->fs = saved_fs; + task_unlock(current); + + free_fs_struct(copied_fs); +out_unlock: + sdcardfs_put_lower_path(dentry, &lower_path); +out_revert: + revert_fsids(saved_cred); +out_eacces: + return err; +} + +static int sdcardfs_rmdir(struct inode *dir, struct dentry *dentry) +{ + struct dentry *lower_dentry; + struct dentry *lower_dir_dentry; + struct vfsmount *lower_mnt; + int err; + struct path lower_path; + const struct cred *saved_cred = NULL; + + if (!check_caller_access_to_name(dir, &dentry->d_name)) { + err = -EACCES; + goto out_eacces; + } + + /* save current_cred and override it */ + saved_cred = override_fsids(SDCARDFS_SB(dir->i_sb), + SDCARDFS_I(dir)->data); + if (!saved_cred) + return -ENOMEM; + + /* sdcardfs_get_real_lower(): in case of remove an user's obb dentry + * the dentry on the original path should be deleted. + */ + sdcardfs_get_real_lower(dentry, &lower_path); + + lower_dentry = lower_path.dentry; + lower_mnt = lower_path.mnt; + lower_dir_dentry = lock_parent(lower_dentry); + + err = vfs_rmdir2(lower_mnt, d_inode(lower_dir_dentry), lower_dentry); + if (err) + goto out; + + d_drop(dentry); /* drop our dentry on success (why not VFS's job?) */ + if (d_inode(dentry)) + clear_nlink(d_inode(dentry)); + fsstack_copy_attr_times(dir, d_inode(lower_dir_dentry)); + fsstack_copy_inode_size(dir, d_inode(lower_dir_dentry)); + set_nlink(dir, d_inode(lower_dir_dentry)->i_nlink); + +out: + unlock_dir(lower_dir_dentry); + sdcardfs_put_real_lower(dentry, &lower_path); + revert_fsids(saved_cred); +out_eacces: + return err; +} + +/* + * The locking rules in sdcardfs_rename are complex. We could use a simpler + * superblock-level name-space lock for renames and copy-ups. + */ +static int sdcardfs_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, + unsigned int flags) +{ + int err = 0; + struct dentry *lower_old_dentry = NULL; + struct dentry *lower_new_dentry = NULL; + struct dentry *lower_old_dir_dentry = NULL; + struct dentry *lower_new_dir_dentry = NULL; + struct vfsmount *lower_mnt = NULL; + struct dentry *trap = NULL; + struct path lower_old_path, lower_new_path; + const struct cred *saved_cred = NULL; + + if (flags) + return -EINVAL; + + if (!check_caller_access_to_name(old_dir, &old_dentry->d_name) || + !check_caller_access_to_name(new_dir, &new_dentry->d_name)) { + err = -EACCES; + goto out_eacces; + } + + /* save current_cred and override it */ + saved_cred = override_fsids(SDCARDFS_SB(old_dir->i_sb), + SDCARDFS_I(new_dir)->data); + if (!saved_cred) + return -ENOMEM; + + sdcardfs_get_real_lower(old_dentry, &lower_old_path); + sdcardfs_get_lower_path(new_dentry, &lower_new_path); + lower_old_dentry = lower_old_path.dentry; + lower_new_dentry = lower_new_path.dentry; + lower_mnt = lower_old_path.mnt; + lower_old_dir_dentry = dget_parent(lower_old_dentry); + lower_new_dir_dentry = dget_parent(lower_new_dentry); + + trap = lock_rename(lower_old_dir_dentry, lower_new_dir_dentry); + /* source should not be ancestor of target */ + if (trap == lower_old_dentry) { + err = -EINVAL; + goto out; + } + /* target should not be ancestor of source */ + if (trap == lower_new_dentry) { + err = -ENOTEMPTY; + goto out; + } + + err = vfs_rename2(lower_mnt, + d_inode(lower_old_dir_dentry), lower_old_dentry, + d_inode(lower_new_dir_dentry), lower_new_dentry, + NULL, 0); + if (err) + goto out; + + /* Copy attrs from lower dir, but i_uid/i_gid */ + sdcardfs_copy_and_fix_attrs(new_dir, d_inode(lower_new_dir_dentry)); + fsstack_copy_inode_size(new_dir, d_inode(lower_new_dir_dentry)); + + if (new_dir != old_dir) { + sdcardfs_copy_and_fix_attrs(old_dir, d_inode(lower_old_dir_dentry)); + fsstack_copy_inode_size(old_dir, d_inode(lower_old_dir_dentry)); + } + get_derived_permission_new(new_dentry->d_parent, old_dentry, &new_dentry->d_name); + fixup_tmp_permissions(d_inode(old_dentry)); + fixup_lower_ownership(old_dentry, new_dentry->d_name.name); + d_invalidate(old_dentry); /* Can't fixup ownership recursively :( */ +out: + unlock_rename(lower_old_dir_dentry, lower_new_dir_dentry); + dput(lower_old_dir_dentry); + dput(lower_new_dir_dentry); + sdcardfs_put_real_lower(old_dentry, &lower_old_path); + sdcardfs_put_lower_path(new_dentry, &lower_new_path); + revert_fsids(saved_cred); +out_eacces: + return err; +} + +#if 0 +static int sdcardfs_readlink(struct dentry *dentry, char __user *buf, int bufsiz) +{ + int err; + struct dentry *lower_dentry; + struct path lower_path; + /* XXX readlink does not requires overriding credential */ + + sdcardfs_get_lower_path(dentry, &lower_path); + lower_dentry = lower_path.dentry; + if (!d_inode(lower_dentry)->i_op || + !d_inode(lower_dentry)->i_op->readlink) { + err = -EINVAL; + goto out; + } + + err = d_inode(lower_dentry)->i_op->readlink(lower_dentry, + buf, bufsiz); + if (err < 0) + goto out; + fsstack_copy_attr_atime(d_inode(dentry), d_inode(lower_dentry)); + +out: + sdcardfs_put_lower_path(dentry, &lower_path); + return err; +} +#endif + +#if 0 +static const char *sdcardfs_follow_link(struct dentry *dentry, void **cookie) +{ + char *buf; + int len = PAGE_SIZE, err; + mm_segment_t old_fs; + + /* This is freed by the put_link method assuming a successful call. */ + buf = kmalloc(len, GFP_KERNEL); + if (!buf) { + buf = ERR_PTR(-ENOMEM); + return buf; + } + + /* read the symlink, and then we will follow it */ + old_fs = get_fs(); + set_fs(KERNEL_DS); + err = sdcardfs_readlink(dentry, buf, len); + set_fs(old_fs); + if (err < 0) { + kfree(buf); + buf = ERR_PTR(err); + } else { + buf[err] = '\0'; + } + return *cookie = buf; +} +#endif + +static int sdcardfs_permission_wrn(struct inode *inode, int mask) +{ + WARN_RATELIMIT(1, "sdcardfs does not support permission. Use permission2.\n"); + return -EINVAL; +} + +void copy_attrs(struct inode *dest, const struct inode *src) +{ + dest->i_mode = src->i_mode; + dest->i_uid = src->i_uid; + dest->i_gid = src->i_gid; + dest->i_rdev = src->i_rdev; + dest->i_atime = src->i_atime; + dest->i_mtime = src->i_mtime; + dest->i_ctime = src->i_ctime; + dest->i_blkbits = src->i_blkbits; + dest->i_flags = src->i_flags; +#ifdef CONFIG_FS_POSIX_ACL + dest->i_acl = src->i_acl; +#endif +#ifdef CONFIG_SECURITY + dest->i_security = src->i_security; +#endif +} + +static int sdcardfs_permission(struct vfsmount *mnt, struct inode *inode, int mask) +{ + int err; + struct inode tmp; + struct sdcardfs_inode_data *top = top_data_get(SDCARDFS_I(inode)); + + if (IS_ERR(mnt)) + return PTR_ERR(mnt); + + if (!top) + return -EINVAL; + + /* + * Permission check on sdcardfs inode. + * Calling process should have AID_SDCARD_RW permission + * Since generic_permission only needs i_mode, i_uid, + * i_gid, and i_sb, we can create a fake inode to pass + * this information down in. + * + * The underlying code may attempt to take locks in some + * cases for features we're not using, but if that changes, + * locks must be dealt with to avoid undefined behavior. + */ + copy_attrs(&tmp, inode); + tmp.i_uid = make_kuid(&init_user_ns, top->d_uid); + tmp.i_gid = make_kgid(&init_user_ns, get_gid(mnt, inode->i_sb, top)); + tmp.i_mode = (inode->i_mode & S_IFMT) + | get_mode(mnt, SDCARDFS_I(inode), top); + data_put(top); + tmp.i_sb = inode->i_sb; + if (IS_POSIXACL(inode)) + pr_warn("%s: This may be undefined behavior...\n", __func__); + err = generic_permission(&tmp, mask); + return err; +} + +static int sdcardfs_setattr_wrn(struct dentry *dentry, struct iattr *ia) +{ + WARN_RATELIMIT(1, "sdcardfs does not support setattr. User setattr2.\n"); + return -EINVAL; +} + +static int sdcardfs_setattr(struct vfsmount *mnt, struct dentry *dentry, struct iattr *ia) +{ + int err; + struct dentry *lower_dentry; + struct vfsmount *lower_mnt; + struct inode *inode; + struct inode *lower_inode; + struct path lower_path; + struct iattr lower_ia; + struct dentry *parent; + struct inode tmp; + struct dentry tmp_d; + struct sdcardfs_inode_data *top; + + const struct cred *saved_cred = NULL; + + inode = d_inode(dentry); + top = top_data_get(SDCARDFS_I(inode)); + + if (!top) + return -EINVAL; + + /* + * Permission check on sdcardfs inode. + * Calling process should have AID_SDCARD_RW permission + * Since generic_permission only needs i_mode, i_uid, + * i_gid, and i_sb, we can create a fake inode to pass + * this information down in. + * + * The underlying code may attempt to take locks in some + * cases for features we're not using, but if that changes, + * locks must be dealt with to avoid undefined behavior. + * + */ + copy_attrs(&tmp, inode); + tmp.i_uid = make_kuid(&init_user_ns, top->d_uid); + tmp.i_gid = make_kgid(&init_user_ns, get_gid(mnt, dentry->d_sb, top)); + tmp.i_mode = (inode->i_mode & S_IFMT) + | get_mode(mnt, SDCARDFS_I(inode), top); + tmp.i_size = i_size_read(inode); + data_put(top); + tmp.i_sb = inode->i_sb; + tmp_d.d_inode = &tmp; + + /* + * Check if user has permission to change dentry. We don't check if + * this user can change the lower inode: that should happen when + * calling notify_change on the lower inode. + */ + /* prepare our own lower struct iattr (with the lower file) */ + memcpy(&lower_ia, ia, sizeof(lower_ia)); + /* Allow touch updating timestamps. A previous permission check ensures + * we have write access. Changes to mode, owner, and group are ignored + */ + ia->ia_valid |= ATTR_FORCE; + err = setattr_prepare(&tmp_d, ia); + + if (!err) { + /* check the Android group ID */ + parent = dget_parent(dentry); + if (!check_caller_access_to_name(d_inode(parent), &dentry->d_name)) + err = -EACCES; + dput(parent); + } + + if (err) + goto out_err; + + /* save current_cred and override it */ + saved_cred = override_fsids(SDCARDFS_SB(dentry->d_sb), + SDCARDFS_I(inode)->data); + if (!saved_cred) + return -ENOMEM; + + sdcardfs_get_lower_path(dentry, &lower_path); + lower_dentry = lower_path.dentry; + lower_mnt = lower_path.mnt; + lower_inode = sdcardfs_lower_inode(inode); + + if (ia->ia_valid & ATTR_FILE) + lower_ia.ia_file = sdcardfs_lower_file(ia->ia_file); + + lower_ia.ia_valid &= ~(ATTR_UID | ATTR_GID | ATTR_MODE); + + /* + * If shrinking, first truncate upper level to cancel writing dirty + * pages beyond the new eof; and also if its' maxbytes is more + * limiting (fail with -EFBIG before making any change to the lower + * level). There is no need to vmtruncate the upper level + * afterwards in the other cases: we fsstack_copy_inode_size from + * the lower level. + */ + if (ia->ia_valid & ATTR_SIZE) { + err = inode_newsize_ok(&tmp, ia->ia_size); + if (err) { + goto out; + } + truncate_setsize(inode, ia->ia_size); + } + + /* + * mode change is for clearing setuid/setgid bits. Allow lower fs + * to interpret this in its own way. + */ + if (lower_ia.ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) + lower_ia.ia_valid &= ~ATTR_MODE; + + /* notify the (possibly copied-up) lower inode */ + /* + * Note: we use d_inode(lower_dentry), because lower_inode may be + * unlinked (no inode->i_sb and i_ino==0. This happens if someone + * tries to open(), unlink(), then ftruncate() a file. + */ + inode_lock(d_inode(lower_dentry)); + err = notify_change2(lower_mnt, lower_dentry, &lower_ia, /* note: lower_ia */ + NULL); + inode_unlock(d_inode(lower_dentry)); + if (err) + goto out; + + /* get attributes from the lower inode and update derived permissions */ + sdcardfs_copy_and_fix_attrs(inode, lower_inode); + + /* + * Not running fsstack_copy_inode_size(inode, lower_inode), because + * VFS should update our inode size, and notify_change on + * lower_inode should update its size. + */ + +out: + sdcardfs_put_lower_path(dentry, &lower_path); + revert_fsids(saved_cred); +out_err: + return err; +} + +static int sdcardfs_fillattr(struct vfsmount *mnt, struct inode *inode, + struct kstat *lower_stat, struct kstat *stat) +{ + struct sdcardfs_inode_info *info = SDCARDFS_I(inode); + struct sdcardfs_inode_data *top = top_data_get(info); + struct super_block *sb = inode->i_sb; + + if (!top) + return -EINVAL; + + stat->dev = inode->i_sb->s_dev; + stat->ino = inode->i_ino; + stat->mode = (inode->i_mode & S_IFMT) | get_mode(mnt, info, top); + stat->nlink = inode->i_nlink; + stat->uid = make_kuid(&init_user_ns, top->d_uid); + stat->gid = make_kgid(&init_user_ns, get_gid(mnt, sb, top)); + stat->rdev = inode->i_rdev; + stat->size = lower_stat->size; + stat->atime = lower_stat->atime; + stat->mtime = lower_stat->mtime; + stat->ctime = lower_stat->ctime; + stat->blksize = lower_stat->blksize; + stat->blocks = lower_stat->blocks; + data_put(top); + return 0; +} +static int sdcardfs_getattr(const struct path *path, struct kstat *stat, + u32 request_mask, unsigned int flags) +{ + struct vfsmount *mnt = path->mnt; + struct dentry *dentry = path->dentry; + struct kstat lower_stat; + struct path lower_path; + struct dentry *parent; + int err; + + parent = dget_parent(dentry); + if (!check_caller_access_to_name(d_inode(parent), &dentry->d_name)) { + dput(parent); + return -EACCES; + } + dput(parent); + + sdcardfs_get_lower_path(dentry, &lower_path); + err = vfs_getattr(&lower_path, &lower_stat, request_mask, flags); + if (err) + goto out; + sdcardfs_copy_and_fix_attrs(d_inode(dentry), + d_inode(lower_path.dentry)); + err = sdcardfs_fillattr(mnt, d_inode(dentry), &lower_stat, stat); +out: + sdcardfs_put_lower_path(dentry, &lower_path); + return err; +} + +const struct inode_operations sdcardfs_symlink_iops = { + .permission2 = sdcardfs_permission, + .setattr2 = sdcardfs_setattr, + /* XXX Following operations are implemented, + * but FUSE(sdcard) or FAT does not support them + * These methods are *NOT* perfectly tested. + .readlink = sdcardfs_readlink, + .follow_link = sdcardfs_follow_link, + .put_link = kfree_put_link, + */ +}; + +const struct inode_operations sdcardfs_dir_iops = { + .create = sdcardfs_create, + .lookup = sdcardfs_lookup, + .permission = sdcardfs_permission_wrn, + .permission2 = sdcardfs_permission, + .unlink = sdcardfs_unlink, + .mkdir = sdcardfs_mkdir, + .rmdir = sdcardfs_rmdir, + .rename = sdcardfs_rename, + .setattr = sdcardfs_setattr_wrn, + .setattr2 = sdcardfs_setattr, + .getattr = sdcardfs_getattr, +}; + +const struct inode_operations sdcardfs_main_iops = { + .permission = sdcardfs_permission_wrn, + .permission2 = sdcardfs_permission, + .setattr = sdcardfs_setattr_wrn, + .setattr2 = sdcardfs_setattr, + .getattr = sdcardfs_getattr, +}; diff --git a/fs/sdcardfs/lookup.c b/fs/sdcardfs/lookup.c new file mode 100644 index 000000000000..73179ce2591f --- /dev/null +++ b/fs/sdcardfs/lookup.c @@ -0,0 +1,470 @@ +/* + * fs/sdcardfs/lookup.c + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#include "sdcardfs.h" +#include "linux/delay.h" + +/* The dentry cache is just so we have properly sized dentries */ +static struct kmem_cache *sdcardfs_dentry_cachep; + +int sdcardfs_init_dentry_cache(void) +{ + sdcardfs_dentry_cachep = + kmem_cache_create("sdcardfs_dentry", + sizeof(struct sdcardfs_dentry_info), + 0, SLAB_RECLAIM_ACCOUNT, NULL); + + return sdcardfs_dentry_cachep ? 0 : -ENOMEM; +} + +void sdcardfs_destroy_dentry_cache(void) +{ + kmem_cache_destroy(sdcardfs_dentry_cachep); +} + +void free_dentry_private_data(struct dentry *dentry) +{ + kmem_cache_free(sdcardfs_dentry_cachep, dentry->d_fsdata); + dentry->d_fsdata = NULL; +} + +/* allocate new dentry private data */ +int new_dentry_private_data(struct dentry *dentry) +{ + struct sdcardfs_dentry_info *info = SDCARDFS_D(dentry); + + /* use zalloc to init dentry_info.lower_path */ + info = kmem_cache_zalloc(sdcardfs_dentry_cachep, GFP_ATOMIC); + if (!info) + return -ENOMEM; + + spin_lock_init(&info->lock); + dentry->d_fsdata = info; + + return 0; +} + +struct inode_data { + struct inode *lower_inode; + userid_t id; +}; + +static int sdcardfs_inode_test(struct inode *inode, void *candidate_data/*void *candidate_lower_inode*/) +{ + struct inode *current_lower_inode = sdcardfs_lower_inode(inode); + userid_t current_userid = SDCARDFS_I(inode)->data->userid; + + if (current_lower_inode == ((struct inode_data *)candidate_data)->lower_inode && + current_userid == ((struct inode_data *)candidate_data)->id) + return 1; /* found a match */ + else + return 0; /* no match */ +} + +static int sdcardfs_inode_set(struct inode *inode, void *lower_inode) +{ + /* we do actual inode initialization in sdcardfs_iget */ + return 0; +} + +struct inode *sdcardfs_iget(struct super_block *sb, struct inode *lower_inode, userid_t id) +{ + struct sdcardfs_inode_info *info; + struct inode_data data; + struct inode *inode; /* the new inode to return */ + + if (!igrab(lower_inode)) + return ERR_PTR(-ESTALE); + + data.id = id; + data.lower_inode = lower_inode; + inode = iget5_locked(sb, /* our superblock */ + /* + * hashval: we use inode number, but we can + * also use "(unsigned long)lower_inode" + * instead. + */ + lower_inode->i_ino, /* hashval */ + sdcardfs_inode_test, /* inode comparison function */ + sdcardfs_inode_set, /* inode init function */ + &data); /* data passed to test+set fxns */ + if (!inode) { + iput(lower_inode); + return ERR_PTR(-ENOMEM); + } + /* if found a cached inode, then just return it (after iput) */ + if (!(inode->i_state & I_NEW)) { + iput(lower_inode); + return inode; + } + + /* initialize new inode */ + info = SDCARDFS_I(inode); + + inode->i_ino = lower_inode->i_ino; + sdcardfs_set_lower_inode(inode, lower_inode); + + inode->i_version++; + + /* use different set of inode ops for symlinks & directories */ + if (S_ISDIR(lower_inode->i_mode)) + inode->i_op = &sdcardfs_dir_iops; + else if (S_ISLNK(lower_inode->i_mode)) + inode->i_op = &sdcardfs_symlink_iops; + else + inode->i_op = &sdcardfs_main_iops; + + /* use different set of file ops for directories */ + if (S_ISDIR(lower_inode->i_mode)) + inode->i_fop = &sdcardfs_dir_fops; + else + inode->i_fop = &sdcardfs_main_fops; + + inode->i_mapping->a_ops = &sdcardfs_aops; + + inode->i_atime.tv_sec = 0; + inode->i_atime.tv_nsec = 0; + inode->i_mtime.tv_sec = 0; + inode->i_mtime.tv_nsec = 0; + inode->i_ctime.tv_sec = 0; + inode->i_ctime.tv_nsec = 0; + + /* properly initialize special inodes */ + if (S_ISBLK(lower_inode->i_mode) || S_ISCHR(lower_inode->i_mode) || + S_ISFIFO(lower_inode->i_mode) || S_ISSOCK(lower_inode->i_mode)) + init_special_inode(inode, lower_inode->i_mode, + lower_inode->i_rdev); + + /* all well, copy inode attributes */ + sdcardfs_copy_and_fix_attrs(inode, lower_inode); + fsstack_copy_inode_size(inode, lower_inode); + + unlock_new_inode(inode); + return inode; +} + +/* + * Helper interpose routine, called directly by ->lookup to handle + * spliced dentries. + */ +static struct dentry *__sdcardfs_interpose(struct dentry *dentry, + struct super_block *sb, + struct path *lower_path, + userid_t id) +{ + struct inode *inode; + struct inode *lower_inode; + struct super_block *lower_sb; + struct dentry *ret_dentry; + + lower_inode = d_inode(lower_path->dentry); + lower_sb = sdcardfs_lower_super(sb); + + /* check that the lower file system didn't cross a mount point */ + if (lower_inode->i_sb != lower_sb) { + ret_dentry = ERR_PTR(-EXDEV); + goto out; + } + + /* + * We allocate our new inode below by calling sdcardfs_iget, + * which will initialize some of the new inode's fields + */ + + /* inherit lower inode number for sdcardfs's inode */ + inode = sdcardfs_iget(sb, lower_inode, id); + if (IS_ERR(inode)) { + ret_dentry = ERR_CAST(inode); + goto out; + } + + ret_dentry = d_splice_alias(inode, dentry); + dentry = ret_dentry ?: dentry; + if (!IS_ERR(dentry)) + update_derived_permission_lock(dentry); +out: + return ret_dentry; +} + +/* + * Connect an sdcardfs inode dentry/inode with several lower ones. This is + * the classic stackable file system "vnode interposition" action. + * + * @dentry: sdcardfs's dentry which interposes on lower one + * @sb: sdcardfs's super_block + * @lower_path: the lower path (caller does path_get/put) + */ +int sdcardfs_interpose(struct dentry *dentry, struct super_block *sb, + struct path *lower_path, userid_t id) +{ + struct dentry *ret_dentry; + + ret_dentry = __sdcardfs_interpose(dentry, sb, lower_path, id); + return PTR_ERR(ret_dentry); +} + +struct sdcardfs_name_data { + struct dir_context ctx; + const struct qstr *to_find; + char *name; + bool found; +}; + +static int sdcardfs_name_match(struct dir_context *ctx, const char *name, + int namelen, loff_t offset, u64 ino, unsigned int d_type) +{ + struct sdcardfs_name_data *buf = container_of(ctx, struct sdcardfs_name_data, ctx); + struct qstr candidate = QSTR_INIT(name, namelen); + + if (qstr_case_eq(buf->to_find, &candidate)) { + memcpy(buf->name, name, namelen); + buf->name[namelen] = 0; + buf->found = true; + return 1; + } + return 0; +} + +/* + * Main driver function for sdcardfs's lookup. + * + * Returns: NULL (ok), ERR_PTR if an error occurred. + * Fills in lower_parent_path with <dentry,mnt> on success. + */ +static struct dentry *__sdcardfs_lookup(struct dentry *dentry, + unsigned int flags, struct path *lower_parent_path, userid_t id) +{ + int err = 0; + struct vfsmount *lower_dir_mnt; + struct dentry *lower_dir_dentry = NULL; + struct dentry *lower_dentry; + const struct qstr *name; + struct path lower_path; + struct qstr dname; + struct dentry *ret_dentry = NULL; + struct sdcardfs_sb_info *sbi; + + sbi = SDCARDFS_SB(dentry->d_sb); + /* must initialize dentry operations */ + d_set_d_op(dentry, &sdcardfs_ci_dops); + + if (IS_ROOT(dentry)) + goto out; + + name = &dentry->d_name; + + /* now start the actual lookup procedure */ + lower_dir_dentry = lower_parent_path->dentry; + lower_dir_mnt = lower_parent_path->mnt; + + /* Use vfs_path_lookup to check if the dentry exists or not */ + err = vfs_path_lookup(lower_dir_dentry, lower_dir_mnt, name->name, 0, + &lower_path); + /* check for other cases */ + if (err == -ENOENT) { + struct file *file; + const struct cred *cred = current_cred(); + + struct sdcardfs_name_data buffer = { + .ctx.actor = sdcardfs_name_match, + .to_find = name, + .name = __getname(), + .found = false, + }; + + if (!buffer.name) { + err = -ENOMEM; + goto out; + } + file = dentry_open(lower_parent_path, O_RDONLY, cred); + if (IS_ERR(file)) { + err = PTR_ERR(file); + goto put_name; + } + err = iterate_dir(file, &buffer.ctx); + fput(file); + if (err) + goto put_name; + + if (buffer.found) + err = vfs_path_lookup(lower_dir_dentry, + lower_dir_mnt, + buffer.name, 0, + &lower_path); + else + err = -ENOENT; +put_name: + __putname(buffer.name); + } + + /* no error: handle positive dentries */ + if (!err) { + /* check if the dentry is an obb dentry + * if true, the lower_inode must be replaced with + * the inode of the graft path + */ + + if (need_graft_path(dentry)) { + + /* setup_obb_dentry() + * The lower_path will be stored to the dentry's orig_path + * and the base obbpath will be copyed to the lower_path variable. + * if an error returned, there's no change in the lower_path + * returns: -ERRNO if error (0: no error) + */ + err = setup_obb_dentry(dentry, &lower_path); + + if (err) { + /* if the sbi->obbpath is not available, we can optionally + * setup the lower_path with its orig_path. + * but, the current implementation just returns an error + * because the sdcard daemon also regards this case as + * a lookup fail. + */ + pr_info("sdcardfs: base obbpath is not available\n"); + sdcardfs_put_reset_orig_path(dentry); + goto out; + } + } + + sdcardfs_set_lower_path(dentry, &lower_path); + ret_dentry = + __sdcardfs_interpose(dentry, dentry->d_sb, &lower_path, id); + if (IS_ERR(ret_dentry)) { + err = PTR_ERR(ret_dentry); + /* path_put underlying path on error */ + sdcardfs_put_reset_lower_path(dentry); + } + goto out; + } + + /* + * We don't consider ENOENT an error, and we want to return a + * negative dentry. + */ + if (err && err != -ENOENT) + goto out; + + /* instatiate a new negative dentry */ + dname.name = name->name; + dname.len = name->len; + + /* See if the low-level filesystem might want + * to use its own hash + */ + lower_dentry = d_hash_and_lookup(lower_dir_dentry, &dname); + if (IS_ERR(lower_dentry)) + return lower_dentry; + + if (!lower_dentry) { + /* We called vfs_path_lookup earlier, and did not get a negative + * dentry then. Don't confuse the lower filesystem by forcing + * one on it now... + */ + err = -ENOENT; + goto out; + } + + lower_path.dentry = lower_dentry; + lower_path.mnt = mntget(lower_dir_mnt); + sdcardfs_set_lower_path(dentry, &lower_path); + + /* + * If the intent is to create a file, then don't return an error, so + * the VFS will continue the process of making this negative dentry + * into a positive one. + */ + if (flags & (LOOKUP_CREATE|LOOKUP_RENAME_TARGET)) + err = 0; + +out: + if (err) + return ERR_PTR(err); + return ret_dentry; +} + +/* + * On success: + * fills dentry object appropriate values and returns NULL. + * On fail (== error) + * returns error ptr + * + * @dir : Parent inode. + * @dentry : Target dentry to lookup. we should set each of fields. + * (dentry->d_name is initialized already) + * @nd : nameidata of parent inode + */ +struct dentry *sdcardfs_lookup(struct inode *dir, struct dentry *dentry, + unsigned int flags) +{ + struct dentry *ret = NULL, *parent; + struct path lower_parent_path; + int err = 0; + const struct cred *saved_cred = NULL; + + parent = dget_parent(dentry); + + if (!check_caller_access_to_name(d_inode(parent), &dentry->d_name)) { + ret = ERR_PTR(-EACCES); + goto out_err; + } + + /* save current_cred and override it */ + saved_cred = override_fsids(SDCARDFS_SB(dir->i_sb), + SDCARDFS_I(dir)->data); + if (!saved_cred) { + ret = ERR_PTR(-ENOMEM); + goto out_err; + } + + sdcardfs_get_lower_path(parent, &lower_parent_path); + + /* allocate dentry private data. We free it in ->d_release */ + err = new_dentry_private_data(dentry); + if (err) { + ret = ERR_PTR(err); + goto out; + } + + ret = __sdcardfs_lookup(dentry, flags, &lower_parent_path, + SDCARDFS_I(dir)->data->userid); + if (IS_ERR(ret)) + goto out; + if (ret) + dentry = ret; + if (d_inode(dentry)) { + fsstack_copy_attr_times(d_inode(dentry), + sdcardfs_lower_inode(d_inode(dentry))); + /* get derived permission */ + get_derived_permission(parent, dentry); + fixup_tmp_permissions(d_inode(dentry)); + fixup_lower_ownership(dentry, dentry->d_name.name); + } + /* update parent directory's atime */ + fsstack_copy_attr_atime(d_inode(parent), + sdcardfs_lower_inode(d_inode(parent))); + +out: + sdcardfs_put_lower_path(parent, &lower_parent_path); + revert_fsids(saved_cred); +out_err: + dput(parent); + return ret; +} diff --git a/fs/sdcardfs/main.c b/fs/sdcardfs/main.c new file mode 100644 index 000000000000..d890c5711907 --- /dev/null +++ b/fs/sdcardfs/main.c @@ -0,0 +1,511 @@ +/* + * fs/sdcardfs/main.c + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#include "sdcardfs.h" +#include <linux/module.h> +#include <linux/types.h> +#include <linux/parser.h> + +enum { + Opt_fsuid, + Opt_fsgid, + Opt_gid, + Opt_debug, + Opt_mask, + Opt_multiuser, + Opt_userid, + Opt_reserved_mb, + Opt_gid_derivation, + Opt_default_normal, + Opt_nocache, + Opt_unshared_obb, + Opt_err, +}; + +static const match_table_t sdcardfs_tokens = { + {Opt_fsuid, "fsuid=%u"}, + {Opt_fsgid, "fsgid=%u"}, + {Opt_gid, "gid=%u"}, + {Opt_debug, "debug"}, + {Opt_mask, "mask=%u"}, + {Opt_userid, "userid=%d"}, + {Opt_multiuser, "multiuser"}, + {Opt_gid_derivation, "derive_gid"}, + {Opt_default_normal, "default_normal"}, + {Opt_unshared_obb, "unshared_obb"}, + {Opt_reserved_mb, "reserved_mb=%u"}, + {Opt_nocache, "nocache"}, + {Opt_err, NULL} +}; + +static int parse_options(struct super_block *sb, char *options, int silent, + int *debug, struct sdcardfs_vfsmount_options *vfsopts, + struct sdcardfs_mount_options *opts) +{ + char *p; + substring_t args[MAX_OPT_ARGS]; + int option; + + /* by default, we use AID_MEDIA_RW as uid, gid */ + opts->fs_low_uid = AID_MEDIA_RW; + opts->fs_low_gid = AID_MEDIA_RW; + vfsopts->mask = 0; + opts->multiuser = false; + opts->fs_user_id = 0; + vfsopts->gid = 0; + /* by default, 0MB is reserved */ + opts->reserved_mb = 0; + /* by default, gid derivation is off */ + opts->gid_derivation = false; + opts->default_normal = false; + opts->nocache = false; + + *debug = 0; + + if (!options) + return 0; + + while ((p = strsep(&options, ",")) != NULL) { + int token; + + if (!*p) + continue; + + token = match_token(p, sdcardfs_tokens, args); + + switch (token) { + case Opt_debug: + *debug = 1; + break; + case Opt_fsuid: + if (match_int(&args[0], &option)) + return 0; + opts->fs_low_uid = option; + break; + case Opt_fsgid: + if (match_int(&args[0], &option)) + return 0; + opts->fs_low_gid = option; + break; + case Opt_gid: + if (match_int(&args[0], &option)) + return 0; + vfsopts->gid = option; + break; + case Opt_userid: + if (match_int(&args[0], &option)) + return 0; + opts->fs_user_id = option; + break; + case Opt_mask: + if (match_int(&args[0], &option)) + return 0; + vfsopts->mask = option; + break; + case Opt_multiuser: + opts->multiuser = true; + break; + case Opt_reserved_mb: + if (match_int(&args[0], &option)) + return 0; + opts->reserved_mb = option; + break; + case Opt_gid_derivation: + opts->gid_derivation = true; + break; + case Opt_default_normal: + opts->default_normal = true; + break; + case Opt_nocache: + opts->nocache = true; + break; + case Opt_unshared_obb: + opts->unshared_obb = true; + break; + /* unknown option */ + default: + if (!silent) + pr_err("Unrecognized mount option \"%s\" or missing value", p); + return -EINVAL; + } + } + + if (*debug) { + pr_info("sdcardfs : options - debug:%d\n", *debug); + pr_info("sdcardfs : options - uid:%d\n", + opts->fs_low_uid); + pr_info("sdcardfs : options - gid:%d\n", + opts->fs_low_gid); + } + + return 0; +} + +int parse_options_remount(struct super_block *sb, char *options, int silent, + struct sdcardfs_vfsmount_options *vfsopts) +{ + char *p; + substring_t args[MAX_OPT_ARGS]; + int option; + int debug; + + if (!options) + return 0; + + while ((p = strsep(&options, ",")) != NULL) { + int token; + + if (!*p) + continue; + + token = match_token(p, sdcardfs_tokens, args); + + switch (token) { + case Opt_debug: + debug = 1; + break; + case Opt_gid: + if (match_int(&args[0], &option)) + return 0; + vfsopts->gid = option; + + break; + case Opt_mask: + if (match_int(&args[0], &option)) + return 0; + vfsopts->mask = option; + break; + case Opt_unshared_obb: + case Opt_default_normal: + case Opt_multiuser: + case Opt_userid: + case Opt_fsuid: + case Opt_fsgid: + case Opt_reserved_mb: + case Opt_gid_derivation: + if (!silent) + pr_warn("Option \"%s\" can't be changed during remount\n", p); + break; + /* unknown option */ + default: + if (!silent) + pr_err("Unrecognized mount option \"%s\" or missing value", p); + return -EINVAL; + } + } + + if (debug) { + pr_info("sdcardfs : options - debug:%d\n", debug); + pr_info("sdcardfs : options - gid:%d\n", vfsopts->gid); + pr_info("sdcardfs : options - mask:%d\n", vfsopts->mask); + } + + return 0; +} + +#if 0 +/* + * our custom d_alloc_root work-alike + * + * we can't use d_alloc_root if we want to use our own interpose function + * unchanged, so we simply call our own "fake" d_alloc_root + */ +static struct dentry *sdcardfs_d_alloc_root(struct super_block *sb) +{ + struct dentry *ret = NULL; + + if (sb) { + static const struct qstr name = { + .name = "/", + .len = 1 + }; + + ret = d_alloc(NULL, &name); + if (ret) { + d_set_d_op(ret, &sdcardfs_ci_dops); + ret->d_sb = sb; + ret->d_parent = ret; + } + } + return ret; +} +#endif + +DEFINE_MUTEX(sdcardfs_super_list_lock); +EXPORT_SYMBOL_GPL(sdcardfs_super_list_lock); +LIST_HEAD(sdcardfs_super_list); +EXPORT_SYMBOL_GPL(sdcardfs_super_list); + +/* + * There is no need to lock the sdcardfs_super_info's rwsem as there is no + * way anyone can have a reference to the superblock at this point in time. + */ +static int sdcardfs_read_super(struct vfsmount *mnt, struct super_block *sb, + const char *dev_name, void *raw_data, int silent) +{ + int err = 0; + int debug; + struct super_block *lower_sb; + struct path lower_path; + struct sdcardfs_sb_info *sb_info; + struct sdcardfs_vfsmount_options *mnt_opt = mnt->data; + struct inode *inode; + + pr_info("sdcardfs version 2.0\n"); + + if (!dev_name) { + pr_err("sdcardfs: read_super: missing dev_name argument\n"); + err = -EINVAL; + goto out; + } + + pr_info("sdcardfs: dev_name -> %s\n", dev_name); + pr_info("sdcardfs: options -> %s\n", (char *)raw_data); + pr_info("sdcardfs: mnt -> %p\n", mnt); + + /* parse lower path */ + err = kern_path(dev_name, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, + &lower_path); + if (err) { + pr_err("sdcardfs: error accessing lower directory '%s'\n", dev_name); + goto out; + } + + /* allocate superblock private data */ + sb->s_fs_info = kzalloc(sizeof(struct sdcardfs_sb_info), GFP_KERNEL); + if (!SDCARDFS_SB(sb)) { + pr_crit("sdcardfs: read_super: out of memory\n"); + err = -ENOMEM; + goto out_free; + } + + sb_info = sb->s_fs_info; + /* parse options */ + err = parse_options(sb, raw_data, silent, &debug, mnt_opt, &sb_info->options); + if (err) { + pr_err("sdcardfs: invalid options\n"); + goto out_freesbi; + } + + /* set the lower superblock field of upper superblock */ + lower_sb = lower_path.dentry->d_sb; + atomic_inc(&lower_sb->s_active); + sdcardfs_set_lower_super(sb, lower_sb); + + sb->s_stack_depth = lower_sb->s_stack_depth + 1; + if (sb->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) { + pr_err("sdcardfs: maximum fs stacking depth exceeded\n"); + err = -EINVAL; + goto out_sput; + } + + /* inherit maxbytes from lower file system */ + sb->s_maxbytes = lower_sb->s_maxbytes; + + /* + * Our c/m/atime granularity is 1 ns because we may stack on file + * systems whose granularity is as good. + */ + sb->s_time_gran = 1; + + sb->s_magic = SDCARDFS_SUPER_MAGIC; + sb->s_op = &sdcardfs_sops; + + /* get a new inode and allocate our root dentry */ + inode = sdcardfs_iget(sb, d_inode(lower_path.dentry), 0); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + goto out_sput; + } + sb->s_root = d_make_root(inode); + if (!sb->s_root) { + err = -ENOMEM; + goto out_sput; + } + d_set_d_op(sb->s_root, &sdcardfs_ci_dops); + + /* link the upper and lower dentries */ + sb->s_root->d_fsdata = NULL; + err = new_dentry_private_data(sb->s_root); + if (err) + goto out_freeroot; + + /* set the lower dentries for s_root */ + sdcardfs_set_lower_path(sb->s_root, &lower_path); + + /* + * No need to call interpose because we already have a positive + * dentry, which was instantiated by d_make_root. Just need to + * d_rehash it. + */ + d_rehash(sb->s_root); + + /* setup permission policy */ + sb_info->obbpath_s = kzalloc(PATH_MAX, GFP_KERNEL); + mutex_lock(&sdcardfs_super_list_lock); + if (sb_info->options.multiuser) { + setup_derived_state(d_inode(sb->s_root), PERM_PRE_ROOT, + sb_info->options.fs_user_id, AID_ROOT); + snprintf(sb_info->obbpath_s, PATH_MAX, "%s/obb", dev_name); + } else { + setup_derived_state(d_inode(sb->s_root), PERM_ROOT, + sb_info->options.fs_user_id, AID_ROOT); + snprintf(sb_info->obbpath_s, PATH_MAX, "%s/Android/obb", dev_name); + } + fixup_tmp_permissions(d_inode(sb->s_root)); + sb_info->sb = sb; + list_add(&sb_info->list, &sdcardfs_super_list); + mutex_unlock(&sdcardfs_super_list_lock); + + if (!silent) + pr_info("sdcardfs: mounted on top of %s type %s\n", + dev_name, lower_sb->s_type->name); + goto out; /* all is well */ + + /* no longer needed: free_dentry_private_data(sb->s_root); */ +out_freeroot: + dput(sb->s_root); + sb->s_root = NULL; +out_sput: + /* drop refs we took earlier */ + atomic_dec(&lower_sb->s_active); +out_freesbi: + kfree(SDCARDFS_SB(sb)); + sb->s_fs_info = NULL; +out_free: + path_put(&lower_path); + +out: + return err; +} + +struct sdcardfs_mount_private { + struct vfsmount *mnt; + const char *dev_name; + void *raw_data; +}; + +static int __sdcardfs_fill_super( + struct super_block *sb, + void *_priv, int silent) +{ + struct sdcardfs_mount_private *priv = _priv; + + return sdcardfs_read_super(priv->mnt, + sb, priv->dev_name, priv->raw_data, silent); +} + +static struct dentry *sdcardfs_mount(struct vfsmount *mnt, + struct file_system_type *fs_type, int flags, + const char *dev_name, void *raw_data) +{ + struct sdcardfs_mount_private priv = { + .mnt = mnt, + .dev_name = dev_name, + .raw_data = raw_data + }; + + return mount_nodev(fs_type, flags, + &priv, __sdcardfs_fill_super); +} + +static struct dentry *sdcardfs_mount_wrn(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data) +{ + WARN(1, "sdcardfs does not support mount. Use mount2.\n"); + return ERR_PTR(-EINVAL); +} + +void *sdcardfs_alloc_mnt_data(void) +{ + return kmalloc(sizeof(struct sdcardfs_vfsmount_options), GFP_KERNEL); +} + +void sdcardfs_kill_sb(struct super_block *sb) +{ + struct sdcardfs_sb_info *sbi; + + if (sb->s_magic == SDCARDFS_SUPER_MAGIC && sb->s_fs_info) { + sbi = SDCARDFS_SB(sb); + mutex_lock(&sdcardfs_super_list_lock); + list_del(&sbi->list); + mutex_unlock(&sdcardfs_super_list_lock); + } + kill_anon_super(sb); +} + +static struct file_system_type sdcardfs_fs_type = { + .owner = THIS_MODULE, + .name = SDCARDFS_NAME, + .mount = sdcardfs_mount_wrn, + .mount2 = sdcardfs_mount, + .alloc_mnt_data = sdcardfs_alloc_mnt_data, + .kill_sb = sdcardfs_kill_sb, + .fs_flags = 0, +}; +MODULE_ALIAS_FS(SDCARDFS_NAME); + +static int __init init_sdcardfs_fs(void) +{ + int err; + + pr_info("Registering sdcardfs " SDCARDFS_VERSION "\n"); + + err = sdcardfs_init_inode_cache(); + if (err) + goto out; + err = sdcardfs_init_dentry_cache(); + if (err) + goto out; + err = packagelist_init(); + if (err) + goto out; + err = register_filesystem(&sdcardfs_fs_type); +out: + if (err) { + sdcardfs_destroy_inode_cache(); + sdcardfs_destroy_dentry_cache(); + packagelist_exit(); + } + return err; +} + +static void __exit exit_sdcardfs_fs(void) +{ + sdcardfs_destroy_inode_cache(); + sdcardfs_destroy_dentry_cache(); + packagelist_exit(); + unregister_filesystem(&sdcardfs_fs_type); + pr_info("Completed sdcardfs module unload\n"); +} + +/* Original wrapfs authors */ +MODULE_AUTHOR("Erez Zadok, Filesystems and Storage Lab, Stony Brook University (http://www.fsl.cs.sunysb.edu/)"); + +/* Original sdcardfs authors */ +MODULE_AUTHOR("Woojoong Lee, Daeho Jeong, Kitae Lee, Yeongjin Gil System Memory Lab., Samsung Electronics"); + +/* Current maintainer */ +MODULE_AUTHOR("Daniel Rosenberg, Google"); +MODULE_DESCRIPTION("Sdcardfs " SDCARDFS_VERSION); +MODULE_LICENSE("GPL"); + +module_init(init_sdcardfs_fs); +module_exit(exit_sdcardfs_fs); diff --git a/fs/sdcardfs/mmap.c b/fs/sdcardfs/mmap.c new file mode 100644 index 000000000000..2847c0ec5e0a --- /dev/null +++ b/fs/sdcardfs/mmap.c @@ -0,0 +1,87 @@ +/* + * fs/sdcardfs/mmap.c + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#include "sdcardfs.h" + +static int sdcardfs_fault(struct vm_fault *vmf) +{ + int err; + struct file *file; + const struct vm_operations_struct *lower_vm_ops; + + file = (struct file *)vmf->vma->vm_private_data; + lower_vm_ops = SDCARDFS_F(file)->lower_vm_ops; + BUG_ON(!lower_vm_ops); + + err = lower_vm_ops->fault(vmf); + return err; +} + +static void sdcardfs_vm_open(struct vm_area_struct *vma) +{ + struct file *file = (struct file *)vma->vm_private_data; + + get_file(file); +} + +static void sdcardfs_vm_close(struct vm_area_struct *vma) +{ + struct file *file = (struct file *)vma->vm_private_data; + + fput(file); +} + +static int sdcardfs_page_mkwrite(struct vm_fault *vmf) +{ + int err = 0; + struct file *file; + const struct vm_operations_struct *lower_vm_ops; + + file = (struct file *)vmf->vma->vm_private_data; + lower_vm_ops = SDCARDFS_F(file)->lower_vm_ops; + BUG_ON(!lower_vm_ops); + if (!lower_vm_ops->page_mkwrite) + goto out; + + err = lower_vm_ops->page_mkwrite(vmf); +out: + return err; +} + +static ssize_t sdcardfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) +{ + /* + * This function should never be called directly. We need it + * to exist, to get past a check in open_check_o_direct(), + * which is called from do_last(). + */ + return -EINVAL; +} + +const struct address_space_operations sdcardfs_aops = { + .direct_IO = sdcardfs_direct_IO, +}; + +const struct vm_operations_struct sdcardfs_vm_ops = { + .fault = sdcardfs_fault, + .page_mkwrite = sdcardfs_page_mkwrite, + .open = sdcardfs_vm_open, + .close = sdcardfs_vm_close, +}; diff --git a/fs/sdcardfs/multiuser.h b/fs/sdcardfs/multiuser.h new file mode 100644 index 000000000000..85341e753f8c --- /dev/null +++ b/fs/sdcardfs/multiuser.h @@ -0,0 +1,53 @@ +/* + * fs/sdcardfs/multiuser.h + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#define AID_USER_OFFSET 100000 /* offset for uid ranges for each user */ +#define AID_APP_START 10000 /* first app user */ +#define AID_APP_END 19999 /* last app user */ +#define AID_CACHE_GID_START 20000 /* start of gids for apps to mark cached data */ +#define AID_EXT_GID_START 30000 /* start of gids for apps to mark external data */ +#define AID_EXT_CACHE_GID_START 40000 /* start of gids for apps to mark external cached data */ +#define AID_EXT_CACHE_GID_END 49999 /* end of gids for apps to mark external cached data */ +#define AID_SHARED_GID_START 50000 /* start of gids for apps in each user to share */ + +typedef uid_t userid_t; +typedef uid_t appid_t; + +static inline uid_t multiuser_get_uid(userid_t user_id, appid_t app_id) +{ + return (user_id * AID_USER_OFFSET) + (app_id % AID_USER_OFFSET); +} + +static inline bool uid_is_app(uid_t uid) +{ + appid_t appid = uid % AID_USER_OFFSET; + + return appid >= AID_APP_START && appid <= AID_APP_END; +} + +static inline gid_t multiuser_get_ext_cache_gid(uid_t uid) +{ + return uid - AID_APP_START + AID_EXT_CACHE_GID_START; +} + +static inline gid_t multiuser_get_ext_gid(uid_t uid) +{ + return uid - AID_APP_START + AID_EXT_GID_START; +} diff --git a/fs/sdcardfs/packagelist.c b/fs/sdcardfs/packagelist.c new file mode 100644 index 000000000000..4b9a5635f1e0 --- /dev/null +++ b/fs/sdcardfs/packagelist.c @@ -0,0 +1,882 @@ +/* + * fs/sdcardfs/packagelist.c + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#include "sdcardfs.h" +#include <linux/hashtable.h> +#include <linux/ctype.h> +#include <linux/delay.h> +#include <linux/radix-tree.h> +#include <linux/dcache.h> + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/slab.h> + +#include <linux/configfs.h> + +struct hashtable_entry { + struct hlist_node hlist; + struct hlist_node dlist; /* for deletion cleanup */ + struct qstr key; + atomic_t value; +}; + +static DEFINE_HASHTABLE(package_to_appid, 8); +static DEFINE_HASHTABLE(package_to_userid, 8); +static DEFINE_HASHTABLE(ext_to_groupid, 8); + + +static struct kmem_cache *hashtable_entry_cachep; + +static unsigned int full_name_case_hash(const void *salt, const unsigned char *name, unsigned int len) +{ + unsigned long hash = init_name_hash(salt); + + while (len--) + hash = partial_name_hash(tolower(*name++), hash); + return end_name_hash(hash); +} + +static inline void qstr_init(struct qstr *q, const char *name) +{ + q->name = name; + q->len = strlen(q->name); + q->hash = full_name_case_hash(0, q->name, q->len); +} + +static inline int qstr_copy(const struct qstr *src, struct qstr *dest) +{ + dest->name = kstrdup(src->name, GFP_KERNEL); + dest->hash_len = src->hash_len; + return !!dest->name; +} + + +static appid_t __get_appid(const struct qstr *key) +{ + struct hashtable_entry *hash_cur; + unsigned int hash = key->hash; + appid_t ret_id; + + rcu_read_lock(); + hash_for_each_possible_rcu(package_to_appid, hash_cur, hlist, hash) { + if (qstr_case_eq(key, &hash_cur->key)) { + ret_id = atomic_read(&hash_cur->value); + rcu_read_unlock(); + return ret_id; + } + } + rcu_read_unlock(); + return 0; +} + +appid_t get_appid(const char *key) +{ + struct qstr q; + + qstr_init(&q, key); + return __get_appid(&q); +} + +static appid_t __get_ext_gid(const struct qstr *key) +{ + struct hashtable_entry *hash_cur; + unsigned int hash = key->hash; + appid_t ret_id; + + rcu_read_lock(); + hash_for_each_possible_rcu(ext_to_groupid, hash_cur, hlist, hash) { + if (qstr_case_eq(key, &hash_cur->key)) { + ret_id = atomic_read(&hash_cur->value); + rcu_read_unlock(); + return ret_id; + } + } + rcu_read_unlock(); + return 0; +} + +appid_t get_ext_gid(const char *key) +{ + struct qstr q; + + qstr_init(&q, key); + return __get_ext_gid(&q); +} + +static appid_t __is_excluded(const struct qstr *app_name, userid_t user) +{ + struct hashtable_entry *hash_cur; + unsigned int hash = app_name->hash; + + rcu_read_lock(); + hash_for_each_possible_rcu(package_to_userid, hash_cur, hlist, hash) { + if (atomic_read(&hash_cur->value) == user && + qstr_case_eq(app_name, &hash_cur->key)) { + rcu_read_unlock(); + return 1; + } + } + rcu_read_unlock(); + return 0; +} + +appid_t is_excluded(const char *key, userid_t user) +{ + struct qstr q; + qstr_init(&q, key); + return __is_excluded(&q, user); +} + +/* Kernel has already enforced everything we returned through + * derive_permissions_locked(), so this is used to lock down access + * even further, such as enforcing that apps hold sdcard_rw. + */ +int check_caller_access_to_name(struct inode *parent_node, const struct qstr *name) +{ + struct qstr q_autorun = QSTR_LITERAL("autorun.inf"); + struct qstr q__android_secure = QSTR_LITERAL(".android_secure"); + struct qstr q_android_secure = QSTR_LITERAL("android_secure"); + + /* Always block security-sensitive files at root */ + if (parent_node && SDCARDFS_I(parent_node)->data->perm == PERM_ROOT) { + if (qstr_case_eq(name, &q_autorun) + || qstr_case_eq(name, &q__android_secure) + || qstr_case_eq(name, &q_android_secure)) { + return 0; + } + } + + /* Root always has access; access for any other UIDs should always + * be controlled through packages.list. + */ + if (from_kuid(&init_user_ns, current_fsuid()) == 0) + return 1; + + /* No extra permissions to enforce */ + return 1; +} + +static struct hashtable_entry *alloc_hashtable_entry(const struct qstr *key, + appid_t value) +{ + struct hashtable_entry *ret = kmem_cache_alloc(hashtable_entry_cachep, + GFP_KERNEL); + if (!ret) + return NULL; + INIT_HLIST_NODE(&ret->dlist); + INIT_HLIST_NODE(&ret->hlist); + + if (!qstr_copy(key, &ret->key)) { + kmem_cache_free(hashtable_entry_cachep, ret); + return NULL; + } + + atomic_set(&ret->value, value); + return ret; +} + +static int insert_packagelist_appid_entry_locked(const struct qstr *key, appid_t value) +{ + struct hashtable_entry *hash_cur; + struct hashtable_entry *new_entry; + unsigned int hash = key->hash; + + hash_for_each_possible_rcu(package_to_appid, hash_cur, hlist, hash) { + if (qstr_case_eq(key, &hash_cur->key)) { + atomic_set(&hash_cur->value, value); + return 0; + } + } + new_entry = alloc_hashtable_entry(key, value); + if (!new_entry) + return -ENOMEM; + hash_add_rcu(package_to_appid, &new_entry->hlist, hash); + return 0; +} + +static int insert_ext_gid_entry_locked(const struct qstr *key, appid_t value) +{ + struct hashtable_entry *hash_cur; + struct hashtable_entry *new_entry; + unsigned int hash = key->hash; + + /* An extension can only belong to one gid */ + hash_for_each_possible_rcu(ext_to_groupid, hash_cur, hlist, hash) { + if (qstr_case_eq(key, &hash_cur->key)) + return -EINVAL; + } + new_entry = alloc_hashtable_entry(key, value); + if (!new_entry) + return -ENOMEM; + hash_add_rcu(ext_to_groupid, &new_entry->hlist, hash); + return 0; +} + +static int insert_userid_exclude_entry_locked(const struct qstr *key, userid_t value) +{ + struct hashtable_entry *hash_cur; + struct hashtable_entry *new_entry; + unsigned int hash = key->hash; + + /* Only insert if not already present */ + hash_for_each_possible_rcu(package_to_userid, hash_cur, hlist, hash) { + if (atomic_read(&hash_cur->value) == value && + qstr_case_eq(key, &hash_cur->key)) + return 0; + } + new_entry = alloc_hashtable_entry(key, value); + if (!new_entry) + return -ENOMEM; + hash_add_rcu(package_to_userid, &new_entry->hlist, hash); + return 0; +} + +static void fixup_all_perms_name(const struct qstr *key) +{ + struct sdcardfs_sb_info *sbinfo; + struct limit_search limit = { + .flags = BY_NAME, + .name = QSTR_INIT(key->name, key->len), + }; + list_for_each_entry(sbinfo, &sdcardfs_super_list, list) { + if (sbinfo_has_sdcard_magic(sbinfo)) + fixup_perms_recursive(sbinfo->sb->s_root, &limit); + } +} + +static void fixup_all_perms_name_userid(const struct qstr *key, userid_t userid) +{ + struct sdcardfs_sb_info *sbinfo; + struct limit_search limit = { + .flags = BY_NAME | BY_USERID, + .name = QSTR_INIT(key->name, key->len), + .userid = userid, + }; + list_for_each_entry(sbinfo, &sdcardfs_super_list, list) { + if (sbinfo_has_sdcard_magic(sbinfo)) + fixup_perms_recursive(sbinfo->sb->s_root, &limit); + } +} + +static void fixup_all_perms_userid(userid_t userid) +{ + struct sdcardfs_sb_info *sbinfo; + struct limit_search limit = { + .flags = BY_USERID, + .userid = userid, + }; + list_for_each_entry(sbinfo, &sdcardfs_super_list, list) { + if (sbinfo_has_sdcard_magic(sbinfo)) + fixup_perms_recursive(sbinfo->sb->s_root, &limit); + } +} + +static int insert_packagelist_entry(const struct qstr *key, appid_t value) +{ + int err; + + mutex_lock(&sdcardfs_super_list_lock); + err = insert_packagelist_appid_entry_locked(key, value); + if (!err) + fixup_all_perms_name(key); + mutex_unlock(&sdcardfs_super_list_lock); + + return err; +} + +static int insert_ext_gid_entry(const struct qstr *key, appid_t value) +{ + int err; + + mutex_lock(&sdcardfs_super_list_lock); + err = insert_ext_gid_entry_locked(key, value); + mutex_unlock(&sdcardfs_super_list_lock); + + return err; +} + +static int insert_userid_exclude_entry(const struct qstr *key, userid_t value) +{ + int err; + + mutex_lock(&sdcardfs_super_list_lock); + err = insert_userid_exclude_entry_locked(key, value); + if (!err) + fixup_all_perms_name_userid(key, value); + mutex_unlock(&sdcardfs_super_list_lock); + + return err; +} + +static void free_hashtable_entry(struct hashtable_entry *entry) +{ + kfree(entry->key.name); + kmem_cache_free(hashtable_entry_cachep, entry); +} + +static void remove_packagelist_entry_locked(const struct qstr *key) +{ + struct hashtable_entry *hash_cur; + unsigned int hash = key->hash; + struct hlist_node *h_t; + HLIST_HEAD(free_list); + + hash_for_each_possible_rcu(package_to_userid, hash_cur, hlist, hash) { + if (qstr_case_eq(key, &hash_cur->key)) { + hash_del_rcu(&hash_cur->hlist); + hlist_add_head(&hash_cur->dlist, &free_list); + } + } + hash_for_each_possible_rcu(package_to_appid, hash_cur, hlist, hash) { + if (qstr_case_eq(key, &hash_cur->key)) { + hash_del_rcu(&hash_cur->hlist); + hlist_add_head(&hash_cur->dlist, &free_list); + break; + } + } + synchronize_rcu(); + hlist_for_each_entry_safe(hash_cur, h_t, &free_list, dlist) + free_hashtable_entry(hash_cur); +} + +static void remove_packagelist_entry(const struct qstr *key) +{ + mutex_lock(&sdcardfs_super_list_lock); + remove_packagelist_entry_locked(key); + fixup_all_perms_name(key); + mutex_unlock(&sdcardfs_super_list_lock); +} + +static void remove_ext_gid_entry_locked(const struct qstr *key, gid_t group) +{ + struct hashtable_entry *hash_cur; + unsigned int hash = key->hash; + + hash_for_each_possible_rcu(ext_to_groupid, hash_cur, hlist, hash) { + if (qstr_case_eq(key, &hash_cur->key) && atomic_read(&hash_cur->value) == group) { + hash_del_rcu(&hash_cur->hlist); + synchronize_rcu(); + free_hashtable_entry(hash_cur); + break; + } + } +} + +static void remove_ext_gid_entry(const struct qstr *key, gid_t group) +{ + mutex_lock(&sdcardfs_super_list_lock); + remove_ext_gid_entry_locked(key, group); + mutex_unlock(&sdcardfs_super_list_lock); +} + +static void remove_userid_all_entry_locked(userid_t userid) +{ + struct hashtable_entry *hash_cur; + struct hlist_node *h_t; + HLIST_HEAD(free_list); + int i; + + hash_for_each_rcu(package_to_userid, i, hash_cur, hlist) { + if (atomic_read(&hash_cur->value) == userid) { + hash_del_rcu(&hash_cur->hlist); + hlist_add_head(&hash_cur->dlist, &free_list); + } + } + synchronize_rcu(); + hlist_for_each_entry_safe(hash_cur, h_t, &free_list, dlist) { + free_hashtable_entry(hash_cur); + } +} + +static void remove_userid_all_entry(userid_t userid) +{ + mutex_lock(&sdcardfs_super_list_lock); + remove_userid_all_entry_locked(userid); + fixup_all_perms_userid(userid); + mutex_unlock(&sdcardfs_super_list_lock); +} + +static void remove_userid_exclude_entry_locked(const struct qstr *key, userid_t userid) +{ + struct hashtable_entry *hash_cur; + unsigned int hash = key->hash; + + hash_for_each_possible_rcu(package_to_userid, hash_cur, hlist, hash) { + if (qstr_case_eq(key, &hash_cur->key) && + atomic_read(&hash_cur->value) == userid) { + hash_del_rcu(&hash_cur->hlist); + synchronize_rcu(); + free_hashtable_entry(hash_cur); + break; + } + } +} + +static void remove_userid_exclude_entry(const struct qstr *key, userid_t userid) +{ + mutex_lock(&sdcardfs_super_list_lock); + remove_userid_exclude_entry_locked(key, userid); + fixup_all_perms_name_userid(key, userid); + mutex_unlock(&sdcardfs_super_list_lock); +} + +static void packagelist_destroy(void) +{ + struct hashtable_entry *hash_cur; + struct hlist_node *h_t; + HLIST_HEAD(free_list); + int i; + + mutex_lock(&sdcardfs_super_list_lock); + hash_for_each_rcu(package_to_appid, i, hash_cur, hlist) { + hash_del_rcu(&hash_cur->hlist); + hlist_add_head(&hash_cur->dlist, &free_list); + } + hash_for_each_rcu(package_to_userid, i, hash_cur, hlist) { + hash_del_rcu(&hash_cur->hlist); + hlist_add_head(&hash_cur->dlist, &free_list); + } + synchronize_rcu(); + hlist_for_each_entry_safe(hash_cur, h_t, &free_list, dlist) + free_hashtable_entry(hash_cur); + mutex_unlock(&sdcardfs_super_list_lock); + pr_info("sdcardfs: destroyed packagelist pkgld\n"); +} + +#define SDCARDFS_CONFIGFS_ATTR(_pfx, _name) \ +static struct configfs_attribute _pfx##attr_##_name = { \ + .ca_name = __stringify(_name), \ + .ca_mode = S_IRUGO | S_IWUGO, \ + .ca_owner = THIS_MODULE, \ + .show = _pfx##_name##_show, \ + .store = _pfx##_name##_store, \ +} + +#define SDCARDFS_CONFIGFS_ATTR_RO(_pfx, _name) \ +static struct configfs_attribute _pfx##attr_##_name = { \ + .ca_name = __stringify(_name), \ + .ca_mode = S_IRUGO, \ + .ca_owner = THIS_MODULE, \ + .show = _pfx##_name##_show, \ +} + +#define SDCARDFS_CONFIGFS_ATTR_WO(_pfx, _name) \ +static struct configfs_attribute _pfx##attr_##_name = { \ + .ca_name = __stringify(_name), \ + .ca_mode = S_IWUGO, \ + .ca_owner = THIS_MODULE, \ + .store = _pfx##_name##_store, \ +} + +struct package_details { + struct config_item item; + struct qstr name; +}; + +static inline struct package_details *to_package_details(struct config_item *item) +{ + return item ? container_of(item, struct package_details, item) : NULL; +} + +static ssize_t package_details_appid_show(struct config_item *item, char *page) +{ + return scnprintf(page, PAGE_SIZE, "%u\n", __get_appid(&to_package_details(item)->name)); +} + +static ssize_t package_details_appid_store(struct config_item *item, + const char *page, size_t count) +{ + unsigned int tmp; + int ret; + + ret = kstrtouint(page, 10, &tmp); + if (ret) + return ret; + + ret = insert_packagelist_entry(&to_package_details(item)->name, tmp); + + if (ret) + return ret; + + return count; +} + +static ssize_t package_details_excluded_userids_show(struct config_item *item, + char *page) +{ + struct package_details *package_details = to_package_details(item); + struct hashtable_entry *hash_cur; + unsigned int hash = package_details->name.hash; + int count = 0; + + rcu_read_lock(); + hash_for_each_possible_rcu(package_to_userid, hash_cur, hlist, hash) { + if (qstr_case_eq(&package_details->name, &hash_cur->key)) + count += scnprintf(page + count, PAGE_SIZE - count, + "%d ", atomic_read(&hash_cur->value)); + } + rcu_read_unlock(); + if (count) + count--; + count += scnprintf(page + count, PAGE_SIZE - count, "\n"); + return count; +} + +static ssize_t package_details_excluded_userids_store(struct config_item *item, + const char *page, size_t count) +{ + unsigned int tmp; + int ret; + + ret = kstrtouint(page, 10, &tmp); + if (ret) + return ret; + + ret = insert_userid_exclude_entry(&to_package_details(item)->name, tmp); + + if (ret) + return ret; + + return count; +} + +static ssize_t package_details_clear_userid_store(struct config_item *item, + const char *page, size_t count) +{ + unsigned int tmp; + int ret; + + ret = kstrtouint(page, 10, &tmp); + if (ret) + return ret; + remove_userid_exclude_entry(&to_package_details(item)->name, tmp); + return count; +} + +static void package_details_release(struct config_item *item) +{ + struct package_details *package_details = to_package_details(item); + + pr_info("sdcardfs: removing %s\n", package_details->name.name); + remove_packagelist_entry(&package_details->name); + kfree(package_details->name.name); + kfree(package_details); +} + +SDCARDFS_CONFIGFS_ATTR(package_details_, appid); +SDCARDFS_CONFIGFS_ATTR(package_details_, excluded_userids); +SDCARDFS_CONFIGFS_ATTR_WO(package_details_, clear_userid); + +static struct configfs_attribute *package_details_attrs[] = { + &package_details_attr_appid, + &package_details_attr_excluded_userids, + &package_details_attr_clear_userid, + NULL, +}; + +static struct configfs_item_operations package_details_item_ops = { + .release = package_details_release, +}; + +static struct config_item_type package_appid_type = { + .ct_item_ops = &package_details_item_ops, + .ct_attrs = package_details_attrs, + .ct_owner = THIS_MODULE, +}; + +struct extensions_value { + struct config_group group; + unsigned int num; +}; + +struct extension_details { + struct config_item item; + struct qstr name; + unsigned int num; +}; + +static inline struct extensions_value *to_extensions_value(struct config_item *item) +{ + return item ? container_of(to_config_group(item), struct extensions_value, group) : NULL; +} + +static inline struct extension_details *to_extension_details(struct config_item *item) +{ + return item ? container_of(item, struct extension_details, item) : NULL; +} + +static void extension_details_release(struct config_item *item) +{ + struct extension_details *extension_details = to_extension_details(item); + + pr_info("sdcardfs: No longer mapping %s files to gid %d\n", + extension_details->name.name, extension_details->num); + remove_ext_gid_entry(&extension_details->name, extension_details->num); + kfree(extension_details->name.name); + kfree(extension_details); +} + +static struct configfs_item_operations extension_details_item_ops = { + .release = extension_details_release, +}; + +static struct config_item_type extension_details_type = { + .ct_item_ops = &extension_details_item_ops, + .ct_owner = THIS_MODULE, +}; + +static struct config_item *extension_details_make_item(struct config_group *group, const char *name) +{ + struct extensions_value *extensions_value = to_extensions_value(&group->cg_item); + struct extension_details *extension_details = kzalloc(sizeof(struct extension_details), GFP_KERNEL); + const char *tmp; + int ret; + + if (!extension_details) + return ERR_PTR(-ENOMEM); + + tmp = kstrdup(name, GFP_KERNEL); + if (!tmp) { + kfree(extension_details); + return ERR_PTR(-ENOMEM); + } + qstr_init(&extension_details->name, tmp); + extension_details->num = extensions_value->num; + ret = insert_ext_gid_entry(&extension_details->name, extensions_value->num); + + if (ret) { + kfree(extension_details->name.name); + kfree(extension_details); + return ERR_PTR(ret); + } + config_item_init_type_name(&extension_details->item, name, &extension_details_type); + + return &extension_details->item; +} + +static struct configfs_group_operations extensions_value_group_ops = { + .make_item = extension_details_make_item, +}; + +static struct config_item_type extensions_name_type = { + .ct_group_ops = &extensions_value_group_ops, + .ct_owner = THIS_MODULE, +}; + +static struct config_group *extensions_make_group(struct config_group *group, const char *name) +{ + struct extensions_value *extensions_value; + unsigned int tmp; + int ret; + + extensions_value = kzalloc(sizeof(struct extensions_value), GFP_KERNEL); + if (!extensions_value) + return ERR_PTR(-ENOMEM); + ret = kstrtouint(name, 10, &tmp); + if (ret) { + kfree(extensions_value); + return ERR_PTR(ret); + } + + extensions_value->num = tmp; + config_group_init_type_name(&extensions_value->group, name, + &extensions_name_type); + return &extensions_value->group; +} + +static void extensions_drop_group(struct config_group *group, struct config_item *item) +{ + struct extensions_value *value = to_extensions_value(item); + + pr_info("sdcardfs: No longer mapping any files to gid %d\n", value->num); + kfree(value); +} + +static struct configfs_group_operations extensions_group_ops = { + .make_group = extensions_make_group, + .drop_item = extensions_drop_group, +}; + +static struct config_item_type extensions_type = { + .ct_group_ops = &extensions_group_ops, + .ct_owner = THIS_MODULE, +}; + +struct config_group extension_group = { + .cg_item = { + .ci_namebuf = "extensions", + .ci_type = &extensions_type, + }, +}; + +static struct config_item *packages_make_item(struct config_group *group, const char *name) +{ + struct package_details *package_details; + const char *tmp; + + package_details = kzalloc(sizeof(struct package_details), GFP_KERNEL); + if (!package_details) + return ERR_PTR(-ENOMEM); + tmp = kstrdup(name, GFP_KERNEL); + if (!tmp) { + kfree(package_details); + return ERR_PTR(-ENOMEM); + } + qstr_init(&package_details->name, tmp); + config_item_init_type_name(&package_details->item, name, + &package_appid_type); + + return &package_details->item; +} + +static ssize_t packages_list_show(struct config_item *item, char *page) +{ + struct hashtable_entry *hash_cur_app; + struct hashtable_entry *hash_cur_user; + int i; + int count = 0, written = 0; + const char errormsg[] = "<truncated>\n"; + unsigned int hash; + + rcu_read_lock(); + hash_for_each_rcu(package_to_appid, i, hash_cur_app, hlist) { + written = scnprintf(page + count, PAGE_SIZE - sizeof(errormsg) - count, "%s %d\n", + hash_cur_app->key.name, atomic_read(&hash_cur_app->value)); + hash = hash_cur_app->key.hash; + hash_for_each_possible_rcu(package_to_userid, hash_cur_user, hlist, hash) { + if (qstr_case_eq(&hash_cur_app->key, &hash_cur_user->key)) { + written += scnprintf(page + count + written - 1, + PAGE_SIZE - sizeof(errormsg) - count - written + 1, + " %d\n", atomic_read(&hash_cur_user->value)) - 1; + } + } + if (count + written == PAGE_SIZE - sizeof(errormsg) - 1) { + count += scnprintf(page + count, PAGE_SIZE - count, errormsg); + break; + } + count += written; + } + rcu_read_unlock(); + + return count; +} + +static ssize_t packages_remove_userid_store(struct config_item *item, + const char *page, size_t count) +{ + unsigned int tmp; + int ret; + + ret = kstrtouint(page, 10, &tmp); + if (ret) + return ret; + remove_userid_all_entry(tmp); + return count; +} + +static struct configfs_attribute packages_attr_packages_gid_list = { + .ca_name = "packages_gid.list", + .ca_mode = S_IRUGO, + .ca_owner = THIS_MODULE, + .show = packages_list_show, +}; + +SDCARDFS_CONFIGFS_ATTR_WO(packages_, remove_userid); + +static struct configfs_attribute *packages_attrs[] = { + &packages_attr_packages_gid_list, + &packages_attr_remove_userid, + NULL, +}; + +/* + * Note that, since no extra work is required on ->drop_item(), + * no ->drop_item() is provided. + */ +static struct configfs_group_operations packages_group_ops = { + .make_item = packages_make_item, +}; + +static struct config_item_type packages_type = { + .ct_group_ops = &packages_group_ops, + .ct_attrs = packages_attrs, + .ct_owner = THIS_MODULE, +}; + +struct config_group *sd_default_groups[] = { + &extension_group, + NULL, +}; + +static struct configfs_subsystem sdcardfs_packages = { + .su_group = { + .cg_item = { + .ci_namebuf = "sdcardfs", + .ci_type = &packages_type, + }, + }, +}; + +static int configfs_sdcardfs_init(void) +{ + int ret, i; + struct configfs_subsystem *subsys = &sdcardfs_packages; + + config_group_init(&subsys->su_group); + for (i = 0; sd_default_groups[i]; i++) { + config_group_init(sd_default_groups[i]); + configfs_add_default_group(sd_default_groups[i], &subsys->su_group); + } + mutex_init(&subsys->su_mutex); + ret = configfs_register_subsystem(subsys); + if (ret) { + pr_err("Error %d while registering subsystem %s\n", + ret, + subsys->su_group.cg_item.ci_namebuf); + } + return ret; +} + +static void configfs_sdcardfs_exit(void) +{ + configfs_unregister_subsystem(&sdcardfs_packages); +} + +int packagelist_init(void) +{ + hashtable_entry_cachep = + kmem_cache_create("packagelist_hashtable_entry", + sizeof(struct hashtable_entry), 0, 0, NULL); + if (!hashtable_entry_cachep) { + pr_err("sdcardfs: failed creating pkgl_hashtable entry slab cache\n"); + return -ENOMEM; + } + + configfs_sdcardfs_init(); + return 0; +} + +void packagelist_exit(void) +{ + configfs_sdcardfs_exit(); + packagelist_destroy(); + kmem_cache_destroy(hashtable_entry_cachep); +} diff --git a/fs/sdcardfs/sdcardfs.h b/fs/sdcardfs/sdcardfs.h new file mode 100644 index 000000000000..6219771ed71c --- /dev/null +++ b/fs/sdcardfs/sdcardfs.h @@ -0,0 +1,654 @@ +/* + * fs/sdcardfs/sdcardfs.h + * + * The sdcardfs v2.0 + * This file system replaces the sdcard daemon on Android + * On version 2.0, some of the daemon functions have been ported + * to support the multi-user concepts of Android 4.4 + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#ifndef _SDCARDFS_H_ +#define _SDCARDFS_H_ + +#include <linux/dcache.h> +#include <linux/file.h> +#include <linux/fs.h> +#include <linux/aio.h> +#include <linux/kref.h> +#include <linux/mm.h> +#include <linux/mount.h> +#include <linux/namei.h> +#include <linux/seq_file.h> +#include <linux/statfs.h> +#include <linux/fs_stack.h> +#include <linux/magic.h> +#include <linux/uaccess.h> +#include <linux/slab.h> +#include <linux/sched.h> +#include <linux/types.h> +#include <linux/security.h> +#include <linux/string.h> +#include <linux/list.h> +#include "multiuser.h" + +/* the file system name */ +#define SDCARDFS_NAME "sdcardfs" + +/* sdcardfs root inode number */ +#define SDCARDFS_ROOT_INO 1 + +/* useful for tracking code reachability */ +#define UDBG pr_default("DBG:%s:%s:%d\n", __FILE__, __func__, __LINE__) + +#define SDCARDFS_DIRENT_SIZE 256 + +/* temporary static uid settings for development */ +#define AID_ROOT 0 /* uid for accessing /mnt/sdcard & extSdcard */ +#define AID_MEDIA_RW 1023 /* internal media storage write access */ + +#define AID_SDCARD_RW 1015 /* external storage write access */ +#define AID_SDCARD_R 1028 /* external storage read access */ +#define AID_SDCARD_PICS 1033 /* external storage photos access */ +#define AID_SDCARD_AV 1034 /* external storage audio/video access */ +#define AID_SDCARD_ALL 1035 /* access all users external storage */ +#define AID_MEDIA_OBB 1059 /* obb files */ + +#define AID_SDCARD_IMAGE 1057 + +#define AID_PACKAGE_INFO 1027 + + +/* + * Permissions are handled by our permission function. + * We don't want anyone who happens to look at our inode value to prematurely + * block access, so store more permissive values. These are probably never + * used. + */ +#define fixup_tmp_permissions(x) \ + do { \ + (x)->i_uid = make_kuid(&init_user_ns, \ + SDCARDFS_I(x)->data->d_uid); \ + (x)->i_gid = make_kgid(&init_user_ns, AID_SDCARD_RW); \ + (x)->i_mode = ((x)->i_mode & S_IFMT) | 0775;\ + } while (0) + +/* Android 5.0 support */ + +/* Permission mode for a specific node. Controls how file permissions + * are derived for children nodes. + */ +typedef enum { + /* Nothing special; this node should just inherit from its parent. */ + PERM_INHERIT, + /* This node is one level above a normal root; used for legacy layouts + * which use the first level to represent user_id. + */ + PERM_PRE_ROOT, + /* This node is "/" */ + PERM_ROOT, + /* This node is "/Android" */ + PERM_ANDROID, + /* This node is "/Android/data" */ + PERM_ANDROID_DATA, + /* This node is "/Android/obb" */ + PERM_ANDROID_OBB, + /* This node is "/Android/media" */ + PERM_ANDROID_MEDIA, + /* This node is "/Android/[data|media|obb]/[package]" */ + PERM_ANDROID_PACKAGE, + /* This node is "/Android/[data|media|obb]/[package]/cache" */ + PERM_ANDROID_PACKAGE_CACHE, +} perm_t; + +struct sdcardfs_sb_info; +struct sdcardfs_mount_options; +struct sdcardfs_inode_info; +struct sdcardfs_inode_data; + +/* Do not directly use this function. Use OVERRIDE_CRED() instead. */ +const struct cred *override_fsids(struct sdcardfs_sb_info *sbi, + struct sdcardfs_inode_data *data); +/* Do not directly use this function, use REVERT_CRED() instead. */ +void revert_fsids(const struct cred *old_cred); + +/* operations vectors defined in specific files */ +extern const struct file_operations sdcardfs_main_fops; +extern const struct file_operations sdcardfs_dir_fops; +extern const struct inode_operations sdcardfs_main_iops; +extern const struct inode_operations sdcardfs_dir_iops; +extern const struct inode_operations sdcardfs_symlink_iops; +extern const struct super_operations sdcardfs_sops; +extern const struct dentry_operations sdcardfs_ci_dops; +extern const struct address_space_operations sdcardfs_aops, sdcardfs_dummy_aops; +extern const struct vm_operations_struct sdcardfs_vm_ops; + +extern int sdcardfs_init_inode_cache(void); +extern void sdcardfs_destroy_inode_cache(void); +extern int sdcardfs_init_dentry_cache(void); +extern void sdcardfs_destroy_dentry_cache(void); +extern int new_dentry_private_data(struct dentry *dentry); +extern void free_dentry_private_data(struct dentry *dentry); +extern struct dentry *sdcardfs_lookup(struct inode *dir, struct dentry *dentry, + unsigned int flags); +extern struct inode *sdcardfs_iget(struct super_block *sb, + struct inode *lower_inode, userid_t id); +extern int sdcardfs_interpose(struct dentry *dentry, struct super_block *sb, + struct path *lower_path, userid_t id); + +/* file private data */ +struct sdcardfs_file_info { + struct file *lower_file; + const struct vm_operations_struct *lower_vm_ops; +}; + +struct sdcardfs_inode_data { + struct kref refcount; + bool abandoned; + + perm_t perm; + userid_t userid; + uid_t d_uid; + bool under_android; + bool under_cache; + bool under_obb; +}; + +/* sdcardfs inode data in memory */ +struct sdcardfs_inode_info { + struct inode *lower_inode; + /* state derived based on current position in hierarchy */ + struct sdcardfs_inode_data *data; + + /* top folder for ownership */ + spinlock_t top_lock; + struct sdcardfs_inode_data *top_data; + + struct inode vfs_inode; +}; + + +/* sdcardfs dentry data in memory */ +struct sdcardfs_dentry_info { + spinlock_t lock; /* protects lower_path */ + struct path lower_path; + struct path orig_path; +}; + +struct sdcardfs_mount_options { + uid_t fs_low_uid; + gid_t fs_low_gid; + userid_t fs_user_id; + bool multiuser; + bool gid_derivation; + bool default_normal; + bool unshared_obb; + unsigned int reserved_mb; + bool nocache; +}; + +struct sdcardfs_vfsmount_options { + gid_t gid; + mode_t mask; +}; + +extern int parse_options_remount(struct super_block *sb, char *options, int silent, + struct sdcardfs_vfsmount_options *vfsopts); + +/* sdcardfs super-block data in memory */ +struct sdcardfs_sb_info { + struct super_block *sb; + struct super_block *lower_sb; + /* derived perm policy : some of options have been added + * to sdcardfs_mount_options (Android 4.4 support) + */ + struct sdcardfs_mount_options options; + spinlock_t lock; /* protects obbpath */ + char *obbpath_s; + struct path obbpath; + void *pkgl_id; + struct list_head list; +}; + +/* + * inode to private data + * + * Since we use containers and the struct inode is _inside_ the + * sdcardfs_inode_info structure, SDCARDFS_I will always (given a non-NULL + * inode pointer), return a valid non-NULL pointer. + */ +static inline struct sdcardfs_inode_info *SDCARDFS_I(const struct inode *inode) +{ + return container_of(inode, struct sdcardfs_inode_info, vfs_inode); +} + +/* dentry to private data */ +#define SDCARDFS_D(dent) ((struct sdcardfs_dentry_info *)(dent)->d_fsdata) + +/* superblock to private data */ +#define SDCARDFS_SB(super) ((struct sdcardfs_sb_info *)(super)->s_fs_info) + +/* file to private Data */ +#define SDCARDFS_F(file) ((struct sdcardfs_file_info *)((file)->private_data)) + +/* file to lower file */ +static inline struct file *sdcardfs_lower_file(const struct file *f) +{ + return SDCARDFS_F(f)->lower_file; +} + +static inline void sdcardfs_set_lower_file(struct file *f, struct file *val) +{ + SDCARDFS_F(f)->lower_file = val; +} + +/* inode to lower inode. */ +static inline struct inode *sdcardfs_lower_inode(const struct inode *i) +{ + return SDCARDFS_I(i)->lower_inode; +} + +static inline void sdcardfs_set_lower_inode(struct inode *i, struct inode *val) +{ + SDCARDFS_I(i)->lower_inode = val; +} + +/* superblock to lower superblock */ +static inline struct super_block *sdcardfs_lower_super( + const struct super_block *sb) +{ + return SDCARDFS_SB(sb)->lower_sb; +} + +static inline void sdcardfs_set_lower_super(struct super_block *sb, + struct super_block *val) +{ + SDCARDFS_SB(sb)->lower_sb = val; +} + +/* path based (dentry/mnt) macros */ +static inline void pathcpy(struct path *dst, const struct path *src) +{ + dst->dentry = src->dentry; + dst->mnt = src->mnt; +} + +/* sdcardfs_get_pname functions calls path_get() + * therefore, the caller must call "proper" path_put functions + */ +#define SDCARDFS_DENT_FUNC(pname) \ +static inline void sdcardfs_get_##pname(const struct dentry *dent, \ + struct path *pname) \ +{ \ + spin_lock(&SDCARDFS_D(dent)->lock); \ + pathcpy(pname, &SDCARDFS_D(dent)->pname); \ + path_get(pname); \ + spin_unlock(&SDCARDFS_D(dent)->lock); \ + return; \ +} \ +static inline void sdcardfs_put_##pname(const struct dentry *dent, \ + struct path *pname) \ +{ \ + path_put(pname); \ + return; \ +} \ +static inline void sdcardfs_set_##pname(const struct dentry *dent, \ + struct path *pname) \ +{ \ + spin_lock(&SDCARDFS_D(dent)->lock); \ + pathcpy(&SDCARDFS_D(dent)->pname, pname); \ + spin_unlock(&SDCARDFS_D(dent)->lock); \ + return; \ +} \ +static inline void sdcardfs_reset_##pname(const struct dentry *dent) \ +{ \ + spin_lock(&SDCARDFS_D(dent)->lock); \ + SDCARDFS_D(dent)->pname.dentry = NULL; \ + SDCARDFS_D(dent)->pname.mnt = NULL; \ + spin_unlock(&SDCARDFS_D(dent)->lock); \ + return; \ +} \ +static inline void sdcardfs_put_reset_##pname(const struct dentry *dent) \ +{ \ + struct path pname; \ + spin_lock(&SDCARDFS_D(dent)->lock); \ + if (SDCARDFS_D(dent)->pname.dentry) { \ + pathcpy(&pname, &SDCARDFS_D(dent)->pname); \ + SDCARDFS_D(dent)->pname.dentry = NULL; \ + SDCARDFS_D(dent)->pname.mnt = NULL; \ + spin_unlock(&SDCARDFS_D(dent)->lock); \ + path_put(&pname); \ + } else \ + spin_unlock(&SDCARDFS_D(dent)->lock); \ + return; \ +} + +SDCARDFS_DENT_FUNC(lower_path) +SDCARDFS_DENT_FUNC(orig_path) + +static inline bool sbinfo_has_sdcard_magic(struct sdcardfs_sb_info *sbinfo) +{ + return sbinfo && sbinfo->sb + && sbinfo->sb->s_magic == SDCARDFS_SUPER_MAGIC; +} + +static inline struct sdcardfs_inode_data *data_get( + struct sdcardfs_inode_data *data) +{ + if (data) + kref_get(&data->refcount); + return data; +} + +static inline struct sdcardfs_inode_data *top_data_get( + struct sdcardfs_inode_info *info) +{ + struct sdcardfs_inode_data *top_data; + + spin_lock(&info->top_lock); + top_data = data_get(info->top_data); + spin_unlock(&info->top_lock); + return top_data; +} + +extern void data_release(struct kref *ref); + +static inline void data_put(struct sdcardfs_inode_data *data) +{ + kref_put(&data->refcount, data_release); +} + +static inline void release_own_data(struct sdcardfs_inode_info *info) +{ + /* + * This happens exactly once per inode. At this point, the inode that + * originally held this data is about to be freed, and all references + * to it are held as a top value, and will likely be released soon. + */ + info->data->abandoned = true; + data_put(info->data); +} + +static inline void set_top(struct sdcardfs_inode_info *info, + struct sdcardfs_inode_info *top_owner) +{ + struct sdcardfs_inode_data *old_top; + struct sdcardfs_inode_data *new_top = NULL; + + if (top_owner) + new_top = top_data_get(top_owner); + + spin_lock(&info->top_lock); + old_top = info->top_data; + info->top_data = new_top; + if (old_top) + data_put(old_top); + spin_unlock(&info->top_lock); +} + +static inline int get_gid(struct vfsmount *mnt, + struct super_block *sb, + struct sdcardfs_inode_data *data) +{ + struct sdcardfs_vfsmount_options *vfsopts = mnt->data; + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(sb); + + if (vfsopts->gid == AID_SDCARD_RW && !sbi->options.default_normal) + /* As an optimization, certain trusted system components only run + * as owner but operate across all users. Since we're now handing + * out the sdcard_rw GID only to trusted apps, we're okay relaxing + * the user boundary enforcement for the default view. The UIDs + * assigned to app directories are still multiuser aware. + */ + return AID_SDCARD_RW; + else + return multiuser_get_uid(data->userid, vfsopts->gid); +} + +static inline int get_mode(struct vfsmount *mnt, + struct sdcardfs_inode_info *info, + struct sdcardfs_inode_data *data) +{ + int owner_mode; + int filtered_mode; + struct sdcardfs_vfsmount_options *opts = mnt->data; + int visible_mode = 0775 & ~opts->mask; + + + if (data->perm == PERM_PRE_ROOT) { + /* Top of multi-user view should always be visible to ensure + * secondary users can traverse inside. + */ + visible_mode = 0711; + } else if (data->under_android) { + /* Block "other" access to Android directories, since only apps + * belonging to a specific user should be in there; we still + * leave +x open for the default view. + */ + if (opts->gid == AID_SDCARD_RW) + visible_mode = visible_mode & ~0006; + else + visible_mode = visible_mode & ~0007; + } + owner_mode = info->lower_inode->i_mode & 0700; + filtered_mode = visible_mode & (owner_mode | (owner_mode >> 3) | (owner_mode >> 6)); + return filtered_mode; +} + +static inline int has_graft_path(const struct dentry *dent) +{ + int ret = 0; + + spin_lock(&SDCARDFS_D(dent)->lock); + if (SDCARDFS_D(dent)->orig_path.dentry != NULL) + ret = 1; + spin_unlock(&SDCARDFS_D(dent)->lock); + + return ret; +} + +static inline void sdcardfs_get_real_lower(const struct dentry *dent, + struct path *real_lower) +{ + /* in case of a local obb dentry + * the orig_path should be returned + */ + if (has_graft_path(dent)) + sdcardfs_get_orig_path(dent, real_lower); + else + sdcardfs_get_lower_path(dent, real_lower); +} + +static inline void sdcardfs_put_real_lower(const struct dentry *dent, + struct path *real_lower) +{ + if (has_graft_path(dent)) + sdcardfs_put_orig_path(dent, real_lower); + else + sdcardfs_put_lower_path(dent, real_lower); +} + +extern struct mutex sdcardfs_super_list_lock; +extern struct list_head sdcardfs_super_list; + +/* for packagelist.c */ +extern appid_t get_appid(const char *app_name); +extern appid_t get_ext_gid(const char *app_name); +extern appid_t is_excluded(const char *app_name, userid_t userid); +extern int check_caller_access_to_name(struct inode *parent_node, const struct qstr *name); +extern int packagelist_init(void); +extern void packagelist_exit(void); + +/* for derived_perm.c */ +#define BY_NAME (1 << 0) +#define BY_USERID (1 << 1) +struct limit_search { + unsigned int flags; + struct qstr name; + userid_t userid; +}; + +extern void setup_derived_state(struct inode *inode, perm_t perm, + userid_t userid, uid_t uid); +extern void get_derived_permission(struct dentry *parent, struct dentry *dentry); +extern void get_derived_permission_new(struct dentry *parent, struct dentry *dentry, const struct qstr *name); +extern void fixup_perms_recursive(struct dentry *dentry, struct limit_search *limit); + +extern void update_derived_permission_lock(struct dentry *dentry); +void fixup_lower_ownership(struct dentry *dentry, const char *name); +extern int need_graft_path(struct dentry *dentry); +extern int is_base_obbpath(struct dentry *dentry); +extern int is_obbpath_invalid(struct dentry *dentry); +extern int setup_obb_dentry(struct dentry *dentry, struct path *lower_path); + +/* locking helpers */ +static inline struct dentry *lock_parent(struct dentry *dentry) +{ + struct dentry *dir = dget_parent(dentry); + + inode_lock_nested(d_inode(dir), I_MUTEX_PARENT); + return dir; +} + +static inline void unlock_dir(struct dentry *dir) +{ + inode_unlock(d_inode(dir)); + dput(dir); +} + +static inline int prepare_dir(const char *path_s, uid_t uid, gid_t gid, mode_t mode) +{ + int err; + struct dentry *dent; + struct iattr attrs; + struct path parent; + + dent = kern_path_locked(path_s, &parent); + if (IS_ERR(dent)) { + err = PTR_ERR(dent); + if (err == -EEXIST) + err = 0; + goto out_unlock; + } + + err = vfs_mkdir2(parent.mnt, d_inode(parent.dentry), dent, mode); + if (err) { + if (err == -EEXIST) + err = 0; + goto out_dput; + } + + attrs.ia_uid = make_kuid(&init_user_ns, uid); + attrs.ia_gid = make_kgid(&init_user_ns, gid); + attrs.ia_valid = ATTR_UID | ATTR_GID; + inode_lock(d_inode(dent)); + notify_change2(parent.mnt, dent, &attrs, NULL); + inode_unlock(d_inode(dent)); + +out_dput: + dput(dent); + +out_unlock: + /* parent dentry locked by lookup_create */ + inode_unlock(d_inode(parent.dentry)); + path_put(&parent); + return err; +} + +/* + * Return 1, if a disk has enough free space, otherwise 0. + * We assume that any files can not be overwritten. + */ +static inline int check_min_free_space(struct dentry *dentry, size_t size, int dir) +{ + int err; + struct path lower_path; + struct kstatfs statfs; + u64 avail; + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + + if (sbi->options.reserved_mb) { + /* Get fs stat of lower filesystem. */ + sdcardfs_get_lower_path(dentry, &lower_path); + err = vfs_statfs(&lower_path, &statfs); + sdcardfs_put_lower_path(dentry, &lower_path); + + if (unlikely(err)) + return 0; + + /* Invalid statfs informations. */ + if (unlikely(statfs.f_bsize == 0)) + return 0; + + /* if you are checking directory, set size to f_bsize. */ + if (unlikely(dir)) + size = statfs.f_bsize; + + /* available size */ + avail = statfs.f_bavail * statfs.f_bsize; + + /* not enough space */ + if ((u64)size > avail) + return 0; + + /* enough space */ + if ((avail - size) > (sbi->options.reserved_mb * 1024 * 1024)) + return 1; + + return 0; + } else + return 1; +} + +/* + * Copies attrs and maintains sdcardfs managed attrs + * Since our permission check handles all special permissions, set those to be open + */ +static inline void sdcardfs_copy_and_fix_attrs(struct inode *dest, const struct inode *src) +{ + dest->i_mode = (src->i_mode & S_IFMT) | S_IRWXU | S_IRWXG | + S_IROTH | S_IXOTH; /* 0775 */ + dest->i_uid = make_kuid(&init_user_ns, SDCARDFS_I(dest)->data->d_uid); + dest->i_gid = make_kgid(&init_user_ns, AID_SDCARD_RW); + dest->i_rdev = src->i_rdev; + dest->i_atime = src->i_atime; + dest->i_mtime = src->i_mtime; + dest->i_ctime = src->i_ctime; + dest->i_blkbits = src->i_blkbits; + dest->i_flags = src->i_flags; + set_nlink(dest, src->i_nlink); +} + +static inline bool str_case_eq(const char *s1, const char *s2) +{ + return !strcasecmp(s1, s2); +} + +static inline bool str_n_case_eq(const char *s1, const char *s2, size_t len) +{ + return !strncasecmp(s1, s2, len); +} + +static inline bool qstr_case_eq(const struct qstr *q1, const struct qstr *q2) +{ + return q1->len == q2->len && str_n_case_eq(q1->name, q2->name, q2->len); +} + +#define QSTR_LITERAL(string) QSTR_INIT(string, sizeof(string)-1) + +#endif /* not _SDCARDFS_H_ */ diff --git a/fs/sdcardfs/super.c b/fs/sdcardfs/super.c new file mode 100644 index 000000000000..140696ed3ed3 --- /dev/null +++ b/fs/sdcardfs/super.c @@ -0,0 +1,333 @@ +/* + * fs/sdcardfs/super.c + * + * Copyright (c) 2013 Samsung Electronics Co. Ltd + * Authors: Daeho Jeong, Woojoong Lee, Seunghwan Hyun, + * Sunghwan Yun, Sungjong Seo + * + * This program has been developed as a stackable file system based on + * the WrapFS which written by + * + * Copyright (c) 1998-2011 Erez Zadok + * Copyright (c) 2009 Shrikar Archak + * Copyright (c) 2003-2011 Stony Brook University + * Copyright (c) 2003-2011 The Research Foundation of SUNY + * + * This file is dual licensed. It may be redistributed and/or modified + * under the terms of the Apache 2.0 License OR version 2 of the GNU + * General Public License. + */ + +#include "sdcardfs.h" + +/* + * The inode cache is used with alloc_inode for both our inode info and the + * vfs inode. + */ +static struct kmem_cache *sdcardfs_inode_cachep; + +/* + * To support the top references, we must track some data separately. + * An sdcardfs_inode_info always has a reference to its data, and once set up, + * also has a reference to its top. The top may be itself, in which case it + * holds two references to its data. When top is changed, it takes a ref to the + * new data and then drops the ref to the old data. + */ +static struct kmem_cache *sdcardfs_inode_data_cachep; + +void data_release(struct kref *ref) +{ + struct sdcardfs_inode_data *data = + container_of(ref, struct sdcardfs_inode_data, refcount); + + kmem_cache_free(sdcardfs_inode_data_cachep, data); +} + +/* final actions when unmounting a file system */ +static void sdcardfs_put_super(struct super_block *sb) +{ + struct sdcardfs_sb_info *spd; + struct super_block *s; + + spd = SDCARDFS_SB(sb); + if (!spd) + return; + + if (spd->obbpath_s) { + kfree(spd->obbpath_s); + path_put(&spd->obbpath); + } + + /* decrement lower super references */ + s = sdcardfs_lower_super(sb); + sdcardfs_set_lower_super(sb, NULL); + atomic_dec(&s->s_active); + + kfree(spd); + sb->s_fs_info = NULL; +} + +static int sdcardfs_statfs(struct dentry *dentry, struct kstatfs *buf) +{ + int err; + struct path lower_path; + u32 min_blocks; + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); + + sdcardfs_get_lower_path(dentry, &lower_path); + err = vfs_statfs(&lower_path, buf); + sdcardfs_put_lower_path(dentry, &lower_path); + + if (sbi->options.reserved_mb) { + /* Invalid statfs informations. */ + if (buf->f_bsize == 0) { + pr_err("Returned block size is zero.\n"); + return -EINVAL; + } + + min_blocks = ((sbi->options.reserved_mb * 1024 * 1024)/buf->f_bsize); + buf->f_blocks -= min_blocks; + + if (buf->f_bavail > min_blocks) + buf->f_bavail -= min_blocks; + else + buf->f_bavail = 0; + + /* Make reserved blocks invisiable to media storage */ + buf->f_bfree = buf->f_bavail; + } + + /* set return buf to our f/s to avoid confusing user-level utils */ + buf->f_type = SDCARDFS_SUPER_MAGIC; + + return err; +} + +/* + * @flags: numeric mount options + * @options: mount options string + */ +static int sdcardfs_remount_fs(struct super_block *sb, int *flags, char *options) +{ + int err = 0; + + /* + * The VFS will take care of "ro" and "rw" flags among others. We + * can safely accept a few flags (RDONLY, MANDLOCK), and honor + * SILENT, but anything else left over is an error. + */ + if ((*flags & ~(MS_RDONLY | MS_MANDLOCK | MS_SILENT)) != 0) { + pr_err("sdcardfs: remount flags 0x%x unsupported\n", *flags); + err = -EINVAL; + } + + return err; +} + +/* + * @mnt: mount point we are remounting + * @sb: superblock we are remounting + * @flags: numeric mount options + * @options: mount options string + */ +static int sdcardfs_remount_fs2(struct vfsmount *mnt, struct super_block *sb, + int *flags, char *options) +{ + int err = 0; + + /* + * The VFS will take care of "ro" and "rw" flags among others. We + * can safely accept a few flags (RDONLY, MANDLOCK), and honor + * SILENT, but anything else left over is an error. + */ + if ((*flags & ~(MS_RDONLY | MS_MANDLOCK | MS_SILENT | MS_REMOUNT)) != 0) { + pr_err("sdcardfs: remount flags 0x%x unsupported\n", *flags); + err = -EINVAL; + } + pr_info("Remount options were %s for vfsmnt %p.\n", options, mnt); + err = parse_options_remount(sb, options, *flags & ~MS_SILENT, mnt->data); + + + return err; +} + +static void *sdcardfs_clone_mnt_data(void *data) +{ + struct sdcardfs_vfsmount_options *opt = kmalloc(sizeof(struct sdcardfs_vfsmount_options), GFP_KERNEL); + struct sdcardfs_vfsmount_options *old = data; + + if (!opt) + return NULL; + opt->gid = old->gid; + opt->mask = old->mask; + return opt; +} + +static void sdcardfs_copy_mnt_data(void *data, void *newdata) +{ + struct sdcardfs_vfsmount_options *old = data; + struct sdcardfs_vfsmount_options *new = newdata; + + old->gid = new->gid; + old->mask = new->mask; +} + +/* + * Called by iput() when the inode reference count reached zero + * and the inode is not hashed anywhere. Used to clear anything + * that needs to be, before the inode is completely destroyed and put + * on the inode free list. + */ +static void sdcardfs_evict_inode(struct inode *inode) +{ + struct inode *lower_inode; + + truncate_inode_pages(&inode->i_data, 0); + set_top(SDCARDFS_I(inode), NULL); + clear_inode(inode); + /* + * Decrement a reference to a lower_inode, which was incremented + * by our read_inode when it was created initially. + */ + lower_inode = sdcardfs_lower_inode(inode); + sdcardfs_set_lower_inode(inode, NULL); + iput(lower_inode); +} + +static struct inode *sdcardfs_alloc_inode(struct super_block *sb) +{ + struct sdcardfs_inode_info *i; + struct sdcardfs_inode_data *d; + + i = kmem_cache_alloc(sdcardfs_inode_cachep, GFP_KERNEL); + if (!i) + return NULL; + + /* memset everything up to the inode to 0 */ + memset(i, 0, offsetof(struct sdcardfs_inode_info, vfs_inode)); + + d = kmem_cache_alloc(sdcardfs_inode_data_cachep, + GFP_KERNEL | __GFP_ZERO); + if (!d) { + kmem_cache_free(sdcardfs_inode_cachep, i); + return NULL; + } + + i->data = d; + kref_init(&d->refcount); + i->top_data = d; + spin_lock_init(&i->top_lock); + kref_get(&d->refcount); + + i->vfs_inode.i_version = 1; + return &i->vfs_inode; +} + +static void i_callback(struct rcu_head *head) +{ + struct inode *inode = container_of(head, struct inode, i_rcu); + + release_own_data(SDCARDFS_I(inode)); + kmem_cache_free(sdcardfs_inode_cachep, SDCARDFS_I(inode)); +} + +static void sdcardfs_destroy_inode(struct inode *inode) +{ + call_rcu(&inode->i_rcu, i_callback); +} + +/* sdcardfs inode cache constructor */ +static void init_once(void *obj) +{ + struct sdcardfs_inode_info *i = obj; + + inode_init_once(&i->vfs_inode); +} + +int sdcardfs_init_inode_cache(void) +{ + sdcardfs_inode_cachep = + kmem_cache_create("sdcardfs_inode_cache", + sizeof(struct sdcardfs_inode_info), 0, + SLAB_RECLAIM_ACCOUNT, init_once); + + if (!sdcardfs_inode_cachep) + return -ENOMEM; + + sdcardfs_inode_data_cachep = + kmem_cache_create("sdcardfs_inode_data_cache", + sizeof(struct sdcardfs_inode_data), 0, + SLAB_RECLAIM_ACCOUNT, NULL); + if (!sdcardfs_inode_data_cachep) { + kmem_cache_destroy(sdcardfs_inode_cachep); + return -ENOMEM; + } + + return 0; +} + +/* sdcardfs inode cache destructor */ +void sdcardfs_destroy_inode_cache(void) +{ + kmem_cache_destroy(sdcardfs_inode_data_cachep); + kmem_cache_destroy(sdcardfs_inode_cachep); +} + +/* + * Used only in nfs, to kill any pending RPC tasks, so that subsequent + * code can actually succeed and won't leave tasks that need handling. + */ +static void sdcardfs_umount_begin(struct super_block *sb) +{ + struct super_block *lower_sb; + + lower_sb = sdcardfs_lower_super(sb); + if (lower_sb && lower_sb->s_op && lower_sb->s_op->umount_begin) + lower_sb->s_op->umount_begin(lower_sb); +} + +static int sdcardfs_show_options(struct vfsmount *mnt, struct seq_file *m, + struct dentry *root) +{ + struct sdcardfs_sb_info *sbi = SDCARDFS_SB(root->d_sb); + struct sdcardfs_mount_options *opts = &sbi->options; + struct sdcardfs_vfsmount_options *vfsopts = mnt->data; + + if (opts->fs_low_uid != 0) + seq_printf(m, ",fsuid=%u", opts->fs_low_uid); + if (opts->fs_low_gid != 0) + seq_printf(m, ",fsgid=%u", opts->fs_low_gid); + if (vfsopts->gid != 0) + seq_printf(m, ",gid=%u", vfsopts->gid); + if (opts->multiuser) + seq_puts(m, ",multiuser"); + if (vfsopts->mask) + seq_printf(m, ",mask=%u", vfsopts->mask); + if (opts->fs_user_id) + seq_printf(m, ",userid=%u", opts->fs_user_id); + if (opts->gid_derivation) + seq_puts(m, ",derive_gid"); + if (opts->default_normal) + seq_puts(m, ",default_normal"); + if (opts->reserved_mb != 0) + seq_printf(m, ",reserved=%uMB", opts->reserved_mb); + if (opts->nocache) + seq_printf(m, ",nocache"); + + return 0; +}; + +const struct super_operations sdcardfs_sops = { + .put_super = sdcardfs_put_super, + .statfs = sdcardfs_statfs, + .remount_fs = sdcardfs_remount_fs, + .remount_fs2 = sdcardfs_remount_fs2, + .clone_mnt_data = sdcardfs_clone_mnt_data, + .copy_mnt_data = sdcardfs_copy_mnt_data, + .evict_inode = sdcardfs_evict_inode, + .umount_begin = sdcardfs_umount_begin, + .show_options2 = sdcardfs_show_options, + .alloc_inode = sdcardfs_alloc_inode, + .destroy_inode = sdcardfs_destroy_inode, + .drop_inode = generic_delete_inode, +}; diff --git a/fs/super.c b/fs/super.c index 219f7ca7c5d2..589f919ec20b 100644 --- a/fs/super.c +++ b/fs/super.c @@ -814,7 +814,8 @@ rescan: } /** - * do_remount_sb - asks filesystem to change mount options. + * do_remount_sb2 - asks filesystem to change mount options. + * @mnt: mount we are looking at * @sb: superblock in question * @sb_flags: revised superblock flags * @data: the rest of options @@ -822,7 +823,7 @@ rescan: * * Alters the mount options of a mounted file system. */ -int do_remount_sb(struct super_block *sb, int sb_flags, void *data, int force) +int do_remount_sb2(struct vfsmount *mnt, struct super_block *sb, int sb_flags, void *data, int force) { int retval; int remount_ro; @@ -864,7 +865,16 @@ int do_remount_sb(struct super_block *sb, int sb_flags, void *data, int force) } } - if (sb->s_op->remount_fs) { + if (mnt && sb->s_op->remount_fs2) { + retval = sb->s_op->remount_fs2(mnt, sb, &sb_flags, data); + if (retval) { + if (!force) + goto cancel_readonly; + /* If forced remount, go ahead despite any errors */ + WARN(1, "forced remount of a %s fs returned %i\n", + sb->s_type->name, retval); + } + } else if (sb->s_op->remount_fs) { retval = sb->s_op->remount_fs(sb, &sb_flags, data); if (retval) { if (!force) @@ -896,12 +906,17 @@ cancel_readonly: return retval; } +int do_remount_sb(struct super_block *sb, int flags, void *data, int force) +{ + return do_remount_sb2(NULL, sb, flags, data, force); +} + static void do_emergency_remount(struct work_struct *work) { struct super_block *sb, *p = NULL; spin_lock(&sb_lock); - list_for_each_entry(sb, &super_blocks, s_list) { + list_for_each_entry_reverse(sb, &super_blocks, s_list) { if (hlist_unhashed(&sb->s_instances)) continue; sb->s_count++; @@ -1217,7 +1232,7 @@ struct dentry *mount_single(struct file_system_type *fs_type, EXPORT_SYMBOL(mount_single); struct dentry * -mount_fs(struct file_system_type *type, int flags, const char *name, void *data) +mount_fs(struct file_system_type *type, int flags, const char *name, struct vfsmount *mnt, void *data) { struct dentry *root; struct super_block *sb; @@ -1234,7 +1249,10 @@ mount_fs(struct file_system_type *type, int flags, const char *name, void *data) goto out_free_secdata; } - root = type->mount(type, flags, name, data); + if (type->mount2) + root = type->mount2(mnt, type, flags, name, data); + else + root = type->mount(type, flags, name, data); if (IS_ERR(root)) { error = PTR_ERR(root); goto out_free_secdata; diff --git a/fs/sync.c b/fs/sync.c index 83ac79a960dd..12f2aa594c50 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -9,7 +9,7 @@ #include <linux/slab.h> #include <linux/export.h> #include <linux/namei.h> -#include <linux/sched.h> +#include <linux/sched/xacct.h> #include <linux/writeback.h> #include <linux/syscalls.h> #include <linux/linkage.h> @@ -219,6 +219,7 @@ static int do_fsync(unsigned int fd, int datasync) if (f.file) { ret = vfs_fsync(f.file, datasync); fdput(f); + inc_syscfs(current); } return ret; } diff --git a/fs/ubifs/crypto.c b/fs/ubifs/crypto.c index 16a5d5c82073..55c508fe8131 100644 --- a/fs/ubifs/crypto.c +++ b/fs/ubifs/crypto.c @@ -24,14 +24,6 @@ static bool ubifs_crypt_empty_dir(struct inode *inode) return ubifs_check_dir_empty(inode) == 0; } -static unsigned int ubifs_crypt_max_namelen(struct inode *inode) -{ - if (S_ISLNK(inode->i_mode)) - return UBIFS_MAX_INO_DATA; - else - return UBIFS_MAX_NLEN; -} - int ubifs_encrypt(const struct inode *inode, struct ubifs_data_node *dn, unsigned int in_len, unsigned int *out_len, int block) { @@ -88,7 +80,6 @@ const struct fscrypt_operations ubifs_crypt_operations = { .key_prefix = "ubifs:", .get_context = ubifs_crypt_get_context, .set_context = ubifs_crypt_set_context, - .is_encrypted = __ubifs_crypt_is_encrypted, .empty_dir = ubifs_crypt_empty_dir, - .max_namelen = ubifs_crypt_max_namelen, + .max_namelen = UBIFS_MAX_NLEN, }; diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 358abc26dbc0..57109a26ef3e 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -220,20 +220,9 @@ static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry, dbg_gen("'%pd' in dir ino %lu", dentry, dir->i_ino); - if (ubifs_crypt_is_encrypted(dir)) { - err = fscrypt_get_encryption_info(dir); - - /* - * DCACHE_ENCRYPTED_WITH_KEY is set if the dentry is - * created while the directory was encrypted and we - * have access to the key. - */ - if (fscrypt_has_encryption_key(dir)) - fscrypt_set_encrypted_dentry(dentry); - fscrypt_set_d_op(dentry); - if (err && err != -ENOKEY) - return ERR_PTR(err); - } + err = fscrypt_prepare_lookup(dir, dentry, flags); + if (err) + return ERR_PTR(err); err = fscrypt_setup_filename(dir, &dentry->d_name, 1, &nm); if (err) @@ -1150,38 +1139,24 @@ static int ubifs_symlink(struct inode *dir, struct dentry *dentry, struct ubifs_inode *dir_ui = ubifs_inode(dir); struct ubifs_info *c = dir->i_sb->s_fs_info; int err, sz_change, len = strlen(symname); - struct fscrypt_str disk_link = FSTR_INIT((char *)symname, len + 1); - struct fscrypt_symlink_data *sd = NULL; + struct fscrypt_str disk_link; struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1, .new_ino_d = ALIGN(len, 8), .dirtied_ino = 1 }; struct fscrypt_name nm; - if (ubifs_crypt_is_encrypted(dir)) { - err = fscrypt_get_encryption_info(dir); - if (err) - goto out_budg; - - if (!fscrypt_has_encryption_key(dir)) { - err = -EPERM; - goto out_budg; - } + dbg_gen("dent '%pd', target '%s' in dir ino %lu", dentry, + symname, dir->i_ino); - disk_link.len = (fscrypt_fname_encrypted_size(dir, len) + - sizeof(struct fscrypt_symlink_data)); - } + err = fscrypt_prepare_symlink(dir, symname, len, UBIFS_MAX_INO_DATA, + &disk_link); + if (err) + return err; /* * Budget request settings: new inode, new direntry and changing parent * directory inode. */ - - dbg_gen("dent '%pd', target '%s' in dir ino %lu", dentry, - symname, dir->i_ino); - - if (disk_link.len > UBIFS_MAX_INO_DATA) - return -ENAMETOOLONG; - err = ubifs_budget_space(c, &req); if (err) return err; @@ -1205,36 +1180,20 @@ static int ubifs_symlink(struct inode *dir, struct dentry *dentry, goto out_inode; } - if (ubifs_crypt_is_encrypted(dir)) { - struct qstr istr = QSTR_INIT(symname, len); - struct fscrypt_str ostr; - - sd = kzalloc(disk_link.len, GFP_NOFS); - if (!sd) { - err = -ENOMEM; - goto out_inode; - } - - ostr.name = sd->encrypted_path; - ostr.len = disk_link.len; - - err = fscrypt_fname_usr_to_disk(inode, &istr, &ostr); + if (IS_ENCRYPTED(inode)) { + disk_link.name = ui->data; /* encrypt directly into ui->data */ + err = fscrypt_encrypt_symlink(inode, symname, len, &disk_link); if (err) goto out_inode; - - sd->len = cpu_to_le16(ostr.len); - disk_link.name = (char *)sd; } else { + memcpy(ui->data, disk_link.name, disk_link.len); inode->i_link = ui->data; } - memcpy(ui->data, disk_link.name, disk_link.len); - ((char *)ui->data)[disk_link.len - 1] = '\0'; - /* * The terminating zero byte is not written to the flash media and it * is put just to make later in-memory string processing simpler. Thus, - * data length is @len, not @len + %1. + * data length is @disk_link.len - 1, not @disk_link.len. */ ui->data_len = disk_link.len - 1; inode->i_size = ubifs_inode(inode)->ui_size = disk_link.len - 1; @@ -1268,7 +1227,6 @@ out_fname: fscrypt_free_filename(&nm); out_budg: ubifs_release_budget(c, &req); - kfree(sd); return err; } diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 46e5a58c4b05..76fff889a2f7 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1664,49 +1664,17 @@ static const char *ubifs_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { - int err; - struct fscrypt_symlink_data *sd; struct ubifs_inode *ui = ubifs_inode(inode); - struct fscrypt_str cstr; - struct fscrypt_str pstr; - if (!ubifs_crypt_is_encrypted(inode)) + if (!IS_ENCRYPTED(inode)) return ui->data; if (!dentry) return ERR_PTR(-ECHILD); - err = fscrypt_get_encryption_info(inode); - if (err) - return ERR_PTR(err); - - sd = (struct fscrypt_symlink_data *)ui->data; - cstr.name = sd->encrypted_path; - cstr.len = le16_to_cpu(sd->len); - - if (cstr.len == 0) - return ERR_PTR(-ENOENT); - - if ((cstr.len + sizeof(struct fscrypt_symlink_data) - 1) > ui->data_len) - return ERR_PTR(-EIO); - - err = fscrypt_fname_alloc_buffer(inode, cstr.len, &pstr); - if (err) - return ERR_PTR(err); - - err = fscrypt_fname_disk_to_usr(inode, 0, 0, &cstr, &pstr); - if (err) { - fscrypt_fname_free_buffer(&pstr); - return ERR_PTR(err); - } - - pstr.name[pstr.len] = '\0'; - - set_delayed_call(done, kfree_link, pstr.name); - return pstr.name; + return fscrypt_get_symlink(inode, ui->data, ui->data_len, done); } - const struct address_space_operations ubifs_file_address_operations = { .readpage = ubifs_readpage, .writepage = ubifs_writepage, diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c index 1f6d16105990..e666459f63c7 100644 --- a/fs/ubifs/ioctl.c +++ b/fs/ubifs/ioctl.c @@ -43,7 +43,8 @@ void ubifs_set_inode_flags(struct inode *inode) { unsigned int flags = ubifs_inode(inode)->flags; - inode->i_flags &= ~(S_SYNC | S_APPEND | S_IMMUTABLE | S_DIRSYNC); + inode->i_flags &= ~(S_SYNC | S_APPEND | S_IMMUTABLE | S_DIRSYNC | + S_ENCRYPTED); if (flags & UBIFS_SYNC_FL) inode->i_flags |= S_SYNC; if (flags & UBIFS_APPEND_FL) @@ -52,6 +53,8 @@ void ubifs_set_inode_flags(struct inode *inode) inode->i_flags |= S_IMMUTABLE; if (flags & UBIFS_DIRSYNC_FL) inode->i_flags |= S_DIRSYNC; + if (flags & UBIFS_CRYPT_FL) + inode->i_flags |= S_ENCRYPTED; } /* diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index ad827cf642fe..8dd12b0bfb2b 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -379,9 +379,7 @@ out: } done: clear_inode(inode); -#ifdef CONFIG_UBIFS_FS_ENCRYPTION - fscrypt_put_encryption_info(inode, NULL); -#endif + fscrypt_put_encryption_info(inode); } static void ubifs_dirty_inode(struct inode *inode, int flags) @@ -2016,12 +2014,6 @@ static struct ubifs_info *alloc_ubifs_info(struct ubi_volume_desc *ubi) return c; } -#ifndef CONFIG_UBIFS_FS_ENCRYPTION -const struct fscrypt_operations ubifs_crypt_operations = { - .is_encrypted = __ubifs_crypt_is_encrypted, -}; -#endif - static int ubifs_fill_super(struct super_block *sb, void *data, int silent) { struct ubifs_info *c = sb->s_fs_info; @@ -2064,7 +2056,9 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent) sb->s_maxbytes = c->max_inode_sz = MAX_LFS_FILESIZE; sb->s_op = &ubifs_super_operations; sb->s_xattr = ubifs_xattr_handlers; +#ifdef CONFIG_UBIFS_FS_ENCRYPTION sb->s_cop = &ubifs_crypt_operations; +#endif mutex_lock(&c->umount_mutex); err = mount_ubifs(c); diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index cd43651f1731..63c7468147eb 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -38,12 +38,11 @@ #include <linux/backing-dev.h> #include <linux/security.h> #include <linux/xattr.h> -#ifdef CONFIG_UBIFS_FS_ENCRYPTION -#include <linux/fscrypt_supp.h> -#else -#include <linux/fscrypt_notsupp.h> -#endif #include <linux/random.h> + +#define __FS_HAS_ENCRYPTION IS_ENABLED(CONFIG_UBIFS_FS_ENCRYPTION) +#include <linux/fscrypt.h> + #include "ubifs-media.h" /* Version of this UBIFS implementation */ @@ -1835,18 +1834,13 @@ int ubifs_decrypt(const struct inode *inode, struct ubifs_data_node *dn, extern const struct fscrypt_operations ubifs_crypt_operations; -static inline bool __ubifs_crypt_is_encrypted(struct inode *inode) +static inline bool ubifs_crypt_is_encrypted(const struct inode *inode) { - struct ubifs_inode *ui = ubifs_inode(inode); + const struct ubifs_inode *ui = ubifs_inode(inode); return ui->flags & UBIFS_CRYPT_FL; } -static inline bool ubifs_crypt_is_encrypted(const struct inode *inode) -{ - return __ubifs_crypt_is_encrypted((struct inode *)inode); -} - /* Normal UBIFS messages */ __printf(2, 3) void ubifs_msg(const struct ubifs_info *c, const char *fmt, ...); diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index c13eae819cbc..5ddc89d564fd 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -170,6 +170,7 @@ static int create_xattr(struct ubifs_info *c, struct inode *host, err = ubifs_jnl_update(c, host, nm, inode, 0, 1); if (err) goto out_cancel; + ubifs_set_inode_flags(host); mutex_unlock(&host_ui->ui_mutex); ubifs_release_budget(c, &req); diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index e2b2196fd942..6499056a8064 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -886,7 +886,8 @@ static int userfaultfd_release(struct inode *inode, struct file *file) new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), - NULL_VM_UFFD_CTX); + NULL_VM_UFFD_CTX, + vma_get_anon_name(vma)); if (prev) vma = prev; else @@ -1446,7 +1447,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), - ((struct vm_userfaultfd_ctx){ ctx })); + ((struct vm_userfaultfd_ctx){ ctx }), + vma_get_anon_name(vma)); if (prev) { vma = prev; goto next; @@ -1608,7 +1610,8 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), - NULL_VM_UFFD_CTX); + NULL_VM_UFFD_CTX, + vma_get_anon_name(vma)); if (prev) { vma = prev; goto next; diff --git a/fs/utimes.c b/fs/utimes.c index e4b3d7c2c9f5..4f3b158f04a4 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -88,7 +88,7 @@ static int utimes_common(const struct path *path, struct timespec64 *times) } retry_deleg: inode_lock(inode); - error = notify_change(path->dentry, &newattrs, &delegated_inode); + error = notify_change2(path->mnt, path->dentry, &newattrs, &delegated_inode); inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); diff --git a/fs/xattr.c b/fs/xattr.c index 50029811fbe3..35ead9b764c6 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -131,7 +131,7 @@ xattr_permission(struct inode *inode, const char *name, int mask) return -EPERM; } - return inode_permission(inode, mask); + return inode_permission2(ERR_PTR(-EOPNOTSUPP), inode, mask); } int @@ -307,6 +307,9 @@ __vfs_getxattr(struct dentry *dentry, struct inode *inode, const char *name, handler = xattr_resolve_name(inode, &name); if (IS_ERR(handler)) return PTR_ERR(handler); + if (unlikely(handler->__get)) + return handler->__get(handler, dentry, inode, name, value, + size); if (!handler->get) return -EOPNOTSUPP; return handler->get(handler, dentry, inode, name, value, size); @@ -318,6 +321,7 @@ vfs_getxattr(struct dentry *dentry, const char *name, void *value, size_t size) { struct inode *inode = dentry->d_inode; int error; + const struct xattr_handler *handler; error = xattr_permission(inode, name, MAY_READ); if (error) @@ -340,7 +344,12 @@ vfs_getxattr(struct dentry *dentry, const char *name, void *value, size_t size) return ret; } nolsm: - return __vfs_getxattr(dentry, inode, name, value, size); + handler = xattr_resolve_name(inode, &name); + if (IS_ERR(handler)) + return PTR_ERR(handler); + if (!handler->get) + return -EOPNOTSUPP; + return handler->get(handler, dentry, inode, name, value, size); } EXPORT_SYMBOL_GPL(vfs_getxattr); diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 48e618b20d34..dbcad11cf615 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -67,10 +67,12 @@ */ #ifdef CONFIG_LD_DEAD_CODE_DATA_ELIMINATION #define TEXT_MAIN .text .text.[0-9a-zA-Z_]* +#define TEXT_CFI_MAIN .text.cfi .text.[0-9a-zA-Z_]*.cfi #define DATA_MAIN .data .data.[0-9a-zA-Z_]* #define BSS_MAIN .bss .bss.[0-9a-zA-Z_]* #else #define TEXT_MAIN .text +#define TEXT_CFI_MAIN .text.cfi #define DATA_MAIN .data #define BSS_MAIN .bss #endif @@ -105,7 +107,7 @@ #ifdef CONFIG_FTRACE_MCOUNT_RECORD #define MCOUNT_REC() . = ALIGN(8); \ VMLINUX_SYMBOL(__start_mcount_loc) = .; \ - *(__mcount_loc) \ + KEEP(*(__mcount_loc)) \ VMLINUX_SYMBOL(__stop_mcount_loc) = .; #else #define MCOUNT_REC() @@ -461,6 +463,8 @@ ALIGN_FUNCTION(); \ *(.text.hot TEXT_MAIN .text.fixup .text.unlikely) \ *(.text..refcount) \ + *(.text..ftrace) \ + *(TEXT_CFI_MAIN) \ *(.ref.text) \ MEM_KEEP(init.text) \ MEM_KEEP(exit.text) \ @@ -513,7 +517,7 @@ VMLINUX_SYMBOL(__softirqentry_text_end) = .; /* Section used for early init (in .S files) */ -#define HEAD_TEXT *(.head.text) +#define HEAD_TEXT KEEP(*(.head.text)) #define HEAD_TEXT_SECTION \ .head.text : AT(ADDR(.head.text) - LOAD_OFFSET) { \ @@ -558,7 +562,7 @@ MEM_DISCARD(init.data) \ KERNEL_CTORS() \ MCOUNT_REC() \ - *(.init.rodata) \ + *(.init.rodata .init.rodata.*) \ FTRACE_EVENTS() \ TRACE_SYSCALLS() \ KPROBE_BLACKLIST() \ @@ -577,7 +581,7 @@ EARLYCON_TABLE() #define INIT_TEXT \ - *(.init.text) \ + *(.init.text .init.text.*) \ *(.text.startup) \ MEM_DISCARD(init.text) @@ -594,7 +598,7 @@ MEM_DISCARD(exit.text) #define EXIT_CALL \ - *(.exitcall.exit) + KEEP(*(.exitcall.exit)) /* * bss (Block Started by Symbol) - uninitialized data diff --git a/include/crypto/chacha.h b/include/crypto/chacha.h new file mode 100644 index 000000000000..3d261f5cd156 --- /dev/null +++ b/include/crypto/chacha.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Common values and helper functions for the ChaCha and XChaCha stream ciphers. + * + * XChaCha extends ChaCha's nonce to 192 bits, while provably retaining ChaCha's + * security. Here they share the same key size, tfm context, and setkey + * function; only their IV size and encrypt/decrypt function differ. + * + * The ChaCha paper specifies 20, 12, and 8-round variants. In general, it is + * recommended to use the 20-round variant ChaCha20. However, the other + * variants can be needed in some performance-sensitive scenarios. The generic + * ChaCha code currently allows only the 20 and 12-round variants. + */ + +#ifndef _CRYPTO_CHACHA_H +#define _CRYPTO_CHACHA_H + +#include <crypto/skcipher.h> +#include <linux/types.h> +#include <linux/crypto.h> + +/* 32-bit stream position, then 96-bit nonce (RFC7539 convention) */ +#define CHACHA_IV_SIZE 16 + +#define CHACHA_KEY_SIZE 32 +#define CHACHA_BLOCK_SIZE 64 + +/* 192-bit nonce, then 64-bit stream position */ +#define XCHACHA_IV_SIZE 32 + +struct chacha_ctx { + u32 key[8]; + int nrounds; +}; + +void chacha_block(u32 *state, u8 *stream, int nrounds); +static inline void chacha20_block(u32 *state, u8 *stream) +{ + chacha_block(state, stream, 20); +} +void hchacha_block(const u32 *in, u32 *out, int nrounds); + +void crypto_chacha_init(u32 *state, struct chacha_ctx *ctx, u8 *iv); + +int crypto_chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key, + unsigned int keysize); +int crypto_chacha12_setkey(struct crypto_skcipher *tfm, const u8 *key, + unsigned int keysize); + +int crypto_chacha_crypt(struct skcipher_request *req); +int crypto_xchacha_crypt(struct skcipher_request *req); + +#endif /* _CRYPTO_CHACHA_H */ diff --git a/include/crypto/chacha20.h b/include/crypto/chacha20.h deleted file mode 100644 index caaa470389e0..000000000000 --- a/include/crypto/chacha20.h +++ /dev/null @@ -1,27 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Common values for the ChaCha20 algorithm - */ - -#ifndef _CRYPTO_CHACHA20_H -#define _CRYPTO_CHACHA20_H - -#include <crypto/skcipher.h> -#include <linux/types.h> -#include <linux/crypto.h> - -#define CHACHA20_IV_SIZE 16 -#define CHACHA20_KEY_SIZE 32 -#define CHACHA20_BLOCK_SIZE 64 - -struct chacha20_ctx { - u32 key[8]; -}; - -void chacha20_block(u32 *state, void *stream); -void crypto_chacha20_init(u32 *state, struct chacha20_ctx *ctx, u8 *iv); -int crypto_chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key, - unsigned int keysize); -int crypto_chacha20_crypt(struct skcipher_request *req); - -#endif diff --git a/include/crypto/nhpoly1305.h b/include/crypto/nhpoly1305.h new file mode 100644 index 000000000000..53c04423c582 --- /dev/null +++ b/include/crypto/nhpoly1305.h @@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Common values and helper functions for the NHPoly1305 hash function. + */ + +#ifndef _NHPOLY1305_H +#define _NHPOLY1305_H + +#include <crypto/hash.h> +#include <crypto/poly1305.h> + +/* NH parameterization: */ + +/* Endianness: little */ +/* Word size: 32 bits (works well on NEON, SSE2, AVX2) */ + +/* Stride: 2 words (optimal on ARM32 NEON; works okay on other CPUs too) */ +#define NH_PAIR_STRIDE 2 +#define NH_MESSAGE_UNIT (NH_PAIR_STRIDE * 2 * sizeof(u32)) + +/* Num passes (Toeplitz iteration count): 4, to give ε = 2^{-128} */ +#define NH_NUM_PASSES 4 +#define NH_HASH_BYTES (NH_NUM_PASSES * sizeof(u64)) + +/* Max message size: 1024 bytes (32x compression factor) */ +#define NH_NUM_STRIDES 64 +#define NH_MESSAGE_WORDS (NH_PAIR_STRIDE * 2 * NH_NUM_STRIDES) +#define NH_MESSAGE_BYTES (NH_MESSAGE_WORDS * sizeof(u32)) +#define NH_KEY_WORDS (NH_MESSAGE_WORDS + \ + NH_PAIR_STRIDE * 2 * (NH_NUM_PASSES - 1)) +#define NH_KEY_BYTES (NH_KEY_WORDS * sizeof(u32)) + +#define NHPOLY1305_KEY_SIZE (POLY1305_BLOCK_SIZE + NH_KEY_BYTES) + +struct nhpoly1305_key { + struct poly1305_key poly_key; + u32 nh_key[NH_KEY_WORDS]; +}; + +struct nhpoly1305_state { + + /* Running total of polynomial evaluation */ + struct poly1305_state poly_state; + + /* Partial block buffer */ + u8 buffer[NH_MESSAGE_UNIT]; + unsigned int buflen; + + /* + * Number of bytes remaining until the current NH message reaches + * NH_MESSAGE_BYTES. When nonzero, 'nh_hash' holds the partial NH hash. + */ + unsigned int nh_remaining; + + __le64 nh_hash[NH_NUM_PASSES]; +}; + +typedef void (*nh_t)(const u32 *key, const u8 *message, size_t message_len, + __le64 hash[NH_NUM_PASSES]); + +int crypto_nhpoly1305_setkey(struct crypto_shash *tfm, + const u8 *key, unsigned int keylen); + +int crypto_nhpoly1305_init(struct shash_desc *desc); +int crypto_nhpoly1305_update(struct shash_desc *desc, + const u8 *src, unsigned int srclen); +int crypto_nhpoly1305_update_helper(struct shash_desc *desc, + const u8 *src, unsigned int srclen, + nh_t nh_fn); +int crypto_nhpoly1305_final(struct shash_desc *desc, u8 *dst); +int crypto_nhpoly1305_final_helper(struct shash_desc *desc, u8 *dst, + nh_t nh_fn); + +#endif /* _NHPOLY1305_H */ diff --git a/include/crypto/poly1305.h b/include/crypto/poly1305.h index f718a19da82f..34317ed2071e 100644 --- a/include/crypto/poly1305.h +++ b/include/crypto/poly1305.h @@ -13,13 +13,21 @@ #define POLY1305_KEY_SIZE 32 #define POLY1305_DIGEST_SIZE 16 +struct poly1305_key { + u32 r[5]; /* key, base 2^26 */ +}; + +struct poly1305_state { + u32 h[5]; /* accumulator, base 2^26 */ +}; + struct poly1305_desc_ctx { /* key */ - u32 r[5]; + struct poly1305_key r; /* finalize key */ u32 s[4]; /* accumulator */ - u32 h[5]; + struct poly1305_state h; /* partial buffer */ u8 buf[POLY1305_BLOCK_SIZE]; /* bytes used in partial buffer */ @@ -30,6 +38,22 @@ struct poly1305_desc_ctx { bool sset; }; +/* + * Poly1305 core functions. These implement the ε-almost-∆-universal hash + * function underlying the Poly1305 MAC, i.e. they don't add an encrypted nonce + * ("s key") at the end. They also only support block-aligned inputs. + */ +void poly1305_core_setkey(struct poly1305_key *key, const u8 *raw_key); +static inline void poly1305_core_init(struct poly1305_state *state) +{ + memset(state->h, 0, sizeof(state->h)); +} +void poly1305_core_blocks(struct poly1305_state *state, + const struct poly1305_key *key, + const void *src, unsigned int nblocks); +void poly1305_core_emit(const struct poly1305_state *state, void *dst); + +/* Crypto API helper functions for the Poly1305 MAC */ int crypto_poly1305_init(struct shash_desc *desc); unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx, const u8 *src, unsigned int srclen); diff --git a/include/linux/amba/mmci.h b/include/linux/amba/mmci.h index da8357ba11bc..02dc2f3a76f7 100644 --- a/include/linux/amba/mmci.h +++ b/include/linux/amba/mmci.h @@ -6,6 +6,15 @@ #define AMBA_MMCI_H #include <linux/mmc/host.h> +#include <linux/mmc/card.h> +#include <linux/mmc/sdio_func.h> + +struct embedded_sdio_data { + struct sdio_cis cis; + struct sdio_cccr cccr; + struct sdio_embedded_func *funcs; + int num_funcs; +}; /** * struct mmci_platform_data - platform configuration for the MMCI @@ -32,6 +41,7 @@ struct mmci_platform_data { int gpio_wp; int gpio_cd; bool cd_invert; + struct embedded_sdio_data *embedded_sdio; }; #endif diff --git a/include/linux/android_aid.h b/include/linux/android_aid.h new file mode 100644 index 000000000000..6f1fa1792dfc --- /dev/null +++ b/include/linux/android_aid.h @@ -0,0 +1,28 @@ +/* include/linux/android_aid.h + * + * Copyright (C) 2008 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#ifndef _LINUX_ANDROID_AID_H +#define _LINUX_ANDROID_AID_H + +/* AIDs that the kernel treats differently */ +#define AID_OBSOLETE_000 KGIDT_INIT(3001) /* was NET_BT_ADMIN */ +#define AID_OBSOLETE_001 KGIDT_INIT(3002) /* was NET_BT */ +#define AID_INET KGIDT_INIT(3003) +#define AID_NET_RAW KGIDT_INIT(3004) +#define AID_NET_ADMIN KGIDT_INIT(3005) +#define AID_NET_BW_STATS KGIDT_INIT(3006) /* read bandwidth statistics */ +#define AID_NET_BW_ACCT KGIDT_INIT(3007) /* change bandwidth statistics accounting */ + +#endif diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index d4fcb0efb896..d70f95476927 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -6,15 +6,43 @@ #define _LINUX_ARCH_TOPOLOGY_H_ #include <linux/types.h> +#include <linux/percpu.h> void topology_normalize_cpu_scale(void); +int topology_detect_flags(void); +int topology_smt_flags(void); +int topology_core_flags(void); +int topology_cpu_flags(void); +int topology_update_cpu_topology(void); struct device_node; bool topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu); +DECLARE_PER_CPU(unsigned long, cpu_scale); + struct sched_domain; -unsigned long topology_get_cpu_scale(struct sched_domain *sd, int cpu); +static inline +unsigned long topology_get_cpu_scale(struct sched_domain *sd, int cpu) +{ + return per_cpu(cpu_scale, cpu); +} void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity); +DECLARE_PER_CPU(unsigned long, freq_scale); + +static inline +unsigned long topology_get_freq_scale(struct sched_domain *sd, int cpu) +{ + return per_cpu(freq_scale, cpu); +} + +DECLARE_PER_CPU(unsigned long, max_freq_scale); + +static inline +unsigned long topology_get_max_freq_scale(struct sched_domain *sd, int cpu) +{ + return per_cpu(max_freq_scale, cpu); +} + #endif /* _LINUX_ARCH_TOPOLOGY_H_ */ diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 18863d56273c..9f721ee6690d 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -160,6 +160,7 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, #define SMCCC_SMC_INST "smc #0" #define SMCCC_HVC_INST "hvc #0" +#define SMCCC_REG(n) asm("x" # n) #elif defined(CONFIG_ARM) #include <asm/opcodes-sec.h> @@ -167,6 +168,7 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, #define SMCCC_SMC_INST __SMC(0) #define SMCCC_HVC_INST __HVC(0) +#define SMCCC_REG(n) asm("r" # n) #endif @@ -199,57 +201,57 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, #define __declare_arg_0(a0, res) \ struct arm_smccc_res *___res = res; \ - register unsigned long r0 asm("r0") = (u32)a0; \ - register unsigned long r1 asm("r1"); \ - register unsigned long r2 asm("r2"); \ - register unsigned long r3 asm("r3") + register unsigned long r0 SMCCC_REG(0) = (u32)a0; \ + register unsigned long r1 SMCCC_REG(1); \ + register unsigned long r2 SMCCC_REG(2); \ + register unsigned long r3 SMCCC_REG(3) #define __declare_arg_1(a0, a1, res) \ typeof(a1) __a1 = a1; \ struct arm_smccc_res *___res = res; \ - register unsigned long r0 asm("r0") = (u32)a0; \ - register unsigned long r1 asm("r1") = __a1; \ - register unsigned long r2 asm("r2"); \ - register unsigned long r3 asm("r3") + register unsigned long r0 SMCCC_REG(0) = (u32)a0; \ + register unsigned long r1 SMCCC_REG(1) = __a1; \ + register unsigned long r2 SMCCC_REG(2); \ + register unsigned long r3 SMCCC_REG(3) #define __declare_arg_2(a0, a1, a2, res) \ typeof(a1) __a1 = a1; \ typeof(a2) __a2 = a2; \ struct arm_smccc_res *___res = res; \ - register unsigned long r0 asm("r0") = (u32)a0; \ - register unsigned long r1 asm("r1") = __a1; \ - register unsigned long r2 asm("r2") = __a2; \ - register unsigned long r3 asm("r3") + register unsigned long r0 SMCCC_REG(0) = (u32)a0; \ + register unsigned long r1 SMCCC_REG(1) = __a1; \ + register unsigned long r2 SMCCC_REG(2) = __a2; \ + register unsigned long r3 SMCCC_REG(3) #define __declare_arg_3(a0, a1, a2, a3, res) \ typeof(a1) __a1 = a1; \ typeof(a2) __a2 = a2; \ typeof(a3) __a3 = a3; \ struct arm_smccc_res *___res = res; \ - register unsigned long r0 asm("r0") = (u32)a0; \ - register unsigned long r1 asm("r1") = __a1; \ - register unsigned long r2 asm("r2") = __a2; \ - register unsigned long r3 asm("r3") = __a3 + register unsigned long r0 SMCCC_REG(0) = (u32)a0; \ + register unsigned long r1 SMCCC_REG(1) = __a1; \ + register unsigned long r2 SMCCC_REG(2) = __a2; \ + register unsigned long r3 SMCCC_REG(3) = __a3 #define __declare_arg_4(a0, a1, a2, a3, a4, res) \ typeof(a4) __a4 = a4; \ __declare_arg_3(a0, a1, a2, a3, res); \ - register unsigned long r4 asm("r4") = __a4 + register unsigned long r4 SMCCC_REG(4) = __a4 #define __declare_arg_5(a0, a1, a2, a3, a4, a5, res) \ typeof(a5) __a5 = a5; \ __declare_arg_4(a0, a1, a2, a3, a4, res); \ - register unsigned long r5 asm("r5") = __a5 + register unsigned long r5 SMCCC_REG(5) = __a5 #define __declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res) \ typeof(a6) __a6 = a6; \ __declare_arg_5(a0, a1, a2, a3, a4, a5, res); \ - register unsigned long r6 asm("r6") = __a6 + register unsigned long r6 SMCCC_REG(6) = __a6 #define __declare_arg_7(a0, a1, a2, a3, a4, a5, a6, a7, res) \ typeof(a7) __a7 = a7; \ __declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res); \ - register unsigned long r7 asm("r7") = __a7 + register unsigned long r7 SMCCC_REG(7) = __a7 #define ___declare_args(count, ...) __declare_arg_ ## count(__VA_ARGS__) #define __declare_args(count, ...) ___declare_args(count, __VA_ARGS__) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e9e87599338e..c2954ab168af 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -200,6 +200,9 @@ struct bpf_prog_aux { struct bpf_map **used_maps; struct bpf_prog *prog; struct user_struct *user; +#ifdef CONFIG_SECURITY + void *security; +#endif union { struct work_struct work; struct rcu_head rcu; @@ -255,6 +258,9 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); +extern const struct file_operations bpf_map_fops; +extern const struct file_operations bpf_prog_fops; + #define BPF_PROG_TYPE(_id, _ops) \ extern const struct bpf_verifier_ops _ops; #define BPF_MAP_TYPE(_id, _ops) \ @@ -284,11 +290,11 @@ void bpf_map_area_free(void *base); extern int sysctl_unprivileged_bpf_disabled; -int bpf_map_new_fd(struct bpf_map *map); +int bpf_map_new_fd(struct bpf_map *map, int flags); int bpf_prog_new_fd(struct bpf_prog *prog); int bpf_obj_pin_user(u32 ufd, const char __user *pathname); -int bpf_obj_get_user(const char __user *pathname); +int bpf_obj_get_user(const char __user *pathname, int flags); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); @@ -306,6 +312,8 @@ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file, void *key, void *value, u64 map_flags); int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value); +int bpf_get_file_flag(int flags); + /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and * forced to use 'long' read/writes to try to atomically copy long counters. * Best-effort only. No barriers here, since it _will_ race with concurrent @@ -325,6 +333,8 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr); +struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type); + /* Map specifics */ struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key); void __dev_map_insert_ctx(struct bpf_map *map, u32 index); @@ -382,11 +392,17 @@ static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages) { } -static inline int bpf_obj_get_user(const char __user *pathname) +static inline int bpf_obj_get_user(const char __user *pathname, int flags) { return -EOPNOTSUPP; } +static inline struct bpf_prog *bpf_prog_get_type_path(const char *name, + enum bpf_prog_type type) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key) { diff --git a/include/linux/cfi.h b/include/linux/cfi.h new file mode 100644 index 000000000000..e27033d5dd53 --- /dev/null +++ b/include/linux/cfi.h @@ -0,0 +1,38 @@ +#ifndef _LINUX_CFI_H +#define _LINUX_CFI_H + +#include <linux/stringify.h> + +#ifdef CONFIG_CFI_CLANG +#ifdef CONFIG_MODULES + +typedef void (*cfi_check_fn)(uint64_t, void *, void *); + +/* Compiler-generated function in each module, and the kernel */ +#define CFI_CHECK_FN __cfi_check +#define CFI_CHECK_FN_NAME __stringify(CFI_CHECK_FN) + +extern void CFI_CHECK_FN(uint64_t, void *, void *); + +#ifdef CONFIG_CFI_CLANG_SHADOW +extern void cfi_module_add(struct module *mod, unsigned long min_addr, + unsigned long max_addr); + +extern void cfi_module_remove(struct module *mod, unsigned long min_addr, + unsigned long max_addr); +#else +static inline void cfi_module_add(struct module *mod, unsigned long min_addr, + unsigned long max_addr) +{ +} + +static inline void cfi_module_remove(struct module *mod, unsigned long min_addr, + unsigned long max_addr) +{ +} +#endif /* CONFIG_CFI_CLANG_SHADOW */ + +#endif /* CONFIG_MODULES */ +#endif /* CONFIG_CFI_CLANG */ + +#endif /* _LINUX_CFI_H */ diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 9e1ff02d6c4e..2604f8750f54 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -19,6 +19,7 @@ #include <linux/percpu-rwsem.h> #include <linux/workqueue.h> #include <linux/bpf-cgroup.h> +#include <linux/psi_types.h> #ifdef CONFIG_CGROUPS @@ -30,6 +31,7 @@ struct kernfs_node; struct kernfs_ops; struct kernfs_open_file; struct seq_file; +struct poll_table_struct; #define MAX_CGROUP_TYPE_NAMELEN 32 #define MAX_CGROUP_ROOT_NAMELEN 64 @@ -374,6 +376,9 @@ struct cgroup { /* used to schedule release agent */ struct work_struct release_agent_work; + /* used to track pressure stalls */ + struct psi_group psi; + /* used to store eBPF programs */ struct cgroup_bpf bpf; @@ -504,6 +509,9 @@ struct cftype { ssize_t (*write)(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off); + unsigned int (*poll)(struct kernfs_open_file *of, + struct poll_table_struct *pt); + #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lock_class_key lockdep_key; #endif diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 3be0c9e7e150..05ee3c0ad3e4 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -638,6 +638,11 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp) pr_cont_kernfs_path(cgrp->kn); } +static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) +{ + return &cgrp->psi; +} + static inline void cgroup_init_kthreadd(void) { /* @@ -692,6 +697,16 @@ static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp) return NULL; } +static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) +{ + return NULL; +} + +static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) +{ + return NULL; +} + static inline bool task_under_cgroup_hierarchy(struct task_struct *task, struct cgroup *ancestor) { diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h index acb77dcff3b4..8996c092568b 100644 --- a/include/linux/cgroup_subsys.h +++ b/include/linux/cgroup_subsys.h @@ -21,6 +21,10 @@ SUBSYS(cpu) SUBSYS(cpuacct) #endif +#if IS_ENABLED(CONFIG_SCHED_TUNE) +SUBSYS(schedtune) +#endif + #if IS_ENABLED(CONFIG_BLK_CGROUP) SUBSYS(io) #endif diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 673fa522a7ab..6c5b4d73713e 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -25,6 +25,15 @@ #undef __noretpoline #endif +#ifdef CONFIG_LTO_CLANG +#ifdef CONFIG_FTRACE_MCOUNT_RECORD +#define __norecordmcount \ + __attribute__((__section__(".text..ftrace"))) +#endif + +#define __nocfi __attribute__((no_sanitize("cfi"))) +#endif + /* * Not all versions of clang implement the the type-generic versions * of the builtin overflow checkers. Fortunately, clang implements diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 222fcefaa6a7..a207f820d3b0 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -269,6 +269,14 @@ struct ftrace_likely_data { # define __nostackprotector #endif +#ifndef __norecordmcount +#define __norecordmcount +#endif + +#ifndef __nocfi +#define __nocfi +#endif + /* * Assume alignment of return value. */ diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index cad1eb50d668..67f4e960880e 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -912,6 +912,11 @@ static inline bool policy_has_boost_freq(struct cpufreq_policy *policy) extern void arch_freq_prepare_all(void); extern unsigned int arch_freq_get_on_cpu(int cpu); +extern void arch_set_freq_scale(struct cpumask *cpus, unsigned long cur_freq, + unsigned long max_freq); +extern void arch_set_max_freq_scale(struct cpumask *cpus, + unsigned long policy_max_freq); + /* the following are really really optional */ extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs; extern struct freq_attr cpufreq_freq_attr_scaling_boost_freqs; diff --git a/include/linux/cpufreq_times.h b/include/linux/cpufreq_times.h new file mode 100644 index 000000000000..0eb6dc9d0fe2 --- /dev/null +++ b/include/linux/cpufreq_times.h @@ -0,0 +1,46 @@ +/* drivers/cpufreq/cpufreq_times.c + * + * Copyright (C) 2018 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#ifndef _LINUX_CPUFREQ_TIMES_H +#define _LINUX_CPUFREQ_TIMES_H + +#include <linux/cpufreq.h> +#include <linux/pid.h> + +#ifdef CONFIG_CPU_FREQ_TIMES +void cpufreq_task_times_init(struct task_struct *p); +void cpufreq_task_times_alloc(struct task_struct *p); +void cpufreq_task_times_exit(struct task_struct *p); +int proc_time_in_state_show(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *p); +void cpufreq_acct_update_power(struct task_struct *p, u64 cputime); +void cpufreq_times_create_policy(struct cpufreq_policy *policy); +void cpufreq_times_record_transition(struct cpufreq_policy *policy, + unsigned int new_freq); +void cpufreq_task_times_remove_uids(uid_t uid_start, uid_t uid_end); +int single_uid_time_in_state_open(struct inode *inode, struct file *file); +#else +static inline void cpufreq_task_times_init(struct task_struct *p) {} +static inline void cpufreq_task_times_alloc(struct task_struct *p) {} +static inline void cpufreq_task_times_exit(struct task_struct *p) {} +static inline void cpufreq_acct_update_power(struct task_struct *p, + u64 cputime) {} +static inline void cpufreq_times_create_policy(struct cpufreq_policy *policy) {} +static inline void cpufreq_times_record_transition( + struct cpufreq_policy *policy, unsigned int new_freq) {} +static inline void cpufreq_task_times_remove_uids(uid_t uid_start, + uid_t uid_end) {} +#endif /* CONFIG_CPU_FREQ_TIMES */ +#endif /* _LINUX_CPUFREQ_TIMES_H */ diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index a6989e02d0a0..113a14833ad3 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -131,7 +131,8 @@ extern bool cpuidle_not_available(struct cpuidle_driver *drv, struct cpuidle_device *dev); extern int cpuidle_select(struct cpuidle_driver *drv, - struct cpuidle_device *dev); + struct cpuidle_device *dev, + bool *stop_tick); extern int cpuidle_enter(struct cpuidle_driver *drv, struct cpuidle_device *dev, int index); extern void cpuidle_reflect(struct cpuidle_device *dev, int index); @@ -163,7 +164,7 @@ static inline bool cpuidle_not_available(struct cpuidle_driver *drv, struct cpuidle_device *dev) {return true; } static inline int cpuidle_select(struct cpuidle_driver *drv, - struct cpuidle_device *dev) + struct cpuidle_device *dev, bool *stop_tick) {return -ENODEV; } static inline int cpuidle_enter(struct cpuidle_driver *drv, struct cpuidle_device *dev, int index) @@ -214,7 +215,7 @@ static inline void cpuidle_use_deepest_state(bool enable) #endif /* kernel/sched/idle.c */ -extern void sched_idle_set_state(struct cpuidle_state *idle_state); +extern void sched_idle_set_state(struct cpuidle_state *idle_state, int index); extern void default_idle_call(void); #ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED @@ -246,7 +247,8 @@ struct cpuidle_governor { struct cpuidle_device *dev); int (*select) (struct cpuidle_driver *drv, - struct cpuidle_device *dev); + struct cpuidle_device *dev, + bool *stop_tick); void (*reflect) (struct cpuidle_device *dev, int index); }; diff --git a/include/linux/crypto.h b/include/linux/crypto.h index de96913306cb..5e14fac088d5 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -24,6 +24,7 @@ #include <linux/slab.h> #include <linux/string.h> #include <linux/uaccess.h> +#include <linux/completion.h> /* * Autoloaded crypto modules should only use a prefixed name to avoid allowing @@ -481,6 +482,45 @@ struct crypto_alg { } CRYPTO_MINALIGN_ATTR; /* + * A helper struct for waiting for completion of async crypto ops + */ +struct crypto_wait { + struct completion completion; + int err; +}; + +/* + * Macro for declaring a crypto op async wait object on stack + */ +#define DECLARE_CRYPTO_WAIT(_wait) \ + struct crypto_wait _wait = { \ + COMPLETION_INITIALIZER_ONSTACK((_wait).completion), 0 } + +/* + * Async ops completion helper functioons + */ +void crypto_req_done(struct crypto_async_request *req, int err); + +static inline int crypto_wait_req(int err, struct crypto_wait *wait) +{ + switch (err) { + case -EINPROGRESS: + case -EBUSY: + wait_for_completion(&wait->completion); + reinit_completion(&wait->completion); + err = wait->err; + break; + }; + + return err; +} + +static inline void crypto_init_wait(struct crypto_wait *wait) +{ + init_completion(&wait->completion); +} + +/* * Algorithm registration interface. */ int crypto_register_alg(struct crypto_alg *alg); diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 006f4ccda5f5..e79b7ba88a9b 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -149,6 +149,7 @@ struct dentry_operations { int (*d_manage)(const struct path *, bool); struct dentry *(*d_real)(struct dentry *, const struct inode *, unsigned int, unsigned int); + void (*d_canonical_path)(const struct path *, struct path *); } ____cacheline_aligned; /* diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 31c865d1842e..577d1b25fccd 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -57,7 +57,12 @@ struct task_delay_info { u64 freepages_start; u64 freepages_delay; /* wait for memory reclaim */ + + u64 thrashing_start; + u64 thrashing_delay; /* wait for thrashing page */ + u32 freepages_count; /* total count of memory reclaim */ + u32 thrashing_count; /* total count of thrash waits */ }; #endif @@ -76,6 +81,8 @@ extern int __delayacct_add_tsk(struct taskstats *, struct task_struct *); extern __u64 __delayacct_blkio_ticks(struct task_struct *); extern void __delayacct_freepages_start(void); extern void __delayacct_freepages_end(void); +extern void __delayacct_thrashing_start(void); +extern void __delayacct_thrashing_end(void); static inline int delayacct_is_task_waiting_on_io(struct task_struct *p) { @@ -156,6 +163,18 @@ static inline void delayacct_freepages_end(void) __delayacct_freepages_end(); } +static inline void delayacct_thrashing_start(void) +{ + if (current->delays) + __delayacct_thrashing_start(); +} + +static inline void delayacct_thrashing_end(void) +{ + if (current->delays) + __delayacct_thrashing_end(); +} + #else static inline void delayacct_set_flag(int flag) {} @@ -182,6 +201,10 @@ static inline void delayacct_freepages_start(void) {} static inline void delayacct_freepages_end(void) {} +static inline void delayacct_thrashing_start(void) +{} +static inline void delayacct_thrashing_end(void) +{} #endif /* CONFIG_TASK_DELAY_ACCT */ diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 171895072435..6385ecd03155 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -111,6 +111,7 @@ struct dma_fence_cb { * @get_driver_name: returns the driver name. * @get_timeline_name: return the name of the context this fence belongs to. * @enable_signaling: enable software signaling of fence. + * @disable_signaling: disable software signaling of fence (optional). * @signaled: [optional] peek whether the fence is signaled, can be null. * @wait: custom wait implementation, or dma_fence_default_wait. * @release: [optional] called on destruction of fence, can be null @@ -170,6 +171,7 @@ struct dma_fence_ops { const char * (*get_driver_name)(struct dma_fence *fence); const char * (*get_timeline_name)(struct dma_fence *fence); bool (*enable_signaling)(struct dma_fence *fence); + void (*disable_signaling)(struct dma_fence *fence); bool (*signaled)(struct dma_fence *fence); signed long (*wait)(struct dma_fence *fence, bool intr, signed long timeout); diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 2a0c453d7235..f5740423b002 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /** * include/linux/f2fs_fs.h * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef _LINUX_F2FS_FS_H #define _LINUX_F2FS_FS_H @@ -21,6 +18,7 @@ #define F2FS_BLKSIZE 4096 /* support only 4KB block */ #define F2FS_BLKSIZE_BITS 12 /* bits for F2FS_BLKSIZE */ #define F2FS_MAX_EXTENSION 64 /* # of extension entries */ +#define F2FS_EXTENSION_LEN 8 /* max size of extension */ #define F2FS_BLK_ALIGN(x) (((x) + F2FS_BLKSIZE - 1) >> F2FS_BLKSIZE_BITS) #define NULL_ADDR ((block_t)0) /* used as block_t addresses */ @@ -36,15 +34,16 @@ #define F2FS_NODE_INO(sbi) ((sbi)->node_ino_num) #define F2FS_META_INO(sbi) ((sbi)->meta_ino_num) -#define F2FS_IO_SIZE(sbi) (1 << (sbi)->write_io_size_bits) /* Blocks */ -#define F2FS_IO_SIZE_KB(sbi) (1 << ((sbi)->write_io_size_bits + 2)) /* KB */ -#define F2FS_IO_SIZE_BYTES(sbi) (1 << ((sbi)->write_io_size_bits + 12)) /* B */ -#define F2FS_IO_SIZE_BITS(sbi) ((sbi)->write_io_size_bits) /* power of 2 */ +#define F2FS_MAX_QUOTAS 3 + +#define F2FS_IO_SIZE(sbi) (1 << F2FS_OPTION(sbi).write_io_size_bits) /* Blocks */ +#define F2FS_IO_SIZE_KB(sbi) (1 << (F2FS_OPTION(sbi).write_io_size_bits + 2)) /* KB */ +#define F2FS_IO_SIZE_BYTES(sbi) (1 << (F2FS_OPTION(sbi).write_io_size_bits + 12)) /* B */ +#define F2FS_IO_SIZE_BITS(sbi) (F2FS_OPTION(sbi).write_io_size_bits) /* power of 2 */ #define F2FS_IO_SIZE_MASK(sbi) (F2FS_IO_SIZE(sbi) - 1) /* This flag is used by node and meta inodes, and by recovery */ #define GFP_F2FS_ZERO (GFP_NOFS | __GFP_ZERO) -#define GFP_F2FS_HIGH_ZERO (GFP_NOFS | __GFP_ZERO | __GFP_HIGHMEM) /* * For further optimization on multi-head logs, on-disk layout supports maximum @@ -100,7 +99,7 @@ struct f2fs_super_block { __u8 uuid[16]; /* 128-bit uuid for volume */ __le16 volume_name[MAX_VOLUME_NAME]; /* volume name */ __le32 extension_count; /* # of extensions below */ - __u8 extension_list[F2FS_MAX_EXTENSION][8]; /* extension array */ + __u8 extension_list[F2FS_MAX_EXTENSION][F2FS_EXTENSION_LEN];/* extension array */ __le32 cp_payload; __u8 version[VERSION_LEN]; /* the kernel version */ __u8 init_version[VERSION_LEN]; /* the initial kernel version */ @@ -108,12 +107,20 @@ struct f2fs_super_block { __u8 encryption_level; /* versioning level for encryption */ __u8 encrypt_pw_salt[16]; /* Salt used for string2key algorithm */ struct f2fs_device devs[MAX_DEVICES]; /* device list */ - __u8 reserved[327]; /* valid reserved region */ + __le32 qf_ino[F2FS_MAX_QUOTAS]; /* quota inode numbers */ + __u8 hot_ext_count; /* # of hot file extension */ + __u8 reserved[310]; /* valid reserved region */ + __le32 crc; /* checksum of superblock */ } __packed; /* * For checkpoint */ +#define CP_DISABLED_QUICK_FLAG 0x00002000 +#define CP_DISABLED_FLAG 0x00001000 +#define CP_QUOTA_NEED_FSCK_FLAG 0x00000800 +#define CP_LARGE_NAT_BITMAP_FLAG 0x00000400 +#define CP_NOCRC_RECOVERY_FLAG 0x00000200 #define CP_TRIMMED_FLAG 0x00000100 #define CP_NAT_BITS_FLAG 0x00000080 #define CP_CRC_RECOVERY_FLAG 0x00000040 @@ -180,11 +187,12 @@ struct f2fs_orphan_block { struct f2fs_extent { __le32 fofs; /* start file offset of the extent */ __le32 blk; /* start block address of the extent */ - __le32 len; /* lengh of the extent */ + __le32 len; /* length of the extent */ } __packed; #define F2FS_NAME_LEN 255 -#define F2FS_INLINE_XATTR_ADDRS 50 /* 200 bytes for inline xattrs */ +/* 200 bytes for inline xattrs by default */ +#define DEFAULT_INLINE_XATTR_ADDRS 50 #define DEF_ADDRS_PER_INODE 923 /* Address Pointers in an Inode */ #define CUR_ADDRS_PER_INODE(inode) (DEF_ADDRS_PER_INODE - \ get_extra_isize(inode)) @@ -208,6 +216,7 @@ struct f2fs_extent { #define F2FS_DATA_EXIST 0x08 /* file inline data exist flag */ #define F2FS_INLINE_DOTS 0x10 /* file having implicit dot dentries */ #define F2FS_EXTRA_ATTR 0x20 /* file having extra attribute */ +#define F2FS_PIN_FILE 0x40 /* file should not be gced */ struct f2fs_inode { __le16 i_mode; /* file mode */ @@ -225,7 +234,13 @@ struct f2fs_inode { __le32 i_ctime_nsec; /* change time in nano scale */ __le32 i_mtime_nsec; /* modification time in nano scale */ __le32 i_generation; /* file version (for NFS) */ - __le32 i_current_depth; /* only for directory depth */ + union { + __le32 i_current_depth; /* only for directory depth */ + __le16 i_gc_failures; /* + * # of gc failures on pinned file. + * only for regular files. + */ + }; __le32 i_xattr_nid; /* nid to save xattr */ __le32 i_flags; /* file attributes */ __le32 i_pino; /* parent inode number */ @@ -238,11 +253,13 @@ struct f2fs_inode { union { struct { __le16 i_extra_isize; /* extra inode attribute size */ - __le16 i_padding; /* padding */ + __le16 i_inline_xattr_size; /* inline xattr size, unit: 4 bytes */ __le32 i_projid; /* project id */ __le32 i_inode_checksum;/* inode meta checksum */ + __le64 i_crtime; /* creation time */ + __le32 i_crtime_nsec; /* creation time in nano scale */ __le32 i_extra_end[0]; /* for attribute size calculation */ - }; + } __packed; __le32 i_addr[DEF_ADDRS_PER_INODE]; /* Pointers to data blocks */ }; __le32 i_nid[DEF_NIDS_PER_INODE]; /* direct(2), indirect(2), @@ -268,7 +285,7 @@ enum { struct node_footer { __le32 nid; /* node id */ - __le32 ino; /* inode nunmber */ + __le32 ino; /* inode number */ __le32 flag; /* include cold/fsync/dentry marks and offset */ __le64 cp_ver; /* checkpoint version */ __le32 next_blkaddr; /* next node page block address */ @@ -288,7 +305,6 @@ struct f2fs_node { * For NAT entries */ #define NAT_ENTRY_PER_BLOCK (PAGE_SIZE / sizeof(struct f2fs_nat_entry)) -#define NAT_ENTRY_BITMAP_SIZE ((NAT_ENTRY_PER_BLOCK + 7) / 8) struct f2fs_nat_entry { __u8 version; /* latest version of cached nat entry */ @@ -474,12 +490,12 @@ typedef __le32 f2fs_hash_t; /* * space utilization of regular dentry and inline dentry (w/o extra reservation) - * regular dentry inline dentry - * bitmap 1 * 27 = 27 1 * 23 = 23 - * reserved 1 * 3 = 3 1 * 7 = 7 - * dentry 11 * 214 = 2354 11 * 182 = 2002 - * filename 8 * 214 = 1712 8 * 182 = 1456 - * total 4096 3488 + * regular dentry inline dentry (def) inline dentry (min) + * bitmap 1 * 27 = 27 1 * 23 = 23 1 * 1 = 1 + * reserved 1 * 3 = 3 1 * 7 = 7 1 * 1 = 1 + * dentry 11 * 214 = 2354 11 * 182 = 2002 11 * 2 = 22 + * filename 8 * 214 = 1712 8 * 182 = 1456 8 * 2 = 16 + * total 4096 3488 40 * * Note: there are more reserved space in inline dentry than in regular * dentry, when converting inline dentry we should handle this carefully. @@ -491,12 +507,13 @@ typedef __le32 f2fs_hash_t; #define SIZE_OF_RESERVED (PAGE_SIZE - ((SIZE_OF_DIR_ENTRY + \ F2FS_SLOT_LEN) * \ NR_DENTRY_IN_BLOCK + SIZE_OF_DENTRY_BITMAP)) +#define MIN_INLINE_DENTRY_SIZE 40 /* just include '.' and '..' entries */ /* One directory entry slot representing F2FS_SLOT_LEN-sized file name */ struct f2fs_dir_entry { __le32 hash_code; /* hash code of file name */ __le32 ino; /* inode number */ - __le16 name_len; /* lengh of file name */ + __le16 name_len; /* length of file name */ __u8 file_type; /* file type */ } __packed; diff --git a/include/linux/fs.h b/include/linux/fs.h index 92b9cf88a95e..9efb5a4296ff 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1603,13 +1603,21 @@ extern bool inode_owner_or_capable(const struct inode *inode); * VFS helper functions.. */ extern int vfs_create(struct inode *, struct dentry *, umode_t, bool); +extern int vfs_create2(struct vfsmount *, struct inode *, struct dentry *, umode_t, bool); extern int vfs_mkdir(struct inode *, struct dentry *, umode_t); +extern int vfs_mkdir2(struct vfsmount *, struct inode *, struct dentry *, umode_t); extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t); +extern int vfs_mknod2(struct vfsmount *, struct inode *, struct dentry *, umode_t, dev_t); extern int vfs_symlink(struct inode *, struct dentry *, const char *); +extern int vfs_symlink2(struct vfsmount *, struct inode *, struct dentry *, const char *); extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct inode **); +extern int vfs_link2(struct vfsmount *, struct dentry *, struct inode *, struct dentry *, struct inode **); extern int vfs_rmdir(struct inode *, struct dentry *); +extern int vfs_rmdir2(struct vfsmount *, struct inode *, struct dentry *); extern int vfs_unlink(struct inode *, struct dentry *, struct inode **); +extern int vfs_unlink2(struct vfsmount *, struct inode *, struct dentry *, struct inode **); extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int); +extern int vfs_rename2(struct vfsmount *, struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int); extern int vfs_whiteout(struct inode *, struct dentry *); extern struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, @@ -1740,6 +1748,7 @@ struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *); int (*permission) (struct inode *, int); + int (*permission2) (struct vfsmount *, struct inode *, int); struct posix_acl * (*get_acl)(struct inode *, int); int (*readlink) (struct dentry *, char __user *,int); @@ -1754,7 +1763,8 @@ struct inode_operations { int (*rename) (struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); int (*setattr) (struct dentry *, struct iattr *); - int (*getattr) (const struct path *, struct kstat *, u32, unsigned int); + int (*setattr2) (struct vfsmount *, struct dentry *, struct iattr *); + int (*getattr) (const struct path *, struct kstat *, u32, unsigned int); ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); @@ -1824,9 +1834,13 @@ struct super_operations { int (*unfreeze_fs) (struct super_block *); int (*statfs) (struct dentry *, struct kstatfs *); int (*remount_fs) (struct super_block *, int *, char *); + int (*remount_fs2) (struct vfsmount *, struct super_block *, int *, char *); + void *(*clone_mnt_data) (void *); + void (*copy_mnt_data) (void *, void *); void (*umount_begin) (struct super_block *); int (*show_options)(struct seq_file *, struct dentry *); + int (*show_options2)(struct vfsmount *,struct seq_file *, struct dentry *); int (*show_devname)(struct seq_file *, struct dentry *); int (*show_path)(struct seq_file *, struct dentry *); int (*show_stats)(struct seq_file *, struct dentry *); @@ -1863,6 +1877,7 @@ struct super_operations { #else #define S_DAX 0 /* Make all the DAX code disappear */ #endif +#define S_ENCRYPTED 16384 /* Encrypted file (using fs/crypto/) */ /* * Note that nosuid etc flags are inode-specific: setting some file-system @@ -1902,6 +1917,7 @@ static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags #define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT) #define IS_NOSEC(inode) ((inode)->i_flags & S_NOSEC) #define IS_DAX(inode) ((inode)->i_flags & S_DAX) +#define IS_ENCRYPTED(inode) ((inode)->i_flags & S_ENCRYPTED) #define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \ (inode)->i_rdev == WHITEOUT_DEV) @@ -2084,6 +2100,9 @@ struct file_system_type { #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ struct dentry *(*mount) (struct file_system_type *, int, const char *, void *); + struct dentry *(*mount2) (struct vfsmount *, struct file_system_type *, int, + const char *, void *); + void *(*alloc_mnt_data) (void); void (*kill_sb) (struct super_block *); struct module *owner; struct file_system_type * next; @@ -2385,6 +2404,8 @@ struct filename { extern long vfs_truncate(const struct path *, loff_t); extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); +extern int do_truncate2(struct vfsmount *, struct dentry *, loff_t start, + unsigned int time_attrs, struct file *filp); extern int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len); extern long do_sys_open(int dfd, const char __user *filename, int flags, @@ -2691,8 +2712,11 @@ extern void emergency_remount(void); extern sector_t bmap(struct inode *, sector_t); #endif extern int notify_change(struct dentry *, struct iattr *, struct inode **); +extern int notify_change2(struct vfsmount *, struct dentry *, struct iattr *, struct inode **); extern int inode_permission(struct inode *, int); +extern int inode_permission2(struct vfsmount *, struct inode *, int); extern int __inode_permission(struct inode *, int); +extern int __inode_permission2(struct vfsmount *, struct inode *, int); extern int generic_permission(struct inode *, int); extern int __check_sticky(struct inode *dir, struct inode *inode); diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h new file mode 100644 index 000000000000..952ab97af325 --- /dev/null +++ b/include/linux/fscrypt.h @@ -0,0 +1,254 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * fscrypt.h: declarations for per-file encryption + * + * Filesystems that implement per-file encryption include this header + * file with the __FS_HAS_ENCRYPTION set according to whether that filesystem + * is being built with encryption support or not. + * + * Copyright (C) 2015, Google, Inc. + * + * Written by Michael Halcrow, 2015. + * Modified by Jaegeuk Kim, 2015. + */ +#ifndef _LINUX_FSCRYPT_H +#define _LINUX_FSCRYPT_H + +#include <linux/fs.h> + +#define FS_CRYPTO_BLOCK_SIZE 16 + +struct fscrypt_ctx; +struct fscrypt_info; + +struct fscrypt_str { + unsigned char *name; + u32 len; +}; + +struct fscrypt_name { + const struct qstr *usr_fname; + struct fscrypt_str disk_name; + u32 hash; + u32 minor_hash; + struct fscrypt_str crypto_buf; +}; + +#define FSTR_INIT(n, l) { .name = n, .len = l } +#define FSTR_TO_QSTR(f) QSTR_INIT((f)->name, (f)->len) +#define fname_name(p) ((p)->disk_name.name) +#define fname_len(p) ((p)->disk_name.len) + +/* Maximum value for the third parameter of fscrypt_operations.set_context(). */ +#define FSCRYPT_SET_CONTEXT_MAX_SIZE 28 + +#if __FS_HAS_ENCRYPTION +#include <linux/fscrypt_supp.h> +#else +#include <linux/fscrypt_notsupp.h> +#endif + +/** + * fscrypt_require_key - require an inode's encryption key + * @inode: the inode we need the key for + * + * If the inode is encrypted, set up its encryption key if not already done. + * Then require that the key be present and return -ENOKEY otherwise. + * + * No locks are needed, and the key will live as long as the struct inode --- so + * it won't go away from under you. + * + * Return: 0 on success, -ENOKEY if the key is missing, or another -errno code + * if a problem occurred while setting up the encryption key. + */ +static inline int fscrypt_require_key(struct inode *inode) +{ + if (IS_ENCRYPTED(inode)) { + int err = fscrypt_get_encryption_info(inode); + + if (err) + return err; + if (!fscrypt_has_encryption_key(inode)) + return -ENOKEY; + } + return 0; +} + +/** + * fscrypt_prepare_link - prepare to link an inode into a possibly-encrypted directory + * @old_dentry: an existing dentry for the inode being linked + * @dir: the target directory + * @dentry: negative dentry for the target filename + * + * A new link can only be added to an encrypted directory if the directory's + * encryption key is available --- since otherwise we'd have no way to encrypt + * the filename. Therefore, we first set up the directory's encryption key (if + * not already done) and return an error if it's unavailable. + * + * We also verify that the link will not violate the constraint that all files + * in an encrypted directory tree use the same encryption policy. + * + * Return: 0 on success, -ENOKEY if the directory's encryption key is missing, + * -EPERM if the link would result in an inconsistent encryption policy, or + * another -errno code. + */ +static inline int fscrypt_prepare_link(struct dentry *old_dentry, + struct inode *dir, + struct dentry *dentry) +{ + if (IS_ENCRYPTED(dir)) + return __fscrypt_prepare_link(d_inode(old_dentry), dir); + return 0; +} + +/** + * fscrypt_prepare_rename - prepare for a rename between possibly-encrypted directories + * @old_dir: source directory + * @old_dentry: dentry for source file + * @new_dir: target directory + * @new_dentry: dentry for target location (may be negative unless exchanging) + * @flags: rename flags (we care at least about %RENAME_EXCHANGE) + * + * Prepare for ->rename() where the source and/or target directories may be + * encrypted. A new link can only be added to an encrypted directory if the + * directory's encryption key is available --- since otherwise we'd have no way + * to encrypt the filename. A rename to an existing name, on the other hand, + * *is* cryptographically possible without the key. However, we take the more + * conservative approach and just forbid all no-key renames. + * + * We also verify that the rename will not violate the constraint that all files + * in an encrypted directory tree use the same encryption policy. + * + * Return: 0 on success, -ENOKEY if an encryption key is missing, -EPERM if the + * rename would cause inconsistent encryption policies, or another -errno code. + */ +static inline int fscrypt_prepare_rename(struct inode *old_dir, + struct dentry *old_dentry, + struct inode *new_dir, + struct dentry *new_dentry, + unsigned int flags) +{ + if (IS_ENCRYPTED(old_dir) || IS_ENCRYPTED(new_dir)) + return __fscrypt_prepare_rename(old_dir, old_dentry, + new_dir, new_dentry, flags); + return 0; +} + +/** + * fscrypt_prepare_lookup - prepare to lookup a name in a possibly-encrypted directory + * @dir: directory being searched + * @dentry: filename being looked up + * @flags: lookup flags + * + * Prepare for ->lookup() in a directory which may be encrypted. Lookups can be + * done with or without the directory's encryption key; without the key, + * filenames are presented in encrypted form. Therefore, we'll try to set up + * the directory's encryption key, but even without it the lookup can continue. + * + * To allow invalidating stale dentries if the directory's encryption key is + * added later, we also install a custom ->d_revalidate() method and use the + * DCACHE_ENCRYPTED_WITH_KEY flag to indicate whether a given dentry is a + * plaintext name (flag set) or a ciphertext name (flag cleared). + * + * Return: 0 on success, -errno if a problem occurred while setting up the + * encryption key + */ +static inline int fscrypt_prepare_lookup(struct inode *dir, + struct dentry *dentry, + unsigned int flags) +{ + if (IS_ENCRYPTED(dir)) + return __fscrypt_prepare_lookup(dir, dentry); + return 0; +} + +/** + * fscrypt_prepare_setattr - prepare to change a possibly-encrypted inode's attributes + * @dentry: dentry through which the inode is being changed + * @attr: attributes to change + * + * Prepare for ->setattr() on a possibly-encrypted inode. On an encrypted file, + * most attribute changes are allowed even without the encryption key. However, + * without the encryption key we do have to forbid truncates. This is needed + * because the size being truncated to may not be a multiple of the filesystem + * block size, and in that case we'd have to decrypt the final block, zero the + * portion past i_size, and re-encrypt it. (We *could* allow truncating to a + * filesystem block boundary, but it's simpler to just forbid all truncates --- + * and we already forbid all other contents modifications without the key.) + * + * Return: 0 on success, -ENOKEY if the key is missing, or another -errno code + * if a problem occurred while setting up the encryption key. + */ +static inline int fscrypt_prepare_setattr(struct dentry *dentry, + struct iattr *attr) +{ + if (attr->ia_valid & ATTR_SIZE) + return fscrypt_require_key(d_inode(dentry)); + return 0; +} + +/** + * fscrypt_prepare_symlink - prepare to create a possibly-encrypted symlink + * @dir: directory in which the symlink is being created + * @target: plaintext symlink target + * @len: length of @target excluding null terminator + * @max_len: space the filesystem has available to store the symlink target + * @disk_link: (out) the on-disk symlink target being prepared + * + * This function computes the size the symlink target will require on-disk, + * stores it in @disk_link->len, and validates it against @max_len. An + * encrypted symlink may be longer than the original. + * + * Additionally, @disk_link->name is set to @target if the symlink will be + * unencrypted, but left NULL if the symlink will be encrypted. For encrypted + * symlinks, the filesystem must call fscrypt_encrypt_symlink() to create the + * on-disk target later. (The reason for the two-step process is that some + * filesystems need to know the size of the symlink target before creating the + * inode, e.g. to determine whether it will be a "fast" or "slow" symlink.) + * + * Return: 0 on success, -ENAMETOOLONG if the symlink target is too long, + * -ENOKEY if the encryption key is missing, or another -errno code if a problem + * occurred while setting up the encryption key. + */ +static inline int fscrypt_prepare_symlink(struct inode *dir, + const char *target, + unsigned int len, + unsigned int max_len, + struct fscrypt_str *disk_link) +{ + if (IS_ENCRYPTED(dir) || fscrypt_dummy_context_enabled(dir)) + return __fscrypt_prepare_symlink(dir, len, max_len, disk_link); + + disk_link->name = (unsigned char *)target; + disk_link->len = len + 1; + if (disk_link->len > max_len) + return -ENAMETOOLONG; + return 0; +} + +/** + * fscrypt_encrypt_symlink - encrypt the symlink target if needed + * @inode: symlink inode + * @target: plaintext symlink target + * @len: length of @target excluding null terminator + * @disk_link: (in/out) the on-disk symlink target being prepared + * + * If the symlink target needs to be encrypted, then this function encrypts it + * into @disk_link->name. fscrypt_prepare_symlink() must have been called + * previously to compute @disk_link->len. If the filesystem did not allocate a + * buffer for @disk_link->name after calling fscrypt_prepare_link(), then one + * will be kmalloc()'ed and the filesystem will be responsible for freeing it. + * + * Return: 0 on success, -errno on failure + */ +static inline int fscrypt_encrypt_symlink(struct inode *inode, + const char *target, + unsigned int len, + struct fscrypt_str *disk_link) +{ + if (IS_ENCRYPTED(inode)) + return __fscrypt_encrypt_symlink(inode, target, len, disk_link); + return 0; +} + +#endif /* _LINUX_FSCRYPT_H */ diff --git a/include/linux/fscrypt_common.h b/include/linux/fscrypt_common.h deleted file mode 100644 index 854d724978fa..000000000000 --- a/include/linux/fscrypt_common.h +++ /dev/null @@ -1,142 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * fscrypt_common.h: common declarations for per-file encryption - * - * Copyright (C) 2015, Google, Inc. - * - * Written by Michael Halcrow, 2015. - * Modified by Jaegeuk Kim, 2015. - */ - -#ifndef _LINUX_FSCRYPT_COMMON_H -#define _LINUX_FSCRYPT_COMMON_H - -#include <linux/key.h> -#include <linux/fs.h> -#include <linux/mm.h> -#include <linux/bio.h> -#include <linux/dcache.h> -#include <crypto/skcipher.h> -#include <uapi/linux/fs.h> - -#define FS_CRYPTO_BLOCK_SIZE 16 - -struct fscrypt_info; - -struct fscrypt_ctx { - union { - struct { - struct page *bounce_page; /* Ciphertext page */ - struct page *control_page; /* Original page */ - } w; - struct { - struct bio *bio; - struct work_struct work; - } r; - struct list_head free_list; /* Free list */ - }; - u8 flags; /* Flags */ -}; - -/** - * For encrypted symlinks, the ciphertext length is stored at the beginning - * of the string in little-endian format. - */ -struct fscrypt_symlink_data { - __le16 len; - char encrypted_path[1]; -} __packed; - -struct fscrypt_str { - unsigned char *name; - u32 len; -}; - -struct fscrypt_name { - const struct qstr *usr_fname; - struct fscrypt_str disk_name; - u32 hash; - u32 minor_hash; - struct fscrypt_str crypto_buf; -}; - -#define FSTR_INIT(n, l) { .name = n, .len = l } -#define FSTR_TO_QSTR(f) QSTR_INIT((f)->name, (f)->len) -#define fname_name(p) ((p)->disk_name.name) -#define fname_len(p) ((p)->disk_name.len) - -/* - * fscrypt superblock flags - */ -#define FS_CFLG_OWN_PAGES (1U << 1) - -/* - * crypto opertions for filesystems - */ -struct fscrypt_operations { - unsigned int flags; - const char *key_prefix; - int (*get_context)(struct inode *, void *, size_t); - int (*set_context)(struct inode *, const void *, size_t, void *); - bool (*dummy_context)(struct inode *); - bool (*is_encrypted)(struct inode *); - bool (*empty_dir)(struct inode *); - unsigned (*max_namelen)(struct inode *); -}; - -/* Maximum value for the third parameter of fscrypt_operations.set_context(). */ -#define FSCRYPT_SET_CONTEXT_MAX_SIZE 28 - -static inline bool fscrypt_dummy_context_enabled(struct inode *inode) -{ - if (inode->i_sb->s_cop->dummy_context && - inode->i_sb->s_cop->dummy_context(inode)) - return true; - return false; -} - -static inline bool fscrypt_valid_enc_modes(u32 contents_mode, - u32 filenames_mode) -{ - if (contents_mode == FS_ENCRYPTION_MODE_AES_128_CBC && - filenames_mode == FS_ENCRYPTION_MODE_AES_128_CTS) - return true; - - if (contents_mode == FS_ENCRYPTION_MODE_AES_256_XTS && - filenames_mode == FS_ENCRYPTION_MODE_AES_256_CTS) - return true; - - return false; -} - -static inline bool fscrypt_is_dot_dotdot(const struct qstr *str) -{ - if (str->len == 1 && str->name[0] == '.') - return true; - - if (str->len == 2 && str->name[0] == '.' && str->name[1] == '.') - return true; - - return false; -} - -static inline struct page *fscrypt_control_page(struct page *page) -{ -#if IS_ENABLED(CONFIG_FS_ENCRYPTION) - return ((struct fscrypt_ctx *)page_private(page))->w.control_page; -#else - WARN_ON_ONCE(1); - return ERR_PTR(-EINVAL); -#endif -} - -static inline int fscrypt_has_encryption_key(const struct inode *inode) -{ -#if IS_ENABLED(CONFIG_FS_ENCRYPTION) - return (inode->i_crypt_info != NULL); -#else - return 0; -#endif -} - -#endif /* _LINUX_FSCRYPT_COMMON_H */ diff --git a/include/linux/fscrypt_notsupp.h b/include/linux/fscrypt_notsupp.h index 19609ceea350..ee8b43e4c15a 100644 --- a/include/linux/fscrypt_notsupp.h +++ b/include/linux/fscrypt_notsupp.h @@ -4,14 +4,31 @@ * * This stubs out the fscrypt functions for filesystems configured without * encryption support. + * + * Do not include this file directly. Use fscrypt.h instead! */ +#ifndef _LINUX_FSCRYPT_H +#error "Incorrect include of linux/fscrypt_notsupp.h!" +#endif #ifndef _LINUX_FSCRYPT_NOTSUPP_H #define _LINUX_FSCRYPT_NOTSUPP_H -#include <linux/fscrypt_common.h> +static inline bool fscrypt_has_encryption_key(const struct inode *inode) +{ + return false; +} + +static inline bool fscrypt_dummy_context_enabled(struct inode *inode) +{ + return false; +} /* crypto.c */ +static inline void fscrypt_enqueue_decrypt_work(struct work_struct *work) +{ +} + static inline struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *inode, gfp_t gfp_flags) { @@ -40,18 +57,13 @@ static inline int fscrypt_decrypt_page(const struct inode *inode, return -EOPNOTSUPP; } - -static inline void fscrypt_restore_control_page(struct page *page) -{ - return; -} - -static inline void fscrypt_set_d_op(struct dentry *dentry) +static inline struct page *fscrypt_control_page(struct page *page) { - return; + WARN_ON_ONCE(1); + return ERR_PTR(-EINVAL); } -static inline void fscrypt_set_encrypted_dentry(struct dentry *dentry) +static inline void fscrypt_restore_control_page(struct page *page) { return; } @@ -87,8 +99,7 @@ static inline int fscrypt_get_encryption_info(struct inode *inode) return -EOPNOTSUPP; } -static inline void fscrypt_put_encryption_info(struct inode *inode, - struct fscrypt_info *ci) +static inline void fscrypt_put_encryption_info(struct inode *inode) { return; } @@ -98,7 +109,7 @@ static inline int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname, int lookup, struct fscrypt_name *fname) { - if (dir->i_sb->s_cop->is_encrypted(dir)) + if (IS_ENCRYPTED(dir)) return -EOPNOTSUPP; memset(fname, 0, sizeof(struct fscrypt_name)); @@ -113,16 +124,8 @@ static inline void fscrypt_free_filename(struct fscrypt_name *fname) return; } -static inline u32 fscrypt_fname_encrypted_size(const struct inode *inode, - u32 ilen) -{ - /* never happens */ - WARN_ON(1); - return 0; -} - static inline int fscrypt_fname_alloc_buffer(const struct inode *inode, - u32 ilen, + u32 max_encrypted_len, struct fscrypt_str *crypto_str) { return -EOPNOTSUPP; @@ -141,13 +144,6 @@ static inline int fscrypt_fname_disk_to_usr(struct inode *inode, return -EOPNOTSUPP; } -static inline int fscrypt_fname_usr_to_disk(struct inode *inode, - const struct qstr *iname, - struct fscrypt_str *oname) -{ - return -EOPNOTSUPP; -} - static inline bool fscrypt_match_name(const struct fscrypt_name *fname, const u8 *de_name, u32 de_name_len) { @@ -158,10 +154,13 @@ static inline bool fscrypt_match_name(const struct fscrypt_name *fname, } /* bio.c */ -static inline void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *ctx, - struct bio *bio) +static inline void fscrypt_decrypt_bio(struct bio *bio) +{ +} + +static inline void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx, + struct bio *bio) { - return; } static inline void fscrypt_pullback_bio_page(struct page **page, bool restore) @@ -175,4 +174,58 @@ static inline int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, return -EOPNOTSUPP; } +/* hooks.c */ + +static inline int fscrypt_file_open(struct inode *inode, struct file *filp) +{ + if (IS_ENCRYPTED(inode)) + return -EOPNOTSUPP; + return 0; +} + +static inline int __fscrypt_prepare_link(struct inode *inode, + struct inode *dir) +{ + return -EOPNOTSUPP; +} + +static inline int __fscrypt_prepare_rename(struct inode *old_dir, + struct dentry *old_dentry, + struct inode *new_dir, + struct dentry *new_dentry, + unsigned int flags) +{ + return -EOPNOTSUPP; +} + +static inline int __fscrypt_prepare_lookup(struct inode *dir, + struct dentry *dentry) +{ + return -EOPNOTSUPP; +} + +static inline int __fscrypt_prepare_symlink(struct inode *dir, + unsigned int len, + unsigned int max_len, + struct fscrypt_str *disk_link) +{ + return -EOPNOTSUPP; +} + +static inline int __fscrypt_encrypt_symlink(struct inode *inode, + const char *target, + unsigned int len, + struct fscrypt_str *disk_link) +{ + return -EOPNOTSUPP; +} + +static inline const char *fscrypt_get_symlink(struct inode *inode, + const void *caddr, + unsigned int max_size, + struct delayed_call *done) +{ + return ERR_PTR(-EOPNOTSUPP); +} + #endif /* _LINUX_FSCRYPT_NOTSUPP_H */ diff --git a/include/linux/fscrypt_supp.h b/include/linux/fscrypt_supp.h index 5153dce22f09..6456c6b2005f 100644 --- a/include/linux/fscrypt_supp.h +++ b/include/linux/fscrypt_supp.h @@ -2,16 +2,64 @@ /* * fscrypt_supp.h * - * This is included by filesystems configured with encryption support. + * Do not include this file directly. Use fscrypt.h instead! */ +#ifndef _LINUX_FSCRYPT_H +#error "Incorrect include of linux/fscrypt_supp.h!" +#endif #ifndef _LINUX_FSCRYPT_SUPP_H #define _LINUX_FSCRYPT_SUPP_H -#include <linux/fscrypt_common.h> +#include <linux/mm.h> +#include <linux/slab.h> + +/* + * fscrypt superblock flags + */ +#define FS_CFLG_OWN_PAGES (1U << 1) + +/* + * crypto operations for filesystems + */ +struct fscrypt_operations { + unsigned int flags; + const char *key_prefix; + int (*get_context)(struct inode *, void *, size_t); + int (*set_context)(struct inode *, const void *, size_t, void *); + bool (*dummy_context)(struct inode *); + bool (*empty_dir)(struct inode *); + unsigned int max_namelen; +}; + +struct fscrypt_ctx { + union { + struct { + struct page *bounce_page; /* Ciphertext page */ + struct page *control_page; /* Original page */ + } w; + struct { + struct bio *bio; + struct work_struct work; + } r; + struct list_head free_list; /* Free list */ + }; + u8 flags; /* Flags */ +}; + +static inline bool fscrypt_has_encryption_key(const struct inode *inode) +{ + return (inode->i_crypt_info != NULL); +} + +static inline bool fscrypt_dummy_context_enabled(struct inode *inode) +{ + return inode->i_sb->s_cop->dummy_context && + inode->i_sb->s_cop->dummy_context(inode); +} /* crypto.c */ -extern struct kmem_cache *fscrypt_info_cachep; +extern void fscrypt_enqueue_decrypt_work(struct work_struct *); extern struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *, gfp_t); extern void fscrypt_release_ctx(struct fscrypt_ctx *); extern struct page *fscrypt_encrypt_page(const struct inode *, struct page *, @@ -19,21 +67,13 @@ extern struct page *fscrypt_encrypt_page(const struct inode *, struct page *, u64, gfp_t); extern int fscrypt_decrypt_page(const struct inode *, struct page *, unsigned int, unsigned int, u64); -extern void fscrypt_restore_control_page(struct page *); -extern const struct dentry_operations fscrypt_d_ops; - -static inline void fscrypt_set_d_op(struct dentry *dentry) +static inline struct page *fscrypt_control_page(struct page *page) { - d_set_d_op(dentry, &fscrypt_d_ops); + return ((struct fscrypt_ctx *)page_private(page))->w.control_page; } -static inline void fscrypt_set_encrypted_dentry(struct dentry *dentry) -{ - spin_lock(&dentry->d_lock); - dentry->d_flags |= DCACHE_ENCRYPTED_WITH_KEY; - spin_unlock(&dentry->d_lock); -} +extern void fscrypt_restore_control_page(struct page *); /* policy.c */ extern int fscrypt_ioctl_set_policy(struct file *, const void __user *); @@ -43,7 +83,7 @@ extern int fscrypt_inherit_context(struct inode *, struct inode *, void *, bool); /* keyinfo.c */ extern int fscrypt_get_encryption_info(struct inode *); -extern void fscrypt_put_encryption_info(struct inode *, struct fscrypt_info *); +extern void fscrypt_put_encryption_info(struct inode *); /* fname.c */ extern int fscrypt_setup_filename(struct inode *, const struct qstr *, @@ -54,14 +94,11 @@ static inline void fscrypt_free_filename(struct fscrypt_name *fname) kfree(fname->crypto_buf.name); } -extern u32 fscrypt_fname_encrypted_size(const struct inode *, u32); extern int fscrypt_fname_alloc_buffer(const struct inode *, u32, struct fscrypt_str *); extern void fscrypt_fname_free_buffer(struct fscrypt_str *); extern int fscrypt_fname_disk_to_usr(struct inode *, u32, u32, const struct fscrypt_str *, struct fscrypt_str *); -extern int fscrypt_fname_usr_to_disk(struct inode *, const struct qstr *, - struct fscrypt_str *); #define FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE 32 @@ -138,9 +175,30 @@ static inline bool fscrypt_match_name(const struct fscrypt_name *fname, } /* bio.c */ -extern void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *, struct bio *); +extern void fscrypt_decrypt_bio(struct bio *); +extern void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx, + struct bio *bio); extern void fscrypt_pullback_bio_page(struct page **, bool); extern int fscrypt_zeroout_range(const struct inode *, pgoff_t, sector_t, unsigned int); +/* hooks.c */ +extern int fscrypt_file_open(struct inode *inode, struct file *filp); +extern int __fscrypt_prepare_link(struct inode *inode, struct inode *dir); +extern int __fscrypt_prepare_rename(struct inode *old_dir, + struct dentry *old_dentry, + struct inode *new_dir, + struct dentry *new_dentry, + unsigned int flags); +extern int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry); +extern int __fscrypt_prepare_symlink(struct inode *dir, unsigned int len, + unsigned int max_len, + struct fscrypt_str *disk_link); +extern int __fscrypt_encrypt_symlink(struct inode *inode, const char *target, + unsigned int len, + struct fscrypt_str *disk_link); +extern const char *fscrypt_get_symlink(struct inode *inode, const void *caddr, + unsigned int max_size, + struct delayed_call *done); + #endif /* _LINUX_FSCRYPT_SUPP_H */ diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index bdaf22582f6e..4636b8f8893e 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -214,12 +214,19 @@ static inline void fsnotify_modify(struct file *file) static inline void fsnotify_open(struct file *file) { const struct path *path = &file->f_path; + struct path lower_path; struct inode *inode = path->dentry->d_inode; __u32 mask = FS_OPEN; if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; + if (path->dentry->d_op && path->dentry->d_op->d_canonical_path) { + path->dentry->d_op->d_canonical_path(path, &lower_path); + fsnotify_parent(&lower_path, NULL, mask); + fsnotify(lower_path.dentry->d_inode, mask, &lower_path, FSNOTIFY_EVENT_PATH, NULL, 0); + path_put(&lower_path); + } fsnotify_parent(path, NULL, mask); fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0); } diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index e54d257983f2..ff3e5b109f9c 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -254,8 +254,16 @@ static inline int ftrace_function_local_disabled(struct ftrace_ops *ops) return *this_cpu_ptr(ops->disabled); } +#ifdef CONFIG_CFI_CLANG +/* Use a C stub with the correct type for CFI */ +static inline void ftrace_stub(unsigned long a0, unsigned long a1, + struct ftrace_ops *op, struct pt_regs *regs) +{ +} +#else extern void ftrace_stub(unsigned long a0, unsigned long a1, struct ftrace_ops *op, struct pt_regs *regs); +#endif #else /* !CONFIG_FUNCTION_TRACER */ /* @@ -743,7 +751,8 @@ static inline unsigned long get_lock_parent_ip(void) static inline void time_hardirqs_off(unsigned long a0, unsigned long a1) { } #endif -#ifdef CONFIG_PREEMPT_TRACER +#if defined(CONFIG_PREEMPT_TRACER) || \ + (defined(CONFIG_DEBUG_PREEMPT) && defined(CONFIG_PREEMPTIRQ_EVENTS)) extern void trace_preempt_on(unsigned long a0, unsigned long a1); extern void trace_preempt_off(unsigned long a0, unsigned long a1); #else diff --git a/include/linux/gpio_event.h b/include/linux/gpio_event.h new file mode 100644 index 000000000000..2613fc5e4a93 --- /dev/null +++ b/include/linux/gpio_event.h @@ -0,0 +1,170 @@ +/* include/linux/gpio_event.h + * + * Copyright (C) 2007 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#ifndef _LINUX_GPIO_EVENT_H +#define _LINUX_GPIO_EVENT_H + +#include <linux/input.h> + +struct gpio_event_input_devs { + int count; + struct input_dev *dev[]; +}; +enum { + GPIO_EVENT_FUNC_UNINIT = 0x0, + GPIO_EVENT_FUNC_INIT = 0x1, + GPIO_EVENT_FUNC_SUSPEND = 0x2, + GPIO_EVENT_FUNC_RESUME = 0x3, +}; +struct gpio_event_info { + int (*func)(struct gpio_event_input_devs *input_devs, + struct gpio_event_info *info, + void **data, int func); + int (*event)(struct gpio_event_input_devs *input_devs, + struct gpio_event_info *info, + void **data, unsigned int dev, unsigned int type, + unsigned int code, int value); /* out events */ + bool no_suspend; +}; + +struct gpio_event_platform_data { + const char *name; + struct gpio_event_info **info; + size_t info_count; + int (*power)(const struct gpio_event_platform_data *pdata, bool on); + const char *names[]; /* If name is NULL, names contain a NULL */ + /* terminated list of input devices to create */ +}; + +#define GPIO_EVENT_DEV_NAME "gpio-event" + +/* Key matrix */ + +enum gpio_event_matrix_flags { + /* unset: drive active output low, set: drive active output high */ + GPIOKPF_ACTIVE_HIGH = 1U << 0, + GPIOKPF_DEBOUNCE = 1U << 1, + GPIOKPF_REMOVE_SOME_PHANTOM_KEYS = 1U << 2, + GPIOKPF_REMOVE_PHANTOM_KEYS = GPIOKPF_REMOVE_SOME_PHANTOM_KEYS | + GPIOKPF_DEBOUNCE, + GPIOKPF_DRIVE_INACTIVE = 1U << 3, + GPIOKPF_LEVEL_TRIGGERED_IRQ = 1U << 4, + GPIOKPF_PRINT_UNMAPPED_KEYS = 1U << 16, + GPIOKPF_PRINT_MAPPED_KEYS = 1U << 17, + GPIOKPF_PRINT_PHANTOM_KEYS = 1U << 18, +}; + +#define MATRIX_CODE_BITS (10) +#define MATRIX_KEY_MASK ((1U << MATRIX_CODE_BITS) - 1) +#define MATRIX_KEY(dev, code) \ + (((dev) << MATRIX_CODE_BITS) | (code & MATRIX_KEY_MASK)) + +extern int gpio_event_matrix_func(struct gpio_event_input_devs *input_devs, + struct gpio_event_info *info, void **data, int func); +struct gpio_event_matrix_info { + /* initialize to gpio_event_matrix_func */ + struct gpio_event_info info; + /* size must be ninputs * noutputs */ + const unsigned short *keymap; + unsigned int *input_gpios; + unsigned int *output_gpios; + unsigned int ninputs; + unsigned int noutputs; + /* time to wait before reading inputs after driving each output */ + ktime_t settle_time; + /* time to wait before scanning the keypad a second time */ + ktime_t debounce_delay; + ktime_t poll_time; + unsigned flags; +}; + +/* Directly connected inputs and outputs */ + +enum gpio_event_direct_flags { + GPIOEDF_ACTIVE_HIGH = 1U << 0, +/* GPIOEDF_USE_DOWN_IRQ = 1U << 1, */ +/* GPIOEDF_USE_IRQ = (1U << 2) | GPIOIDF_USE_DOWN_IRQ, */ + GPIOEDF_PRINT_KEYS = 1U << 8, + GPIOEDF_PRINT_KEY_DEBOUNCE = 1U << 9, + GPIOEDF_PRINT_KEY_UNSTABLE = 1U << 10, +}; + +struct gpio_event_direct_entry { + uint32_t gpio:16; + uint32_t code:10; + uint32_t dev:6; +}; + +/* inputs */ +extern int gpio_event_input_func(struct gpio_event_input_devs *input_devs, + struct gpio_event_info *info, void **data, int func); +struct gpio_event_input_info { + /* initialize to gpio_event_input_func */ + struct gpio_event_info info; + ktime_t debounce_time; + ktime_t poll_time; + uint16_t flags; + uint16_t type; + const struct gpio_event_direct_entry *keymap; + size_t keymap_size; +}; + +/* outputs */ +extern int gpio_event_output_func(struct gpio_event_input_devs *input_devs, + struct gpio_event_info *info, void **data, int func); +extern int gpio_event_output_event(struct gpio_event_input_devs *input_devs, + struct gpio_event_info *info, void **data, + unsigned int dev, unsigned int type, + unsigned int code, int value); +struct gpio_event_output_info { + /* initialize to gpio_event_output_func and gpio_event_output_event */ + struct gpio_event_info info; + uint16_t flags; + uint16_t type; + const struct gpio_event_direct_entry *keymap; + size_t keymap_size; +}; + + +/* axes */ + +enum gpio_event_axis_flags { + GPIOEAF_PRINT_UNKNOWN_DIRECTION = 1U << 16, + GPIOEAF_PRINT_RAW = 1U << 17, + GPIOEAF_PRINT_EVENT = 1U << 18, +}; + +extern int gpio_event_axis_func(struct gpio_event_input_devs *input_devs, + struct gpio_event_info *info, void **data, int func); +struct gpio_event_axis_info { + /* initialize to gpio_event_axis_func */ + struct gpio_event_info info; + uint8_t count; /* number of gpios for this axis */ + uint8_t dev; /* device index when using multiple input devices */ + uint8_t type; /* EV_REL or EV_ABS */ + uint16_t code; + uint16_t decoded_size; + uint16_t (*map)(struct gpio_event_axis_info *info, uint16_t in); + uint32_t *gpio; + uint32_t flags; +}; +#define gpio_axis_2bit_gray_map gpio_axis_4bit_gray_map +#define gpio_axis_3bit_gray_map gpio_axis_4bit_gray_map +uint16_t gpio_axis_4bit_gray_map( + struct gpio_event_axis_info *info, uint16_t in); +uint16_t gpio_axis_5bit_singletrack_map( + struct gpio_event_axis_info *info, uint16_t in); + +#endif diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 5511dc963dd5..9403062319db 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -405,6 +405,7 @@ static inline ktime_t hrtimer_get_remaining(const struct hrtimer *timer) } extern u64 hrtimer_get_next_event(void); +extern u64 hrtimer_next_event_without(const struct hrtimer *exclude); extern bool hrtimer_active(const struct hrtimer *timer); diff --git a/include/linux/init.h b/include/linux/init.h index 07cab8a053af..f138e5b918c2 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -47,7 +47,7 @@ /* These are for everybody (although not all archs will actually discard it in modules) */ -#define __init __section(.init.text) __cold __inittrace __latent_entropy __noinitretpoline +#define __init __section(.init.text) __cold __inittrace __latent_entropy __noinitretpoline __nocfi #define __initdata __section(.init.data) #define __initconst __section(.init.rodata) #define __exitdata __section(.exit.data) @@ -153,6 +153,15 @@ extern bool initcall_debug; #ifndef __ASSEMBLY__ +#ifdef CONFIG_LTO_CLANG + /* prepend the variable name with __COUNTER__ to ensure correct ordering */ + #define ___initcall_name2(c, fn, id) __initcall_##c##_##fn##id + #define ___initcall_name1(c, fn, id) ___initcall_name2(c, fn, id) + #define __initcall_name(fn, id) ___initcall_name1(__COUNTER__, fn, id) +#else + #define __initcall_name(fn, id) __initcall_##fn##id +#endif + /* * initcalls are now grouped by functionality into separate * subsections. Ordering inside the subsections is determined @@ -170,7 +179,7 @@ extern bool initcall_debug; */ #define __define_initcall(fn, id) \ - static initcall_t __initcall_##fn##id __used \ + static initcall_t __initcall_name(fn, id) __used \ __attribute__((__section__(".initcall" #id ".init"))) = fn; /* diff --git a/include/linux/initramfs.h b/include/linux/initramfs.h new file mode 100644 index 000000000000..fc7da63b125b --- /dev/null +++ b/include/linux/initramfs.h @@ -0,0 +1,32 @@ +/* + * include/linux/initramfs.h + * + * Copyright (C) 2015, Google + * Rom Lemarchand <romlem@android.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#ifndef _LINUX_INITRAMFS_H +#define _LINUX_INITRAMFS_H + +#include <linux/kconfig.h> + +#if IS_BUILTIN(CONFIG_BLK_DEV_INITRD) + +int __init default_rootfs(void); + +#endif + +#endif /* _LINUX_INITRAMFS_H */ diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 067a6fa675ed..3e3893f1b596 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -42,6 +42,7 @@ struct ipv6_devconf { __s32 accept_ra_rt_info_max_plen; #endif #endif + __s32 accept_ra_rt_table; __s32 proxy_ndp; __s32 accept_source_route; __s32 accept_ra_from_local; diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 9385aa57497b..a27cf6652327 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -62,8 +62,11 @@ extern int register_refined_jiffies(long clock_tick_rate); /* TICK_NSEC is the time between ticks in nsec assuming SHIFTED_HZ */ #define TICK_NSEC ((NSEC_PER_SEC+HZ/2)/HZ) -/* TICK_USEC is the time between ticks in usec assuming fake USER_HZ */ -#define TICK_USEC ((1000000UL + USER_HZ/2) / USER_HZ) +/* TICK_USEC is the time between ticks in usec assuming SHIFTED_HZ */ +#define TICK_USEC ((USEC_PER_SEC + HZ/2) / HZ) + +/* USER_TICK_USEC is the time between ticks in usec assuming fake USER_HZ */ +#define USER_TICK_USEC ((1000000UL + USER_HZ/2) / USER_HZ) #ifndef __jiffy_arch_data #define __jiffy_arch_data diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 5e539e5bb70c..21c4a3aa5b57 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -24,6 +24,7 @@ struct seq_file; struct vm_area_struct; struct super_block; struct file_system_type; +struct poll_table_struct; struct kernfs_open_node; struct kernfs_iattrs; @@ -261,6 +262,9 @@ struct kernfs_ops { ssize_t (*write)(struct kernfs_open_file *of, char *buf, size_t bytes, loff_t off); + unsigned int (*poll)(struct kernfs_open_file *of, + struct poll_table_struct *pt); + int (*mmap)(struct kernfs_open_file *of, struct vm_area_struct *vma); #ifdef CONFIG_DEBUG_LOCK_ALLOC @@ -348,6 +352,8 @@ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name, int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name, const void *new_ns); int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr); +unsigned int kernfs_generic_poll(struct kernfs_open_file *of, + struct poll_table_struct *pt); void kernfs_notify(struct kernfs_node *kn); const void *kernfs_super_ns(struct super_block *sb); diff --git a/include/linux/keycombo.h b/include/linux/keycombo.h new file mode 100644 index 000000000000..c6db2626b0d3 --- /dev/null +++ b/include/linux/keycombo.h @@ -0,0 +1,36 @@ +/* + * include/linux/keycombo.h - platform data structure for keycombo driver + * + * Copyright (C) 2014 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#ifndef _LINUX_KEYCOMBO_H +#define _LINUX_KEYCOMBO_H + +#define KEYCOMBO_NAME "keycombo" + +/* + * if key_down_fn and key_up_fn are both present, you are guaranteed that + * key_down_fn will return before key_up_fn is called, and that key_up_fn + * is called iff key_down_fn is called. + */ +struct keycombo_platform_data { + void (*key_down_fn)(void *); + void (*key_up_fn)(void *); + void *priv; + int key_down_delay; /* Time in ms */ + int *keys_up; + int keys_down[]; /* 0 terminated */ +}; + +#endif /* _LINUX_KEYCOMBO_H */ diff --git a/include/linux/keyreset.h b/include/linux/keyreset.h new file mode 100644 index 000000000000..2e34afab65e4 --- /dev/null +++ b/include/linux/keyreset.h @@ -0,0 +1,29 @@ +/* + * include/linux/keyreset.h - platform data structure for resetkeys driver + * + * Copyright (C) 2014 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#ifndef _LINUX_KEYRESET_H +#define _LINUX_KEYRESET_H + +#define KEYRESET_NAME "keyreset" + +struct keyreset_platform_data { + int (*reset_fn)(void); + int key_down_delay; + int *keys_up; + int keys_down[]; /* 0 terminated */ +}; + +#endif /* _LINUX_KEYRESET_H */ diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index c9258124e417..7161d8e7ee79 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1351,6 +1351,40 @@ * @inode we wish to get the security context of. * @ctx is a pointer in which to place the allocated security context. * @ctxlen points to the place to put the length of @ctx. + * + * Security hooks for using the eBPF maps and programs functionalities through + * eBPF syscalls. + * + * @bpf: + * Do a initial check for all bpf syscalls after the attribute is copied + * into the kernel. The actual security module can implement their own + * rules to check the specific cmd they need. + * + * @bpf_map: + * Do a check when the kernel generate and return a file descriptor for + * eBPF maps. + * + * @map: bpf map that we want to access + * @mask: the access flags + * + * @bpf_prog: + * Do a check when the kernel generate and return a file descriptor for + * eBPF programs. + * + * @prog: bpf prog that userspace want to use. + * + * @bpf_map_alloc_security: + * Initialize the security field inside bpf map. + * + * @bpf_map_free_security: + * Clean up the security information stored inside bpf map. + * + * @bpf_prog_alloc_security: + * Initialize the security field inside bpf program. + * + * @bpf_prog_free_security: + * Clean up the security information stored inside bpf prog. + * */ union security_list_options { int (*binder_set_context_mgr)(struct task_struct *mgr); @@ -1682,6 +1716,17 @@ union security_list_options { struct audit_context *actx); void (*audit_rule_free)(void *lsmrule); #endif /* CONFIG_AUDIT */ + +#ifdef CONFIG_BPF_SYSCALL + int (*bpf)(int cmd, union bpf_attr *attr, + unsigned int size); + int (*bpf_map)(struct bpf_map *map, fmode_t fmode); + int (*bpf_prog)(struct bpf_prog *prog); + int (*bpf_map_alloc_security)(struct bpf_map *map); + void (*bpf_map_free_security)(struct bpf_map *map); + int (*bpf_prog_alloc_security)(struct bpf_prog_aux *aux); + void (*bpf_prog_free_security)(struct bpf_prog_aux *aux); +#endif /* CONFIG_BPF_SYSCALL */ }; struct security_hook_heads { @@ -1901,6 +1946,15 @@ struct security_hook_heads { struct list_head audit_rule_match; struct list_head audit_rule_free; #endif /* CONFIG_AUDIT */ +#ifdef CONFIG_BPF_SYSCALL + struct list_head bpf; + struct list_head bpf_map; + struct list_head bpf_prog; + struct list_head bpf_map_alloc_security; + struct list_head bpf_map_free_security; + struct list_head bpf_prog_alloc_security; + struct list_head bpf_prog_free_security; +#endif /* CONFIG_BPF_SYSCALL */ } __randomize_layout; /* diff --git a/include/linux/memory-state-time.h b/include/linux/memory-state-time.h new file mode 100644 index 000000000000..d2212b027866 --- /dev/null +++ b/include/linux/memory-state-time.h @@ -0,0 +1,42 @@ +/* include/linux/memory-state-time.h + * + * Copyright (C) 2016 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/workqueue.h> + +#define UPDATE_MEMORY_STATE(BLOCK, VALUE) BLOCK->update_call(BLOCK, VALUE) + +struct memory_state_update_block; + +typedef void (*memory_state_update_fn_t)(struct memory_state_update_block *ub, + int value); + +/* This struct is populated when you pass it to a memory_state_register* + * function. The update_call function is used for an update and defined in the + * typedef memory_state_update_fn_t + */ +struct memory_state_update_block { + memory_state_update_fn_t update_call; + int id; +}; + +/* Register a frequency struct memory_state_update_block to provide updates to + * memory_state_time about frequency changes using its update_call function. + */ +struct memory_state_update_block *memory_state_register_frequency_source(void); + +/* Register a bandwidth struct memory_state_update_block to provide updates to + * memory_state_time about bandwidth changes using its update_call function. + */ +struct memory_state_update_block *memory_state_register_bandwidth_source(void); diff --git a/include/linux/mm.h b/include/linux/mm.h index 156940758fc5..293ccec49ff1 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1243,6 +1243,8 @@ extern void pagefault_out_of_memory(void); extern void show_free_areas(unsigned int flags, nodemask_t *nodemask); +void shmem_set_file(struct vm_area_struct *vma, struct file *file); + extern bool can_do_mlock(void); extern int user_shm_lock(size_t, struct user_struct *); extern void user_shm_unlock(size_t, struct user_struct *); @@ -2114,7 +2116,7 @@ static inline int vma_adjust(struct vm_area_struct *vma, unsigned long start, extern struct vm_area_struct *vma_merge(struct mm_struct *, struct vm_area_struct *prev, unsigned long addr, unsigned long end, unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t, - struct mempolicy *, struct vm_userfaultfd_ctx); + struct mempolicy *, struct vm_userfaultfd_ctx, const char __user *); extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *); extern int __split_vma(struct mm_struct *, struct vm_area_struct *, unsigned long addr, int new_below); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index be5d445bac98..a646e4d8d494 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -309,11 +309,18 @@ struct vm_area_struct { /* * For areas with an address space and backing store, * linkage into the address_space->i_mmap interval tree. + * + * For private anonymous mappings, a pointer to a null terminated string + * in the user process containing the name given to the vma, or NULL + * if unnamed. */ - struct { - struct rb_node rb; - unsigned long rb_subtree_last; - } shared; + union { + struct { + struct rb_node rb; + unsigned long rb_subtree_last; + } shared; + const char __user *anon_name; + }; /* * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma @@ -660,4 +667,13 @@ typedef struct { unsigned long val; } swp_entry_t; +/* Return the name for an anonymous mapping or NULL for a file-backed mapping */ +static inline const char __user *vma_get_anon_name(struct vm_area_struct *vma) +{ + if (vma->vm_file) + return NULL; + + return vma->anon_name; +} + #endif /* _LINUX_MM_TYPES_H */ diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 9a43763a68ad..227961c5011b 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -439,6 +439,15 @@ struct mmc_host { bool cqe_enabled; bool cqe_on; +#ifdef CONFIG_MMC_EMBEDDED_SDIO + struct { + struct sdio_cis *cis; + struct sdio_cccr *cccr; + struct sdio_embedded_func *funcs; + int num_funcs; + } embedded_sdio_data; +#endif + unsigned long private[0] ____cacheline_aligned; }; @@ -451,6 +460,14 @@ void mmc_free_host(struct mmc_host *); int mmc_of_parse(struct mmc_host *host); int mmc_of_parse_voltage(struct device_node *np, u32 *mask); +#ifdef CONFIG_MMC_EMBEDDED_SDIO +extern void mmc_set_embedded_sdio_data(struct mmc_host *host, + struct sdio_cis *cis, + struct sdio_cccr *cccr, + struct sdio_embedded_func *funcs, + int num_funcs); +#endif + static inline void *mmc_priv(struct mmc_host *host) { return (void *)host->private; diff --git a/include/linux/mmc/pm.h b/include/linux/mmc/pm.h index 4a139204c20c..6e2d6a135c7e 100644 --- a/include/linux/mmc/pm.h +++ b/include/linux/mmc/pm.h @@ -26,5 +26,6 @@ typedef unsigned int mmc_pm_flag_t; #define MMC_PM_KEEP_POWER (1 << 0) /* preserve card power during suspend */ #define MMC_PM_WAKE_SDIO_IRQ (1 << 1) /* wake up host system on SDIO IRQ assertion */ +#define MMC_PM_IGNORE_PM_NOTIFY (1 << 2) /* ignore mmc pm notify */ #endif /* LINUX_MMC_PM_H */ diff --git a/include/linux/mmc/sdio_func.h b/include/linux/mmc/sdio_func.h index 97ca105347a6..f466f381ad25 100644 --- a/include/linux/mmc/sdio_func.h +++ b/include/linux/mmc/sdio_func.h @@ -23,6 +23,14 @@ struct sdio_func; typedef void (sdio_irq_handler_t)(struct sdio_func *); /* + * Structure used to hold embedded SDIO device data from platform layer + */ +struct sdio_embedded_func { + uint8_t f_class; + uint32_t f_maxblksize; +}; + +/* * SDIO function CIS tuple (unknown to the core) */ struct sdio_func_tuple { diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index f679f5268467..71b7a8bc82ea 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -163,6 +163,7 @@ enum node_stat_item { NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ WORKINGSET_REFAULT, WORKINGSET_ACTIVATE, + WORKINGSET_RESTORE, WORKINGSET_NODERECLAIM, NR_ANON_MAPPED, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. diff --git a/include/linux/module.h b/include/linux/module.h index c290de08c830..96c51179d500 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -19,6 +19,7 @@ #include <linux/jump_label.h> #include <linux/export.h> #include <linux/rbtree_latch.h> +#include <linux/cfi.h> #include <linux/percpu.h> #include <asm/module.h> @@ -346,6 +347,10 @@ struct module { const s32 *crcs; unsigned int num_syms; +#ifdef CONFIG_CFI_CLANG + cfi_check_fn cfi_check; +#endif + /* Kernel parameters. */ #ifdef CONFIG_SYSFS struct mutex param_lock; diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index 1d7140fef154..ba36506db4fb 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -228,19 +228,11 @@ struct kparam_array VERIFY_OCTAL_PERMISSIONS(perm), level, flags, { arg } } /* Obsolete - use module_param_cb() */ -#define module_param_call(name, set, get, arg, perm) \ - static const struct kernel_param_ops __param_ops_##name = \ - { .flags = 0, (void *)set, (void *)get }; \ +#define module_param_call(name, _set, _get, arg, perm) \ + static const struct kernel_param_ops __param_ops_##name = \ + { .flags = 0, .set = _set, .get = _get }; \ __module_param_call(MODULE_PARAM_PREFIX, \ - name, &__param_ops_##name, arg, \ - (perm) + sizeof(__check_old_set_param(set))*0, -1, 0) - -/* We don't get oldget: it's often a new-style param_get_uint, etc. */ -static inline int -__check_old_set_param(int (*oldset)(const char *, struct kernel_param *)) -{ - return 0; -} + name, &__param_ops_##name, arg, perm, -1, 0) #ifdef CONFIG_SYSFS extern void kernel_param_lock(struct module *mod); diff --git a/include/linux/mount.h b/include/linux/mount.h index 45b1f56c6c2f..1ff21c19b0b9 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -68,6 +68,7 @@ struct vfsmount { struct dentry *mnt_root; /* root of the mounted tree */ struct super_block *mnt_sb; /* pointer to superblock */ int mnt_flags; + void *data; } __randomize_layout; struct file; /* forward dec */ diff --git a/include/linux/namei.h b/include/linux/namei.h index a982bb7cd480..db4f5c09a7da 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -80,8 +80,11 @@ extern struct dentry *user_path_create(int, const char __user *, struct path *, extern void done_path_create(struct path *, struct dentry *); extern struct dentry *kern_path_locked(const char *, struct path *); extern int kern_path_mountpoint(int, const char *, struct path *, unsigned int); +extern int vfs_path_lookup(struct dentry *, struct vfsmount *, + const char *, unsigned int, struct path *); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); +extern struct dentry *lookup_one_len2(const char *, struct vfsmount *mnt, struct dentry *, int); extern struct dentry *lookup_one_len_unlocked(const char *, struct dentry *, int); extern int follow_down_one(struct path *); diff --git a/include/linux/netfilter/xt_quota2.h b/include/linux/netfilter/xt_quota2.h new file mode 100644 index 000000000000..eadc6903314e --- /dev/null +++ b/include/linux/netfilter/xt_quota2.h @@ -0,0 +1,25 @@ +#ifndef _XT_QUOTA_H +#define _XT_QUOTA_H + +enum xt_quota_flags { + XT_QUOTA_INVERT = 1 << 0, + XT_QUOTA_GROW = 1 << 1, + XT_QUOTA_PACKET = 1 << 2, + XT_QUOTA_NO_CHANGE = 1 << 3, + XT_QUOTA_MASK = 0x0F, +}; + +struct xt_quota_counter; + +struct xt_quota_mtinfo2 { + char name[15]; + u_int8_t flags; + + /* Comparison-invariant */ + aligned_u64 quota; + + /* Used internally by the kernel */ + struct xt_quota_counter *master __attribute__((aligned(8))); +}; + +#endif /* _XT_QUOTA_H */ diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index 013c5418aeec..064bac7a464b 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -66,6 +66,27 @@ extern unsigned long of_get_flat_dt_root(void); extern int of_get_flat_dt_size(void); extern uint32_t of_get_flat_dt_phandle(unsigned long node); +/* + * early_init_dt_scan_chosen - scan the device tree for ramdisk and bootargs + * + * The boot arguments will be placed into the memory pointed to by @data. + * That memory should be COMMAND_LINE_SIZE big and initialized to be a valid + * (possibly empty) string. Logic for what will be in @data after this + * function finishes: + * + * - CONFIG_CMDLINE_FORCE=true + * CONFIG_CMDLINE + * - CONFIG_CMDLINE_EXTEND=true, @data is non-empty string + * @data + dt bootargs (even if dt bootargs are empty) + * - CONFIG_CMDLINE_EXTEND=true, @data is empty string + * CONFIG_CMDLINE + dt bootargs (even if dt bootargs are empty) + * - CMDLINE_FROM_BOOTLOADER=true, dt bootargs=non-empty: + * dt bootargs + * - CMDLINE_FROM_BOOTLOADER=true, dt bootargs=empty, @data is non-empty string + * @data is left unchanged + * - CMDLINE_FROM_BOOTLOADER=true, dt bootargs=empty, @data is empty string + * CONFIG_CMDLINE (or "" if that's not defined) + */ extern int early_init_dt_scan_chosen(unsigned long node, const char *uname, int depth, void *data); extern int early_init_dt_scan_memory(unsigned long node, const char *uname, diff --git a/include/linux/overflow.h b/include/linux/overflow.h index d309788f4cd2..980beb1d891d 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -202,6 +202,79 @@ #endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */ +/** + * array_size() - Calculate size of 2-dimensional array. + * + * @a: dimension one + * @b: dimension two + * + * Calculates size of 2-dimensional array: @a * @b. + * + * Returns: number of bytes needed to represent the array or SIZE_MAX on + * overflow. + */ +static inline __must_check size_t array_size(size_t a, size_t b) +{ + size_t bytes; + + if (check_mul_overflow(a, b, &bytes)) + return SIZE_MAX; + + return bytes; +} + +/** + * array3_size() - Calculate size of 3-dimensional array. + * + * @a: dimension one + * @b: dimension two + * @c: dimension three + * + * Calculates size of 3-dimensional array: @a * @b * @c. + * + * Returns: number of bytes needed to represent the array or SIZE_MAX on + * overflow. + */ +static inline __must_check size_t array3_size(size_t a, size_t b, size_t c) +{ + size_t bytes; + + if (check_mul_overflow(a, b, &bytes)) + return SIZE_MAX; + if (check_mul_overflow(bytes, c, &bytes)) + return SIZE_MAX; + + return bytes; +} + +static inline __must_check size_t __ab_c_size(size_t n, size_t size, size_t c) +{ + size_t bytes; + + if (check_mul_overflow(n, size, &bytes)) + return SIZE_MAX; + if (check_add_overflow(bytes, c, &bytes)) + return SIZE_MAX; + + return bytes; +} + +/** + * struct_size() - Calculate size of structure with trailing array. + * @p: Pointer to the structure. + * @member: Name of the array member. + * @n: Number of elements in the array. + * + * Calculates size of memory needed for structure @p followed by an + * array of @n @member elements. + * + * Return: number of bytes needed or SIZE_MAX on overflow. + */ +#define struct_size(p, member, n) \ + __ab_c_size(n, \ + sizeof(*(p)->member) + __must_be_array((p)->member),\ + sizeof(*(p))) + /** check_shl_overflow() - Calculate a left-shifted value and check overflow * * @a: Value to be shifted diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 7cbd8195ffb3..a02794afc4dc 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -74,13 +74,14 @@ */ enum pageflags { PG_locked, /* Page is locked. Don't touch. */ - PG_error, PG_referenced, PG_uptodate, PG_dirty, PG_lru, PG_active, + PG_workingset, PG_waiters, /* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */ + PG_error, PG_slab, PG_owner_priv_1, /* Owner use. If pagecache, fs may use*/ PG_arch_1, @@ -273,6 +274,8 @@ PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD) PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD) PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD) TESTCLEARFLAG(Active, active, PF_HEAD) +PAGEFLAG(Workingset, workingset, PF_HEAD) + TESTCLEARFLAG(Workingset, workingset, PF_HEAD) __PAGEFLAG(Slab, slab, PF_NO_TAIL) __PAGEFLAG(SlobFree, slob_free, PF_NO_TAIL) PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index e08b5339023c..cdfe171c0106 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -243,7 +243,7 @@ static inline gfp_t readahead_gfp_mask(struct address_space *x) __GFP_COLD | __GFP_NORETRY | __GFP_NOWARN; } -typedef int filler_t(void *, struct page *); +typedef int filler_t(struct file *, struct page *); pgoff_t page_cache_next_hole(struct address_space *mapping, pgoff_t index, unsigned long max_scan); @@ -256,6 +256,7 @@ pgoff_t page_cache_prev_hole(struct address_space *mapping, #define FGP_WRITE 0x00000008 #define FGP_NOFS 0x00000010 #define FGP_NOWAIT 0x00000020 +#define FGP_FOR_MMAP 0x00000040 struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, int fgp_flags, gfp_t cache_gfp_mask); @@ -366,8 +367,16 @@ static inline unsigned find_get_pages(struct address_space *mapping, } unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, unsigned int nr_pages, struct page **pages); -unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index, - int tag, unsigned int nr_pages, struct page **pages); +unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, + pgoff_t end, int tag, unsigned int nr_pages, + struct page **pages); +static inline unsigned find_get_pages_tag(struct address_space *mapping, + pgoff_t *index, int tag, unsigned int nr_pages, + struct page **pages) +{ + return find_get_pages_range_tag(mapping, index, (pgoff_t)-1, tag, + nr_pages, pages); +} unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start, int tag, unsigned int nr_entries, struct page **entries, pgoff_t *indices); @@ -394,7 +403,7 @@ extern int read_cache_pages(struct address_space *mapping, static inline struct page *read_mapping_page(struct address_space *mapping, pgoff_t index, void *data) { - filler_t *filler = (filler_t *)mapping->a_ops->readpage; + filler_t *filler = mapping->a_ops->readpage; return read_cache_page(mapping, index, filler, data); } diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index 2636c0c0f279..4f56e0ad9d00 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -38,9 +38,17 @@ static inline unsigned pagevec_lookup(struct pagevec *pvec, return pagevec_lookup_range(pvec, mapping, start, (pgoff_t)-1); } -unsigned pagevec_lookup_tag(struct pagevec *pvec, - struct address_space *mapping, pgoff_t *index, int tag, - unsigned nr_pages); +unsigned pagevec_lookup_range_tag(struct pagevec *pvec, + struct address_space *mapping, pgoff_t *index, pgoff_t end, + int tag); +unsigned pagevec_lookup_range_nr_tag(struct pagevec *pvec, + struct address_space *mapping, pgoff_t *index, pgoff_t end, + int tag, unsigned max_pages); +static inline unsigned pagevec_lookup_tag(struct pagevec *pvec, + struct address_space *mapping, pgoff_t *index, int tag) +{ + return pagevec_lookup_range_tag(pvec, mapping, index, (pgoff_t)-1, tag); +} static inline void pagevec_init(struct pagevec *pvec, int cold) { diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 956d76744c91..00ae925e2878 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1170,6 +1170,11 @@ extern int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write, int perf_event_max_stack_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); +static inline bool perf_paranoid_any(void) +{ + return sysctl_perf_event_paranoid > 2; +} + static inline bool perf_paranoid_tracepoint_raw(void) { return sysctl_perf_event_paranoid > -1; diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index b2b7255ec7f5..540595a321a7 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -12,6 +12,7 @@ #include <linux/bug.h> #include <linux/slab.h> #include <linux/rcupdate.h> +#include <linux/refcount.h> #include <uapi/linux/posix_acl.h> struct posix_acl_entry { @@ -24,7 +25,7 @@ struct posix_acl_entry { }; struct posix_acl { - atomic_t a_refcount; + refcount_t a_refcount; struct rcu_head a_rcu; unsigned int a_count; struct posix_acl_entry a_entries[0]; @@ -41,7 +42,7 @@ static inline struct posix_acl * posix_acl_dup(struct posix_acl *acl) { if (acl) - atomic_inc(&acl->a_refcount); + refcount_inc(&acl->a_refcount); return acl; } @@ -51,7 +52,7 @@ posix_acl_dup(struct posix_acl *acl) static inline void posix_acl_release(struct posix_acl *acl) { - if (acl && atomic_dec_and_test(&acl->a_refcount)) + if (acl && refcount_dec_and_test(&acl->a_refcount)) kfree_rcu(acl, a_rcu); } diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 4617cf4f6c5b..c25e166ea7d0 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -18,6 +18,7 @@ #include <linux/leds.h> #include <linux/spinlock.h> #include <linux/notifier.h> +#include <linux/types.h> /* * All voltages, currents, charges, energies, time and temperatures in uV, @@ -149,6 +150,12 @@ enum power_supply_property { POWER_SUPPLY_PROP_PRECHARGE_CURRENT, POWER_SUPPLY_PROP_CHARGE_TERM_CURRENT, POWER_SUPPLY_PROP_CALIBRATE, + /* Local extensions */ + POWER_SUPPLY_PROP_USB_HC, + POWER_SUPPLY_PROP_USB_OTG, + POWER_SUPPLY_PROP_CHARGE_ENABLED, + /* Local extensions of type int64_t */ + POWER_SUPPLY_PROP_CHARGE_COUNTER_EXT, /* Properties of type `const char *' */ POWER_SUPPLY_PROP_MODEL_NAME, POWER_SUPPLY_PROP_MANUFACTURER, @@ -177,6 +184,7 @@ enum power_supply_notifier_events { union power_supply_propval { int intval; const char *strval; + int64_t int64val; }; struct device_node; diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 928ef9e4d912..d1c705eb4984 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -71,6 +71,12 @@ static inline int remove_proc_subtree(const char *name, struct proc_dir_entry *p #endif /* CONFIG_PROC_FS */ +#ifdef CONFIG_PROC_UID +extern void proc_register_uid(kuid_t uid); +#else +static inline void proc_register_uid(kuid_t uid) {} +#endif + struct net; static inline struct proc_dir_entry *proc_net_mkdir( diff --git a/include/linux/psi.h b/include/linux/psi.h new file mode 100644 index 000000000000..b825fa53d498 --- /dev/null +++ b/include/linux/psi.h @@ -0,0 +1,63 @@ +#ifndef _LINUX_PSI_H +#define _LINUX_PSI_H + +#include <linux/jump_label.h> +#include <linux/psi_types.h> +#include <linux/sched.h> +#include <linux/poll.h> +#include <linux/cgroup-defs.h> + +struct seq_file; +struct css_set; + +#ifdef CONFIG_PSI + +extern struct static_key_false psi_disabled; + +void psi_init(void); + +void psi_task_change(struct task_struct *task, int clear, int set); + +void psi_memstall_tick(struct task_struct *task, int cpu); +void psi_memstall_enter(unsigned long *flags); +void psi_memstall_leave(unsigned long *flags); + +int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res); + +#ifdef CONFIG_CGROUPS +int psi_cgroup_alloc(struct cgroup *cgrp); +void psi_cgroup_free(struct cgroup *cgrp); +void cgroup_move_task(struct task_struct *p, struct css_set *to); + +struct psi_trigger *psi_trigger_create(struct psi_group *group, + char *buf, size_t nbytes, enum psi_res res); +void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *t); + +unsigned int psi_trigger_poll(void **trigger_ptr, struct file *file, + poll_table *wait); +#endif + +#else /* CONFIG_PSI */ + +static inline void psi_init(void) {} + +static inline void psi_memstall_enter(unsigned long *flags) {} +static inline void psi_memstall_leave(unsigned long *flags) {} + +#ifdef CONFIG_CGROUPS +static inline int psi_cgroup_alloc(struct cgroup *cgrp) +{ + return 0; +} +static inline void psi_cgroup_free(struct cgroup *cgrp) +{ +} +static inline void cgroup_move_task(struct task_struct *p, struct css_set *to) +{ + rcu_assign_pointer(p->cgroups, to); +} +#endif + +#endif /* CONFIG_PSI */ + +#endif /* _LINUX_PSI_H */ diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h new file mode 100644 index 000000000000..07aaf9b82241 --- /dev/null +++ b/include/linux/psi_types.h @@ -0,0 +1,173 @@ +#ifndef _LINUX_PSI_TYPES_H +#define _LINUX_PSI_TYPES_H + +#include <linux/kthread.h> +#include <linux/seqlock.h> +#include <linux/types.h> +#include <linux/kref.h> +#include <linux/wait.h> + +#ifdef CONFIG_PSI + +/* Tracked task states */ +enum psi_task_count { + NR_IOWAIT, + NR_MEMSTALL, + NR_RUNNING, + NR_PSI_TASK_COUNTS = 3, +}; + +/* Task state bitmasks */ +#define TSK_IOWAIT (1 << NR_IOWAIT) +#define TSK_MEMSTALL (1 << NR_MEMSTALL) +#define TSK_RUNNING (1 << NR_RUNNING) + +/* Resources that workloads could be stalled on */ +enum psi_res { + PSI_IO, + PSI_MEM, + PSI_CPU, + NR_PSI_RESOURCES = 3, +}; + +/* + * Pressure states for each resource: + * + * SOME: Stalled tasks & working tasks + * FULL: Stalled tasks & no working tasks + */ +enum psi_states { + PSI_IO_SOME, + PSI_IO_FULL, + PSI_MEM_SOME, + PSI_MEM_FULL, + PSI_CPU_SOME, + /* Only per-CPU, to weigh the CPU in the global average: */ + PSI_NONIDLE, + NR_PSI_STATES = 6, +}; + +enum psi_aggregators { + PSI_AVGS = 0, + PSI_POLL, + NR_PSI_AGGREGATORS, +}; + +struct psi_group_cpu { + /* 1st cacheline updated by the scheduler */ + + /* Aggregator needs to know of concurrent changes */ + seqcount_t seq ____cacheline_aligned_in_smp; + + /* States of the tasks belonging to this group */ + unsigned int tasks[NR_PSI_TASK_COUNTS]; + + /* Aggregate pressure state derived from the tasks */ + u32 state_mask; + + /* Period time sampling buckets for each state of interest (ns) */ + u32 times[NR_PSI_STATES]; + + /* Time of last task change in this group (rq_clock) */ + u64 state_start; + + /* 2nd cacheline updated by the aggregator */ + + /* Delta detection against the sampling buckets */ + u32 times_prev[NR_PSI_AGGREGATORS][NR_PSI_STATES] + ____cacheline_aligned_in_smp; +}; + +/* PSI growth tracking window */ +struct psi_window { + /* Window size in ns */ + u64 size; + + /* Start time of the current window in ns */ + u64 start_time; + + /* Value at the start of the window */ + u64 start_value; + + /* Value growth in the previous window */ + u64 prev_growth; +}; + +struct psi_trigger { + /* PSI state being monitored by the trigger */ + enum psi_states state; + + /* User-spacified threshold in ns */ + u64 threshold; + + /* List node inside triggers list */ + struct list_head node; + + /* Backpointer needed during trigger destruction */ + struct psi_group *group; + + /* Wait queue for polling */ + wait_queue_head_t event_wait; + + /* Pending event flag */ + int event; + + /* Tracking window */ + struct psi_window win; + + /* + * Time last event was generated. Used for rate-limiting + * events to one per window + */ + u64 last_event_time; + + /* Refcounting to prevent premature destruction */ + struct kref refcount; +}; + +struct psi_group { + /* Protects data used by the aggregator */ + struct mutex avgs_lock; + + /* Per-cpu task state & time tracking */ + struct psi_group_cpu __percpu *pcpu; + + /* Running pressure averages */ + u64 avg_total[NR_PSI_STATES - 1]; + u64 avg_last_update; + u64 avg_next_update; + + /* Aggregator work control */ + struct delayed_work avgs_work; + + /* Total stall times and sampled pressure averages */ + u64 total[NR_PSI_AGGREGATORS][NR_PSI_STATES - 1]; + unsigned long avg[NR_PSI_STATES - 1][3]; + + /* Monitor work control */ + atomic_t poll_scheduled; + struct kthread_worker __rcu *poll_kworker; + struct kthread_delayed_work poll_work; + + /* Protects data used by the monitor */ + struct mutex trigger_lock; + + /* Configured polling triggers */ + struct list_head triggers; + u32 nr_triggers[NR_PSI_STATES - 1]; + u32 poll_states; + u64 poll_min_period; + + /* Total stall times at the start of monitor activation */ + u64 polling_total[NR_PSI_STATES - 1]; + u64 polling_next_update; + u64 polling_until; +}; + +#else /* CONFIG_PSI */ + +struct psi_group { }; + +#endif /* CONFIG_PSI */ + +#endif /* _LINUX_PSI_TYPES_H */ diff --git a/include/linux/pstore_ram.h b/include/linux/pstore_ram.h index 9395f06e8372..10fe2e28701f 100644 --- a/include/linux/pstore_ram.h +++ b/include/linux/pstore_ram.h @@ -80,6 +80,8 @@ void persistent_ram_free_old(struct persistent_ram_zone *prz); ssize_t persistent_ram_ecc_string(struct persistent_ram_zone *prz, char *str, size_t len); +void ramoops_console_write_buf(const char *buf, size_t size); + /* * Ramoops platform data * @mem_size memory size for ramoops diff --git a/include/linux/sched.h b/include/linux/sched.h index 99650f05c271..fd2e5fdba129 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -206,6 +206,15 @@ struct task_group; /* Task command name length: */ #define TASK_COMM_LEN 16 +enum task_event { + PUT_PREV_TASK = 0, + PICK_NEXT_TASK = 1, + TASK_WAKE = 2, + TASK_MIGRATE = 3, + TASK_UPDATE = 4, + IRQ_UPDATE = 5, +}; + extern cpumask_var_t cpu_isolated_map; extern void scheduler_tick(void); @@ -317,6 +326,34 @@ struct load_weight { u32 inv_weight; }; +/** + * struct util_est - Estimation utilization of FAIR tasks + * @enqueued: instantaneous estimated utilization of a task/cpu + * @ewma: the Exponential Weighted Moving Average (EWMA) + * utilization of a task + * + * Support data structure to track an Exponential Weighted Moving Average + * (EWMA) of a FAIR task's utilization. New samples are added to the moving + * average each time a task completes an activation. Sample's weight is chosen + * so that the EWMA will be relatively insensitive to transient changes to the + * task's workload. + * + * The enqueued attribute has a slightly different meaning for tasks and cpus: + * - task: the task's util_avg at last task dequeue time + * - cfs_rq: the sum of util_est.enqueued for each RUNNABLE task on that CPU + * Thus, the util_est.enqueued of a task represents the contribution on the + * estimated utilization of the CPU where that task is currently enqueued. + * + * Only for tasks we track a moving average of the past instantaneous + * estimated utilization. This allows to absorb sporadic drops in utilization + * of an otherwise almost periodic task. + */ +struct util_est { + unsigned int enqueued; + unsigned int ewma; +#define UTIL_EST_WEIGHT_SHIFT 2 +}; + /* * The load_avg/util_avg accumulates an infinite geometric series * (see __update_load_avg() in kernel/sched/fair.c). @@ -376,6 +413,7 @@ struct sched_avg { u32 period_contrib; unsigned long load_avg; unsigned long util_avg; + struct util_est util_est; }; struct sched_statistics { @@ -450,6 +488,41 @@ struct sched_entity { #endif }; +#ifdef CONFIG_SCHED_WALT +#define RAVG_HIST_SIZE_MAX 5 + +/* ravg represents frequency scaled cpu-demand of tasks */ +struct ravg { + /* + * 'mark_start' marks the beginning of an event (task waking up, task + * starting to execute, task being preempted) within a window + * + * 'sum' represents how runnable a task has been within current + * window. It incorporates both running time and wait time and is + * frequency scaled. + * + * 'sum_history' keeps track of history of 'sum' seen over previous + * RAVG_HIST_SIZE windows. Windows where task was entirely sleeping are + * ignored. + * + * 'demand' represents maximum sum seen over previous + * sysctl_sched_ravg_hist_size windows. 'demand' could drive frequency + * demand for tasks. + * + * 'curr_window' represents task's contribution to cpu busy time + * statistics (rq->curr_runnable_sum) in current window + * + * 'prev_window' represents task's contribution to cpu busy time + * statistics (rq->prev_runnable_sum) in previous window + */ + u64 mark_start; + u32 sum, demand; + u32 sum_history[RAVG_HIST_SIZE_MAX]; + u32 curr_window, prev_window; + u16 active_windows; +}; +#endif + struct sched_rt_entity { struct list_head run_list; unsigned long timeout; @@ -602,6 +675,16 @@ struct task_struct { const struct sched_class *sched_class; struct sched_entity se; struct sched_rt_entity rt; +#ifdef CONFIG_SCHED_WALT + struct ravg ravg; + /* + * 'init_load_pct' represents the initial task load assigned to children + * of this task + */ + u32 init_load_pct; + u64 last_sleep_ts; +#endif + #ifdef CONFIG_CGROUP_SCHED struct task_group *sched_task_group; #endif @@ -668,6 +751,10 @@ struct task_struct { unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; unsigned sched_remote_wakeup:1; +#ifdef CONFIG_PSI + unsigned sched_psi_wake_requeue:1; +#endif + /* Force alignment to the next boundary: */ unsigned :0; @@ -752,6 +839,10 @@ struct task_struct { u64 stimescaled; #endif u64 gtime; +#ifdef CONFIG_CPU_FREQ_TIMES + u64 *time_in_state; + unsigned int max_state; +#endif struct prev_cputime prev_cputime; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN struct vtime vtime; @@ -926,6 +1017,10 @@ struct task_struct { siginfo_t *last_siginfo; struct task_io_accounting ioac; +#ifdef CONFIG_PSI + /* Pressure stall state */ + unsigned int psi_flags; +#endif #ifdef CONFIG_TASK_XACCT /* Accumulated RSS usage: */ u64 acct_rss_mem1; @@ -1356,6 +1451,7 @@ extern struct pid *cad_pid; #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ +#define PF_MEMSTALL 0x01000000 /* Stalled due to lack of memory */ #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h index d1ad3d825561..0b55834efd46 100644 --- a/include/linux/sched/cpufreq.h +++ b/include/linux/sched/cpufreq.h @@ -12,8 +12,6 @@ #define SCHED_CPUFREQ_DL (1U << 1) #define SCHED_CPUFREQ_IOWAIT (1U << 2) -#define SCHED_CPUFREQ_RT_DL (SCHED_CPUFREQ_RT | SCHED_CPUFREQ_DL) - #ifdef CONFIG_CPU_FREQ struct update_util_data { void (*func)(struct update_util_data *data, u64 time, unsigned int flags); diff --git a/include/linux/sched/energy.h b/include/linux/sched/energy.h new file mode 100644 index 000000000000..a9b0349dc018 --- /dev/null +++ b/include/linux/sched/energy.h @@ -0,0 +1,40 @@ +#ifndef _LINUX_SCHED_ENERGY_H +#define _LINUX_SCHED_ENERGY_H + +#include <linux/sched.h> +#include <linux/slab.h> + +/* + * There doesn't seem to be an NR_CPUS style max number of sched domain + * levels so here's an arbitrary constant one for the moment. + * + * The levels alluded to here correspond to entries in struct + * sched_domain_topology_level that are meant to be populated by arch + * specific code (topology.c). + */ +#define NR_SD_LEVELS 8 + +#define SD_LEVEL0 0 +#define SD_LEVEL1 1 +#define SD_LEVEL2 2 +#define SD_LEVEL3 3 +#define SD_LEVEL4 4 +#define SD_LEVEL5 5 +#define SD_LEVEL6 6 +#define SD_LEVEL7 7 + +/* + * Convenience macro for iterating through said sd levels. + */ +#define for_each_possible_sd_level(level) \ + for (level = 0; level < NR_SD_LEVELS; level++) + +extern struct sched_group_energy *sge_array[NR_CPUS][NR_SD_LEVELS]; + +#ifdef CONFIG_GENERIC_ARCH_TOPOLOGY +void init_sched_energy_costs(void); +#else +void init_sched_energy_costs(void) {} +#endif + +#endif diff --git a/include/linux/sched/loadavg.h b/include/linux/sched/loadavg.h index 80bc84ba5d2a..4859bea47a7b 100644 --- a/include/linux/sched/loadavg.h +++ b/include/linux/sched/loadavg.h @@ -22,10 +22,26 @@ extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift); #define EXP_5 2014 /* 1/exp(5sec/5min) */ #define EXP_15 2037 /* 1/exp(5sec/15min) */ -#define CALC_LOAD(load,exp,n) \ - load *= exp; \ - load += n*(FIXED_1-exp); \ - load >>= FSHIFT; +/* + * a1 = a0 * e + a * (1 - e) + */ +static inline unsigned long +calc_load(unsigned long load, unsigned long exp, unsigned long active) +{ + unsigned long newload; + + newload = load * exp + active * (FIXED_1 - exp); + if (active >= load) + newload += FIXED_1-1; + + return newload / FIXED_1; +} + +extern unsigned long calc_load_n(unsigned long load, unsigned long exp, + unsigned long active, unsigned int n); + +#define LOAD_INT(x) ((x) >> FSHIFT) +#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) extern void calc_global_load(unsigned long ticks); diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 1c1a1512ec55..1b722616d6bd 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -21,8 +21,16 @@ enum { sysctl_hung_task_timeout_secs = 0 }; extern unsigned int sysctl_sched_latency; extern unsigned int sysctl_sched_min_granularity; +extern unsigned int sysctl_sched_sync_hint_enable; +extern unsigned int sysctl_sched_cstate_aware; extern unsigned int sysctl_sched_wakeup_granularity; extern unsigned int sysctl_sched_child_runs_first; +#ifdef CONFIG_SCHED_WALT +extern unsigned int sysctl_sched_use_walt_cpu_util; +extern unsigned int sysctl_sched_use_walt_task_util; +extern unsigned int sysctl_sched_walt_init_task_load_pct; +extern unsigned int sysctl_sched_walt_cpu_high_irqload; +#endif enum sched_tunable_scaling { SCHED_TUNABLESCALING_NONE, diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 5a92baa91e0c..b45ae1319c95 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -26,6 +26,7 @@ #define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */ #define SD_OVERLAP 0x2000 /* sched_domains of this level overlap */ #define SD_NUMA 0x4000 /* cross-node balancing */ +#define SD_SHARE_CAP_STATES 0x8000 /* Domain members share capacity state */ /* * Increase resolution of cpu_capacity calculations @@ -66,12 +67,31 @@ struct sched_domain_attr { extern int sched_domain_level_max; +struct capacity_state { + unsigned long cap; /* compute capacity */ + unsigned long frequency;/* frequency */ + unsigned long power; /* power consumption at this compute capacity */ +}; + +struct idle_state { + unsigned long power; /* power consumption in this idle state */ +}; + +struct sched_group_energy { + unsigned int nr_idle_states; /* number of idle states */ + struct idle_state *idle_states; /* ptr to idle state array */ + unsigned int nr_cap_states; /* number of capacity states */ + struct capacity_state *cap_states; /* ptr to capacity state array */ +}; + struct sched_group; struct sched_domain_shared { atomic_t ref; atomic_t nr_busy_cpus; int has_idle_cores; + + bool overutilized; }; struct sched_domain { @@ -173,6 +193,9 @@ bool cpus_share_cache(int this_cpu, int that_cpu); typedef const struct cpumask *(*sched_domain_mask_f)(int cpu); typedef int (*sched_domain_flags_f)(void); +typedef +const struct sched_group_energy * const(*sched_domain_energy_f)(int cpu); +extern bool energy_aware(void); #define SDTL_OVERLAP 0x01 @@ -186,6 +209,7 @@ struct sd_data { struct sched_domain_topology_level { sched_domain_mask_f mask; sched_domain_flags_f sd_flags; + sched_domain_energy_f energy; int flags; int numa_level; struct sd_data data; diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h index 10b19a192b2d..a3661e93da6f 100644 --- a/include/linux/sched/wake_q.h +++ b/include/linux/sched/wake_q.h @@ -34,6 +34,7 @@ struct wake_q_head { struct wake_q_node *first; struct wake_q_node **lastp; + int count; }; #define WAKE_Q_TAIL ((struct wake_q_node *) 0x01) @@ -45,6 +46,7 @@ static inline void wake_q_init(struct wake_q_head *head) { head->first = WAKE_Q_TAIL; head->lastp = &head->first; + head->count = 0; } extern void wake_q_add(struct wake_q_head *head, diff --git a/include/linux/sched/xacct.h b/include/linux/sched/xacct.h index c078f0a94cec..9544c9d9d534 100644 --- a/include/linux/sched/xacct.h +++ b/include/linux/sched/xacct.h @@ -28,6 +28,11 @@ static inline void inc_syscw(struct task_struct *tsk) { tsk->ioac.syscw++; } + +static inline void inc_syscfs(struct task_struct *tsk) +{ + tsk->ioac.syscfs++; +} #else static inline void add_rchar(struct task_struct *tsk, ssize_t amt) { @@ -44,6 +49,10 @@ static inline void inc_syscr(struct task_struct *tsk) static inline void inc_syscw(struct task_struct *tsk) { } + +static inline void inc_syscfs(struct task_struct *tsk) +{ +} #endif #endif /* _LINUX_SCHED_XACCT_H */ diff --git a/include/linux/security.h b/include/linux/security.h index ce6265960d6c..73f1ef625d40 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1730,6 +1730,54 @@ static inline void securityfs_remove(struct dentry *dentry) #endif +#ifdef CONFIG_BPF_SYSCALL +union bpf_attr; +struct bpf_map; +struct bpf_prog; +struct bpf_prog_aux; +#ifdef CONFIG_SECURITY +extern int security_bpf(int cmd, union bpf_attr *attr, unsigned int size); +extern int security_bpf_map(struct bpf_map *map, fmode_t fmode); +extern int security_bpf_prog(struct bpf_prog *prog); +extern int security_bpf_map_alloc(struct bpf_map *map); +extern void security_bpf_map_free(struct bpf_map *map); +extern int security_bpf_prog_alloc(struct bpf_prog_aux *aux); +extern void security_bpf_prog_free(struct bpf_prog_aux *aux); +#else +static inline int security_bpf(int cmd, union bpf_attr *attr, + unsigned int size) +{ + return 0; +} + +static inline int security_bpf_map(struct bpf_map *map, fmode_t fmode) +{ + return 0; +} + +static inline int security_bpf_prog(struct bpf_prog *prog) +{ + return 0; +} + +static inline int security_bpf_map_alloc(struct bpf_map *map) +{ + return 0; +} + +static inline void security_bpf_map_free(struct bpf_map *map) +{ } + +static inline int security_bpf_prog_alloc(struct bpf_prog_aux *aux) +{ + return 0; +} + +static inline void security_bpf_prog_free(struct bpf_prog_aux *aux) +{ } +#endif /* CONFIG_SECURITY */ +#endif /* CONFIG_BPF_SYSCALL */ + #ifdef CONFIG_SECURITY static inline char *alloc_secdata(void) diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 8544357d92d0..2e5aa1bc42e8 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -444,6 +444,7 @@ extern bool pm_get_wakeup_count(unsigned int *count, bool block); extern bool pm_save_wakeup_count(unsigned int count); extern void pm_wakep_autosleep_enabled(bool set); extern void pm_print_active_wakeup_sources(void); +extern void pm_get_active_wakeup_sources(char *pending_sources, size_t max); static inline void lock_system_sleep(void) { diff --git a/include/linux/swap.h b/include/linux/swap.h index 411953964c34..19c537eb37b3 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -304,7 +304,7 @@ struct vma_swap_readahead { /* linux/mm/workingset.c */ void *workingset_eviction(struct address_space *mapping, struct page *page); -bool workingset_refault(void *shadow); +void workingset_refault(struct page *page, void *shadow); void workingset_activation(struct page *page); void workingset_update_node(struct radix_tree_node *node, void *private); diff --git a/include/linux/task_io_accounting.h b/include/linux/task_io_accounting.h index 6f6acce064de..bb26108ca23c 100644 --- a/include/linux/task_io_accounting.h +++ b/include/linux/task_io_accounting.h @@ -19,6 +19,8 @@ struct task_io_accounting { u64 syscr; /* # of write syscalls */ u64 syscw; + /* # of fsync syscalls */ + u64 syscfs; #endif /* CONFIG_TASK_XACCT */ #ifdef CONFIG_TASK_IO_ACCOUNTING diff --git a/include/linux/task_io_accounting_ops.h b/include/linux/task_io_accounting_ops.h index bb5498bcdd96..733ab62ae141 100644 --- a/include/linux/task_io_accounting_ops.h +++ b/include/linux/task_io_accounting_ops.h @@ -97,6 +97,7 @@ static inline void task_chr_io_accounting_add(struct task_io_accounting *dst, dst->wchar += src->wchar; dst->syscr += src->syscr; dst->syscw += src->syscw; + dst->syscfs += src->syscfs; } #else static inline void task_chr_io_accounting_add(struct task_io_accounting *dst, diff --git a/include/linux/tick.h b/include/linux/tick.h index 5cdac11dd317..bd8219943a91 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -114,26 +114,45 @@ enum tick_dep_bits { #ifdef CONFIG_NO_HZ_COMMON extern bool tick_nohz_enabled; extern int tick_nohz_tick_stopped(void); +extern void tick_nohz_idle_stop_tick(void); +extern void tick_nohz_idle_retain_tick(void); +extern void tick_nohz_idle_restart_tick(void); extern void tick_nohz_idle_enter(void); extern void tick_nohz_idle_exit(void); extern void tick_nohz_irq_exit(void); -extern ktime_t tick_nohz_get_sleep_length(void); +extern bool tick_nohz_idle_got_tick(void); +extern ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next); extern unsigned long tick_nohz_get_idle_calls(void); extern unsigned long tick_nohz_get_idle_calls_cpu(int cpu); extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time); extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time); + +static inline void tick_nohz_idle_stop_tick_protected(void) +{ + local_irq_disable(); + tick_nohz_idle_stop_tick(); + local_irq_enable(); +} + #else /* !CONFIG_NO_HZ_COMMON */ #define tick_nohz_enabled (0) static inline int tick_nohz_tick_stopped(void) { return 0; } +static inline void tick_nohz_idle_stop_tick(void) { } +static inline void tick_nohz_idle_retain_tick(void) { } +static inline void tick_nohz_idle_restart_tick(void) { } static inline void tick_nohz_idle_enter(void) { } static inline void tick_nohz_idle_exit(void) { } +static inline bool tick_nohz_idle_got_tick(void) { return false; } -static inline ktime_t tick_nohz_get_sleep_length(void) +static inline ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next) { - return NSEC_PER_SEC / HZ; + *delta_next = TICK_NSEC; + return *delta_next; } static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; } static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; } + +static inline void tick_nohz_idle_stop_tick_protected(void) { } #endif /* !CONFIG_NO_HZ_COMMON */ #ifdef CONFIG_NO_HZ_FULL diff --git a/include/linux/usb/class-dual-role.h b/include/linux/usb/class-dual-role.h new file mode 100644 index 000000000000..c6df2238012e --- /dev/null +++ b/include/linux/usb/class-dual-role.h @@ -0,0 +1,129 @@ +#ifndef __LINUX_CLASS_DUAL_ROLE_H__ +#define __LINUX_CLASS_DUAL_ROLE_H__ + +#include <linux/workqueue.h> +#include <linux/errno.h> +#include <linux/types.h> + +struct device; + +enum dual_role_supported_modes { + DUAL_ROLE_SUPPORTED_MODES_DFP_AND_UFP = 0, + DUAL_ROLE_SUPPORTED_MODES_DFP, + DUAL_ROLE_SUPPORTED_MODES_UFP, +/*The following should be the last element*/ + DUAL_ROLE_PROP_SUPPORTED_MODES_TOTAL, +}; + +enum { + DUAL_ROLE_PROP_MODE_UFP = 0, + DUAL_ROLE_PROP_MODE_DFP, + DUAL_ROLE_PROP_MODE_NONE, +/*The following should be the last element*/ + DUAL_ROLE_PROP_MODE_TOTAL, +}; + +enum { + DUAL_ROLE_PROP_PR_SRC = 0, + DUAL_ROLE_PROP_PR_SNK, + DUAL_ROLE_PROP_PR_NONE, +/*The following should be the last element*/ + DUAL_ROLE_PROP_PR_TOTAL, + +}; + +enum { + DUAL_ROLE_PROP_DR_HOST = 0, + DUAL_ROLE_PROP_DR_DEVICE, + DUAL_ROLE_PROP_DR_NONE, +/*The following should be the last element*/ + DUAL_ROLE_PROP_DR_TOTAL, +}; + +enum { + DUAL_ROLE_PROP_VCONN_SUPPLY_NO = 0, + DUAL_ROLE_PROP_VCONN_SUPPLY_YES, +/*The following should be the last element*/ + DUAL_ROLE_PROP_VCONN_SUPPLY_TOTAL, +}; + +enum dual_role_property { + DUAL_ROLE_PROP_SUPPORTED_MODES = 0, + DUAL_ROLE_PROP_MODE, + DUAL_ROLE_PROP_PR, + DUAL_ROLE_PROP_DR, + DUAL_ROLE_PROP_VCONN_SUPPLY, +}; + +struct dual_role_phy_instance; + +/* Description of typec port */ +struct dual_role_phy_desc { + /* /sys/class/dual_role_usb/<name>/ */ + const char *name; + enum dual_role_supported_modes supported_modes; + enum dual_role_property *properties; + size_t num_properties; + + /* Callback for "cat /sys/class/dual_role_usb/<name>/<property>" */ + int (*get_property)(struct dual_role_phy_instance *dual_role, + enum dual_role_property prop, + unsigned int *val); + /* Callback for "echo <value> > + * /sys/class/dual_role_usb/<name>/<property>" */ + int (*set_property)(struct dual_role_phy_instance *dual_role, + enum dual_role_property prop, + const unsigned int *val); + /* Decides whether userspace can change a specific property */ + int (*property_is_writeable)(struct dual_role_phy_instance *dual_role, + enum dual_role_property prop); +}; + +struct dual_role_phy_instance { + const struct dual_role_phy_desc *desc; + + /* Driver private data */ + void *drv_data; + + struct device dev; + struct work_struct changed_work; +}; + +#if IS_ENABLED(CONFIG_DUAL_ROLE_USB_INTF) +extern void dual_role_instance_changed(struct dual_role_phy_instance + *dual_role); +extern struct dual_role_phy_instance *__must_check +devm_dual_role_instance_register(struct device *parent, + const struct dual_role_phy_desc *desc); +extern void devm_dual_role_instance_unregister(struct device *dev, + struct dual_role_phy_instance + *dual_role); +extern int dual_role_get_property(struct dual_role_phy_instance *dual_role, + enum dual_role_property prop, + unsigned int *val); +extern int dual_role_set_property(struct dual_role_phy_instance *dual_role, + enum dual_role_property prop, + const unsigned int *val); +extern int dual_role_property_is_writeable(struct dual_role_phy_instance + *dual_role, + enum dual_role_property prop); +extern void *dual_role_get_drvdata(struct dual_role_phy_instance *dual_role); +#else /* CONFIG_DUAL_ROLE_USB_INTF */ +static inline void dual_role_instance_changed(struct dual_role_phy_instance + *dual_role){} +static inline struct dual_role_phy_instance *__must_check +devm_dual_role_instance_register(struct device *parent, + const struct dual_role_phy_desc *desc) +{ + return ERR_PTR(-ENOSYS); +} +static inline void devm_dual_role_instance_unregister(struct device *dev, + struct dual_role_phy_instance + *dual_role){} +static inline void *dual_role_get_drvdata(struct dual_role_phy_instance + *dual_role) +{ + return ERR_PTR(-ENOSYS); +} +#endif /* CONFIG_DUAL_ROLE_USB_INTF */ +#endif /* __LINUX_CLASS_DUAL_ROLE_H__ */ diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index a865698361c1..47603facd6d3 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -589,6 +589,7 @@ struct usb_function_instance { struct config_group group; struct list_head cfs_list; struct usb_function_driver *fd; + struct usb_function *f; int (*set_inst_name)(struct usb_function_instance *inst, const char *name); void (*free_func_inst)(struct usb_function_instance *inst); diff --git a/include/linux/usb/f_accessory.h b/include/linux/usb/f_accessory.h new file mode 100644 index 000000000000..ebe3c4d59309 --- /dev/null +++ b/include/linux/usb/f_accessory.h @@ -0,0 +1,23 @@ +/* + * Gadget Function Driver for Android USB accessories + * + * Copyright (C) 2011 Google, Inc. + * Author: Mike Lockwood <lockwood@android.com> + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#ifndef __LINUX_USB_F_ACCESSORY_H +#define __LINUX_USB_F_ACCESSORY_H + +#include <uapi/linux/usb/f_accessory.h> + +#endif /* __LINUX_USB_F_ACCESSORY_H */ diff --git a/include/linux/verification.h b/include/linux/verification.h index cfa4730d607a..60ea906b603f 100644 --- a/include/linux/verification.h +++ b/include/linux/verification.h @@ -32,9 +32,13 @@ enum key_being_used_for { }; extern const char *const key_being_used_for[NR__KEY_BEING_USED_FOR]; -#ifdef CONFIG_SYSTEM_DATA_VERIFICATION - struct key; +struct public_key_signature; + +extern int verify_signature_one(const struct public_key_signature *sig, + struct key *trusted_keys, const char *keyid); + +#ifdef CONFIG_SYSTEM_DATA_VERIFICATION extern int verify_pkcs7_signature(const void *data, size_t len, const void *raw_pkcs7, size_t pkcs7_len, diff --git a/include/linux/wakeup_reason.h b/include/linux/wakeup_reason.h new file mode 100644 index 000000000000..d84d8c301546 --- /dev/null +++ b/include/linux/wakeup_reason.h @@ -0,0 +1,32 @@ +/* + * include/linux/wakeup_reason.h + * + * Logs the reason which caused the kernel to resume + * from the suspend mode. + * + * Copyright (C) 2014 Google, Inc. + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _LINUX_WAKEUP_REASON_H +#define _LINUX_WAKEUP_REASON_H + +#define MAX_SUSPEND_ABORT_LEN 256 + +void log_wakeup_reason(int irq); +int check_wakeup_reason(int irq); + +#ifdef CONFIG_SUSPEND +void log_suspend_abort_reason(const char *fmt, ...); +#else +static inline void log_suspend_abort_reason(const char *fmt, ...) { } +#endif + +#endif /* _LINUX_WAKEUP_REASON_H */ diff --git a/include/linux/xattr.h b/include/linux/xattr.h index d70f77a4b62a..7f538d232179 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -30,10 +30,13 @@ struct xattr_handler { const char *prefix; int flags; /* fs private flags */ bool (*list)(struct dentry *dentry); - int (*get)(const struct xattr_handler *, struct dentry *dentry, + int (*get)(const struct xattr_handler *handler, struct dentry *dentry, struct inode *inode, const char *name, void *buffer, size_t size); - int (*set)(const struct xattr_handler *, struct dentry *dentry, + int (*__get)(const struct xattr_handler *handler, struct dentry *dentry, + struct inode *inode, const char *name, void *buffer, + size_t size); + int (*set)(const struct xattr_handler *handler, struct dentry *dentry, struct inode *inode, const char *name, const void *buffer, size_t size, int flags); }; diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h index 57a8e98f2708..2219cce81ca4 100644 --- a/include/linux/zsmalloc.h +++ b/include/linux/zsmalloc.h @@ -47,6 +47,8 @@ void zs_destroy_pool(struct zs_pool *pool); unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t flags); void zs_free(struct zs_pool *pool, unsigned long obj); +size_t zs_huge_class_size(struct zs_pool *pool); + void *zs_map_object(struct zs_pool *pool, unsigned long handle, enum zs_mapmode mm); void zs_unmap_object(struct zs_pool *pool, unsigned long handle); diff --git a/include/net/addrconf.h b/include/net/addrconf.h index f30ee99a1d72..4e5316a8fbf2 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -263,6 +263,8 @@ static inline bool ipv6_is_mld(struct sk_buff *skb, int nexthdr, int offset) void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao); +u32 addrconf_rt_table(const struct net_device *dev, u32 default_table); + /* * anycast prototypes (anycast.c) */ diff --git a/include/net/dst.h b/include/net/dst.h index 90bad764bc98..3a05256c484d 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -501,6 +501,14 @@ static inline struct dst_entry *xfrm_lookup(struct net *net, return dst_orig; } +static inline struct dst_entry * +xfrm_lookup_with_ifid(struct net *net, struct dst_entry *dst_orig, + const struct flowi *fl, const struct sock *sk, + int flags, u32 if_id) +{ + return dst_orig; +} + static inline struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, @@ -520,6 +528,12 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags); +struct dst_entry *xfrm_lookup_with_ifid(struct net *net, + struct dst_entry *dst_orig, + const struct flowi *fl, + const struct sock *sk, int flags, + u32 if_id); + struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags); diff --git a/include/net/ndisc.h b/include/net/ndisc.h index ddfbb591e2c5..35d7c887a5b9 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -38,6 +38,8 @@ enum { ND_OPT_RDNSS = 25, /* RFC5006 */ ND_OPT_DNSSL = 31, /* RFC6106 */ ND_OPT_6CO = 34, /* RFC6775 */ + ND_OPT_CAPTIVE_PORTAL = 37, /* RFC7710 */ + ND_OPT_PREF64 = 38, /* RFC-ietf-6man-ra-pref64-09 */ __ND_OPT_MAX }; diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index b6dbc80b6ed1..3f76ddab656e 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -285,7 +285,7 @@ static inline bool nf_ct_should_gc(const struct nf_conn *ct) struct kernel_param; -int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp); +int nf_conntrack_set_hashsize(const char *val, const struct kernel_param *kp); int nf_conntrack_hash_resize(unsigned int hashsize); extern struct hlist_nulls_head *nf_conntrack_hash; diff --git a/include/net/tcp.h b/include/net/tcp.h index 58e8e57787cf..12834f9f8272 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -277,6 +277,7 @@ extern int sysctl_tcp_autocorking; extern int sysctl_tcp_invalid_ratelimit; extern int sysctl_tcp_pacing_ss_ratio; extern int sysctl_tcp_pacing_ca_ratio; +extern int sysctl_tcp_default_init_rwnd; extern atomic_long_t tcp_memory_allocated; extern struct percpu_counter tcp_sockets_allocated; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 57b8b11cf7d4..453286adc79b 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -23,6 +23,7 @@ #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/flow.h> +#include <net/gro_cells.h> #include <linux/interrupt.h> @@ -147,6 +148,7 @@ struct xfrm_state { struct xfrm_id id; struct xfrm_selector sel; struct xfrm_mark mark; + u32 if_id; u32 tfcpad; u32 genid; @@ -166,7 +168,7 @@ struct xfrm_state { int header_len; int trailer_len; u32 extra_flags; - u32 output_mark; + struct xfrm_mark smark; } props; struct xfrm_lifetime_cfg lft; @@ -292,6 +294,13 @@ struct xfrm_replay { int (*overflow)(struct xfrm_state *x, struct sk_buff *skb); }; +struct xfrm_if_cb { + struct xfrm_if *(*decode_session)(struct sk_buff *skb); +}; + +void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb); +void xfrm_if_unregister_cb(void); + struct net_device; struct xfrm_type; struct xfrm_dst; @@ -572,6 +581,7 @@ struct xfrm_policy { atomic_t genid; u32 priority; u32 index; + u32 if_id; struct xfrm_mark mark; struct xfrm_selector selector; struct xfrm_lifetime_cfg lft; @@ -1005,6 +1015,22 @@ static inline void xfrm_dst_destroy(struct xfrm_dst *xdst) void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev); +struct xfrm_if_parms { + char name[IFNAMSIZ]; /* name of XFRM device */ + int link; /* ifindex of underlying L2 interface */ + u32 if_id; /* interface identifyer */ +}; + +struct xfrm_if { + struct xfrm_if __rcu *next; /* next interface in list */ + struct net_device *dev; /* virtual device associated with interface */ + struct net_device *phydev; /* physical device */ + struct net *net; /* netns for packet i/o */ + struct xfrm_if_parms p; /* interface parms */ + + struct gro_cells gro_cells; +}; + struct xfrm_offload { /* Output sequence number for replay protection on offloading. */ struct { @@ -1516,8 +1542,8 @@ struct xfrm_state *xfrm_state_find(const xfrm_address_t *daddr, const struct flowi *fl, struct xfrm_tmpl *tmpl, struct xfrm_policy *pol, int *err, - unsigned short family); -struct xfrm_state *xfrm_stateonly_find(struct net *net, u32 mark, + unsigned short family, u32 if_id); +struct xfrm_state *xfrm_stateonly_find(struct net *net, u32 mark, u32 if_id, xfrm_address_t *daddr, xfrm_address_t *saddr, unsigned short family, @@ -1674,20 +1700,20 @@ int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk, void *); void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net); int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl); -struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, +struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id, u8 type, int dir, struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx, int delete, int *err); -struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8, int dir, - u32 id, int delete, int *err); +struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id, u8, + int dir, u32 id, int delete, int *err); int xfrm_policy_flush(struct net *net, u8 type, bool task_valid); void xfrm_policy_hash_rebuild(struct net *net); u32 xfrm_get_acqseq(void); int verify_spi_info(u8 proto, u32 min, u32 max); int xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi); struct xfrm_state *xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, - u8 mode, u32 reqid, u8 proto, + u8 mode, u32 reqid, u32 if_id, u8 proto, const xfrm_address_t *daddr, const xfrm_address_t *saddr, int create, unsigned short family); @@ -1964,6 +1990,22 @@ static inline int xfrm_mark_put(struct sk_buff *skb, const struct xfrm_mark *m) return ret; } +static inline __u32 xfrm_smark_get(__u32 mark, struct xfrm_state *x) +{ + struct xfrm_mark *m = &x->props.smark; + + return (m->v & m->m) | (mark & ~m->m); +} + +static inline int xfrm_if_id_put(struct sk_buff *skb, __u32 if_id) +{ + int ret = 0; + + if (if_id) + ret = nla_put_u32(skb, XFRMA_IF_ID, if_id); + return ret; +} + static inline int xfrm_tunnel_check(struct sk_buff *skb, struct xfrm_state *x, unsigned int family) { diff --git a/include/trace/events/android_fs.h b/include/trace/events/android_fs.h new file mode 100644 index 000000000000..49509533d3fa --- /dev/null +++ b/include/trace/events/android_fs.h @@ -0,0 +1,65 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM android_fs + +#if !defined(_TRACE_ANDROID_FS_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_ANDROID_FS_H + +#include <linux/tracepoint.h> +#include <trace/events/android_fs_template.h> + +DEFINE_EVENT(android_fs_data_start_template, android_fs_dataread_start, + TP_PROTO(struct inode *inode, loff_t offset, int bytes, + pid_t pid, char *pathname, char *command), + TP_ARGS(inode, offset, bytes, pid, pathname, command)); + +DEFINE_EVENT(android_fs_data_end_template, android_fs_dataread_end, + TP_PROTO(struct inode *inode, loff_t offset, int bytes), + TP_ARGS(inode, offset, bytes)); + +DEFINE_EVENT(android_fs_data_start_template, android_fs_datawrite_start, + TP_PROTO(struct inode *inode, loff_t offset, int bytes, + pid_t pid, char *pathname, char *command), + TP_ARGS(inode, offset, bytes, pid, pathname, command)); + +DEFINE_EVENT(android_fs_data_end_template, android_fs_datawrite_end, + TP_PROTO(struct inode *inode, loff_t offset, int bytes), + TP_ARGS(inode, offset, bytes)); + +#endif /* _TRACE_ANDROID_FS_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> + +#ifndef ANDROID_FSTRACE_GET_PATHNAME +#define ANDROID_FSTRACE_GET_PATHNAME + +/* Sizes an on-stack array, so careful if sizing this up ! */ +#define MAX_TRACE_PATHBUF_LEN 256 + +static inline char * +android_fstrace_get_pathname(char *buf, int buflen, struct inode *inode) +{ + char *path; + struct dentry *d; + + /* + * d_obtain_alias() will either iput() if it locates an existing + * dentry or transfer the reference to the new dentry created. + * So get an extra reference here. + */ + ihold(inode); + d = d_obtain_alias(inode); + if (likely(!IS_ERR(d))) { + path = dentry_path_raw(d, buf, buflen); + if (unlikely(IS_ERR(path))) { + strcpy(buf, "ERROR"); + path = buf; + } + dput(d); + } else { + strcpy(buf, "ERROR"); + path = buf; + } + return path; +} +#endif diff --git a/include/trace/events/android_fs_template.h b/include/trace/events/android_fs_template.h new file mode 100644 index 000000000000..b23d17b56c63 --- /dev/null +++ b/include/trace/events/android_fs_template.h @@ -0,0 +1,64 @@ +#if !defined(_TRACE_ANDROID_FS_TEMPLATE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_ANDROID_FS_TEMPLATE_H + +#include <linux/tracepoint.h> + +DECLARE_EVENT_CLASS(android_fs_data_start_template, + TP_PROTO(struct inode *inode, loff_t offset, int bytes, + pid_t pid, char *pathname, char *command), + TP_ARGS(inode, offset, bytes, pid, pathname, command), + TP_STRUCT__entry( + __string(pathbuf, pathname); + __field(loff_t, offset); + __field(int, bytes); + __field(loff_t, i_size); + __string(cmdline, command); + __field(pid_t, pid); + __field(ino_t, ino); + ), + TP_fast_assign( + { + /* + * Replace the spaces in filenames and cmdlines + * because this screws up the tooling that parses + * the traces. + */ + __assign_str(pathbuf, pathname); + (void)strreplace(__get_str(pathbuf), ' ', '_'); + __entry->offset = offset; + __entry->bytes = bytes; + __entry->i_size = i_size_read(inode); + __assign_str(cmdline, command); + (void)strreplace(__get_str(cmdline), ' ', '_'); + __entry->pid = pid; + __entry->ino = inode->i_ino; + } + ), + TP_printk("entry_name %s, offset %llu, bytes %d, cmdline %s," + " pid %d, i_size %llu, ino %lu", + __get_str(pathbuf), __entry->offset, __entry->bytes, + __get_str(cmdline), __entry->pid, __entry->i_size, + (unsigned long) __entry->ino) +); + +DECLARE_EVENT_CLASS(android_fs_data_end_template, + TP_PROTO(struct inode *inode, loff_t offset, int bytes), + TP_ARGS(inode, offset, bytes), + TP_STRUCT__entry( + __field(ino_t, ino); + __field(loff_t, offset); + __field(int, bytes); + ), + TP_fast_assign( + { + __entry->ino = inode->i_ino; + __entry->offset = offset; + __entry->bytes = bytes; + } + ), + TP_printk("ino %lu, offset %llu, bytes %d", + (unsigned long) __entry->ino, + __entry->offset, __entry->bytes) +); + +#endif /* _TRACE_ANDROID_FS_TEMPLATE_H */ diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 7ab40491485b..2ce6af3235fb 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -137,6 +137,30 @@ TRACE_DEFINE_ENUM(CP_TRIMMED); { CP_UMOUNT, "Umount" }, \ { CP_TRIMMED, "Trimmed" }) +#define show_fsync_cpreason(type) \ + __print_symbolic(type, \ + { CP_NO_NEEDED, "no needed" }, \ + { CP_NON_REGULAR, "non regular" }, \ + { CP_HARDLINK, "hardlink" }, \ + { CP_SB_NEED_CP, "sb needs cp" }, \ + { CP_WRONG_PINO, "wrong pino" }, \ + { CP_NO_SPC_ROLL, "no space roll forward" }, \ + { CP_NODE_NEED_CP, "node needs cp" }, \ + { CP_FASTBOOT_MODE, "fastboot mode" }, \ + { CP_SPEC_LOG_NUM, "log type is 2" }, \ + { CP_RECOVER_DIR, "dir needs recovery" }) + +#define show_shutdown_mode(type) \ + __print_symbolic(type, \ + { F2FS_GOING_DOWN_FULLSYNC, "full sync" }, \ + { F2FS_GOING_DOWN_METASYNC, "meta sync" }, \ + { F2FS_GOING_DOWN_NOSYNC, "no sync" }, \ + { F2FS_GOING_DOWN_METAFLUSH, "meta flush" }, \ + { F2FS_GOING_DOWN_NEED_FSCK, "need fsck" }) + +struct f2fs_sb_info; +struct f2fs_io_info; +struct extent_info; struct victim_sel_policy; struct f2fs_map_blocks; @@ -211,14 +235,14 @@ DEFINE_EVENT(f2fs__inode, f2fs_sync_file_enter, TRACE_EVENT(f2fs_sync_file_exit, - TP_PROTO(struct inode *inode, int need_cp, int datasync, int ret), + TP_PROTO(struct inode *inode, int cp_reason, int datasync, int ret), - TP_ARGS(inode, need_cp, datasync, ret), + TP_ARGS(inode, cp_reason, datasync, ret), TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) - __field(int, need_cp) + __field(int, cp_reason) __field(int, datasync) __field(int, ret) ), @@ -226,15 +250,15 @@ TRACE_EVENT(f2fs_sync_file_exit, TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; - __entry->need_cp = need_cp; + __entry->cp_reason = cp_reason; __entry->datasync = datasync; __entry->ret = ret; ), - TP_printk("dev = (%d,%d), ino = %lu, checkpoint is %s, " + TP_printk("dev = (%d,%d), ino = %lu, cp_reason: %s, " "datasync = %d, ret = %d", show_dev_ino(__entry), - __entry->need_cp ? "needed" : "not needed", + show_fsync_cpreason(__entry->cp_reason), __entry->datasync, __entry->ret) ); @@ -521,6 +545,9 @@ TRACE_EVENT(f2fs_map_blocks, __field(block_t, m_lblk) __field(block_t, m_pblk) __field(unsigned int, m_len) + __field(unsigned int, m_flags) + __field(int, m_seg_type) + __field(bool, m_may_create) __field(int, ret) ), @@ -530,15 +557,22 @@ TRACE_EVENT(f2fs_map_blocks, __entry->m_lblk = map->m_lblk; __entry->m_pblk = map->m_pblk; __entry->m_len = map->m_len; + __entry->m_flags = map->m_flags; + __entry->m_seg_type = map->m_seg_type; + __entry->m_may_create = map->m_may_create; __entry->ret = ret; ), TP_printk("dev = (%d,%d), ino = %lu, file offset = %llu, " - "start blkaddr = 0x%llx, len = 0x%llx, err = %d", + "start blkaddr = 0x%llx, len = 0x%llx, flags = %u," + "seg_type = %d, may_create = %d, err = %d", show_dev_ino(__entry), (unsigned long long)__entry->m_lblk, (unsigned long long)__entry->m_pblk, (unsigned long long)__entry->m_len, + __entry->m_flags, + __entry->m_seg_type, + __entry->m_may_create, __entry->ret) ); @@ -729,6 +763,91 @@ TRACE_EVENT(f2fs_get_victim, __entry->free) ); +TRACE_EVENT(f2fs_lookup_start, + + TP_PROTO(struct inode *dir, struct dentry *dentry, unsigned int flags), + + TP_ARGS(dir, dentry, flags), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(const char *, name) + __field(unsigned int, flags) + ), + + TP_fast_assign( + __entry->dev = dir->i_sb->s_dev; + __entry->ino = dir->i_ino; + __entry->name = dentry->d_name.name; + __entry->flags = flags; + ), + + TP_printk("dev = (%d,%d), pino = %lu, name:%s, flags:%u", + show_dev_ino(__entry), + __entry->name, + __entry->flags) +); + +TRACE_EVENT(f2fs_lookup_end, + + TP_PROTO(struct inode *dir, struct dentry *dentry, nid_t ino, + int err), + + TP_ARGS(dir, dentry, ino, err), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(const char *, name) + __field(nid_t, cino) + __field(int, err) + ), + + TP_fast_assign( + __entry->dev = dir->i_sb->s_dev; + __entry->ino = dir->i_ino; + __entry->name = dentry->d_name.name; + __entry->cino = ino; + __entry->err = err; + ), + + TP_printk("dev = (%d,%d), pino = %lu, name:%s, ino:%u, err:%d", + show_dev_ino(__entry), + __entry->name, + __entry->cino, + __entry->err) +); + +TRACE_EVENT(f2fs_readdir, + + TP_PROTO(struct inode *dir, loff_t start_pos, loff_t end_pos, int err), + + TP_ARGS(dir, start_pos, end_pos, err), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(loff_t, start) + __field(loff_t, end) + __field(int, err) + ), + + TP_fast_assign( + __entry->dev = dir->i_sb->s_dev; + __entry->ino = dir->i_ino; + __entry->start = start_pos; + __entry->end = end_pos; + __entry->err = err; + ), + + TP_printk("dev = (%d,%d), ino = %lu, start_pos:%llu, end_pos:%llu, err:%d", + show_dev_ino(__entry), + __entry->start, + __entry->end, + __entry->err) +); + TRACE_EVENT(f2fs_fallocate, TP_PROTO(struct inode *inode, int mode, @@ -1287,6 +1406,13 @@ DEFINE_EVENT(f2fs_discard, f2fs_issue_discard, TP_ARGS(dev, blkstart, blklen) ); +DEFINE_EVENT(f2fs_discard, f2fs_remove_discard, + + TP_PROTO(struct block_device *dev, block_t blkstart, block_t blklen), + + TP_ARGS(dev, blkstart, blklen) +); + TRACE_EVENT(f2fs_issue_reset_zone, TP_PROTO(struct block_device *dev, block_t blkstart), @@ -1512,6 +1638,30 @@ DEFINE_EVENT(f2fs_sync_dirty_inodes, f2fs_sync_dirty_inodes_exit, TP_ARGS(sb, type, count) ); +TRACE_EVENT(f2fs_shutdown, + + TP_PROTO(struct f2fs_sb_info *sbi, unsigned int mode, int ret), + + TP_ARGS(sbi, mode, ret), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(unsigned int, mode) + __field(int, ret) + ), + + TP_fast_assign( + __entry->dev = sbi->sb->s_dev; + __entry->mode = mode; + __entry->ret = ret; + ), + + TP_printk("dev = (%d,%d), mode: %s, ret:%d", + show_dev(__entry->dev), + show_shutdown_mode(__entry->mode), + __entry->ret) +); + #endif /* _TRACE_F2FS_H */ /* This part must be outside protection */ diff --git a/include/trace/events/gpu.h b/include/trace/events/gpu.h new file mode 100644 index 000000000000..7e15cdfafe5a --- /dev/null +++ b/include/trace/events/gpu.h @@ -0,0 +1,143 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM gpu + +#if !defined(_TRACE_GPU_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_GPU_H + +#include <linux/tracepoint.h> +#include <linux/time.h> + +#define show_secs_from_ns(ns) \ + ({ \ + u64 t = ns + (NSEC_PER_USEC / 2); \ + do_div(t, NSEC_PER_SEC); \ + t; \ + }) + +#define show_usecs_from_ns(ns) \ + ({ \ + u64 t = ns + (NSEC_PER_USEC / 2) ; \ + u32 rem; \ + do_div(t, NSEC_PER_USEC); \ + rem = do_div(t, USEC_PER_SEC); \ + }) + +/* + * The gpu_sched_switch event indicates that a switch from one GPU context to + * another occurred on one of the GPU hardware blocks. + * + * The gpu_name argument identifies the GPU hardware block. Each independently + * scheduled GPU hardware block should have a different name. This may be used + * in different ways for different GPUs. For example, if a GPU includes + * multiple processing cores it may use names "GPU 0", "GPU 1", etc. If a GPU + * includes a separately scheduled 2D and 3D hardware block, it might use the + * names "2D" and "3D". + * + * The timestamp argument is the timestamp at which the switch occurred on the + * GPU. These timestamps are in units of nanoseconds and must use + * approximately the same time as sched_clock, though they need not come from + * any CPU clock. The timestamps for a single hardware block must be + * monotonically nondecreasing. This means that if a variable compensation + * offset is used to translate from some other clock to the sched_clock, then + * care must be taken when increasing that offset, and doing so may result in + * multiple events with the same timestamp. + * + * The next_ctx_id argument identifies the next context that was running on + * the GPU hardware block. A value of 0 indicates that the hardware block + * will be idle. + * + * The next_prio argument indicates the priority of the next context at the + * time of the event. The exact numeric values may mean different things for + * different GPUs, but they should follow the rule that lower values indicate a + * higher priority. + * + * The next_job_id argument identifies the batch of work that the GPU will be + * working on. This should correspond to a job_id that was previously traced + * as a gpu_job_enqueue event when the batch of work was created. + */ +TRACE_EVENT(gpu_sched_switch, + + TP_PROTO(const char *gpu_name, u64 timestamp, + u32 next_ctx_id, s32 next_prio, u32 next_job_id), + + TP_ARGS(gpu_name, timestamp, next_ctx_id, next_prio, next_job_id), + + TP_STRUCT__entry( + __string( gpu_name, gpu_name ) + __field( u64, timestamp ) + __field( u32, next_ctx_id ) + __field( s32, next_prio ) + __field( u32, next_job_id ) + ), + + TP_fast_assign( + __assign_str(gpu_name, gpu_name); + __entry->timestamp = timestamp; + __entry->next_ctx_id = next_ctx_id; + __entry->next_prio = next_prio; + __entry->next_job_id = next_job_id; + ), + + TP_printk("gpu_name=%s ts=%llu.%06lu next_ctx_id=%lu next_prio=%ld " + "next_job_id=%lu", + __get_str(gpu_name), + (unsigned long long)show_secs_from_ns(__entry->timestamp), + (unsigned long)show_usecs_from_ns(__entry->timestamp), + (unsigned long)__entry->next_ctx_id, + (long)__entry->next_prio, + (unsigned long)__entry->next_job_id) +); + +/* + * The gpu_job_enqueue event indicates that a batch of work has been queued up + * to be processed by the GPU. This event is not intended to indicate that + * the batch of work has been submitted to the GPU hardware, but rather that + * it has been submitted to the GPU kernel driver. + * + * This event should be traced on the thread that initiated the work being + * queued. For example, if a batch of work is submitted to the kernel by a + * userland thread, the event should be traced on that thread. + * + * The ctx_id field identifies the GPU context in which the batch of work + * being queued is to be run. + * + * The job_id field identifies the batch of work being queued within the given + * GPU context. The first batch of work submitted for a given GPU context + * should have a job_id of 0, and each subsequent batch of work should + * increment the job_id by 1. + * + * The type field identifies the type of the job being enqueued. The job + * types may be different for different GPU hardware. For example, a GPU may + * differentiate between "2D", "3D", and "compute" jobs. + */ +TRACE_EVENT(gpu_job_enqueue, + + TP_PROTO(u32 ctx_id, u32 job_id, const char *type), + + TP_ARGS(ctx_id, job_id, type), + + TP_STRUCT__entry( + __field( u32, ctx_id ) + __field( u32, job_id ) + __string( type, type ) + ), + + TP_fast_assign( + __entry->ctx_id = ctx_id; + __entry->job_id = job_id; + __assign_str(type, type); + ), + + TP_printk("ctx_id=%lu job_id=%lu type=%s", + (unsigned long)__entry->ctx_id, + (unsigned long)__entry->job_id, + __get_str(type)) +); + +#undef show_secs_from_ns +#undef show_usecs_from_ns + +#endif /* _TRACE_GPU_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index 72162f3a03fa..40b9cc3bfaf9 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -89,6 +89,7 @@ {1UL << PG_dirty, "dirty" }, \ {1UL << PG_lru, "lru" }, \ {1UL << PG_active, "active" }, \ + {1UL << PG_workingset, "workingset" }, \ {1UL << PG_slab, "slab" }, \ {1UL << PG_owner_priv_1, "owner_priv_1" }, \ {1UL << PG_arch_1, "arch_1" }, \ diff --git a/include/trace/events/net.h b/include/trace/events/net.h index 9c886739246a..f1a300c8ef85 100644 --- a/include/trace/events/net.h +++ b/include/trace/events/net.h @@ -58,7 +58,7 @@ TRACE_EVENT(net_dev_start_xmit, __entry->gso_type = skb_shinfo(skb)->gso_type; ), - TP_printk("dev=%s queue_mapping=%u skbaddr=%p vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d len=%u data_len=%u network_offset=%d transport_offset_valid=%d transport_offset=%d tx_flags=%d gso_size=%d gso_segs=%d gso_type=%#x", + TP_printk("dev=%s queue_mapping=%u skbaddr=%pK vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d len=%u data_len=%u network_offset=%d transport_offset_valid=%d transport_offset=%d tx_flags=%d gso_size=%d gso_segs=%d gso_type=%#x", __get_str(name), __entry->queue_mapping, __entry->skbaddr, __entry->vlan_tagged, __entry->vlan_proto, __entry->vlan_tci, __entry->protocol, __entry->ip_summed, __entry->len, @@ -91,7 +91,7 @@ TRACE_EVENT(net_dev_xmit, __assign_str(name, dev->name); ), - TP_printk("dev=%s skbaddr=%p len=%u rc=%d", + TP_printk("dev=%s skbaddr=%pK len=%u rc=%d", __get_str(name), __entry->skbaddr, __entry->len, __entry->rc) ); @@ -113,7 +113,7 @@ DECLARE_EVENT_CLASS(net_dev_template, __assign_str(name, skb->dev->name); ), - TP_printk("dev=%s skbaddr=%p len=%u", + TP_printk("dev=%s skbaddr=%pK len=%u", __get_str(name), __entry->skbaddr, __entry->len) ) @@ -192,7 +192,7 @@ DECLARE_EVENT_CLASS(net_dev_rx_verbose_template, __entry->gso_type = skb_shinfo(skb)->gso_type; ), - TP_printk("dev=%s napi_id=%#x queue_mapping=%u skbaddr=%p vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d hash=0x%08x l4_hash=%d len=%u data_len=%u truesize=%u mac_header_valid=%d mac_header=%d nr_frags=%d gso_size=%d gso_type=%#x", + TP_printk("dev=%s napi_id=%#x queue_mapping=%u skbaddr=%pK vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d hash=0x%08x l4_hash=%d len=%u data_len=%u truesize=%u mac_header_valid=%d mac_header=%d nr_frags=%d gso_size=%d gso_type=%#x", __get_str(name), __entry->napi_id, __entry->queue_mapping, __entry->skbaddr, __entry->vlan_tagged, __entry->vlan_proto, __entry->vlan_tci, __entry->protocol, __entry->ip_summed, diff --git a/include/trace/events/power.h b/include/trace/events/power.h index 908977d69783..3eac1f9f66b9 100644 --- a/include/trace/events/power.h +++ b/include/trace/events/power.h @@ -148,6 +148,31 @@ DEFINE_EVENT(cpu, cpu_frequency, TP_ARGS(frequency, cpu_id) ); +TRACE_EVENT(cpu_frequency_limits, + + TP_PROTO(unsigned int max_freq, unsigned int min_freq, + unsigned int cpu_id), + + TP_ARGS(max_freq, min_freq, cpu_id), + + TP_STRUCT__entry( + __field( u32, min_freq ) + __field( u32, max_freq ) + __field( u32, cpu_id ) + ), + + TP_fast_assign( + __entry->min_freq = min_freq; + __entry->max_freq = max_freq; + __entry->cpu_id = cpu_id; + ), + + TP_printk("min=%lu max=%lu cpu_id=%lu", + (unsigned long)__entry->min_freq, + (unsigned long)__entry->max_freq, + (unsigned long)__entry->cpu_id) +); + TRACE_EVENT(device_pm_callback_start, TP_PROTO(struct device *dev, const char *pm_ops, int event), @@ -301,6 +326,25 @@ DEFINE_EVENT(clock, clock_set_rate, TP_ARGS(name, state, cpu_id) ); +TRACE_EVENT(clock_set_parent, + + TP_PROTO(const char *name, const char *parent_name), + + TP_ARGS(name, parent_name), + + TP_STRUCT__entry( + __string( name, name ) + __string( parent_name, parent_name ) + ), + + TP_fast_assign( + __assign_str(name, name); + __assign_str(parent_name, parent_name); + ), + + TP_printk("%s parent=%s", __get_str(name), __get_str(parent_name)) +); + /* * The power domain events are used for power domains transitions */ diff --git a/include/trace/events/preemptirq.h b/include/trace/events/preemptirq.h new file mode 100644 index 000000000000..9c4eb33c5a1d --- /dev/null +++ b/include/trace/events/preemptirq.h @@ -0,0 +1,73 @@ +#ifdef CONFIG_PREEMPTIRQ_EVENTS + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM preemptirq + +#if !defined(_TRACE_PREEMPTIRQ_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_PREEMPTIRQ_H + +#include <linux/ktime.h> +#include <linux/tracepoint.h> +#include <linux/string.h> +#include <asm/sections.h> + +DECLARE_EVENT_CLASS(preemptirq_template, + + TP_PROTO(unsigned long ip, unsigned long parent_ip), + + TP_ARGS(ip, parent_ip), + + TP_STRUCT__entry( + __field(u32, caller_offs) + __field(u32, parent_offs) + ), + + TP_fast_assign( + __entry->caller_offs = (u32)(ip - (unsigned long)_stext); + __entry->parent_offs = (u32)(parent_ip - (unsigned long)_stext); + ), + + TP_printk("caller=%pF parent=%pF", + (void *)((unsigned long)(_stext) + __entry->caller_offs), + (void *)((unsigned long)(_stext) + __entry->parent_offs)) +); + +#ifndef CONFIG_PROVE_LOCKING +DEFINE_EVENT(preemptirq_template, irq_disable, + TP_PROTO(unsigned long ip, unsigned long parent_ip), + TP_ARGS(ip, parent_ip)); + +DEFINE_EVENT(preemptirq_template, irq_enable, + TP_PROTO(unsigned long ip, unsigned long parent_ip), + TP_ARGS(ip, parent_ip)); +#endif + +#ifdef CONFIG_DEBUG_PREEMPT +DEFINE_EVENT(preemptirq_template, preempt_disable, + TP_PROTO(unsigned long ip, unsigned long parent_ip), + TP_ARGS(ip, parent_ip)); + +DEFINE_EVENT(preemptirq_template, preempt_enable, + TP_PROTO(unsigned long ip, unsigned long parent_ip), + TP_ARGS(ip, parent_ip)); +#endif + +#endif /* _TRACE_PREEMPTIRQ_H */ + +#include <trace/define_trace.h> + +#endif /* !CONFIG_PREEMPTIRQ_EVENTS */ + +#if !defined(CONFIG_PREEMPTIRQ_EVENTS) || defined(CONFIG_PROVE_LOCKING) +#define trace_irq_enable(...) +#define trace_irq_disable(...) +#define trace_irq_enable_rcuidle(...) +#define trace_irq_disable_rcuidle(...) +#endif + +#if !defined(CONFIG_PREEMPTIRQ_EVENTS) || !defined(CONFIG_DEBUG_PREEMPT) +#define trace_preempt_enable(...) +#define trace_preempt_disable(...) +#define trace_preempt_enable_rcuidle(...) +#define trace_preempt_disable_rcuidle(...) +#endif diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 18197e0bb510..30145bcd1a32 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -241,7 +241,7 @@ DECLARE_EVENT_CLASS(sched_process_template, DEFINE_EVENT(sched_process_template, sched_process_free, TP_PROTO(struct task_struct *p), TP_ARGS(p)); - + /* * Tracepoint for a task exiting: @@ -396,6 +396,30 @@ DEFINE_EVENT(sched_stat_template, sched_stat_blocked, TP_ARGS(tsk, delay)); /* + * Tracepoint for recording the cause of uninterruptible sleep. + */ +TRACE_EVENT(sched_blocked_reason, + + TP_PROTO(struct task_struct *tsk), + + TP_ARGS(tsk), + + TP_STRUCT__entry( + __field( pid_t, pid ) + __field( void*, caller ) + __field( bool, io_wait ) + ), + + TP_fast_assign( + __entry->pid = tsk->pid; + __entry->caller = (void*)get_wchan(tsk); + __entry->io_wait = tsk->in_iowait; + ), + + TP_printk("pid=%d iowait=%d caller=%pS", __entry->pid, __entry->io_wait, __entry->caller) +); + +/* * Tracepoint for accounting runtime (time the task is executing * on a CPU). */ @@ -587,6 +611,621 @@ TRACE_EVENT(sched_wake_idle_without_ipi, TP_printk("cpu=%d", __entry->cpu) ); + +#ifdef CONFIG_SMP +#ifdef CREATE_TRACE_POINTS +static inline +int __trace_sched_cpu(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ +#ifdef CONFIG_FAIR_GROUP_SCHED + struct rq *rq = cfs_rq ? cfs_rq->rq : NULL; +#else + struct rq *rq = cfs_rq ? container_of(cfs_rq, struct rq, cfs) : NULL; +#endif + return rq ? cpu_of(rq) + : task_cpu((container_of(se, struct task_struct, se))); +} + +static inline +int __trace_sched_path(struct cfs_rq *cfs_rq, char *path, int len) +{ +#ifdef CONFIG_FAIR_GROUP_SCHED + int l = path ? len : 0; + + if (cfs_rq && task_group_is_autogroup(cfs_rq->tg)) + return autogroup_path(cfs_rq->tg, path, l) + 1; + else if (cfs_rq && cfs_rq->tg->css.cgroup) + return cgroup_path(cfs_rq->tg->css.cgroup, path, l) + 1; +#endif + if (path) + strcpy(path, "(null)"); + + return strlen("(null)"); +} + +static inline +struct cfs_rq *__trace_sched_group_cfs_rq(struct sched_entity *se) +{ +#ifdef CONFIG_FAIR_GROUP_SCHED + return se->my_q; +#else + return NULL; +#endif +} +#endif /* CREATE_TRACE_POINTS */ + +#ifdef CONFIG_SCHED_WALT +extern unsigned int sysctl_sched_use_walt_cpu_util; +extern unsigned int sysctl_sched_use_walt_task_util; +extern unsigned int walt_ravg_window; +extern bool walt_disabled; + +#define walt_util(util_var, demand_sum) {\ + u64 sum = demand_sum << SCHED_CAPACITY_SHIFT;\ + do_div(sum, walt_ravg_window);\ + util_var = (typeof(util_var))sum;\ + } +#endif + +/* + * Tracepoint for cfs_rq load tracking: + */ +TRACE_EVENT(sched_load_cfs_rq, + + TP_PROTO(struct cfs_rq *cfs_rq), + + TP_ARGS(cfs_rq), + + TP_STRUCT__entry( + __field( int, cpu ) + __dynamic_array(char, path, + __trace_sched_path(cfs_rq, NULL, 0) ) + __field( unsigned long, load ) + __field( unsigned long, util ) + __field( unsigned long, util_pelt ) + __field( unsigned long, util_walt ) + ), + + TP_fast_assign( + __entry->cpu = __trace_sched_cpu(cfs_rq, NULL); + __trace_sched_path(cfs_rq, __get_dynamic_array(path), + __get_dynamic_array_len(path)); + __entry->load = cfs_rq->runnable_load_avg; + __entry->util = cfs_rq->avg.util_avg; + __entry->util_pelt = cfs_rq->avg.util_avg; + __entry->util_walt = 0; +#ifdef CONFIG_SCHED_WALT + if (&cfs_rq->rq->cfs == cfs_rq) { + walt_util(__entry->util_walt, + cfs_rq->rq->prev_runnable_sum); + if (!walt_disabled && sysctl_sched_use_walt_cpu_util) + __entry->util = __entry->util_walt; + } +#endif + ), + + TP_printk("cpu=%d path=%s load=%lu util=%lu util_pelt=%lu util_walt=%lu", + __entry->cpu, __get_str(path), __entry->load, __entry->util, + __entry->util_pelt, __entry->util_walt) +); + +/* + * Tracepoint for rt_rq load tracking: + */ +struct rt_rq; + +TRACE_EVENT(sched_load_rt_rq, + + TP_PROTO(int cpu, struct rt_rq *rt_rq), + + TP_ARGS(cpu, rt_rq), + + TP_STRUCT__entry( + __field( int, cpu ) + __field( unsigned long, util ) + ), + + TP_fast_assign( + __entry->cpu = cpu; + __entry->util = rt_rq->avg.util_avg; + ), + + TP_printk("cpu=%d util=%lu", __entry->cpu, + __entry->util) +); + +/* + * Tracepoint for sched_entity load tracking: + */ +TRACE_EVENT(sched_load_se, + + TP_PROTO(struct sched_entity *se), + + TP_ARGS(se), + + TP_STRUCT__entry( + __field( int, cpu ) + __dynamic_array(char, path, + __trace_sched_path(__trace_sched_group_cfs_rq(se), NULL, 0) ) + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( unsigned long, load ) + __field( unsigned long, util ) + __field( unsigned long, util_pelt ) + __field( unsigned long, util_walt ) + ), + + TP_fast_assign( + struct cfs_rq *gcfs_rq = __trace_sched_group_cfs_rq(se); + struct task_struct *p = gcfs_rq ? NULL + : container_of(se, struct task_struct, se); + + __entry->cpu = __trace_sched_cpu(gcfs_rq, se); + __trace_sched_path(gcfs_rq, __get_dynamic_array(path), + __get_dynamic_array_len(path)); + memcpy(__entry->comm, p ? p->comm : "(null)", + p ? TASK_COMM_LEN : sizeof("(null)")); + __entry->pid = p ? p->pid : -1; + __entry->load = se->avg.load_avg; + __entry->util = se->avg.util_avg; + __entry->util_pelt = __entry->util; + __entry->util_walt = 0; +#ifdef CONFIG_SCHED_WALT + if (!se->my_q) { + struct task_struct *p = container_of(se, struct task_struct, se); + walt_util(__entry->util_walt, p->ravg.demand); + if (!walt_disabled && sysctl_sched_use_walt_task_util) + __entry->util = __entry->util_walt; + } +#endif + ), + + TP_printk("cpu=%d path=%s comm=%s pid=%d load=%lu util=%lu util_pelt=%lu util_walt=%lu", + __entry->cpu, __get_str(path), __entry->comm, + __entry->pid, __entry->load, __entry->util, + __entry->util_pelt, __entry->util_walt) +); + +/* + * Tracepoint for task_group load tracking: + */ +#ifdef CONFIG_FAIR_GROUP_SCHED +TRACE_EVENT(sched_load_tg, + + TP_PROTO(struct cfs_rq *cfs_rq), + + TP_ARGS(cfs_rq), + + TP_STRUCT__entry( + __field( int, cpu ) + __dynamic_array(char, path, + __trace_sched_path(cfs_rq, NULL, 0) ) + __field( long, load ) + ), + + TP_fast_assign( + __entry->cpu = cfs_rq->rq->cpu; + __trace_sched_path(cfs_rq, __get_dynamic_array(path), + __get_dynamic_array_len(path)); + __entry->load = atomic_long_read(&cfs_rq->tg->load_avg); + ), + + TP_printk("cpu=%d path=%s load=%ld", __entry->cpu, __get_str(path), + __entry->load) +); +#endif /* CONFIG_FAIR_GROUP_SCHED */ + +/* + * Tracepoint for accounting CPU boosted utilization + */ +TRACE_EVENT(sched_boost_cpu, + + TP_PROTO(int cpu, unsigned long util, long margin), + + TP_ARGS(cpu, util, margin), + + TP_STRUCT__entry( + __field( int, cpu ) + __field( unsigned long, util ) + __field(long, margin ) + ), + + TP_fast_assign( + __entry->cpu = cpu; + __entry->util = util; + __entry->margin = margin; + ), + + TP_printk("cpu=%d util=%lu margin=%ld", + __entry->cpu, + __entry->util, + __entry->margin) +); + +/* + * Tracepoint for schedtune_tasks_update + */ +TRACE_EVENT(sched_tune_tasks_update, + + TP_PROTO(struct task_struct *tsk, int cpu, int tasks, int idx, + int boost, int max_boost, u64 group_ts), + + TP_ARGS(tsk, cpu, tasks, idx, boost, max_boost, group_ts), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( int, cpu ) + __field( int, tasks ) + __field( int, idx ) + __field( int, boost ) + __field( int, max_boost ) + __field( u64, group_ts ) + ), + + TP_fast_assign( + memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); + __entry->pid = tsk->pid; + __entry->cpu = cpu; + __entry->tasks = tasks; + __entry->idx = idx; + __entry->boost = boost; + __entry->max_boost = max_boost; + __entry->group_ts = group_ts; + ), + + TP_printk("pid=%d comm=%s " + "cpu=%d tasks=%d idx=%d boost=%d max_boost=%d timeout=%llu", + __entry->pid, __entry->comm, + __entry->cpu, __entry->tasks, __entry->idx, + __entry->boost, __entry->max_boost, + __entry->group_ts) +); + +/* + * Tracepoint for schedtune_boostgroup_update + */ +TRACE_EVENT(sched_tune_boostgroup_update, + + TP_PROTO(int cpu, int variation, int max_boost), + + TP_ARGS(cpu, variation, max_boost), + + TP_STRUCT__entry( + __field( int, cpu ) + __field( int, variation ) + __field( int, max_boost ) + ), + + TP_fast_assign( + __entry->cpu = cpu; + __entry->variation = variation; + __entry->max_boost = max_boost; + ), + + TP_printk("cpu=%d variation=%d max_boost=%d", + __entry->cpu, __entry->variation, __entry->max_boost) +); + +/* + * Tracepoint for accounting task boosted utilization + */ +TRACE_EVENT(sched_boost_task, + + TP_PROTO(struct task_struct *tsk, unsigned long util, long margin), + + TP_ARGS(tsk, util, margin), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( unsigned long, util ) + __field( long, margin ) + + ), + + TP_fast_assign( + memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); + __entry->pid = tsk->pid; + __entry->util = util; + __entry->margin = margin; + ), + + TP_printk("comm=%s pid=%d util=%lu margin=%ld", + __entry->comm, __entry->pid, + __entry->util, + __entry->margin) +); + +/* + * Tracepoint for system overutilized flag + */ +struct sched_domain; +TRACE_EVENT_CONDITION(sched_overutilized, + + TP_PROTO(struct sched_domain *sd, bool was_overutilized, bool overutilized), + + TP_ARGS(sd, was_overutilized, overutilized), + + TP_CONDITION(overutilized != was_overutilized), + + TP_STRUCT__entry( + __field( bool, overutilized ) + __array( char, cpulist , 32 ) + ), + + TP_fast_assign( + __entry->overutilized = overutilized; + scnprintf(__entry->cpulist, sizeof(__entry->cpulist), "%*pbl", cpumask_pr_args(sched_domain_span(sd))); + ), + + TP_printk("overutilized=%d sd_span=%s", + __entry->overutilized ? 1 : 0, __entry->cpulist) +); + +/* + * Tracepoint for find_best_target + */ +TRACE_EVENT(sched_find_best_target, + + TP_PROTO(struct task_struct *tsk, bool prefer_idle, + unsigned long min_util, int start_cpu, + int best_idle, int best_active, int target), + + TP_ARGS(tsk, prefer_idle, min_util, start_cpu, + best_idle, best_active, target), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( unsigned long, min_util ) + __field( bool, prefer_idle ) + __field( int, start_cpu ) + __field( int, best_idle ) + __field( int, best_active ) + __field( int, target ) + ), + + TP_fast_assign( + memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); + __entry->pid = tsk->pid; + __entry->min_util = min_util; + __entry->prefer_idle = prefer_idle; + __entry->start_cpu = start_cpu; + __entry->best_idle = best_idle; + __entry->best_active = best_active; + __entry->target = target; + ), + + TP_printk("pid=%d comm=%s prefer_idle=%d start_cpu=%d " + "best_idle=%d best_active=%d target=%d", + __entry->pid, __entry->comm, + __entry->prefer_idle, __entry->start_cpu, + __entry->best_idle, __entry->best_active, + __entry->target) +); + +/* + * Tracepoint for tasks' estimated utilization. + */ +TRACE_EVENT(sched_util_est_task, + + TP_PROTO(struct task_struct *tsk, struct sched_avg *avg), + + TP_ARGS(tsk, avg), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( int, cpu ) + __field( unsigned int, util_avg ) + __field( unsigned int, est_enqueued ) + __field( unsigned int, est_ewma ) + ), + + TP_fast_assign( + memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN); + __entry->pid = tsk->pid; + __entry->cpu = task_cpu(tsk); + __entry->util_avg = avg->util_avg; + __entry->est_enqueued = avg->util_est.enqueued; + __entry->est_ewma = avg->util_est.ewma; + ), + + TP_printk("comm=%s pid=%d cpu=%d util_avg=%u util_est_ewma=%u util_est_enqueued=%u", + __entry->comm, + __entry->pid, + __entry->cpu, + __entry->util_avg, + __entry->est_ewma, + __entry->est_enqueued) +); + +/* + * Tracepoint for root cfs_rq's estimated utilization. + */ +TRACE_EVENT(sched_util_est_cpu, + + TP_PROTO(int cpu, struct cfs_rq *cfs_rq), + + TP_ARGS(cpu, cfs_rq), + + TP_STRUCT__entry( + __field( int, cpu ) + __field( unsigned int, util_avg ) + __field( unsigned int, util_est_enqueued ) + ), + + TP_fast_assign( + __entry->cpu = cpu; + __entry->util_avg = cfs_rq->avg.util_avg; + __entry->util_est_enqueued = cfs_rq->avg.util_est.enqueued; + ), + + TP_printk("cpu=%d util_avg=%u util_est_enqueued=%u", + __entry->cpu, + __entry->util_avg, + __entry->util_est_enqueued) +); + +#ifdef CONFIG_SCHED_WALT +struct rq; + +TRACE_EVENT(walt_update_task_ravg, + + TP_PROTO(struct task_struct *p, struct rq *rq, int evt, + u64 wallclock, u64 irqtime), + + TP_ARGS(p, rq, evt, wallclock, irqtime), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field( pid_t, cur_pid ) + __field( u64, wallclock ) + __field( u64, mark_start ) + __field( u64, delta_m ) + __field( u64, win_start ) + __field( u64, delta ) + __field( u64, irqtime ) + __array( char, evt, 16 ) + __field(unsigned int, demand ) + __field(unsigned int, sum ) + __field( int, cpu ) + __field( u64, cs ) + __field( u64, ps ) + __field( u32, curr_window ) + __field( u32, prev_window ) + __field( u64, nt_cs ) + __field( u64, nt_ps ) + __field( u32, active_windows ) + ), + + TP_fast_assign( + static const char* walt_event_names[] = + { + "PUT_PREV_TASK", + "PICK_NEXT_TASK", + "TASK_WAKE", + "TASK_MIGRATE", + "TASK_UPDATE", + "IRQ_UPDATE" + }; + __entry->wallclock = wallclock; + __entry->win_start = rq->window_start; + __entry->delta = (wallclock - rq->window_start); + strcpy(__entry->evt, walt_event_names[evt]); + __entry->cpu = rq->cpu; + __entry->cur_pid = rq->curr->pid; + memcpy(__entry->comm, p->comm, TASK_COMM_LEN); + __entry->pid = p->pid; + __entry->mark_start = p->ravg.mark_start; + __entry->delta_m = (wallclock - p->ravg.mark_start); + __entry->demand = p->ravg.demand; + __entry->sum = p->ravg.sum; + __entry->irqtime = irqtime; + __entry->cs = rq->curr_runnable_sum; + __entry->ps = rq->prev_runnable_sum; + __entry->curr_window = p->ravg.curr_window; + __entry->prev_window = p->ravg.prev_window; + __entry->nt_cs = rq->nt_curr_runnable_sum; + __entry->nt_ps = rq->nt_prev_runnable_sum; + __entry->active_windows = p->ravg.active_windows; + ), + + TP_printk("wallclock=%llu window_start=%llu delta=%llu event=%s cpu=%d cur_pid=%d pid=%d comm=%s" + " mark_start=%llu delta=%llu demand=%u sum=%u irqtime=%llu" + " curr_runnable_sum=%llu prev_runnable_sum=%llu cur_window=%u" + " prev_window=%u nt_curr_runnable_sum=%llu nt_prev_runnable_sum=%llu active_windows=%u", + __entry->wallclock, __entry->win_start, __entry->delta, + __entry->evt, __entry->cpu, __entry->cur_pid, + __entry->pid, __entry->comm, __entry->mark_start, + __entry->delta_m, __entry->demand, + __entry->sum, __entry->irqtime, + __entry->cs, __entry->ps, + __entry->curr_window, __entry->prev_window, + __entry->nt_cs, __entry->nt_ps, + __entry->active_windows + ) +); + +TRACE_EVENT(walt_update_history, + + TP_PROTO(struct rq *rq, struct task_struct *p, u32 runtime, int samples, + int evt), + + TP_ARGS(rq, p, runtime, samples, evt), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __field(unsigned int, runtime ) + __field( int, samples ) + __field( int, evt ) + __field( u64, demand ) + __field(unsigned int, walt_avg ) + __field(unsigned int, pelt_avg ) + __array( u32, hist, RAVG_HIST_SIZE_MAX) + __field( int, cpu ) + ), + + TP_fast_assign( + memcpy(__entry->comm, p->comm, TASK_COMM_LEN); + __entry->pid = p->pid; + __entry->runtime = runtime; + __entry->samples = samples; + __entry->evt = evt; + __entry->demand = p->ravg.demand; + walt_util(__entry->walt_avg,__entry->demand); + __entry->pelt_avg = p->se.avg.util_avg; + memcpy(__entry->hist, p->ravg.sum_history, + RAVG_HIST_SIZE_MAX * sizeof(u32)); + __entry->cpu = rq->cpu; + ), + + TP_printk("pid=%d comm=%s runtime=%u samples=%d event=%d demand=%llu ravg_window=%u" + " walt=%u pelt=%u hist0=%u hist1=%u hist2=%u hist3=%u hist4=%u cpu=%d", + __entry->pid, __entry->comm, + __entry->runtime, __entry->samples, __entry->evt, + __entry->demand, + walt_ravg_window, + __entry->walt_avg, + __entry->pelt_avg, + __entry->hist[0], __entry->hist[1], + __entry->hist[2], __entry->hist[3], + __entry->hist[4], __entry->cpu) +); + +TRACE_EVENT(walt_migration_update_sum, + + TP_PROTO(struct rq *rq, struct task_struct *p), + + TP_ARGS(rq, p), + + TP_STRUCT__entry( + __field(int, cpu ) + __field(int, pid ) + __field( u64, cs ) + __field( u64, ps ) + __field( s64, nt_cs ) + __field( s64, nt_ps ) + ), + + TP_fast_assign( + __entry->cpu = cpu_of(rq); + __entry->cs = rq->curr_runnable_sum; + __entry->ps = rq->prev_runnable_sum; + __entry->nt_cs = (s64)rq->nt_curr_runnable_sum; + __entry->nt_ps = (s64)rq->nt_prev_runnable_sum; + __entry->pid = p->pid; + ), + + TP_printk("cpu=%d curr_runnable_sum=%llu prev_runnable_sum=%llu nt_curr_runnable_sum=%lld nt_prev_runnable_sum=%lld pid=%d", + __entry->cpu, __entry->cs, __entry->ps, + __entry->nt_cs, __entry->nt_ps, __entry->pid) +); +#endif /* CONFIG_SCHED_WALT */ +#endif /* CONFIG_SMP */ #endif /* _TRACE_SCHED_H */ /* This part must be outside protection */ diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h index bfaec6903b8b..36a53fdf3247 100644 --- a/include/uapi/linux/android/binder.h +++ b/include/uapi/linux/android/binder.h @@ -38,9 +38,64 @@ enum { BINDER_TYPE_PTR = B_PACK_CHARS('p', 't', '*', B_TYPE_LARGE), }; -enum { +/** + * enum flat_binder_object_shifts: shift values for flat_binder_object_flags + * @FLAT_BINDER_FLAG_SCHED_POLICY_SHIFT: shift for getting scheduler policy. + * + */ +enum flat_binder_object_shifts { + FLAT_BINDER_FLAG_SCHED_POLICY_SHIFT = 9, +}; + +/** + * enum flat_binder_object_flags - flags for use in flat_binder_object.flags + */ +enum flat_binder_object_flags { + /** + * @FLAT_BINDER_FLAG_PRIORITY_MASK: bit-mask for min scheduler priority + * + * These bits can be used to set the minimum scheduler priority + * at which transactions into this node should run. Valid values + * in these bits depend on the scheduler policy encoded in + * @FLAT_BINDER_FLAG_SCHED_POLICY_MASK. + * + * For SCHED_NORMAL/SCHED_BATCH, the valid range is between [-20..19] + * For SCHED_FIFO/SCHED_RR, the value can run between [1..99] + */ FLAT_BINDER_FLAG_PRIORITY_MASK = 0xff, + /** + * @FLAT_BINDER_FLAG_ACCEPTS_FDS: whether the node accepts fds. + */ FLAT_BINDER_FLAG_ACCEPTS_FDS = 0x100, + /** + * @FLAT_BINDER_FLAG_SCHED_POLICY_MASK: bit-mask for scheduling policy + * + * These two bits can be used to set the min scheduling policy at which + * transactions on this node should run. These match the UAPI + * scheduler policy values, eg: + * 00b: SCHED_NORMAL + * 01b: SCHED_FIFO + * 10b: SCHED_RR + * 11b: SCHED_BATCH + */ + FLAT_BINDER_FLAG_SCHED_POLICY_MASK = + 3U << FLAT_BINDER_FLAG_SCHED_POLICY_SHIFT, + + /** + * @FLAT_BINDER_FLAG_INHERIT_RT: whether the node inherits RT policy + * + * Only when set, calls into this node will inherit a real-time + * scheduling policy from the caller (for synchronous transactions). + */ + FLAT_BINDER_FLAG_INHERIT_RT = 0x800, + + /** + * @FLAT_BINDER_FLAG_TXN_SECURITY_CTX: request security contexts + * + * Only when set, causes senders to include their security + * context + */ + FLAT_BINDER_FLAG_TXN_SECURITY_CTX = 0x1000, }; #ifdef BINDER_IPC_32BIT @@ -200,6 +255,15 @@ struct binder_node_debug_info { __u32 has_weak_ref; }; +struct binder_node_info_for_ref { + __u32 handle; + __u32 strong_count; + __u32 weak_count; + __u32 reserved1; + __u32 reserved2; + __u32 reserved3; +}; + #define BINDER_WRITE_READ _IOWR('b', 1, struct binder_write_read) #define BINDER_SET_IDLE_TIMEOUT _IOW('b', 3, __s64) #define BINDER_SET_MAX_THREADS _IOW('b', 5, __u32) @@ -208,6 +272,8 @@ struct binder_node_debug_info { #define BINDER_THREAD_EXIT _IOW('b', 8, __s32) #define BINDER_VERSION _IOWR('b', 9, struct binder_version) #define BINDER_GET_NODE_DEBUG_INFO _IOWR('b', 11, struct binder_node_debug_info) +#define BINDER_GET_NODE_INFO_FOR_REF _IOWR('b', 12, struct binder_node_info_for_ref) +#define BINDER_SET_CONTEXT_MGR_EXT _IOW('b', 13, struct flat_binder_object) /* * NOTE: Two special error codes you should check for when calling @@ -266,6 +332,11 @@ struct binder_transaction_data { } data; }; +struct binder_transaction_data_secctx { + struct binder_transaction_data transaction_data; + binder_uintptr_t secctx; +}; + struct binder_transaction_data_sg { struct binder_transaction_data transaction_data; binder_size_t buffers_size; @@ -301,6 +372,11 @@ enum binder_driver_return_protocol { BR_OK = _IO('r', 1), /* No parameters! */ + BR_TRANSACTION_SEC_CTX = _IOR('r', 2, + struct binder_transaction_data_secctx), + /* + * binder_transaction_data_secctx: the received command. + */ BR_TRANSACTION = _IOR('r', 2, struct binder_transaction_data), BR_REPLY = _IOR('r', 3, struct binder_transaction_data), /* diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 30f2ce76b517..a88b2c458dcc 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -176,6 +176,10 @@ enum bpf_attach_type { /* Specify numa node during map creation */ #define BPF_F_NUMA_NODE (1U << 2) +/* Flags for accessing BPF object */ +#define BPF_F_RDONLY (1U << 3) +#define BPF_F_WRONLY (1U << 4) + union bpf_attr { struct { /* anonymous struct used by BPF_MAP_CREATE command */ __u32 map_type; /* one of enum bpf_map_type */ @@ -216,6 +220,7 @@ union bpf_attr { struct { /* anonymous struct used by BPF_OBJ_* commands */ __aligned_u64 pathname; __u32 bpf_fd; + __u32 file_flags; }; struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */ @@ -243,6 +248,7 @@ union bpf_attr { __u32 map_id; }; __u32 next_id; + __u32 open_flags; }; struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */ diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h index 6448cdd9a350..586bf89f6b87 100644 --- a/include/uapi/linux/fcntl.h +++ b/include/uapi/linux/fcntl.h @@ -41,6 +41,7 @@ #define F_SEAL_SHRINK 0x0002 /* prevent file from shrinking */ #define F_SEAL_GROW 0x0004 /* prevent file from growing */ #define F_SEAL_WRITE 0x0008 /* prevent writes */ +#define F_SEAL_FUTURE_WRITE 0x0010 /* prevent writes */ /* (1U << 31) is reserved for signed error codes */ /* diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 4199f8acbce5..e4d0261080db 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -265,7 +265,8 @@ struct fsxattr { #define FS_POLICY_FLAGS_PAD_16 0x02 #define FS_POLICY_FLAGS_PAD_32 0x03 #define FS_POLICY_FLAGS_PAD_MASK 0x03 -#define FS_POLICY_FLAGS_VALID 0x03 +#define FS_POLICY_FLAG_DIRECT_KEY 0x04 /* use master key directly */ +#define FS_POLICY_FLAGS_VALID 0x07 /* Encryption algorithms */ #define FS_ENCRYPTION_MODE_INVALID 0 @@ -275,6 +276,9 @@ struct fsxattr { #define FS_ENCRYPTION_MODE_AES_256_CTS 4 #define FS_ENCRYPTION_MODE_AES_128_CBC 5 #define FS_ENCRYPTION_MODE_AES_128_CTS 6 +#define FS_ENCRYPTION_MODE_SPECK128_256_XTS 7 /* Removed, do not use. */ +#define FS_ENCRYPTION_MODE_SPECK128_256_CTS 8 /* Removed, do not use. */ +#define FS_ENCRYPTION_MODE_ADIANTUM 9 struct fscrypt_policy { __u8 version; diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index daac48210b2c..8fb4d4259e9e 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -378,6 +378,7 @@ enum fuse_opcode { FUSE_READDIRPLUS = 44, FUSE_RENAME2 = 45, FUSE_LSEEK = 46, + FUSE_CANONICAL_PATH= 2016, /* CUSE specific operations */ CUSE_INIT = 4096, diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 1f00f0cd6790..b9a7c97f3cc2 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -451,6 +451,16 @@ enum { #define IFLA_MACSEC_MAX (__IFLA_MACSEC_MAX - 1) +/* XFRM section */ +enum { + IFLA_XFRM_UNSPEC, + IFLA_XFRM_LINK, + IFLA_XFRM_IF_ID, + __IFLA_XFRM_MAX +}; + +#define IFLA_XFRM_MAX (__IFLA_XFRM_MAX - 1) + enum macsec_validation_type { MACSEC_VALIDATE_DISABLED = 0, MACSEC_VALIDATE_CHECK = 1, diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index b22a9c4e1b12..8c3ea81d5bd7 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -166,6 +166,7 @@ enum { DEVCONF_ACCEPT_DAD, DEVCONF_FORCE_TLLAO, DEVCONF_NDISC_NOTIFY, + DEVCONF_ACCEPT_RA_RT_TABLE, DEVCONF_MLDV1_UNSOLICITED_REPORT_INTERVAL, DEVCONF_MLDV2_UNSOLICITED_REPORT_INTERVAL, DEVCONF_SUPPRESS_FRAG_NDISC, diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index aa50113ebe5b..5bdb07fed129 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -55,6 +55,8 @@ #define REISER2FS_SUPER_MAGIC_STRING "ReIsEr2Fs" #define REISER2FS_JR_SUPER_MAGIC_STRING "ReIsEr3Fs" +#define SDCARDFS_SUPER_MAGIC 0x5dca2df5 + #define SMB_SUPER_MAGIC 0x517B #define CGROUP_SUPER_MAGIC 0x27e0eb #define CGROUP2_SUPER_MAGIC 0x63677270 diff --git a/include/uapi/linux/netfilter/xt_IDLETIMER.h b/include/uapi/linux/netfilter/xt_IDLETIMER.h index 3c586a19baea..c82a1c1d53ec 100644 --- a/include/uapi/linux/netfilter/xt_IDLETIMER.h +++ b/include/uapi/linux/netfilter/xt_IDLETIMER.h @@ -5,6 +5,7 @@ * Header file for Xtables timer target module. * * Copyright (C) 2004, 2010 Nokia Corporation + * * Written by Timo Teras <ext-timo.teras@nokia.com> * * Converted to x_tables and forward-ported to 2.6.34 @@ -33,12 +34,19 @@ #include <linux/types.h> #define MAX_IDLETIMER_LABEL_SIZE 28 +#define NLMSG_MAX_SIZE 64 + +#define NL_EVENT_TYPE_INACTIVE 0 +#define NL_EVENT_TYPE_ACTIVE 1 struct idletimer_tg_info { __u32 timeout; char label[MAX_IDLETIMER_LABEL_SIZE]; + /* Use netlink messages for notification in addition to sysfs */ + __u8 send_nl_msg; + /* for kernel module internal use only */ struct idletimer_tg *timer __attribute__((aligned(8))); }; diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 214102fab940..6040dba9a202 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -211,4 +211,7 @@ struct prctl_mm_map { # define PR_SPEC_DISABLE (1UL << 2) # define PR_SPEC_FORCE_DISABLE (1UL << 3) +#define PR_SET_VMA 0x53564d41 +# define PR_SET_VMA_ANON_NAME 0 + #endif /* _LINUX_PRCTL_H */ diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h index b7aa7bb2349f..5e8ca16a9079 100644 --- a/include/uapi/linux/taskstats.h +++ b/include/uapi/linux/taskstats.h @@ -34,7 +34,7 @@ */ -#define TASKSTATS_VERSION 8 +#define TASKSTATS_VERSION 9 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -164,6 +164,10 @@ struct taskstats { /* Delay waiting for memory reclaim */ __u64 freepages_count; __u64 freepages_delay_total; + + /* Delay waiting for thrashing page */ + __u64 thrashing_count; + __u64 thrashing_delay_total; }; diff --git a/include/uapi/linux/usb/f_accessory.h b/include/uapi/linux/usb/f_accessory.h new file mode 100644 index 000000000000..0baeb7d0d74c --- /dev/null +++ b/include/uapi/linux/usb/f_accessory.h @@ -0,0 +1,146 @@ +/* + * Gadget Function Driver for Android USB accessories + * + * Copyright (C) 2011 Google, Inc. + * Author: Mike Lockwood <lockwood@android.com> + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#ifndef _UAPI_LINUX_USB_F_ACCESSORY_H +#define _UAPI_LINUX_USB_F_ACCESSORY_H + +/* Use Google Vendor ID when in accessory mode */ +#define USB_ACCESSORY_VENDOR_ID 0x18D1 + + +/* Product ID to use when in accessory mode */ +#define USB_ACCESSORY_PRODUCT_ID 0x2D00 + +/* Product ID to use when in accessory mode and adb is enabled */ +#define USB_ACCESSORY_ADB_PRODUCT_ID 0x2D01 + +/* Indexes for strings sent by the host via ACCESSORY_SEND_STRING */ +#define ACCESSORY_STRING_MANUFACTURER 0 +#define ACCESSORY_STRING_MODEL 1 +#define ACCESSORY_STRING_DESCRIPTION 2 +#define ACCESSORY_STRING_VERSION 3 +#define ACCESSORY_STRING_URI 4 +#define ACCESSORY_STRING_SERIAL 5 + +/* Control request for retrieving device's protocol version + * + * requestType: USB_DIR_IN | USB_TYPE_VENDOR + * request: ACCESSORY_GET_PROTOCOL + * value: 0 + * index: 0 + * data version number (16 bits little endian) + * 1 for original accessory support + * 2 adds HID and device to host audio support + */ +#define ACCESSORY_GET_PROTOCOL 51 + +/* Control request for host to send a string to the device + * + * requestType: USB_DIR_OUT | USB_TYPE_VENDOR + * request: ACCESSORY_SEND_STRING + * value: 0 + * index: string ID + * data zero terminated UTF8 string + * + * The device can later retrieve these strings via the + * ACCESSORY_GET_STRING_* ioctls + */ +#define ACCESSORY_SEND_STRING 52 + +/* Control request for starting device in accessory mode. + * The host sends this after setting all its strings to the device. + * + * requestType: USB_DIR_OUT | USB_TYPE_VENDOR + * request: ACCESSORY_START + * value: 0 + * index: 0 + * data none + */ +#define ACCESSORY_START 53 + +/* Control request for registering a HID device. + * Upon registering, a unique ID is sent by the accessory in the + * value parameter. This ID will be used for future commands for + * the device + * + * requestType: USB_DIR_OUT | USB_TYPE_VENDOR + * request: ACCESSORY_REGISTER_HID_DEVICE + * value: Accessory assigned ID for the HID device + * index: total length of the HID report descriptor + * data none + */ +#define ACCESSORY_REGISTER_HID 54 + +/* Control request for unregistering a HID device. + * + * requestType: USB_DIR_OUT | USB_TYPE_VENDOR + * request: ACCESSORY_REGISTER_HID + * value: Accessory assigned ID for the HID device + * index: 0 + * data none + */ +#define ACCESSORY_UNREGISTER_HID 55 + +/* Control request for sending the HID report descriptor. + * If the HID descriptor is longer than the endpoint zero max packet size, + * the descriptor will be sent in multiple ACCESSORY_SET_HID_REPORT_DESC + * commands. The data for the descriptor must be sent sequentially + * if multiple packets are needed. + * + * requestType: USB_DIR_OUT | USB_TYPE_VENDOR + * request: ACCESSORY_SET_HID_REPORT_DESC + * value: Accessory assigned ID for the HID device + * index: offset of data in descriptor + * (needed when HID descriptor is too big for one packet) + * data the HID report descriptor + */ +#define ACCESSORY_SET_HID_REPORT_DESC 56 + +/* Control request for sending HID events. + * + * requestType: USB_DIR_OUT | USB_TYPE_VENDOR + * request: ACCESSORY_SEND_HID_EVENT + * value: Accessory assigned ID for the HID device + * index: 0 + * data the HID report for the event + */ +#define ACCESSORY_SEND_HID_EVENT 57 + +/* Control request for setting the audio mode. + * + * requestType: USB_DIR_OUT | USB_TYPE_VENDOR + * request: ACCESSORY_SET_AUDIO_MODE + * value: 0 - no audio + * 1 - device to host, 44100 16-bit stereo PCM + * index: 0 + * data none + */ +#define ACCESSORY_SET_AUDIO_MODE 58 + +/* ioctls for retrieving strings set by the host */ +#define ACCESSORY_GET_STRING_MANUFACTURER _IOW('M', 1, char[256]) +#define ACCESSORY_GET_STRING_MODEL _IOW('M', 2, char[256]) +#define ACCESSORY_GET_STRING_DESCRIPTION _IOW('M', 3, char[256]) +#define ACCESSORY_GET_STRING_VERSION _IOW('M', 4, char[256]) +#define ACCESSORY_GET_STRING_URI _IOW('M', 5, char[256]) +#define ACCESSORY_GET_STRING_SERIAL _IOW('M', 6, char[256]) +/* returns 1 if there is a start request pending */ +#define ACCESSORY_IS_START_REQUESTED _IO('M', 7) +/* returns audio mode (set via the ACCESSORY_SET_AUDIO_MODE control request) */ +#define ACCESSORY_GET_AUDIO_MODE _IO('M', 8) + +#endif /* _UAPI_LINUX_USB_F_ACCESSORY_H */ diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index 0b636432cdf3..ff7cfdc6cb44 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -305,9 +305,12 @@ enum xfrm_attr_type_t { XFRMA_ADDRESS_FILTER, /* struct xfrm_address_filter */ XFRMA_PAD, XFRMA_OFFLOAD_DEV, /* struct xfrm_user_offload */ - XFRMA_OUTPUT_MARK, /* __u32 */ + XFRMA_SET_MARK, /* __u32 */ + XFRMA_SET_MARK_MASK, /* __u32 */ + XFRMA_IF_ID, /* __u32 */ __XFRMA_MAX +#define XFRMA_OUTPUT_MARK XFRMA_SET_MARK /* Compatibility */ #define XFRMA_MAX (__XFRMA_MAX - 1) }; diff --git a/init/Kconfig b/init/Kconfig index 46075327c165..f1ffb30ae926 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -400,6 +400,15 @@ config IRQ_TIME_ACCOUNTING If in doubt, say N here. +config SCHED_WALT + bool "Support window based load tracking" + depends on SMP + help + This feature will allow the scheduler to maintain a tunable window + based set of metrics for tasks and runqueues. These metrics can be + used to guide task placement as well as task frequency requirements + for cpufreq governors. + config BSD_PROCESS_ACCT bool "BSD Process Accounting" depends on MULTIUSER @@ -470,6 +479,45 @@ config TASK_IO_ACCOUNTING Say N if unsure. +config PSI + bool "Pressure stall information tracking" + help + Collect metrics that indicate how overcommitted the CPU, memory, + and IO capacity are in the system. + + If you say Y here, the kernel will create /proc/pressure/ with the + pressure statistics files cpu, memory, and io. These will indicate + the share of walltime in which some or all tasks in the system are + delayed due to contention of the respective resource. + + In kernels with cgroup support, cgroups (cgroup2 only) will + have cpu.pressure, memory.pressure, and io.pressure files, + which aggregate pressure stalls for the grouped tasks only. + + For more details see Documentation/accounting/psi.txt. + + Say N if unsure. + +config PSI_DEFAULT_DISABLED + bool "Require boot parameter to enable pressure stall information tracking" + default n + depends on PSI + help + If set, pressure stall information tracking will be disabled + per default but can be enabled through passing psi=1 on the + kernel commandline during boot. + + This feature adds some code to the task wakeup and sleep + paths of the scheduler. The overhead is too low to affect + common scheduling-intense workloads in practice (such as + webservers, memcache), but it does show up in artificial + scheduler stress tests, such as hackbench. + + If you are paranoid and not sure what the kernel will be + used for, say Y. + + Say N if unsure. + endmenu # "CPU/Task time and stats accounting" source "kernel/rcu/Kconfig" @@ -586,6 +634,41 @@ config HAVE_UNSTABLE_SCHED_CLOCK config GENERIC_SCHED_CLOCK bool +menu "FAIR Scheuler tunables" + +choice + prompt "Utilization's PELT half-Life" + default PELT_UTIL_HALFLIFE_32 + help + Allows choosing one of the possible values for the PELT half-life to + be used for the update of the utilization of tasks and CPUs. + The half-life is the amount of [ms] required by the PELT signal to + build up to 50% utilization. The higher the half-life the longer it + takes for a task to be represented as a big one. + + If not sure, use the default of 32 ms. + +config PELT_UTIL_HALFLIFE_32 + bool "32 ms, default for server" + +config PELT_UTIL_HALFLIFE_16 + bool "16 ms, suggested for interactive workloads" + help + Use 16ms as PELT half-life value. This will increase the ramp-up and + decay of utlization and load twice as fast as for the default + configuration using 32ms. + +config PELT_UTIL_HALFLIFE_8 + bool "8 ms, very fast" + help + Use 8ms as PELT half-life value. This will increase the ramp-up and + decay of utlization and load four time as fast as for the default + configuration using 32ms. + +endchoice + +endmenu # FAIR Scheduler tunables" + # # For architectures that want to enable the support for NUMA-affine scheduler # balancing logic: @@ -733,6 +816,7 @@ config FAIR_GROUP_SCHED config CFS_BANDWIDTH bool "CPU bandwidth provisioning for FAIR_GROUP_SCHED" depends on FAIR_GROUP_SCHED + depends on !SCHED_WALT default n help This option allows users to define CPU bandwidth rates (limits) for @@ -959,6 +1043,39 @@ config SCHED_AUTOGROUP desktop applications. Task group autogeneration is currently based upon task session. +config SCHED_TUNE + bool "Boosting for CFS tasks (EXPERIMENTAL)" + depends on SMP + help + This option enables support for task classification using a new + cgroup controller, schedtune. Schedtune allows tasks to be given + a boost value and marked as latency-sensitive or not. This option + provides the "schedtune" controller. + + This new controller: + 1. allows only a two layers hierarchy, where the root defines the + system-wide boost value and its direct childrens define each one a + different "class of tasks" to be boosted with a different value + 2. supports up to 16 different task classes, each one which could be + configured with a different boost value + + Latency-sensitive tasks are not subject to energy-aware wakeup + task placement. The boost value assigned to tasks is used to + influence task placement and CPU frequency selection (if + utilization-driven frequency selection is in use). + + If unsure, say N. + +config DEFAULT_USE_ENERGY_AWARE + bool "Default to enabling the Energy Aware Scheduler feature" + default n + help + This option defaults the ENERGY_AWARE scheduling feature to true, + as without SCHED_DEBUG set this feature can't be enabled or disabled + via sysctl. + + Say N if unsure. + config SYSFS_DEPRECATED bool "Enable deprecated sysfs features to support old userspace tools" depends on SYSFS @@ -1887,7 +2004,7 @@ endif # MODULES config MODULES_TREE_LOOKUP def_bool y - depends on PERF_EVENTS || TRACING + depends on PERF_EVENTS || TRACING || CFI_CLANG config INIT_ALL_POSSIBLE bool diff --git a/init/Makefile b/init/Makefile index 1dbb23787290..a04f1c18b58c 100644 --- a/init/Makefile +++ b/init/Makefile @@ -6,11 +6,8 @@ ccflags-y := -fno-function-sections -fno-data-sections obj-y := main.o version.o mounts.o -ifneq ($(CONFIG_BLK_DEV_INITRD),y) obj-y += noinitramfs.o -else obj-$(CONFIG_BLK_DEV_INITRD) += initramfs.o -endif obj-$(CONFIG_GENERIC_CALIBRATE_DELAY) += calibrate.o ifneq ($(CONFIG_ARCH_INIT_TASK),y) diff --git a/init/do_mounts_dm.c b/init/do_mounts_dm.c new file mode 100644 index 000000000000..e76c137a4cb6 --- /dev/null +++ b/init/do_mounts_dm.c @@ -0,0 +1,409 @@ +/* do_mounts_dm.c + * Copyright (C) 2010 The Chromium OS Authors <chromium-os-dev@chromium.org> + * All Rights Reserved. + * Based on do_mounts_md.c + * + * This file is released under the GPL. + */ +#include <linux/device-mapper.h> +#include <linux/fs.h> +#include <linux/string.h> + +#include "do_mounts.h" + +#define DM_MAX_NAME 32 +#define DM_MAX_UUID 129 +#define DM_NO_UUID "none" + +#define DM_MSG_PREFIX "init" + +/* Separators used for parsing the dm= argument. */ +#define DM_FIELD_SEP ' ' +#define DM_LINE_SEP ',' + +/* + * When the device-mapper and any targets are compiled into the kernel + * (not a module), one target may be created and used as the root device at + * boot time with the parameters given with the boot line dm=... + * The code for that is here. + */ + +struct dm_setup_target { + sector_t begin; + sector_t length; + char *type; + char *params; + /* simple singly linked list */ + struct dm_setup_target *next; +}; + +static struct { + int minor; + int ro; + char name[DM_MAX_NAME]; + char uuid[DM_MAX_UUID]; + char *targets; + struct dm_setup_target *target; + int target_count; +} dm_setup_args __initdata; + +static __initdata int dm_early_setup; + +static size_t __init get_dm_option(char *str, char **next, char sep) +{ + size_t len = 0; + char *endp = NULL; + + if (!str) + return 0; + + endp = strchr(str, sep); + if (!endp) { /* act like strchrnul */ + len = strlen(str); + endp = str + len; + } else { + len = endp - str; + } + + if (endp == str) + return 0; + + if (!next) + return len; + + if (*endp == 0) { + /* Don't advance past the nul. */ + *next = endp; + } else { + *next = endp + 1; + } + return len; +} + +static int __init dm_setup_args_init(void) +{ + dm_setup_args.minor = 0; + dm_setup_args.ro = 0; + dm_setup_args.target = NULL; + dm_setup_args.target_count = 0; + return 0; +} + +static int __init dm_setup_cleanup(void) +{ + struct dm_setup_target *target = dm_setup_args.target; + struct dm_setup_target *old_target = NULL; + while (target) { + kfree(target->type); + kfree(target->params); + old_target = target; + target = target->next; + kfree(old_target); + dm_setup_args.target_count--; + } + BUG_ON(dm_setup_args.target_count); + return 0; +} + +static char * __init dm_setup_parse_device_args(char *str) +{ + char *next = NULL; + size_t len = 0; + + /* Grab the logical name of the device to be exported to udev */ + len = get_dm_option(str, &next, DM_FIELD_SEP); + if (!len) { + DMERR("failed to parse device name"); + goto parse_fail; + } + len = min(len + 1, sizeof(dm_setup_args.name)); + strlcpy(dm_setup_args.name, str, len); /* includes nul */ + str = skip_spaces(next); + + /* Grab the UUID value or "none" */ + len = get_dm_option(str, &next, DM_FIELD_SEP); + if (!len) { + DMERR("failed to parse device uuid"); + goto parse_fail; + } + len = min(len + 1, sizeof(dm_setup_args.uuid)); + strlcpy(dm_setup_args.uuid, str, len); + str = skip_spaces(next); + + /* Determine if the table/device will be read only or read-write */ + if (!strncmp("ro,", str, 3)) { + dm_setup_args.ro = 1; + } else if (!strncmp("rw,", str, 3)) { + dm_setup_args.ro = 0; + } else { + DMERR("failed to parse table mode"); + goto parse_fail; + } + str = skip_spaces(str + 3); + + return str; + +parse_fail: + return NULL; +} + +static void __init dm_substitute_devices(char *str, size_t str_len) +{ + char *candidate = str; + char *candidate_end = str; + char old_char; + size_t len = 0; + dev_t dev; + + if (str_len < 3) + return; + + while (str && *str) { + candidate = strchr(str, '/'); + if (!candidate) + break; + + /* Avoid embedded slashes */ + if (candidate != str && *(candidate - 1) != DM_FIELD_SEP) { + str = strchr(candidate, DM_FIELD_SEP); + continue; + } + + len = get_dm_option(candidate, &candidate_end, DM_FIELD_SEP); + str = skip_spaces(candidate_end); + if (len < 3 || len > 37) /* name_to_dev_t max; maj:mix min */ + continue; + + /* Temporarily terminate with a nul */ + candidate_end--; + old_char = *candidate_end; + *candidate_end = '\0'; + + DMDEBUG("converting candidate device '%s' to dev_t", candidate); + /* Use the boot-time specific device naming */ + dev = name_to_dev_t(candidate); + *candidate_end = old_char; + + DMDEBUG(" -> %u", dev); + /* No suitable replacement found */ + if (!dev) + continue; + + /* Rewrite the /dev/path as a major:minor */ + len = snprintf(candidate, len, "%u:%u", MAJOR(dev), MINOR(dev)); + if (!len) { + DMERR("error substituting device major/minor."); + break; + } + candidate += len; + /* Pad out with spaces (fixing our nul) */ + while (candidate < candidate_end) + *(candidate++) = DM_FIELD_SEP; + } +} + +static int __init dm_setup_parse_targets(char *str) +{ + char *next = NULL; + size_t len = 0; + struct dm_setup_target **target = NULL; + + /* Targets are defined as per the table format but with a + * comma as a newline separator. */ + target = &dm_setup_args.target; + while (str && *str) { + *target = kzalloc(sizeof(struct dm_setup_target), GFP_KERNEL); + if (!*target) { + DMERR("failed to allocate memory for target %d", + dm_setup_args.target_count); + goto parse_fail; + } + dm_setup_args.target_count++; + + (*target)->begin = simple_strtoull(str, &next, 10); + if (!next || *next != DM_FIELD_SEP) { + DMERR("failed to parse starting sector for target %d", + dm_setup_args.target_count - 1); + goto parse_fail; + } + str = skip_spaces(next + 1); + + (*target)->length = simple_strtoull(str, &next, 10); + if (!next || *next != DM_FIELD_SEP) { + DMERR("failed to parse length for target %d", + dm_setup_args.target_count - 1); + goto parse_fail; + } + str = skip_spaces(next + 1); + + len = get_dm_option(str, &next, DM_FIELD_SEP); + if (!len || + !((*target)->type = kstrndup(str, len, GFP_KERNEL))) { + DMERR("failed to parse type for target %d", + dm_setup_args.target_count - 1); + goto parse_fail; + } + str = skip_spaces(next); + + len = get_dm_option(str, &next, DM_LINE_SEP); + if (!len || + !((*target)->params = kstrndup(str, len, GFP_KERNEL))) { + DMERR("failed to parse params for target %d", + dm_setup_args.target_count - 1); + goto parse_fail; + } + str = skip_spaces(next); + + /* Before moving on, walk through the copied target and + * attempt to replace all /dev/xxx with the major:minor number. + * It may not be possible to resolve them traditionally at + * boot-time. */ + dm_substitute_devices((*target)->params, len); + + target = &((*target)->next); + } + DMDEBUG("parsed %d targets", dm_setup_args.target_count); + + return 0; + +parse_fail: + return 1; +} + +/* + * Parse the command-line parameters given our kernel, but do not + * actually try to invoke the DM device now; that is handled by + * dm_setup_drive after the low-level disk drivers have initialised. + * dm format is as follows: + * dm="name uuid fmode,[table line 1],[table line 2],..." + * May be used with root=/dev/dm-0 as it always uses the first dm minor. + */ + +static int __init dm_setup(char *str) +{ + dm_setup_args_init(); + + str = dm_setup_parse_device_args(str); + if (!str) { + DMDEBUG("str is NULL"); + goto parse_fail; + } + + /* Target parsing is delayed until we have dynamic memory */ + dm_setup_args.targets = str; + + printk(KERN_INFO "dm: will configure '%s' on dm-%d\n", + dm_setup_args.name, dm_setup_args.minor); + + dm_early_setup = 1; + return 1; + +parse_fail: + printk(KERN_WARNING "dm: Invalid arguments supplied to dm=.\n"); + return 0; +} + + +static void __init dm_setup_drive(void) +{ + struct mapped_device *md = NULL; + struct dm_table *table = NULL; + struct dm_setup_target *target; + char *uuid = dm_setup_args.uuid; + fmode_t fmode = FMODE_READ; + + /* Finish parsing the targets. */ + if (dm_setup_parse_targets(dm_setup_args.targets)) + goto parse_fail; + + if (dm_create(dm_setup_args.minor, &md)) { + DMDEBUG("failed to create the device"); + goto dm_create_fail; + } + DMDEBUG("created device '%s'", dm_device_name(md)); + + /* In addition to flagging the table below, the disk must be + * set explicitly ro/rw. */ + set_disk_ro(dm_disk(md), dm_setup_args.ro); + + if (!dm_setup_args.ro) + fmode |= FMODE_WRITE; + if (dm_table_create(&table, fmode, dm_setup_args.target_count, md)) { + DMDEBUG("failed to create the table"); + goto dm_table_create_fail; + } + + target = dm_setup_args.target; + while (target) { + DMINFO("adding target '%llu %llu %s %s'", + (unsigned long long) target->begin, + (unsigned long long) target->length, target->type, + target->params); + if (dm_table_add_target(table, target->type, target->begin, + target->length, target->params)) { + DMDEBUG("failed to add the target to the table"); + goto add_target_fail; + } + target = target->next; + } + + if (dm_table_complete(table)) { + DMDEBUG("failed to complete the table"); + goto table_complete_fail; + } + + /* Suspend the device so that we can bind it to the table. */ + if (dm_suspend(md, 0)) { + DMDEBUG("failed to suspend the device pre-bind"); + goto suspend_fail; + } + + /* Bind the table to the device. This is the only way to associate + * md->map with the table and set the disk capacity directly. */ + if (dm_swap_table(md, table)) { /* should return NULL. */ + DMDEBUG("failed to bind the device to the table"); + goto table_bind_fail; + } + + /* Finally, resume and the device should be ready. */ + if (dm_resume(md)) { + DMDEBUG("failed to resume the device"); + goto resume_fail; + } + + /* Export the dm device via the ioctl interface */ + if (!strcmp(DM_NO_UUID, dm_setup_args.uuid)) + uuid = NULL; + if (dm_ioctl_export(md, dm_setup_args.name, uuid)) { + DMDEBUG("failed to export device with given name and uuid"); + goto export_fail; + } + printk(KERN_INFO "dm: dm-%d is ready\n", dm_setup_args.minor); + + dm_setup_cleanup(); + return; + +export_fail: +resume_fail: +table_bind_fail: +suspend_fail: +table_complete_fail: +add_target_fail: +dm_table_create_fail: + dm_put(md); +dm_create_fail: + dm_setup_cleanup(); +parse_fail: + printk(KERN_WARNING "dm: starting dm-%d (%s) failed\n", + dm_setup_args.minor, dm_setup_args.name); +} + +__setup("dm=", dm_setup); + +void __init dm_run_setup(void) +{ + if (!dm_early_setup) + return; + printk(KERN_INFO "dm: attempting early device configuration.\n"); + dm_setup_drive(); +} diff --git a/init/initramfs.c b/init/initramfs.c index 7046feffef6b..5ea7f1b5ec44 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -20,6 +20,7 @@ #include <linux/syscalls.h> #include <linux/utime.h> #include <linux/file.h> +#include <linux/initramfs.h> static ssize_t __init xwrite(int fd, const char *p, size_t count) { @@ -607,10 +608,29 @@ static void __init clean_rootfs(void) } #endif +static int __initdata do_skip_initramfs; + +static int __init skip_initramfs_param(char *str) +{ + if (*str) + return 0; + do_skip_initramfs = 1; + return 1; +} +__setup("skip_initramfs", skip_initramfs_param); + static int __init populate_rootfs(void) { + char *err; + + if (do_skip_initramfs) { + if (initrd_start) + free_initrd(); + return default_rootfs(); + } + /* Load the built in initramfs */ - char *err = unpack_to_rootfs(__initramfs_start, __initramfs_size); + err = unpack_to_rootfs(__initramfs_start, __initramfs_size); if (err) panic("%s", err); /* Failed to decompress INTERNAL initramfs */ /* If available load the bootloader supplied initrd */ diff --git a/init/noinitramfs.c b/init/noinitramfs.c index 267739d85179..bcc8bcb053ee 100644 --- a/init/noinitramfs.c +++ b/init/noinitramfs.c @@ -21,11 +21,16 @@ #include <linux/stat.h> #include <linux/kdev_t.h> #include <linux/syscalls.h> +#include <linux/kconfig.h> +#include <linux/initramfs.h> /* * Create a simple rootfs that is similar to the default initramfs */ -static int __init default_rootfs(void) +#if !IS_BUILTIN(CONFIG_BLK_DEV_INITRD) +static +#endif +int __init default_rootfs(void) { int err; @@ -49,4 +54,6 @@ out: printk(KERN_WARNING "Failed to create a rootfs\n"); return err; } +#if !IS_BUILTIN(CONFIG_BLK_DEV_INITRD) rootfs_initcall(default_rootfs); +#endif diff --git a/ipc/mqueue.c b/ipc/mqueue.c index dccd4ecb786a..8ed150ca1f43 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -754,7 +754,7 @@ static struct file *do_create(struct ipc_namespace *ipc_ns, struct inode *dir, } mode &= ~current_umask(); - ret = vfs_create(dir, path->dentry, mode, true); + ret = vfs_create2(path->mnt, dir, path->dentry, mode, true); path->dentry->d_fsdata = NULL; if (ret) return ERR_PTR(ret); @@ -770,7 +770,7 @@ static struct file *do_open(struct path *path, int oflag) if ((oflag & O_ACCMODE) == (O_RDWR | O_WRONLY)) return ERR_PTR(-EINVAL); acc = oflag2acc[oflag & O_ACCMODE]; - if (inode_permission(d_inode(path->dentry), acc)) + if (inode_permission2(path->mnt, d_inode(path->dentry), acc)) return ERR_PTR(-EACCES); return dentry_open(path, oflag, current_cred()); } @@ -799,7 +799,7 @@ static int do_mq_open(const char __user *u_name, int oflag, umode_t mode, ro = mnt_want_write(mnt); /* we'll drop it in any case */ error = 0; inode_lock(d_inode(root)); - path.dentry = lookup_one_len(name->name, root, strlen(name->name)); + path.dentry = lookup_one_len2(name->name, mnt, root, strlen(name->name)); if (IS_ERR(path.dentry)) { error = PTR_ERR(path.dentry); goto out_putfd; @@ -879,7 +879,7 @@ SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name) if (err) goto out_name; inode_lock_nested(d_inode(mnt->mnt_root), I_MUTEX_PARENT); - dentry = lookup_one_len(name->name, mnt->mnt_root, + dentry = lookup_one_len2(name->name, mnt, mnt->mnt_root, strlen(name->name)); if (IS_ERR(dentry)) { err = PTR_ERR(dentry); @@ -891,7 +891,7 @@ SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name) err = -ENOENT; } else { ihold(inode); - err = vfs_unlink(d_inode(dentry->d_parent), dentry, NULL); + err = vfs_unlink2(mnt, d_inode(dentry->d_parent), dentry, NULL); } dput(dentry); diff --git a/kernel/Makefile b/kernel/Makefile index 43e92e3691ec..475174c6a3fd 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -35,6 +35,9 @@ CFLAGS_kcov.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) # cond_syscall is currently not LTO compatible CFLAGS_sys_ni.o = $(DISABLE_LTO) +# Don't instrument error handlers +CFLAGS_cfi.o = $(DISABLE_CFI_CLANG) + obj-y += sched/ obj-y += locking/ obj-y += power/ @@ -99,6 +102,7 @@ obj-$(CONFIG_TRACEPOINTS) += trace/ obj-$(CONFIG_IRQ_WORK) += irq_work.o obj-$(CONFIG_CPU_PM) += cpu_pm.o obj-$(CONFIG_BPF) += bpf/ +obj-$(CONFIG_CFI_CLANG) += cfi.o obj-$(CONFIG_PERF_EVENTS) += events/ diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index a8f55ea4146b..148895e2457f 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -19,6 +19,9 @@ #include "map_in_map.h" +#define ARRAY_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + static void bpf_array_free_percpu(struct bpf_array *array) { int i; @@ -60,7 +63,8 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size == 0 || attr->map_flags & ~BPF_F_NUMA_NODE || + attr->value_size == 0 || + attr->map_flags & ~ARRAY_CREATE_FLAG_MASK || (percpu && numa_node != NUMA_NO_NODE)) return ERR_PTR(-EINVAL); diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 1060eee6c8d5..1a846a636ae1 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -50,6 +50,9 @@ #include <linux/bpf.h> #include <linux/filter.h> +#define DEV_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + struct bpf_dtab_netdev { struct net_device *dev; struct bpf_dtab *dtab; @@ -83,7 +86,7 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE) + attr->value_size != 4 || attr->map_flags & ~DEV_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); dtab = kzalloc(sizeof(*dtab), GFP_USER); diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 6cc090d015f6..adb302d04ab3 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -18,8 +18,9 @@ #include "bpf_lru_list.h" #include "map_in_map.h" -#define HTAB_CREATE_FLAG_MASK \ - (BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE) +#define HTAB_CREATE_FLAG_MASK \ + (BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE | \ + BPF_F_RDONLY | BPF_F_WRONLY) struct bucket { struct hlist_nulls_head head; diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index ccf9ffd5da78..556d70b9e731 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -295,7 +295,7 @@ out: } static void *bpf_obj_do_get(const struct filename *pathname, - enum bpf_type *type) + enum bpf_type *type, int flags) { struct inode *inode; struct path path; @@ -307,7 +307,7 @@ static void *bpf_obj_do_get(const struct filename *pathname, return ERR_PTR(ret); inode = d_backing_inode(path.dentry); - ret = inode_permission(inode, MAY_WRITE); + ret = inode_permission(inode, ACC_MODE(flags)); if (ret) goto out; @@ -326,18 +326,23 @@ out: return ERR_PTR(ret); } -int bpf_obj_get_user(const char __user *pathname) +int bpf_obj_get_user(const char __user *pathname, int flags) { enum bpf_type type = BPF_TYPE_UNSPEC; struct filename *pname; int ret = -ENOENT; + int f_flags; void *raw; + f_flags = bpf_get_file_flag(flags); + if (f_flags < 0) + return f_flags; + pname = getname(pathname); if (IS_ERR(pname)) return PTR_ERR(pname); - raw = bpf_obj_do_get(pname, &type); + raw = bpf_obj_do_get(pname, &type, f_flags); if (IS_ERR(raw)) { ret = PTR_ERR(raw); goto out; @@ -346,7 +351,7 @@ int bpf_obj_get_user(const char __user *pathname) if (type == BPF_TYPE_PROG) ret = bpf_prog_new_fd(raw); else if (type == BPF_TYPE_MAP) - ret = bpf_map_new_fd(raw); + ret = bpf_map_new_fd(raw, f_flags); else goto out; @@ -363,7 +368,42 @@ out: putname(pname); return ret; } -EXPORT_SYMBOL_GPL(bpf_obj_get_user); + +static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type type) +{ + struct bpf_prog *prog; + int ret = inode_permission(inode, MAY_READ); + if (ret) + return ERR_PTR(ret); + + if (inode->i_op == &bpf_map_iops) + return ERR_PTR(-EINVAL); + if (inode->i_op != &bpf_prog_iops) + return ERR_PTR(-EACCES); + + prog = inode->i_private; + + ret = security_bpf_prog(prog); + if (ret < 0) + return ERR_PTR(ret); + + return bpf_prog_inc(prog); +} + +struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type) +{ + struct bpf_prog *prog; + struct path path; + int ret = kern_path(name, LOOKUP_FOLLOW, &path); + if (ret) + return ERR_PTR(ret); + prog = __get_prog_inode(d_backing_inode(path.dentry), type); + if (!IS_ERR(prog)) + touch_atime(&path); + path_put(&path); + return prog; +} +EXPORT_SYMBOL(bpf_prog_get_type_path); /* * Display the mount options in /proc/mounts. diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index c28c584b734e..224362fbd1b0 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -406,7 +406,8 @@ static int trie_delete_elem(struct bpf_map *map, void *key) #define LPM_KEY_SIZE_MAX LPM_KEY_SIZE(LPM_DATA_SIZE_MAX) #define LPM_KEY_SIZE_MIN LPM_KEY_SIZE(LPM_DATA_SIZE_MIN) -#define LPM_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE) +#define LPM_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE | \ + BPF_F_RDONLY | BPF_F_WRONLY) static struct bpf_map *trie_alloc(union bpf_attr *attr) { diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 22991e19c01c..0fffca42dac9 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -41,6 +41,9 @@ #include <net/strparser.h> #include <net/tcp.h> +#define SOCK_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + struct bpf_stab { struct bpf_map map; struct sock **sock_map; @@ -511,7 +514,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE) + attr->value_size != 4 || attr->map_flags & ~SOCK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); if (attr->value_size > KMALLOC_MAX_SIZE) diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 135be433e9a0..a15bc636cc98 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -11,6 +11,9 @@ #include <linux/perf_event.h> #include "percpu_freelist.h" +#define STACK_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + struct stack_map_bucket { struct pcpu_freelist_node fnode; u32 hash; @@ -60,7 +63,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) if (!capable(CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); - if (attr->map_flags & ~BPF_F_NUMA_NODE) + if (attr->map_flags & ~STACK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); /* check sanity of attributes */ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 21073682061d..fa749278ce6d 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -31,6 +31,8 @@ #define IS_FD_HASH(map) ((map)->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) #define IS_FD_MAP(map) (IS_FD_ARRAY(map) || IS_FD_HASH(map)) +#define BPF_OBJ_FLAG_MASK (BPF_F_RDONLY | BPF_F_WRONLY) + DEFINE_PER_CPU(int, bpf_prog_active); static DEFINE_IDR(prog_idr); static DEFINE_SPINLOCK(prog_idr_lock); @@ -207,6 +209,7 @@ static void bpf_map_free_deferred(struct work_struct *work) struct bpf_map *map = container_of(work, struct bpf_map, work); bpf_map_uncharge_memlock(map); + security_bpf_map_free(map); /* implementation dependent freeing */ map->ops->map_free(map); } @@ -291,17 +294,54 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) } #endif -static const struct file_operations bpf_map_fops = { +static ssize_t bpf_dummy_read(struct file *filp, char __user *buf, size_t siz, + loff_t *ppos) +{ + /* We need this handler such that alloc_file() enables + * f_mode with FMODE_CAN_READ. + */ + return -EINVAL; +} + +static ssize_t bpf_dummy_write(struct file *filp, const char __user *buf, + size_t siz, loff_t *ppos) +{ + /* We need this handler such that alloc_file() enables + * f_mode with FMODE_CAN_WRITE. + */ + return -EINVAL; +} + +const struct file_operations bpf_map_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_map_show_fdinfo, #endif .release = bpf_map_release, + .read = bpf_dummy_read, + .write = bpf_dummy_write, }; -int bpf_map_new_fd(struct bpf_map *map) +int bpf_map_new_fd(struct bpf_map *map, int flags) { + int ret; + + ret = security_bpf_map(map, OPEN_FMODE(flags)); + if (ret < 0) + return ret; + return anon_inode_getfd("bpf-map", &bpf_map_fops, map, - O_RDWR | O_CLOEXEC); + flags | O_CLOEXEC); +} + +int bpf_get_file_flag(int flags) +{ + if ((flags & BPF_F_RDONLY) && (flags & BPF_F_WRONLY)) + return -EINVAL; + if (flags & BPF_F_RDONLY) + return O_RDONLY; + if (flags & BPF_F_WRONLY) + return O_WRONLY; + return O_RDWR; } /* helper macro to check that unused fields 'union bpf_attr' are zero */ @@ -318,12 +358,17 @@ static int map_create(union bpf_attr *attr) { int numa_node = bpf_map_attr_numa_node(attr); struct bpf_map *map; + int f_flags; int err; err = CHECK_ATTR(BPF_MAP_CREATE); if (err) return -EINVAL; + f_flags = bpf_get_file_flag(attr->map_flags); + if (f_flags < 0) + return f_flags; + if (numa_node != NUMA_NO_NODE && ((unsigned int)numa_node >= nr_node_ids || !node_online(numa_node))) @@ -337,15 +382,19 @@ static int map_create(union bpf_attr *attr) atomic_set(&map->refcnt, 1); atomic_set(&map->usercnt, 1); - err = bpf_map_charge_memlock(map); + err = security_bpf_map_alloc(map); if (err) goto free_map_nouncharge; + err = bpf_map_charge_memlock(map); + if (err) + goto free_map_sec; + err = bpf_map_alloc_id(map); if (err) goto free_map; - err = bpf_map_new_fd(map); + err = bpf_map_new_fd(map, f_flags); if (err < 0) { /* failed to allocate fd. * bpf_map_put_with_uref() is needed because the above @@ -362,6 +411,8 @@ static int map_create(union bpf_attr *attr) free_map: bpf_map_uncharge_memlock(map); +free_map_sec: + security_bpf_map_free(map); free_map_nouncharge: map->ops->map_free(map); return err; @@ -460,6 +511,11 @@ static int map_lookup_elem(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); + if (!(f.file->f_mode & FMODE_CAN_READ)) { + err = -EPERM; + goto err_put; + } + key = memdup_user(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); @@ -554,6 +610,11 @@ static int map_update_elem(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); + if (!(f.file->f_mode & FMODE_CAN_WRITE)) { + err = -EPERM; + goto err_put; + } + key = memdup_user(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); @@ -638,6 +699,11 @@ static int map_delete_elem(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); + if (!(f.file->f_mode & FMODE_CAN_WRITE)) { + err = -EPERM; + goto err_put; + } + key = memdup_user(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); @@ -682,6 +748,11 @@ static int map_get_next_key(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); + if (!(f.file->f_mode & FMODE_CAN_READ)) { + err = -EPERM; + goto err_put; + } + if (ukey) { key = memdup_user(ukey, map->key_size); if (IS_ERR(key)) { @@ -836,6 +907,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu) free_used_maps(aux); bpf_prog_uncharge_memlock(aux->prog); + security_bpf_prog_free(aux); bpf_prog_free(aux->prog); } @@ -883,15 +955,23 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) } #endif -static const struct file_operations bpf_prog_fops = { +const struct file_operations bpf_prog_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_prog_show_fdinfo, #endif .release = bpf_prog_release, + .read = bpf_dummy_read, + .write = bpf_dummy_write, }; int bpf_prog_new_fd(struct bpf_prog *prog) { + int ret; + + ret = security_bpf_prog(prog); + if (ret < 0) + return ret; + return anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog, O_RDWR | O_CLOEXEC); } @@ -1031,10 +1111,14 @@ static int bpf_prog_load(union bpf_attr *attr) if (!prog) return -ENOMEM; - err = bpf_prog_charge_memlock(prog); + err = security_bpf_prog_alloc(prog->aux); if (err) goto free_prog_nouncharge; + err = bpf_prog_charge_memlock(prog); + if (err) + goto free_prog_sec; + prog->len = attr->insn_cnt; err = -EFAULT; @@ -1093,16 +1177,18 @@ free_used_maps: free_used_maps(prog->aux); free_prog: bpf_prog_uncharge_memlock(prog); +free_prog_sec: + security_bpf_prog_free(prog->aux); free_prog_nouncharge: bpf_prog_free(prog); return err; } -#define BPF_OBJ_LAST_FIELD bpf_fd +#define BPF_OBJ_LAST_FIELD file_flags static int bpf_obj_pin(const union bpf_attr *attr) { - if (CHECK_ATTR(BPF_OBJ)) + if (CHECK_ATTR(BPF_OBJ) || attr->file_flags != 0) return -EINVAL; return bpf_obj_pin_user(attr->bpf_fd, u64_to_user_ptr(attr->pathname)); @@ -1110,10 +1196,12 @@ static int bpf_obj_pin(const union bpf_attr *attr) static int bpf_obj_get(const union bpf_attr *attr) { - if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0) + if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0 || + attr->file_flags & ~BPF_OBJ_FLAG_MASK) return -EINVAL; - return bpf_obj_get_user(u64_to_user_ptr(attr->pathname)); + return bpf_obj_get_user(u64_to_user_ptr(attr->pathname), + attr->file_flags); } #ifdef CONFIG_CGROUP_BPF @@ -1327,20 +1415,26 @@ static int bpf_prog_get_fd_by_id(const union bpf_attr *attr) return fd; } -#define BPF_MAP_GET_FD_BY_ID_LAST_FIELD map_id +#define BPF_MAP_GET_FD_BY_ID_LAST_FIELD open_flags static int bpf_map_get_fd_by_id(const union bpf_attr *attr) { struct bpf_map *map; u32 id = attr->map_id; + int f_flags; int fd; - if (CHECK_ATTR(BPF_MAP_GET_FD_BY_ID)) + if (CHECK_ATTR(BPF_MAP_GET_FD_BY_ID) || + attr->open_flags & ~BPF_OBJ_FLAG_MASK) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; + f_flags = bpf_get_file_flag(attr->open_flags); + if (f_flags < 0) + return f_flags; + spin_lock_bh(&map_idr_lock); map = idr_find(&map_idr, id); if (map) @@ -1352,7 +1446,7 @@ static int bpf_map_get_fd_by_id(const union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); - fd = bpf_map_new_fd(map); + fd = bpf_map_new_fd(map, f_flags); if (fd < 0) bpf_map_put_with_uref(map); @@ -1492,6 +1586,10 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz if (copy_from_user(&attr, uattr, size) != 0) return -EFAULT; + err = security_bpf(cmd, &attr, size); + if (err < 0) + return err; + switch (cmd) { case BPF_MAP_CREATE: err = map_create(&attr); diff --git a/kernel/cfi.c b/kernel/cfi.c new file mode 100644 index 000000000000..3265b55efc22 --- /dev/null +++ b/kernel/cfi.c @@ -0,0 +1,308 @@ +/* + * CFI (Control Flow Integrity) error and slowpath handling + * + * Copyright (C) 2017 Google, Inc. + */ + +#include <linux/gfp.h> +#include <linux/module.h> +#include <linux/printk.h> +#include <linux/ratelimit.h> +#include <linux/rcupdate.h> +#include <linux/spinlock.h> +#include <asm/bug.h> +#include <asm/cacheflush.h> +#include <asm/memory.h> +#include <asm/set_memory.h> + +/* Compiler-defined handler names */ +#ifdef CONFIG_CFI_PERMISSIVE +#define cfi_failure_handler __ubsan_handle_cfi_check_fail +#define cfi_slowpath_handler __cfi_slowpath_diag +#else /* enforcing */ +#define cfi_failure_handler __ubsan_handle_cfi_check_fail_abort +#define cfi_slowpath_handler __cfi_slowpath +#endif /* CONFIG_CFI_PERMISSIVE */ + +static inline void handle_cfi_failure(void *ptr) +{ +#ifdef CONFIG_CFI_PERMISSIVE + WARN_RATELIMIT(1, "CFI failure (target: [<%px>] %pF):\n", ptr, ptr); +#else + pr_err("CFI failure (target: [<%px>] %pF):\n", ptr, ptr); + BUG(); +#endif +} + +#ifdef CONFIG_MODULES +#ifdef CONFIG_CFI_CLANG_SHADOW +struct shadow_range { + /* Module address range */ + unsigned long mod_min_addr; + unsigned long mod_max_addr; + /* Module page range */ + unsigned long min_page; + unsigned long max_page; +}; + +#define SHADOW_ORDER 1 +#define SHADOW_PAGES (1 << SHADOW_ORDER) +#define SHADOW_SIZE \ + ((SHADOW_PAGES * PAGE_SIZE - sizeof(struct shadow_range)) / sizeof(u16)) +#define SHADOW_INVALID 0xFFFF + +struct cfi_shadow { + /* Page range covered by the shadow */ + struct shadow_range r; + /* Page offsets to __cfi_check functions in modules */ + u16 shadow[SHADOW_SIZE]; +}; + +static DEFINE_SPINLOCK(shadow_update_lock); +static struct cfi_shadow __rcu *cfi_shadow __read_mostly = NULL; + +static inline int ptr_to_shadow(const struct cfi_shadow *s, unsigned long ptr) +{ + unsigned long index; + unsigned long page = ptr >> PAGE_SHIFT; + + if (unlikely(page < s->r.min_page)) + return -1; /* Outside of module area */ + + index = page - s->r.min_page; + + if (index >= SHADOW_SIZE) + return -1; /* Cannot be addressed with shadow */ + + return (int)index; +} + +static inline unsigned long shadow_to_ptr(const struct cfi_shadow *s, + int index) +{ + BUG_ON(index < 0 || index >= SHADOW_SIZE); + + if (unlikely(s->shadow[index] == SHADOW_INVALID)) + return 0; + + return (s->r.min_page + s->shadow[index]) << PAGE_SHIFT; +} + +static inline unsigned long shadow_to_page(const struct cfi_shadow *s, + int index) +{ + BUG_ON(index < 0 || index >= SHADOW_SIZE); + + return (s->r.min_page + index) << PAGE_SHIFT; +} + +static void prepare_next_shadow(const struct cfi_shadow __rcu *prev, + struct cfi_shadow *next) +{ + int i, index, check; + + /* Mark everything invalid */ + memset(next->shadow, 0xFF, sizeof(next->shadow)); + + if (!prev) + return; /* No previous shadow */ + + /* If the base address didn't change, update is not needed */ + if (prev->r.min_page == next->r.min_page) { + memcpy(next->shadow, prev->shadow, sizeof(next->shadow)); + return; + } + + /* Convert the previous shadow to the new address range */ + for (i = 0; i < SHADOW_SIZE; ++i) { + if (prev->shadow[i] == SHADOW_INVALID) + continue; + + index = ptr_to_shadow(next, shadow_to_page(prev, i)); + if (index < 0) + continue; + + check = ptr_to_shadow(next, + shadow_to_ptr(prev, prev->shadow[i])); + if (check < 0) + continue; + + next->shadow[index] = (u16)check; + } +} + +static void add_module_to_shadow(struct cfi_shadow *s, struct module *mod) +{ + unsigned long ptr; + unsigned long min_page_addr; + unsigned long max_page_addr; + unsigned long check = (unsigned long)mod->cfi_check; + int check_index = ptr_to_shadow(s, check); + + BUG_ON((check & PAGE_MASK) != check); /* Must be page aligned */ + + if (check_index < 0) + return; /* Module not addressable with shadow */ + + min_page_addr = (unsigned long)mod->core_layout.base & PAGE_MASK; + max_page_addr = (unsigned long)mod->core_layout.base + + mod->core_layout.text_size; + max_page_addr &= PAGE_MASK; + + /* For each page, store the check function index in the shadow */ + for (ptr = min_page_addr; ptr <= max_page_addr; ptr += PAGE_SIZE) { + int index = ptr_to_shadow(s, ptr); + if (index >= 0) { + /* Assume a page only contains code for one module */ + BUG_ON(s->shadow[index] != SHADOW_INVALID); + s->shadow[index] = (u16)check_index; + } + } +} + +static void remove_module_from_shadow(struct cfi_shadow *s, struct module *mod) +{ + unsigned long ptr; + unsigned long min_page_addr; + unsigned long max_page_addr; + + min_page_addr = (unsigned long)mod->core_layout.base & PAGE_MASK; + max_page_addr = (unsigned long)mod->core_layout.base + + mod->core_layout.text_size; + max_page_addr &= PAGE_MASK; + + for (ptr = min_page_addr; ptr <= max_page_addr; ptr += PAGE_SIZE) { + int index = ptr_to_shadow(s, ptr); + if (index >= 0) + s->shadow[index] = SHADOW_INVALID; + } +} + +typedef void (*update_shadow_fn)(struct cfi_shadow *, struct module *); + +static void update_shadow(struct module *mod, unsigned long min_addr, + unsigned long max_addr, update_shadow_fn fn) +{ + struct cfi_shadow *prev; + struct cfi_shadow *next = (struct cfi_shadow *) + __get_free_pages(GFP_KERNEL, SHADOW_ORDER); + + BUG_ON(!next); + + next->r.mod_min_addr = min_addr; + next->r.mod_max_addr = max_addr; + next->r.min_page = min_addr >> PAGE_SHIFT; + next->r.max_page = max_addr >> PAGE_SHIFT; + + spin_lock(&shadow_update_lock); + prev = rcu_dereference_protected(cfi_shadow, 1); + prepare_next_shadow(prev, next); + + fn(next, mod); + set_memory_ro((unsigned long)next, SHADOW_PAGES); + rcu_assign_pointer(cfi_shadow, next); + + spin_unlock(&shadow_update_lock); + synchronize_rcu(); + + if (prev) { + set_memory_rw((unsigned long)prev, SHADOW_PAGES); + free_pages((unsigned long)prev, SHADOW_ORDER); + } +} + +void cfi_module_add(struct module *mod, unsigned long min_addr, + unsigned long max_addr) +{ + update_shadow(mod, min_addr, max_addr, add_module_to_shadow); +} +EXPORT_SYMBOL(cfi_module_add); + +void cfi_module_remove(struct module *mod, unsigned long min_addr, + unsigned long max_addr) +{ + update_shadow(mod, min_addr, max_addr, remove_module_from_shadow); +} +EXPORT_SYMBOL(cfi_module_remove); + +static inline cfi_check_fn ptr_to_check_fn(const struct cfi_shadow __rcu *s, + unsigned long ptr) +{ + int index; + unsigned long check; + + if (unlikely(!s)) + return NULL; /* No shadow available */ + + if (ptr < s->r.mod_min_addr || ptr > s->r.mod_max_addr) + return NULL; /* Not in a mapped module */ + + index = ptr_to_shadow(s, ptr); + if (index < 0) + return NULL; /* Cannot be addressed with shadow */ + + return (cfi_check_fn)shadow_to_ptr(s, index); +} +#endif /* CONFIG_CFI_CLANG_SHADOW */ + +static inline cfi_check_fn find_module_cfi_check(void *ptr) +{ + struct module *mod; + + preempt_disable(); + mod = __module_address((unsigned long)ptr); + preempt_enable(); + + if (mod) + return mod->cfi_check; + + return CFI_CHECK_FN; +} + +static inline cfi_check_fn find_cfi_check(void *ptr) +{ +#ifdef CONFIG_CFI_CLANG_SHADOW + cfi_check_fn f; + + if (!rcu_access_pointer(cfi_shadow)) + return CFI_CHECK_FN; /* No loaded modules */ + + /* Look up the __cfi_check function to use */ + rcu_read_lock(); + f = ptr_to_check_fn(rcu_dereference(cfi_shadow), (unsigned long)ptr); + rcu_read_unlock(); + + if (f) + return f; + + /* + * Fall back to find_module_cfi_check, which works also for a larger + * module address space, but is slower. + */ +#endif /* CONFIG_CFI_CLANG_SHADOW */ + + return find_module_cfi_check(ptr); +} + +void cfi_slowpath_handler(uint64_t id, void *ptr, void *diag) +{ + cfi_check_fn check = find_cfi_check(ptr); + + if (likely(check)) + check(id, ptr, diag); + else /* Don't allow unchecked modules */ + handle_cfi_failure(ptr); +} +EXPORT_SYMBOL(cfi_slowpath_handler); +#endif /* CONFIG_MODULES */ + +void cfi_failure_handler(void *data, void *ptr, void *vtable) +{ + handle_cfi_failure(ptr); +} +EXPORT_SYMBOL(cfi_failure_handler); + +void __cfi_check_fail(void *data, void *ptr) +{ + handle_cfi_failure(ptr); +} diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 545f29c5268d..1d166be184f7 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -542,7 +542,8 @@ static ssize_t __cgroup1_procs_write(struct kernfs_open_file *of, tcred = get_task_cred(task); if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) && !uid_eq(cred->euid, tcred->uid) && - !uid_eq(cred->euid, tcred->suid)) + !uid_eq(cred->euid, tcred->suid) && + !ns_capable(tcred->user_ns, CAP_SYS_NICE)) ret = -EACCES; put_cred(tcred); if (ret) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index a2fed8fbd2bd..e5a72325aa01 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -54,6 +54,7 @@ #include <linux/proc_ns.h> #include <linux/nsproxy.h> #include <linux/file.h> +#include <linux/psi.h> #include <net/sock.h> #define CREATE_TRACE_POINTS @@ -798,7 +799,7 @@ static void css_set_move_task(struct task_struct *task, */ WARN_ON_ONCE(task->flags & PF_EXITING); - rcu_assign_pointer(task->cgroups, to_cset); + cgroup_move_task(task, to_cset); list_add_tail(&task->cg_list, use_mg_tasks ? &to_cset->mg_tasks : &to_cset->tasks); } @@ -3338,6 +3339,79 @@ static int cgroup_stat_show(struct seq_file *seq, void *v) return 0; } +#ifdef CONFIG_PSI +static int cgroup_io_pressure_show(struct seq_file *seq, void *v) +{ + return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_IO); +} +static int cgroup_memory_pressure_show(struct seq_file *seq, void *v) +{ + return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_MEM); +} +static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v) +{ + return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_CPU); +} + +static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, enum psi_res res) +{ + struct psi_trigger *new; + struct cgroup *cgrp; + + cgrp = cgroup_kn_lock_live(of->kn, false); + if (!cgrp) + return -ENODEV; + + cgroup_get(cgrp); + cgroup_kn_unlock(of->kn); + + new = psi_trigger_create(&cgrp->psi, buf, nbytes, res); + if (IS_ERR(new)) { + cgroup_put(cgrp); + return PTR_ERR(new); + } + + psi_trigger_replace(&of->priv, new); + + cgroup_put(cgrp); + + return nbytes; +} + +static ssize_t cgroup_io_pressure_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + return cgroup_pressure_write(of, buf, nbytes, PSI_IO); +} + +static ssize_t cgroup_memory_pressure_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + return cgroup_pressure_write(of, buf, nbytes, PSI_MEM); +} + +static ssize_t cgroup_cpu_pressure_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + return cgroup_pressure_write(of, buf, nbytes, PSI_CPU); +} + +static unsigned int cgroup_pressure_poll(struct kernfs_open_file *of, + poll_table *pt) +{ + return psi_trigger_poll(&of->priv, of->file, pt); +} + +static void cgroup_pressure_release(struct kernfs_open_file *of) +{ + psi_trigger_replace(&of->priv, NULL); +} +#endif /* CONFIG_PSI */ + static int cgroup_file_open(struct kernfs_open_file *of) { struct cftype *cft = of->kn->priv; @@ -3405,6 +3479,17 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, return ret ?: nbytes; } +static unsigned int cgroup_file_poll(struct kernfs_open_file *of, + poll_table *pt) +{ + struct cftype *cft = of->kn->priv; + + if (cft->poll) + return cft->poll(of, pt); + + return kernfs_generic_poll(of, pt); +} + static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos) { return seq_cft(seq)->seq_start(seq, ppos); @@ -3443,6 +3528,7 @@ static struct kernfs_ops cgroup_kf_single_ops = { .open = cgroup_file_open, .release = cgroup_file_release, .write = cgroup_file_write, + .poll = cgroup_file_poll, .seq_show = cgroup_seqfile_show, }; @@ -3451,6 +3537,7 @@ static struct kernfs_ops cgroup_kf_ops = { .open = cgroup_file_open, .release = cgroup_file_release, .write = cgroup_file_write, + .poll = cgroup_file_poll, .seq_start = cgroup_seqfile_start, .seq_next = cgroup_seqfile_next, .seq_stop = cgroup_seqfile_stop, @@ -4494,6 +4581,32 @@ static struct cftype cgroup_base_files[] = { .name = "cgroup.stat", .seq_show = cgroup_stat_show, }, +#ifdef CONFIG_PSI + { + .name = "io.pressure", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cgroup_io_pressure_show, + .write = cgroup_io_pressure_write, + .poll = cgroup_pressure_poll, + .release = cgroup_pressure_release, + }, + { + .name = "memory.pressure", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cgroup_memory_pressure_show, + .write = cgroup_memory_pressure_write, + .poll = cgroup_pressure_poll, + .release = cgroup_pressure_release, + }, + { + .name = "cpu.pressure", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cgroup_cpu_pressure_show, + .write = cgroup_cpu_pressure_write, + .poll = cgroup_pressure_poll, + .release = cgroup_pressure_release, + }, +#endif /* CONFIG_PSI */ { } /* terminate */ }; @@ -4554,6 +4667,8 @@ static void css_free_work_fn(struct work_struct *work) */ cgroup_put(cgroup_parent(cgrp)); kernfs_put(cgrp->kn); + if (cgroup_on_dfl(cgrp)) + psi_cgroup_free(cgrp); kfree(cgrp); } else { /* @@ -4834,6 +4949,12 @@ static struct cgroup *cgroup_create(struct cgroup *parent) if (!cgroup_on_dfl(cgrp)) cgrp->subtree_control = cgroup_control(cgrp); + if (cgroup_on_dfl(cgrp)) { + ret = psi_cgroup_alloc(cgrp); + if (ret) + goto out_idr_free; + } + if (parent) cgroup_bpf_inherit(cgrp, parent); @@ -4841,6 +4962,8 @@ static struct cgroup *cgroup_create(struct cgroup *parent) return cgrp; +out_idr_free: + cgroup_idr_remove(&root->cgroup_idr, cgrp->id); out_cancel_ref: percpu_ref_exit(&cgrp->self.refcnt); out_free_cgrp: diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 0a0e1aa11f5e..f834680ca42b 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -103,6 +103,7 @@ struct cpuset { /* user-configured CPUs and Memory Nodes allow to tasks */ cpumask_var_t cpus_allowed; + cpumask_var_t cpus_requested; nodemask_t mems_allowed; /* effective CPUs and Memory Nodes allow to tasks */ @@ -412,7 +413,7 @@ static void cpuset_update_task_spread_flag(struct cpuset *cs, static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q) { - return cpumask_subset(p->cpus_allowed, q->cpus_allowed) && + return cpumask_subset(p->cpus_requested, q->cpus_requested) && nodes_subset(p->mems_allowed, q->mems_allowed) && is_cpu_exclusive(p) <= is_cpu_exclusive(q) && is_mem_exclusive(p) <= is_mem_exclusive(q); @@ -511,7 +512,7 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial) cpuset_for_each_child(c, css, par) { if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) && c != cur && - cpumask_intersects(trial->cpus_allowed, c->cpus_allowed)) + cpumask_intersects(trial->cpus_requested, c->cpus_requested)) goto out; if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) && c != cur && @@ -976,17 +977,18 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, if (!*buf) { cpumask_clear(trialcs->cpus_allowed); } else { - retval = cpulist_parse(buf, trialcs->cpus_allowed); + retval = cpulist_parse(buf, trialcs->cpus_requested); if (retval < 0) return retval; - if (!cpumask_subset(trialcs->cpus_allowed, - top_cpuset.cpus_allowed)) + if (!cpumask_subset(trialcs->cpus_requested, cpu_present_mask)) return -EINVAL; + + cpumask_and(trialcs->cpus_allowed, trialcs->cpus_requested, cpu_active_mask); } /* Nothing to do if the cpus didn't change */ - if (cpumask_equal(cs->cpus_allowed, trialcs->cpus_allowed)) + if (cpumask_equal(cs->cpus_requested, trialcs->cpus_requested)) return 0; retval = validate_change(cs, trialcs); @@ -995,6 +997,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, spin_lock_irq(&callback_lock); cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed); + cpumask_copy(cs->cpus_requested, trialcs->cpus_requested); spin_unlock_irq(&callback_lock); /* use trialcs->cpus_allowed as a temp variable */ @@ -1763,7 +1766,7 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v) switch (type) { case FILE_CPULIST: - seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->cpus_allowed)); + seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->cpus_requested)); break; case FILE_MEMLIST: seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->mems_allowed)); @@ -1953,11 +1956,14 @@ cpuset_css_alloc(struct cgroup_subsys_state *parent_css) return ERR_PTR(-ENOMEM); if (!alloc_cpumask_var(&cs->cpus_allowed, GFP_KERNEL)) goto free_cs; + if (!alloc_cpumask_var(&cs->cpus_requested, GFP_KERNEL)) + goto free_allowed; if (!alloc_cpumask_var(&cs->effective_cpus, GFP_KERNEL)) - goto free_cpus; + goto free_requested; set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); cpumask_clear(cs->cpus_allowed); + cpumask_clear(cs->cpus_requested); nodes_clear(cs->mems_allowed); cpumask_clear(cs->effective_cpus); nodes_clear(cs->effective_mems); @@ -1966,7 +1972,9 @@ cpuset_css_alloc(struct cgroup_subsys_state *parent_css) return &cs->css; -free_cpus: +free_requested: + free_cpumask_var(cs->cpus_requested); +free_allowed: free_cpumask_var(cs->cpus_allowed); free_cs: kfree(cs); @@ -2029,6 +2037,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) cs->mems_allowed = parent->mems_allowed; cs->effective_mems = parent->mems_allowed; cpumask_copy(cs->cpus_allowed, parent->cpus_allowed); + cpumask_copy(cs->cpus_requested, parent->cpus_requested); cpumask_copy(cs->effective_cpus, parent->cpus_allowed); spin_unlock_irq(&callback_lock); out_unlock: @@ -2063,6 +2072,7 @@ static void cpuset_css_free(struct cgroup_subsys_state *css) free_cpumask_var(cs->effective_cpus); free_cpumask_var(cs->cpus_allowed); + free_cpumask_var(cs->cpus_requested); kfree(cs); } @@ -2125,8 +2135,10 @@ int __init cpuset_init(void) BUG_ON(!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL)); + BUG_ON(!alloc_cpumask_var(&top_cpuset.cpus_requested, GFP_KERNEL)); cpumask_setall(top_cpuset.cpus_allowed); + cpumask_setall(top_cpuset.cpus_requested); nodes_setall(top_cpuset.mems_allowed); cpumask_setall(top_cpuset.effective_cpus); nodes_setall(top_cpuset.effective_mems); @@ -2259,7 +2271,7 @@ retry: goto retry; } - cpumask_and(&new_cpus, cs->cpus_allowed, parent_cs(cs)->effective_cpus); + cpumask_and(&new_cpus, cs->cpus_requested, parent_cs(cs)->effective_cpus); nodes_and(new_mems, cs->mems_allowed, parent_cs(cs)->effective_mems); cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus); diff --git a/kernel/configs/android-base.config b/kernel/configs/android-base.config deleted file mode 100644 index d3fd428f4b92..000000000000 --- a/kernel/configs/android-base.config +++ /dev/null @@ -1,161 +0,0 @@ -# KEEP ALPHABETICALLY SORTED -# CONFIG_DEVKMEM is not set -# CONFIG_DEVMEM is not set -# CONFIG_FHANDLE is not set -# CONFIG_INET_LRO is not set -# CONFIG_NFSD is not set -# CONFIG_NFS_FS is not set -# CONFIG_OABI_COMPAT is not set -# CONFIG_SYSVIPC is not set -# CONFIG_USELIB is not set -CONFIG_ANDROID=y -CONFIG_ANDROID_BINDER_IPC=y -CONFIG_ANDROID_BINDER_DEVICES=binder,hwbinder,vndbinder -CONFIG_ANDROID_LOW_MEMORY_KILLER=y -CONFIG_ARMV8_DEPRECATED=y -CONFIG_ASHMEM=y -CONFIG_AUDIT=y -CONFIG_BLK_DEV_INITRD=y -CONFIG_CGROUPS=y -CONFIG_CGROUP_BPF=y -CONFIG_CGROUP_CPUACCT=y -CONFIG_CGROUP_DEBUG=y -CONFIG_CGROUP_FREEZER=y -CONFIG_CGROUP_SCHED=y -CONFIG_CP15_BARRIER_EMULATION=y -CONFIG_DEFAULT_SECURITY_SELINUX=y -CONFIG_EMBEDDED=y -CONFIG_FB=y -CONFIG_HARDENED_USERCOPY=y -CONFIG_HIGH_RES_TIMERS=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -CONFIG_INET6_AH=y -CONFIG_INET6_ESP=y -CONFIG_INET6_IPCOMP=y -CONFIG_INET=y -CONFIG_INET_DIAG_DESTROY=y -CONFIG_INET_ESP=y -CONFIG_INET_XFRM_MODE_TUNNEL=y -CONFIG_IP6_NF_FILTER=y -CONFIG_IP6_NF_IPTABLES=y -CONFIG_IP6_NF_MANGLE=y -CONFIG_IP6_NF_RAW=y -CONFIG_IP6_NF_TARGET_REJECT=y -CONFIG_IPV6=y -CONFIG_IPV6_MIP6=y -CONFIG_IPV6_MULTIPLE_TABLES=y -CONFIG_IPV6_OPTIMISTIC_DAD=y -CONFIG_IPV6_ROUTER_PREF=y -CONFIG_IPV6_ROUTE_INFO=y -CONFIG_IP_ADVANCED_ROUTER=y -CONFIG_IP_MULTICAST=y -CONFIG_IP_MULTIPLE_TABLES=y -CONFIG_IP_NF_ARPFILTER=y -CONFIG_IP_NF_ARPTABLES=y -CONFIG_IP_NF_ARP_MANGLE=y -CONFIG_IP_NF_FILTER=y -CONFIG_IP_NF_IPTABLES=y -CONFIG_IP_NF_MANGLE=y -CONFIG_IP_NF_MATCH_AH=y -CONFIG_IP_NF_MATCH_ECN=y -CONFIG_IP_NF_MATCH_TTL=y -CONFIG_IP_NF_NAT=y -CONFIG_IP_NF_RAW=y -CONFIG_IP_NF_SECURITY=y -CONFIG_IP_NF_TARGET_MASQUERADE=y -CONFIG_IP_NF_TARGET_NETMAP=y -CONFIG_IP_NF_TARGET_REDIRECT=y -CONFIG_IP_NF_TARGET_REJECT=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -CONFIG_MODVERSIONS=y -CONFIG_NET=y -CONFIG_NETDEVICES=y -CONFIG_NETFILTER=y -CONFIG_NETFILTER_TPROXY=y -CONFIG_NETFILTER_XT_MATCH_COMMENT=y -CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=y -CONFIG_NETFILTER_XT_MATCH_CONNMARK=y -CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y -CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=y -CONFIG_NETFILTER_XT_MATCH_HELPER=y -CONFIG_NETFILTER_XT_MATCH_IPRANGE=y -CONFIG_NETFILTER_XT_MATCH_LENGTH=y -CONFIG_NETFILTER_XT_MATCH_LIMIT=y -CONFIG_NETFILTER_XT_MATCH_MAC=y -CONFIG_NETFILTER_XT_MATCH_MARK=y -CONFIG_NETFILTER_XT_MATCH_PKTTYPE=y -CONFIG_NETFILTER_XT_MATCH_POLICY=y -CONFIG_NETFILTER_XT_MATCH_QUOTA=y -CONFIG_NETFILTER_XT_MATCH_SOCKET=y -CONFIG_NETFILTER_XT_MATCH_STATE=y -CONFIG_NETFILTER_XT_MATCH_STATISTIC=y -CONFIG_NETFILTER_XT_MATCH_STRING=y -CONFIG_NETFILTER_XT_MATCH_TIME=y -CONFIG_NETFILTER_XT_MATCH_U32=y -CONFIG_NETFILTER_XT_TARGET_CLASSIFY=y -CONFIG_NETFILTER_XT_TARGET_CONNMARK=y -CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y -CONFIG_NETFILTER_XT_TARGET_IDLETIMER=y -CONFIG_NETFILTER_XT_TARGET_MARK=y -CONFIG_NETFILTER_XT_TARGET_NFLOG=y -CONFIG_NETFILTER_XT_TARGET_NFQUEUE=y -CONFIG_NETFILTER_XT_TARGET_SECMARK=y -CONFIG_NETFILTER_XT_TARGET_TCPMSS=y -CONFIG_NETFILTER_XT_TARGET_TPROXY=y -CONFIG_NETFILTER_XT_TARGET_TRACE=y -CONFIG_NET_CLS_ACT=y -CONFIG_NET_CLS_U32=y -CONFIG_NET_EMATCH=y -CONFIG_NET_EMATCH_U32=y -CONFIG_NET_KEY=y -CONFIG_NET_SCHED=y -CONFIG_NET_SCH_HTB=y -CONFIG_NF_CONNTRACK=y -CONFIG_NF_CONNTRACK_AMANDA=y -CONFIG_NF_CONNTRACK_EVENTS=y -CONFIG_NF_CONNTRACK_FTP=y -CONFIG_NF_CONNTRACK_H323=y -CONFIG_NF_CONNTRACK_IPV4=y -CONFIG_NF_CONNTRACK_IPV6=y -CONFIG_NF_CONNTRACK_IRC=y -CONFIG_NF_CONNTRACK_NETBIOS_NS=y -CONFIG_NF_CONNTRACK_PPTP=y -CONFIG_NF_CONNTRACK_SANE=y -CONFIG_NF_CONNTRACK_SECMARK=y -CONFIG_NF_CONNTRACK_TFTP=y -CONFIG_NF_CT_NETLINK=y -CONFIG_NF_CT_PROTO_DCCP=y -CONFIG_NF_CT_PROTO_SCTP=y -CONFIG_NF_CT_PROTO_UDPLITE=y -CONFIG_NF_NAT=y -CONFIG_NO_HZ=y -CONFIG_PACKET=y -CONFIG_PM_AUTOSLEEP=y -CONFIG_PM_WAKELOCKS=y -CONFIG_PPP=y -CONFIG_PPP_BSDCOMP=y -CONFIG_PPP_DEFLATE=y -CONFIG_PPP_MPPE=y -CONFIG_PREEMPT=y -CONFIG_QUOTA=y -CONFIG_RANDOMIZE_BASE=y -CONFIG_RTC_CLASS=y -CONFIG_RT_GROUP_SCHED=y -CONFIG_SECCOMP=y -CONFIG_SECURITY=y -CONFIG_SECURITY_NETWORK=y -CONFIG_SECURITY_SELINUX=y -CONFIG_SETEND_EMULATION=y -CONFIG_STAGING=y -CONFIG_SWP_EMULATION=y -CONFIG_SYNC=y -CONFIG_TUN=y -CONFIG_UNIX=y -CONFIG_USB_GADGET=y -CONFIG_USB_CONFIGFS=y -CONFIG_USB_CONFIGFS_F_FS=y -CONFIG_USB_CONFIGFS_F_MIDI=y -CONFIG_USB_OTG_WAKELOCK=y -CONFIG_XFRM_USER=y diff --git a/kernel/configs/android-fetch-configs.sh b/kernel/configs/android-fetch-configs.sh new file mode 100755 index 000000000000..2dcd2981e1be --- /dev/null +++ b/kernel/configs/android-fetch-configs.sh @@ -0,0 +1,4 @@ +#!/bin/sh + +curl https://android.googlesource.com/kernel/configs/+archive/master/android-4.14.tar.gz | tar xzv + diff --git a/kernel/configs/android-recommended.config b/kernel/configs/android-recommended.config deleted file mode 100644 index 946fb92418f7..000000000000 --- a/kernel/configs/android-recommended.config +++ /dev/null @@ -1,129 +0,0 @@ -# KEEP ALPHABETICALLY SORTED -# CONFIG_AIO is not set -# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set -# CONFIG_INPUT_MOUSE is not set -# CONFIG_LEGACY_PTYS is not set -# CONFIG_NF_CONNTRACK_SIP is not set -# CONFIG_PM_WAKELOCKS_GC is not set -# CONFIG_VT is not set -CONFIG_ARM64_SW_TTBR0_PAN=y -CONFIG_BACKLIGHT_LCD_SUPPORT=y -CONFIG_BLK_DEV_DM=y -CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_SIZE=8192 -CONFIG_CC_STACKPROTECTOR_STRONG=y -CONFIG_COMPACTION=y -CONFIG_CPU_SW_DOMAIN_PAN=y -CONFIG_DM_CRYPT=y -CONFIG_DM_UEVENT=y -CONFIG_DM_VERITY=y -CONFIG_DM_VERITY_FEC=y -CONFIG_DRAGONRISE_FF=y -CONFIG_ENABLE_DEFAULT_TRACERS=y -CONFIG_EXT4_FS=y -CONFIG_EXT4_FS_SECURITY=y -CONFIG_FUSE_FS=y -CONFIG_GREENASIA_FF=y -CONFIG_HIDRAW=y -CONFIG_HID_A4TECH=y -CONFIG_HID_ACRUX=y -CONFIG_HID_ACRUX_FF=y -CONFIG_HID_APPLE=y -CONFIG_HID_BELKIN=y -CONFIG_HID_CHERRY=y -CONFIG_HID_CHICONY=y -CONFIG_HID_CYPRESS=y -CONFIG_HID_DRAGONRISE=y -CONFIG_HID_ELECOM=y -CONFIG_HID_EMS_FF=y -CONFIG_HID_EZKEY=y -CONFIG_HID_GREENASIA=y -CONFIG_HID_GYRATION=y -CONFIG_HID_HOLTEK=y -CONFIG_HID_KENSINGTON=y -CONFIG_HID_KEYTOUCH=y -CONFIG_HID_KYE=y -CONFIG_HID_LCPOWER=y -CONFIG_HID_LOGITECH=y -CONFIG_HID_LOGITECH_DJ=y -CONFIG_HID_MAGICMOUSE=y -CONFIG_HID_MICROSOFT=y -CONFIG_HID_MONTEREY=y -CONFIG_HID_MULTITOUCH=y -CONFIG_HID_NTRIG=y -CONFIG_HID_ORTEK=y -CONFIG_HID_PANTHERLORD=y -CONFIG_HID_PETALYNX=y -CONFIG_HID_PICOLCD=y -CONFIG_HID_PRIMAX=y -CONFIG_HID_PRODIKEYS=y -CONFIG_HID_ROCCAT=y -CONFIG_HID_SAITEK=y -CONFIG_HID_SAMSUNG=y -CONFIG_HID_SMARTJOYPLUS=y -CONFIG_HID_SONY=y -CONFIG_HID_SPEEDLINK=y -CONFIG_HID_SUNPLUS=y -CONFIG_HID_THRUSTMASTER=y -CONFIG_HID_TIVO=y -CONFIG_HID_TOPSEED=y -CONFIG_HID_TWINHAN=y -CONFIG_HID_UCLOGIC=y -CONFIG_HID_WACOM=y -CONFIG_HID_WALTOP=y -CONFIG_HID_WIIMOTE=y -CONFIG_HID_ZEROPLUS=y -CONFIG_HID_ZYDACRON=y -CONFIG_INPUT_EVDEV=y -CONFIG_INPUT_GPIO=y -CONFIG_INPUT_JOYSTICK=y -CONFIG_INPUT_MISC=y -CONFIG_INPUT_TABLET=y -CONFIG_INPUT_UINPUT=y -CONFIG_ION=y -CONFIG_JOYSTICK_XPAD=y -CONFIG_JOYSTICK_XPAD_FF=y -CONFIG_JOYSTICK_XPAD_LEDS=y -CONFIG_KALLSYMS_ALL=y -CONFIG_KSM=y -CONFIG_LOGIG940_FF=y -CONFIG_LOGIRUMBLEPAD2_FF=y -CONFIG_LOGITECH_FF=y -CONFIG_MD=y -CONFIG_MEDIA_SUPPORT=y -CONFIG_MSDOS_FS=y -CONFIG_PANIC_TIMEOUT=5 -CONFIG_PANTHERLORD_FF=y -CONFIG_PERF_EVENTS=y -CONFIG_PM_DEBUG=y -CONFIG_PM_RUNTIME=y -CONFIG_PM_WAKELOCKS_LIMIT=0 -CONFIG_POWER_SUPPLY=y -CONFIG_PSTORE=y -CONFIG_PSTORE_CONSOLE=y -CONFIG_PSTORE_RAM=y -CONFIG_SCHEDSTATS=y -CONFIG_SMARTJOYPLUS_FF=y -CONFIG_SND=y -CONFIG_SOUND=y -CONFIG_STRICT_KERNEL_RWX=y -CONFIG_SUSPEND_TIME=y -CONFIG_TABLET_USB_ACECAD=y -CONFIG_TABLET_USB_AIPTEK=y -CONFIG_TABLET_USB_GTCO=y -CONFIG_TABLET_USB_HANWANG=y -CONFIG_TABLET_USB_KBTAB=y -CONFIG_TASKSTATS=y -CONFIG_TASK_DELAY_ACCT=y -CONFIG_TASK_IO_ACCOUNTING=y -CONFIG_TASK_XACCT=y -CONFIG_TIMER_STATS=y -CONFIG_TMPFS=y -CONFIG_TMPFS_POSIX_ACL=y -CONFIG_UHID=y -CONFIG_USB_ANNOUNCE_NEW_DEVICES=y -CONFIG_USB_EHCI_HCD=y -CONFIG_USB_HIDDEV=y -CONFIG_USB_USBNET=y -CONFIG_VFAT_FS=y diff --git a/kernel/cpu.c b/kernel/cpu.c index d8c77bfb6e7e..8254270fc427 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1242,6 +1242,7 @@ void __weak arch_enable_nonboot_cpus_end(void) void enable_nonboot_cpus(void) { int cpu, error; + struct device *cpu_device; /* Allow everyone to use the CPU hotplug again */ cpu_maps_update_begin(); @@ -1259,6 +1260,12 @@ void enable_nonboot_cpus(void) trace_suspend_resume(TPS("CPU_ON"), cpu, false); if (!error) { pr_info("CPU%d is up\n", cpu); + cpu_device = get_cpu_device(cpu); + if (!cpu_device) + pr_err("%s: failed to get cpu%d device\n", + __func__, cpu); + else + kobject_uevent(&cpu_device->kobj, KOBJ_ONLINE); continue; } pr_warn("Error taking CPU%d up: %d\n", cpu, error); diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index 6a4b41484afe..1a94ff18a462 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -217,7 +217,7 @@ static char *kdb_read(char *buffer, size_t bufsize) int i; int diag, dtab_count; int key, buf_size, ret; - + static int last_crlf; diag = kdbgetintenv("DTABCOUNT", &dtab_count); if (diag) @@ -238,6 +238,9 @@ poll_again: return buffer; if (key != 9) tab = 0; + if (key != 10 && key != 13) + last_crlf = 0; + switch (key) { case 8: /* backspace */ if (cp > buffer) { @@ -255,7 +258,12 @@ poll_again: *cp = tmp; } break; - case 13: /* enter */ + case 10: /* new line */ + case 13: /* carriage return */ + /* handle \n after \r */ + if (last_crlf && last_crlf != key) + break; + last_crlf = key; *lastchar++ = '\n'; *lastchar++ = '\0'; if (!KDB_STATE(KGDB_TRANS)) { diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 15d902daeef6..90bd7895dc85 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -2586,16 +2586,11 @@ static int kdb_summary(int argc, const char **argv) } kdb_printf("%02ld:%02ld\n", val.uptime/(60*60), (val.uptime/60)%60); - /* lifted from fs/proc/proc_misc.c::loadavg_read_proc() */ - -#define LOAD_INT(x) ((x) >> FSHIFT) -#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) kdb_printf("load avg %ld.%02ld %ld.%02ld %ld.%02ld\n", LOAD_INT(val.loads[0]), LOAD_FRAC(val.loads[0]), LOAD_INT(val.loads[1]), LOAD_FRAC(val.loads[1]), LOAD_INT(val.loads[2]), LOAD_FRAC(val.loads[2])); -#undef LOAD_INT -#undef LOAD_FRAC + /* Display in kilobytes */ #define K(x) ((x) << (PAGE_SHIFT - 10)) kdb_printf("\nMemTotal: %8lu kB\nMemFree: %8lu kB\n" diff --git a/kernel/delayacct.c b/kernel/delayacct.c index ca8ac2824f0b..2a12b988c717 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -135,9 +135,12 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) d->swapin_delay_total = (tmp < d->swapin_delay_total) ? 0 : tmp; tmp = d->freepages_delay_total + tsk->delays->freepages_delay; d->freepages_delay_total = (tmp < d->freepages_delay_total) ? 0 : tmp; + tmp = d->thrashing_delay_total + tsk->delays->thrashing_delay; + d->thrashing_delay_total = (tmp < d->thrashing_delay_total) ? 0 : tmp; d->blkio_count += tsk->delays->blkio_count; d->swapin_count += tsk->delays->swapin_count; d->freepages_count += tsk->delays->freepages_count; + d->thrashing_count += tsk->delays->thrashing_count; raw_spin_unlock_irqrestore(&tsk->delays->lock, flags); return 0; @@ -169,3 +172,15 @@ void __delayacct_freepages_end(void) ¤t->delays->freepages_count); } +void __delayacct_thrashing_start(void) +{ + current->delays->thrashing_start = ktime_get_ns(); +} + +void __delayacct_thrashing_end(void) +{ + delayacct_end(¤t->delays->lock, + ¤t->delays->thrashing_start, + ¤t->delays->thrashing_delay, + ¤t->delays->thrashing_count); +} diff --git a/kernel/events/core.c b/kernel/events/core.c index e50b140053f9..edf872b47a04 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -402,8 +402,13 @@ static cpumask_var_t perf_online_mask; * 0 - disallow raw tracepoint access for unpriv * 1 - disallow cpu events for unpriv * 2 - disallow kernel profiling for unpriv + * 3 - disallow all unpriv perf event use */ +#ifdef CONFIG_SECURITY_PERF_EVENTS_RESTRICT +int sysctl_perf_event_paranoid __read_mostly = 3; +#else int sysctl_perf_event_paranoid __read_mostly = 2; +#endif /* Minimum for 512 kiB + 1 user control page */ int sysctl_perf_event_mlock __read_mostly = 512 + (PAGE_SIZE / 1024); /* 'free' kiB per user */ @@ -10028,6 +10033,9 @@ SYSCALL_DEFINE5(perf_event_open, if (flags & ~PERF_FLAG_ALL) return -EINVAL; + if (perf_paranoid_any() && !capable(CAP_SYS_ADMIN)) + return -EACCES; + err = perf_copy_attr(attr_uptr, &attr); if (err) return err; diff --git a/kernel/fork.c b/kernel/fork.c index 0a328cf0cb13..c106b2c1681e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -90,6 +90,7 @@ #include <linux/kcov.h> #include <linux/livepatch.h> #include <linux/thread_info.h> +#include <linux/cpufreq_times.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> @@ -361,6 +362,8 @@ void put_task_stack(struct task_struct *tsk) void free_task(struct task_struct *tsk) { + cpufreq_task_times_exit(tsk); + #ifndef CONFIG_THREAD_INFO_IN_TASK /* * The task is finally done with both the stack and thread_info, @@ -1612,6 +1615,8 @@ static __latent_entropy struct task_struct *copy_process( if (!p) goto fork_out; + cpufreq_task_times_init(p); + /* * This _must_ happen before we call free_task(), i.e. before we jump * to any of the bad_fork_* labels. This is to avoid freeing @@ -1683,6 +1688,10 @@ static __latent_entropy struct task_struct *copy_process( p->default_timer_slack_ns = current->timer_slack_ns; +#ifdef CONFIG_PSI + p->psi_flags = 0; +#endif + task_io_accounting_init(&p->ioac); acct_clear_integrals(p); @@ -2078,6 +2087,8 @@ long _do_fork(unsigned long clone_flags, struct completion vfork; struct pid *pid; + cpufreq_task_times_alloc(p); + trace_sched_process_fork(current, p); pid = get_task_pid(p, PIDTYPE_PID); diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 3e1b66366ac2..06432e1a792a 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -304,6 +304,24 @@ int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize, !!__bpf_address_lookup(addr, symbolsize, offset, namebuf); } +#ifdef CONFIG_CFI_CLANG +/* + * LLVM appends .cfi to function names when CONFIG_CFI_CLANG is enabled, + * which causes confusion and potentially breaks user space tools, so we + * will strip the postfix from expanded symbol names. + */ +static inline void cleanup_symbol_name(char *s) +{ + char *res; + + res = strrchr(s, '.'); + if (res && !strcmp(res, ".cfi")) + *res = '\0'; +} +#else +static inline void cleanup_symbol_name(char *s) {} +#endif + /* * Lookup an address * - modname is set to NULL if it's in the kernel. @@ -330,7 +348,9 @@ const char *kallsyms_lookup(unsigned long addr, namebuf, KSYM_NAME_LEN); if (modname) *modname = NULL; - return namebuf; + + ret = namebuf; + goto found; } /* See if it's in a module or a BPF JITed image. */ @@ -339,11 +359,16 @@ const char *kallsyms_lookup(unsigned long addr, if (!ret) ret = bpf_address_lookup(addr, symbolsize, offset, modname, namebuf); + +found: + cleanup_symbol_name(namebuf); return ret; } int lookup_symbol_name(unsigned long addr, char *symname) { + int res; + symname[0] = '\0'; symname[KSYM_NAME_LEN - 1] = '\0'; @@ -354,15 +379,23 @@ int lookup_symbol_name(unsigned long addr, char *symname) /* Grab name */ kallsyms_expand_symbol(get_symbol_offset(pos), symname, KSYM_NAME_LEN); - return 0; + goto found; } /* See if it's in a module. */ - return lookup_module_symbol_name(addr, symname); + res = lookup_module_symbol_name(addr, symname); + if (res) + return res; + +found: + cleanup_symbol_name(symname); + return 0; } int lookup_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name) { + int res; + name[0] = '\0'; name[KSYM_NAME_LEN - 1] = '\0'; @@ -374,10 +407,16 @@ int lookup_symbol_attrs(unsigned long addr, unsigned long *size, kallsyms_expand_symbol(get_symbol_offset(pos), name, KSYM_NAME_LEN); modname[0] = '\0'; - return 0; + goto found; } /* See if it's in a module. */ - return lookup_module_symbol_attrs(addr, size, offset, modname, name); + res = lookup_module_symbol_attrs(addr, size, offset, modname, name); + if (res) + return res; + +found: + cleanup_symbol_name(name); + return 0; } /* Look up a kernel symbol and return it in a text buffer. */ diff --git a/kernel/module.c b/kernel/module.c index 2806c9b6577c..a43d6a370198 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2139,6 +2139,8 @@ void __weak module_arch_freeing_init(struct module *mod) { } +static void cfi_cleanup(struct module *mod); + /* Free a module, remove from lists, etc. */ static void free_module(struct module *mod) { @@ -2180,6 +2182,10 @@ static void free_module(struct module *mod) /* This may be empty, but that's OK */ disable_ro_nx(&mod->init_layout); + + /* Clean up CFI for the module. */ + cfi_cleanup(mod); + module_arch_freeing_init(mod); module_memfree(mod->init_layout.base); kfree(mod->args); @@ -3377,6 +3383,8 @@ int __weak module_finalize(const Elf_Ehdr *hdr, return 0; } +static void cfi_init(struct module *mod); + static int post_relocation(struct module *mod, const struct load_info *info) { /* Sort exception table now relocations are done. */ @@ -3389,6 +3397,9 @@ static int post_relocation(struct module *mod, const struct load_info *info) /* Setup kallsyms-specific fields. */ add_kallsyms(mod, info); + /* Setup CFI for the module. */ + cfi_init(mod); + /* Arch-specific module finalizing. */ return module_finalize(info->hdr, info->sechdrs, mod); } @@ -4134,6 +4145,22 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, } #endif /* CONFIG_KALLSYMS */ +static void cfi_init(struct module *mod) +{ +#ifdef CONFIG_CFI_CLANG + mod->cfi_check = + (cfi_check_fn)mod_find_symname(mod, CFI_CHECK_FN_NAME); + cfi_module_add(mod, module_addr_min, module_addr_max); +#endif +} + +static void cfi_cleanup(struct module *mod) +{ +#ifdef CONFIG_CFI_CLANG + cfi_module_remove(mod, module_addr_min, module_addr_max); +#endif +} + /* Maximum number of characters written by module_flags() */ #define MODULE_FLAGS_BUF_SIZE (TAINT_FLAGS_COUNT + 4) diff --git a/kernel/power/Makefile b/kernel/power/Makefile index a3f79f0eef36..5c1743d4d8ef 100644 --- a/kernel/power/Makefile +++ b/kernel/power/Makefile @@ -15,3 +15,5 @@ obj-$(CONFIG_PM_AUTOSLEEP) += autosleep.o obj-$(CONFIG_PM_WAKELOCKS) += wakelock.o obj-$(CONFIG_MAGIC_SYSRQ) += poweroff.o + +obj-$(CONFIG_SUSPEND) += wakeup_reason.o diff --git a/kernel/power/process.c b/kernel/power/process.c index 7381d49a44db..c366e3d34a07 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -22,6 +22,7 @@ #include <linux/kmod.h> #include <trace/events/power.h> #include <linux/cpuset.h> +#include <linux/wakeup_reason.h> /* * Timeout for stopping processes @@ -38,6 +39,9 @@ static int try_to_freeze_tasks(bool user_only) unsigned int elapsed_msecs; bool wakeup = false; int sleep_usecs = USEC_PER_MSEC; +#ifdef CONFIG_PM_SLEEP + char suspend_abort[MAX_SUSPEND_ABORT_LEN]; +#endif start = ktime_get_boottime(); @@ -67,6 +71,11 @@ static int try_to_freeze_tasks(bool user_only) break; if (pm_wakeup_pending()) { +#ifdef CONFIG_PM_SLEEP + pm_get_active_wakeup_sources(suspend_abort, + MAX_SUSPEND_ABORT_LEN); + log_suspend_abort_reason(suspend_abort); +#endif wakeup = true; break; } @@ -85,26 +94,27 @@ static int try_to_freeze_tasks(bool user_only) elapsed = ktime_sub(end, start); elapsed_msecs = ktime_to_ms(elapsed); - if (todo) { + if (wakeup) { pr_cont("\n"); - pr_err("Freezing of tasks %s after %d.%03d seconds " - "(%d tasks refusing to freeze, wq_busy=%d):\n", - wakeup ? "aborted" : "failed", + pr_err("Freezing of tasks aborted after %d.%03d seconds", + elapsed_msecs / 1000, elapsed_msecs % 1000); + } else if (todo) { + pr_cont("\n"); + pr_err("Freezing of tasks failed after %d.%03d seconds" + " (%d tasks refusing to freeze, wq_busy=%d):\n", elapsed_msecs / 1000, elapsed_msecs % 1000, todo - wq_busy, wq_busy); if (wq_busy) show_workqueue_state(); - if (!wakeup) { - read_lock(&tasklist_lock); - for_each_process_thread(g, p) { - if (p != current && !freezer_should_skip(p) - && freezing(p) && !frozen(p)) - sched_show_task(p); - } - read_unlock(&tasklist_lock); + read_lock(&tasklist_lock); + for_each_process_thread(g, p) { + if (p != current && !freezer_should_skip(p) + && freezing(p) && !frozen(p)) + sched_show_task(p); } + read_unlock(&tasklist_lock); } else { pr_cont("(elapsed %d.%03d seconds) ", elapsed_msecs / 1000, elapsed_msecs % 1000); diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index c0bc2c89697a..4789ca7e1019 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -31,6 +31,7 @@ #include <trace/events/power.h> #include <linux/compiler.h> #include <linux/moduleparam.h> +#include <linux/wakeup_reason.h> #include "power.h" @@ -389,7 +390,8 @@ void __weak arch_suspend_enable_irqs(void) */ static int suspend_enter(suspend_state_t state, bool *wakeup) { - int error; + char suspend_abort[MAX_SUSPEND_ABORT_LEN]; + int error, last_dev; error = platform_suspend_prepare(state); if (error) @@ -397,7 +399,11 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) error = dpm_suspend_late(PMSG_SUSPEND); if (error) { + last_dev = suspend_stats.last_failed_dev + REC_FAILED_NUM - 1; + last_dev %= REC_FAILED_NUM; pr_err("late suspend of devices failed\n"); + log_suspend_abort_reason("%s device failed to power down", + suspend_stats.failed_devs[last_dev]); goto Platform_finish; } error = platform_suspend_prepare_late(state); @@ -411,7 +417,11 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) error = dpm_suspend_noirq(PMSG_SUSPEND); if (error) { + last_dev = suspend_stats.last_failed_dev + REC_FAILED_NUM - 1; + last_dev %= REC_FAILED_NUM; pr_err("noirq suspend of devices failed\n"); + log_suspend_abort_reason("noirq suspend of %s device failed", + suspend_stats.failed_devs[last_dev]); goto Platform_early_resume; } error = platform_suspend_prepare_noirq(state); @@ -422,8 +432,10 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) goto Platform_wake; error = disable_nonboot_cpus(); - if (error || suspend_test(TEST_CPUS)) + if (error || suspend_test(TEST_CPUS)) { + log_suspend_abort_reason("Disabling non-boot cpus failed"); goto Enable_cpus; + } arch_suspend_disable_irqs(); BUG_ON(!irqs_disabled()); @@ -438,6 +450,9 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) trace_suspend_resume(TPS("machine_suspend"), state, false); } else if (*wakeup) { + pm_get_active_wakeup_sources(suspend_abort, + MAX_SUSPEND_ABORT_LEN); + log_suspend_abort_reason(suspend_abort); error = -EBUSY; } syscore_resume(); @@ -487,6 +502,7 @@ int suspend_devices_and_enter(suspend_state_t state) error = dpm_suspend_start(PMSG_SUSPEND); if (error) { pr_err("Some devices failed to suspend, or early wake event detected\n"); + log_suspend_abort_reason("Some devices failed to suspend, or early wake event detected"); goto Recover_platform; } suspend_test_finish("suspend devices"); diff --git a/kernel/power/wakeup_reason.c b/kernel/power/wakeup_reason.c new file mode 100644 index 000000000000..252611fad2fe --- /dev/null +++ b/kernel/power/wakeup_reason.c @@ -0,0 +1,225 @@ +/* + * kernel/power/wakeup_reason.c + * + * Logs the reasons which caused the kernel to resume from + * the suspend mode. + * + * Copyright (C) 2014 Google, Inc. + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include <linux/wakeup_reason.h> +#include <linux/kernel.h> +#include <linux/irq.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/kobject.h> +#include <linux/sysfs.h> +#include <linux/init.h> +#include <linux/spinlock.h> +#include <linux/notifier.h> +#include <linux/suspend.h> + + +#define MAX_WAKEUP_REASON_IRQS 32 +static int irq_list[MAX_WAKEUP_REASON_IRQS]; +static int irqcount; +static bool suspend_abort; +static char abort_reason[MAX_SUSPEND_ABORT_LEN]; +static struct kobject *wakeup_reason; +static DEFINE_SPINLOCK(resume_reason_lock); + +static ktime_t last_monotime; /* monotonic time before last suspend */ +static ktime_t curr_monotime; /* monotonic time after last suspend */ +static ktime_t last_stime; /* monotonic boottime offset before last suspend */ +static ktime_t curr_stime; /* monotonic boottime offset after last suspend */ + +static ssize_t last_resume_reason_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + int irq_no, buf_offset = 0; + struct irq_desc *desc; + spin_lock(&resume_reason_lock); + if (suspend_abort) { + buf_offset = sprintf(buf, "Abort: %s", abort_reason); + } else { + for (irq_no = 0; irq_no < irqcount; irq_no++) { + desc = irq_to_desc(irq_list[irq_no]); + if (desc && desc->action && desc->action->name) + buf_offset += sprintf(buf + buf_offset, "%d %s\n", + irq_list[irq_no], desc->action->name); + else + buf_offset += sprintf(buf + buf_offset, "%d\n", + irq_list[irq_no]); + } + } + spin_unlock(&resume_reason_lock); + return buf_offset; +} + +static ssize_t last_suspend_time_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + struct timespec sleep_time; + struct timespec total_time; + struct timespec suspend_resume_time; + + /* + * total_time is calculated from monotonic bootoffsets because + * unlike CLOCK_MONOTONIC it include the time spent in suspend state. + */ + total_time = ktime_to_timespec(ktime_sub(curr_stime, last_stime)); + + /* + * suspend_resume_time is calculated as monotonic (CLOCK_MONOTONIC) + * time interval before entering suspend and post suspend. + */ + suspend_resume_time = ktime_to_timespec(ktime_sub(curr_monotime, last_monotime)); + + /* sleep_time = total_time - suspend_resume_time */ + sleep_time = timespec_sub(total_time, suspend_resume_time); + + /* Export suspend_resume_time and sleep_time in pair here. */ + return sprintf(buf, "%lu.%09lu %lu.%09lu\n", + suspend_resume_time.tv_sec, suspend_resume_time.tv_nsec, + sleep_time.tv_sec, sleep_time.tv_nsec); +} + +static struct kobj_attribute resume_reason = __ATTR_RO(last_resume_reason); +static struct kobj_attribute suspend_time = __ATTR_RO(last_suspend_time); + +static struct attribute *attrs[] = { + &resume_reason.attr, + &suspend_time.attr, + NULL, +}; +static struct attribute_group attr_group = { + .attrs = attrs, +}; + +/* + * logs all the wake up reasons to the kernel + * stores the irqs to expose them to the userspace via sysfs + */ +void log_wakeup_reason(int irq) +{ + struct irq_desc *desc; + desc = irq_to_desc(irq); + if (desc && desc->action && desc->action->name) + printk(KERN_INFO "Resume caused by IRQ %d, %s\n", irq, + desc->action->name); + else + printk(KERN_INFO "Resume caused by IRQ %d\n", irq); + + spin_lock(&resume_reason_lock); + if (irqcount == MAX_WAKEUP_REASON_IRQS) { + spin_unlock(&resume_reason_lock); + printk(KERN_WARNING "Resume caused by more than %d IRQs\n", + MAX_WAKEUP_REASON_IRQS); + return; + } + + irq_list[irqcount++] = irq; + spin_unlock(&resume_reason_lock); +} + +int check_wakeup_reason(int irq) +{ + int irq_no; + int ret = false; + + spin_lock(&resume_reason_lock); + for (irq_no = 0; irq_no < irqcount; irq_no++) + if (irq_list[irq_no] == irq) { + ret = true; + break; + } + spin_unlock(&resume_reason_lock); + return ret; +} + +void log_suspend_abort_reason(const char *fmt, ...) +{ + va_list args; + + spin_lock(&resume_reason_lock); + + //Suspend abort reason has already been logged. + if (suspend_abort) { + spin_unlock(&resume_reason_lock); + return; + } + + suspend_abort = true; + va_start(args, fmt); + vsnprintf(abort_reason, MAX_SUSPEND_ABORT_LEN, fmt, args); + va_end(args); + spin_unlock(&resume_reason_lock); +} + +/* Detects a suspend and clears all the previous wake up reasons*/ +static int wakeup_reason_pm_event(struct notifier_block *notifier, + unsigned long pm_event, void *unused) +{ + switch (pm_event) { + case PM_SUSPEND_PREPARE: + spin_lock(&resume_reason_lock); + irqcount = 0; + suspend_abort = false; + spin_unlock(&resume_reason_lock); + /* monotonic time since boot */ + last_monotime = ktime_get(); + /* monotonic time since boot including the time spent in suspend */ + last_stime = ktime_get_boottime(); + break; + case PM_POST_SUSPEND: + /* monotonic time since boot */ + curr_monotime = ktime_get(); + /* monotonic time since boot including the time spent in suspend */ + curr_stime = ktime_get_boottime(); + break; + default: + break; + } + return NOTIFY_DONE; +} + +static struct notifier_block wakeup_reason_pm_notifier_block = { + .notifier_call = wakeup_reason_pm_event, +}; + +/* Initializes the sysfs parameter + * registers the pm_event notifier + */ +int __init wakeup_reason_init(void) +{ + int retval; + + retval = register_pm_notifier(&wakeup_reason_pm_notifier_block); + if (retval) + printk(KERN_WARNING "[%s] failed to register PM notifier %d\n", + __func__, retval); + + wakeup_reason = kobject_create_and_add("wakeup_reasons", kernel_kobj); + if (!wakeup_reason) { + printk(KERN_WARNING "[%s] failed to create a sysfs kobject\n", + __func__); + return 1; + } + retval = sysfs_create_group(wakeup_reason, &attr_group); + if (retval) { + kobject_put(wakeup_reason); + printk(KERN_WARNING "[%s] failed to create a sysfs group %d\n", + __func__, retval); + } + return 0; +} + +late_initcall(wakeup_reason_init); diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index a9ee16bbc693..c4f150b38b52 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -20,10 +20,14 @@ obj-y += core.o loadavg.o clock.o cputime.o obj-y += idle_task.o fair.o rt.o deadline.o obj-y += wait.o wait_bit.o swait.o completion.o idle.o obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o +obj-$(CONFIG_GENERIC_ARCH_TOPOLOGY) += energy.o +obj-$(CONFIG_SCHED_WALT) += walt.o obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o obj-$(CONFIG_SCHEDSTATS) += stats.o obj-$(CONFIG_SCHED_DEBUG) += debug.o +obj-$(CONFIG_SCHED_TUNE) += tune.o obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o obj-$(CONFIG_CPU_FREQ) += cpufreq.o obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o obj-$(CONFIG_MEMBARRIER) += membarrier.o +obj-$(CONFIG_PSI) += psi.o diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c index 1d179ab9ef8d..0c011dd5470b 100644 --- a/kernel/sched/autogroup.c +++ b/kernel/sched/autogroup.c @@ -263,7 +263,6 @@ out: } #endif /* CONFIG_PROC_FS */ -#ifdef CONFIG_SCHED_DEBUG int autogroup_path(struct task_group *tg, char *buf, int buflen) { if (!task_group_is_autogroup(tg)) @@ -271,4 +270,3 @@ int autogroup_path(struct task_group *tg, char *buf, int buflen) return snprintf(buf, buflen, "%s-%ld", "/autogroup", tg->autogroup->id); } -#endif /* CONFIG_SCHED_DEBUG */ diff --git a/kernel/sched/autogroup.h b/kernel/sched/autogroup.h index 27cd22b89824..590184bbdc7f 100644 --- a/kernel/sched/autogroup.h +++ b/kernel/sched/autogroup.h @@ -56,11 +56,9 @@ autogroup_task_group(struct task_struct *p, struct task_group *tg) return tg; } -#ifdef CONFIG_SCHED_DEBUG static inline int autogroup_path(struct task_group *tg, char *buf, int buflen) { return 0; } -#endif #endif /* CONFIG_SCHED_AUTOGROUP */ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index c5599174e745..069133eaa68b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -39,6 +39,7 @@ #define CREATE_TRACE_POINTS #include <trace/events/sched.h> +#include "walt.h" DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); @@ -439,6 +440,8 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task) if (cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL)) return; + head->count++; + get_task_struct(task); /* @@ -448,6 +451,10 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task) head->lastp = &node->next; } +static int +try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags, + int sibling_count_hint); + void wake_up_q(struct wake_q_head *head) { struct wake_q_node *node = head->first; @@ -462,10 +469,10 @@ void wake_up_q(struct wake_q_head *head) task->wake_q.next = NULL; /* - * wake_up_process() implies a wmb() to pair with the queueing + * try_to_wake_up() implies a wmb() to pair with the queueing * in wake_q_add() so as not to miss wakeups. */ - wake_up_process(task); + try_to_wake_up(task, TASK_NORMAL, 0, head->count); put_task_struct(task); } } @@ -757,8 +764,10 @@ static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags) if (!(flags & ENQUEUE_NOCLOCK)) update_rq_clock(rq); - if (!(flags & ENQUEUE_RESTORE)) + if (!(flags & ENQUEUE_RESTORE)) { sched_info_queued(rq, p); + psi_enqueue(p, flags & ENQUEUE_WAKEUP); + } p->sched_class->enqueue_task(rq, p, flags); } @@ -768,8 +777,10 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags) if (!(flags & DEQUEUE_NOCLOCK)) update_rq_clock(rq); - if (!(flags & DEQUEUE_SAVE)) + if (!(flags & DEQUEUE_SAVE)) { sched_info_dequeued(rq, p); + psi_dequeue(p, flags & DEQUEUE_SLEEP); + } p->sched_class->dequeue_task(rq, p, flags); } @@ -948,8 +959,10 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf, p->on_rq = TASK_ON_RQ_MIGRATING; dequeue_task(rq, p, DEQUEUE_NOCLOCK); + rq_unpin_lock(rq, rf); + double_lock_balance(rq, cpu_rq(new_cpu)); set_task_cpu(p, new_cpu); - rq_unlock(rq, rf); + double_rq_unlock(cpu_rq(new_cpu), rq); rq = cpu_rq(new_cpu); @@ -1206,6 +1219,8 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) p->sched_class->migrate_task_rq(p); p->se.nr_migrations++; perf_event_task_migrate(p); + + walt_fixup_busy_time(p, new_cpu); } __set_task_cpu(p, new_cpu); @@ -1555,12 +1570,14 @@ out: * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable. */ static inline -int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags) +int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags, + int sibling_count_hint) { lockdep_assert_held(&p->pi_lock); if (p->nr_cpus_allowed > 1) - cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags); + cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags, + sibling_count_hint); else cpu = cpumask_any(&p->cpus_allowed); @@ -1966,11 +1983,33 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) * */ +#ifdef CONFIG_SMP +#ifdef CONFIG_SCHED_WALT +/* utility function to update walt signals at wakeup */ +static inline void walt_try_to_wake_up(struct task_struct *p) +{ + struct rq *rq = cpu_rq(task_cpu(p)); + struct rq_flags rf; + u64 wallclock; + + rq_lock_irqsave(rq, &rf); + wallclock = walt_ktime_clock(); + walt_update_task_ravg(rq->curr, rq, TASK_UPDATE, wallclock, 0); + walt_update_task_ravg(p, rq, TASK_WAKE, wallclock, 0); + rq_unlock_irqrestore(rq, &rf); +} +#else +#define walt_try_to_wake_up(a) {} +#endif +#endif + /** * try_to_wake_up - wake up a thread * @p: the thread to be awakened * @state: the mask of task states that can be woken * @wake_flags: wake modifier flags (WF_*) + * @sibling_count_hint: A hint at the number of threads that are being woken up + * in this event. * * If (@state & @p->state) @p->state = TASK_RUNNING. * @@ -1983,7 +2022,8 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) * %false otherwise. */ static int -try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) +try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags, + int sibling_count_hint) { unsigned long flags; int cpu, success = 0; @@ -2061,6 +2101,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) */ smp_cond_load_acquire(&p->on_cpu, !VAL); + walt_try_to_wake_up(p); + p->sched_contributes_to_load = !!task_contributes_to_load(p); p->state = TASK_WAKING; @@ -2069,9 +2111,11 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) atomic_dec(&task_rq(p)->nr_iowait); } - cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags); + cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags, + sibling_count_hint); if (task_cpu(p) != cpu) { wake_flags |= WF_MIGRATED; + psi_ttwu_dequeue(p); set_task_cpu(p, cpu); } @@ -2130,6 +2174,11 @@ static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf) trace_sched_waking(p); if (!task_on_rq_queued(p)) { + u64 wallclock = walt_ktime_clock(); + + walt_update_task_ravg(rq->curr, rq, TASK_UPDATE, wallclock, 0); + walt_update_task_ravg(p, rq, TASK_WAKE, wallclock, 0); + if (p->in_iowait) { delayacct_blkio_end(p); atomic_dec(&rq->nr_iowait); @@ -2157,13 +2206,13 @@ out: */ int wake_up_process(struct task_struct *p) { - return try_to_wake_up(p, TASK_NORMAL, 0); + return try_to_wake_up(p, TASK_NORMAL, 0, 1); } EXPORT_SYMBOL(wake_up_process); int wake_up_state(struct task_struct *p, unsigned int state) { - return try_to_wake_up(p, state, 0); + return try_to_wake_up(p, state, 0, 1); } /* @@ -2182,7 +2231,12 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) p->se.prev_sum_exec_runtime = 0; p->se.nr_migrations = 0; p->se.vruntime = 0; +#ifdef CONFIG_SCHED_WALT + p->last_sleep_ts = 0; +#endif + INIT_LIST_HEAD(&p->se.group_node); + walt_init_new_task_load(p); #ifdef CONFIG_FAIR_GROUP_SCHED p->se.cfs_rq = NULL; @@ -2459,6 +2513,9 @@ void wake_up_new_task(struct task_struct *p) struct rq *rq; raw_spin_lock_irqsave(&p->pi_lock, rf.flags); + + walt_init_new_task_load(p); + p->state = TASK_RUNNING; #ifdef CONFIG_SMP /* @@ -2469,13 +2526,15 @@ void wake_up_new_task(struct task_struct *p) * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq, * as we're not fully set-up yet. */ - __set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0)); + __set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0, 1)); #endif rq = __task_rq_lock(p, &rf); update_rq_clock(rq); post_init_entity_util_avg(&p->se); activate_task(rq, p, ENQUEUE_NOCLOCK); + walt_mark_task_starting(p); + p->on_rq = TASK_ON_RQ_QUEUED; trace_sched_wakeup_new(p); check_preempt_curr(rq, p, WF_FORK); @@ -2930,7 +2989,7 @@ void sched_exec(void) int dest_cpu; raw_spin_lock_irqsave(&p->pi_lock, flags); - dest_cpu = p->sched_class->select_task_rq(p, task_cpu(p), SD_BALANCE_EXEC, 0); + dest_cpu = p->sched_class->select_task_rq(p, task_cpu(p), SD_BALANCE_EXEC, 0, 1); if (dest_cpu == smp_processor_id()) goto unlock; @@ -3029,10 +3088,14 @@ void scheduler_tick(void) rq_lock(rq, &rf); + walt_set_window_start(rq, &rf); + walt_update_task_ravg(rq->curr, rq, TASK_UPDATE, + walt_ktime_clock(), 0); update_rq_clock(rq); curr->sched_class->task_tick(rq, curr, 0); cpu_load_update_active(rq); calc_global_load_tick(rq); + psi_task_tick(rq); rq_unlock(rq, &rf); @@ -3300,6 +3363,7 @@ static void __sched notrace __schedule(bool preempt) struct rq_flags rf; struct rq *rq; int cpu; + u64 wallclock; cpu = smp_processor_id(); rq = cpu_rq(cpu); @@ -3355,10 +3419,17 @@ static void __sched notrace __schedule(bool preempt) } next = pick_next_task(rq, prev, &rf); + wallclock = walt_ktime_clock(); + walt_update_task_ravg(prev, rq, PUT_PREV_TASK, wallclock, 0); + walt_update_task_ravg(next, rq, PICK_NEXT_TASK, wallclock, 0); clear_tsk_need_resched(prev); clear_preempt_need_resched(); if (likely(prev != next)) { +#ifdef CONFIG_SCHED_WALT + if (!prev->on_rq) + prev->last_sleep_ts = wallclock; +#endif rq->nr_switches++; rq->curr = next; /* @@ -3619,7 +3690,7 @@ asmlinkage __visible void __sched preempt_schedule_irq(void) int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flags, void *key) { - return try_to_wake_up(curr->private, mode, wake_flags); + return try_to_wake_up(curr->private, mode, wake_flags, 1); } EXPORT_SYMBOL(default_wake_function); @@ -4819,9 +4890,7 @@ SYSCALL_DEFINE0(sched_yield) struct rq_flags rf; struct rq *rq; - local_irq_disable(); - rq = this_rq(); - rq_lock(rq, &rf); + rq = this_rq_lock_irq(&rf); schedstat_inc(rq->yld_count); current->sched_class->yield_task(rq); @@ -5712,6 +5781,9 @@ int sched_cpu_dying(unsigned int cpu) sched_ttwu_pending(); rq_lock_irqsave(rq, &rf); + + walt_migrate_sync_cpu(cpu); + if (rq->rd) { BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); set_rq_offline(rq); @@ -5922,12 +5994,18 @@ void __init sched_init(void) rq->idle_stamp = 0; rq->avg_idle = 2*sysctl_sched_migration_cost; rq->max_idle_balance_cost = sysctl_sched_migration_cost; +#ifdef CONFIG_SCHED_WALT + rq->cur_irqload = 0; + rq->avg_irqload = 0; + rq->irqload_ts = 0; +#endif INIT_LIST_HEAD(&rq->cfs_tasks); rq_attach_root(rq, &def_root_domain); #ifdef CONFIG_NO_HZ_COMMON rq->last_load_update_tick = jiffies; + rq->last_blocked_load_update_tick = jiffies; rq->nohz_flags = 0; #endif #ifdef CONFIG_NO_HZ_FULL @@ -5967,6 +6045,8 @@ void __init sched_init(void) init_schedstats(); + psi_init(); + scheduler_running = 1; } diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index f8c45d30ec6d..c839713c37ca 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -19,11 +19,14 @@ #include "sched.h" +unsigned long boosted_cpu_util(int cpu); + #define SUGOV_KTHREAD_PRIORITY 50 struct sugov_tunables { struct gov_attr_set attr_set; - unsigned int rate_limit_us; + unsigned int up_rate_limit_us; + unsigned int down_rate_limit_us; }; struct sugov_policy { @@ -34,7 +37,9 @@ struct sugov_policy { raw_spinlock_t update_lock; /* For shared policies */ u64 last_freq_update_time; - s64 freq_update_delay_ns; + s64 min_rate_limit_ns; + s64 up_rate_delay_ns; + s64 down_rate_delay_ns; unsigned int next_freq; unsigned int cached_raw_freq; @@ -111,8 +116,32 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time) return true; } + /* No need to recalculate next freq for min_rate_limit_us + * at least. However we might still decide to further rate + * limit once frequency change direction is decided, according + * to the separate rate limits. + */ + + delta_ns = time - sg_policy->last_freq_update_time; + return delta_ns >= sg_policy->min_rate_limit_ns; +} + +static bool sugov_up_down_rate_limit(struct sugov_policy *sg_policy, u64 time, + unsigned int next_freq) +{ + s64 delta_ns; + delta_ns = time - sg_policy->last_freq_update_time; - return delta_ns >= sg_policy->freq_update_delay_ns; + + if (next_freq > sg_policy->next_freq && + delta_ns < sg_policy->up_rate_delay_ns) + return true; + + if (next_freq < sg_policy->next_freq && + delta_ns < sg_policy->down_rate_delay_ns) + return true; + + return false; } static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time, @@ -123,6 +152,9 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time, if (sg_policy->next_freq == next_freq) return; + if (sugov_up_down_rate_limit(sg_policy, time, next_freq)) + return; + sg_policy->next_freq = next_freq; sg_policy->last_freq_update_time = time; @@ -178,13 +210,13 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy, static void sugov_get_util(unsigned long *util, unsigned long *max, int cpu) { - struct rq *rq = cpu_rq(cpu); - unsigned long cfs_max; + unsigned long max_cap; - cfs_max = arch_scale_cpu_capacity(NULL, cpu); + max_cap = arch_scale_cpu_capacity(NULL, cpu); - *util = min(rq->cfs.avg.util_avg, cfs_max); - *max = cfs_max; + *util = boosted_cpu_util(cpu); + *util = min(*util, max_cap); + *max = max_cap; } static void sugov_set_iowait_boost(struct sugov_cpu *sg_cpu, u64 time, @@ -272,7 +304,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, busy = sugov_cpu_is_busy(sg_cpu); - if (flags & SCHED_CPUFREQ_RT_DL) { + if (flags & SCHED_CPUFREQ_DL) { next_f = policy->cpuinfo.max_freq; } else { sugov_get_util(&util, &max, sg_cpu->cpu); @@ -290,6 +322,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, sg_policy->cached_raw_freq = 0; } } + sugov_update_commit(sg_policy, time, next_f); } @@ -318,7 +351,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time) j_sg_cpu->iowait_boost_pending = false; continue; } - if (j_sg_cpu->flags & SCHED_CPUFREQ_RT_DL) + if (j_sg_cpu->flags & SCHED_CPUFREQ_DL) return policy->cpuinfo.max_freq; j_util = j_sg_cpu->util; @@ -354,7 +387,7 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time, sg_cpu->last_update = time; if (sugov_should_update_freq(sg_policy, time)) { - if (flags & SCHED_CPUFREQ_RT_DL) + if (flags & SCHED_CPUFREQ_DL) next_f = sg_policy->policy->cpuinfo.max_freq; else next_f = sugov_next_freq_shared(sg_cpu, time); @@ -409,15 +442,52 @@ static inline struct sugov_tunables *to_sugov_tunables(struct gov_attr_set *attr return container_of(attr_set, struct sugov_tunables, attr_set); } -static ssize_t rate_limit_us_show(struct gov_attr_set *attr_set, char *buf) +static DEFINE_MUTEX(min_rate_lock); + +static void update_min_rate_limit_ns(struct sugov_policy *sg_policy) +{ + mutex_lock(&min_rate_lock); + sg_policy->min_rate_limit_ns = min(sg_policy->up_rate_delay_ns, + sg_policy->down_rate_delay_ns); + mutex_unlock(&min_rate_lock); +} + +static ssize_t up_rate_limit_us_show(struct gov_attr_set *attr_set, char *buf) { struct sugov_tunables *tunables = to_sugov_tunables(attr_set); - return sprintf(buf, "%u\n", tunables->rate_limit_us); + return sprintf(buf, "%u\n", tunables->up_rate_limit_us); } -static ssize_t rate_limit_us_store(struct gov_attr_set *attr_set, const char *buf, - size_t count) +static ssize_t down_rate_limit_us_show(struct gov_attr_set *attr_set, char *buf) +{ + struct sugov_tunables *tunables = to_sugov_tunables(attr_set); + + return sprintf(buf, "%u\n", tunables->down_rate_limit_us); +} + +static ssize_t up_rate_limit_us_store(struct gov_attr_set *attr_set, + const char *buf, size_t count) +{ + struct sugov_tunables *tunables = to_sugov_tunables(attr_set); + struct sugov_policy *sg_policy; + unsigned int rate_limit_us; + + if (kstrtouint(buf, 10, &rate_limit_us)) + return -EINVAL; + + tunables->up_rate_limit_us = rate_limit_us; + + list_for_each_entry(sg_policy, &attr_set->policy_list, tunables_hook) { + sg_policy->up_rate_delay_ns = rate_limit_us * NSEC_PER_USEC; + update_min_rate_limit_ns(sg_policy); + } + + return count; +} + +static ssize_t down_rate_limit_us_store(struct gov_attr_set *attr_set, + const char *buf, size_t count) { struct sugov_tunables *tunables = to_sugov_tunables(attr_set); struct sugov_policy *sg_policy; @@ -426,18 +496,22 @@ static ssize_t rate_limit_us_store(struct gov_attr_set *attr_set, const char *bu if (kstrtouint(buf, 10, &rate_limit_us)) return -EINVAL; - tunables->rate_limit_us = rate_limit_us; + tunables->down_rate_limit_us = rate_limit_us; - list_for_each_entry(sg_policy, &attr_set->policy_list, tunables_hook) - sg_policy->freq_update_delay_ns = rate_limit_us * NSEC_PER_USEC; + list_for_each_entry(sg_policy, &attr_set->policy_list, tunables_hook) { + sg_policy->down_rate_delay_ns = rate_limit_us * NSEC_PER_USEC; + update_min_rate_limit_ns(sg_policy); + } return count; } -static struct governor_attr rate_limit_us = __ATTR_RW(rate_limit_us); +static struct governor_attr up_rate_limit_us = __ATTR_RW(up_rate_limit_us); +static struct governor_attr down_rate_limit_us = __ATTR_RW(down_rate_limit_us); static struct attribute *sugov_attributes[] = { - &rate_limit_us.attr, + &up_rate_limit_us.attr, + &down_rate_limit_us.attr, NULL }; @@ -584,7 +658,8 @@ static int sugov_init(struct cpufreq_policy *policy) goto stop_kthread; } - tunables->rate_limit_us = cpufreq_policy_transition_delay_us(policy); + tunables->up_rate_limit_us = cpufreq_policy_transition_delay_us(policy); + tunables->down_rate_limit_us = cpufreq_policy_transition_delay_us(policy); policy->governor_data = sg_policy; sg_policy->tunables = tunables; @@ -643,7 +718,11 @@ static int sugov_start(struct cpufreq_policy *policy) struct sugov_policy *sg_policy = policy->governor_data; unsigned int cpu; - sg_policy->freq_update_delay_ns = sg_policy->tunables->rate_limit_us * NSEC_PER_USEC; + sg_policy->up_rate_delay_ns = + sg_policy->tunables->up_rate_limit_us * NSEC_PER_USEC; + sg_policy->down_rate_delay_ns = + sg_policy->tunables->down_rate_limit_us * NSEC_PER_USEC; + update_min_rate_limit_ns(sg_policy); sg_policy->last_freq_update_time = 0; sg_policy->next_freq = UINT_MAX; sg_policy->work_in_progress = false; @@ -656,7 +735,7 @@ static int sugov_start(struct cpufreq_policy *policy) memset(sg_cpu, 0, sizeof(*sg_cpu)); sg_cpu->cpu = cpu; sg_cpu->sg_policy = sg_policy; - sg_cpu->flags = SCHED_CPUFREQ_RT; + sg_cpu->flags = SCHED_CPUFREQ_DL; sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq; } diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 45c2cd37fe6b..196de0dfd455 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -5,7 +5,9 @@ #include <linux/static_key.h> #include <linux/context_tracking.h> #include <linux/sched/cputime.h> +#include <linux/cpufreq_times.h> #include "sched.h" +#include "walt.h" #ifdef CONFIG_IRQ_TIME_ACCOUNTING @@ -55,11 +57,18 @@ void irqtime_account_irq(struct task_struct *curr) struct irqtime *irqtime = this_cpu_ptr(&cpu_irqtime); s64 delta; int cpu; +#ifdef CONFIG_SCHED_WALT + u64 wallclock; + bool account = true; +#endif if (!sched_clock_irqtime) return; cpu = smp_processor_id(); +#ifdef CONFIG_SCHED_WALT + wallclock = sched_clock_cpu(cpu); +#endif delta = sched_clock_cpu(cpu) - irqtime->irq_start_time; irqtime->irq_start_time += delta; @@ -73,6 +82,13 @@ void irqtime_account_irq(struct task_struct *curr) irqtime_account_delta(irqtime, delta, CPUTIME_IRQ); else if (in_serving_softirq() && curr != this_cpu_ksoftirqd()) irqtime_account_delta(irqtime, delta, CPUTIME_SOFTIRQ); +#ifdef CONFIG_SCHED_WALT + else + account = false; + + if (account) + walt_account_irqtime(cpu, curr, delta, wallclock); +#endif } EXPORT_SYMBOL_GPL(irqtime_account_irq); @@ -132,6 +148,9 @@ void account_user_time(struct task_struct *p, u64 cputime) /* Account for user time used */ acct_account_cputime(p); + + /* Account power usage for user time */ + cpufreq_acct_update_power(p, cputime); } /* @@ -176,6 +195,9 @@ void account_system_index_time(struct task_struct *p, /* Account for system time used */ acct_account_cputime(p); + + /* Account power usage for system time */ + cpufreq_acct_update_power(p, cputime); } /* diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 22770168bff8..691109ba5a90 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -20,6 +20,8 @@ #include <linux/slab.h> #include <uapi/linux/sched/types.h> +#include "walt.h" + struct dl_bandwidth def_dl_bandwidth; static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se) @@ -1289,6 +1291,7 @@ void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) WARN_ON(!dl_prio(prio)); dl_rq->dl_nr_running++; add_nr_running(rq_of_dl_rq(dl_rq), 1); + walt_inc_cumulative_runnable_avg(rq_of_dl_rq(dl_rq), dl_task_of(dl_se)); inc_dl_deadline(dl_rq, deadline); inc_dl_migration(dl_se, dl_rq); @@ -1303,6 +1306,7 @@ void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) WARN_ON(!dl_rq->dl_nr_running); dl_rq->dl_nr_running--; sub_nr_running(rq_of_dl_rq(dl_rq), 1); + walt_dec_cumulative_runnable_avg(rq_of_dl_rq(dl_rq), dl_task_of(dl_se)); dec_dl_deadline(dl_rq, dl_se->deadline); dec_dl_migration(dl_se, dl_rq); @@ -1508,7 +1512,8 @@ static void yield_task_dl(struct rq *rq) static int find_later_rq(struct task_struct *task); static int -select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags) +select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags, + int sibling_count_hint) { struct task_struct *curr; struct rq *rq; @@ -2020,7 +2025,9 @@ retry: deactivate_task(rq, next_task, 0); sub_running_bw(next_task->dl.dl_bw, &rq->dl); sub_rq_bw(next_task->dl.dl_bw, &rq->dl); + next_task->on_rq = TASK_ON_RQ_MIGRATING; set_task_cpu(next_task, later_rq->cpu); + next_task->on_rq = TASK_ON_RQ_QUEUED; add_rq_bw(next_task->dl.dl_bw, &later_rq->dl); add_running_bw(next_task->dl.dl_bw, &later_rq->dl); activate_task(later_rq, next_task, 0); @@ -2112,7 +2119,9 @@ static void pull_dl_task(struct rq *this_rq) deactivate_task(src_rq, p, 0); sub_running_bw(p->dl.dl_bw, &src_rq->dl); sub_rq_bw(p->dl.dl_bw, &src_rq->dl); + p->on_rq = TASK_ON_RQ_MIGRATING; set_task_cpu(p, this_cpu); + p->on_rq = TASK_ON_RQ_QUEUED; add_rq_bw(p->dl.dl_bw, &this_rq->dl); add_running_bw(p->dl.dl_bw, &this_rq->dl); activate_task(this_rq, p, 0); diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 187c04a34ba1..d8895f6ec4db 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -267,9 +267,60 @@ set_table_entry(struct ctl_table *entry, } static struct ctl_table * +sd_alloc_ctl_energy_table(struct sched_group_energy *sge) +{ + struct ctl_table *table = sd_alloc_ctl_entry(5); + + if (table == NULL) + return NULL; + + set_table_entry(&table[0], "nr_idle_states", &sge->nr_idle_states, + sizeof(int), 0444, proc_dointvec_minmax, false); + set_table_entry(&table[1], "idle_states", &sge->idle_states[0].power, + sge->nr_idle_states*sizeof(struct idle_state), 0444, + proc_doulongvec_minmax, false); + set_table_entry(&table[2], "nr_cap_states", &sge->nr_cap_states, + sizeof(int), 0444, proc_dointvec_minmax, false); + set_table_entry(&table[3], "cap_states", &sge->cap_states[0].cap, + sge->nr_cap_states*sizeof(struct capacity_state), 0444, + proc_doulongvec_minmax, false); + + return table; +} + +static struct ctl_table * +sd_alloc_ctl_group_table(struct sched_group *sg) +{ + struct ctl_table *table = sd_alloc_ctl_entry(2); + + if (table == NULL) + return NULL; + + table->procname = kstrdup("energy", GFP_KERNEL); + table->mode = 0555; + table->child = sd_alloc_ctl_energy_table((struct sched_group_energy *)sg->sge); + + return table; +} + +static struct ctl_table * sd_alloc_ctl_domain_table(struct sched_domain *sd) { - struct ctl_table *table = sd_alloc_ctl_entry(14); + struct ctl_table *table; + unsigned int nr_entries = 14; + + int i = 0; + struct sched_group *sg = sd->groups; + + if (sg->sge) { + int nr_sgs = 0; + + do {} while (nr_sgs++, sg = sg->next, sg != sd->groups); + + nr_entries += nr_sgs; + } + + table = sd_alloc_ctl_entry(nr_entries); if (table == NULL) return NULL; @@ -302,7 +353,19 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd) sizeof(long), 0644, proc_doulongvec_minmax, false); set_table_entry(&table[12], "name", sd->name, CORENAME_MAX_SIZE, 0444, proc_dostring, false); - /* &table[13] is terminator */ + sg = sd->groups; + if (sg->sge) { + char buf[32]; + struct ctl_table *entry = &table[13]; + + do { + snprintf(buf, 32, "group%d", i); + entry->procname = kstrdup(buf, GFP_KERNEL); + entry->mode = 0555; + entry->child = sd_alloc_ctl_group_table(sg); + } while (entry++, i++, sg = sg->next, sg != sd->groups); + } + /* &table[nr_entries-1] is terminator */ return table; } @@ -568,6 +631,8 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) cfs_rq->runnable_load_avg); SEQ_printf(m, " .%-30s: %lu\n", "util_avg", cfs_rq->avg.util_avg); + SEQ_printf(m, " .%-30s: %u\n", "util_est_enqueued", + cfs_rq->avg.util_est.enqueued); SEQ_printf(m, " .%-30s: %ld\n", "removed_load_avg", atomic_long_read(&cfs_rq->removed_load_avg)); SEQ_printf(m, " .%-30s: %ld\n", "removed_util_avg", @@ -1014,6 +1079,8 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, P(se.avg.load_avg); P(se.avg.util_avg); P(se.avg.last_update_time); + P(se.avg.util_est.ewma); + P(se.avg.util_est.enqueued); #endif P(policy); P(prio); diff --git a/kernel/sched/energy.c b/kernel/sched/energy.c new file mode 100644 index 000000000000..8342de041e11 --- /dev/null +++ b/kernel/sched/energy.c @@ -0,0 +1,306 @@ +/* + * Obtain energy cost data from DT and populate relevant scheduler data + * structures. + * + * Copyright (C) 2015 ARM Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ +#define pr_fmt(fmt) "sched-energy: " fmt + +#include <linux/gfp.h> +#include <linux/of.h> +#include <linux/printk.h> +#include <linux/sched.h> +#include <linux/sched/topology.h> +#include <linux/sched/energy.h> +#include <linux/stddef.h> +#include <linux/arch_topology.h> +#include <linux/cpu.h> +#include <linux/pm_opp.h> +#include <linux/platform_device.h> + +#include "sched.h" + +struct sched_group_energy *sge_array[NR_CPUS][NR_SD_LEVELS]; + +static void free_resources(void) +{ + int cpu, sd_level; + struct sched_group_energy *sge; + + for_each_possible_cpu(cpu) { + for_each_possible_sd_level(sd_level) { + sge = sge_array[cpu][sd_level]; + if (sge) { + kfree(sge->cap_states); + kfree(sge->idle_states); + kfree(sge); + } + } + } +} +static bool sge_ready; +static bool freq_energy_model; + +void check_max_cap_vs_cpu_scale(int cpu, struct sched_group_energy *sge) +{ + unsigned long max_cap, cpu_scale; + + max_cap = sge->cap_states[sge->nr_cap_states - 1].cap; + cpu_scale = topology_get_cpu_scale(NULL, cpu); + + if (max_cap == cpu_scale) + return; + + pr_warn("CPU%d max energy model capacity=%ld != cpu_scale=%ld\n", cpu, + max_cap, cpu_scale); +} + +void init_sched_energy_costs(void) +{ + struct device_node *cn, *cp; + struct capacity_state *cap_states; + struct idle_state *idle_states; + struct sched_group_energy *sge; + const struct property *prop; + int sd_level, i, nstates, cpu; + const __be32 *val; + + for_each_possible_cpu(cpu) { + cn = of_get_cpu_node(cpu, NULL); + if (!cn) { + pr_warn("CPU device node missing for CPU %d\n", cpu); + return; + } + + if (!of_find_property(cn, "sched-energy-costs", NULL)) { + pr_warn("CPU device node has no sched-energy-costs\n"); + return; + } + /* Check if the energy model contains frequency/power values */ + if (of_find_property(cn, "freq-energy-model", NULL)) + freq_energy_model = true; + + for_each_possible_sd_level(sd_level) { + cp = of_parse_phandle(cn, "sched-energy-costs", sd_level); + if (!cp) + break; + + prop = of_find_property(cp, "busy-cost-data", NULL); + if (!prop || !prop->value) { + pr_warn("No busy-cost data, skipping sched_energy init\n"); + goto out; + } + + sge = kcalloc(1, sizeof(struct sched_group_energy), + GFP_NOWAIT); + + nstates = (prop->length / sizeof(u32)) / 2; + cap_states = kcalloc(nstates, + sizeof(struct capacity_state), + GFP_NOWAIT); + + for (i = 0, val = prop->value; i < nstates; i++) { + if (freq_energy_model) { + /* + * Capacity values will be calculated later using + * frequency reported by OPP driver and cpu_uarch_scale + * values. + */ + cap_states[i].frequency = be32_to_cpup(val++); + cap_states[i].cap = 0; + } else { + cap_states[i].frequency = 0; + cap_states[i].cap = be32_to_cpup(val++); + } + cap_states[i].power = be32_to_cpup(val++); + } + + sge->nr_cap_states = nstates; + sge->cap_states = cap_states; + + prop = of_find_property(cp, "idle-cost-data", NULL); + if (!prop || !prop->value) { + pr_warn("No idle-cost data, skipping sched_energy init\n"); + goto out; + } + + nstates = (prop->length / sizeof(u32)); + idle_states = kcalloc(nstates, + sizeof(struct idle_state), + GFP_NOWAIT); + + for (i = 0, val = prop->value; i < nstates; i++) + idle_states[i].power = be32_to_cpup(val++); + + sge->nr_idle_states = nstates; + sge->idle_states = idle_states; + + sge_array[cpu][sd_level] = sge; + } + if (!freq_energy_model) + check_max_cap_vs_cpu_scale(cpu, sge_array[cpu][SD_LEVEL0]); + } + sge_ready = true; + pr_info("Sched-energy-costs installed from DT\n"); + return; + +out: + free_resources(); +} + +static int sched_energy_probe(struct platform_device *pdev) +{ + int cpu; + unsigned long *max_frequencies = NULL; + int ret; + + if (!sge_ready) + return -EPROBE_DEFER; + + if (!energy_aware() || !freq_energy_model) + return 0; + + max_frequencies = kmalloc_array(nr_cpu_ids, sizeof(unsigned long), + GFP_KERNEL); + if (!max_frequencies) { + ret = -ENOMEM; + goto exit; + } + + /* + * Find system max possible frequency and max frequencies for each + * CPUs. + */ + for_each_possible_cpu(cpu) { + struct device *cpu_dev; + struct dev_pm_opp *opp; + + cpu_dev = get_cpu_device(cpu); + if (IS_ERR_OR_NULL(cpu_dev)) { + if (!cpu_dev) + ret = -EINVAL; + else + ret = PTR_ERR(cpu_dev); + goto exit; + } + + max_frequencies[cpu] = ULONG_MAX; + + opp = dev_pm_opp_find_freq_floor(cpu_dev, + &max_frequencies[cpu]); + if (IS_ERR_OR_NULL(opp)) { + if (!opp || PTR_ERR(opp) == -ENODEV) + ret = -EPROBE_DEFER; + else + ret = PTR_ERR(opp); + goto exit; + } + + /* Convert HZ to KHZ */ + max_frequencies[cpu] /= 1000; + } + + /* update capacity in energy model */ + for_each_possible_cpu(cpu) { + unsigned long cpu_max_cap; + struct sched_group_energy *sge_l0, *sge; + cpu_max_cap = topology_get_cpu_scale(NULL, cpu); + + /* + * All the cap_states have same frequency table so use + * SD_LEVEL0's. + */ + sge_l0 = sge_array[cpu][SD_LEVEL0]; + if (sge_l0 && sge_l0->nr_cap_states > 0) { + int i; + int ncapstates = sge_l0->nr_cap_states; + + for (i = 0; i < ncapstates; i++) { + int sd_level; + unsigned long freq, cap; + + /* + * Energy model can contain more frequency + * steps than actual for multiple speedbin + * support. Ceil the max capacity with actual + * one. + */ + freq = min(sge_l0->cap_states[i].frequency, + max_frequencies[cpu]); + cap = DIV_ROUND_UP(cpu_max_cap * freq, + max_frequencies[cpu]); + + for_each_possible_sd_level(sd_level) { + sge = sge_array[cpu][sd_level]; + if (!sge) + break; + sge->cap_states[i].cap = cap; + } + dev_dbg(&pdev->dev, + "cpu=%d freq=%ld cap=%ld power_d0=%ld\n", + cpu, freq, sge_l0->cap_states[i].cap, + sge_l0->cap_states[i].power); + } + + dev_info(&pdev->dev, + "cpu=%d [freq=%ld cap=%ld power_d0=%ld] -> [freq=%ld cap=%ld power_d0=%ld]\n", + cpu, + sge_l0->cap_states[0].frequency, + sge_l0->cap_states[0].cap, + sge_l0->cap_states[0].power, + sge_l0->cap_states[ncapstates - 1].frequency, + sge_l0->cap_states[ncapstates - 1].cap, + sge_l0->cap_states[ncapstates - 1].power + ); + } + } + + kfree(max_frequencies); + dev_info(&pdev->dev, "Sched-energy-costs capacity updated\n"); + return 0; + +exit: + if (ret != -EPROBE_DEFER) + dev_err(&pdev->dev, "error=%d\n", ret); + kfree(max_frequencies); + return ret; +} + +static struct platform_driver energy_driver = { + .driver = { + .name = "sched-energy", + }, + .probe = sched_energy_probe, +}; + +static struct platform_device energy_device = { + .name = "sched-energy", +}; + +static int __init sched_energy_init(void) +{ + int ret; + + ret = platform_device_register(&energy_device); + if (ret) + pr_err("%s device_register failed:%d\n", __func__, ret); + ret = platform_driver_register(&energy_driver); + if (ret) { + pr_err("%s driver_register failed:%d\n", __func__, ret); + platform_device_unregister(&energy_device); + } + return ret; +} +subsys_initcall(sched_energy_init); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 81096dd0ca0c..5a3a2e563f1c 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -37,6 +37,8 @@ #include <trace/events/sched.h> #include "sched.h" +#include "tune.h" +#include "walt.h" /* * Targeted preemption latency for CPU-bound tasks: @@ -55,6 +57,15 @@ unsigned int sysctl_sched_latency = 6000000ULL; unsigned int normalized_sysctl_sched_latency = 6000000ULL; /* + * Enable/disable honoring sync flag in energy-aware wakeups. + */ +unsigned int sysctl_sched_sync_hint_enable = 1; +/* + * Enable/disable using cstate knowledge in idle sibling selection + */ +unsigned int sysctl_sched_cstate_aware = 1; + +/* * The initial- and re-scaling of tunables is configurable * * Options are: @@ -100,6 +111,13 @@ unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL; const_debug unsigned int sysctl_sched_migration_cost = 500000UL; +#ifdef CONFIG_SCHED_WALT +unsigned int sysctl_sched_use_walt_cpu_util = 1; +unsigned int sysctl_sched_use_walt_task_util = 1; +__read_mostly unsigned int sysctl_sched_walt_cpu_high_irqload = + (10 * NSEC_PER_MSEC); +#endif + #ifdef CONFIG_SMP /* * For asym packing, by default the lower numbered cpu has higher priority. @@ -710,14 +728,17 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se) static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu); static unsigned long task_h_load(struct task_struct *p); +static unsigned long capacity_of(int cpu); /* Give new sched_entity start runnable values to heavy its load in infant time */ void init_entity_runnable_average(struct sched_entity *se) { struct sched_avg *sa = &se->avg; - sa->last_update_time = 0; + memset(sa, 0, sizeof(*sa)); /* + * util_avg is initialized in post_init_entity_util_avg. + * util_est should start from zero. * sched_avg's period_contrib should be strictly less then 1024, so * we give it 1023 to make sure it is almost a period (1024us), and * will definitely be update (after enqueue). @@ -732,11 +753,6 @@ void init_entity_runnable_average(struct sched_entity *se) if (entity_is_task(se)) sa->load_avg = scale_load_down(se->load.weight); sa->load_sum = sa->load_avg * LOAD_AVG_MAX; - /* - * At this point, util_avg won't be used in select_task_rq_fair anyway - */ - sa->util_avg = 0; - sa->util_sum = 0; /* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */ } @@ -967,6 +983,7 @@ update_stats_enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) } trace_sched_stat_blocked(tsk, delta); + trace_sched_blocked_reason(tsk); /* * Blocking time is in units of nanosecs, so shift by @@ -1431,7 +1448,6 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page, static unsigned long weighted_cpuload(struct rq *rq); static unsigned long source_load(int cpu, int type); static unsigned long target_load(int cpu, int type); -static unsigned long capacity_of(int cpu); /* Cached statistics for all CPUs within a node */ struct numa_stats { @@ -2988,7 +3004,8 @@ accumulate_sum(u64 delta, int cpu, struct sched_avg *sa, */ static __always_inline int ___update_load_avg(u64 now, int cpu, struct sched_avg *sa, - unsigned long weight, int running, struct cfs_rq *cfs_rq) + unsigned long weight, int running, struct cfs_rq *cfs_rq, + struct rt_rq *rt_rq) { u64 delta; @@ -3044,21 +3061,83 @@ ___update_load_avg(u64 now, int cpu, struct sched_avg *sa, } sa->util_avg = sa->util_sum / (LOAD_AVG_MAX - 1024 + sa->period_contrib); + if (cfs_rq) + trace_sched_load_cfs_rq(cfs_rq); + else { + if (likely(!rt_rq)) + trace_sched_load_se(container_of(sa, struct sched_entity, avg)); + else + trace_sched_load_rt_rq(cpu, rt_rq); + } + return 1; } +/* + * When a task is dequeued, its estimated utilization should not be update if + * its util_avg has not been updated at least once. + * This flag is used to synchronize util_avg updates with util_est updates. + * We map this information into the LSB bit of the utilization saved at + * dequeue time (i.e. util_est.dequeued). + */ +#define UTIL_AVG_UNCHANGED 0x1 + +static inline void cfs_se_util_change(struct sched_avg *avg) +{ + unsigned int enqueued; + + if (!sched_feat(UTIL_EST)) + return; + + /* Avoid store if the flag has been already set */ + enqueued = avg->util_est.enqueued; + if (!(enqueued & UTIL_AVG_UNCHANGED)) + return; + + /* Reset flag to report util_avg has been updated */ + enqueued &= ~UTIL_AVG_UNCHANGED; + WRITE_ONCE(avg->util_est.enqueued, enqueued); +} + static int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se) { - return ___update_load_avg(now, cpu, &se->avg, 0, 0, NULL); + return ___update_load_avg(now, cpu, &se->avg, 0, 0, NULL, NULL); } static int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se) { - return ___update_load_avg(now, cpu, &se->avg, - se->on_rq * scale_load_down(se->load.weight), - cfs_rq->curr == se, NULL); + if (___update_load_avg(now, cpu, &se->avg, + se->on_rq * scale_load_down(se->load.weight), + cfs_rq->curr == se, NULL, NULL)) { + cfs_se_util_change(&se->avg); + +#ifdef UTIL_EST_DEBUG + /* + * Trace utilization only for actual tasks. + * + * These trace events are mostly useful to get easier to + * read plots for the estimated utilization, where we can + * compare it with the actual grow/decrease of the original + * PELT signal. + * Let's keep them disabled by default in "production kernels". + */ + if (entity_is_task(se)) { + struct task_struct *tsk = task_of(se); + + trace_sched_util_est_task(tsk, &se->avg); + + /* Trace utilization only for top level CFS RQ */ + cfs_rq = &(task_rq(tsk)->cfs); + trace_sched_util_est_cpu(cpu, cfs_rq); + } +#endif /* UTIL_EST_DEBUG */ + + return 1; + } + + return 0; } static int @@ -3066,7 +3145,7 @@ __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq) { return ___update_load_avg(now, cpu, &cfs_rq->avg, scale_load_down(cfs_rq->load.weight), - cfs_rq->curr != NULL, cfs_rq); + cfs_rq->curr != NULL, cfs_rq, NULL); } /* @@ -3119,6 +3198,8 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) atomic_long_add(delta, &cfs_rq->tg->load_avg); cfs_rq->tg_load_avg_contrib = cfs_rq->avg.load_avg; } + + trace_sched_load_tg(cfs_rq); } /* @@ -3287,6 +3368,9 @@ static inline int propagate_entity_load_avg(struct sched_entity *se) update_tg_cfs_util(cfs_rq, se); update_tg_cfs_load(cfs_rq, se); + trace_sched_load_cfs_rq(cfs_rq); + trace_sched_load_se(se); + return 1; } @@ -3401,6 +3485,15 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) return decayed || removed_load; } +int update_rt_rq_load_avg(u64 now, int cpu, struct rt_rq *rt_rq, int running) +{ + int ret; + + ret = ___update_load_avg(now, cpu, &rt_rq->avg, running, running, NULL, rt_rq); + + return ret; +} + /* * Optional action to be done while updating the load average */ @@ -3448,6 +3541,8 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s set_tg_cfs_propagate(cfs_rq); cfs_rq_util_change(cfs_rq); + + trace_sched_load_cfs_rq(cfs_rq); } /** @@ -3468,6 +3563,8 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s set_tg_cfs_propagate(cfs_rq); cfs_rq_util_change(cfs_rq); + + trace_sched_load_cfs_rq(cfs_rq); } /* Add the load generated by se into cfs_rq's load average */ @@ -3564,6 +3661,157 @@ static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq) static int idle_balance(struct rq *this_rq, struct rq_flags *rf); +static inline int task_fits_capacity(struct task_struct *p, long capacity); + +static inline void update_misfit_status(struct task_struct *p, struct rq *rq) +{ + if (!static_branch_unlikely(&sched_asym_cpucapacity)) + return; + + if (!p) { + rq->misfit_task_load = 0; + return; + } + + if (task_fits_capacity(p, capacity_of(cpu_of(rq)))) { + rq->misfit_task_load = 0; + return; + } + + rq->misfit_task_load = task_h_load(p); +} + +static inline unsigned long task_util(struct task_struct *p) +{ +#ifdef CONFIG_SCHED_WALT + if (likely(!walt_disabled && sysctl_sched_use_walt_task_util)) + return (p->ravg.demand / + (walt_ravg_window >> SCHED_CAPACITY_SHIFT)); +#endif + return READ_ONCE(p->se.avg.util_avg); +} + +static inline unsigned long _task_util_est(struct task_struct *p) +{ + struct util_est ue = READ_ONCE(p->se.avg.util_est); + + return max(ue.ewma, ue.enqueued); +} + +static inline unsigned long task_util_est(struct task_struct *p) +{ +#ifdef CONFIG_SCHED_WALT + if (likely(!walt_disabled && sysctl_sched_use_walt_task_util)) + return (p->ravg.demand / + (walt_ravg_window >> SCHED_CAPACITY_SHIFT)); +#endif + return max(task_util(p), _task_util_est(p)); +} + +static inline void util_est_enqueue(struct cfs_rq *cfs_rq, + struct task_struct *p) +{ + unsigned int enqueued; + + if (!sched_feat(UTIL_EST)) + return; + + /* Update root cfs_rq's estimated utilization */ + enqueued = cfs_rq->avg.util_est.enqueued; + enqueued += (_task_util_est(p) | UTIL_AVG_UNCHANGED); + WRITE_ONCE(cfs_rq->avg.util_est.enqueued, enqueued); + + trace_sched_util_est_task(p, &p->se.avg); + trace_sched_util_est_cpu(cpu_of(rq_of(cfs_rq)), cfs_rq); +} + +/* + * Check if a (signed) value is within a specified (unsigned) margin, + * based on the observation that: + * + * abs(x) < y := (unsigned)(x + y - 1) < (2 * y - 1) + * + * NOTE: this only works when value + maring < INT_MAX. + */ +static inline bool within_margin(int value, int margin) +{ + return ((unsigned int)(value + margin - 1) < (2 * margin - 1)); +} + +static void +util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep) +{ + long last_ewma_diff; + struct util_est ue; + + if (!sched_feat(UTIL_EST)) + return; + + /* + * Update root cfs_rq's estimated utilization + * + * If *p is the last task then the root cfs_rq's estimated utilization + * of a CPU is 0 by definition. + */ + ue.enqueued = 0; + if (cfs_rq->nr_running) { + ue.enqueued = cfs_rq->avg.util_est.enqueued; + ue.enqueued -= min_t(unsigned int, ue.enqueued, + (_task_util_est(p) | UTIL_AVG_UNCHANGED)); + } + WRITE_ONCE(cfs_rq->avg.util_est.enqueued, ue.enqueued); + + trace_sched_util_est_cpu(cpu_of(rq_of(cfs_rq)), cfs_rq); + + /* + * Skip update of task's estimated utilization when the task has not + * yet completed an activation, e.g. being migrated. + */ + if (!task_sleep) + return; + + /* + * If the PELT values haven't changed since enqueue time, + * skip the util_est update. + */ + ue = p->se.avg.util_est; + if (ue.enqueued & UTIL_AVG_UNCHANGED) + return; + + /* + * Skip update of task's estimated utilization when its EWMA is + * already ~1% close to its last activation value. + */ + ue.enqueued = (task_util(p) | UTIL_AVG_UNCHANGED); + last_ewma_diff = ue.enqueued - ue.ewma; + if (within_margin(last_ewma_diff, (SCHED_CAPACITY_SCALE / 100))) + return; + + /* + * Update Task's estimated utilization + * + * When *p completes an activation we can consolidate another sample + * of the task size. This is done by storing the current PELT value + * as ue.enqueued and by using this value to update the Exponential + * Weighted Moving Average (EWMA): + * + * ewma(t) = w * task_util(p) + (1-w) * ewma(t-1) + * = w * task_util(p) + ewma(t-1) - w * ewma(t-1) + * = w * (task_util(p) - ewma(t-1)) + ewma(t-1) + * = w * ( last_ewma_diff ) + ewma(t-1) + * = w * (last_ewma_diff + ewma(t-1) / w) + * + * Where 'w' is the weight of new samples, which is configured to be + * 0.25, thus making w=1/4 ( >>= UTIL_EST_WEIGHT_SHIFT) + */ + ue.ewma <<= UTIL_EST_WEIGHT_SHIFT; + ue.ewma += last_ewma_diff; + ue.ewma >>= UTIL_EST_WEIGHT_SHIFT; + WRITE_ONCE(p->se.avg.util_est, ue); + + trace_sched_util_est_task(p, &p->se.avg); +} + #else /* CONFIG_SMP */ static inline int @@ -3572,6 +3820,11 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) return 0; } +int update_rt_rq_load_avg(u64 now, int cpu, struct rt_rq *rt_rq, int running) +{ + return 0; +} + #define UPDATE_TG 0x0 #define SKIP_AGE_LOAD 0x0 @@ -3596,6 +3849,15 @@ static inline int idle_balance(struct rq *rq, struct rq_flags *rf) return 0; } +static inline void update_misfit_status(struct task_struct *p, struct rq *rq) {} + +static inline void +util_est_enqueue(struct cfs_rq *cfs_rq, struct task_struct *p) {} + +static inline void +util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, + bool task_sleep) {} + #endif /* CONFIG_SMP */ static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se) @@ -4886,6 +5148,46 @@ static inline void hrtick_update(struct rq *rq) } #endif +#ifdef CONFIG_SMP +static bool cpu_overutilized(int cpu); + +static bool sd_overutilized(struct sched_domain *sd) +{ + return sd->shared->overutilized; +} + +static void set_sd_overutilized(struct sched_domain *sd) +{ + trace_sched_overutilized(sd, sd->shared->overutilized, true); + sd->shared->overutilized = true; +} + +static void clear_sd_overutilized(struct sched_domain *sd) +{ + trace_sched_overutilized(sd, sd->shared->overutilized, false); + sd->shared->overutilized = false; +} + +static inline void update_overutilized_status(struct rq *rq) +{ + struct sched_domain *sd; + + rcu_read_lock(); + sd = rcu_dereference(rq->sd); + if (sd && !sd_overutilized(sd) && + cpu_overutilized(rq->cpu)) + set_sd_overutilized(sd); + rcu_read_unlock(); +} + +unsigned long boosted_cpu_util(int cpu); +#else + +#define update_overutilized_status(rq) do {} while (0) +#define boosted_cpu_util(cpu) cpu_util_freq(cpu) + +#endif /* CONFIG_SMP */ + /* * The enqueue_task method is called before nr_running is * increased. Here we update the fair scheduling stats and @@ -4896,6 +5198,33 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) { struct cfs_rq *cfs_rq; struct sched_entity *se = &p->se; + int task_new = !(flags & ENQUEUE_WAKEUP); + + /* + * The code below (indirectly) updates schedutil which looks at + * the cfs_rq utilization to select a frequency. + * Let's add the task's estimated utilization to the cfs_rq's + * estimated utilization, before we update schedutil. + */ + util_est_enqueue(&rq->cfs, p); + + /* + * The code below (indirectly) updates schedutil which looks at + * the cfs_rq utilization to select a frequency. + * Let's update schedtune here to ensure the boost value of the + * current task is accounted for in the selection of the OPP. + * + * We do it also in the case where we enqueue a throttled task; + * we could argue that a throttled task should not boost a CPU, + * however: + * a) properly implementing CPU boosting considering throttled + * tasks will increase a lot the complexity of the solution + * b) it's not easy to quantify the benefits introduced by + * such a more complex solution. + * Thus, for the time being we go for the simple solution and boost + * also for throttled RQs. + */ + schedtune_enqueue_task(p, cpu_of(rq)); /* * If in_iowait is set, the code below may not trigger any cpufreq @@ -4920,6 +5249,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) if (cfs_rq_throttled(cfs_rq)) break; cfs_rq->h_nr_running++; + walt_inc_cfs_cumulative_runnable_avg(cfs_rq, p); flags = ENQUEUE_WAKEUP; } @@ -4927,6 +5257,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); cfs_rq->h_nr_running++; + walt_inc_cfs_cumulative_runnable_avg(cfs_rq, p); if (cfs_rq_throttled(cfs_rq)) break; @@ -4935,8 +5266,12 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) update_cfs_shares(se); } - if (!se) + if (!se) { add_nr_running(rq, 1); + if (!task_new) + update_overutilized_status(rq); + walt_inc_cumulative_runnable_avg(rq, p); + } hrtick_update(rq); } @@ -4954,6 +5289,14 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) struct sched_entity *se = &p->se; int task_sleep = flags & DEQUEUE_SLEEP; + /* + * The code below (indirectly) updates schedutil which looks at + * the cfs_rq utilization to select a frequency. + * Let's update schedtune here to ensure the boost value of the + * current task is not more accounted for in the selection of the OPP. + */ + schedtune_dequeue_task(p, cpu_of(rq)); + for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); dequeue_entity(cfs_rq, se, flags); @@ -4967,6 +5310,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) if (cfs_rq_throttled(cfs_rq)) break; cfs_rq->h_nr_running--; + walt_dec_cfs_cumulative_runnable_avg(cfs_rq, p); /* Don't dequeue parent if it has other entities besides us */ if (cfs_rq->load.weight) { @@ -4986,6 +5330,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); cfs_rq->h_nr_running--; + walt_dec_cfs_cumulative_runnable_avg(cfs_rq, p); if (cfs_rq_throttled(cfs_rq)) break; @@ -4994,9 +5339,12 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) update_cfs_shares(se); } - if (!se) + if (!se) { sub_nr_running(rq, 1); + walt_dec_cumulative_runnable_avg(rq, p); + } + util_est_dequeue(&rq->cfs, p, task_sleep); hrtick_update(rq); } @@ -5304,16 +5652,6 @@ static unsigned long target_load(int cpu, int type) return max(rq->cpu_load[type-1], total); } -static unsigned long capacity_of(int cpu) -{ - return cpu_rq(cpu)->cpu_capacity; -} - -static unsigned long capacity_orig_of(int cpu) -{ - return cpu_rq(cpu)->cpu_capacity_orig; -} - static unsigned long cpu_avg_load_per_task(int cpu) { struct rq *rq = cpu_rq(cpu); @@ -5344,6 +5682,862 @@ static void record_wakee(struct task_struct *p) } /* + * Returns the current capacity of cpu after applying both + * cpu and freq scaling. + */ +unsigned long capacity_curr_of(int cpu) +{ + unsigned long max_cap = cpu_rq(cpu)->cpu_capacity_orig; + unsigned long scale_freq = arch_scale_freq_capacity(NULL, cpu); + + return cap_scale(max_cap, scale_freq); +} + +inline bool energy_aware(void) +{ + return sched_feat(ENERGY_AWARE); +} + +/* + * __cpu_norm_util() returns the cpu util relative to a specific capacity, + * i.e. it's busy ratio, in the range [0..SCHED_CAPACITY_SCALE] which is useful + * for energy calculations. Using the scale-invariant util returned by + * cpu_util() and approximating scale-invariant util by: + * + * util ~ (curr_freq/max_freq)*1024 * capacity_orig/1024 * running_time/time + * + * the normalized util can be found using the specific capacity. + * + * capacity = capacity_orig * curr_freq/max_freq + * + * norm_util = running_time/time ~ util/capacity + */ +static unsigned long __cpu_norm_util(unsigned long util, unsigned long capacity) +{ + if (util >= capacity) + return SCHED_CAPACITY_SCALE; + + return (util << SCHED_CAPACITY_SHIFT)/capacity; +} + +/* + * CPU candidates. + * + * These are labels to reference CPU candidates for an energy_diff. + * Currently we support only two possible candidates: the task's previous CPU + * and another candiate CPU. + * More advanced/aggressive EAS selection policies can consider more + * candidates. + */ +#define EAS_CPU_PRV 0 +#define EAS_CPU_NXT 1 +#define EAS_CPU_BKP 2 + +/* + * energy_diff - supports the computation of the estimated energy impact in + * moving a "task"'s "util_delta" between different CPU candidates. + */ +/* + * NOTE: When using or examining WALT task signals, all wakeup + * latency is included as busy time for task util. + * + * This is relevant here because: + * When debugging is enabled, it can take as much as 1ms to + * write the output to the trace buffer for each eenv + * scenario. For periodic tasks where the sleep time is of + * a similar order, the WALT task util can be inflated. + * + * Further, and even without debugging enabled, + * task wakeup latency changes depending upon the EAS + * wakeup algorithm selected - FIND_BEST_TARGET only does + * energy calculations for up to 2 candidate CPUs. When + * NO_FIND_BEST_TARGET is configured, we can potentially + * do an energy calculation across all CPUS in the system. + * + * The impact to WALT task util on a Juno board + * running a periodic task which only sleeps for 200usec + * between 1ms activations has been measured. + * (i.e. the wakeup latency induced by energy calculation + * and debug output is double the desired sleep time and + * almost equivalent to the runtime which is more-or-less + * the worst case possible for this test) + * + * In this scenario, a task which has a PELT util of around + * 220 is inflated under WALT to have util around 400. + * + * This is simply a property of the way WALT includes + * wakeup latency in busy time while PELT does not. + * + * Hence - be careful when enabling DEBUG_EENV_DECISIONS + * expecially if WALT is the task signal. + */ +/*#define DEBUG_EENV_DECISIONS*/ + +#ifdef DEBUG_EENV_DECISIONS +/* max of 8 levels of sched groups traversed */ +#define EAS_EENV_DEBUG_LEVELS 16 + +struct _eenv_debug { + unsigned long cap; + unsigned long norm_util; + unsigned long cap_energy; + unsigned long idle_energy; + unsigned long this_energy; + unsigned long this_busy_energy; + unsigned long this_idle_energy; + cpumask_t group_cpumask; + unsigned long cpu_util[1]; +}; +#endif + +struct eenv_cpu { + /* CPU ID, must be in cpus_mask */ + int cpu_id; + + /* + * Index (into sched_group_energy::cap_states) of the OPP the + * CPU needs to run at if the task is placed on it. + * This includes the both active and blocked load, due to + * other tasks on this CPU, as well as the task's own + * utilization. + */ + int cap_idx; + int cap; + + /* Estimated system energy */ + unsigned long energy; + + /* Estimated energy variation wrt EAS_CPU_PRV */ + long nrg_delta; + +#ifdef DEBUG_EENV_DECISIONS + struct _eenv_debug *debug; + int debug_idx; +#endif /* DEBUG_EENV_DECISIONS */ +}; + +struct energy_env { + /* Utilization to move */ + struct task_struct *p; + unsigned long util_delta; + unsigned long util_delta_boosted; + + /* Mask of CPUs candidates to evaluate */ + cpumask_t cpus_mask; + + /* CPU candidates to evaluate */ + struct eenv_cpu *cpu; + int eenv_cpu_count; + +#ifdef DEBUG_EENV_DECISIONS + /* pointer to the memory block reserved + * for debug on this CPU - there will be + * sizeof(struct _eenv_debug) * + * (EAS_CPU_CNT * EAS_EENV_DEBUG_LEVELS) + * bytes allocated here. + */ + struct _eenv_debug *debug; +#endif + /* + * Index (into energy_env::cpu) of the morst energy efficient CPU for + * the specified energy_env::task + */ + int next_idx; + int max_cpu_count; + + /* Support data */ + struct sched_group *sg_top; + struct sched_group *sg_cap; + struct sched_group *sg; +}; + +/** + * Amount of capacity of a CPU that is (estimated to be) used by CFS tasks + * @cpu: the CPU to get the utilization of + * + * The unit of the return value must be the one of capacity so we can compare + * the utilization with the capacity of the CPU that is available for CFS task + * (ie cpu_capacity). + * + * cfs_rq.avg.util_avg is the sum of running time of runnable tasks plus the + * recent utilization of currently non-runnable tasks on a CPU. It represents + * the amount of utilization of a CPU in the range [0..capacity_orig] where + * capacity_orig is the cpu_capacity available at the highest frequency, + * i.e. arch_scale_cpu_capacity(). + * The utilization of a CPU converges towards a sum equal to or less than the + * current capacity (capacity_curr <= capacity_orig) of the CPU because it is + * the running time on this CPU scaled by capacity_curr. + * + * The estimated utilization of a CPU is defined to be the maximum between its + * cfs_rq.avg.util_avg and the sum of the estimated utilization of the tasks + * currently RUNNABLE on that CPU. + * This allows to properly represent the expected utilization of a CPU which + * has just got a big task running since a long sleep period. At the same time + * however it preserves the benefits of the "blocked utilization" in + * describing the potential for other tasks waking up on the same CPU. + * + * Nevertheless, cfs_rq.avg.util_avg can be higher than capacity_curr or even + * higher than capacity_orig because of unfortunate rounding in + * cfs.avg.util_avg or just after migrating tasks and new task wakeups until + * the average stabilizes with the new running time. We need to check that the + * utilization stays within the range of [0..capacity_orig] and cap it if + * necessary. Without utilization capping, a group could be seen as overloaded + * (CPU0 utilization at 121% + CPU1 utilization at 80%) whereas CPU1 has 20% of + * available capacity. We allow utilization to overshoot capacity_curr (but not + * capacity_orig) as it useful for predicting the capacity required after task + * migrations (scheduler-driven DVFS). + * + * Return: the (estimated) utilization for the specified CPU + */ +static inline unsigned long cpu_util(int cpu) +{ + struct cfs_rq *cfs_rq; + unsigned int util; + +#ifdef CONFIG_SCHED_WALT + if (likely(!walt_disabled && sysctl_sched_use_walt_cpu_util)) { + u64 walt_cpu_util = cpu_rq(cpu)->cumulative_runnable_avg; + + walt_cpu_util <<= SCHED_CAPACITY_SHIFT; + do_div(walt_cpu_util, walt_ravg_window); + + return min_t(unsigned long, walt_cpu_util, + capacity_orig_of(cpu)); + } +#endif + + cfs_rq = &cpu_rq(cpu)->cfs; + util = READ_ONCE(cfs_rq->avg.util_avg); + + if (sched_feat(UTIL_EST)) + util = max(util, READ_ONCE(cfs_rq->avg.util_est.enqueued)); + + return min_t(unsigned long, util, capacity_orig_of(cpu)); +} + +static inline unsigned long cpu_util_rt(int cpu) +{ + struct rt_rq *rt_rq = &(cpu_rq(cpu)->rt); + + return rt_rq->avg.util_avg; +} + +static inline unsigned long cpu_util_freq(int cpu) +{ +#ifdef CONFIG_SCHED_WALT + u64 walt_cpu_util; + + if (unlikely(walt_disabled || !sysctl_sched_use_walt_cpu_util)) { + return min(cpu_util(cpu) + cpu_util_rt(cpu), + capacity_orig_of(cpu)); + } + + walt_cpu_util = cpu_rq(cpu)->prev_runnable_sum; + walt_cpu_util <<= SCHED_CAPACITY_SHIFT; + do_div(walt_cpu_util, walt_ravg_window); + + return min_t(unsigned long, walt_cpu_util, capacity_orig_of(cpu)); +#else + return min(cpu_util(cpu) + cpu_util_rt(cpu), capacity_orig_of(cpu)); +#endif +} + +/* + * cpu_util_without: compute cpu utilization without any contributions from *p + * @cpu: the CPU which utilization is requested + * @p: the task which utilization should be discounted + * + * The utilization of a CPU is defined by the utilization of tasks currently + * enqueued on that CPU as well as tasks which are currently sleeping after an + * execution on that CPU. + * + * This method returns the utilization of the specified CPU by discounting the + * utilization of the specified task, whenever the task is currently + * contributing to the CPU utilization. + */ +static unsigned long cpu_util_without(int cpu, struct task_struct *p) +{ + struct cfs_rq *cfs_rq; + unsigned int util; + +#ifdef CONFIG_SCHED_WALT + /* + * WALT does not decay idle tasks in the same manner + * as PELT, so it makes little sense to subtract task + * utilization from cpu utilization. Instead just use + * cpu_util for this case. + */ + if (likely(!walt_disabled && sysctl_sched_use_walt_cpu_util)) + return cpu_util(cpu); +#endif + + /* Task has no contribution or is new */ + if (cpu != task_cpu(p) || !READ_ONCE(p->se.avg.last_update_time)) + return cpu_util(cpu); + + cfs_rq = &cpu_rq(cpu)->cfs; + util = READ_ONCE(cfs_rq->avg.util_avg); + + /* Discount task's util from CPU's util */ + util -= min_t(unsigned int, util, task_util(p)); + + /* + * Covered cases: + * + * a) if *p is the only task sleeping on this CPU, then: + * cpu_util (== task_util) > util_est (== 0) + * and thus we return: + * cpu_util_without = (cpu_util - task_util) = 0 + * + * b) if other tasks are SLEEPING on this CPU, which is now exiting + * IDLE, then: + * cpu_util >= task_util + * cpu_util > util_est (== 0) + * and thus we discount *p's blocked utilization to return: + * cpu_util_without = (cpu_util - task_util) >= 0 + * + * c) if other tasks are RUNNABLE on that CPU and + * util_est > cpu_util + * then we use util_est since it returns a more restrictive + * estimation of the spare capacity on that CPU, by just + * considering the expected utilization of tasks already + * runnable on that CPU. + * + * Cases a) and b) are covered by the above code, while case c) is + * covered by the following code when estimated utilization is + * enabled. + */ + if (sched_feat(UTIL_EST)) { + unsigned int estimated = + READ_ONCE(cfs_rq->avg.util_est.enqueued); + + /* + * Despite the following checks we still have a small window + * for a possible race, when an execl's select_task_rq_fair() + * races with LB's detach_task(): + * + * detach_task() + * p->on_rq = TASK_ON_RQ_MIGRATING; + * ---------------------------------- A + * deactivate_task() \ + * dequeue_task() + RaceTime + * util_est_dequeue() / + * ---------------------------------- B + * + * The additional check on "current == p" it's required to + * properly fix the execl regression and it helps in further + * reducing the chances for the above race. + */ + if (unlikely(task_on_rq_queued(p) || current == p)) { + estimated -= min_t(unsigned int, estimated, + (_task_util_est(p) | UTIL_AVG_UNCHANGED)); + } + util = max(util, estimated); + } + + /* + * Utilization (estimated) can exceed the CPU capacity, thus let's + * clamp to the maximum CPU capacity to ensure consistency with + * the cpu_util call. + */ + return min_t(unsigned long, util, capacity_orig_of(cpu)); +} + +static unsigned long group_max_util(struct energy_env *eenv, int cpu_idx) +{ + unsigned long max_util = 0; + unsigned long util; + int cpu; + + for_each_cpu(cpu, sched_group_span(eenv->sg_cap)) { + util = cpu_util_without(cpu, eenv->p); + + /* + * If we are looking at the target CPU specified by the eenv, + * then we should add the (estimated) utilization of the task + * assuming we will wake it up on that CPU. + */ + if (unlikely(cpu == eenv->cpu[cpu_idx].cpu_id)) + util += eenv->util_delta_boosted; + + max_util = max(max_util, util); + } + + return max_util; +} + +/* + * group_norm_util() returns the approximated group util relative to it's + * current capacity (busy ratio) in the range [0..SCHED_CAPACITY_SCALE] for use + * in energy calculations. Since task executions may or may not overlap in time + * in the group the true normalized util is between max(cpu_norm_util(i)) and + * sum(cpu_norm_util(i)) when iterating over all cpus in the group, i. The + * latter is used as the estimate as it leads to a more pessimistic energy + * estimate (more busy). + */ +static unsigned +long group_norm_util(struct energy_env *eenv, int cpu_idx) +{ + unsigned long capacity = eenv->cpu[cpu_idx].cap; + unsigned long util, util_sum = 0; + int cpu; + + for_each_cpu(cpu, sched_group_span(eenv->sg)) { + util = cpu_util_without(cpu, eenv->p); + + /* + * If we are looking at the target CPU specified by the eenv, + * then we should add the (estimated) utilization of the task + * assuming we will wake it up on that CPU. + */ + if (unlikely(cpu == eenv->cpu[cpu_idx].cpu_id)) + util += eenv->util_delta; + + util_sum += __cpu_norm_util(util, capacity); + } + + if (util_sum > SCHED_CAPACITY_SCALE) + return SCHED_CAPACITY_SCALE; + return util_sum; +} + +static int find_new_capacity(struct energy_env *eenv, int cpu_idx) +{ + const struct sched_group_energy *sge = eenv->sg_cap->sge; + unsigned long util = group_max_util(eenv, cpu_idx); + int idx, cap_idx; + + cap_idx = sge->nr_cap_states - 1; + + for (idx = 0; idx < sge->nr_cap_states; idx++) { + if (sge->cap_states[idx].cap >= util) { + cap_idx = idx; + break; + } + } + /* Keep track of SG's capacity */ + eenv->cpu[cpu_idx].cap = sge->cap_states[cap_idx].cap; + eenv->cpu[cpu_idx].cap_idx = cap_idx; + + return cap_idx; +} + +static int group_idle_state(struct energy_env *eenv, int cpu_idx) +{ + struct sched_group *sg = eenv->sg; + int src_in_grp, dst_in_grp; + int i, state = INT_MAX; + int max_idle_state_idx; + long grp_util = 0; + int new_state; + + /* Find the shallowest idle state in the sched group. */ + for_each_cpu(i, sched_group_span(sg)) + state = min(state, idle_get_state_idx(cpu_rq(i))); + + /* Take non-cpuidle idling into account (active idle/arch_cpu_idle()) */ + state++; + /* + * Try to estimate if a deeper idle state is + * achievable when we move the task. + */ + for_each_cpu(i, sched_group_span(sg)) + grp_util += cpu_util(i); + + src_in_grp = cpumask_test_cpu(eenv->cpu[EAS_CPU_PRV].cpu_id, + sched_group_span(sg)); + dst_in_grp = cpumask_test_cpu(eenv->cpu[cpu_idx].cpu_id, + sched_group_span(sg)); + if (src_in_grp == dst_in_grp) { + /* + * both CPUs under consideration are in the same group or not in + * either group, migration should leave idle state the same. + */ + return state; + } + /* + * add or remove util as appropriate to indicate what group util + * will be (worst case - no concurrent execution) after moving the task + */ + grp_util += src_in_grp ? -eenv->util_delta : eenv->util_delta; + + if (grp_util > + ((long)sg->sgc->max_capacity * (int)sg->group_weight)) { + /* + * After moving, the group will be fully occupied + * so assume it will not be idle at all. + */ + return 0; + } + + /* + * after moving, this group is at most partly + * occupied, so it should have some idle time. + */ + max_idle_state_idx = sg->sge->nr_idle_states - 2; + new_state = grp_util * max_idle_state_idx; + if (grp_util <= 0) { + /* group will have no util, use lowest state */ + new_state = max_idle_state_idx + 1; + } else { + /* + * for partially idle, linearly map util to idle + * states, excluding the lowest one. This does not + * correspond to the state we expect to enter in + * reality, but an indication of what might happen. + */ + new_state = min_t(int, max_idle_state_idx, + new_state / sg->sgc->max_capacity); + new_state = max_idle_state_idx - new_state; + } + return new_state; +} + +#ifdef DEBUG_EENV_DECISIONS +static struct _eenv_debug *eenv_debug_entry_ptr(struct _eenv_debug *base, int idx); + +static void store_energy_calc_debug_info(struct energy_env *eenv, int cpu_idx, int cap_idx, int idle_idx) +{ + int debug_idx = eenv->cpu[cpu_idx].debug_idx; + unsigned long sg_util, busy_energy, idle_energy; + const struct sched_group_energy *sge; + struct _eenv_debug *dbg; + int cpu; + + if (debug_idx < EAS_EENV_DEBUG_LEVELS) { + sge = eenv->sg->sge; + sg_util = group_norm_util(eenv, cpu_idx); + busy_energy = sge->cap_states[cap_idx].power; + busy_energy *= sg_util; + idle_energy = SCHED_CAPACITY_SCALE - sg_util; + idle_energy *= sge->idle_states[idle_idx].power; + /* should we use sg_cap or sg? */ + dbg = eenv_debug_entry_ptr(eenv->cpu[cpu_idx].debug, debug_idx); + dbg->cap = sge->cap_states[cap_idx].cap; + dbg->norm_util = sg_util; + dbg->cap_energy = sge->cap_states[cap_idx].power; + dbg->idle_energy = sge->idle_states[idle_idx].power; + dbg->this_energy = busy_energy + idle_energy; + dbg->this_busy_energy = busy_energy; + dbg->this_idle_energy = idle_energy; + + cpumask_copy(&dbg->group_cpumask, + sched_group_span(eenv->sg)); + + for_each_cpu(cpu, &dbg->group_cpumask) + dbg->cpu_util[cpu] = cpu_util(cpu); + + eenv->cpu[cpu_idx].debug_idx = debug_idx+1; + } +} +#else +#define store_energy_calc_debug_info(a,b,c,d) {} +#endif /* DEBUG_EENV_DECISIONS */ + +/* + * calc_sg_energy: compute energy for the eenv's SG (i.e. eenv->sg). + * + * This works in iterations to compute the SG's energy for each CPU + * candidate defined by the energy_env's cpu array. + */ +static void calc_sg_energy(struct energy_env *eenv) +{ + struct sched_group *sg = eenv->sg; + unsigned long busy_energy, idle_energy; + unsigned int busy_power, idle_power; + unsigned long total_energy = 0; + unsigned long sg_util; + int cap_idx, idle_idx; + int cpu_idx; + + for (cpu_idx = EAS_CPU_PRV; cpu_idx < eenv->max_cpu_count; ++cpu_idx) { + if (eenv->cpu[cpu_idx].cpu_id == -1) + continue; + + /* Compute ACTIVE energy */ + cap_idx = find_new_capacity(eenv, cpu_idx); + busy_power = sg->sge->cap_states[cap_idx].power; + sg_util = group_norm_util(eenv, cpu_idx); + busy_energy = sg_util * busy_power; + + /* Compute IDLE energy */ + idle_idx = group_idle_state(eenv, cpu_idx); + idle_power = sg->sge->idle_states[idle_idx].power; + idle_energy = SCHED_CAPACITY_SCALE - sg_util; + idle_energy *= idle_power; + + total_energy = busy_energy + idle_energy; + eenv->cpu[cpu_idx].energy += total_energy; + + store_energy_calc_debug_info(eenv, cpu_idx, cap_idx, idle_idx); + } +} + +/* + * compute_energy() computes the absolute variation in energy consumption by + * moving eenv.util_delta from EAS_CPU_PRV to EAS_CPU_NXT. + * + * NOTE: compute_energy() may fail when racing with sched_domain updates, in + * which case we abort by returning -EINVAL. + */ +static int compute_energy(struct energy_env *eenv) +{ + struct sched_domain *sd; + int cpu; + struct cpumask visit_cpus; + struct sched_group *sg; + int cpu_count; + + WARN_ON(!eenv->sg_top->sge); + + cpumask_copy(&visit_cpus, sched_group_span(eenv->sg_top)); + /* If a cpu is hotplugged in while we are in this function, it does + * not appear in the existing visit_cpus mask which came from the + * sched_group pointer of the sched_domain pointed at by sd_ea for + * either the prev or next cpu and was dereferenced in + * select_energy_cpu_idx. + * Since we will dereference sd_scs later as we iterate through the + * CPUs we expect to visit, new CPUs can be present which are not in + * the visit_cpus mask. Guard this with cpu_count. + */ + cpu_count = cpumask_weight(&visit_cpus); + while (!cpumask_empty(&visit_cpus)) { + struct sched_group *sg_shared_cap = NULL; + + cpu = cpumask_first(&visit_cpus); + + /* + * Is the group utilization affected by cpus outside this + * sched_group? + * This sd may have groups with cpus which were not present + * when we took visit_cpus. + */ + sd = rcu_dereference(per_cpu(sd_scs, cpu)); + if (sd && sd->parent) + sg_shared_cap = sd->parent->groups; + + for_each_domain(cpu, sd) { + sg = sd->groups; + + /* Has this sched_domain already been visited? */ + if (sd->child && group_first_cpu(sg) != cpu) + break; + + do { + eenv->sg_cap = sg; + if (sg_shared_cap && sg_shared_cap->group_weight >= sg->group_weight) + eenv->sg_cap = sg_shared_cap; + + /* + * Compute the energy for all the candidate + * CPUs in the current visited SG. + */ + eenv->sg = sg; + calc_sg_energy(eenv); + + /* remove CPUs we have just visited */ + if (!sd->child) { + /* + * cpu_count here is the number of + * cpus we expect to visit in this + * calculation. If we race against + * hotplug, we can have extra cpus + * added to the groups we are + * iterating which do not appear in + * the visit_cpus mask. In that case + * we are not able to calculate energy + * without restarting so we will bail + * out and use prev_cpu this time. + */ + if (!cpu_count) + return -EINVAL; + cpumask_xor(&visit_cpus, &visit_cpus, sched_group_span(sg)); + cpu_count--; + } + + if (cpumask_equal(sched_group_span(sg), sched_group_span(eenv->sg_top)) && + sd->child) + goto next_cpu; + + } while (sg = sg->next, sg != sd->groups); + } +next_cpu: + cpumask_clear_cpu(cpu, &visit_cpus); + continue; + } + + return 0; +} + +static inline bool cpu_in_sg(struct sched_group *sg, int cpu) +{ + return cpu != -1 && cpumask_test_cpu(cpu, sched_group_span(sg)); +} + +#ifdef DEBUG_EENV_DECISIONS +static void dump_eenv_debug(struct energy_env *eenv) +{ + int cpu_idx, grp_idx; + char cpu_utils[(NR_CPUS*12)+10]="cpu_util: "; + char cpulist[64]; + + trace_printk("eenv scenario: task=%p %s task_util=%lu prev_cpu=%d", + eenv->p, eenv->p->comm, eenv->util_delta, eenv->cpu[EAS_CPU_PRV].cpu_id); + + for (cpu_idx=EAS_CPU_PRV; cpu_idx < eenv->max_cpu_count; cpu_idx++) { + if (eenv->cpu[cpu_idx].cpu_id == -1) + continue; + trace_printk("---Scenario %d: Place task on cpu %d energy=%lu (%d debug logs at %p)", + cpu_idx+1, eenv->cpu[cpu_idx].cpu_id, + eenv->cpu[cpu_idx].energy >> SCHED_CAPACITY_SHIFT, + eenv->cpu[cpu_idx].debug_idx, + eenv->cpu[cpu_idx].debug); + for (grp_idx = 0; grp_idx < eenv->cpu[cpu_idx].debug_idx; grp_idx++) { + struct _eenv_debug *debug; + int cpu, written=0; + + debug = eenv_debug_entry_ptr(eenv->cpu[cpu_idx].debug, grp_idx); + cpu = scnprintf(cpulist, sizeof(cpulist), "%*pbl", cpumask_pr_args(&debug->group_cpumask)); + + cpu_utils[0] = 0; + /* print out the relevant cpu_util */ + for_each_cpu(cpu, &(debug->group_cpumask)) { + char tmp[64]; + if (written > sizeof(cpu_utils)-10) { + cpu_utils[written]=0; + break; + } + written += snprintf(tmp, sizeof(tmp), "cpu%d(%lu) ", cpu, debug->cpu_util[cpu]); + strcat(cpu_utils, tmp); + } + /* trace the data */ + trace_printk(" | %s : cap=%lu nutil=%lu, cap_nrg=%lu, idle_nrg=%lu energy=%lu busy_energy=%lu idle_energy=%lu %s", + cpulist, debug->cap, debug->norm_util, + debug->cap_energy, debug->idle_energy, + debug->this_energy >> SCHED_CAPACITY_SHIFT, + debug->this_busy_energy >> SCHED_CAPACITY_SHIFT, + debug->this_idle_energy >> SCHED_CAPACITY_SHIFT, + cpu_utils); + + } + trace_printk("---"); + } + trace_printk("----- done"); + return; +} +#else +#define dump_eenv_debug(a) {} +#endif /* DEBUG_EENV_DECISIONS */ +/* + * select_energy_cpu_idx(): estimate the energy impact of changing the + * utilization distribution. + * + * The eenv parameter specifies the changes: utilization amount and a + * collection of possible CPU candidates. The number of candidates + * depends upon the selection algorithm used. + * + * If find_best_target was used to select candidate CPUs, there will + * be at most 3 including prev_cpu. If not, we used a brute force + * selection which will provide the union of: + * * CPUs belonging to the highest sd which is not overutilized + * * CPUs the task is allowed to run on + * * online CPUs + * + * This function returns the index of a CPU candidate specified by the + * energy_env which corresponds to the most energy efficient CPU. + * Thus, 0 (EAS_CPU_PRV) means that non of the CPU candidate is more energy + * efficient than running on prev_cpu. This is also the value returned in case + * of abort due to error conditions during the computations. The only + * exception to this if we fail to access the energy model via sd_ea, where + * we return -1 with the intent of asking the system to use a different + * wakeup placement algorithm. + * + * A value greater than zero means that the most energy efficient CPU is the + * one represented by eenv->cpu[eenv->next_idx].cpu_id. + */ +static inline int select_energy_cpu_idx(struct energy_env *eenv) +{ + int last_cpu_idx = eenv->max_cpu_count - 1; + struct sched_domain *sd; + struct sched_group *sg; + int sd_cpu = -1; + int cpu_idx; + int margin; + + sd_cpu = eenv->cpu[EAS_CPU_PRV].cpu_id; + sd = rcu_dereference(per_cpu(sd_ea, sd_cpu)); + if (!sd) + return -1; + + cpumask_clear(&eenv->cpus_mask); + for (cpu_idx = EAS_CPU_PRV; cpu_idx < eenv->max_cpu_count; ++cpu_idx) { + int cpu = eenv->cpu[cpu_idx].cpu_id; + + if (cpu < 0) + continue; + cpumask_set_cpu(cpu, &eenv->cpus_mask); + } + + sg = sd->groups; + do { + /* Skip SGs which do not contains a candidate CPU */ + if (!cpumask_intersects(&eenv->cpus_mask, sched_group_span(sg))) + continue; + + eenv->sg_top = sg; + if (compute_energy(eenv) == -EINVAL) + return EAS_CPU_PRV; + } while (sg = sg->next, sg != sd->groups); + /* remember - eenv energy values are unscaled */ + + /* + * Compute the dead-zone margin used to prevent too many task + * migrations with negligible energy savings. + * An energy saving is considered meaningful if it reduces the energy + * consumption of EAS_CPU_PRV CPU candidate by at least ~1.56% + */ + margin = eenv->cpu[EAS_CPU_PRV].energy >> 6; + + /* + * By default the EAS_CPU_PRV CPU is considered the most energy + * efficient, with a 0 energy variation. + */ + eenv->next_idx = EAS_CPU_PRV; + eenv->cpu[EAS_CPU_PRV].nrg_delta = 0; + + dump_eenv_debug(eenv); + + /* + * Compare the other CPU candidates to find a CPU which can be + * more energy efficient then EAS_CPU_PRV + */ + if (sched_feat(FBT_STRICT_ORDER)) + last_cpu_idx = EAS_CPU_BKP; + + for(cpu_idx = EAS_CPU_NXT; cpu_idx <= last_cpu_idx; cpu_idx++) { + if (eenv->cpu[cpu_idx].cpu_id < 0) + continue; + eenv->cpu[cpu_idx].nrg_delta = + eenv->cpu[cpu_idx].energy - + eenv->cpu[EAS_CPU_PRV].energy; + + /* filter energy variations within the dead-zone margin */ + if (abs(eenv->cpu[cpu_idx].nrg_delta) < margin) + eenv->cpu[cpu_idx].nrg_delta = 0; + /* update the schedule candidate with min(nrg_delta) */ + if (eenv->cpu[cpu_idx].nrg_delta < + eenv->cpu[eenv->next_idx].nrg_delta) { + eenv->next_idx = cpu_idx; + /* break out if we want to stop on first saving candidate */ + if (sched_feat(FBT_STRICT_ORDER)) + break; + } + } + + return eenv->next_idx; +} + +/* * Detect M:N waker/wakee relationships via a switching-frequency heuristic. * * A waker of many should wake a different task than the one last awakened @@ -5360,15 +6554,18 @@ static void record_wakee(struct task_struct *p) * whatever is irrelevant, spread criteria is apparent partner count exceeds * socket size. */ -static int wake_wide(struct task_struct *p) +static int wake_wide(struct task_struct *p, int sibling_count_hint) { unsigned int master = current->wakee_flips; unsigned int slave = p->wakee_flips; - int factor = this_cpu_read(sd_llc_size); + int llc_size = this_cpu_read(sd_llc_size); + + if (sibling_count_hint >= llc_size) + return 1; if (master < slave) swap(master, slave); - if (slave < factor || master < slave * factor) + if (slave < llc_size || master < slave * llc_size) return 0; return 1; } @@ -5454,17 +6651,112 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, return affine; } -static inline int task_util(struct task_struct *p); -static int cpu_util_wake(int cpu, struct task_struct *p); +#ifdef CONFIG_SCHED_TUNE +struct reciprocal_value schedtune_spc_rdiv; + +static long +schedtune_margin(unsigned long signal, long boost) +{ + long long margin = 0; + + /* + * Signal proportional compensation (SPC) + * + * The Boost (B) value is used to compute a Margin (M) which is + * proportional to the complement of the original Signal (S): + * M = B * (SCHED_CAPACITY_SCALE - S) + * The obtained M could be used by the caller to "boost" S. + */ + if (boost >= 0) { + margin = SCHED_CAPACITY_SCALE - signal; + margin *= boost; + } else + margin = -signal * boost; + + margin = reciprocal_divide(margin, schedtune_spc_rdiv); + + if (boost < 0) + margin *= -1; + return margin; +} + +static inline int +schedtune_cpu_margin(unsigned long util, int cpu) +{ + int boost = schedtune_cpu_boost(cpu); + + if (boost == 0) + return 0; + + return schedtune_margin(util, boost); +} + +static inline long +schedtune_task_margin(struct task_struct *task) +{ + int boost = schedtune_task_boost(task); + unsigned long util; + long margin; + + if (boost == 0) + return 0; + + util = task_util_est(task); + margin = schedtune_margin(util, boost); + + return margin; +} + +#else /* CONFIG_SCHED_TUNE */ -static unsigned long capacity_spare_wake(int cpu, struct task_struct *p) +static inline int +schedtune_cpu_margin(unsigned long util, int cpu) +{ + return 0; +} + +static inline int +schedtune_task_margin(struct task_struct *task) +{ + return 0; +} + +#endif /* CONFIG_SCHED_TUNE */ + +unsigned long +boosted_cpu_util(int cpu) +{ + unsigned long util = cpu_util_freq(cpu); + long margin = schedtune_cpu_margin(util, cpu); + + trace_sched_boost_cpu(cpu, util, margin); + + return util + margin; +} + +static inline unsigned long +boosted_task_util(struct task_struct *task) +{ + unsigned long util = task_util_est(task); + long margin = schedtune_task_margin(task); + + trace_sched_boost_task(task, util, margin); + + return util + margin; +} + +static unsigned long cpu_util_without(int cpu, struct task_struct *p); + +static unsigned long capacity_spare_without(int cpu, struct task_struct *p) { - return capacity_orig_of(cpu) - cpu_util_wake(cpu, p); + return max_t(long, capacity_of(cpu) - cpu_util_without(cpu, p), 0); } /* * find_idlest_group finds and returns the least busy CPU group within the * domain. + * + * Assumes p is allowed on at least one CPU in sd. */ static struct sched_group * find_idlest_group(struct sched_domain *sd, struct task_struct *p, @@ -5472,8 +6764,9 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, { struct sched_group *idlest = NULL, *group = sd->groups; struct sched_group *most_spare_sg = NULL; - unsigned long min_runnable_load = ULONG_MAX, this_runnable_load = 0; - unsigned long min_avg_load = ULONG_MAX, this_avg_load = 0; + unsigned long min_runnable_load = ULONG_MAX; + unsigned long this_runnable_load = ULONG_MAX; + unsigned long min_avg_load = ULONG_MAX, this_avg_load = ULONG_MAX; unsigned long most_spare = 0, this_spare = 0; int load_idx = sd->forkexec_idx; int imbalance_scale = 100 + (sd->imbalance_pct-100)/2; @@ -5516,7 +6809,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, avg_load += cfs_rq_load_avg(&cpu_rq(i)->cfs); - spare_cap = capacity_spare_wake(i, p); + spare_cap = capacity_spare_without(i, p); if (spare_cap > max_spare_cap) max_spare_cap = spare_cap; @@ -5594,10 +6887,10 @@ skip_spare: } /* - * find_idlest_cpu - find the idlest cpu among the cpus in group. + * find_idlest_group_cpu - find the idlest cpu among the cpus in group. */ static int -find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) +find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) { unsigned long load, min_load = ULONG_MAX; unsigned int min_exit_latency = UINT_MAX; @@ -5646,6 +6939,53 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu; } +static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p, + int cpu, int prev_cpu, int sd_flag) +{ + int new_cpu = cpu; + + if (!cpumask_intersects(sched_domain_span(sd), &p->cpus_allowed)) + return prev_cpu; + + while (sd) { + struct sched_group *group; + struct sched_domain *tmp; + int weight; + + if (!(sd->flags & sd_flag)) { + sd = sd->child; + continue; + } + + group = find_idlest_group(sd, p, cpu, sd_flag); + if (!group) { + sd = sd->child; + continue; + } + + new_cpu = find_idlest_group_cpu(group, p, cpu); + if (new_cpu == cpu) { + /* Now try balancing at a lower domain level of cpu */ + sd = sd->child; + continue; + } + + /* Now try balancing at a lower domain level of new_cpu */ + cpu = new_cpu; + weight = sd->span_weight; + sd = NULL; + for_each_domain(cpu, tmp) { + if (weight <= tmp->span_weight) + break; + if (tmp->flags & sd_flag) + sd = tmp; + } + /* while loop will break here if sd == NULL */ + } + + return new_cpu; +} + #ifdef CONFIG_SCHED_SMT DEFINE_STATIC_KEY_FALSE(sched_smt_present); EXPORT_SYMBOL_GPL(sched_smt_present); @@ -5829,7 +7169,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t /* * Try and locate an idle core/thread in the LLC cache domain. */ -static int select_idle_sibling(struct task_struct *p, int prev, int target) +static inline int __select_idle_sibling(struct task_struct *p, int prev, int target) { struct sched_domain *sd; int i; @@ -5862,61 +7202,408 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) return target; } -/* - * cpu_util returns the amount of capacity of a CPU that is used by CFS - * tasks. The unit of the return value must be the one of capacity so we can - * compare the utilization with the capacity of the CPU that is available for - * CFS task (ie cpu_capacity). - * - * cfs_rq.avg.util_avg is the sum of running time of runnable tasks plus the - * recent utilization of currently non-runnable tasks on a CPU. It represents - * the amount of utilization of a CPU in the range [0..capacity_orig] where - * capacity_orig is the cpu_capacity available at the highest frequency - * (arch_scale_freq_capacity()). - * The utilization of a CPU converges towards a sum equal to or less than the - * current capacity (capacity_curr <= capacity_orig) of the CPU because it is - * the running time on this CPU scaled by capacity_curr. - * - * Nevertheless, cfs_rq.avg.util_avg can be higher than capacity_curr or even - * higher than capacity_orig because of unfortunate rounding in - * cfs.avg.util_avg or just after migrating tasks and new task wakeups until - * the average stabilizes with the new running time. We need to check that the - * utilization stays within the range of [0..capacity_orig] and cap it if - * necessary. Without utilization capping, a group could be seen as overloaded - * (CPU0 utilization at 121% + CPU1 utilization at 80%) whereas CPU1 has 20% of - * available capacity. We allow utilization to overshoot capacity_curr (but not - * capacity_orig) as it useful for predicting the capacity required after task - * migrations (scheduler-driven DVFS). - */ -static int cpu_util(int cpu) +static inline int select_idle_sibling_cstate_aware(struct task_struct *p, int prev, int target) +{ + struct sched_domain *sd; + struct sched_group *sg; + int best_idle_cpu = -1; + int best_idle_cstate = -1; + int best_idle_capacity = INT_MAX; + int i; + + /* + * Iterate the domains and find an elegible idle cpu. + */ + sd = rcu_dereference(per_cpu(sd_llc, target)); + for_each_lower_domain(sd) { + sg = sd->groups; + do { + if (!cpumask_intersects( + sched_group_span(sg), &p->cpus_allowed)) + goto next; + + for_each_cpu_and(i, &p->cpus_allowed, sched_group_span(sg)) { + int idle_idx; + unsigned long new_usage; + unsigned long capacity_orig; + + if (!idle_cpu(i)) + goto next; + + /* figure out if the task can fit here at all */ + new_usage = boosted_task_util(p); + capacity_orig = capacity_orig_of(i); + + if (new_usage > capacity_orig) + goto next; + + /* if the task fits without changing OPP and we + * intended to use this CPU, just proceed + */ + if (i == target && new_usage <= capacity_curr_of(target)) { + return target; + } + + /* otherwise select CPU with shallowest idle state + * to reduce wakeup latency. + */ + idle_idx = idle_get_state_idx(cpu_rq(i)); + + if (idle_idx < best_idle_cstate && + capacity_orig <= best_idle_capacity) { + best_idle_cpu = i; + best_idle_cstate = idle_idx; + best_idle_capacity = capacity_orig; + } + } + next: + sg = sg->next; + } while (sg != sd->groups); + } + + if (best_idle_cpu >= 0) + target = best_idle_cpu; + + return target; +} + +static int select_idle_sibling(struct task_struct *p, int prev, int target) { - unsigned long util = cpu_rq(cpu)->cfs.avg.util_avg; - unsigned long capacity = capacity_orig_of(cpu); + if (!sysctl_sched_cstate_aware) + return __select_idle_sibling(p, prev, target); - return (util >= capacity) ? capacity : util; + return select_idle_sibling_cstate_aware(p, prev, target); } -static inline int task_util(struct task_struct *p) +static inline int task_fits_capacity(struct task_struct *p, long capacity) { - return p->se.avg.util_avg; + return capacity * 1024 > boosted_task_util(p) * capacity_margin; } -/* - * cpu_util_wake: Compute cpu utilization with any contributions from - * the waking task p removed. - */ -static int cpu_util_wake(int cpu, struct task_struct *p) +static int start_cpu(bool boosted) { - unsigned long util, capacity; + struct root_domain *rd = cpu_rq(smp_processor_id())->rd; - /* Task has no contribution or is new */ - if (cpu != task_cpu(p) || !p->se.avg.last_update_time) - return cpu_util(cpu); + return boosted ? rd->max_cap_orig_cpu : rd->min_cap_orig_cpu; +} + +static inline int find_best_target(struct task_struct *p, int *backup_cpu, + bool boosted, bool prefer_idle) +{ + unsigned long min_util = boosted_task_util(p); + unsigned long target_capacity = ULONG_MAX; + unsigned long min_wake_util = ULONG_MAX; + unsigned long target_max_spare_cap = 0; + unsigned long target_util = ULONG_MAX; + unsigned long best_active_util = ULONG_MAX; + int best_idle_cstate = INT_MAX; + struct sched_domain *sd; + struct sched_group *sg; + int best_active_cpu = -1; + int best_idle_cpu = -1; + int target_cpu = -1; + int cpu, i; + + *backup_cpu = -1; + + /* + * In most cases, target_capacity tracks capacity_orig of the most + * energy efficient CPU candidate, thus requiring to minimise + * target_capacity. For these cases target_capacity is already + * initialized to ULONG_MAX. + * However, for prefer_idle and boosted tasks we look for a high + * performance CPU, thus requiring to maximise target_capacity. In this + * case we initialise target_capacity to 0. + */ + if (prefer_idle && boosted) + target_capacity = 0; - capacity = capacity_orig_of(cpu); - util = max_t(long, cpu_rq(cpu)->cfs.avg.util_avg - task_util(p), 0); + /* Find start CPU based on boost value */ + cpu = start_cpu(boosted); + if (cpu < 0) + return -1; + + /* Find SD for the start CPU */ + sd = rcu_dereference(per_cpu(sd_ea, cpu)); + if (!sd) + return -1; - return (util >= capacity) ? capacity : util; + /* Scan CPUs in all SDs */ + sg = sd->groups; + do { + for_each_cpu_and(i, &p->cpus_allowed, sched_group_span(sg)) { + unsigned long capacity_curr = capacity_curr_of(i); + unsigned long capacity_orig = capacity_orig_of(i); + unsigned long wake_util, new_util; + long spare_cap; + int idle_idx = INT_MAX; + + if (!cpu_online(i)) + continue; + + if (walt_cpu_high_irqload(i)) + continue; + + /* + * p's blocked utilization is still accounted for on prev_cpu + * so prev_cpu will receive a negative bias due to the double + * accounting. However, the blocked utilization may be zero. + */ + wake_util = cpu_util_without(i, p); + new_util = wake_util + task_util_est(p); + + /* + * Ensure minimum capacity to grant the required boost. + * The target CPU can be already at a capacity level higher + * than the one required to boost the task. + */ + new_util = max(min_util, new_util); + if (new_util > capacity_orig) + continue; + + /* + * Pre-compute the maximum possible capacity we expect + * to have available on this CPU once the task is + * enqueued here. + */ + spare_cap = capacity_orig - new_util; + + if (idle_cpu(i)) + idle_idx = idle_get_state_idx(cpu_rq(i)); + + + /* + * Case A) Latency sensitive tasks + * + * Unconditionally favoring tasks that prefer idle CPU to + * improve latency. + * + * Looking for: + * - an idle CPU, whatever its idle_state is, since + * the first CPUs we explore are more likely to be + * reserved for latency sensitive tasks. + * - a non idle CPU where the task fits in its current + * capacity and has the maximum spare capacity. + * - a non idle CPU with lower contention from other + * tasks and running at the lowest possible OPP. + * + * The last two goals tries to favor a non idle CPU + * where the task can run as if it is "almost alone". + * A maximum spare capacity CPU is favoured since + * the task already fits into that CPU's capacity + * without waiting for an OPP chance. + * + * The following code path is the only one in the CPUs + * exploration loop which is always used by + * prefer_idle tasks. It exits the loop with wither a + * best_active_cpu or a target_cpu which should + * represent an optimal choice for latency sensitive + * tasks. + */ + if (prefer_idle) { + + /* + * Case A.1: IDLE CPU + * Return the best IDLE CPU we find: + * - for boosted tasks: the CPU with the highest + * performance (i.e. biggest capacity_orig) + * - for !boosted tasks: the most energy + * efficient CPU (i.e. smallest capacity_orig) + */ + if (idle_cpu(i)) { + if (boosted && + capacity_orig < target_capacity) + continue; + if (!boosted && + capacity_orig > target_capacity) + continue; + if (capacity_orig == target_capacity && + sysctl_sched_cstate_aware && + best_idle_cstate <= idle_idx) + continue; + + target_capacity = capacity_orig; + best_idle_cstate = idle_idx; + best_idle_cpu = i; + continue; + } + if (best_idle_cpu != -1) + continue; + + /* + * Case A.2: Target ACTIVE CPU + * Favor CPUs with max spare capacity. + */ + if (capacity_curr > new_util && + spare_cap > target_max_spare_cap) { + target_max_spare_cap = spare_cap; + target_cpu = i; + continue; + } + if (target_cpu != -1) + continue; + + + /* + * Case A.3: Backup ACTIVE CPU + * Favor CPUs with: + * - lower utilization due to other tasks + * - lower utilization with the task in + */ + if (wake_util > min_wake_util) + continue; + if (new_util > best_active_util) + continue; + min_wake_util = wake_util; + best_active_util = new_util; + best_active_cpu = i; + continue; + } + + /* + * Enforce EAS mode + * + * For non latency sensitive tasks, skip CPUs that + * will be overutilized by moving the task there. + * + * The goal here is to remain in EAS mode as long as + * possible at least for !prefer_idle tasks. + */ + if ((new_util * capacity_margin) > + (capacity_orig * SCHED_CAPACITY_SCALE)) + continue; + + /* + * Favor CPUs with smaller capacity for non latency + * sensitive tasks. + */ + if (capacity_orig > target_capacity) + continue; + + /* + * Case B) Non latency sensitive tasks on IDLE CPUs. + * + * Find an optimal backup IDLE CPU for non latency + * sensitive tasks. + * + * Looking for: + * - minimizing the capacity_orig, + * i.e. preferring LITTLE CPUs + * - favoring shallowest idle states + * i.e. avoid to wakeup deep-idle CPUs + * + * The following code path is used by non latency + * sensitive tasks if IDLE CPUs are available. If at + * least one of such CPUs are available it sets the + * best_idle_cpu to the most suitable idle CPU to be + * selected. + * + * If idle CPUs are available, favour these CPUs to + * improve performances by spreading tasks. + * Indeed, the energy_diff() computed by the caller + * will take care to ensure the minimization of energy + * consumptions without affecting performance. + */ + if (idle_cpu(i)) { + /* + * Skip CPUs in deeper idle state, but only + * if they are also less energy efficient. + * IOW, prefer a deep IDLE LITTLE CPU vs a + * shallow idle big CPU. + */ + if (capacity_orig == target_capacity && + sysctl_sched_cstate_aware && + best_idle_cstate <= idle_idx) + continue; + + target_capacity = capacity_orig; + best_idle_cstate = idle_idx; + best_idle_cpu = i; + continue; + } + + /* + * Case C) Non latency sensitive tasks on ACTIVE CPUs. + * + * Pack tasks in the most energy efficient capacities. + * + * This task packing strategy prefers more energy + * efficient CPUs (i.e. pack on smaller maximum + * capacity CPUs) while also trying to spread tasks to + * run them all at the lower OPP. + * + * This assumes for example that it's more energy + * efficient to run two tasks on two CPUs at a lower + * OPP than packing both on a single CPU but running + * that CPU at an higher OPP. + * + * Thus, this case keep track of the CPU with the + * smallest maximum capacity and highest spare maximum + * capacity. + */ + + /* Favor CPUs with maximum spare capacity */ + if (capacity_orig == target_capacity && + spare_cap < target_max_spare_cap) + continue; + + target_max_spare_cap = spare_cap; + target_capacity = capacity_orig; + target_util = new_util; + target_cpu = i; + } + + } while (sg = sg->next, sg != sd->groups); + + /* + * For non latency sensitive tasks, cases B and C in the previous loop, + * we pick the best IDLE CPU only if we was not able to find a target + * ACTIVE CPU. + * + * Policies priorities: + * + * - prefer_idle tasks: + * + * a) IDLE CPU available: best_idle_cpu + * b) ACTIVE CPU where task fits and has the bigger maximum spare + * capacity (i.e. target_cpu) + * c) ACTIVE CPU with less contention due to other tasks + * (i.e. best_active_cpu) + * + * - NON prefer_idle tasks: + * + * a) ACTIVE CPU: target_cpu + * b) IDLE CPU: best_idle_cpu + */ + + if (prefer_idle && (best_idle_cpu != -1)) { + trace_sched_find_best_target(p, prefer_idle, min_util, cpu, + best_idle_cpu, best_active_cpu, + best_idle_cpu); + + return best_idle_cpu; + } + + if (target_cpu == -1) + target_cpu = prefer_idle + ? best_active_cpu + : best_idle_cpu; + else + *backup_cpu = prefer_idle + ? best_active_cpu + : best_idle_cpu; + + trace_sched_find_best_target(p, prefer_idle, min_util, cpu, + best_idle_cpu, best_active_cpu, + target_cpu); + + /* it is possible for target and backup + * to select same CPU - if so, drop backup + */ + if (*backup_cpu == target_cpu) + *backup_cpu = -1; + + return target_cpu; } /* @@ -5930,8 +7617,11 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu) { long min_cap, max_cap; + if (!static_branch_unlikely(&sched_asym_cpucapacity)) + return 0; + min_cap = min(capacity_orig_of(prev_cpu), capacity_orig_of(cpu)); - max_cap = cpu_rq(cpu)->rd->max_cpu_capacity; + max_cap = cpu_rq(cpu)->rd->max_cpu_capacity.val; /* Minimum capacity is close to max, no need to abort wake_affine */ if (max_cap - min_cap < max_cap >> 3) @@ -5940,7 +7630,297 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu) /* Bring task utilization in sync with prev_cpu */ sync_entity_load_avg(&p->se); - return min_cap * 1024 < task_util(p) * capacity_margin; + return !task_fits_capacity(p, min_cap); +} + +static bool cpu_overutilized(int cpu) +{ + return (capacity_of(cpu) * 1024) < (cpu_util(cpu) * capacity_margin); +} + +DEFINE_PER_CPU(struct energy_env, eenv_cache); + +/* kernels often have NR_CPUS defined to be much + * larger than exist in practise on booted systems. + * Allocate the cpu array for eenv calculations + * at boot time to avoid massive overprovisioning. + */ +#ifdef DEBUG_EENV_DECISIONS +static inline int eenv_debug_size_per_dbg_entry(void) +{ + return sizeof(struct _eenv_debug) + (sizeof(unsigned long) * num_possible_cpus()); +} + +static inline int eenv_debug_size_per_cpu_entry(void) +{ + /* each cpu struct has an array of _eenv_debug structs + * which have an array of unsigned longs at the end - + * the allocation should be extended so that there are + * at least 'num_possible_cpus' entries in the array. + */ + return EAS_EENV_DEBUG_LEVELS * eenv_debug_size_per_dbg_entry(); +} +/* given a per-_eenv_cpu debug env ptr, get the ptr for a given index */ +static inline struct _eenv_debug *eenv_debug_entry_ptr(struct _eenv_debug *base, int idx) +{ + char *ptr = (char *)base; + ptr += (idx * eenv_debug_size_per_dbg_entry()); + return (struct _eenv_debug *)ptr; +} +/* given a pointer to the per-cpu global copy of _eenv_debug, get + * a pointer to the specified _eenv_cpu debug env. + */ +static inline struct _eenv_debug *eenv_debug_percpu_debug_env_ptr(struct _eenv_debug *base, int cpu_idx) +{ + char *ptr = (char *)base; + ptr += (cpu_idx * eenv_debug_size_per_cpu_entry()); + return (struct _eenv_debug *)ptr; +} + +static inline int eenv_debug_size(void) +{ + return num_possible_cpus() * eenv_debug_size_per_cpu_entry(); +} +#endif + +static inline void alloc_eenv(void) +{ + int cpu; + int cpu_count = num_possible_cpus(); + + for_each_possible_cpu(cpu) { + struct energy_env *eenv = &per_cpu(eenv_cache, cpu); + eenv->cpu = kmalloc(sizeof(struct eenv_cpu) * cpu_count, GFP_KERNEL); + eenv->eenv_cpu_count = cpu_count; +#ifdef DEBUG_EENV_DECISIONS + eenv->debug = (struct _eenv_debug *)kmalloc(eenv_debug_size(), GFP_KERNEL); +#endif + } +} + +static inline void reset_eenv(struct energy_env *eenv) +{ + int cpu_count; + struct eenv_cpu *cpu; +#ifdef DEBUG_EENV_DECISIONS + struct _eenv_debug *debug; + int cpu_idx; + debug = eenv->debug; +#endif + + cpu_count = eenv->eenv_cpu_count; + cpu = eenv->cpu; + memset(eenv, 0, sizeof(struct energy_env)); + eenv->cpu = cpu; + memset(eenv->cpu, 0, sizeof(struct eenv_cpu)*cpu_count); + eenv->eenv_cpu_count = cpu_count; + +#ifdef DEBUG_EENV_DECISIONS + memset(debug, 0, eenv_debug_size()); + eenv->debug = debug; + for(cpu_idx = 0; cpu_idx < eenv->eenv_cpu_count; cpu_idx++) + eenv->cpu[cpu_idx].debug = eenv_debug_percpu_debug_env_ptr(debug, cpu_idx); +#endif +} +/* + * get_eenv - reset the eenv struct cached for this CPU + * + * When the eenv is returned, it is configured to do + * energy calculations for the maximum number of CPUs + * the task can be placed on. The prev_cpu entry is + * filled in here. Callers are responsible for adding + * other CPU candidates up to eenv->max_cpu_count. + */ +static inline struct energy_env *get_eenv(struct task_struct *p, int prev_cpu) +{ + struct energy_env *eenv; + cpumask_t cpumask_possible_cpus; + int cpu = smp_processor_id(); + int i; + + eenv = &(per_cpu(eenv_cache, cpu)); + reset_eenv(eenv); + + /* populate eenv */ + eenv->p = p; + /* use boosted task util for capacity selection + * during energy calculation, but unboosted task + * util for group utilization calculations + */ + eenv->util_delta = task_util_est(p); + eenv->util_delta_boosted = boosted_task_util(p); + + cpumask_and(&cpumask_possible_cpus, &p->cpus_allowed, cpu_online_mask); + eenv->max_cpu_count = cpumask_weight(&cpumask_possible_cpus); + + for (i=0; i < eenv->max_cpu_count; i++) + eenv->cpu[i].cpu_id = -1; + eenv->cpu[EAS_CPU_PRV].cpu_id = prev_cpu; + eenv->next_idx = EAS_CPU_PRV; + + return eenv; +} + +/* + * Needs to be called inside rcu_read_lock critical section. + * sd is a pointer to the sched domain we wish to use for an + * energy-aware placement option. + */ +static int find_energy_efficient_cpu(struct sched_domain *sd, + struct task_struct *p, + int cpu, int prev_cpu, + int sync) +{ + int use_fbt = sched_feat(FIND_BEST_TARGET); + int cpu_iter, eas_cpu_idx = EAS_CPU_NXT; + int target_cpu = -1; + struct energy_env *eenv; + + if (sysctl_sched_sync_hint_enable && sync) { + if (cpumask_test_cpu(cpu, &p->cpus_allowed)) { + return cpu; + } + } + + /* prepopulate energy diff environment */ + eenv = get_eenv(p, prev_cpu); + if (eenv->max_cpu_count < 2) + return -1; + + if(!use_fbt) { + /* + * using this function outside wakeup balance will not supply + * an sd ptr. Instead, fetch the highest level with energy data. + */ + if (!sd) + sd = rcu_dereference(per_cpu(sd_ea, prev_cpu)); + + for_each_cpu_and(cpu_iter, &p->cpus_allowed, sched_domain_span(sd)) { + unsigned long spare; + + /* prev_cpu already in list */ + if (cpu_iter == prev_cpu) + continue; + + /* + * Consider only CPUs where the task is expected to + * fit without making the CPU overutilized. + */ + spare = capacity_spare_without(cpu_iter, p); + if (spare * 1024 < capacity_margin * task_util_est(p)) + continue; + + /* Add CPU candidate */ + eenv->cpu[eas_cpu_idx++].cpu_id = cpu_iter; + eenv->max_cpu_count = eas_cpu_idx; + + /* stop adding CPUs if we have no space left */ + if (eas_cpu_idx >= eenv->eenv_cpu_count) + break; + } + } else { + int boosted = (schedtune_task_boost(p) > 0); + int prefer_idle; + + /* + * give compiler a hint that if sched_features + * cannot be changed, it is safe to optimise out + * all if(prefer_idle) blocks. + */ + prefer_idle = sched_feat(EAS_PREFER_IDLE) ? + (schedtune_prefer_idle(p) > 0) : 0; + + eenv->max_cpu_count = EAS_CPU_BKP + 1; + + /* Find a cpu with sufficient capacity */ + target_cpu = find_best_target(p, &eenv->cpu[EAS_CPU_BKP].cpu_id, + boosted, prefer_idle); + + /* Immediately return a found idle CPU for a prefer_idle task */ + if (prefer_idle && target_cpu >= 0 && idle_cpu(target_cpu)) + return target_cpu; + + /* Place target into NEXT slot */ + eenv->cpu[EAS_CPU_NXT].cpu_id = target_cpu; + + /* take note if no backup was found */ + if (eenv->cpu[EAS_CPU_BKP].cpu_id < 0) + eenv->max_cpu_count = EAS_CPU_BKP; + + /* take note if no target was found */ + if (eenv->cpu[EAS_CPU_NXT].cpu_id < 0) + eenv->max_cpu_count = EAS_CPU_NXT; + } + + if (eenv->max_cpu_count == EAS_CPU_NXT) { + /* + * we did not find any energy-awareness + * candidates beyond prev_cpu, so we will + * fall-back to the regular slow-path. + */ + return -1; + } + + /* find most energy-efficient CPU */ + target_cpu = select_energy_cpu_idx(eenv) < 0 ? -1 : + eenv->cpu[eenv->next_idx].cpu_id; + + return target_cpu; +} + +static inline bool nohz_kick_needed(struct rq *rq, bool only_update); +static void nohz_balancer_kick(bool only_update); + +/* + * wake_energy: Make the decision if we want to use an energy-aware + * wakeup task placement or not. This is limited to situations where + * we cannot use energy-awareness right now. + * + * Returns TRUE if we should attempt energy-aware wakeup, FALSE if not. + * + * Should only be called from select_task_rq_fair inside the RCU + * read-side critical section. + */ +static inline int wake_energy(struct task_struct *p, int prev_cpu, + int sd_flag, int wake_flags) +{ + struct sched_domain *sd = NULL; + int sync = wake_flags & WF_SYNC; + + sd = rcu_dereference_sched(cpu_rq(prev_cpu)->sd); + + /* + * Check all definite no-energy-awareness conditions + */ + if (!sd) + return false; + + if (!energy_aware()) + return false; + + if (sd_overutilized(sd)) + return false; + + /* + * we cannot do energy-aware wakeup placement sensibly + * for tasks with 0 utilization, so let them be placed + * according to the normal strategy. + * However if fbt is in use we may still benefit from + * the heuristics we use there in selecting candidate + * CPUs. + */ + if (unlikely(!sched_feat(FIND_BEST_TARGET) && !task_util_est(p))) + return false; + + if(!sched_feat(EAS_PREFER_IDLE)){ + /* + * Force prefer-idle tasks into the slow path, this may not happen + * if none of the sd flags matched. + */ + if (schedtune_prefer_idle(p) > 0 && !sync) + return false; + } + return true; } /* @@ -5956,21 +7936,28 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu) * preempt must be disabled. */ static int -select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_flags) +select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_flags, + int sibling_count_hint) { - struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL; + struct sched_domain *tmp, *affine_sd = NULL; + struct sched_domain *sd = NULL, *energy_sd = NULL; int cpu = smp_processor_id(); int new_cpu = prev_cpu; int want_affine = 0; + int want_energy = 0; int sync = wake_flags & WF_SYNC; + rcu_read_lock(); + if (sd_flag & SD_BALANCE_WAKE) { record_wakee(p); - want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu) - && cpumask_test_cpu(cpu, &p->cpus_allowed); + want_energy = wake_energy(p, prev_cpu, sd_flag, wake_flags); + want_affine = !want_energy && + !wake_wide(p, sibling_count_hint) && + !wake_cap(p, cpu, prev_cpu) && + cpumask_test_cpu(cpu, &p->cpus_allowed); } - rcu_read_lock(); for_each_domain(cpu, tmp) { if (!(tmp->flags & SD_LOAD_BALANCE)) break; @@ -5985,9 +7972,22 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f break; } + /* + * If we are able to try an energy-aware wakeup, + * select the highest non-overutilized sched domain + * which includes this cpu and prev_cpu + * + * maybe want to not test prev_cpu and only consider + * the current one? + */ + if (want_energy && + !sd_overutilized(tmp) && + cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) + energy_sd = tmp; + if (tmp->flags & sd_flag) sd = tmp; - else if (!want_affine) + else if (!(want_affine || want_energy)) break; } @@ -6000,47 +8000,38 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f new_cpu = cpu; } + if (sd && !(sd_flag & SD_BALANCE_FORK)) { + /* + * We're going to need the task's util for capacity_spare_without + * in find_idlest_group. Sync it up to prev_cpu's + * last_update_time. + */ + sync_entity_load_avg(&p->se); + } + if (!sd) { - pick_cpu: +pick_cpu: if (sd_flag & SD_BALANCE_WAKE) /* XXX always ? */ new_cpu = select_idle_sibling(p, prev_cpu, new_cpu); - } else while (sd) { - struct sched_group *group; - int weight; - - if (!(sd->flags & sd_flag)) { - sd = sd->child; - continue; - } - - group = find_idlest_group(sd, p, cpu, sd_flag); - if (!group) { - sd = sd->child; - continue; - } - - new_cpu = find_idlest_cpu(group, p, cpu); - if (new_cpu == -1 || new_cpu == cpu) { - /* Now try balancing at a lower domain level of cpu */ - sd = sd->child; - continue; - } + } else { + if (energy_sd) + new_cpu = find_energy_efficient_cpu(energy_sd, p, cpu, prev_cpu, sync); - /* Now try balancing at a lower domain level of new_cpu */ - cpu = new_cpu; - weight = sd->span_weight; - sd = NULL; - for_each_domain(cpu, tmp) { - if (weight <= tmp->span_weight) - break; - if (tmp->flags & sd_flag) - sd = tmp; - } - /* while loop will break here if sd == NULL */ + /* if we did an energy-aware placement and had no choices available + * then fall back to the default find_idlest_cpu choice + */ + if (!energy_sd || (energy_sd && new_cpu == -1)) + new_cpu = find_idlest_cpu(sd, p, cpu, prev_cpu, sd_flag); } + rcu_read_unlock(); +#ifdef CONFIG_NO_HZ_COMMON + if (nohz_kick_needed(cpu_rq(new_cpu), true)) + nohz_balancer_kick(true); +#endif + return new_cpu; } @@ -6355,6 +8346,8 @@ again: if (hrtick_enabled(rq)) hrtick_start_fair(rq, p); + update_misfit_status(p, rq); + return p; simple: #endif @@ -6372,9 +8365,12 @@ simple: if (hrtick_enabled(rq)) hrtick_start_fair(rq, p); + update_misfit_status(p, rq); + return p; idle: + update_misfit_status(NULL, rq); new_tasks = idle_balance(rq, rf); /* @@ -6580,6 +8576,13 @@ static unsigned long __read_mostly max_load_balance_interval = HZ/10; enum fbq_type { regular, remote, all }; +enum group_type { + group_other = 0, + group_misfit_task, + group_imbalanced, + group_overloaded, +}; + #define LBF_ALL_PINNED 0x01 #define LBF_NEED_BREAK 0x02 #define LBF_DST_PINNED 0x04 @@ -6598,6 +8601,7 @@ struct lb_env { int new_dst_cpu; enum cpu_idle_type idle; long imbalance; + unsigned int src_grp_nr_running; /* The set of CPUs under consideration for load-balancing */ struct cpumask *cpus; @@ -6608,6 +8612,7 @@ struct lb_env { unsigned int loop_max; enum fbq_type fbq_type; + enum group_type src_grp_type; struct list_head tasks; }; @@ -6787,13 +8792,18 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) /* * detach_task() -- detach the task for the migration specified in env */ -static void detach_task(struct task_struct *p, struct lb_env *env) +static void detach_task(struct task_struct *p, struct lb_env *env, + struct rq_flags *rf) { lockdep_assert_held(&env->src_rq->lock); p->on_rq = TASK_ON_RQ_MIGRATING; deactivate_task(env->src_rq, p, DEQUEUE_NOCLOCK); + rq_unpin_lock(env->src_rq, rf); + double_lock_balance(env->src_rq, env->dst_rq); set_task_cpu(p, env->dst_cpu); + double_unlock_balance(env->src_rq, env->dst_rq); + rq_repin_lock(env->src_rq, rf); } /* @@ -6802,7 +8812,8 @@ static void detach_task(struct task_struct *p, struct lb_env *env) * * Returns a task if successful and NULL otherwise. */ -static struct task_struct *detach_one_task(struct lb_env *env) +static struct task_struct *detach_one_task(struct lb_env *env, + struct rq_flags *rf) { struct task_struct *p, *n; @@ -6812,7 +8823,7 @@ static struct task_struct *detach_one_task(struct lb_env *env) if (!can_migrate_task(p, env)) continue; - detach_task(p, env); + detach_task(p, env, rf); /* * Right now, this is only the second place where @@ -6834,7 +8845,7 @@ static const unsigned int sched_nr_migrate_break = 32; * * Returns number of detached tasks if successful and 0 otherwise. */ -static int detach_tasks(struct lb_env *env) +static int detach_tasks(struct lb_env *env, struct rq_flags *rf) { struct list_head *tasks = &env->src_rq->cfs_tasks; struct task_struct *p; @@ -6887,7 +8898,7 @@ static int detach_tasks(struct lb_env *env) if ((load / 2) > env->imbalance) goto next; - detach_task(p, env); + detach_task(p, env, rf); list_add(&p->se.group_node, &env->tasks); detached++; @@ -7005,6 +9016,10 @@ static void update_blocked_averages(int cpu) if (se && !skip_blocked_update(se)) update_load_avg(se, 0); } + update_rt_rq_load_avg(rq_clock_task(rq), cpu, &rq->rt, 0); +#ifdef CONFIG_NO_HZ_COMMON + rq->last_blocked_load_update_tick = jiffies; +#endif rq_unlock_irqrestore(rq, &rf); } @@ -7064,6 +9079,10 @@ static inline void update_blocked_averages(int cpu) rq_lock_irqsave(rq, &rf); update_rq_clock(rq); update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq); + update_rt_rq_load_avg(rq_clock_task(rq), cpu, &rq->rt, 0); +#ifdef CONFIG_NO_HZ_COMMON + rq->last_blocked_load_update_tick = jiffies; +#endif rq_unlock_irqrestore(rq, &rf); } @@ -7075,12 +9094,6 @@ static unsigned long task_h_load(struct task_struct *p) /********** Helpers for find_busiest_group ************************/ -enum group_type { - group_other = 0, - group_imbalanced, - group_overloaded, -}; - /* * sg_lb_stats - stats of a sched_group required for load_balancing */ @@ -7096,6 +9109,8 @@ struct sg_lb_stats { unsigned int group_weight; enum group_type group_type; int group_no_capacity; + /* A cpu has a task too big for its capacity */ + unsigned long group_misfit_task_load; #ifdef CONFIG_NUMA_BALANCING unsigned int nr_numa_running; unsigned int nr_preferred_running; @@ -7112,6 +9127,7 @@ struct sd_lb_stats { unsigned long total_running; unsigned long total_load; /* Total load of all groups in sd */ unsigned long total_capacity; /* Total capacity of all groups in sd */ + unsigned long total_util; /* Total util of all groups in sd */ unsigned long avg_load; /* Average load across all groups in sd */ struct sg_lb_stats busiest_stat;/* Statistics of the busiest group */ @@ -7132,6 +9148,7 @@ static inline void init_sd_lb_stats(struct sd_lb_stats *sds) .total_running = 0UL, .total_load = 0UL, .total_capacity = 0UL, + .total_util = 0UL, .busiest_stat = { .avg_load = 0UL, .sum_nr_running = 0, @@ -7195,13 +9212,46 @@ static unsigned long scale_rt_capacity(int cpu) return 1; } +void init_max_cpu_capacity(struct max_cpu_capacity *mcc) +{ + raw_spin_lock_init(&mcc->lock); + mcc->val = 0; + mcc->cpu = -1; +} + static void update_cpu_capacity(struct sched_domain *sd, int cpu) { unsigned long capacity = arch_scale_cpu_capacity(sd, cpu); struct sched_group *sdg = sd->groups; + struct max_cpu_capacity *mcc; + unsigned long max_capacity; + int max_cap_cpu; + unsigned long flags; cpu_rq(cpu)->cpu_capacity_orig = capacity; + capacity *= arch_scale_max_freq_capacity(sd, cpu); + capacity >>= SCHED_CAPACITY_SHIFT; + + mcc = &cpu_rq(cpu)->rd->max_cpu_capacity; + + raw_spin_lock_irqsave(&mcc->lock, flags); + max_capacity = mcc->val; + max_cap_cpu = mcc->cpu; + + if ((max_capacity > capacity && max_cap_cpu == cpu) || + max_capacity < capacity) { + mcc->val = capacity; + mcc->cpu = cpu; +#ifdef CONFIG_SCHED_DEBUG + raw_spin_unlock_irqrestore(&mcc->lock, flags); + pr_info("CPU%d: update max cpu_capacity %lu\n", cpu, capacity); + goto skip_unlock; +#endif + } + raw_spin_unlock_irqrestore(&mcc->lock, flags); + +skip_unlock: __attribute__ ((unused)); capacity *= scale_rt_capacity(cpu); capacity >>= SCHED_CAPACITY_SHIFT; @@ -7211,13 +9261,14 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu) cpu_rq(cpu)->cpu_capacity = capacity; sdg->sgc->capacity = capacity; sdg->sgc->min_capacity = capacity; + sdg->sgc->max_capacity = capacity; } void update_group_capacity(struct sched_domain *sd, int cpu) { struct sched_domain *child = sd->child; struct sched_group *group, *sdg = sd->groups; - unsigned long capacity, min_capacity; + unsigned long capacity, min_capacity, max_capacity; unsigned long interval; interval = msecs_to_jiffies(sd->balance_interval); @@ -7231,6 +9282,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu) capacity = 0; min_capacity = ULONG_MAX; + max_capacity = 0; if (child->flags & SD_OVERLAP) { /* @@ -7261,6 +9313,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu) } min_capacity = min(capacity, min_capacity); + max_capacity = max(capacity, max_capacity); } } else { /* @@ -7274,12 +9327,14 @@ void update_group_capacity(struct sched_domain *sd, int cpu) capacity += sgc->capacity; min_capacity = min(sgc->min_capacity, min_capacity); + max_capacity = max(sgc->max_capacity, max_capacity); group = group->next; } while (group != child->groups); } sdg->sgc->capacity = capacity; sdg->sgc->min_capacity = min_capacity; + sdg->sgc->max_capacity = max_capacity; } /* @@ -7375,16 +9430,40 @@ group_is_overloaded(struct lb_env *env, struct sg_lb_stats *sgs) } /* - * group_smaller_cpu_capacity: Returns true if sched_group sg has smaller + * group_smaller_min_cpu_capacity: Returns true if sched_group sg has smaller * per-CPU capacity than sched_group ref. */ static inline bool -group_smaller_cpu_capacity(struct sched_group *sg, struct sched_group *ref) +group_smaller_min_cpu_capacity(struct sched_group *sg, struct sched_group *ref) { return sg->sgc->min_capacity * capacity_margin < ref->sgc->min_capacity * 1024; } +/* + * group_smaller_max_cpu_capacity: Returns true if sched_group sg has smaller + * per-CPU capacity_orig than sched_group ref. + */ +static inline bool +group_smaller_max_cpu_capacity(struct sched_group *sg, struct sched_group *ref) +{ + return sg->sgc->max_capacity * capacity_margin < + ref->sgc->max_capacity * 1024; +} + +/* + * group_similar_cpu_capacity: Returns true if the minimum capacity of the + * compared groups differ by less than 12.5%. + */ +static inline bool +group_similar_cpu_capacity(struct sched_group *sg, struct sched_group *ref) +{ + long diff = sg->sgc->min_capacity - ref->sgc->min_capacity; + long max = max(sg->sgc->min_capacity, ref->sgc->min_capacity); + + return abs(diff) < max >> 3; +} + static inline enum group_type group_classify(struct sched_group *group, struct sg_lb_stats *sgs) @@ -7395,6 +9474,9 @@ group_type group_classify(struct sched_group *group, if (sg_imbalanced(group)) return group_imbalanced; + if (sgs->group_misfit_task_load) + return group_misfit_task; + return group_other; } @@ -7405,12 +9487,13 @@ group_type group_classify(struct sched_group *group, * @load_idx: Load index of sched_domain of this_cpu for load calc. * @local_group: Does group contain this_cpu. * @sgs: variable to hold the statistics for this group. - * @overload: Indicate more than one runnable task for any CPU. + * @overload: Indicate pullable load (e.g. >1 runnable task). + * @overutilized: Indicate overutilization for any CPU. */ static inline void update_sg_lb_stats(struct lb_env *env, struct sched_group *group, int load_idx, int local_group, struct sg_lb_stats *sgs, - bool *overload) + bool *overload, bool *overutilized, bool *misfit_task) { unsigned long load; int i, nr_running; @@ -7444,6 +9527,20 @@ static inline void update_sg_lb_stats(struct lb_env *env, */ if (!nr_running && idle_cpu(i)) sgs->idle_cpus++; + + if (env->sd->flags & SD_ASYM_CPUCAPACITY && + sgs->group_misfit_task_load < rq->misfit_task_load) { + sgs->group_misfit_task_load = rq->misfit_task_load; + *overload = 1; + } + + + if (cpu_overutilized(i)) { + *overutilized = true; + + if (rq->misfit_task_load) + *misfit_task = true; + } } /* Adjust by relative CPU capacity of the group */ @@ -7479,6 +9576,17 @@ static bool update_sd_pick_busiest(struct lb_env *env, { struct sg_lb_stats *busiest = &sds->busiest_stat; + /* + * Don't try to pull misfit tasks we can't help. + * We can use max_capacity here as reduction in capacity on some + * cpus in the group should either be possible to resolve + * internally or be covered by avg_load imbalance (eventually). + */ + if (sgs->group_type == group_misfit_task && + (!group_smaller_max_cpu_capacity(sg, sds->local) || + !group_has_capacity(env, &sds->local_stat))) + return false; + if (sgs->group_type > busiest->group_type) return true; @@ -7498,7 +9606,23 @@ static bool update_sd_pick_busiest(struct lb_env *env, * power/energy consequences are not considered. */ if (sgs->sum_nr_running <= sgs->group_weight && - group_smaller_cpu_capacity(sds->local, sg)) + group_smaller_min_cpu_capacity(sds->local, sg)) + return false; + + /* + * Candidate sg doesn't face any severe imbalance issues so + * don't disturb unless the groups are of similar capacity + * where balancing is more harmless. + */ + if (sgs->group_type == group_other && + !group_similar_cpu_capacity(sds->local, sg)) + return false; + + /* + * If we have more than one misfit sg go with the biggest misfit. + */ + if (sgs->group_type == group_misfit_task && + sgs->group_misfit_task_load < busiest->group_misfit_task_load) return false; asym_packing: @@ -7558,6 +9682,18 @@ static inline enum fbq_type fbq_classify_rq(struct rq *rq) } #endif /* CONFIG_NUMA_BALANCING */ +#ifdef CONFIG_NO_HZ_COMMON +static struct { + cpumask_var_t idle_cpus_mask; + atomic_t nr_cpus; + unsigned long next_balance; /* in jiffy units */ + unsigned long next_update; /* in jiffy units */ +} nohz ____cacheline_aligned; +#endif + +#define lb_sd_parent(sd) \ + (sd->parent && sd->parent->groups != sd->parent->groups->next) + /** * update_sd_lb_stats - Update sched_domain's statistics for load balancing. * @env: The load balancing environment. @@ -7569,11 +9705,33 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd struct sched_group *sg = env->sd->groups; struct sg_lb_stats *local = &sds->local_stat; struct sg_lb_stats tmp_sgs; - int load_idx, prefer_sibling = 0; - bool overload = false; + int load_idx; + bool overload = false, overutilized = false, misfit_task = false; + bool prefer_sibling = child && child->flags & SD_PREFER_SIBLING; - if (child && child->flags & SD_PREFER_SIBLING) - prefer_sibling = 1; +#ifdef CONFIG_NO_HZ_COMMON + if (env->idle == CPU_NEWLY_IDLE) { + int cpu; + + /* Update the stats of NOHZ idle CPUs in the sd */ + for_each_cpu_and(cpu, sched_domain_span(env->sd), + nohz.idle_cpus_mask) { + struct rq *rq = cpu_rq(cpu); + + /* ... Unless we've already done since the last tick */ + if (time_after(jiffies, + rq->last_blocked_load_update_tick)) + update_blocked_averages(cpu); + } + } + /* + * If we've just updated all of the NOHZ idle CPUs, then we can push + * back the next nohz.next_update, which will prevent an unnecessary + * wakeup for the nohz stats kick + */ + if (cpumask_subset(nohz.idle_cpus_mask, sched_domain_span(env->sd))) + nohz.next_update = jiffies + LOAD_AVG_PERIOD; +#endif load_idx = get_sd_load_idx(env->sd, env->idle); @@ -7592,7 +9750,8 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd } update_sg_lb_stats(env, sg, load_idx, local_group, sgs, - &overload); + &overload, &overutilized, + &misfit_task); if (local_group) goto next_group; @@ -7624,6 +9783,7 @@ next_group: sds->total_running += sgs->sum_nr_running; sds->total_load += sgs->group_load; sds->total_capacity += sgs->group_capacity; + sds->total_util += sgs->group_util; sg = sg->next; } while (sg != env->sd->groups); @@ -7631,11 +9791,52 @@ next_group: if (env->sd->flags & SD_NUMA) env->fbq_type = fbq_classify_group(&sds->busiest_stat); - if (!env->sd->parent) { + env->src_grp_nr_running = sds->busiest_stat.sum_nr_running; + + if (!lb_sd_parent(env->sd)) { /* update overload indicator if we are at root domain */ - if (env->dst_rq->rd->overload != overload) - env->dst_rq->rd->overload = overload; + if (READ_ONCE(env->dst_rq->rd->overload) != overload) + WRITE_ONCE(env->dst_rq->rd->overload, overload); + } + + if (overutilized) + set_sd_overutilized(env->sd); + else + clear_sd_overutilized(env->sd); + + /* + * If there is a misfit task in one cpu in this sched_domain + * it is likely that the imbalance cannot be sorted out among + * the cpu's in this sched_domain. In this case set the + * overutilized flag at the parent sched_domain. + */ + if (misfit_task) { + struct sched_domain *sd = env->sd->parent; + + /* + * In case of a misfit task, load balance at the parent + * sched domain level will make sense only if the the cpus + * have a different capacity. If cpus at a domain level have + * the same capacity, the misfit task cannot be well + * accomodated in any of the cpus and there in no point in + * trying a load balance at this level + */ + while (sd) { + if (sd->flags & SD_ASYM_CPUCAPACITY) { + set_sd_overutilized(sd); + break; + } + sd = sd->parent; + } } + + /* + * If the domain util is greater that domain capacity, load balancing + * needs to be done at the next sched domain level as well. + */ + if (lb_sd_parent(env->sd) && + sds->total_capacity * 1024 < sds->total_util * capacity_margin) + set_sd_overutilized(env->sd->parent); } /** @@ -7751,7 +9952,22 @@ void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds) capa_move /= SCHED_CAPACITY_SCALE; /* Move if we gain throughput */ - if (capa_move > capa_now) + if (capa_move > capa_now) { + env->imbalance = busiest->load_per_task; + return; + } + + /* We can't see throughput improvement with the load-based + * method, but it is possible depending upon group size and + * capacity range that there might still be an underutilized + * cpu available in an asymmetric capacity system. Do one last + * check just in case. + */ + if (env->sd->flags & SD_ASYM_CPUCAPACITY && + busiest->group_type == group_overloaded && + busiest->sum_nr_running > busiest->group_weight && + local->sum_nr_running < local->group_weight && + local->group_capacity < busiest->group_capacity) env->imbalance = busiest->load_per_task; } @@ -7784,8 +10000,9 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * factors in sg capacity and sgs with smaller group_type are * skipped when updating the busiest sg: */ - if (busiest->avg_load <= sds->avg_load || - local->avg_load >= sds->avg_load) { + if (busiest->group_type != group_misfit_task && + (busiest->avg_load <= sds->avg_load || + local->avg_load >= sds->avg_load)) { env->imbalance = 0; return fix_small_imbalance(env, sds); } @@ -7819,6 +10036,22 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s (sds->avg_load - local->avg_load) * local->group_capacity ) / SCHED_CAPACITY_SCALE; + /* Boost imbalance to allow misfit task to be balanced. + * Always do this if we are doing a NEWLY_IDLE balance + * on the assumption that any tasks we have must not be + * long-running (and hence we cannot rely upon load). + * However if we are not idle, we should assume the tasks + * we have are longer running and not override load-based + * calculations above unless we are sure that the local + * group is underutilized. + */ + if (busiest->group_type == group_misfit_task && + (env->idle == CPU_NEWLY_IDLE || + local->sum_nr_running < local->group_weight)) { + env->imbalance = max_t(long, env->imbalance, + busiest->group_misfit_task_load); + } + /* * if *imbalance is less than the average load per runnable task * there is no guarantee that any tasks will be moved so we'll have @@ -7854,6 +10087,10 @@ static struct sched_group *find_busiest_group(struct lb_env *env) * this level. */ update_sd_lb_stats(env, &sds); + + if (energy_aware() && !sd_overutilized(env->sd)) + goto out_balanced; + local = &sds.local_stat; busiest = &sds.busiest_stat; @@ -7877,11 +10114,18 @@ static struct sched_group *find_busiest_group(struct lb_env *env) if (busiest->group_type == group_imbalanced) goto force_balance; - /* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */ - if (env->idle == CPU_NEWLY_IDLE && group_has_capacity(env, local) && + /* + * When dst_cpu is idle, prevent SMP nice and/or asymmetric group + * capacities from resulting in underutilization due to avg_load. + */ + if (env->idle != CPU_NOT_IDLE && group_has_capacity(env, local) && busiest->group_no_capacity) goto force_balance; + /* Misfit tasks should be dealt with regardless of the avg load */ + if (busiest->group_type == group_misfit_task) + goto force_balance; + /* * If the local group is busier than the selected busiest group * don't try and pull any tasks. @@ -7919,6 +10163,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env) force_balance: /* Looks like there is an imbalance. Compute it */ + env->src_grp_type = busiest->group_type; calculate_imbalance(env, &sds); return sds.busiest; @@ -7966,8 +10211,31 @@ static struct rq *find_busiest_queue(struct lb_env *env, if (rt > env->fbq_type) continue; + /* + * For ASYM_CPUCAPACITY domains with misfit tasks we simply + * seek the "biggest" misfit task. + */ + if (env->src_grp_type == group_misfit_task) { + if (rq->misfit_task_load > busiest_load) { + busiest_load = rq->misfit_task_load; + busiest = rq; + } + continue; + } + capacity = capacity_of(i); + /* + * For ASYM_CPUCAPACITY domains, don't pick a cpu that could + * eventually lead to active_balancing high->low capacity. + * Higher per-cpu capacity is considered better than balancing + * average load. + */ + if (env->sd->flags & SD_ASYM_CPUCAPACITY && + capacity_of(env->dst_cpu) < capacity && + rq->nr_running == 1) + continue; + wl = weighted_cpuload(rq); /* @@ -8035,6 +10303,21 @@ static int need_active_balance(struct lb_env *env) return 1; } + if ((capacity_of(env->src_cpu) < capacity_of(env->dst_cpu)) && + ((capacity_orig_of(env->src_cpu) < capacity_orig_of(env->dst_cpu))) && + env->src_rq->cfs.h_nr_running == 1 && + cpu_overutilized(env->src_cpu) && + !cpu_overutilized(env->dst_cpu)) { + return 1; + } + + if (env->src_grp_type == group_misfit_task) + return 1; + + if (env->src_grp_type == group_overloaded && + env->src_rq->misfit_task_load) + return 1; + return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2); } @@ -8087,7 +10370,7 @@ static int load_balance(int this_cpu, struct rq *this_rq, int *continue_balancing) { int ld_moved, cur_ld_moved, active_balance = 0; - struct sched_domain *sd_parent = sd->parent; + struct sched_domain *sd_parent = lb_sd_parent(sd) ? sd->parent : NULL; struct sched_group *group; struct rq *busiest; struct rq_flags rf; @@ -8153,7 +10436,7 @@ more_balance: * cur_ld_moved - load moved in current iteration * ld_moved - cumulative load moved across iterations */ - cur_ld_moved = detach_tasks(&env); + cur_ld_moved = detach_tasks(&env, &rf); /* * We've detached some tasks from busiest_rq. Every @@ -8253,7 +10536,8 @@ more_balance: * excessive cache_hot migrations and active balances. */ if (idle != CPU_NEWLY_IDLE) - sd->nr_balance_failed++; + if (env.src_grp_nr_running > 1) + sd->nr_balance_failed++; if (need_active_balance(&env)) { unsigned long flags; @@ -8359,6 +10643,7 @@ static inline unsigned long get_sd_balance_interval(struct sched_domain *sd, int cpu_busy) { unsigned long interval = sd->balance_interval; + unsigned int cpu; if (cpu_busy) interval *= sd->busy_factor; @@ -8367,6 +10652,24 @@ get_sd_balance_interval(struct sched_domain *sd, int cpu_busy) interval = msecs_to_jiffies(interval); interval = clamp(interval, 1UL, max_load_balance_interval); + /* + * check if sched domain is marked as overutilized + * we ought to only do this on systems which have SD_ASYMCAPACITY + * but we want to do it for all sched domains in those systems + * So for now, just check if overutilized as a proxy. + */ + /* + * If we are overutilized and we have a misfit task, then + * we want to balance as soon as practically possible, so + * we return an interval of zero. + */ + if (energy_aware() && sd_overutilized(sd)) { + /* we know the root is overutilized, let's check for a misfit task */ + for_each_cpu(cpu, sched_domain_span(sd)) { + if (cpu_rq(cpu)->misfit_task_load) + return 1; + } + } return interval; } @@ -8416,7 +10719,7 @@ static int idle_balance(struct rq *this_rq, struct rq_flags *rf) rq_unpin_lock(this_rq, rf); if (this_rq->avg_idle < sysctl_sched_migration_cost || - !this_rq->rd->overload) { + !READ_ONCE(this_rq->rd->overload)) { rcu_read_lock(); sd = rcu_dereference_check_sched_domain(this_rq->sd); if (sd) @@ -8434,8 +10737,12 @@ static int idle_balance(struct rq *this_rq, struct rq_flags *rf) int continue_balancing = 1; u64 t0, domain_cost; - if (!(sd->flags & SD_LOAD_BALANCE)) + if (!(sd->flags & SD_LOAD_BALANCE)) { + if (time_after_eq(jiffies, + sd->groups->sgc->next_update)) + update_group_capacity(sd, this_cpu); continue; + } if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost) { update_next_balance(sd, &next_balance); @@ -8566,7 +10873,7 @@ static int active_load_balance_cpu_stop(void *data) schedstat_inc(sd->alb_count); update_rq_clock(busiest_rq); - p = detach_one_task(&env); + p = detach_one_task(&env, &rf); if (p) { schedstat_inc(sd->alb_pushed); /* Active balancing done, reset the failure counter. */ @@ -8600,11 +10907,6 @@ static inline int on_null_domain(struct rq *rq) * needed, they will kick the idle load balancer, which then does idle * load balancing for all the idle CPUs. */ -static struct { - cpumask_var_t idle_cpus_mask; - atomic_t nr_cpus; - unsigned long next_balance; /* in jiffy units */ -} nohz ____cacheline_aligned; static inline int find_new_ilb(void) { @@ -8621,7 +10923,7 @@ static inline int find_new_ilb(void) * nohz_load_balancer CPU (if there is one) otherwise fallback to any idle * CPU (if there is one). */ -static void nohz_balancer_kick(void) +static void nohz_balancer_kick(bool only_update) { int ilb_cpu; @@ -8634,6 +10936,10 @@ static void nohz_balancer_kick(void) if (test_and_set_bit(NOHZ_BALANCE_KICK, nohz_flags(ilb_cpu))) return; + + if (only_update) + set_bit(NOHZ_STATS_KICK, nohz_flags(ilb_cpu)); + /* * Use smp_send_reschedule() instead of resched_cpu(). * This way we generate a sched IPI on the target cpu which @@ -8721,6 +11027,8 @@ void nohz_balance_enter_idle(int cpu) atomic_inc(&nohz.nr_cpus); set_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)); } +#else +static inline void nohz_balancer_kick(bool only_update) {} #endif static DEFINE_SPINLOCK(balancing); @@ -8752,8 +11060,6 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle) int need_serialize, need_decay = 0; u64 max_cost = 0; - update_blocked_averages(cpu); - rcu_read_lock(); for_each_domain(cpu, sd) { /* @@ -8768,8 +11074,15 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle) } max_cost += sd->max_newidle_lb_cost; - if (!(sd->flags & SD_LOAD_BALANCE)) + if (energy_aware() && !sd_overutilized(sd)) + continue; + + if (!(sd->flags & SD_LOAD_BALANCE)) { + if (time_after_eq(jiffies, + sd->groups->sgc->next_update)) + update_group_capacity(sd, cpu); continue; + } /* * Stop the load balance at this level. There is another @@ -8852,6 +11165,7 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) { int this_cpu = this_rq->cpu; struct rq *rq; + struct sched_domain *sd; int balance_cpu; /* Earliest time when we have to do rebalance again */ unsigned long next_balance = jiffies + 60*HZ; @@ -8861,6 +11175,23 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) !test_bit(NOHZ_BALANCE_KICK, nohz_flags(this_cpu))) goto end; + /* + * This cpu is going to update the blocked load of idle CPUs either + * before doing a rebalancing or just to keep metrics up to date. we + * can safely update the next update timestamp + */ + rcu_read_lock(); + sd = rcu_dereference(this_rq->sd); + /* + * Check whether there is a sched_domain available for this cpu. + * The last other cpu can have been unplugged since the ILB has been + * triggered and the sched_domain can now be null. The idle balance + * sequence will quickly be aborted as there is no more idle CPUs + */ + if (sd) + nohz.next_update = jiffies + msecs_to_jiffies(LOAD_AVG_PERIOD); + rcu_read_unlock(); + for_each_cpu(balance_cpu, nohz.idle_cpus_mask) { if (balance_cpu == this_cpu || !idle_cpu(balance_cpu)) continue; @@ -8887,7 +11218,15 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) cpu_load_update_idle(rq); rq_unlock_irq(rq, &rf); - rebalance_domains(rq, CPU_IDLE); + update_blocked_averages(balance_cpu); + /* + * This idle load balance softirq may have been + * triggered only to update the blocked load and shares + * of idle CPUs (which we have just done for + * balance_cpu). In that case skip the actual balance. + */ + if (!test_bit(NOHZ_STATS_KICK, nohz_flags(this_cpu))) + rebalance_domains(rq, idle); } if (time_after(next_balance, rq->next_balance)) { @@ -8918,7 +11257,7 @@ end: * - For SD_ASYM_PACKING, if the lower numbered cpu's in the scheduler * domain span are idle. */ -static inline bool nohz_kick_needed(struct rq *rq) +static inline bool nohz_kick_needed(struct rq *rq, bool only_update) { unsigned long now = jiffies; struct sched_domain_shared *sds; @@ -8926,7 +11265,7 @@ static inline bool nohz_kick_needed(struct rq *rq) int nr_busy, i, cpu = rq->cpu; bool kick = false; - if (unlikely(rq->idle_balance)) + if (unlikely(rq->idle_balance) && !only_update) return false; /* @@ -8943,15 +11282,27 @@ static inline bool nohz_kick_needed(struct rq *rq) if (likely(!atomic_read(&nohz.nr_cpus))) return false; + if (only_update) { + if (time_before(now, nohz.next_update)) + return false; + else + return true; + } + if (time_before(now, nohz.next_balance)) return false; - if (rq->nr_running >= 2) + if (rq->nr_running >= 2 && + (!energy_aware() || cpu_overutilized(cpu))) return true; + /* Do idle load balance if there have misfit task */ + if (energy_aware()) + return rq->misfit_task_load; + rcu_read_lock(); sds = rcu_dereference(per_cpu(sd_llc_shared, cpu)); - if (sds) { + if (sds && !energy_aware()) { /* * XXX: write a coherent comment on why we do this. * See also: http://lkml.kernel.org/r/20111202010832.602203411@sbsiddha-desk.sc.intel.com @@ -8992,6 +11343,7 @@ unlock: } #else static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) { } +static inline bool nohz_kick_needed(struct rq *rq, bool only_update) { return false; } #endif /* @@ -9013,7 +11365,14 @@ static __latent_entropy void run_rebalance_domains(struct softirq_action *h) * and abort nohz_idle_balance altogether if we pull some load. */ nohz_idle_balance(this_rq, idle); + update_blocked_averages(this_rq->cpu); +#ifdef CONFIG_NO_HZ_COMMON + if (!test_bit(NOHZ_STATS_KICK, nohz_flags(this_rq->cpu))) + rebalance_domains(this_rq, idle); + clear_bit(NOHZ_STATS_KICK, nohz_flags(this_rq->cpu)); +#else rebalance_domains(this_rq, idle); +#endif } /* @@ -9028,8 +11387,8 @@ void trigger_load_balance(struct rq *rq) if (time_after_eq(jiffies, rq->next_balance)) raise_softirq(SCHED_SOFTIRQ); #ifdef CONFIG_NO_HZ_COMMON - if (nohz_kick_needed(rq)) - nohz_balancer_kick(); + if (nohz_kick_needed(rq, false)) + nohz_balancer_kick(false); #endif } @@ -9065,6 +11424,10 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) if (static_branch_unlikely(&sched_numa_balancing)) task_tick_numa(rq, curr); + + update_misfit_status(curr, rq); + + update_overutilized_status(rq); } /* @@ -9609,8 +11972,11 @@ __init void init_sched_fair_class(void) #ifdef CONFIG_NO_HZ_COMMON nohz.next_balance = jiffies; + nohz.next_update = jiffies; zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT); #endif + + alloc_eenv(); #endif /* SMP */ } diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 9552fd5854bf..dbade300ef8c 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -85,3 +85,47 @@ SCHED_FEAT(ATTACH_AGE_LOAD, true) SCHED_FEAT(WA_IDLE, true) SCHED_FEAT(WA_WEIGHT, true) SCHED_FEAT(WA_BIAS, true) + +/* + * UtilEstimation. Use estimated CPU utilization. + */ +SCHED_FEAT(UTIL_EST, true) + +/* + * Energy aware scheduling. Use platform energy model to guide scheduling + * decisions optimizing for energy efficiency. + */ +#ifdef CONFIG_DEFAULT_USE_ENERGY_AWARE +SCHED_FEAT(ENERGY_AWARE, true) +#else +SCHED_FEAT(ENERGY_AWARE, false) +#endif + +/* + * Energy aware scheduling algorithm choices: + * EAS_PREFER_IDLE + * Direct tasks in a schedtune.prefer_idle=1 group through + * the EAS path for wakeup task placement. Otherwise, put + * those tasks through the mainline slow path. + * FIND_BEST_TARGET + * Limit the number of placement options for which we calculate + * energy by using heuristics to select 'best idle' and + * 'best active' cpu options. + * FBT_STRICT_ORDER + * ON: If the target CPU saves any energy, use that. + * OFF: Use whichever of target or backup saves most. + */ +SCHED_FEAT(EAS_PREFER_IDLE, true) +SCHED_FEAT(FIND_BEST_TARGET, true) +SCHED_FEAT(FBT_STRICT_ORDER, true) + +/* + * Apply schedtune boost hold to tasks of all sched classes. + * If enabled, schedtune will hold the boost applied to a CPU + * for 50ms regardless of task activation - if the task is + * still running 50ms later, the boost hold expires and schedtune + * boost will expire immediately the task stops. + * If disabled, this behaviour will only apply to tasks of the + * RT class. + */ +SCHED_FEAT(SCHEDTUNE_BOOST_HOLD_ALL, false) diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 257f4f0b4532..2e973e667b0d 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -25,9 +25,10 @@ extern char __cpuidle_text_start[], __cpuidle_text_end[]; * sched_idle_set_state - Record idle state for the current CPU. * @idle_state: State to record. */ -void sched_idle_set_state(struct cpuidle_state *idle_state) +void sched_idle_set_state(struct cpuidle_state *idle_state, int index) { idle_set_state(this_rq(), idle_state); + idle_set_state_idx(this_rq(), index); } static int __read_mostly cpu_idle_force_poll; @@ -146,13 +147,15 @@ static void cpuidle_idle_call(void) } /* - * Tell the RCU framework we are entering an idle section, - * so no more rcu read side critical sections and one more + * The RCU framework needs to be told that we are entering an idle + * section, so no more rcu read side critical sections and one more * step to the grace period */ - rcu_idle_enter(); if (cpuidle_not_available(drv, dev)) { + tick_nohz_idle_stop_tick(); + rcu_idle_enter(); + default_idle_call(); goto exit_idle; } @@ -169,20 +172,37 @@ static void cpuidle_idle_call(void) if (idle_should_enter_s2idle() || dev->use_deepest_state) { if (idle_should_enter_s2idle()) { + rcu_idle_enter(); + entered_state = cpuidle_enter_s2idle(drv, dev); if (entered_state > 0) { local_irq_enable(); goto exit_idle; } + + rcu_idle_exit(); } + tick_nohz_idle_stop_tick(); + rcu_idle_enter(); + next_state = cpuidle_find_deepest_state(drv, dev); call_cpuidle(drv, dev, next_state); } else { + bool stop_tick = true; + /* * Ask the cpuidle framework to choose a convenient idle state. */ - next_state = cpuidle_select(drv, dev); + next_state = cpuidle_select(drv, dev, &stop_tick); + + if (stop_tick) + tick_nohz_idle_stop_tick(); + else + tick_nohz_idle_retain_tick(); + + rcu_idle_enter(); + entered_state = call_cpuidle(drv, dev, next_state); /* * Give the governor an opportunity to reflect on the outcome @@ -227,6 +247,7 @@ static void do_idle(void) rmb(); if (cpu_is_offline(smp_processor_id())) { + tick_nohz_idle_stop_tick_protected(); cpuhp_report_idle_dead(); arch_cpu_idle_dead(); } @@ -240,10 +261,12 @@ static void do_idle(void) * broadcast device expired for us, we don't want to go deep * idle as we know that the IPI is going to arrive right away. */ - if (cpu_idle_force_poll || tick_check_broadcast_expired()) + if (cpu_idle_force_poll || tick_check_broadcast_expired()) { + tick_nohz_idle_restart_tick(); cpu_idle_poll(); - else + } else { cpuidle_idle_call(); + } arch_cpu_idle_exit(); } diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c index d518664cce4f..609abdf1c938 100644 --- a/kernel/sched/idle_task.c +++ b/kernel/sched/idle_task.c @@ -10,7 +10,8 @@ #ifdef CONFIG_SMP static int -select_task_rq_idle(struct task_struct *p, int cpu, int sd_flag, int flags) +select_task_rq_idle(struct task_struct *p, int cpu, int sd_flag, int flags, + int sibling_count_hint) { return task_cpu(p); /* IDLE tasks as never migrated */ } diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index 89a989e4d758..73157e882918 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -95,19 +95,73 @@ long calc_load_fold_active(struct rq *this_rq, long adjust) return delta; } -/* - * a1 = a0 * e + a * (1 - e) +/** + * fixed_power_int - compute: x^n, in O(log n) time + * + * @x: base of the power + * @frac_bits: fractional bits of @x + * @n: power to raise @x to. + * + * By exploiting the relation between the definition of the natural power + * function: x^n := x*x*...*x (x multiplied by itself for n times), and + * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i, + * (where: n_i \elem {0, 1}, the binary vector representing n), + * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is + * of course trivially computable in O(log_2 n), the length of our binary + * vector. */ static unsigned long -calc_load(unsigned long load, unsigned long exp, unsigned long active) +fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n) { - unsigned long newload; + unsigned long result = 1UL << frac_bits; + + if (n) { + for (;;) { + if (n & 1) { + result *= x; + result += 1UL << (frac_bits - 1); + result >>= frac_bits; + } + n >>= 1; + if (!n) + break; + x *= x; + x += 1UL << (frac_bits - 1); + x >>= frac_bits; + } + } - newload = load * exp + active * (FIXED_1 - exp); - if (active >= load) - newload += FIXED_1-1; + return result; +} - return newload / FIXED_1; +/* + * a1 = a0 * e + a * (1 - e) + * + * a2 = a1 * e + a * (1 - e) + * = (a0 * e + a * (1 - e)) * e + a * (1 - e) + * = a0 * e^2 + a * (1 - e) * (1 + e) + * + * a3 = a2 * e + a * (1 - e) + * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e) + * = a0 * e^3 + a * (1 - e) * (1 + e + e^2) + * + * ... + * + * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1] + * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e) + * = a0 * e^n + a * (1 - e^n) + * + * [1] application of the geometric series: + * + * n 1 - x^(n+1) + * S_n := \Sum x^i = ------------- + * i=0 1 - x + */ +unsigned long +calc_load_n(unsigned long load, unsigned long exp, + unsigned long active, unsigned int n) +{ + return calc_load(load, fixed_power_int(exp, FSHIFT, n), active); } #ifdef CONFIG_NO_HZ_COMMON @@ -229,75 +283,6 @@ static long calc_load_nohz_fold(void) return delta; } -/** - * fixed_power_int - compute: x^n, in O(log n) time - * - * @x: base of the power - * @frac_bits: fractional bits of @x - * @n: power to raise @x to. - * - * By exploiting the relation between the definition of the natural power - * function: x^n := x*x*...*x (x multiplied by itself for n times), and - * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i, - * (where: n_i \elem {0, 1}, the binary vector representing n), - * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is - * of course trivially computable in O(log_2 n), the length of our binary - * vector. - */ -static unsigned long -fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n) -{ - unsigned long result = 1UL << frac_bits; - - if (n) { - for (;;) { - if (n & 1) { - result *= x; - result += 1UL << (frac_bits - 1); - result >>= frac_bits; - } - n >>= 1; - if (!n) - break; - x *= x; - x += 1UL << (frac_bits - 1); - x >>= frac_bits; - } - } - - return result; -} - -/* - * a1 = a0 * e + a * (1 - e) - * - * a2 = a1 * e + a * (1 - e) - * = (a0 * e + a * (1 - e)) * e + a * (1 - e) - * = a0 * e^2 + a * (1 - e) * (1 + e) - * - * a3 = a2 * e + a * (1 - e) - * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e) - * = a0 * e^3 + a * (1 - e) * (1 + e + e^2) - * - * ... - * - * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1] - * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e) - * = a0 * e^n + a * (1 - e^n) - * - * [1] application of the geometric series: - * - * n 1 - x^(n+1) - * S_n := \Sum x^i = ------------- - * i=0 1 - x - */ -static unsigned long -calc_load_n(unsigned long load, unsigned long exp, - unsigned long active, unsigned int n) -{ - return calc_load(load, fixed_power_int(exp, FSHIFT, n), active); -} - /* * NO_HZ can leave us missing all per-cpu ticks calling * calc_load_fold_active(), but since a NO_HZ CPU folds its delta into diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c new file mode 100644 index 000000000000..59d5371694e4 --- /dev/null +++ b/kernel/sched/psi.c @@ -0,0 +1,1285 @@ +/* + * Pressure stall information for CPU, memory and IO + * + * Copyright (c) 2018 Facebook, Inc. + * Author: Johannes Weiner <hannes@cmpxchg.org> + * + * Polling support by Suren Baghdasaryan <surenb@google.com> + * Copyright (c) 2018 Google, Inc. + * + * When CPU, memory and IO are contended, tasks experience delays that + * reduce throughput and introduce latencies into the workload. Memory + * and IO contention, in addition, can cause a full loss of forward + * progress in which the CPU goes idle. + * + * This code aggregates individual task delays into resource pressure + * metrics that indicate problems with both workload health and + * resource utilization. + * + * Model + * + * The time in which a task can execute on a CPU is our baseline for + * productivity. Pressure expresses the amount of time in which this + * potential cannot be realized due to resource contention. + * + * This concept of productivity has two components: the workload and + * the CPU. To measure the impact of pressure on both, we define two + * contention states for a resource: SOME and FULL. + * + * In the SOME state of a given resource, one or more tasks are + * delayed on that resource. This affects the workload's ability to + * perform work, but the CPU may still be executing other tasks. + * + * In the FULL state of a given resource, all non-idle tasks are + * delayed on that resource such that nobody is advancing and the CPU + * goes idle. This leaves both workload and CPU unproductive. + * + * (Naturally, the FULL state doesn't exist for the CPU resource.) + * + * SOME = nr_delayed_tasks != 0 + * FULL = nr_delayed_tasks != 0 && nr_running_tasks == 0 + * + * The percentage of wallclock time spent in those compound stall + * states gives pressure numbers between 0 and 100 for each resource, + * where the SOME percentage indicates workload slowdowns and the FULL + * percentage indicates reduced CPU utilization: + * + * %SOME = time(SOME) / period + * %FULL = time(FULL) / period + * + * Multiple CPUs + * + * The more tasks and available CPUs there are, the more work can be + * performed concurrently. This means that the potential that can go + * unrealized due to resource contention *also* scales with non-idle + * tasks and CPUs. + * + * Consider a scenario where 257 number crunching tasks are trying to + * run concurrently on 256 CPUs. If we simply aggregated the task + * states, we would have to conclude a CPU SOME pressure number of + * 100%, since *somebody* is waiting on a runqueue at all + * times. However, that is clearly not the amount of contention the + * workload is experiencing: only one out of 256 possible exceution + * threads will be contended at any given time, or about 0.4%. + * + * Conversely, consider a scenario of 4 tasks and 4 CPUs where at any + * given time *one* of the tasks is delayed due to a lack of memory. + * Again, looking purely at the task state would yield a memory FULL + * pressure number of 0%, since *somebody* is always making forward + * progress. But again this wouldn't capture the amount of execution + * potential lost, which is 1 out of 4 CPUs, or 25%. + * + * To calculate wasted potential (pressure) with multiple processors, + * we have to base our calculation on the number of non-idle tasks in + * conjunction with the number of available CPUs, which is the number + * of potential execution threads. SOME becomes then the proportion of + * delayed tasks to possibe threads, and FULL is the share of possible + * threads that are unproductive due to delays: + * + * threads = min(nr_nonidle_tasks, nr_cpus) + * SOME = min(nr_delayed_tasks / threads, 1) + * FULL = (threads - min(nr_running_tasks, threads)) / threads + * + * For the 257 number crunchers on 256 CPUs, this yields: + * + * threads = min(257, 256) + * SOME = min(1 / 256, 1) = 0.4% + * FULL = (256 - min(257, 256)) / 256 = 0% + * + * For the 1 out of 4 memory-delayed tasks, this yields: + * + * threads = min(4, 4) + * SOME = min(1 / 4, 1) = 25% + * FULL = (4 - min(3, 4)) / 4 = 25% + * + * [ Substitute nr_cpus with 1, and you can see that it's a natural + * extension of the single-CPU model. ] + * + * Implementation + * + * To assess the precise time spent in each such state, we would have + * to freeze the system on task changes and start/stop the state + * clocks accordingly. Obviously that doesn't scale in practice. + * + * Because the scheduler aims to distribute the compute load evenly + * among the available CPUs, we can track task state locally to each + * CPU and, at much lower frequency, extrapolate the global state for + * the cumulative stall times and the running averages. + * + * For each runqueue, we track: + * + * tSOME[cpu] = time(nr_delayed_tasks[cpu] != 0) + * tFULL[cpu] = time(nr_delayed_tasks[cpu] && !nr_running_tasks[cpu]) + * tNONIDLE[cpu] = time(nr_nonidle_tasks[cpu] != 0) + * + * and then periodically aggregate: + * + * tNONIDLE = sum(tNONIDLE[i]) + * + * tSOME = sum(tSOME[i] * tNONIDLE[i]) / tNONIDLE + * tFULL = sum(tFULL[i] * tNONIDLE[i]) / tNONIDLE + * + * %SOME = tSOME / period + * %FULL = tFULL / period + * + * This gives us an approximation of pressure that is practical + * cost-wise, yet way more sensitive and accurate than periodic + * sampling of the aggregate task states would be. + */ + +#include "../workqueue_internal.h" +#include <uapi/linux/sched/types.h> +#include <linux/sched/loadavg.h> +#include <linux/seq_file.h> +#include <linux/proc_fs.h> +#include <linux/seqlock.h> +#include <linux/uaccess.h> +#include <linux/cgroup.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/ctype.h> +#include <linux/file.h> +#include <linux/poll.h> +#include <linux/psi.h> +#include "sched.h" + +static int psi_bug __read_mostly; + +DEFINE_STATIC_KEY_FALSE(psi_disabled); + +#ifdef CONFIG_PSI_DEFAULT_DISABLED +static bool psi_enable; +#else +static bool psi_enable = true; +#endif +static int __init setup_psi(char *str) +{ + return kstrtobool(str, &psi_enable) == 0; +} +__setup("psi=", setup_psi); + +/* Running averages - we need to be higher-res than loadavg */ +#define PSI_FREQ (2*HZ+1) /* 2 sec intervals */ +#define EXP_10s 1677 /* 1/exp(2s/10s) as fixed-point */ +#define EXP_60s 1981 /* 1/exp(2s/60s) */ +#define EXP_300s 2034 /* 1/exp(2s/300s) */ + +/* PSI trigger definitions */ +#define WINDOW_MIN_US 500000 /* Min window size is 500ms */ +#define WINDOW_MAX_US 10000000 /* Max window size is 10s */ +#define UPDATES_PER_WINDOW 10 /* 10 updates per window */ + +/* Sampling frequency in nanoseconds */ +static u64 psi_period __read_mostly; + +/* System-level pressure and stall tracking */ +static DEFINE_PER_CPU(struct psi_group_cpu, system_group_pcpu); +static struct psi_group psi_system = { + .pcpu = &system_group_pcpu, +}; + +static void psi_avgs_work(struct work_struct *work); + +static void group_init(struct psi_group *group) +{ + int cpu; + + for_each_possible_cpu(cpu) + seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq); + group->avg_last_update = sched_clock(); + group->avg_next_update = group->avg_last_update + psi_period; + INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work); + mutex_init(&group->avgs_lock); + /* Init trigger-related members */ + atomic_set(&group->poll_scheduled, 0); + mutex_init(&group->trigger_lock); + INIT_LIST_HEAD(&group->triggers); + memset(group->nr_triggers, 0, sizeof(group->nr_triggers)); + group->poll_states = 0; + group->poll_min_period = U32_MAX; + memset(group->polling_total, 0, sizeof(group->polling_total)); + group->polling_next_update = ULLONG_MAX; + group->polling_until = 0; + rcu_assign_pointer(group->poll_kworker, NULL); +} + +void __init psi_init(void) +{ + if (!psi_enable) { + static_branch_enable(&psi_disabled); + return; + } + + psi_period = jiffies_to_nsecs(PSI_FREQ); + group_init(&psi_system); +} + +static bool test_state(unsigned int *tasks, enum psi_states state) +{ + switch (state) { + case PSI_IO_SOME: + return tasks[NR_IOWAIT]; + case PSI_IO_FULL: + return tasks[NR_IOWAIT] && !tasks[NR_RUNNING]; + case PSI_MEM_SOME: + return tasks[NR_MEMSTALL]; + case PSI_MEM_FULL: + return tasks[NR_MEMSTALL] && !tasks[NR_RUNNING]; + case PSI_CPU_SOME: + return tasks[NR_RUNNING] > 1; + case PSI_NONIDLE: + return tasks[NR_IOWAIT] || tasks[NR_MEMSTALL] || + tasks[NR_RUNNING]; + default: + return false; + } +} + +static void get_recent_times(struct psi_group *group, int cpu, + enum psi_aggregators aggregator, u32 *times, + u32 *pchanged_states) +{ + struct psi_group_cpu *groupc = per_cpu_ptr(group->pcpu, cpu); + u64 now, state_start; + enum psi_states s; + unsigned int seq; + u32 state_mask; + + *pchanged_states = 0; + + /* Snapshot a coherent view of the CPU state */ + do { + seq = read_seqcount_begin(&groupc->seq); + now = cpu_clock(cpu); + memcpy(times, groupc->times, sizeof(groupc->times)); + state_mask = groupc->state_mask; + state_start = groupc->state_start; + } while (read_seqcount_retry(&groupc->seq, seq)); + + /* Calculate state time deltas against the previous snapshot */ + for (s = 0; s < NR_PSI_STATES; s++) { + u32 delta; + /* + * In addition to already concluded states, we also + * incorporate currently active states on the CPU, + * since states may last for many sampling periods. + * + * This way we keep our delta sampling buckets small + * (u32) and our reported pressure close to what's + * actually happening. + */ + if (state_mask & (1 << s)) + times[s] += now - state_start; + + delta = times[s] - groupc->times_prev[aggregator][s]; + groupc->times_prev[aggregator][s] = times[s]; + + times[s] = delta; + if (delta) + *pchanged_states |= (1 << s); + } +} + +static void calc_avgs(unsigned long avg[3], int missed_periods, + u64 time, u64 period) +{ + unsigned long pct; + + /* Fill in zeroes for periods of no activity */ + if (missed_periods) { + avg[0] = calc_load_n(avg[0], EXP_10s, 0, missed_periods); + avg[1] = calc_load_n(avg[1], EXP_60s, 0, missed_periods); + avg[2] = calc_load_n(avg[2], EXP_300s, 0, missed_periods); + } + + /* Sample the most recent active period */ + pct = div_u64(time * 100, period); + pct *= FIXED_1; + avg[0] = calc_load(avg[0], EXP_10s, pct); + avg[1] = calc_load(avg[1], EXP_60s, pct); + avg[2] = calc_load(avg[2], EXP_300s, pct); +} + +static void collect_percpu_times(struct psi_group *group, + enum psi_aggregators aggregator, + u32 *pchanged_states) +{ + u64 deltas[NR_PSI_STATES - 1] = { 0, }; + unsigned long nonidle_total = 0; + u32 changed_states = 0; + int cpu; + int s; + + /* + * Collect the per-cpu time buckets and average them into a + * single time sample that is normalized to wallclock time. + * + * For averaging, each CPU is weighted by its non-idle time in + * the sampling period. This eliminates artifacts from uneven + * loading, or even entirely idle CPUs. + */ + for_each_possible_cpu(cpu) { + u32 times[NR_PSI_STATES]; + u32 nonidle; + u32 cpu_changed_states; + + get_recent_times(group, cpu, aggregator, times, + &cpu_changed_states); + changed_states |= cpu_changed_states; + + nonidle = nsecs_to_jiffies(times[PSI_NONIDLE]); + nonidle_total += nonidle; + + for (s = 0; s < PSI_NONIDLE; s++) + deltas[s] += (u64)times[s] * nonidle; + } + + /* + * Integrate the sample into the running statistics that are + * reported to userspace: the cumulative stall times and the + * decaying averages. + * + * Pressure percentages are sampled at PSI_FREQ. We might be + * called more often when the user polls more frequently than + * that; we might be called less often when there is no task + * activity, thus no data, and clock ticks are sporadic. The + * below handles both. + */ + + /* total= */ + for (s = 0; s < NR_PSI_STATES - 1; s++) + group->total[aggregator][s] += + div_u64(deltas[s], max(nonidle_total, 1UL)); + + if (pchanged_states) + *pchanged_states = changed_states; +} + +static u64 update_averages(struct psi_group *group, u64 now) +{ + unsigned long missed_periods = 0; + u64 expires, period; + u64 avg_next_update; + int s; + + /* avgX= */ + expires = group->avg_next_update; + if (now - expires >= psi_period) + missed_periods = div_u64(now - expires, psi_period); + + /* + * The periodic clock tick can get delayed for various + * reasons, especially on loaded systems. To avoid clock + * drift, we schedule the clock in fixed psi_period intervals. + * But the deltas we sample out of the per-cpu buckets above + * are based on the actual time elapsing between clock ticks. + */ + avg_next_update = expires + ((1 + missed_periods) * psi_period); + period = now - (group->avg_last_update + (missed_periods * psi_period)); + group->avg_last_update = now; + + for (s = 0; s < NR_PSI_STATES - 1; s++) { + u32 sample; + + sample = group->total[PSI_AVGS][s] - group->avg_total[s]; + /* + * Due to the lockless sampling of the time buckets, + * recorded time deltas can slip into the next period, + * which under full pressure can result in samples in + * excess of the period length. + * + * We don't want to report non-sensical pressures in + * excess of 100%, nor do we want to drop such events + * on the floor. Instead we punt any overage into the + * future until pressure subsides. By doing this we + * don't underreport the occurring pressure curve, we + * just report it delayed by one period length. + * + * The error isn't cumulative. As soon as another + * delta slips from a period P to P+1, by definition + * it frees up its time T in P. + */ + if (sample > period) + sample = period; + group->avg_total[s] += sample; + calc_avgs(group->avg[s], missed_periods, sample, period); + } + + return avg_next_update; +} + +static void psi_avgs_work(struct work_struct *work) +{ + struct delayed_work *dwork; + struct psi_group *group; + u32 changed_states; + bool nonidle; + u64 now; + + dwork = to_delayed_work(work); + group = container_of(dwork, struct psi_group, avgs_work); + + mutex_lock(&group->avgs_lock); + + now = sched_clock(); + + collect_percpu_times(group, PSI_AVGS, &changed_states); + nonidle = changed_states & (1 << PSI_NONIDLE); + /* + * If there is task activity, periodically fold the per-cpu + * times and feed samples into the running averages. If things + * are idle and there is no data to process, stop the clock. + * Once restarted, we'll catch up the running averages in one + * go - see calc_avgs() and missed_periods. + */ + if (now >= group->avg_next_update) + group->avg_next_update = update_averages(group, now); + + if (nonidle) { + schedule_delayed_work(dwork, nsecs_to_jiffies( + group->avg_next_update - now) + 1); + } + + mutex_unlock(&group->avgs_lock); +} + +/* Trigger tracking window manupulations */ +static void window_reset(struct psi_window *win, u64 now, u64 value, + u64 prev_growth) +{ + win->start_time = now; + win->start_value = value; + win->prev_growth = prev_growth; +} + +/* + * PSI growth tracking window update and growth calculation routine. + * + * This approximates a sliding tracking window by interpolating + * partially elapsed windows using historical growth data from the + * previous intervals. This minimizes memory requirements (by not storing + * all the intermediate values in the previous window) and simplifies + * the calculations. It works well because PSI signal changes only in + * positive direction and over relatively small window sizes the growth + * is close to linear. + */ +static u64 window_update(struct psi_window *win, u64 now, u64 value) +{ + u64 elapsed; + u64 growth; + + elapsed = now - win->start_time; + growth = value - win->start_value; + /* + * After each tracking window passes win->start_value and + * win->start_time get reset and win->prev_growth stores + * the average per-window growth of the previous window. + * win->prev_growth is then used to interpolate additional + * growth from the previous window assuming it was linear. + */ + if (elapsed > win->size) + window_reset(win, now, value, growth); + else { + u32 remaining; + + remaining = win->size - elapsed; + growth += div64_u64(win->prev_growth * remaining, win->size); + } + + return growth; +} + +static void init_triggers(struct psi_group *group, u64 now) +{ + struct psi_trigger *t; + + list_for_each_entry(t, &group->triggers, node) + window_reset(&t->win, now, + group->total[PSI_POLL][t->state], 0); + memcpy(group->polling_total, group->total[PSI_POLL], + sizeof(group->polling_total)); + group->polling_next_update = now + group->poll_min_period; +} + +static u64 update_triggers(struct psi_group *group, u64 now) +{ + struct psi_trigger *t; + bool new_stall = false; + u64 *total = group->total[PSI_POLL]; + + /* + * On subsequent updates, calculate growth deltas and let + * watchers know when their specified thresholds are exceeded. + */ + list_for_each_entry(t, &group->triggers, node) { + u64 growth; + + /* Check for stall activity */ + if (group->polling_total[t->state] == total[t->state]) + continue; + + /* + * Multiple triggers might be looking at the same state, + * remember to update group->polling_total[] once we've + * been through all of them. Also remember to extend the + * polling time if we see new stall activity. + */ + new_stall = true; + + /* Calculate growth since last update */ + growth = window_update(&t->win, now, total[t->state]); + if (growth < t->threshold) + continue; + + /* Limit event signaling to once per window */ + if (now < t->last_event_time + t->win.size) + continue; + + /* Generate an event */ + if (cmpxchg(&t->event, 0, 1) == 0) + wake_up_interruptible(&t->event_wait); + t->last_event_time = now; + } + + if (new_stall) + memcpy(group->polling_total, total, + sizeof(group->polling_total)); + + return now + group->poll_min_period; +} + +/* + * Schedule polling if it's not already scheduled. It's safe to call even from + * hotpath because even though kthread_queue_delayed_work takes worker->lock + * spinlock that spinlock is never contended due to poll_scheduled atomic + * preventing such competition. + */ +static void psi_schedule_poll_work(struct psi_group *group, unsigned long delay) +{ + struct kthread_worker *kworker; + + /* Do not reschedule if already scheduled */ + if (atomic_cmpxchg(&group->poll_scheduled, 0, 1) != 0) + return; + + rcu_read_lock(); + + kworker = rcu_dereference(group->poll_kworker); + /* + * kworker might be NULL in case psi_trigger_destroy races with + * psi_task_change (hotpath) which can't use locks + */ + if (likely(kworker)) + kthread_queue_delayed_work(kworker, &group->poll_work, delay); + else + atomic_set(&group->poll_scheduled, 0); + + rcu_read_unlock(); +} + +static void psi_poll_work(struct kthread_work *work) +{ + struct kthread_delayed_work *dwork; + struct psi_group *group; + u32 changed_states; + u64 now; + + dwork = container_of(work, struct kthread_delayed_work, work); + group = container_of(dwork, struct psi_group, poll_work); + + atomic_set(&group->poll_scheduled, 0); + + mutex_lock(&group->trigger_lock); + + now = sched_clock(); + + collect_percpu_times(group, PSI_POLL, &changed_states); + + if (changed_states & group->poll_states) { + /* Initialize trigger windows when entering polling mode */ + if (now > group->polling_until) + init_triggers(group, now); + + /* + * Keep the monitor active for at least the duration of the + * minimum tracking window as long as monitor states are + * changing. + */ + group->polling_until = now + + group->poll_min_period * UPDATES_PER_WINDOW; + } + + if (now > group->polling_until) { + group->polling_next_update = ULLONG_MAX; + goto out; + } + + if (now >= group->polling_next_update) + group->polling_next_update = update_triggers(group, now); + + psi_schedule_poll_work(group, + nsecs_to_jiffies(group->polling_next_update - now) + 1); + +out: + mutex_unlock(&group->trigger_lock); +} + +static void record_times(struct psi_group_cpu *groupc, int cpu, + bool memstall_tick) +{ + u32 delta; + u64 now; + + now = cpu_clock(cpu); + delta = now - groupc->state_start; + groupc->state_start = now; + + if (groupc->state_mask & (1 << PSI_IO_SOME)) { + groupc->times[PSI_IO_SOME] += delta; + if (groupc->state_mask & (1 << PSI_IO_FULL)) + groupc->times[PSI_IO_FULL] += delta; + } + + if (groupc->state_mask & (1 << PSI_MEM_SOME)) { + groupc->times[PSI_MEM_SOME] += delta; + if (groupc->state_mask & (1 << PSI_MEM_FULL)) + groupc->times[PSI_MEM_FULL] += delta; + else if (memstall_tick) { + u32 sample; + /* + * Since we care about lost potential, a + * memstall is FULL when there are no other + * working tasks, but also when the CPU is + * actively reclaiming and nothing productive + * could run even if it were runnable. + * + * When the timer tick sees a reclaiming CPU, + * regardless of runnable tasks, sample a FULL + * tick (or less if it hasn't been a full tick + * since the last state change). + */ + sample = min(delta, (u32)jiffies_to_nsecs(1)); + groupc->times[PSI_MEM_FULL] += sample; + } + } + + if (groupc->state_mask & (1 << PSI_CPU_SOME)) + groupc->times[PSI_CPU_SOME] += delta; + + if (groupc->state_mask & (1 << PSI_NONIDLE)) + groupc->times[PSI_NONIDLE] += delta; +} + +static u32 psi_group_change(struct psi_group *group, int cpu, + unsigned int clear, unsigned int set) +{ + struct psi_group_cpu *groupc; + unsigned int t, m; + enum psi_states s; + u32 state_mask = 0; + + groupc = per_cpu_ptr(group->pcpu, cpu); + + /* + * First we assess the aggregate resource states this CPU's + * tasks have been in since the last change, and account any + * SOME and FULL time these may have resulted in. + * + * Then we update the task counts according to the state + * change requested through the @clear and @set bits. + */ + write_seqcount_begin(&groupc->seq); + + record_times(groupc, cpu, false); + + for (t = 0, m = clear; m; m &= ~(1 << t), t++) { + if (!(m & (1 << t))) + continue; + if (groupc->tasks[t] == 0 && !psi_bug) { + printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u] clear=%x set=%x\n", + cpu, t, groupc->tasks[0], + groupc->tasks[1], groupc->tasks[2], + clear, set); + psi_bug = 1; + } + groupc->tasks[t]--; + } + + for (t = 0; set; set &= ~(1 << t), t++) + if (set & (1 << t)) + groupc->tasks[t]++; + + /* Calculate state mask representing active states */ + for (s = 0; s < NR_PSI_STATES; s++) { + if (test_state(groupc->tasks, s)) + state_mask |= (1 << s); + } + groupc->state_mask = state_mask; + + write_seqcount_end(&groupc->seq); + + return state_mask; +} + +static struct psi_group *iterate_groups(struct task_struct *task, void **iter) +{ +#ifdef CONFIG_CGROUPS + struct cgroup *cgroup = NULL; + + if (!*iter) + cgroup = task->cgroups->dfl_cgrp; + else if (*iter == &psi_system) + return NULL; + else + cgroup = cgroup_parent(*iter); + + if (cgroup && cgroup_parent(cgroup)) { + *iter = cgroup; + return cgroup_psi(cgroup); + } +#else + if (*iter) + return NULL; +#endif + *iter = &psi_system; + return &psi_system; +} + +void psi_task_change(struct task_struct *task, int clear, int set) +{ + int cpu = task_cpu(task); + struct psi_group *group; + bool wake_clock = true; + void *iter = NULL; + + if (!task->pid) + return; + + if (((task->psi_flags & set) || + (task->psi_flags & clear) != clear) && + !psi_bug) { + printk_deferred(KERN_ERR "psi: inconsistent task state! task=%d:%s cpu=%d psi_flags=%x clear=%x set=%x\n", + task->pid, task->comm, cpu, + task->psi_flags, clear, set); + psi_bug = 1; + } + + task->psi_flags &= ~clear; + task->psi_flags |= set; + + /* + * Periodic aggregation shuts off if there is a period of no + * task changes, so we wake it back up if necessary. However, + * don't do this if the task change is the aggregation worker + * itself going to sleep, or we'll ping-pong forever. + */ + if (unlikely((clear & TSK_RUNNING) && + (task->flags & PF_WQ_WORKER) && + wq_worker_last_func(task) == psi_avgs_work)) + wake_clock = false; + + while ((group = iterate_groups(task, &iter))) { + u32 state_mask = psi_group_change(group, cpu, clear, set); + + if (state_mask & group->poll_states) + psi_schedule_poll_work(group, 1); + + if (wake_clock && !delayed_work_pending(&group->avgs_work)) + schedule_delayed_work(&group->avgs_work, PSI_FREQ); + } +} + +void psi_memstall_tick(struct task_struct *task, int cpu) +{ + struct psi_group *group; + void *iter = NULL; + + while ((group = iterate_groups(task, &iter))) { + struct psi_group_cpu *groupc; + + groupc = per_cpu_ptr(group->pcpu, cpu); + write_seqcount_begin(&groupc->seq); + record_times(groupc, cpu, true); + write_seqcount_end(&groupc->seq); + } +} + +/** + * psi_memstall_enter - mark the beginning of a memory stall section + * @flags: flags to handle nested sections + * + * Marks the calling task as being stalled due to a lack of memory, + * such as waiting for a refault or performing reclaim. + */ +void psi_memstall_enter(unsigned long *flags) +{ + struct rq_flags rf; + struct rq *rq; + + if (static_branch_likely(&psi_disabled)) + return; + + *flags = current->flags & PF_MEMSTALL; + if (*flags) + return; + /* + * PF_MEMSTALL setting & accounting needs to be atomic wrt + * changes to the task's scheduling state, otherwise we can + * race with CPU migration. + */ + rq = this_rq_lock_irq(&rf); + + current->flags |= PF_MEMSTALL; + psi_task_change(current, 0, TSK_MEMSTALL); + + rq_unlock_irq(rq, &rf); +} + +/** + * psi_memstall_leave - mark the end of an memory stall section + * @flags: flags to handle nested memdelay sections + * + * Marks the calling task as no longer stalled due to lack of memory. + */ +void psi_memstall_leave(unsigned long *flags) +{ + struct rq_flags rf; + struct rq *rq; + + if (static_branch_likely(&psi_disabled)) + return; + + if (*flags) + return; + /* + * PF_MEMSTALL clearing & accounting needs to be atomic wrt + * changes to the task's scheduling state, otherwise we could + * race with CPU migration. + */ + rq = this_rq_lock_irq(&rf); + + current->flags &= ~PF_MEMSTALL; + psi_task_change(current, TSK_MEMSTALL, 0); + + rq_unlock_irq(rq, &rf); +} + +#ifdef CONFIG_CGROUPS +int psi_cgroup_alloc(struct cgroup *cgroup) +{ + if (static_branch_likely(&psi_disabled)) + return 0; + + cgroup->psi.pcpu = alloc_percpu(struct psi_group_cpu); + if (!cgroup->psi.pcpu) + return -ENOMEM; + group_init(&cgroup->psi); + return 0; +} + +void psi_cgroup_free(struct cgroup *cgroup) +{ + if (static_branch_likely(&psi_disabled)) + return; + + cancel_delayed_work_sync(&cgroup->psi.avgs_work); + free_percpu(cgroup->psi.pcpu); + /* All triggers must be removed by now */ + WARN_ONCE(cgroup->psi.poll_states, "psi: trigger leak\n"); +} + +/** + * cgroup_move_task - move task to a different cgroup + * @task: the task + * @to: the target css_set + * + * Move task to a new cgroup and safely migrate its associated stall + * state between the different groups. + * + * This function acquires the task's rq lock to lock out concurrent + * changes to the task's scheduling state and - in case the task is + * running - concurrent changes to its stall state. + */ +void cgroup_move_task(struct task_struct *task, struct css_set *to) +{ + unsigned int task_flags = 0; + struct rq_flags rf; + struct rq *rq; + + if (static_branch_likely(&psi_disabled)) { + /* + * Lame to do this here, but the scheduler cannot be locked + * from the outside, so we move cgroups from inside sched/. + */ + rcu_assign_pointer(task->cgroups, to); + return; + } + + rq = task_rq_lock(task, &rf); + + if (task_on_rq_queued(task)) + task_flags = TSK_RUNNING; + else if (task->in_iowait) + task_flags = TSK_IOWAIT; + + if (task->flags & PF_MEMSTALL) + task_flags |= TSK_MEMSTALL; + + if (task_flags) + psi_task_change(task, task_flags, 0); + + /* See comment above */ + rcu_assign_pointer(task->cgroups, to); + + if (task_flags) + psi_task_change(task, 0, task_flags); + + task_rq_unlock(rq, task, &rf); +} +#endif /* CONFIG_CGROUPS */ + +int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) +{ + int full; + u64 now; + + if (static_branch_likely(&psi_disabled)) + return -EOPNOTSUPP; + + /* Update averages before reporting them */ + mutex_lock(&group->avgs_lock); + now = sched_clock(); + collect_percpu_times(group, PSI_AVGS, NULL); + if (now >= group->avg_next_update) + group->avg_next_update = update_averages(group, now); + mutex_unlock(&group->avgs_lock); + + for (full = 0; full < 2 - (res == PSI_CPU); full++) { + unsigned long avg[3]; + u64 total; + int w; + + for (w = 0; w < 3; w++) + avg[w] = group->avg[res * 2 + full][w]; + total = div_u64(group->total[PSI_AVGS][res * 2 + full], + NSEC_PER_USEC); + + seq_printf(m, "%s avg10=%lu.%02lu avg60=%lu.%02lu avg300=%lu.%02lu total=%llu\n", + full ? "full" : "some", + LOAD_INT(avg[0]), LOAD_FRAC(avg[0]), + LOAD_INT(avg[1]), LOAD_FRAC(avg[1]), + LOAD_INT(avg[2]), LOAD_FRAC(avg[2]), + total); + } + + return 0; +} + +static int psi_io_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_IO); +} + +static int psi_memory_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_MEM); +} + +static int psi_cpu_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_CPU); +} + +static int psi_io_open(struct inode *inode, struct file *file) +{ + return single_open(file, psi_io_show, NULL); +} + +static int psi_memory_open(struct inode *inode, struct file *file) +{ + return single_open(file, psi_memory_show, NULL); +} + +static int psi_cpu_open(struct inode *inode, struct file *file) +{ + return single_open(file, psi_cpu_show, NULL); +} + +struct psi_trigger *psi_trigger_create(struct psi_group *group, + char *buf, size_t nbytes, enum psi_res res) +{ + struct psi_trigger *t; + enum psi_states state; + u32 threshold_us; + u32 window_us; + + if (static_branch_likely(&psi_disabled)) + return ERR_PTR(-EOPNOTSUPP); + + if (sscanf(buf, "some %u %u", &threshold_us, &window_us) == 2) + state = PSI_IO_SOME + res * 2; + else if (sscanf(buf, "full %u %u", &threshold_us, &window_us) == 2) + state = PSI_IO_FULL + res * 2; + else + return ERR_PTR(-EINVAL); + + if (state >= PSI_NONIDLE) + return ERR_PTR(-EINVAL); + + if (window_us < WINDOW_MIN_US || + window_us > WINDOW_MAX_US) + return ERR_PTR(-EINVAL); + + /* Check threshold */ + if (threshold_us == 0 || threshold_us > window_us) + return ERR_PTR(-EINVAL); + + t = kmalloc(sizeof(*t), GFP_KERNEL); + if (!t) + return ERR_PTR(-ENOMEM); + + t->group = group; + t->state = state; + t->threshold = threshold_us * NSEC_PER_USEC; + t->win.size = window_us * NSEC_PER_USEC; + window_reset(&t->win, 0, 0, 0); + + t->event = 0; + t->last_event_time = 0; + init_waitqueue_head(&t->event_wait); + kref_init(&t->refcount); + + mutex_lock(&group->trigger_lock); + + if (!rcu_access_pointer(group->poll_kworker)) { + struct sched_param param = { + .sched_priority = MAX_RT_PRIO - 1, + }; + struct kthread_worker *kworker; + + kworker = kthread_create_worker(0, "psimon"); + if (IS_ERR(kworker)) { + kfree(t); + mutex_unlock(&group->trigger_lock); + return ERR_CAST(kworker); + } + sched_setscheduler(kworker->task, SCHED_FIFO, ¶m); + kthread_init_delayed_work(&group->poll_work, + psi_poll_work); + rcu_assign_pointer(group->poll_kworker, kworker); + } + + list_add(&t->node, &group->triggers); + group->poll_min_period = min(group->poll_min_period, + div_u64(t->win.size, UPDATES_PER_WINDOW)); + group->nr_triggers[t->state]++; + group->poll_states |= (1 << t->state); + + mutex_unlock(&group->trigger_lock); + + return t; +} + +static void psi_trigger_destroy(struct kref *ref) +{ + struct psi_trigger *t = container_of(ref, struct psi_trigger, refcount); + struct psi_group *group = t->group; + struct kthread_worker *kworker_to_destroy = NULL; + + if (static_branch_likely(&psi_disabled)) + return; + + /* + * Wakeup waiters to stop polling. Can happen if cgroup is deleted + * from under a polling process. + */ + wake_up_interruptible(&t->event_wait); + + mutex_lock(&group->trigger_lock); + + if (!list_empty(&t->node)) { + struct psi_trigger *tmp; + u64 period = ULLONG_MAX; + + list_del(&t->node); + group->nr_triggers[t->state]--; + if (!group->nr_triggers[t->state]) + group->poll_states &= ~(1 << t->state); + /* reset min update period for the remaining triggers */ + list_for_each_entry(tmp, &group->triggers, node) + period = min(period, div_u64(tmp->win.size, + UPDATES_PER_WINDOW)); + group->poll_min_period = period; + /* Destroy poll_kworker when the last trigger is destroyed */ + if (group->poll_states == 0) { + group->polling_until = 0; + kworker_to_destroy = rcu_dereference_protected( + group->poll_kworker, + lockdep_is_held(&group->trigger_lock)); + rcu_assign_pointer(group->poll_kworker, NULL); + } + } + + mutex_unlock(&group->trigger_lock); + + /* + * Wait for both *trigger_ptr from psi_trigger_replace and + * poll_kworker RCUs to complete their read-side critical sections + * before destroying the trigger and optionally the poll_kworker + */ + synchronize_rcu(); + /* + * Destroy the kworker after releasing trigger_lock to prevent a + * deadlock while waiting for psi_poll_work to acquire trigger_lock + */ + if (kworker_to_destroy) { + kthread_cancel_delayed_work_sync(&group->poll_work); + kthread_destroy_worker(kworker_to_destroy); + } + kfree(t); +} + +void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *new) +{ + struct psi_trigger *old = *trigger_ptr; + + if (static_branch_likely(&psi_disabled)) + return; + + rcu_assign_pointer(*trigger_ptr, new); + if (old) + kref_put(&old->refcount, psi_trigger_destroy); +} + +unsigned int psi_trigger_poll(void **trigger_ptr, struct file *file, + poll_table *wait) +{ + unsigned int ret = DEFAULT_POLLMASK; + struct psi_trigger *t; + + if (static_branch_likely(&psi_disabled)) + return DEFAULT_POLLMASK | POLLERR | POLLPRI; + + rcu_read_lock(); + + t = rcu_dereference(*(void __rcu __force **)trigger_ptr); + if (!t) { + rcu_read_unlock(); + return DEFAULT_POLLMASK | POLLERR | POLLPRI; + } + kref_get(&t->refcount); + + rcu_read_unlock(); + + poll_wait(file, &t->event_wait, wait); + + if (cmpxchg(&t->event, 1, 0) == 1) + ret |= POLLPRI; + + kref_put(&t->refcount, psi_trigger_destroy); + + return ret; +} + +static ssize_t psi_write(struct file *file, const char __user *user_buf, + size_t nbytes, enum psi_res res) +{ + char buf[32]; + size_t buf_size; + struct seq_file *seq; + struct psi_trigger *new; + + if (static_branch_likely(&psi_disabled)) + return -EOPNOTSUPP; + + if (!nbytes) + return -EINVAL; + + buf_size = min(nbytes, sizeof(buf)); + if (copy_from_user(buf, user_buf, buf_size)) + return -EFAULT; + + buf[buf_size - 1] = '\0'; + + new = psi_trigger_create(&psi_system, buf, nbytes, res); + if (IS_ERR(new)) + return PTR_ERR(new); + + seq = file->private_data; + /* Take seq->lock to protect seq->private from concurrent writes */ + mutex_lock(&seq->lock); + psi_trigger_replace(&seq->private, new); + mutex_unlock(&seq->lock); + + return nbytes; +} + +static ssize_t psi_io_write(struct file *file, const char __user *user_buf, + size_t nbytes, loff_t *ppos) +{ + return psi_write(file, user_buf, nbytes, PSI_IO); +} + +static ssize_t psi_memory_write(struct file *file, const char __user *user_buf, + size_t nbytes, loff_t *ppos) +{ + return psi_write(file, user_buf, nbytes, PSI_MEM); +} + +static ssize_t psi_cpu_write(struct file *file, const char __user *user_buf, + size_t nbytes, loff_t *ppos) +{ + return psi_write(file, user_buf, nbytes, PSI_CPU); +} + +static unsigned int psi_fop_poll(struct file *file, poll_table *wait) +{ + struct seq_file *seq = file->private_data; + + return psi_trigger_poll(&seq->private, file, wait); +} + +static int psi_fop_release(struct inode *inode, struct file *file) +{ + struct seq_file *seq = file->private_data; + + psi_trigger_replace(&seq->private, NULL); + return single_release(inode, file); +} + +static const struct file_operations psi_io_fops = { + .open = psi_io_open, + .read = seq_read, + .llseek = seq_lseek, + .write = psi_io_write, + .poll = psi_fop_poll, + .release = psi_fop_release, +}; + +static const struct file_operations psi_memory_fops = { + .open = psi_memory_open, + .read = seq_read, + .llseek = seq_lseek, + .write = psi_memory_write, + .poll = psi_fop_poll, + .release = psi_fop_release, +}; + +static const struct file_operations psi_cpu_fops = { + .open = psi_cpu_open, + .read = seq_read, + .llseek = seq_lseek, + .write = psi_cpu_write, + .poll = psi_fop_poll, + .release = psi_fop_release, +}; + +static int __init psi_proc_init(void) +{ + proc_mkdir("pressure", NULL); + proc_create("pressure/io", 0, NULL, &psi_io_fops); + proc_create("pressure/memory", 0, NULL, &psi_memory_fops); + proc_create("pressure/cpu", 0, NULL, &psi_cpu_fops); + return 0; +} +module_init(psi_proc_init); diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index cc7dd1aaf08e..8e062500987f 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -8,6 +8,9 @@ #include <linux/slab.h> #include <linux/irq_work.h> +#include "tune.h" + +#include "walt.h" int sched_rr_timeslice = RR_TIMESLICE; int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE; @@ -1324,10 +1327,13 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags) { struct sched_rt_entity *rt_se = &p->rt; + schedtune_enqueue_task(p, cpu_of(rq)); + if (flags & ENQUEUE_WAKEUP) rt_se->timeout = 0; enqueue_rt_entity(rt_se, flags); + walt_inc_cumulative_runnable_avg(rq, p); if (!task_current(rq, p) && p->nr_cpus_allowed > 1) enqueue_pushable_task(rq, p); @@ -1337,8 +1343,11 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags) { struct sched_rt_entity *rt_se = &p->rt; + schedtune_dequeue_task(p, cpu_of(rq)); + update_curr_rt(rq); dequeue_rt_entity(rt_se, flags); + walt_dec_cumulative_runnable_avg(rq, p); dequeue_pushable_task(rq, p); } @@ -1381,7 +1390,8 @@ static void yield_task_rt(struct rq *rq) static int find_lowest_rq(struct task_struct *task); static int -select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags) +select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags, + int sibling_count_hint) { struct task_struct *curr; struct rq *rq; @@ -1528,6 +1538,8 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq) return p; } +extern int update_rt_rq_load_avg(u64 now, int cpu, struct rt_rq *rt_rq, int running); + static struct task_struct * pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { @@ -1573,6 +1585,10 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) queue_push_tasks(rq); + if (p) + update_rt_rq_load_avg(rq_clock_task(rq), cpu_of(rq), rt_rq, + rq->curr->sched_class == &rt_sched_class); + return p; } @@ -1580,6 +1596,8 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) { update_curr_rt(rq); + update_rt_rq_load_avg(rq_clock_task(rq), cpu_of(rq), &rq->rt, 1); + /* * The previous task needs to be made eligible for pushing * if it is still active @@ -1847,7 +1865,9 @@ retry: } deactivate_task(rq, next_task, 0); + next_task->on_rq = TASK_ON_RQ_MIGRATING; set_task_cpu(next_task, lowest_rq->cpu); + next_task->on_rq = TASK_ON_RQ_QUEUED; activate_task(lowest_rq, next_task, 0); ret = 1; @@ -2119,7 +2139,9 @@ static void pull_rt_task(struct rq *this_rq) resched = true; deactivate_task(src_rq, p, 0); + p->on_rq = TASK_ON_RQ_MIGRATING; set_task_cpu(p, this_cpu); + p->on_rq = TASK_ON_RQ_QUEUED; activate_task(this_rq, p, 0); /* * We continue with the search, just in @@ -2299,6 +2321,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued) struct sched_rt_entity *rt_se = &p->rt; update_curr_rt(rq); + update_rt_rq_load_avg(rq_clock_task(rq), cpu_of(rq), &rq->rt, 1); watchdog(rq, p); diff --git a/kernel/sched/sched-pelt.h b/kernel/sched/sched-pelt.h index a26473674fb7..df89df6d7595 100644 --- a/kernel/sched/sched-pelt.h +++ b/kernel/sched/sched-pelt.h @@ -1,14 +1,61 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Generated by Documentation/scheduler/sched-pelt; do not modify. */ +#ifdef CONFIG_PELT_UTIL_HALFLIFE_32 static const u32 runnable_avg_yN_inv[] = { - 0xffffffff, 0xfa83b2da, 0xf5257d14, 0xefe4b99a, 0xeac0c6e6, 0xe5b906e6, - 0xe0ccdeeb, 0xdbfbb796, 0xd744fcc9, 0xd2a81d91, 0xce248c14, 0xc9b9bd85, - 0xc5672a10, 0xc12c4cc9, 0xbd08a39e, 0xb8fbaf46, 0xb504f333, 0xb123f581, - 0xad583ee9, 0xa9a15ab4, 0xa5fed6a9, 0xa2704302, 0x9ef5325f, 0x9b8d39b9, - 0x9837f050, 0x94f4efa8, 0x91c3d373, 0x8ea4398a, 0x8b95c1e3, 0x88980e80, - 0x85aac367, 0x82cd8698, + 0xffffffff,0xfa83b2da,0xf5257d14,0xefe4b99a, + 0xeac0c6e6,0xe5b906e6,0xe0ccdeeb,0xdbfbb796, + 0xd744fcc9,0xd2a81d91,0xce248c14,0xc9b9bd85, + 0xc5672a10,0xc12c4cc9,0xbd08a39e,0xb8fbaf46, + 0xb504f333,0xb123f581,0xad583ee9,0xa9a15ab4, + 0xa5fed6a9,0xa2704302,0x9ef5325f,0x9b8d39b9, + 0x9837f050,0x94f4efa8,0x91c3d373,0x8ea4398a, + 0x8b95c1e3,0x88980e80,0x85aac367,0x82cd8698, +}; + +static const u32 runnable_avg_yN_sum[] = { + 0, 1002, 1982, 2941, 3880, 4798, 5697, 6576, 7437, 8279, 9103, + 9909,10698,11470,12226,12966,13690,14398,15091,15769,16433,17082, + 17718,18340,18949,19545,20128,20698,21256,21802,22336,22859,23371, }; #define LOAD_AVG_PERIOD 32 #define LOAD_AVG_MAX 47742 +#define LOAD_AVG_MAX_N 345 + +#endif + +#ifdef CONFIG_PELT_UTIL_HALFLIFE_16 +static const u32 runnable_avg_yN_inv[] = { + 0xffffffff,0xf5257d14,0xeac0c6e6,0xe0ccdeeb, + 0xd744fcc9,0xce248c14,0xc5672a10,0xbd08a39e, + 0xb504f333,0xad583ee9,0xa5fed6a9,0x9ef5325f, + 0x9837f050,0x91c3d373,0x8b95c1e3,0x85aac367, +}; + +static const u32 runnable_avg_yN_sum[] = { + 0, 980, 1919, 2818, 3679, 4503, 5292, 6048, 6772, 7465, 8129, + 8764, 9373, 9956,10514,11048,11560, +}; + +#define LOAD_AVG_PERIOD 16 +#define LOAD_AVG_MAX 24130 +#define LOAD_AVG_MAX_N 172 + +#endif + +#ifdef CONFIG_PELT_UTIL_HALFLIFE_8 +static const u32 runnable_avg_yN_inv[] = { + 0xffffffff,0xeac0c6e6,0xd744fcc9,0xc5672a10, + 0xb504f333,0xa5fed6a9,0x9837f050,0x8b95c1e3, +}; + +static const u32 runnable_avg_yN_sum[] = { + 0, 939, 1800, 2589, 3313, 3977, 4585, 5143, 5655, +}; + +#define LOAD_AVG_PERIOD 8 +#define LOAD_AVG_MAX 12326 +#define LOAD_AVG_MAX_N 85 + +#endif diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 391d73a12ad7..7c415352c4b6 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -26,6 +26,7 @@ #include <linux/kernel_stat.h> #include <linux/binfmts.h> #include <linux/mutex.h> +#include <linux/psi.h> #include <linux/spinlock.h> #include <linux/stop_machine.h> #include <linux/irq_work.h> @@ -274,6 +275,7 @@ extern bool dl_cpu_busy(unsigned int cpu); #ifdef CONFIG_CGROUP_SCHED #include <linux/cgroup.h> +#include <linux/psi.h> struct cfs_rq; struct rt_rq; @@ -499,6 +501,9 @@ struct cfs_rq { u64 throttled_clock_task_time; int throttled, throttle_count; struct list_head throttled_list; +#ifdef CONFIG_SCHED_WALT + u64 cumulative_runnable_avg; +#endif /* CONFIG_SCHED_WALT */ #endif /* CONFIG_CFS_BANDWIDTH */ #endif /* CONFIG_FAIR_GROUP_SCHED */ }; @@ -531,6 +536,9 @@ struct rt_rq { unsigned long rt_nr_total; int overloaded; struct plist_head pushable_tasks; + + struct sched_avg avg; + #endif /* CONFIG_SMP */ int rt_queued; @@ -612,6 +620,12 @@ static inline bool sched_asym_prefer(int a, int b) return arch_asym_cpu_priority(a) > arch_asym_cpu_priority(b); } +struct max_cpu_capacity { + raw_spinlock_t lock; + unsigned long val; + int cpu; +}; + /* * We add the notion of a root-domain which will be used to define per-domain * variables. Each exclusive cpuset essentially defines an island domain by @@ -627,8 +641,12 @@ struct root_domain { cpumask_var_t span; cpumask_var_t online; - /* Indicate more than one runnable task for any CPU */ - bool overload; + /* + * Indicate pullable load on at least one CPU, e.g: + * - More than one runnable task + * - Running task is misfit + */ + int overload; /* * The bit corresponding to a CPU gets set here if such CPU has more @@ -659,13 +677,18 @@ struct root_domain { cpumask_var_t rto_mask; struct cpupri cpupri; - unsigned long max_cpu_capacity; + /* Maximum cpu capacity in the system. */ + struct max_cpu_capacity max_cpu_capacity; + + /* First cpu with maximum and minimum original capacity */ + int max_cap_orig_cpu, min_cap_orig_cpu; }; extern struct root_domain def_root_domain; extern struct mutex sched_domains_mutex; extern void init_defrootdomain(void); +extern void init_max_cpu_capacity(struct max_cpu_capacity *mcc); extern int sched_init_domains(const struct cpumask *cpu_map); extern void rq_attach_root(struct rq *rq, struct root_domain *rd); extern void sched_get_rd(struct root_domain *rd); @@ -701,6 +724,7 @@ struct rq { #ifdef CONFIG_NO_HZ_COMMON #ifdef CONFIG_SMP unsigned long last_load_update_tick; + unsigned long last_blocked_load_update_tick; #endif /* CONFIG_SMP */ unsigned long nohz_flags; #endif /* CONFIG_NO_HZ_COMMON */ @@ -750,6 +774,9 @@ struct rq { struct callback_head *balance_callback; unsigned char idle_balance; + + unsigned long misfit_task_load; + /* For active balancing */ int active_balance; int push_cpu; @@ -769,6 +796,20 @@ struct rq { u64 max_idle_balance_cost; #endif +#ifdef CONFIG_SCHED_WALT + u64 cumulative_runnable_avg; + u64 window_start; + u64 curr_runnable_sum; + u64 prev_runnable_sum; + u64 nt_curr_runnable_sum; + u64 nt_prev_runnable_sum; + u64 cur_irqload; + u64 avg_irqload; + u64 irqload_ts; + u64 cum_window_demand; +#endif /* CONFIG_SCHED_WALT */ + + #ifdef CONFIG_IRQ_TIME_ACCOUNTING u64 prev_irq_time; #endif @@ -816,6 +857,7 @@ struct rq { #ifdef CONFIG_CPU_IDLE /* Must be inspected within a rcu lock section */ struct cpuidle_state *idle_state; + int idle_state_idx; #endif }; @@ -850,6 +892,8 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); #define cpu_curr(cpu) (cpu_rq(cpu)->curr) #define raw_rq() raw_cpu_ptr(&runqueues) +extern void update_rq_clock(struct rq *rq); + static inline u64 __rq_clock_broken(struct rq *rq) { return READ_ONCE(rq->clock); @@ -961,6 +1005,98 @@ static inline void rq_repin_lock(struct rq *rq, struct rq_flags *rf) #endif } +struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf) + __acquires(rq->lock); + +struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) + __acquires(p->pi_lock) + __acquires(rq->lock); + +static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf) + __releases(rq->lock) +{ + rq_unpin_lock(rq, rf); + raw_spin_unlock(&rq->lock); +} + +static inline void +task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf) + __releases(rq->lock) + __releases(p->pi_lock) +{ + rq_unpin_lock(rq, rf); + raw_spin_unlock(&rq->lock); + raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags); +} + +static inline void +rq_lock_irqsave(struct rq *rq, struct rq_flags *rf) + __acquires(rq->lock) +{ + raw_spin_lock_irqsave(&rq->lock, rf->flags); + rq_pin_lock(rq, rf); +} + +static inline void +rq_lock_irq(struct rq *rq, struct rq_flags *rf) + __acquires(rq->lock) +{ + raw_spin_lock_irq(&rq->lock); + rq_pin_lock(rq, rf); +} + +static inline void +rq_lock(struct rq *rq, struct rq_flags *rf) + __acquires(rq->lock) +{ + raw_spin_lock(&rq->lock); + rq_pin_lock(rq, rf); +} + +static inline void +rq_relock(struct rq *rq, struct rq_flags *rf) + __acquires(rq->lock) +{ + raw_spin_lock(&rq->lock); + rq_repin_lock(rq, rf); +} + +static inline void +rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf) + __releases(rq->lock) +{ + rq_unpin_lock(rq, rf); + raw_spin_unlock_irqrestore(&rq->lock, rf->flags); +} + +static inline void +rq_unlock_irq(struct rq *rq, struct rq_flags *rf) + __releases(rq->lock) +{ + rq_unpin_lock(rq, rf); + raw_spin_unlock_irq(&rq->lock); +} + +static inline void +rq_unlock(struct rq *rq, struct rq_flags *rf) + __releases(rq->lock) +{ + rq_unpin_lock(rq, rf); + raw_spin_unlock(&rq->lock); +} + +static inline struct rq * +this_rq_lock_irq(struct rq_flags *rf) + __acquires(rq->lock) +{ + struct rq *rq; + + local_irq_disable(); + rq = this_rq(); + rq_lock(rq, rf); + return rq; +} + #ifdef CONFIG_NUMA enum numa_topology_type { NUMA_DIRECT, @@ -1071,6 +1207,9 @@ DECLARE_PER_CPU(int, sd_llc_id); DECLARE_PER_CPU(struct sched_domain_shared *, sd_llc_shared); DECLARE_PER_CPU(struct sched_domain *, sd_numa); DECLARE_PER_CPU(struct sched_domain *, sd_asym); +DECLARE_PER_CPU(struct sched_domain *, sd_ea); +DECLARE_PER_CPU(struct sched_domain *, sd_scs); +extern struct static_key_false sched_asym_cpucapacity; struct sched_group_capacity { atomic_t ref; @@ -1080,6 +1219,7 @@ struct sched_group_capacity { */ unsigned long capacity; unsigned long min_capacity; /* Min per-CPU capacity in group */ + unsigned long max_capacity; /* Max per-CPU capacity in group */ unsigned long next_update; int imbalance; /* XXX unrelated to capacity but shared group state */ @@ -1097,6 +1237,7 @@ struct sched_group { unsigned int group_weight; struct sched_group_capacity *sgc; int asym_prefer_cpu; /* cpu of highest priority in group */ + const struct sched_group_energy *sge; /* * The CPUs this group covers. @@ -1437,7 +1578,8 @@ struct sched_class { void (*put_prev_task) (struct rq *rq, struct task_struct *p); #ifdef CONFIG_SMP - int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags); + int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags, + int subling_count_hint); void (*migrate_task_rq)(struct task_struct *p); void (*task_woken) (struct rq *this_rq, struct task_struct *task); @@ -1524,6 +1666,17 @@ static inline struct cpuidle_state *idle_get_state(struct rq *rq) SCHED_WARN_ON(!rcu_read_lock_held()); return rq->idle_state; } + +static inline void idle_set_state_idx(struct rq *rq, int idle_state_idx) +{ + rq->idle_state_idx = idle_state_idx; +} + +static inline int idle_get_state_idx(struct rq *rq) +{ + WARN_ON(!rcu_read_lock_held()); + return rq->idle_state_idx; +} #else static inline void idle_set_state(struct rq *rq, struct cpuidle_state *idle_state) @@ -1534,6 +1687,15 @@ static inline struct cpuidle_state *idle_get_state(struct rq *rq) { return NULL; } + +static inline void idle_set_state_idx(struct rq *rq, int idle_state_idx) +{ +} + +static inline int idle_get_state_idx(struct rq *rq) +{ + return -1; +} #endif extern void schedule_idle(void); @@ -1603,8 +1765,8 @@ static inline void add_nr_running(struct rq *rq, unsigned count) if (prev_nr < 2 && rq->nr_running >= 2) { #ifdef CONFIG_SMP - if (!rq->rd->overload) - rq->rd->overload = true; + if (!READ_ONCE(rq->rd->overload)) + WRITE_ONCE(rq->rd->overload, 1); #endif } @@ -1625,8 +1787,6 @@ static inline void rq_last_tick_reset(struct rq *rq) #endif } -extern void update_rq_clock(struct rq *rq); - extern void activate_task(struct rq *rq, struct task_struct *p, int flags); extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags); @@ -1670,6 +1830,7 @@ static inline int hrtick_enabled(struct rq *rq) #ifdef CONFIG_SMP extern void sched_avg_update(struct rq *rq); +extern unsigned long sched_get_rt_rq_util(int cpu); #ifndef arch_scale_freq_capacity static __always_inline @@ -1679,6 +1840,14 @@ unsigned long arch_scale_freq_capacity(struct sched_domain *sd, int cpu) } #endif +#ifndef arch_scale_max_freq_capacity +static __always_inline +unsigned long arch_scale_max_freq_capacity(struct sched_domain *sd, int cpu) +{ + return SCHED_CAPACITY_SCALE; +} +#endif + #ifndef arch_scale_cpu_capacity static __always_inline unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu) @@ -1690,95 +1859,32 @@ unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu) } #endif -static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) -{ - rq->rt_avg += rt_delta * arch_scale_freq_capacity(NULL, cpu_of(rq)); - sched_avg_update(rq); -} -#else -static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { } -static inline void sched_avg_update(struct rq *rq) { } -#endif - -struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf) - __acquires(rq->lock); - -struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) - __acquires(p->pi_lock) - __acquires(rq->lock); - -static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf) - __releases(rq->lock) -{ - rq_unpin_lock(rq, rf); - raw_spin_unlock(&rq->lock); -} - -static inline void -task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf) - __releases(rq->lock) - __releases(p->pi_lock) -{ - rq_unpin_lock(rq, rf); - raw_spin_unlock(&rq->lock); - raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags); -} - -static inline void -rq_lock_irqsave(struct rq *rq, struct rq_flags *rf) - __acquires(rq->lock) -{ - raw_spin_lock_irqsave(&rq->lock, rf->flags); - rq_pin_lock(rq, rf); -} - -static inline void -rq_lock_irq(struct rq *rq, struct rq_flags *rf) - __acquires(rq->lock) +#ifdef CONFIG_SMP +static inline unsigned long capacity_of(int cpu) { - raw_spin_lock_irq(&rq->lock); - rq_pin_lock(rq, rf); + return cpu_rq(cpu)->cpu_capacity; } -static inline void -rq_lock(struct rq *rq, struct rq_flags *rf) - __acquires(rq->lock) +static inline unsigned long capacity_orig_of(int cpu) { - raw_spin_lock(&rq->lock); - rq_pin_lock(rq, rf); + return cpu_rq(cpu)->cpu_capacity_orig; } -static inline void -rq_relock(struct rq *rq, struct rq_flags *rf) - __acquires(rq->lock) -{ - raw_spin_lock(&rq->lock); - rq_repin_lock(rq, rf); -} +extern unsigned int sysctl_sched_use_walt_cpu_util; +extern unsigned int walt_ravg_window; +extern bool walt_disabled; -static inline void -rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf) - __releases(rq->lock) -{ - rq_unpin_lock(rq, rf); - raw_spin_unlock_irqrestore(&rq->lock, rf->flags); -} - -static inline void -rq_unlock_irq(struct rq *rq, struct rq_flags *rf) - __releases(rq->lock) -{ - rq_unpin_lock(rq, rf); - raw_spin_unlock_irq(&rq->lock); -} +#endif /* CONFIG_SMP */ -static inline void -rq_unlock(struct rq *rq, struct rq_flags *rf) - __releases(rq->lock) +static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { - rq_unpin_lock(rq, rf); - raw_spin_unlock(&rq->lock); + rq->rt_avg += rt_delta * arch_scale_freq_capacity(NULL, cpu_of(rq)); + sched_avg_update(rq); } +#else +static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { } +static inline void sched_avg_update(struct rq *rq) { } +#endif #ifdef CONFIG_SMP #ifdef CONFIG_PREEMPT @@ -1996,6 +2102,7 @@ extern void cfs_bandwidth_usage_dec(void); enum rq_nohz_flag_bits { NOHZ_TICK_STOPPED, NOHZ_BALANCE_KICK, + NOHZ_STATS_KICK }; #define nohz_flags(cpu) (&cpu_rq(cpu)->nohz_flags) @@ -2007,6 +2114,9 @@ static inline void nohz_balance_exit_idle(unsigned int cpu) { } #ifdef CONFIG_SMP + +extern void init_energy_aware_data(int cpu); + static inline void __dl_update(struct dl_bw *dl_b, s64 bw) { @@ -2100,6 +2210,17 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {} #endif /* CONFIG_CPU_FREQ */ +#ifdef CONFIG_SCHED_WALT + +static inline bool +walt_task_in_cum_window_demand(struct rq *rq, struct task_struct *p) +{ + return cpu_of(rq) == task_cpu(p) && + (p->on_rq || p->last_sleep_ts >= rq->window_start); +} + +#endif /* CONFIG_SCHED_WALT */ + #ifdef arch_scale_freq_capacity #ifndef arch_scale_freq_invariant #define arch_scale_freq_invariant() (true) diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index baf500d12b7c..5d30f4b7d344 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -55,6 +55,92 @@ rq_sched_info_depart(struct rq *rq, unsigned long long delta) #define schedstat_val_or_zero(var) 0 #endif /* CONFIG_SCHEDSTATS */ +#ifdef CONFIG_PSI +/* + * PSI tracks state that persists across sleeps, such as iowaits and + * memory stalls. As a result, it has to distinguish between sleeps, + * where a task's runnable state changes, and requeues, where a task + * and its state are being moved between CPUs and runqueues. + */ +static inline void psi_enqueue(struct task_struct *p, bool wakeup) +{ + int clear = 0, set = TSK_RUNNING; + + if (static_branch_likely(&psi_disabled)) + return; + + if (!wakeup || p->sched_psi_wake_requeue) { + if (p->flags & PF_MEMSTALL) + set |= TSK_MEMSTALL; + if (p->sched_psi_wake_requeue) + p->sched_psi_wake_requeue = 0; + } else { + if (p->in_iowait) + clear |= TSK_IOWAIT; + } + + psi_task_change(p, clear, set); +} + +static inline void psi_dequeue(struct task_struct *p, bool sleep) +{ + int clear = TSK_RUNNING, set = 0; + + if (static_branch_likely(&psi_disabled)) + return; + + if (!sleep) { + if (p->flags & PF_MEMSTALL) + clear |= TSK_MEMSTALL; + } else { + if (p->in_iowait) + set |= TSK_IOWAIT; + } + + psi_task_change(p, clear, set); +} + +static inline void psi_ttwu_dequeue(struct task_struct *p) +{ + if (static_branch_likely(&psi_disabled)) + return; + /* + * Is the task being migrated during a wakeup? Make sure to + * deregister its sleep-persistent psi states from the old + * queue, and let psi_enqueue() know it has to requeue. + */ + if (unlikely(p->in_iowait || (p->flags & PF_MEMSTALL))) { + struct rq_flags rf; + struct rq *rq; + int clear = 0; + + if (p->in_iowait) + clear |= TSK_IOWAIT; + if (p->flags & PF_MEMSTALL) + clear |= TSK_MEMSTALL; + + rq = __task_rq_lock(p, &rf); + psi_task_change(p, clear, 0); + p->sched_psi_wake_requeue = 1; + __task_rq_unlock(rq, &rf); + } +} + +static inline void psi_task_tick(struct rq *rq) +{ + if (static_branch_likely(&psi_disabled)) + return; + + if (unlikely(rq->curr->flags & PF_MEMSTALL)) + psi_memstall_tick(rq->curr, cpu_of(rq)); +} +#else /* CONFIG_PSI */ +static inline void psi_enqueue(struct task_struct *p, bool wakeup) {} +static inline void psi_dequeue(struct task_struct *p, bool sleep) {} +static inline void psi_ttwu_dequeue(struct task_struct *p) {} +static inline void psi_task_tick(struct rq *rq) {} +#endif /* CONFIG_PSI */ + #ifdef CONFIG_SCHED_INFO static inline void sched_info_reset_dequeued(struct task_struct *t) { diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c index 45caf90b24cd..7ca03e528c45 100644 --- a/kernel/sched/stop_task.c +++ b/kernel/sched/stop_task.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include "sched.h" +#include "walt.h" /* * stop-task scheduling class. @@ -12,7 +13,8 @@ #ifdef CONFIG_SMP static int -select_task_rq_stop(struct task_struct *p, int cpu, int sd_flag, int flags) +select_task_rq_stop(struct task_struct *p, int cpu, int sd_flag, int flags, + int sibling_count_hint) { return task_cpu(p); /* stop tasks as never migrate */ } @@ -43,12 +45,14 @@ static void enqueue_task_stop(struct rq *rq, struct task_struct *p, int flags) { add_nr_running(rq, 1); + walt_inc_cumulative_runnable_avg(rq, p); } static void dequeue_task_stop(struct rq *rq, struct task_struct *p, int flags) { sub_nr_running(rq, 1); + walt_dec_cumulative_runnable_avg(rq, p); } static void yield_task_stop(struct rq *rq) diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 867d173dab48..c5de38dc192f 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -39,9 +39,6 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, if (!(sd->flags & SD_LOAD_BALANCE)) { printk("does not load-balance\n"); - if (sd->parent) - printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain" - " has parent"); return -1; } @@ -154,8 +151,12 @@ static inline bool sched_debug(void) static int sd_degenerate(struct sched_domain *sd) { - if (cpumask_weight(sched_domain_span(sd)) == 1) - return 1; + if (cpumask_weight(sched_domain_span(sd)) == 1) { + if (sd->groups->sge) + sd->flags &= ~SD_LOAD_BALANCE; + else + return 1; + } /* Following flags need at least 2 groups */ if (sd->flags & (SD_LOAD_BALANCE | @@ -165,7 +166,8 @@ static int sd_degenerate(struct sched_domain *sd) SD_SHARE_CPUCAPACITY | SD_ASYM_CPUCAPACITY | SD_SHARE_PKG_RESOURCES | - SD_SHARE_POWERDOMAIN)) { + SD_SHARE_POWERDOMAIN | + SD_SHARE_CAP_STATES)) { if (sd->groups != sd->groups->next) return 0; } @@ -198,7 +200,12 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES | SD_PREFER_SIBLING | - SD_SHARE_POWERDOMAIN); + SD_SHARE_POWERDOMAIN | + SD_SHARE_CAP_STATES); + if (parent->groups->sge) { + parent->flags &= ~SD_LOAD_BALANCE; + return 0; + } if (nr_node_ids == 1) pflags &= ~SD_SERIALIZE; } @@ -294,6 +301,11 @@ static int init_rootdomain(struct root_domain *rd) if (cpupri_init(&rd->cpupri) != 0) goto free_cpudl; + + rd->max_cap_orig_cpu = rd->min_cap_orig_cpu = -1; + + init_max_cpu_capacity(&rd->max_cpu_capacity); + return 0; free_cpudl: @@ -405,11 +417,15 @@ DEFINE_PER_CPU(int, sd_llc_id); DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared); DEFINE_PER_CPU(struct sched_domain *, sd_numa); DEFINE_PER_CPU(struct sched_domain *, sd_asym); +DEFINE_PER_CPU(struct sched_domain *, sd_ea); +DEFINE_PER_CPU(struct sched_domain *, sd_scs); +DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity); static void update_top_cache_domain(int cpu) { struct sched_domain_shared *sds = NULL; struct sched_domain *sd; + struct sched_domain *ea_sd = NULL; int id = cpu; int size = 1; @@ -430,6 +446,32 @@ static void update_top_cache_domain(int cpu) sd = highest_flag_domain(cpu, SD_ASYM_PACKING); rcu_assign_pointer(per_cpu(sd_asym, cpu), sd); + + for_each_domain(cpu, sd) { + if (sd->groups->sge) + ea_sd = sd; + else + break; + } + rcu_assign_pointer(per_cpu(sd_ea, cpu), ea_sd); + + sd = highest_flag_domain(cpu, SD_SHARE_CAP_STATES); + rcu_assign_pointer(per_cpu(sd_scs, cpu), sd); +} + +static void update_asym_cpucapacity(int cpu) +{ + int enable = false; + + rcu_read_lock(); + if (lowest_flag_domain(cpu, SD_ASYM_CPUCAPACITY)) + enable = true; + rcu_read_unlock(); + + if (enable) { + /* This expects to be hotplug-safe */ + static_branch_enable_cpuslocked(&sched_asym_cpucapacity); + } } /* @@ -714,6 +756,7 @@ static void init_overlap_sched_group(struct sched_domain *sd, sg_span = sched_group_span(sg); sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span); sg->sgc->min_capacity = SCHED_CAPACITY_SCALE; + sg->sgc->max_capacity = SCHED_CAPACITY_SCALE; } static int @@ -873,6 +916,7 @@ static struct sched_group *get_group(int cpu, struct sd_data *sdd) sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sched_group_span(sg)); sg->sgc->min_capacity = SCHED_CAPACITY_SCALE; + sg->sgc->max_capacity = SCHED_CAPACITY_SCALE; return sg; } @@ -962,6 +1006,108 @@ next: update_group_capacity(sd, cpu); } +#define cap_state_power(s,i) (s->cap_states[i].power) +#define cap_state_cap(s,i) (s->cap_states[i].cap) +#define idle_state_power(s,i) (s->idle_states[i].power) + +static inline int sched_group_energy_equal(const struct sched_group_energy *a, + const struct sched_group_energy *b) +{ + int i; + + /* check pointers first */ + if (a == b) + return true; + + /* check contents are equivalent */ + if (a->nr_cap_states != b->nr_cap_states) + return false; + if (a->nr_idle_states != b->nr_idle_states) + return false; + for (i=0;i<a->nr_cap_states;i++){ + if (cap_state_power(a,i) != + cap_state_power(b,i)) + return false; + if (cap_state_cap(a,i) != + cap_state_cap(b,i)) + return false; + } + for (i=0;i<a->nr_idle_states;i++){ + if (idle_state_power(a,i) != + idle_state_power(b,i)) + return false; + } + + return true; +} + +#define energy_eff(e, n) \ + ((e->cap_states[n].cap << SCHED_CAPACITY_SHIFT)/e->cap_states[n].power) + +static void init_sched_groups_energy(int cpu, struct sched_domain *sd, + sched_domain_energy_f fn) +{ + struct sched_group *sg = sd->groups; + const struct sched_group_energy *sge; + int i; + + if (!(fn && fn(cpu))) + return; + + if (cpu != group_balance_cpu(sg)) + return; + + if (sd->flags & SD_OVERLAP) { + pr_err("BUG: EAS does not support overlapping sd spans\n"); +#ifdef CONFIG_SCHED_DEBUG + pr_err(" the %s domain has SD_OVERLAP set\n", sd->name); +#endif + return; + } + + if (sd->child && !sd->child->groups->sge) { + pr_err("BUG: EAS setup borken for CPU%d\n", cpu); +#ifdef CONFIG_SCHED_DEBUG + pr_err(" energy data on %s but not on %s domain\n", + sd->name, sd->child->name); +#endif + return; + } + + sge = fn(cpu); + + /* + * Check that the per-cpu provided sd energy data is consistent for all + * cpus within the mask. + */ + if (cpumask_weight(sched_group_span(sg)) > 1) { + struct cpumask mask; + + cpumask_xor(&mask, sched_group_span(sg), get_cpu_mask(cpu)); + + for_each_cpu(i, &mask) + BUG_ON(!sched_group_energy_equal(sge,fn(i))); + } + + /* Check that energy efficiency (capacity/power) is monotonically + * decreasing in the capacity state vector with higher indexes + */ + for (i = 0; i < (sge->nr_cap_states - 1); i++) { + if (energy_eff(sge, i) > energy_eff(sge, i+1)) + continue; +#ifdef CONFIG_SCHED_DEBUG + pr_warn("WARN: cpu=%d, domain=%s: incr. energy eff %lu[%d]->%lu[%d]\n", + cpu, sd->name, energy_eff(sge, i), i, + energy_eff(sge, i+1), i+1); +#else + pr_warn("WARN: cpu=%d: incr. energy eff %lu[%d]->%lu[%d]\n", + cpu, energy_eff(sge, i), i, energy_eff(sge, i+1), i+1); +#endif + } + + sd->groups->sge = fn(cpu); +} + /* * Initializers for schedule domains * Non-inlined to reduce accumulated stack pressure in build_sched_domains() @@ -1081,6 +1227,7 @@ static int sched_domains_curr_level; * SD_NUMA - describes NUMA topologies * SD_SHARE_POWERDOMAIN - describes shared power domain * SD_ASYM_CPUCAPACITY - describes mixed capacity topologies + * SD_SHARE_CAP_STATES - describes shared capacity states * * Odd one out, which beside describing the topology has a quirk also * prescribes the desired behaviour that goes along with it: @@ -1093,7 +1240,8 @@ static int sched_domains_curr_level; SD_NUMA | \ SD_ASYM_PACKING | \ SD_ASYM_CPUCAPACITY | \ - SD_SHARE_POWERDOMAIN) + SD_SHARE_POWERDOMAIN | \ + SD_SHARE_CAP_STATES) static struct sched_domain * sd_init(struct sched_domain_topology_level *tl, @@ -1141,7 +1289,7 @@ sd_init(struct sched_domain_topology_level *tl, | 0*SD_SHARE_CPUCAPACITY | 0*SD_SHARE_PKG_RESOURCES | 0*SD_SERIALIZE - | 0*SD_PREFER_SIBLING + | 1*SD_PREFER_SIBLING | 0*SD_NUMA | sd_flags , @@ -1161,18 +1309,43 @@ sd_init(struct sched_domain_topology_level *tl, sd_id = cpumask_first(sched_domain_span(sd)); /* + * Check if cpu_map eclipses cpu capacity asymmetry. + */ + + if (sd->flags & SD_ASYM_CPUCAPACITY) { + long capacity = arch_scale_cpu_capacity(NULL, sd_id); + bool disable = true; + int i; + + for_each_cpu(i, sched_domain_span(sd)) { + if (capacity != arch_scale_cpu_capacity(NULL, i)) { + disable = false; + break; + } + } + + if (disable) + sd->flags &= ~SD_ASYM_CPUCAPACITY; + } + + /* * Convert topological properties into behaviour. */ if (sd->flags & SD_ASYM_CPUCAPACITY) { struct sched_domain *t = sd; + /* + * Don't attempt to spread across cpus of different capacities. + */ + if (sd->child) + sd->child->flags &= ~SD_PREFER_SIBLING; + for_each_lower_domain(t) t->flags |= SD_BALANCE_WAKE; } if (sd->flags & SD_SHARE_CPUCAPACITY) { - sd->flags |= SD_PREFER_SIBLING; sd->imbalance_pct = 110; sd->smt_gain = 1178; /* ~15% */ @@ -1187,6 +1360,7 @@ sd_init(struct sched_domain_topology_level *tl, sd->busy_idx = 3; sd->idle_idx = 2; + sd->flags &= ~SD_PREFER_SIBLING; sd->flags |= SD_SERIALIZE; if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) { sd->flags &= ~(SD_BALANCE_EXEC | @@ -1196,21 +1370,16 @@ sd_init(struct sched_domain_topology_level *tl, #endif } else { - sd->flags |= SD_PREFER_SIBLING; sd->cache_nice_tries = 1; sd->busy_idx = 2; sd->idle_idx = 1; } - /* - * For all levels sharing cache; connect a sched_domain_shared - * instance. - */ - if (sd->flags & SD_SHARE_PKG_RESOURCES) { - sd->shared = *per_cpu_ptr(sdd->sds, sd_id); - atomic_inc(&sd->shared->ref); + sd->shared = *per_cpu_ptr(sdd->sds, sd_id); + atomic_inc(&sd->shared->ref); + + if (sd->flags & SD_SHARE_PKG_RESOURCES) atomic_set(&sd->shared->nr_busy_cpus, sd_weight); - } sd->private = sdd; @@ -1651,7 +1820,6 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att enum s_alloc alloc_state; struct sched_domain *sd; struct s_data d; - struct rq *rq = NULL; int i, ret = -ENOMEM; alloc_state = __visit_domain_allocation_hell(&d, cpu_map); @@ -1669,8 +1837,6 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att *per_cpu_ptr(d.sd, i) = sd; if (tl->flags & SDTL_OVERLAP) sd->flags |= SD_OVERLAP; - if (cpumask_equal(cpu_map, sched_domain_span(sd))) - break; } } @@ -1690,10 +1856,13 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att /* Calculate CPU capacity for physical packages and nodes */ for (i = nr_cpumask_bits-1; i >= 0; i--) { + struct sched_domain_topology_level *tl = sched_domain_topology; + if (!cpumask_test_cpu(i, cpu_map)) continue; - for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { + for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent, tl++) { + init_sched_groups_energy(i, sd, tl->energy); claim_allocations(i, sd); init_sched_groups_capacity(i, sd); } @@ -1702,21 +1871,25 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att /* Attach the domains */ rcu_read_lock(); for_each_cpu(i, cpu_map) { - rq = cpu_rq(i); + int max_cpu = READ_ONCE(d.rd->max_cap_orig_cpu); + int min_cpu = READ_ONCE(d.rd->min_cap_orig_cpu); + sd = *per_cpu_ptr(d.sd, i); - /* Use READ_ONCE()/WRITE_ONCE() to avoid load/store tearing: */ - if (rq->cpu_capacity_orig > READ_ONCE(d.rd->max_cpu_capacity)) - WRITE_ONCE(d.rd->max_cpu_capacity, rq->cpu_capacity_orig); + if ((max_cpu < 0) || (cpu_rq(i)->cpu_capacity_orig > + cpu_rq(max_cpu)->cpu_capacity_orig)) + WRITE_ONCE(d.rd->max_cap_orig_cpu, i); + + if ((min_cpu < 0) || (cpu_rq(i)->cpu_capacity_orig < + cpu_rq(min_cpu)->cpu_capacity_orig)) + WRITE_ONCE(d.rd->min_cap_orig_cpu, i); cpu_attach_domain(sd, d.rd, i); } rcu_read_unlock(); - if (rq && sched_debug_enabled) { - pr_info("span: %*pbl (max cpu_capacity = %lu)\n", - cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity); - } + if (!cpumask_empty(cpu_map)) + update_asym_cpucapacity(cpumask_first(cpu_map)); ret = 0; error: @@ -1928,4 +2101,3 @@ match2: mutex_unlock(&sched_domains_mutex); } - diff --git a/kernel/sched/tune.c b/kernel/sched/tune.c new file mode 100644 index 000000000000..74a45606dc8c --- /dev/null +++ b/kernel/sched/tune.c @@ -0,0 +1,621 @@ +#include <linux/cgroup.h> +#include <linux/err.h> +#include <linux/kernel.h> +#include <linux/percpu.h> +#include <linux/printk.h> +#include <linux/rcupdate.h> +#include <linux/slab.h> + +#include <trace/events/sched.h> + +#include "sched.h" +#include "tune.h" + +bool schedtune_initialized = false; +extern struct reciprocal_value schedtune_spc_rdiv; + +/* We hold schedtune boost in effect for at least this long */ +#define SCHEDTUNE_BOOST_HOLD_NS 50000000ULL + +/* + * EAS scheduler tunables for task groups. + */ + +/* SchdTune tunables for a group of tasks */ +struct schedtune { + /* SchedTune CGroup subsystem */ + struct cgroup_subsys_state css; + + /* Boost group allocated ID */ + int idx; + + /* Boost value for tasks on that SchedTune CGroup */ + int boost; + + /* Hint to bias scheduling of tasks on that SchedTune CGroup + * towards idle CPUs */ + int prefer_idle; +}; + +static inline struct schedtune *css_st(struct cgroup_subsys_state *css) +{ + return css ? container_of(css, struct schedtune, css) : NULL; +} + +static inline struct schedtune *task_schedtune(struct task_struct *tsk) +{ + return css_st(task_css(tsk, schedtune_cgrp_id)); +} + +static inline struct schedtune *parent_st(struct schedtune *st) +{ + return css_st(st->css.parent); +} + +/* + * SchedTune root control group + * The root control group is used to defined a system-wide boosting tuning, + * which is applied to all tasks in the system. + * Task specific boost tuning could be specified by creating and + * configuring a child control group under the root one. + * By default, system-wide boosting is disabled, i.e. no boosting is applied + * to tasks which are not into a child control group. + */ +static struct schedtune +root_schedtune = { + .boost = 0, + .prefer_idle = 0, +}; + +/* + * Maximum number of boost groups to support + * When per-task boosting is used we still allow only limited number of + * boost groups for two main reasons: + * 1. on a real system we usually have only few classes of workloads which + * make sense to boost with different values (e.g. background vs foreground + * tasks, interactive vs low-priority tasks) + * 2. a limited number allows for a simpler and more memory/time efficient + * implementation especially for the computation of the per-CPU boost + * value + */ +#define BOOSTGROUPS_COUNT 5 + +/* Array of configured boostgroups */ +static struct schedtune *allocated_group[BOOSTGROUPS_COUNT] = { + &root_schedtune, + NULL, +}; + +/* SchedTune boost groups + * Keep track of all the boost groups which impact on CPU, for example when a + * CPU has two RUNNABLE tasks belonging to two different boost groups and thus + * likely with different boost values. + * Since on each system we expect only a limited number of boost groups, here + * we use a simple array to keep track of the metrics required to compute the + * maximum per-CPU boosting value. + */ +struct boost_groups { + /* Maximum boost value for all RUNNABLE tasks on a CPU */ + bool idle; + int boost_max; + u64 boost_ts; + struct { + /* The boost for tasks on that boost group */ + int boost; + /* Count of RUNNABLE tasks on that boost group */ + unsigned tasks; + /* Timestamp of boost activation */ + u64 ts; + } group[BOOSTGROUPS_COUNT]; + /* CPU's boost group locking */ + raw_spinlock_t lock; +}; + +/* Boost groups affecting each CPU in the system */ +DEFINE_PER_CPU(struct boost_groups, cpu_boost_groups); + +static inline bool schedtune_boost_timeout(u64 now, u64 ts) +{ + return ((now - ts) > SCHEDTUNE_BOOST_HOLD_NS); +} + +static inline bool +schedtune_boost_group_active(int idx, struct boost_groups* bg, u64 now) +{ + if (bg->group[idx].tasks) + return true; + + return !schedtune_boost_timeout(now, bg->group[idx].ts); +} + +static void +schedtune_cpu_update(int cpu, u64 now) +{ + struct boost_groups *bg = &per_cpu(cpu_boost_groups, cpu); + int boost_max; + u64 boost_ts; + int idx; + + /* The root boost group is always active */ + boost_max = bg->group[0].boost; + boost_ts = now; + for (idx = 1; idx < BOOSTGROUPS_COUNT; ++idx) { + /* + * A boost group affects a CPU only if it has + * RUNNABLE tasks on that CPU or it has hold + * in effect from a previous task. + */ + if (!schedtune_boost_group_active(idx, bg, now)) + continue; + + /* This boost group is active */ + if (boost_max > bg->group[idx].boost) + continue; + + boost_max = bg->group[idx].boost; + boost_ts = bg->group[idx].ts; + } + /* Ensures boost_max is non-negative when all cgroup boost values + * are neagtive. Avoids under-accounting of cpu capacity which may cause + * task stacking and frequency spikes.*/ + boost_max = max(boost_max, 0); + bg->boost_max = boost_max; + bg->boost_ts = boost_ts; +} + +static int +schedtune_boostgroup_update(int idx, int boost) +{ + struct boost_groups *bg; + int cur_boost_max; + int old_boost; + int cpu; + u64 now; + + /* Update per CPU boost groups */ + for_each_possible_cpu(cpu) { + bg = &per_cpu(cpu_boost_groups, cpu); + + /* + * Keep track of current boost values to compute the per CPU + * maximum only when it has been affected by the new value of + * the updated boost group + */ + cur_boost_max = bg->boost_max; + old_boost = bg->group[idx].boost; + + /* Update the boost value of this boost group */ + bg->group[idx].boost = boost; + + /* Check if this update increase current max */ + now = sched_clock_cpu(cpu); + if (boost > cur_boost_max && + schedtune_boost_group_active(idx, bg, now)) { + bg->boost_max = boost; + bg->boost_ts = bg->group[idx].ts; + + trace_sched_tune_boostgroup_update(cpu, 1, bg->boost_max); + continue; + } + + /* Check if this update has decreased current max */ + if (cur_boost_max == old_boost && old_boost > boost) { + schedtune_cpu_update(cpu, now); + trace_sched_tune_boostgroup_update(cpu, -1, bg->boost_max); + continue; + } + + trace_sched_tune_boostgroup_update(cpu, 0, bg->boost_max); + } + + return 0; +} + +#define ENQUEUE_TASK 1 +#define DEQUEUE_TASK -1 + +static inline bool +schedtune_update_timestamp(struct task_struct *p) +{ + if (sched_feat(SCHEDTUNE_BOOST_HOLD_ALL)) + return true; + + return task_has_rt_policy(p); +} + +static inline void +schedtune_tasks_update(struct task_struct *p, int cpu, int idx, int task_count) +{ + struct boost_groups *bg = &per_cpu(cpu_boost_groups, cpu); + int tasks = bg->group[idx].tasks + task_count; + + /* Update boosted tasks count while avoiding to make it negative */ + bg->group[idx].tasks = max(0, tasks); + + /* Update timeout on enqueue */ + if (task_count > 0) { + u64 now = sched_clock_cpu(cpu); + + if (schedtune_update_timestamp(p)) + bg->group[idx].ts = now; + + /* Boost group activation or deactivation on that RQ */ + if (bg->group[idx].tasks == 1) + schedtune_cpu_update(cpu, now); + } + + trace_sched_tune_tasks_update(p, cpu, tasks, idx, + bg->group[idx].boost, bg->boost_max, + bg->group[idx].ts); +} + +/* + * NOTE: This function must be called while holding the lock on the CPU RQ + */ +void schedtune_enqueue_task(struct task_struct *p, int cpu) +{ + struct boost_groups *bg = &per_cpu(cpu_boost_groups, cpu); + unsigned long irq_flags; + struct schedtune *st; + int idx; + + if (unlikely(!schedtune_initialized)) + return; + + /* + * Boost group accouting is protected by a per-cpu lock and requires + * interrupt to be disabled to avoid race conditions for example on + * do_exit()::cgroup_exit() and task migration. + */ + raw_spin_lock_irqsave(&bg->lock, irq_flags); + rcu_read_lock(); + + st = task_schedtune(p); + idx = st->idx; + + schedtune_tasks_update(p, cpu, idx, ENQUEUE_TASK); + + rcu_read_unlock(); + raw_spin_unlock_irqrestore(&bg->lock, irq_flags); +} + +int schedtune_can_attach(struct cgroup_taskset *tset) +{ + struct task_struct *task; + struct cgroup_subsys_state *css; + struct boost_groups *bg; + struct rq_flags rq_flags; + unsigned int cpu; + struct rq *rq; + int src_bg; /* Source boost group index */ + int dst_bg; /* Destination boost group index */ + int tasks; + u64 now; + + if (unlikely(!schedtune_initialized)) + return 0; + + + cgroup_taskset_for_each(task, css, tset) { + + /* + * Lock the CPU's RQ the task is enqueued to avoid race + * conditions with migration code while the task is being + * accounted + */ + rq = task_rq_lock(task, &rq_flags); + + if (!task->on_rq) { + task_rq_unlock(rq, task, &rq_flags); + continue; + } + + /* + * Boost group accouting is protected by a per-cpu lock and requires + * interrupt to be disabled to avoid race conditions on... + */ + cpu = cpu_of(rq); + bg = &per_cpu(cpu_boost_groups, cpu); + raw_spin_lock(&bg->lock); + + dst_bg = css_st(css)->idx; + src_bg = task_schedtune(task)->idx; + + /* + * Current task is not changing boostgroup, which can + * happen when the new hierarchy is in use. + */ + if (unlikely(dst_bg == src_bg)) { + raw_spin_unlock(&bg->lock); + task_rq_unlock(rq, task, &rq_flags); + continue; + } + + /* + * This is the case of a RUNNABLE task which is switching its + * current boost group. + */ + + /* Move task from src to dst boost group */ + tasks = bg->group[src_bg].tasks - 1; + bg->group[src_bg].tasks = max(0, tasks); + bg->group[dst_bg].tasks += 1; + + /* Update boost hold start for this group */ + now = sched_clock_cpu(cpu); + bg->group[dst_bg].ts = now; + + /* Force boost group re-evaluation at next boost check */ + bg->boost_ts = now - SCHEDTUNE_BOOST_HOLD_NS; + + raw_spin_unlock(&bg->lock); + task_rq_unlock(rq, task, &rq_flags); + } + + return 0; +} + +void schedtune_cancel_attach(struct cgroup_taskset *tset) +{ + /* This can happen only if SchedTune controller is mounted with + * other hierarchies ane one of them fails. Since usually SchedTune is + * mouted on its own hierarcy, for the time being we do not implement + * a proper rollback mechanism */ + WARN(1, "SchedTune cancel attach not implemented"); +} + +/* + * NOTE: This function must be called while holding the lock on the CPU RQ + */ +void schedtune_dequeue_task(struct task_struct *p, int cpu) +{ + struct boost_groups *bg = &per_cpu(cpu_boost_groups, cpu); + unsigned long irq_flags; + struct schedtune *st; + int idx; + + if (unlikely(!schedtune_initialized)) + return; + + /* + * Boost group accouting is protected by a per-cpu lock and requires + * interrupt to be disabled to avoid race conditions on... + */ + raw_spin_lock_irqsave(&bg->lock, irq_flags); + rcu_read_lock(); + + st = task_schedtune(p); + idx = st->idx; + + schedtune_tasks_update(p, cpu, idx, DEQUEUE_TASK); + + rcu_read_unlock(); + raw_spin_unlock_irqrestore(&bg->lock, irq_flags); +} + +int schedtune_cpu_boost(int cpu) +{ + struct boost_groups *bg; + u64 now; + + bg = &per_cpu(cpu_boost_groups, cpu); + now = sched_clock_cpu(cpu); + + /* Check to see if we have a hold in effect */ + if (schedtune_boost_timeout(now, bg->boost_ts)) + schedtune_cpu_update(cpu, now); + + return bg->boost_max; +} + +int schedtune_task_boost(struct task_struct *p) +{ + struct schedtune *st; + int task_boost; + + if (unlikely(!schedtune_initialized)) + return 0; + + /* Get task boost value */ + rcu_read_lock(); + st = task_schedtune(p); + task_boost = st->boost; + rcu_read_unlock(); + + return task_boost; +} + +int schedtune_prefer_idle(struct task_struct *p) +{ + struct schedtune *st; + int prefer_idle; + + if (unlikely(!schedtune_initialized)) + return 0; + + /* Get prefer_idle value */ + rcu_read_lock(); + st = task_schedtune(p); + prefer_idle = st->prefer_idle; + rcu_read_unlock(); + + return prefer_idle; +} + +static u64 +prefer_idle_read(struct cgroup_subsys_state *css, struct cftype *cft) +{ + struct schedtune *st = css_st(css); + + return st->prefer_idle; +} + +static int +prefer_idle_write(struct cgroup_subsys_state *css, struct cftype *cft, + u64 prefer_idle) +{ + struct schedtune *st = css_st(css); + st->prefer_idle = !!prefer_idle; + + return 0; +} + +static s64 +boost_read(struct cgroup_subsys_state *css, struct cftype *cft) +{ + struct schedtune *st = css_st(css); + + return st->boost; +} + +static int +boost_write(struct cgroup_subsys_state *css, struct cftype *cft, + s64 boost) +{ + struct schedtune *st = css_st(css); + + if (boost < 0 || boost > 100) + return -EINVAL; + + st->boost = boost; + + /* Update CPU boost */ + schedtune_boostgroup_update(st->idx, st->boost); + + return 0; +} + +static struct cftype files[] = { + { + .name = "boost", + .read_s64 = boost_read, + .write_s64 = boost_write, + }, + { + .name = "prefer_idle", + .read_u64 = prefer_idle_read, + .write_u64 = prefer_idle_write, + }, + { } /* terminate */ +}; + +static int +schedtune_boostgroup_init(struct schedtune *st) +{ + struct boost_groups *bg; + int cpu; + + /* Keep track of allocated boost groups */ + allocated_group[st->idx] = st; + + /* Initialize the per CPU boost groups */ + for_each_possible_cpu(cpu) { + bg = &per_cpu(cpu_boost_groups, cpu); + bg->group[st->idx].boost = 0; + bg->group[st->idx].tasks = 0; + bg->group[st->idx].ts = 0; + } + + return 0; +} + +static struct cgroup_subsys_state * +schedtune_css_alloc(struct cgroup_subsys_state *parent_css) +{ + struct schedtune *st; + int idx; + + if (!parent_css) + return &root_schedtune.css; + + /* Allow only single level hierachies */ + if (parent_css != &root_schedtune.css) { + pr_err("Nested SchedTune boosting groups not allowed\n"); + return ERR_PTR(-ENOMEM); + } + + /* Allow only a limited number of boosting groups */ + for (idx = 1; idx < BOOSTGROUPS_COUNT; ++idx) + if (!allocated_group[idx]) + break; + if (idx == BOOSTGROUPS_COUNT) { + pr_err("Trying to create more than %d SchedTune boosting groups\n", + BOOSTGROUPS_COUNT); + return ERR_PTR(-ENOSPC); + } + + st = kzalloc(sizeof(*st), GFP_KERNEL); + if (!st) + goto out; + + /* Initialize per CPUs boost group support */ + st->idx = idx; + if (schedtune_boostgroup_init(st)) + goto release; + + return &st->css; + +release: + kfree(st); +out: + return ERR_PTR(-ENOMEM); +} + +static void +schedtune_boostgroup_release(struct schedtune *st) +{ + /* Reset this boost group */ + schedtune_boostgroup_update(st->idx, 0); + + /* Keep track of allocated boost groups */ + allocated_group[st->idx] = NULL; +} + +static void +schedtune_css_free(struct cgroup_subsys_state *css) +{ + struct schedtune *st = css_st(css); + + schedtune_boostgroup_release(st); + kfree(st); +} + +struct cgroup_subsys schedtune_cgrp_subsys = { + .css_alloc = schedtune_css_alloc, + .css_free = schedtune_css_free, + .can_attach = schedtune_can_attach, + .cancel_attach = schedtune_cancel_attach, + .legacy_cftypes = files, + .early_init = 1, +}; + +static inline void +schedtune_init_cgroups(void) +{ + struct boost_groups *bg; + int cpu; + + /* Initialize the per CPU boost groups */ + for_each_possible_cpu(cpu) { + bg = &per_cpu(cpu_boost_groups, cpu); + memset(bg, 0, sizeof(struct boost_groups)); + raw_spin_lock_init(&bg->lock); + } + + pr_info("schedtune: configured to support %d boost groups\n", + BOOSTGROUPS_COUNT); + + schedtune_initialized = true; +} + +/* + * Initialize the cgroup structures + */ +static int +schedtune_init(void) +{ + schedtune_spc_rdiv = reciprocal_value(100); + schedtune_init_cgroups(); + return 0; +} +postcore_initcall(schedtune_init); diff --git a/kernel/sched/tune.h b/kernel/sched/tune.h new file mode 100644 index 000000000000..e79e1b198921 --- /dev/null +++ b/kernel/sched/tune.h @@ -0,0 +1,33 @@ + +#ifdef CONFIG_SCHED_TUNE + +#include <linux/reciprocal_div.h> + +/* + * System energy normalization constants + */ +struct target_nrg { + unsigned long min_power; + unsigned long max_power; + struct reciprocal_value rdiv; +}; + +int schedtune_cpu_boost(int cpu); +int schedtune_task_boost(struct task_struct *tsk); + +int schedtune_prefer_idle(struct task_struct *tsk); + +void schedtune_enqueue_task(struct task_struct *p, int cpu); +void schedtune_dequeue_task(struct task_struct *p, int cpu); + +#else /* CONFIG_SCHED_TUNE */ + +#define schedtune_cpu_boost(cpu) 0 +#define schedtune_task_boost(tsk) 0 + +#define schedtune_prefer_idle(tsk) 0 + +#define schedtune_enqueue_task(task, cpu) do { } while (0) +#define schedtune_dequeue_task(task, cpu) do { } while (0) + +#endif /* CONFIG_SCHED_TUNE */ diff --git a/kernel/sched/walt.c b/kernel/sched/walt.c new file mode 100644 index 000000000000..6a88c6e47d8c --- /dev/null +++ b/kernel/sched/walt.c @@ -0,0 +1,923 @@ +/* + * Copyright (c) 2016, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * + * Window Assisted Load Tracking (WALT) implementation credits: + * Srivatsa Vaddagiri, Steve Muckle, Syed Rameez Mustafa, Joonwoo Park, + * Pavan Kumar Kondeti, Olav Haugan + * + * 2016-03-06: Integration with EAS/refactoring by Vikram Mulukutla + * and Todd Kjos + */ + +#include <linux/acpi.h> +#include <linux/syscore_ops.h> +#include <trace/events/sched.h> +#include "sched.h" +#include "walt.h" + +#define WINDOW_STATS_RECENT 0 +#define WINDOW_STATS_MAX 1 +#define WINDOW_STATS_MAX_RECENT_AVG 2 +#define WINDOW_STATS_AVG 3 +#define WINDOW_STATS_INVALID_POLICY 4 + +#define EXITING_TASK_MARKER 0xdeaddead + +static __read_mostly unsigned int walt_ravg_hist_size = 5; +static __read_mostly unsigned int walt_window_stats_policy = + WINDOW_STATS_MAX_RECENT_AVG; +static __read_mostly unsigned int walt_account_wait_time = 1; +static __read_mostly unsigned int walt_freq_account_wait_time = 0; +static __read_mostly unsigned int walt_io_is_busy = 0; + +unsigned int sysctl_sched_walt_init_task_load_pct = 15; + +/* true -> use PELT based load stats, false -> use window-based load stats */ +bool __read_mostly walt_disabled = false; + +/* + * Window size (in ns). Adjust for the tick size so that the window + * rollover occurs just before the tick boundary. + */ +__read_mostly unsigned int walt_ravg_window = + (20000000 / TICK_NSEC) * TICK_NSEC; +#define MIN_SCHED_RAVG_WINDOW ((10000000 / TICK_NSEC) * TICK_NSEC) +#define MAX_SCHED_RAVG_WINDOW ((1000000000 / TICK_NSEC) * TICK_NSEC) + +static unsigned int sync_cpu; +static ktime_t ktime_last; +static __read_mostly bool walt_ktime_suspended; + +static unsigned int task_load(struct task_struct *p) +{ + return p->ravg.demand; +} + +static inline void fixup_cum_window_demand(struct rq *rq, s64 delta) +{ + rq->cum_window_demand += delta; + if (unlikely((s64)rq->cum_window_demand < 0)) + rq->cum_window_demand = 0; +} + +void +walt_inc_cumulative_runnable_avg(struct rq *rq, + struct task_struct *p) +{ + rq->cumulative_runnable_avg += p->ravg.demand; + + /* + * Add a task's contribution to the cumulative window demand when + * + * (1) task is enqueued with on_rq = 1 i.e migration, + * prio/cgroup/class change. + * (2) task is waking for the first time in this window. + */ + if (p->on_rq || (p->last_sleep_ts < rq->window_start)) + fixup_cum_window_demand(rq, p->ravg.demand); +} + +void +walt_dec_cumulative_runnable_avg(struct rq *rq, + struct task_struct *p) +{ + rq->cumulative_runnable_avg -= p->ravg.demand; + BUG_ON((s64)rq->cumulative_runnable_avg < 0); + + /* + * on_rq will be 1 for sleeping tasks. So check if the task + * is migrating or dequeuing in RUNNING state to change the + * prio/cgroup/class. + */ + if (task_on_rq_migrating(p) || p->state == TASK_RUNNING) + fixup_cum_window_demand(rq, -(s64)p->ravg.demand); +} + +static void +fixup_cumulative_runnable_avg(struct rq *rq, + struct task_struct *p, u64 new_task_load) +{ + s64 task_load_delta = (s64)new_task_load - task_load(p); + + rq->cumulative_runnable_avg += task_load_delta; + if ((s64)rq->cumulative_runnable_avg < 0) + panic("cra less than zero: tld: %lld, task_load(p) = %u\n", + task_load_delta, task_load(p)); + + fixup_cum_window_demand(rq, task_load_delta); +} + +u64 walt_ktime_clock(void) +{ + if (unlikely(walt_ktime_suspended)) + return ktime_to_ns(ktime_last); + return ktime_get_ns(); +} + +static void walt_resume(void) +{ + walt_ktime_suspended = false; +} + +static int walt_suspend(void) +{ + ktime_last = ktime_get(); + walt_ktime_suspended = true; + return 0; +} + +static struct syscore_ops walt_syscore_ops = { + .resume = walt_resume, + .suspend = walt_suspend +}; + +static int __init walt_init_ops(void) +{ + register_syscore_ops(&walt_syscore_ops); + return 0; +} +late_initcall(walt_init_ops); + +#ifdef CONFIG_CFS_BANDWIDTH +void walt_inc_cfs_cumulative_runnable_avg(struct cfs_rq *cfs_rq, + struct task_struct *p) +{ + cfs_rq->cumulative_runnable_avg += p->ravg.demand; +} + +void walt_dec_cfs_cumulative_runnable_avg(struct cfs_rq *cfs_rq, + struct task_struct *p) +{ + cfs_rq->cumulative_runnable_avg -= p->ravg.demand; +} +#endif + +static int exiting_task(struct task_struct *p) +{ + if (p->flags & PF_EXITING) { + if (p->ravg.sum_history[0] != EXITING_TASK_MARKER) { + p->ravg.sum_history[0] = EXITING_TASK_MARKER; + } + return 1; + } + return 0; +} + +static int __init set_walt_ravg_window(char *str) +{ + unsigned int adj_window; + bool no_walt = walt_disabled; + + get_option(&str, &walt_ravg_window); + + /* Adjust for CONFIG_HZ */ + adj_window = (walt_ravg_window / TICK_NSEC) * TICK_NSEC; + + /* Warn if we're a bit too far away from the expected window size */ + WARN(adj_window < walt_ravg_window - NSEC_PER_MSEC, + "tick-adjusted window size %u, original was %u\n", adj_window, + walt_ravg_window); + + walt_ravg_window = adj_window; + + walt_disabled = walt_disabled || + (walt_ravg_window < MIN_SCHED_RAVG_WINDOW || + walt_ravg_window > MAX_SCHED_RAVG_WINDOW); + + WARN(!no_walt && walt_disabled, + "invalid window size, disabling WALT\n"); + + return 0; +} + +early_param("walt_ravg_window", set_walt_ravg_window); + +static void +update_window_start(struct rq *rq, u64 wallclock) +{ + s64 delta; + int nr_windows; + + delta = wallclock - rq->window_start; + /* If the MPM global timer is cleared, set delta as 0 to avoid kernel BUG happening */ + if (delta < 0) { + delta = 0; + WARN_ONCE(1, "WALT wallclock appears to have gone backwards or reset\n"); + } + + if (delta < walt_ravg_window) + return; + + nr_windows = div64_u64(delta, walt_ravg_window); + rq->window_start += (u64)nr_windows * (u64)walt_ravg_window; + + rq->cum_window_demand = rq->cumulative_runnable_avg; +} + +extern unsigned long capacity_curr_of(int cpu); +/* + * Translate absolute delta time accounted on a CPU + * to a scale where 1024 is the capacity of the most + * capable CPU running at FMAX + */ +static u64 scale_exec_time(u64 delta, struct rq *rq) +{ + unsigned long capcurr = capacity_curr_of(cpu_of(rq)); + + return (delta * capcurr) >> SCHED_CAPACITY_SHIFT; +} + +static int cpu_is_waiting_on_io(struct rq *rq) +{ + if (!walt_io_is_busy) + return 0; + + return atomic_read(&rq->nr_iowait); +} + +void walt_account_irqtime(int cpu, struct task_struct *curr, + u64 delta, u64 wallclock) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags, nr_windows; + u64 cur_jiffies_ts; + + raw_spin_lock_irqsave(&rq->lock, flags); + + /* + * cputime (wallclock) uses sched_clock so use the same here for + * consistency. + */ + delta += sched_clock() - wallclock; + cur_jiffies_ts = get_jiffies_64(); + + if (is_idle_task(curr)) + walt_update_task_ravg(curr, rq, IRQ_UPDATE, walt_ktime_clock(), + delta); + + nr_windows = cur_jiffies_ts - rq->irqload_ts; + + if (nr_windows) { + if (nr_windows < 10) { + /* Decay CPU's irqload by 3/4 for each window. */ + rq->avg_irqload *= (3 * nr_windows); + rq->avg_irqload = div64_u64(rq->avg_irqload, + 4 * nr_windows); + } else { + rq->avg_irqload = 0; + } + rq->avg_irqload += rq->cur_irqload; + rq->cur_irqload = 0; + } + + rq->cur_irqload += delta; + rq->irqload_ts = cur_jiffies_ts; + raw_spin_unlock_irqrestore(&rq->lock, flags); +} + + +#define WALT_HIGH_IRQ_TIMEOUT 3 + +u64 walt_irqload(int cpu) { + struct rq *rq = cpu_rq(cpu); + s64 delta; + delta = get_jiffies_64() - rq->irqload_ts; + + /* + * Current context can be preempted by irq and rq->irqload_ts can be + * updated by irq context so that delta can be negative. + * But this is okay and we can safely return as this means there + * was recent irq occurrence. + */ + + if (delta < WALT_HIGH_IRQ_TIMEOUT) + return rq->avg_irqload; + else + return 0; +} + +int walt_cpu_high_irqload(int cpu) { + return walt_irqload(cpu) >= sysctl_sched_walt_cpu_high_irqload; +} + +static int account_busy_for_cpu_time(struct rq *rq, struct task_struct *p, + u64 irqtime, int event) +{ + if (is_idle_task(p)) { + /* TASK_WAKE && TASK_MIGRATE is not possible on idle task! */ + if (event == PICK_NEXT_TASK) + return 0; + + /* PUT_PREV_TASK, TASK_UPDATE && IRQ_UPDATE are left */ + return irqtime || cpu_is_waiting_on_io(rq); + } + + if (event == TASK_WAKE) + return 0; + + if (event == PUT_PREV_TASK || event == IRQ_UPDATE || + event == TASK_UPDATE) + return 1; + + /* Only TASK_MIGRATE && PICK_NEXT_TASK left */ + return walt_freq_account_wait_time; +} + +/* + * Account cpu activity in its busy time counters (rq->curr/prev_runnable_sum) + */ +static void update_cpu_busy_time(struct task_struct *p, struct rq *rq, + int event, u64 wallclock, u64 irqtime) +{ + int new_window, nr_full_windows = 0; + int p_is_curr_task = (p == rq->curr); + u64 mark_start = p->ravg.mark_start; + u64 window_start = rq->window_start; + u32 window_size = walt_ravg_window; + u64 delta; + + new_window = mark_start < window_start; + if (new_window) { + nr_full_windows = div64_u64((window_start - mark_start), + window_size); + if (p->ravg.active_windows < USHRT_MAX) + p->ravg.active_windows++; + } + + /* Handle per-task window rollover. We don't care about the idle + * task or exiting tasks. */ + if (new_window && !is_idle_task(p) && !exiting_task(p)) { + u32 curr_window = 0; + + if (!nr_full_windows) + curr_window = p->ravg.curr_window; + + p->ravg.prev_window = curr_window; + p->ravg.curr_window = 0; + } + + if (!account_busy_for_cpu_time(rq, p, irqtime, event)) { + /* account_busy_for_cpu_time() = 0, so no update to the + * task's current window needs to be made. This could be + * for example + * + * - a wakeup event on a task within the current + * window (!new_window below, no action required), + * - switching to a new task from idle (PICK_NEXT_TASK) + * in a new window where irqtime is 0 and we aren't + * waiting on IO */ + + if (!new_window) + return; + + /* A new window has started. The RQ demand must be rolled + * over if p is the current task. */ + if (p_is_curr_task) { + u64 prev_sum = 0; + + /* p is either idle task or an exiting task */ + if (!nr_full_windows) { + prev_sum = rq->curr_runnable_sum; + } + + rq->prev_runnable_sum = prev_sum; + rq->curr_runnable_sum = 0; + } + + return; + } + + if (!new_window) { + /* account_busy_for_cpu_time() = 1 so busy time needs + * to be accounted to the current window. No rollover + * since we didn't start a new window. An example of this is + * when a task starts execution and then sleeps within the + * same window. */ + + if (!irqtime || !is_idle_task(p) || cpu_is_waiting_on_io(rq)) + delta = wallclock - mark_start; + else + delta = irqtime; + delta = scale_exec_time(delta, rq); + rq->curr_runnable_sum += delta; + if (!is_idle_task(p) && !exiting_task(p)) + p->ravg.curr_window += delta; + + return; + } + + if (!p_is_curr_task) { + /* account_busy_for_cpu_time() = 1 so busy time needs + * to be accounted to the current window. A new window + * has also started, but p is not the current task, so the + * window is not rolled over - just split up and account + * as necessary into curr and prev. The window is only + * rolled over when a new window is processed for the current + * task. + * + * Irqtime can't be accounted by a task that isn't the + * currently running task. */ + + if (!nr_full_windows) { + /* A full window hasn't elapsed, account partial + * contribution to previous completed window. */ + delta = scale_exec_time(window_start - mark_start, rq); + if (!exiting_task(p)) + p->ravg.prev_window += delta; + } else { + /* Since at least one full window has elapsed, + * the contribution to the previous window is the + * full window (window_size). */ + delta = scale_exec_time(window_size, rq); + if (!exiting_task(p)) + p->ravg.prev_window = delta; + } + rq->prev_runnable_sum += delta; + + /* Account piece of busy time in the current window. */ + delta = scale_exec_time(wallclock - window_start, rq); + rq->curr_runnable_sum += delta; + if (!exiting_task(p)) + p->ravg.curr_window = delta; + + return; + } + + if (!irqtime || !is_idle_task(p) || cpu_is_waiting_on_io(rq)) { + /* account_busy_for_cpu_time() = 1 so busy time needs + * to be accounted to the current window. A new window + * has started and p is the current task so rollover is + * needed. If any of these three above conditions are true + * then this busy time can't be accounted as irqtime. + * + * Busy time for the idle task or exiting tasks need not + * be accounted. + * + * An example of this would be a task that starts execution + * and then sleeps once a new window has begun. */ + + if (!nr_full_windows) { + /* A full window hasn't elapsed, account partial + * contribution to previous completed window. */ + delta = scale_exec_time(window_start - mark_start, rq); + if (!is_idle_task(p) && !exiting_task(p)) + p->ravg.prev_window += delta; + + delta += rq->curr_runnable_sum; + } else { + /* Since at least one full window has elapsed, + * the contribution to the previous window is the + * full window (window_size). */ + delta = scale_exec_time(window_size, rq); + if (!is_idle_task(p) && !exiting_task(p)) + p->ravg.prev_window = delta; + + } + /* + * Rollover for normal runnable sum is done here by overwriting + * the values in prev_runnable_sum and curr_runnable_sum. + * Rollover for new task runnable sum has completed by previous + * if-else statement. + */ + rq->prev_runnable_sum = delta; + + /* Account piece of busy time in the current window. */ + delta = scale_exec_time(wallclock - window_start, rq); + rq->curr_runnable_sum = delta; + if (!is_idle_task(p) && !exiting_task(p)) + p->ravg.curr_window = delta; + + return; + } + + if (irqtime) { + /* account_busy_for_cpu_time() = 1 so busy time needs + * to be accounted to the current window. A new window + * has started and p is the current task so rollover is + * needed. The current task must be the idle task because + * irqtime is not accounted for any other task. + * + * Irqtime will be accounted each time we process IRQ activity + * after a period of idleness, so we know the IRQ busy time + * started at wallclock - irqtime. */ + + BUG_ON(!is_idle_task(p)); + mark_start = wallclock - irqtime; + + /* Roll window over. If IRQ busy time was just in the current + * window then that is all that need be accounted. */ + rq->prev_runnable_sum = rq->curr_runnable_sum; + if (mark_start > window_start) { + rq->curr_runnable_sum = scale_exec_time(irqtime, rq); + return; + } + + /* The IRQ busy time spanned multiple windows. Process the + * busy time preceding the current window start first. */ + delta = window_start - mark_start; + if (delta > window_size) + delta = window_size; + delta = scale_exec_time(delta, rq); + rq->prev_runnable_sum += delta; + + /* Process the remaining IRQ busy time in the current window. */ + delta = wallclock - window_start; + rq->curr_runnable_sum = scale_exec_time(delta, rq); + + return; + } + + BUG(); +} + +static int account_busy_for_task_demand(struct task_struct *p, int event) +{ + /* No need to bother updating task demand for exiting tasks + * or the idle task. */ + if (exiting_task(p) || is_idle_task(p)) + return 0; + + /* When a task is waking up it is completing a segment of non-busy + * time. Likewise, if wait time is not treated as busy time, then + * when a task begins to run or is migrated, it is not running and + * is completing a segment of non-busy time. */ + if (event == TASK_WAKE || (!walt_account_wait_time && + (event == PICK_NEXT_TASK || event == TASK_MIGRATE))) + return 0; + + return 1; +} + +/* + * Called when new window is starting for a task, to record cpu usage over + * recently concluded window(s). Normally 'samples' should be 1. It can be > 1 + * when, say, a real-time task runs without preemption for several windows at a + * stretch. + */ +static void update_history(struct rq *rq, struct task_struct *p, + u32 runtime, int samples, int event) +{ + u32 *hist = &p->ravg.sum_history[0]; + int ridx, widx; + u32 max = 0, avg, demand; + u64 sum = 0; + + /* Ignore windows where task had no activity */ + if (!runtime || is_idle_task(p) || exiting_task(p) || !samples) + goto done; + + /* Push new 'runtime' value onto stack */ + widx = walt_ravg_hist_size - 1; + ridx = widx - samples; + for (; ridx >= 0; --widx, --ridx) { + hist[widx] = hist[ridx]; + sum += hist[widx]; + if (hist[widx] > max) + max = hist[widx]; + } + + for (widx = 0; widx < samples && widx < walt_ravg_hist_size; widx++) { + hist[widx] = runtime; + sum += hist[widx]; + if (hist[widx] > max) + max = hist[widx]; + } + + p->ravg.sum = 0; + + if (walt_window_stats_policy == WINDOW_STATS_RECENT) { + demand = runtime; + } else if (walt_window_stats_policy == WINDOW_STATS_MAX) { + demand = max; + } else { + avg = div64_u64(sum, walt_ravg_hist_size); + if (walt_window_stats_policy == WINDOW_STATS_AVG) + demand = avg; + else + demand = max(avg, runtime); + } + + /* + * A throttled deadline sched class task gets dequeued without + * changing p->on_rq. Since the dequeue decrements hmp stats + * avoid decrementing it here again. + * + * When window is rolled over, the cumulative window demand + * is reset to the cumulative runnable average (contribution from + * the tasks on the runqueue). If the current task is dequeued + * already, it's demand is not included in the cumulative runnable + * average. So add the task demand separately to cumulative window + * demand. + */ + if (!task_has_dl_policy(p) || !p->dl.dl_throttled) { + if (task_on_rq_queued(p)) + fixup_cumulative_runnable_avg(rq, p, demand); + else if (rq->curr == p) + fixup_cum_window_demand(rq, demand); + } + + p->ravg.demand = demand; + +done: + trace_walt_update_history(rq, p, runtime, samples, event); + return; +} + +static void add_to_task_demand(struct rq *rq, struct task_struct *p, + u64 delta) +{ + delta = scale_exec_time(delta, rq); + p->ravg.sum += delta; + if (unlikely(p->ravg.sum > walt_ravg_window)) + p->ravg.sum = walt_ravg_window; +} + +/* + * Account cpu demand of task and/or update task's cpu demand history + * + * ms = p->ravg.mark_start; + * wc = wallclock + * ws = rq->window_start + * + * Three possibilities: + * + * a) Task event is contained within one window. + * window_start < mark_start < wallclock + * + * ws ms wc + * | | | + * V V V + * |---------------| + * + * In this case, p->ravg.sum is updated *iff* event is appropriate + * (ex: event == PUT_PREV_TASK) + * + * b) Task event spans two windows. + * mark_start < window_start < wallclock + * + * ms ws wc + * | | | + * V V V + * -----|------------------- + * + * In this case, p->ravg.sum is updated with (ws - ms) *iff* event + * is appropriate, then a new window sample is recorded followed + * by p->ravg.sum being set to (wc - ws) *iff* event is appropriate. + * + * c) Task event spans more than two windows. + * + * ms ws_tmp ws wc + * | | | | + * V V V V + * ---|-------|-------|-------|-------|------ + * | | + * |<------ nr_full_windows ------>| + * + * In this case, p->ravg.sum is updated with (ws_tmp - ms) first *iff* + * event is appropriate, window sample of p->ravg.sum is recorded, + * 'nr_full_window' samples of window_size is also recorded *iff* + * event is appropriate and finally p->ravg.sum is set to (wc - ws) + * *iff* event is appropriate. + * + * IMPORTANT : Leave p->ravg.mark_start unchanged, as update_cpu_busy_time() + * depends on it! + */ +static void update_task_demand(struct task_struct *p, struct rq *rq, + int event, u64 wallclock) +{ + u64 mark_start = p->ravg.mark_start; + u64 delta, window_start = rq->window_start; + int new_window, nr_full_windows; + u32 window_size = walt_ravg_window; + + new_window = mark_start < window_start; + if (!account_busy_for_task_demand(p, event)) { + if (new_window) + /* If the time accounted isn't being accounted as + * busy time, and a new window started, only the + * previous window need be closed out with the + * pre-existing demand. Multiple windows may have + * elapsed, but since empty windows are dropped, + * it is not necessary to account those. */ + update_history(rq, p, p->ravg.sum, 1, event); + return; + } + + if (!new_window) { + /* The simple case - busy time contained within the existing + * window. */ + add_to_task_demand(rq, p, wallclock - mark_start); + return; + } + + /* Busy time spans at least two windows. Temporarily rewind + * window_start to first window boundary after mark_start. */ + delta = window_start - mark_start; + nr_full_windows = div64_u64(delta, window_size); + window_start -= (u64)nr_full_windows * (u64)window_size; + + /* Process (window_start - mark_start) first */ + add_to_task_demand(rq, p, window_start - mark_start); + + /* Push new sample(s) into task's demand history */ + update_history(rq, p, p->ravg.sum, 1, event); + if (nr_full_windows) + update_history(rq, p, scale_exec_time(window_size, rq), + nr_full_windows, event); + + /* Roll window_start back to current to process any remainder + * in current window. */ + window_start += (u64)nr_full_windows * (u64)window_size; + + /* Process (wallclock - window_start) next */ + mark_start = window_start; + add_to_task_demand(rq, p, wallclock - mark_start); +} + +/* Reflect task activity on its demand and cpu's busy time statistics */ +void walt_update_task_ravg(struct task_struct *p, struct rq *rq, + int event, u64 wallclock, u64 irqtime) +{ + if (walt_disabled || !rq->window_start) + return; + + /* there's a bug here - there are many cases where + * we enter here without holding this lock, coming from + * walt_fixup_busy_time - looks like in 4.14 we don't + * hold the dest_rq at time of migration, but I haven't + * yet worked out if it is safe to always lock dest_rq there. + * + * temporarily disable this assert to continue checking the + * rest of the locking here. + */ + //lockdep_assert_held(&rq->lock); + + update_window_start(rq, wallclock); + + if (!p->ravg.mark_start) + goto done; + + update_task_demand(p, rq, event, wallclock); + update_cpu_busy_time(p, rq, event, wallclock, irqtime); + +done: + trace_walt_update_task_ravg(p, rq, event, wallclock, irqtime); + + p->ravg.mark_start = wallclock; +} + +static void reset_task_stats(struct task_struct *p) +{ + u32 sum = 0; + + if (exiting_task(p)) + sum = EXITING_TASK_MARKER; + + memset(&p->ravg, 0, sizeof(struct ravg)); + /* Retain EXITING_TASK marker */ + p->ravg.sum_history[0] = sum; +} + +void walt_mark_task_starting(struct task_struct *p) +{ + u64 wallclock; + struct rq *rq = task_rq(p); + + if (!rq->window_start) { + reset_task_stats(p); + return; + } + + wallclock = walt_ktime_clock(); + p->ravg.mark_start = wallclock; +} + +void walt_set_window_start(struct rq *rq, struct rq_flags *rf) +{ + if (likely(rq->window_start)) + return; + + if (cpu_of(rq) == sync_cpu) { + rq->window_start = 1; + } else { + struct rq *sync_rq = cpu_rq(sync_cpu); + rq_unpin_lock(rq, rf); + double_lock_balance(rq, sync_rq); + rq->window_start = sync_rq->window_start; + rq->curr_runnable_sum = rq->prev_runnable_sum = 0; + raw_spin_unlock(&sync_rq->lock); + rq_repin_lock(rq, rf); + } + + rq->curr->ravg.mark_start = rq->window_start; +} + +void walt_migrate_sync_cpu(int cpu) +{ + if (cpu == sync_cpu) + sync_cpu = smp_processor_id(); +} + +void walt_fixup_busy_time(struct task_struct *p, int new_cpu) +{ + struct rq *src_rq = task_rq(p); + struct rq *dest_rq = cpu_rq(new_cpu); + u64 wallclock; + + if (!p->on_rq && p->state != TASK_WAKING) + return; + + if (exiting_task(p)) { + return; + } + + if (p->state == TASK_WAKING) + double_rq_lock(src_rq, dest_rq); + + wallclock = walt_ktime_clock(); + +//#define LOCK_CONDITION(rq) (debug_locks && !lockdep_is_held(&rq->lock)) +// WARN(LOCK_CONDITION(task_rq(p)), "task_rq(p) not held. p->state=%08lx new_cpu=%d task_cpu=%d", p->state, new_cpu, p->cpu); +// WARN(LOCK_CONDITION(dest_rq), "dest_rq not held. p->state=%08lx new_cpu=%d task_cpu=%d", p->state, new_cpu, p->cpu); + + /* + * It seems that in lots of cases we don't have + * dest_rq locked when we get here, which means + * we can't be sure to the WALT stats - someone + * needs to fix this. + */ + walt_update_task_ravg(task_rq(p)->curr, task_rq(p), + TASK_UPDATE, wallclock, 0); + walt_update_task_ravg(dest_rq->curr, dest_rq, + TASK_UPDATE, wallclock, 0); + +// WARN(LOCK_CONDITION(task_rq(p)), "task_rq(p) not held after rq update. p->state=%08lx new_cpu=%d task_cpu=%d", p->state, new_cpu, p->cpu); + walt_update_task_ravg(p, task_rq(p), TASK_MIGRATE, wallclock, 0); + + /* + * When a task is migrating during the wakeup, adjust + * the task's contribution towards cumulative window + * demand. + */ + if (p->state == TASK_WAKING && + p->last_sleep_ts >= src_rq->window_start) { + fixup_cum_window_demand(src_rq, -(s64)p->ravg.demand); + fixup_cum_window_demand(dest_rq, p->ravg.demand); + } + + if (p->ravg.curr_window) { + src_rq->curr_runnable_sum -= p->ravg.curr_window; + dest_rq->curr_runnable_sum += p->ravg.curr_window; + } + + if (p->ravg.prev_window) { + src_rq->prev_runnable_sum -= p->ravg.prev_window; + dest_rq->prev_runnable_sum += p->ravg.prev_window; + } + + if ((s64)src_rq->prev_runnable_sum < 0) { + src_rq->prev_runnable_sum = 0; + WARN_ON(1); + } + if ((s64)src_rq->curr_runnable_sum < 0) { + src_rq->curr_runnable_sum = 0; + WARN_ON(1); + } + + trace_walt_migration_update_sum(src_rq, p); + trace_walt_migration_update_sum(dest_rq, p); + + if (p->state == TASK_WAKING) + double_rq_unlock(src_rq, dest_rq); +} + +void walt_init_new_task_load(struct task_struct *p) +{ + int i; + u32 init_load_windows = + div64_u64((u64)sysctl_sched_walt_init_task_load_pct * + (u64)walt_ravg_window, 100); + u32 init_load_pct = current->init_load_pct; + + p->init_load_pct = 0; + memset(&p->ravg, 0, sizeof(struct ravg)); + + if (init_load_pct) { + init_load_windows = div64_u64((u64)init_load_pct * + (u64)walt_ravg_window, 100); + } + + p->ravg.demand = init_load_windows; + for (i = 0; i < RAVG_HIST_SIZE_MAX; ++i) + p->ravg.sum_history[i] = init_load_windows; +} diff --git a/kernel/sched/walt.h b/kernel/sched/walt.h new file mode 100644 index 000000000000..3446ca1be8ac --- /dev/null +++ b/kernel/sched/walt.h @@ -0,0 +1,67 @@ +/* + * Copyright (c) 2016, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __WALT_H +#define __WALT_H + +#ifdef CONFIG_SCHED_WALT + +void walt_update_task_ravg(struct task_struct *p, struct rq *rq, int event, + u64 wallclock, u64 irqtime); +void walt_inc_cumulative_runnable_avg(struct rq *rq, struct task_struct *p); +void walt_dec_cumulative_runnable_avg(struct rq *rq, struct task_struct *p); + +void walt_fixup_busy_time(struct task_struct *p, int new_cpu); +void walt_init_new_task_load(struct task_struct *p); +void walt_mark_task_starting(struct task_struct *p); +void walt_set_window_start(struct rq *rq, struct rq_flags *rf); +void walt_migrate_sync_cpu(int cpu); +u64 walt_ktime_clock(void); +void walt_account_irqtime(int cpu, struct task_struct *curr, u64 delta, + u64 wallclock); + +u64 walt_irqload(int cpu); +int walt_cpu_high_irqload(int cpu); + +#else /* CONFIG_SCHED_WALT */ + +static inline void walt_update_task_ravg(struct task_struct *p, struct rq *rq, + int event, u64 wallclock, u64 irqtime) { } +static inline void walt_inc_cumulative_runnable_avg(struct rq *rq, struct task_struct *p) { } +static inline void walt_dec_cumulative_runnable_avg(struct rq *rq, struct task_struct *p) { } +static inline void walt_fixup_busy_time(struct task_struct *p, int new_cpu) { } +static inline void walt_init_new_task_load(struct task_struct *p) { } +static inline void walt_mark_task_starting(struct task_struct *p) { } +static inline void walt_set_window_start(struct rq *rq, struct rq_flags *rf) { } +static inline void walt_migrate_sync_cpu(int cpu) { } +static inline u64 walt_ktime_clock(void) { return 0; } + +#define walt_cpu_high_irqload(cpu) false + +#endif /* CONFIG_SCHED_WALT */ + +#if defined(CONFIG_CFS_BANDWIDTH) && defined(CONFIG_SCHED_WALT) +void walt_inc_cfs_cumulative_runnable_avg(struct cfs_rq *rq, + struct task_struct *p); +void walt_dec_cfs_cumulative_runnable_avg(struct cfs_rq *rq, + struct task_struct *p); +#else +static inline void walt_inc_cfs_cumulative_runnable_avg(struct cfs_rq *rq, + struct task_struct *p) { } +static inline void walt_dec_cfs_cumulative_runnable_avg(struct cfs_rq *rq, + struct task_struct *p) { } +#endif + +extern bool walt_disabled; + +#endif diff --git a/kernel/sys.c b/kernel/sys.c index ab96b9882347..4254d6241a97 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -42,6 +42,8 @@ #include <linux/syscore_ops.h> #include <linux/version.h> #include <linux/ctype.h> +#include <linux/mm.h> +#include <linux/mempolicy.h> #include <linux/compat.h> #include <linux/syscalls.h> @@ -2183,6 +2185,153 @@ static int propagate_has_child_subreaper(struct task_struct *p, void *data) return 1; } +#ifdef CONFIG_MMU +static int prctl_update_vma_anon_name(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, unsigned long end, + const char __user *name_addr) +{ + struct mm_struct *mm = vma->vm_mm; + int error = 0; + pgoff_t pgoff; + + if (name_addr == vma_get_anon_name(vma)) { + *prev = vma; + goto out; + } + + pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); + *prev = vma_merge(mm, *prev, start, end, vma->vm_flags, vma->anon_vma, + vma->vm_file, pgoff, vma_policy(vma), + vma->vm_userfaultfd_ctx, name_addr); + if (*prev) { + vma = *prev; + goto success; + } + + *prev = vma; + + if (start != vma->vm_start) { + error = split_vma(mm, vma, start, 1); + if (error) + goto out; + } + + if (end != vma->vm_end) { + error = split_vma(mm, vma, end, 0); + if (error) + goto out; + } + +success: + if (!vma->vm_file) + vma->anon_name = name_addr; + +out: + if (error == -ENOMEM) + error = -EAGAIN; + return error; +} + +static int prctl_set_vma_anon_name(unsigned long start, unsigned long end, + unsigned long arg) +{ + unsigned long tmp; + struct vm_area_struct *vma, *prev; + int unmapped_error = 0; + int error = -EINVAL; + + /* + * If the interval [start,end) covers some unmapped address + * ranges, just ignore them, but return -ENOMEM at the end. + * - this matches the handling in madvise. + */ + vma = find_vma_prev(current->mm, start, &prev); + if (vma && start > vma->vm_start) + prev = vma; + + for (;;) { + /* Still start < end. */ + error = -ENOMEM; + if (!vma) + return error; + + /* Here start < (end|vma->vm_end). */ + if (start < vma->vm_start) { + unmapped_error = -ENOMEM; + start = vma->vm_start; + if (start >= end) + return error; + } + + /* Here vma->vm_start <= start < (end|vma->vm_end) */ + tmp = vma->vm_end; + if (end < tmp) + tmp = end; + + /* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */ + error = prctl_update_vma_anon_name(vma, &prev, start, tmp, + (const char __user *)arg); + if (error) + return error; + start = tmp; + if (prev && start < prev->vm_end) + start = prev->vm_end; + error = unmapped_error; + if (start >= end) + return error; + if (prev) + vma = prev->vm_next; + else /* madvise_remove dropped mmap_sem */ + vma = find_vma(current->mm, start); + } +} + +static int prctl_set_vma(unsigned long opt, unsigned long start, + unsigned long len_in, unsigned long arg) +{ + struct mm_struct *mm = current->mm; + int error; + unsigned long len; + unsigned long end; + + if (start & ~PAGE_MASK) + return -EINVAL; + len = (len_in + ~PAGE_MASK) & PAGE_MASK; + + /* Check to see whether len was rounded up from small -ve to zero */ + if (len_in && !len) + return -EINVAL; + + end = start + len; + if (end < start) + return -EINVAL; + + if (end == start) + return 0; + + down_write(&mm->mmap_sem); + + switch (opt) { + case PR_SET_VMA_ANON_NAME: + error = prctl_set_vma_anon_name(start, end, arg); + break; + default: + error = -EINVAL; + } + + up_write(&mm->mmap_sem); + + return error; +} +#else /* CONFIG_MMU */ +static int prctl_set_vma(unsigned long opt, unsigned long start, + unsigned long len_in, unsigned long arg) +{ + return -EINVAL; +} +#endif + int __weak arch_prctl_spec_ctrl_get(struct task_struct *t, unsigned long which) { return -EINVAL; @@ -2406,6 +2555,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, return -EINVAL; error = arch_prctl_spec_ctrl_set(me, arg2, arg3); break; + case PR_SET_VMA: + error = prctl_set_vma(arg2, arg3, arg4, arg5); + break; default: error = -EINVAL; break; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 74fc3a9d1923..56b91df1809c 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -105,6 +105,7 @@ extern char core_pattern[]; extern unsigned int core_pipe_limit; #endif extern int pid_max; +extern int extra_free_kbytes; extern int pid_max_min, pid_max_max; extern int percpu_pagelist_fraction; extern int latencytop_enabled; @@ -330,6 +331,50 @@ static struct ctl_table kern_table[] = { .extra1 = &min_sched_granularity_ns, .extra2 = &max_sched_granularity_ns, }, +#ifdef CONFIG_SCHED_WALT + { + .procname = "sched_use_walt_cpu_util", + .data = &sysctl_sched_use_walt_cpu_util, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "sched_use_walt_task_util", + .data = &sysctl_sched_use_walt_task_util, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "sched_walt_init_task_load_pct", + .data = &sysctl_sched_walt_init_task_load_pct, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "sched_walt_cpu_high_irqload", + .data = &sysctl_sched_walt_cpu_high_irqload, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif + { + .procname = "sched_sync_hint_enable", + .data = &sysctl_sched_sync_hint_enable, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "sched_cstate_aware", + .data = &sysctl_sched_cstate_aware, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { .procname = "sched_wakeup_granularity_ns", .data = &sysctl_sched_wakeup_granularity, @@ -1448,6 +1493,14 @@ static struct ctl_table vm_table[] = { .extra2 = &one_thousand, }, { + .procname = "extra_free_kbytes", + .data = &extra_free_kbytes, + .maxlen = sizeof(extra_free_kbytes), + .mode = 0644, + .proc_handler = min_free_kbytes_sysctl_handler, + .extra1 = &zero, + }, + { .procname = "percpu_pagelist_fraction", .data = &percpu_pagelist_fraction, .maxlen = sizeof(percpu_pagelist_fraction), diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index ecce9122343b..3020f7248a4a 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -463,7 +463,8 @@ static inline void hrtimer_update_next_timer(struct hrtimer_cpu_base *cpu_base, #endif } -static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base) +static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base, + const struct hrtimer *exclude) { struct hrtimer_clock_base *base = cpu_base->clock_base; unsigned int active = cpu_base->active_bases; @@ -479,9 +480,24 @@ static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base) next = timerqueue_getnext(&base->active); timer = container_of(next, struct hrtimer, node); + if (timer == exclude) { + /* Get to the next timer in the queue. */ + struct rb_node *rbn = rb_next(&next->node); + + next = rb_entry_safe(rbn, struct timerqueue_node, node); + if (!next) + continue; + + timer = container_of(next, struct hrtimer, node); + } expires = ktime_sub(hrtimer_get_expires(timer), base->offset); if (expires < expires_next) { expires_next = expires; + + /* Skip cpu_base update if a timer is being excluded. */ + if (exclude) + continue; + hrtimer_update_next_timer(cpu_base, timer); } } @@ -560,7 +576,7 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal) if (!cpu_base->hres_active) return; - expires_next = __hrtimer_get_next_event(cpu_base); + expires_next = __hrtimer_get_next_event(cpu_base, NULL); if (skip_equal && expires_next == cpu_base->expires_next) return; @@ -1079,7 +1095,30 @@ u64 hrtimer_get_next_event(void) raw_spin_lock_irqsave(&cpu_base->lock, flags); if (!__hrtimer_hres_active(cpu_base)) - expires = __hrtimer_get_next_event(cpu_base); + expires = __hrtimer_get_next_event(cpu_base, NULL); + + raw_spin_unlock_irqrestore(&cpu_base->lock, flags); + + return expires; +} + +/** + * hrtimer_next_event_without - time until next expiry event w/o one timer + * @exclude: timer to exclude + * + * Returns the next expiry time over all timers except for the @exclude one or + * KTIME_MAX if none of them is pending. + */ +u64 hrtimer_next_event_without(const struct hrtimer *exclude) +{ + struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); + u64 expires = KTIME_MAX; + unsigned long flags; + + raw_spin_lock_irqsave(&cpu_base->lock, flags); + + if (__hrtimer_hres_active(cpu_base)) + expires = __hrtimer_get_next_event(cpu_base, exclude); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); @@ -1321,7 +1360,7 @@ retry: __hrtimer_run_queues(cpu_base, now); /* Reevaluate the clock bases for the next expiry */ - expires_next = __hrtimer_get_next_event(cpu_base); + expires_next = __hrtimer_get_next_event(cpu_base, NULL); /* * Store the new expiry value so the migration code can verify * against it. diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 9288532f73c8..17ce25a49835 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -31,7 +31,7 @@ /* USER_HZ period (usecs): */ -unsigned long tick_usec = TICK_USEC; +unsigned long tick_usec = USER_TICK_USEC; /* SHIFTED_HZ period (nsecs): */ unsigned long tick_nsec; diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 3c7b400512eb..710505b026dd 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -567,14 +567,11 @@ static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now) sched_clock_idle_wakeup_event(); } -static ktime_t tick_nohz_start_idle(struct tick_sched *ts) +static void tick_nohz_start_idle(struct tick_sched *ts) { - ktime_t now = ktime_get(); - - ts->idle_entrytime = now; + ts->idle_entrytime = ktime_get(); ts->idle_active = 1; sched_clock_idle_sleep_event(); - return now; } /** @@ -683,13 +680,10 @@ static inline bool local_timer_softirq_pending(void) return local_softirq_pending() & BIT(TIMER_SOFTIRQ); } -static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, - ktime_t now, int cpu) +static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) { - struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); u64 basemono, next_tick, next_tmr, next_rcu, delta, expires; unsigned long seq, basejiff; - ktime_t tick; /* Read jiffies and the time when jiffies were updated last */ do { @@ -698,6 +692,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, basejiff = jiffies; } while (read_seqretry(&jiffies_lock, seq)); ts->last_jiffies = basejiff; + ts->timer_expires_base = basemono; /* * Keep the periodic tick, when RCU, architecture or irq_work @@ -742,32 +737,20 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, * next period, so no point in stopping it either, bail. */ if (!ts->tick_stopped) { - tick = 0; + ts->timer_expires = 0; goto out; } } /* - * If this CPU is the one which updates jiffies, then give up - * the assignment and let it be taken by the CPU which runs - * the tick timer next, which might be this CPU as well. If we - * don't drop this here the jiffies might be stale and - * do_timer() never invoked. Keep track of the fact that it - * was the one which had the do_timer() duty last. If this CPU - * is the one which had the do_timer() duty last, we limit the - * sleep time to the timekeeping max_deferment value. + * If this CPU is the one which had the do_timer() duty last, we limit + * the sleep time to the timekeeping max_deferment value. * Otherwise we can sleep as long as we want. */ delta = timekeeping_max_deferment(); - if (cpu == tick_do_timer_cpu) { - tick_do_timer_cpu = TICK_DO_TIMER_NONE; - ts->do_timer_last = 1; - } else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) { - delta = KTIME_MAX; - ts->do_timer_last = 0; - } else if (!ts->do_timer_last) { + if (cpu != tick_do_timer_cpu && + (tick_do_timer_cpu != TICK_DO_TIMER_NONE || !ts->do_timer_last)) delta = KTIME_MAX; - } #ifdef CONFIG_NO_HZ_FULL /* Limit the tick delta to the maximum scheduler deferment */ @@ -781,14 +764,42 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, else expires = KTIME_MAX; - expires = min_t(u64, expires, next_tick); - tick = expires; + ts->timer_expires = min_t(u64, expires, next_tick); + +out: + return ts->timer_expires; +} + +static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) +{ + struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); + u64 basemono = ts->timer_expires_base; + u64 expires = ts->timer_expires; + ktime_t tick = expires; + + /* Make sure we won't be trying to stop it twice in a row. */ + ts->timer_expires_base = 0; + + /* + * If this CPU is the one which updates jiffies, then give up + * the assignment and let it be taken by the CPU which runs + * the tick timer next, which might be this CPU as well. If we + * don't drop this here the jiffies might be stale and + * do_timer() never invoked. Keep track of the fact that it + * was the one which had the do_timer() duty last. + */ + if (cpu == tick_do_timer_cpu) { + tick_do_timer_cpu = TICK_DO_TIMER_NONE; + ts->do_timer_last = 1; + } else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) { + ts->do_timer_last = 0; + } /* Skip reprogram of event if its not changed */ if (ts->tick_stopped && (expires == ts->next_tick)) { /* Sanity check: make sure clockevent is actually programmed */ if (tick == KTIME_MAX || ts->next_tick == hrtimer_get_expires(&ts->sched_timer)) - goto out; + return; WARN_ON_ONCE(1); printk_once("basemono: %llu ts->next_tick: %llu dev->next_event: %llu timer->active: %d timer->expires: %llu\n", @@ -821,7 +832,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, if (unlikely(expires == KTIME_MAX)) { if (ts->nohz_mode == NOHZ_MODE_HIGHRES) hrtimer_cancel(&ts->sched_timer); - goto out; + return; } if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { @@ -830,15 +841,22 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, hrtimer_set_expires(&ts->sched_timer, tick); tick_program_event(tick, 1); } +} -out: - /* - * Update the estimated sleep length until the next timer - * (not only the tick). - */ - ts->sleep_length = ktime_sub(dev->next_event, now); - return tick; +static void tick_nohz_retain_tick(struct tick_sched *ts) +{ + ts->timer_expires_base = 0; +} + +#ifdef CONFIG_NO_HZ_FULL +static void tick_nohz_stop_sched_tick(struct tick_sched *ts, int cpu) +{ + if (tick_nohz_next_event(ts, cpu)) + tick_nohz_stop_tick(ts, cpu); + else + tick_nohz_retain_tick(ts); } +#endif /* CONFIG_NO_HZ_FULL */ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now) { @@ -875,7 +893,7 @@ static void tick_nohz_full_update_tick(struct tick_sched *ts) return; if (can_stop_full_tick(cpu, ts)) - tick_nohz_stop_sched_tick(ts, ktime_get(), cpu); + tick_nohz_stop_sched_tick(ts, cpu); else if (ts->tick_stopped) tick_nohz_restart_sched_tick(ts, ktime_get()); #endif @@ -901,10 +919,8 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) return false; } - if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) { - ts->sleep_length = NSEC_PER_SEC / HZ; + if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) return false; - } if (need_resched()) return false; @@ -939,42 +955,65 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) return true; } -static void __tick_nohz_idle_enter(struct tick_sched *ts) +static void __tick_nohz_idle_stop_tick(struct tick_sched *ts) { - ktime_t now, expires; + ktime_t expires; int cpu = smp_processor_id(); - now = tick_nohz_start_idle(ts); + /* + * If tick_nohz_get_sleep_length() ran tick_nohz_next_event(), the + * tick timer expiration time is known already. + */ + if (ts->timer_expires_base) + expires = ts->timer_expires; + else if (can_stop_idle_tick(cpu, ts)) + expires = tick_nohz_next_event(ts, cpu); + else + return; + + ts->idle_calls++; - if (can_stop_idle_tick(cpu, ts)) { + if (expires > 0LL) { int was_stopped = ts->tick_stopped; - ts->idle_calls++; + tick_nohz_stop_tick(ts, cpu); - expires = tick_nohz_stop_sched_tick(ts, now, cpu); - if (expires > 0LL) { - ts->idle_sleeps++; - ts->idle_expires = expires; - } + ts->idle_sleeps++; + ts->idle_expires = expires; if (!was_stopped && ts->tick_stopped) { ts->idle_jiffies = ts->last_jiffies; nohz_balance_enter_idle(cpu); } + } else { + tick_nohz_retain_tick(ts); } } /** - * tick_nohz_idle_enter - stop the idle tick from the idle task + * tick_nohz_idle_stop_tick - stop the idle tick from the idle task * * When the next event is more than a tick into the future, stop the idle tick - * Called when we start the idle loop. - * - * The arch is responsible of calling: + */ +void tick_nohz_idle_stop_tick(void) +{ + __tick_nohz_idle_stop_tick(this_cpu_ptr(&tick_cpu_sched)); +} + +void tick_nohz_idle_retain_tick(void) +{ + tick_nohz_retain_tick(this_cpu_ptr(&tick_cpu_sched)); + /* + * Undo the effect of get_next_timer_interrupt() called from + * tick_nohz_next_event(). + */ + timer_clear_idle(); +} + +/** + * tick_nohz_idle_enter - prepare for entering idle on the current CPU * - * - rcu_idle_enter() after its last use of RCU before the CPU is put - * to sleep. - * - rcu_idle_exit() before the first use of RCU after the CPU is woken up. + * Called when we start the idle loop. */ void tick_nohz_idle_enter(void) { @@ -984,7 +1023,7 @@ void tick_nohz_idle_enter(void) /* * Update the idle state in the scheduler domain hierarchy - * when tick_nohz_stop_sched_tick() is called from the idle loop. + * when tick_nohz_stop_tick() is called from the idle loop. * State will be updated to busy during the first busy tick after * exiting idle. */ @@ -993,8 +1032,11 @@ void tick_nohz_idle_enter(void) local_irq_disable(); ts = this_cpu_ptr(&tick_cpu_sched); + + WARN_ON_ONCE(ts->timer_expires_base); + ts->inidle = 1; - __tick_nohz_idle_enter(ts); + tick_nohz_start_idle(ts); local_irq_enable(); } @@ -1012,21 +1054,62 @@ void tick_nohz_irq_exit(void) struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); if (ts->inidle) - __tick_nohz_idle_enter(ts); + tick_nohz_start_idle(ts); else tick_nohz_full_update_tick(ts); } /** - * tick_nohz_get_sleep_length - return the length of the current sleep + * tick_nohz_idle_got_tick - Check whether or not the tick handler has run + */ +bool tick_nohz_idle_got_tick(void) +{ + struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); + + if (ts->inidle > 1) { + ts->inidle = 1; + return true; + } + return false; +} + +/** + * tick_nohz_get_sleep_length - return the expected length of the current sleep + * @delta_next: duration until the next event if the tick cannot be stopped * * Called from power state control code with interrupts disabled */ -ktime_t tick_nohz_get_sleep_length(void) +ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next) { + struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); + int cpu = smp_processor_id(); + /* + * The idle entry time is expected to be a sufficient approximation of + * the current time at this point. + */ + ktime_t now = ts->idle_entrytime; + ktime_t next_event; + + WARN_ON_ONCE(!ts->inidle); + + *delta_next = ktime_sub(dev->next_event, now); - return ts->sleep_length; + if (!can_stop_idle_tick(cpu, ts)) + return *delta_next; + + next_event = tick_nohz_next_event(ts, cpu); + if (!next_event) + return *delta_next; + + /* + * If the next highres timer to expire is earlier than next_event, the + * idle governor needs to know that. + */ + next_event = min_t(u64, next_event, + hrtimer_next_event_without(&ts->sched_timer)); + + return ktime_sub(next_event, now); } /** @@ -1075,6 +1158,20 @@ static void tick_nohz_account_idle_ticks(struct tick_sched *ts) #endif } +static void __tick_nohz_idle_restart_tick(struct tick_sched *ts, ktime_t now) +{ + tick_nohz_restart_sched_tick(ts, now); + tick_nohz_account_idle_ticks(ts); +} + +void tick_nohz_idle_restart_tick(void) +{ + struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); + + if (ts->tick_stopped) + __tick_nohz_idle_restart_tick(ts, ktime_get()); +} + /** * tick_nohz_idle_exit - restart the idle tick from the idle task * @@ -1090,6 +1187,7 @@ void tick_nohz_idle_exit(void) local_irq_disable(); WARN_ON_ONCE(!ts->inidle); + WARN_ON_ONCE(ts->timer_expires_base); ts->inidle = 0; @@ -1099,10 +1197,8 @@ void tick_nohz_idle_exit(void) if (ts->idle_active) tick_nohz_stop_idle(ts, now); - if (ts->tick_stopped) { - tick_nohz_restart_sched_tick(ts, now); - tick_nohz_account_idle_ticks(ts); - } + if (ts->tick_stopped) + __tick_nohz_idle_restart_tick(ts, now); local_irq_enable(); } @@ -1116,6 +1212,9 @@ static void tick_nohz_handler(struct clock_event_device *dev) struct pt_regs *regs = get_irq_regs(); ktime_t now = ktime_get(); + if (ts->inidle) + ts->inidle = 2; + dev->next_event = KTIME_MAX; tick_sched_do_timer(now); @@ -1213,6 +1312,9 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer) struct pt_regs *regs = get_irq_regs(); ktime_t now = ktime_get(); + if (ts->inidle) + ts->inidle = 2; + tick_sched_do_timer(now); /* diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h index 954b43dbf21c..2b845f2c44b1 100644 --- a/kernel/time/tick-sched.h +++ b/kernel/time/tick-sched.h @@ -38,7 +38,8 @@ enum tick_nohz_mode { * @idle_exittime: Time when the idle state was left * @idle_sleeptime: Sum of the time slept in idle with sched tick stopped * @iowait_sleeptime: Sum of the time slept in idle with sched tick stopped, with IO outstanding - * @sleep_length: Duration of the current idle sleep + * @timer_expires: Anticipated timer expiration time (in case sched tick is stopped) + * @timer_expires_base: Base time clock monotonic for @timer_expires * @do_timer_lst: CPU was the last one doing do_timer before going idle */ struct tick_sched { @@ -58,8 +59,9 @@ struct tick_sched { ktime_t idle_exittime; ktime_t idle_sleeptime; ktime_t iowait_sleeptime; - ktime_t sleep_length; unsigned long last_jiffies; + u64 timer_expires; + u64 timer_expires_base; u64 next_timer; ktime_t idle_expires; int do_timer_last; diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 4ad6f6ca18c1..3ec4922a2655 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -73,6 +73,9 @@ config EVENT_TRACING select GLOB bool +config GPU_TRACEPOINTS + bool + config CONTEXT_SWITCH_TRACER bool @@ -160,6 +163,17 @@ config FUNCTION_GRAPH_TRACER address on the current task structure into a stack of calls. +config PREEMPTIRQ_EVENTS + bool "Enable trace events for preempt and irq disable/enable" + select TRACE_IRQFLAGS + depends on DEBUG_PREEMPT || !PROVE_LOCKING + default n + help + Enable tracing of disable and enable events for preemption and irqs. + For tracing preempt disable/enable events, DEBUG_PREEMPT must be + enabled. For tracing irq disable/enable events, PROVE_LOCKING must + be disabled. + config IRQSOFF_TRACER bool "Interrupts-off Latency Tracer" default n diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 19a15b2f1190..803e38a33bbc 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -35,6 +35,7 @@ obj-$(CONFIG_TRACING) += trace_printk.o obj-$(CONFIG_TRACING_MAP) += tracing_map.o obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o +obj-$(CONFIG_PREEMPTIRQ_EVENTS) += trace_irqsoff.o obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o @@ -68,6 +69,7 @@ obj-$(CONFIG_KGDB_KDB) += trace_kdb.o endif obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o obj-$(CONFIG_UPROBE_EVENTS) += trace_uprobe.o +obj-$(CONFIG_GPU_TRACEPOINTS) += gpu-traces.o obj-$(CONFIG_TRACEPOINT_BENCHMARK) += trace_benchmark.o diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 8a8d92a8045b..5cc253f8fbf7 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -123,8 +123,9 @@ static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *regs); #else /* See comment below, where ftrace_ops_list_func is defined */ -static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip); -#define ftrace_ops_list_func ((ftrace_func_t)ftrace_ops_no_ops) +static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs); +#define ftrace_ops_list_func ftrace_ops_no_ops #endif /* @@ -5612,9 +5613,9 @@ static int ftrace_cmp_ips(const void *a, const void *b) return 0; } -static int ftrace_process_locs(struct module *mod, - unsigned long *start, - unsigned long *end) +static int __norecordmcount ftrace_process_locs(struct module *mod, + unsigned long *start, + unsigned long *end) { struct ftrace_page *start_pg; struct ftrace_page *pg; @@ -6139,7 +6140,8 @@ static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, } NOKPROBE_SYMBOL(ftrace_ops_list_func); #else -static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip) +static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs) { __ftrace_ops_list_func(ip, parent_ip, NULL, NULL); } @@ -6606,14 +6608,17 @@ void ftrace_graph_graph_time_control(bool enable) fgraph_graph_time = enable; } +void ftrace_graph_return_stub(struct ftrace_graph_ret *trace) +{ +} + int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace) { return 0; } /* The callbacks that hook a function */ -trace_func_graph_ret_t ftrace_graph_return = - (trace_func_graph_ret_t)ftrace_stub; +trace_func_graph_ret_t ftrace_graph_return = ftrace_graph_return_stub; trace_func_graph_ent_t ftrace_graph_entry = ftrace_graph_entry_stub; static trace_func_graph_ent_t __ftrace_graph_entry = ftrace_graph_entry_stub; @@ -6841,7 +6846,7 @@ void unregister_ftrace_graph(void) goto out; ftrace_graph_active--; - ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub; + ftrace_graph_return = ftrace_graph_return_stub; ftrace_graph_entry = ftrace_graph_entry_stub; __ftrace_graph_entry = ftrace_graph_entry_stub; ftrace_shutdown(&graph_ops, FTRACE_STOP_FUNC_RET); diff --git a/kernel/trace/gpu-traces.c b/kernel/trace/gpu-traces.c new file mode 100644 index 000000000000..a4b3f00faee3 --- /dev/null +++ b/kernel/trace/gpu-traces.c @@ -0,0 +1,23 @@ +/* + * GPU tracepoints + * + * Copyright (C) 2013 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/module.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/gpu.h> + +EXPORT_TRACEPOINT_SYMBOL(gpu_sched_switch); +EXPORT_TRACEPOINT_SYMBOL(gpu_job_enqueue); diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 72d0d477f5c1..c7530f4556ef 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -66,6 +66,9 @@ struct fgraph_data { #define TRACE_GRAPH_INDENT 2 +/* Flag options */ +#define TRACE_GRAPH_PRINT_FLAT 0x80 + unsigned int fgraph_max_depth; static struct tracer_opt trace_opts[] = { @@ -89,6 +92,8 @@ static struct tracer_opt trace_opts[] = { { TRACER_OPT(sleep-time, TRACE_GRAPH_SLEEP_TIME) }, /* Include time within nested functions */ { TRACER_OPT(graph-time, TRACE_GRAPH_GRAPH_TIME) }, + /* Use standard trace formatting rather than hierarchical */ + { TRACER_OPT(funcgraph-flat, TRACE_GRAPH_PRINT_FLAT) }, { } /* Empty entry */ }; @@ -1251,6 +1256,9 @@ print_graph_function_flags(struct trace_iterator *iter, u32 flags) int cpu = iter->cpu; int ret; + if (flags & TRACE_GRAPH_PRINT_FLAT) + return TRACE_TYPE_UNHANDLED; + if (data && per_cpu_ptr(data->cpu_data, cpu)->ignore) { per_cpu_ptr(data->cpu_data, cpu)->ignore = 0; return TRACE_TYPE_HANDLED; @@ -1308,13 +1316,6 @@ print_graph_function(struct trace_iterator *iter) return print_graph_function_flags(iter, tracer_flags.val); } -static enum print_line_t -print_graph_function_event(struct trace_iterator *iter, int flags, - struct trace_event *event) -{ - return print_graph_function(iter); -} - static void print_lat_header(struct seq_file *s, u32 flags) { static const char spaces[] = " " /* 16 spaces */ @@ -1383,6 +1384,11 @@ void print_graph_headers_flags(struct seq_file *s, u32 flags) struct trace_iterator *iter = s->private; struct trace_array *tr = iter->tr; + if (flags & TRACE_GRAPH_PRINT_FLAT) { + trace_default_header(s); + return; + } + if (!(tr->trace_flags & TRACE_ITER_CONTEXT_INFO)) return; @@ -1464,19 +1470,6 @@ func_graph_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) return 0; } -static struct trace_event_functions graph_functions = { - .trace = print_graph_function_event, -}; - -static struct trace_event graph_trace_entry_event = { - .type = TRACE_GRAPH_ENT, - .funcs = &graph_functions, -}; - -static struct trace_event graph_trace_ret_event = { - .type = TRACE_GRAPH_RET, - .funcs = &graph_functions -}; static struct tracer graph_trace __tracer_data = { .name = "function_graph", @@ -1553,16 +1546,6 @@ static __init int init_graph_trace(void) { max_bytes_for_cpu = snprintf(NULL, 0, "%u", nr_cpu_ids - 1); - if (!register_trace_event(&graph_trace_entry_event)) { - pr_warn("Warning: could not register graph trace events\n"); - return 1; - } - - if (!register_trace_event(&graph_trace_ret_event)) { - pr_warn("Warning: could not register graph trace events\n"); - return 1; - } - return register_tracer(&graph_trace); } diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 2d9e12380dc3..5b465b81cf86 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -16,6 +16,10 @@ #include "trace.h" +#define CREATE_TRACE_POINTS +#include <trace/events/preemptirq.h> + +#if defined(CONFIG_IRQSOFF_TRACER) || defined(CONFIG_PREEMPT_TRACER) static struct trace_array *irqsoff_trace __read_mostly; static int tracer_enabled __read_mostly; @@ -465,63 +469,43 @@ void time_hardirqs_off(unsigned long a0, unsigned long a1) #else /* !CONFIG_PROVE_LOCKING */ /* - * Stubs: - */ - -void trace_softirqs_on(unsigned long ip) -{ -} - -void trace_softirqs_off(unsigned long ip) -{ -} - -inline void print_irqtrace_events(struct task_struct *curr) -{ -} - -/* * We are only interested in hardirq on/off events: */ -void trace_hardirqs_on(void) +static inline void tracer_hardirqs_on(void) { if (!preempt_trace() && irq_trace()) stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1); } -EXPORT_SYMBOL(trace_hardirqs_on); -void trace_hardirqs_off(void) +static inline void tracer_hardirqs_off(void) { if (!preempt_trace() && irq_trace()) start_critical_timing(CALLER_ADDR0, CALLER_ADDR1); } -EXPORT_SYMBOL(trace_hardirqs_off); -__visible void trace_hardirqs_on_caller(unsigned long caller_addr) +static inline void tracer_hardirqs_on_caller(unsigned long caller_addr) { if (!preempt_trace() && irq_trace()) stop_critical_timing(CALLER_ADDR0, caller_addr); } -EXPORT_SYMBOL(trace_hardirqs_on_caller); -__visible void trace_hardirqs_off_caller(unsigned long caller_addr) +static inline void tracer_hardirqs_off_caller(unsigned long caller_addr) { if (!preempt_trace() && irq_trace()) start_critical_timing(CALLER_ADDR0, caller_addr); } -EXPORT_SYMBOL(trace_hardirqs_off_caller); #endif /* CONFIG_PROVE_LOCKING */ #endif /* CONFIG_IRQSOFF_TRACER */ #ifdef CONFIG_PREEMPT_TRACER -void trace_preempt_on(unsigned long a0, unsigned long a1) +static inline void tracer_preempt_on(unsigned long a0, unsigned long a1) { if (preempt_trace() && !irq_trace()) stop_critical_timing(a0, a1); } -void trace_preempt_off(unsigned long a0, unsigned long a1) +static inline void tracer_preempt_off(unsigned long a0, unsigned long a1) { if (preempt_trace() && !irq_trace()) start_critical_timing(a0, a1); @@ -783,3 +767,100 @@ __init static int init_irqsoff_tracer(void) return 0; } core_initcall(init_irqsoff_tracer); +#endif /* IRQSOFF_TRACER || PREEMPTOFF_TRACER */ + +#ifndef CONFIG_IRQSOFF_TRACER +static inline void tracer_hardirqs_on(void) { } +static inline void tracer_hardirqs_off(void) { } +static inline void tracer_hardirqs_on_caller(unsigned long caller_addr) { } +static inline void tracer_hardirqs_off_caller(unsigned long caller_addr) { } +#endif + +#ifndef CONFIG_PREEMPT_TRACER +static inline void tracer_preempt_on(unsigned long a0, unsigned long a1) { } +static inline void tracer_preempt_off(unsigned long a0, unsigned long a1) { } +#endif + +#if defined(CONFIG_TRACE_IRQFLAGS) && !defined(CONFIG_PROVE_LOCKING) +/* Per-cpu variable to prevent redundant calls when IRQs already off */ +static DEFINE_PER_CPU(int, tracing_irq_cpu); + +void trace_hardirqs_on(void) +{ + if (!this_cpu_read(tracing_irq_cpu)) + return; + + trace_irq_enable_rcuidle(CALLER_ADDR0, CALLER_ADDR1); + tracer_hardirqs_on(); + + this_cpu_write(tracing_irq_cpu, 0); +} +EXPORT_SYMBOL(trace_hardirqs_on); + +void trace_hardirqs_off(void) +{ + if (this_cpu_read(tracing_irq_cpu)) + return; + + this_cpu_write(tracing_irq_cpu, 1); + + trace_irq_disable_rcuidle(CALLER_ADDR0, CALLER_ADDR1); + tracer_hardirqs_off(); +} +EXPORT_SYMBOL(trace_hardirqs_off); + +__visible void trace_hardirqs_on_caller(unsigned long caller_addr) +{ + if (!this_cpu_read(tracing_irq_cpu)) + return; + + trace_irq_enable_rcuidle(CALLER_ADDR0, caller_addr); + tracer_hardirqs_on_caller(caller_addr); + + this_cpu_write(tracing_irq_cpu, 0); +} +EXPORT_SYMBOL(trace_hardirqs_on_caller); + +__visible void trace_hardirqs_off_caller(unsigned long caller_addr) +{ + if (this_cpu_read(tracing_irq_cpu)) + return; + + this_cpu_write(tracing_irq_cpu, 1); + + trace_irq_disable_rcuidle(CALLER_ADDR0, caller_addr); + tracer_hardirqs_off_caller(caller_addr); +} +EXPORT_SYMBOL(trace_hardirqs_off_caller); + +/* + * Stubs: + */ + +void trace_softirqs_on(unsigned long ip) +{ +} + +void trace_softirqs_off(unsigned long ip) +{ +} + +inline void print_irqtrace_events(struct task_struct *curr) +{ +} +#endif + +#if defined(CONFIG_PREEMPT_TRACER) || \ + (defined(CONFIG_DEBUG_PREEMPT) && defined(CONFIG_PREEMPTIRQ_EVENTS)) +void trace_preempt_on(unsigned long a0, unsigned long a1) +{ + trace_preempt_enable_rcuidle(a0, a1); + tracer_preempt_on(a0, a1); +} + +void trace_preempt_off(unsigned long a0, unsigned long a1) +{ + trace_preempt_disable_rcuidle(a0, a1); + tracer_preempt_off(a0, a1); +} +#endif diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 4500b00e4e36..416f7fead5fa 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -911,6 +911,174 @@ static struct trace_event trace_fn_event = { .funcs = &trace_fn_funcs, }; +/* TRACE_GRAPH_ENT */ +static enum print_line_t trace_graph_ent_trace(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct trace_seq *s = &iter->seq; + struct ftrace_graph_ent_entry *field; + + trace_assign_type(field, iter->ent); + + trace_seq_puts(s, "graph_ent: func="); + if (trace_seq_has_overflowed(s)) + return TRACE_TYPE_PARTIAL_LINE; + + if (!seq_print_ip_sym(s, field->graph_ent.func, flags)) + return TRACE_TYPE_PARTIAL_LINE; + + trace_seq_puts(s, "\n"); + if (trace_seq_has_overflowed(s)) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t trace_graph_ent_raw(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct ftrace_graph_ent_entry *field; + + trace_assign_type(field, iter->ent); + + trace_seq_printf(&iter->seq, "%lx %d\n", + field->graph_ent.func, + field->graph_ent.depth); + if (trace_seq_has_overflowed(&iter->seq)) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t trace_graph_ent_hex(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct ftrace_graph_ent_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + SEQ_PUT_HEX_FIELD(s, field->graph_ent.func); + SEQ_PUT_HEX_FIELD(s, field->graph_ent.depth); + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t trace_graph_ent_bin(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct ftrace_graph_ent_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + SEQ_PUT_FIELD(s, field->graph_ent.func); + SEQ_PUT_FIELD(s, field->graph_ent.depth); + + return TRACE_TYPE_HANDLED; +} + +static struct trace_event_functions trace_graph_ent_funcs = { + .trace = trace_graph_ent_trace, + .raw = trace_graph_ent_raw, + .hex = trace_graph_ent_hex, + .binary = trace_graph_ent_bin, +}; + +static struct trace_event trace_graph_ent_event = { + .type = TRACE_GRAPH_ENT, + .funcs = &trace_graph_ent_funcs, +}; + +/* TRACE_GRAPH_RET */ +static enum print_line_t trace_graph_ret_trace(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct trace_seq *s = &iter->seq; + struct trace_entry *entry = iter->ent; + struct ftrace_graph_ret_entry *field; + + trace_assign_type(field, entry); + + trace_seq_puts(s, "graph_ret: func="); + if (trace_seq_has_overflowed(s)) + return TRACE_TYPE_PARTIAL_LINE; + + if (!seq_print_ip_sym(s, field->ret.func, flags)) + return TRACE_TYPE_PARTIAL_LINE; + + trace_seq_puts(s, "\n"); + if (trace_seq_has_overflowed(s)) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t trace_graph_ret_raw(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct ftrace_graph_ret_entry *field; + + trace_assign_type(field, iter->ent); + + trace_seq_printf(&iter->seq, "%lx %lld %lld %ld %d\n", + field->ret.func, + field->ret.calltime, + field->ret.rettime, + field->ret.overrun, + field->ret.depth); + if (trace_seq_has_overflowed(&iter->seq)) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t trace_graph_ret_hex(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct ftrace_graph_ret_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + SEQ_PUT_HEX_FIELD(s, field->ret.func); + SEQ_PUT_HEX_FIELD(s, field->ret.calltime); + SEQ_PUT_HEX_FIELD(s, field->ret.rettime); + SEQ_PUT_HEX_FIELD(s, field->ret.overrun); + SEQ_PUT_HEX_FIELD(s, field->ret.depth); + + return TRACE_TYPE_HANDLED; +} + +static enum print_line_t trace_graph_ret_bin(struct trace_iterator *iter, int flags, + struct trace_event *event) +{ + struct ftrace_graph_ret_entry *field; + struct trace_seq *s = &iter->seq; + + trace_assign_type(field, iter->ent); + + SEQ_PUT_FIELD(s, field->ret.func); + SEQ_PUT_FIELD(s, field->ret.calltime); + SEQ_PUT_FIELD(s, field->ret.rettime); + SEQ_PUT_FIELD(s, field->ret.overrun); + SEQ_PUT_FIELD(s, field->ret.depth); + + return TRACE_TYPE_HANDLED; +} + +static struct trace_event_functions trace_graph_ret_funcs = { + .trace = trace_graph_ret_trace, + .raw = trace_graph_ret_raw, + .hex = trace_graph_ret_hex, + .binary = trace_graph_ret_bin, +}; + +static struct trace_event trace_graph_ret_event = { + .type = TRACE_GRAPH_RET, + .funcs = &trace_graph_ret_funcs, +}; + /* TRACE_CTX an TRACE_WAKE */ static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter, char *delim) @@ -1382,6 +1550,8 @@ static struct trace_event trace_raw_data_event = { static struct trace_event *events[] __initdata = { &trace_fn_event, + &trace_graph_ent_event, + &trace_graph_ret_event, &trace_ctx_event, &trace_wake_event, &trace_stack_event, diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index fdf2ea4d64ec..10d13fdcabf4 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -611,7 +611,7 @@ static int probes_seq_show(struct seq_file *m, void *v) /* Don't print "0x (null)" when offset is 0 */ if (tu->offset) { - seq_printf(m, "0x%p", (void *)tu->offset); + seq_printf(m, "0x%px", (void *)tu->offset); } else { switch (sizeof(void *)) { case 4: diff --git a/kernel/user.c b/kernel/user.c index 00281add65b2..1a689bf21ae8 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -17,6 +17,7 @@ #include <linux/interrupt.h> #include <linux/export.h> #include <linux/user_namespace.h> +#include <linux/proc_fs.h> #include <linux/proc_ns.h> /* @@ -202,6 +203,7 @@ struct user_struct *alloc_uid(kuid_t uid) } spin_unlock_irq(&uidhash_lock); } + proc_register_uid(uid); return up; @@ -223,6 +225,7 @@ static int __init uid_cache_init(void) spin_lock_irq(&uidhash_lock); uid_hash_insert(&root_user, uidhashentry(GLOBAL_ROOT_UID)); spin_unlock_irq(&uidhash_lock); + proc_register_uid(GLOBAL_ROOT_UID); return 0; } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 18fae55713b0..96f71d3c9f17 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -912,6 +912,26 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task) } /** + * wq_worker_last_func - retrieve worker's last work function + * + * Determine the last function a worker executed. This is called from + * the scheduler to get a worker's last known identity. + * + * CONTEXT: + * spin_lock_irq(rq->lock) + * + * Return: + * The last work function %current executed as a worker, NULL if it + * hasn't executed any work yet. + */ +work_func_t wq_worker_last_func(struct task_struct *task) +{ + struct worker *worker = kthread_data(task); + + return worker->last_func; +} + +/** * worker_set_flags - set worker flags and adjust nr_running accordingly * @worker: self * @flags: flags to set @@ -2147,6 +2167,9 @@ __acquires(&pool->lock) if (unlikely(cpu_intensive)) worker_clr_flags(worker, WORKER_CPU_INTENSIVE); + /* tag the worker for identification in schedule() */ + worker->last_func = worker->current_func; + /* we're done with it, release */ hash_del(&worker->hentry); worker->current_work = NULL; diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h index d390d1be3748..f8f5fd8df88f 100644 --- a/kernel/workqueue_internal.h +++ b/kernel/workqueue_internal.h @@ -54,6 +54,9 @@ struct worker { /* used only by rescuers to point to the target workqueue */ struct workqueue_struct *rescue_wq; /* I: the workqueue to rescue */ + + /* used by the scheduler to determine a worker's last known identity */ + work_func_t last_func; }; /** @@ -68,9 +71,10 @@ static inline struct worker *current_wq_worker(void) /* * Scheduler hooks for concurrency managed workqueue. Only to be used from - * sched/core.c and workqueue.c. + * sched/ and workqueue.c. */ void wq_worker_waking_up(struct task_struct *task, int cpu); struct task_struct *wq_worker_sleeping(struct task_struct *task); +work_func_t wq_worker_last_func(struct task_struct *task); #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */ diff --git a/lib/Makefile b/lib/Makefile index ae2d261daec9..ba38a18ac8fe 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -31,7 +31,7 @@ endif lib-y := ctype.o string.o vsprintf.o cmdline.o \ rbtree.o radix-tree.o dump_stack.o timerqueue.o\ idr.o int_sqrt.o extable.o \ - sha1.o chacha20.o irq_regs.o argv_split.o \ + sha1.o chacha.o irq_regs.o argv_split.o \ flex_proportions.o ratelimit.o show_mem.o \ is_single_threaded.o plist.o decompress.o kobject_uevent.o \ earlycpio.o seq_buf.o siphash.o \ diff --git a/lib/chacha.c b/lib/chacha.c new file mode 100644 index 000000000000..a46d2832dbab --- /dev/null +++ b/lib/chacha.c @@ -0,0 +1,117 @@ +/* + * The "hash function" used as the core of the ChaCha stream cipher (RFC7539) + * + * Copyright (C) 2015 Martin Willi + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/export.h> +#include <linux/bitops.h> +#include <linux/cryptohash.h> +#include <asm/unaligned.h> +#include <crypto/chacha.h> + +static void chacha_permute(u32 *x, int nrounds) +{ + int i; + + /* whitelist the allowed round counts */ + WARN_ON_ONCE(nrounds != 20 && nrounds != 12); + + for (i = 0; i < nrounds; i += 2) { + x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 16); + x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 16); + x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 16); + x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 16); + + x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 12); + x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 12); + x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 12); + x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 12); + + x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 8); + x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 8); + x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 8); + x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 8); + + x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 7); + x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 7); + x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 7); + x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 7); + + x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 16); + x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 16); + x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 16); + x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 16); + + x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 12); + x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 12); + x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 12); + x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 12); + + x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 8); + x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 8); + x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 8); + x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 8); + + x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 7); + x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 7); + x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 7); + x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 7); + } +} + +/** + * chacha_block - generate one keystream block and increment block counter + * @state: input state matrix (16 32-bit words) + * @stream: output keystream block (64 bytes) + * @nrounds: number of rounds (20 or 12; 20 is recommended) + * + * This is the ChaCha core, a function from 64-byte strings to 64-byte strings. + * The caller has already converted the endianness of the input. This function + * also handles incrementing the block counter in the input matrix. + */ +void chacha_block(u32 *state, u8 *stream, int nrounds) +{ + u32 x[16]; + int i; + + memcpy(x, state, 64); + + chacha_permute(x, nrounds); + + for (i = 0; i < ARRAY_SIZE(x); i++) + put_unaligned_le32(x[i] + state[i], &stream[i * sizeof(u32)]); + + state[12]++; +} +EXPORT_SYMBOL(chacha_block); + +/** + * hchacha_block - abbreviated ChaCha core, for XChaCha + * @in: input state matrix (16 32-bit words) + * @out: output (8 32-bit words) + * @nrounds: number of rounds (20 or 12; 20 is recommended) + * + * HChaCha is the ChaCha equivalent of HSalsa and is an intermediate step + * towards XChaCha (see https://cr.yp.to/snuffle/xsalsa-20081128.pdf). HChaCha + * skips the final addition of the initial state, and outputs only certain words + * of the state. It should not be used for streaming directly. + */ +void hchacha_block(const u32 *in, u32 *out, int nrounds) +{ + u32 x[16]; + + memcpy(x, in, 64); + + chacha_permute(x, nrounds); + + memcpy(&out[0], &x[0], 16); + memcpy(&out[4], &x[12], 16); +} +EXPORT_SYMBOL(hchacha_block); diff --git a/lib/chacha20.c b/lib/chacha20.c deleted file mode 100644 index 250ceed9ec9a..000000000000 --- a/lib/chacha20.c +++ /dev/null @@ -1,79 +0,0 @@ -/* - * ChaCha20 256-bit cipher algorithm, RFC7539 - * - * Copyright (C) 2015 Martin Willi - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ - -#include <linux/kernel.h> -#include <linux/export.h> -#include <linux/bitops.h> -#include <linux/cryptohash.h> -#include <asm/unaligned.h> -#include <crypto/chacha20.h> - -static inline u32 rotl32(u32 v, u8 n) -{ - return (v << n) | (v >> (sizeof(v) * 8 - n)); -} - -extern void chacha20_block(u32 *state, void *stream) -{ - u32 x[16], *out = stream; - int i; - - for (i = 0; i < ARRAY_SIZE(x); i++) - x[i] = state[i]; - - for (i = 0; i < 20; i += 2) { - x[0] += x[4]; x[12] = rotl32(x[12] ^ x[0], 16); - x[1] += x[5]; x[13] = rotl32(x[13] ^ x[1], 16); - x[2] += x[6]; x[14] = rotl32(x[14] ^ x[2], 16); - x[3] += x[7]; x[15] = rotl32(x[15] ^ x[3], 16); - - x[8] += x[12]; x[4] = rotl32(x[4] ^ x[8], 12); - x[9] += x[13]; x[5] = rotl32(x[5] ^ x[9], 12); - x[10] += x[14]; x[6] = rotl32(x[6] ^ x[10], 12); - x[11] += x[15]; x[7] = rotl32(x[7] ^ x[11], 12); - - x[0] += x[4]; x[12] = rotl32(x[12] ^ x[0], 8); - x[1] += x[5]; x[13] = rotl32(x[13] ^ x[1], 8); - x[2] += x[6]; x[14] = rotl32(x[14] ^ x[2], 8); - x[3] += x[7]; x[15] = rotl32(x[15] ^ x[3], 8); - - x[8] += x[12]; x[4] = rotl32(x[4] ^ x[8], 7); - x[9] += x[13]; x[5] = rotl32(x[5] ^ x[9], 7); - x[10] += x[14]; x[6] = rotl32(x[6] ^ x[10], 7); - x[11] += x[15]; x[7] = rotl32(x[7] ^ x[11], 7); - - x[0] += x[5]; x[15] = rotl32(x[15] ^ x[0], 16); - x[1] += x[6]; x[12] = rotl32(x[12] ^ x[1], 16); - x[2] += x[7]; x[13] = rotl32(x[13] ^ x[2], 16); - x[3] += x[4]; x[14] = rotl32(x[14] ^ x[3], 16); - - x[10] += x[15]; x[5] = rotl32(x[5] ^ x[10], 12); - x[11] += x[12]; x[6] = rotl32(x[6] ^ x[11], 12); - x[8] += x[13]; x[7] = rotl32(x[7] ^ x[8], 12); - x[9] += x[14]; x[4] = rotl32(x[4] ^ x[9], 12); - - x[0] += x[5]; x[15] = rotl32(x[15] ^ x[0], 8); - x[1] += x[6]; x[12] = rotl32(x[12] ^ x[1], 8); - x[2] += x[7]; x[13] = rotl32(x[13] ^ x[2], 8); - x[3] += x[4]; x[14] = rotl32(x[14] ^ x[3], 8); - - x[10] += x[15]; x[5] = rotl32(x[5] ^ x[10], 7); - x[11] += x[12]; x[6] = rotl32(x[6] ^ x[11], 7); - x[8] += x[13]; x[7] = rotl32(x[7] ^ x[8], 7); - x[9] += x[14]; x[4] = rotl32(x[4] ^ x[9], 7); - } - - for (i = 0; i < ARRAY_SIZE(x); i++) - out[i] = cpu_to_le32(x[i] + state[i]); - - state[12]++; -} -EXPORT_SYMBOL(chacha20_block); diff --git a/lib/test_printf.c b/lib/test_printf.c index 563f10e6876a..71ebfa43ad05 100644 --- a/lib/test_printf.c +++ b/lib/test_printf.c @@ -24,24 +24,6 @@ #define PAD_SIZE 16 #define FILL_CHAR '$' -#define PTR1 ((void*)0x01234567) -#define PTR2 ((void*)(long)(int)0xfedcba98) - -#if BITS_PER_LONG == 64 -#define PTR1_ZEROES "000000000" -#define PTR1_SPACES " " -#define PTR1_STR "1234567" -#define PTR2_STR "fffffffffedcba98" -#define PTR_WIDTH 16 -#else -#define PTR1_ZEROES "0" -#define PTR1_SPACES " " -#define PTR1_STR "1234567" -#define PTR2_STR "fedcba98" -#define PTR_WIDTH 8 -#endif -#define PTR_WIDTH_STR stringify(PTR_WIDTH) - static unsigned total_tests __initdata; static unsigned failed_tests __initdata; static char *test_buffer __initdata; @@ -217,30 +199,79 @@ test_string(void) test("a | | ", "%-3.s|%-3.0s|%-3.*s", "a", "b", 0, "c"); } +#define PLAIN_BUF_SIZE 64 /* leave some space so we don't oops */ + +#if BITS_PER_LONG == 64 + +#define PTR_WIDTH 16 +#define PTR ((void *)0xffff0123456789ab) +#define PTR_STR "ffff0123456789ab" +#define ZEROS "00000000" /* hex 32 zero bits */ + +static int __init +plain_format(void) +{ + char buf[PLAIN_BUF_SIZE]; + int nchars; + + nchars = snprintf(buf, PLAIN_BUF_SIZE, "%p", PTR); + + if (nchars != PTR_WIDTH || strncmp(buf, ZEROS, strlen(ZEROS)) != 0) + return -1; + + return 0; +} + +#else + +#define PTR_WIDTH 8 +#define PTR ((void *)0x456789ab) +#define PTR_STR "456789ab" + +static int __init +plain_format(void) +{ + /* Format is implicitly tested for 32 bit machines by plain_hash() */ + return 0; +} + +#endif /* BITS_PER_LONG == 64 */ + +static int __init +plain_hash(void) +{ + char buf[PLAIN_BUF_SIZE]; + int nchars; + + nchars = snprintf(buf, PLAIN_BUF_SIZE, "%p", PTR); + + if (nchars != PTR_WIDTH || strncmp(buf, PTR_STR, PTR_WIDTH) == 0) + return -1; + + return 0; +} + +/* + * We can't use test() to test %p because we don't know what output to expect + * after an address is hashed. + */ static void __init plain(void) { - test(PTR1_ZEROES PTR1_STR " " PTR2_STR, "%p %p", PTR1, PTR2); - /* - * The field width is overloaded for some %p extensions to - * pass another piece of information. For plain pointers, the - * behaviour is slightly odd: One cannot pass either the 0 - * flag nor a precision to %p without gcc complaining, and if - * one explicitly gives a field width, the number is no longer - * zero-padded. - */ - test("|" PTR1_STR PTR1_SPACES " | " PTR1_SPACES PTR1_STR "|", - "|%-*p|%*p|", PTR_WIDTH+2, PTR1, PTR_WIDTH+2, PTR1); - test("|" PTR2_STR " | " PTR2_STR "|", - "|%-*p|%*p|", PTR_WIDTH+2, PTR2, PTR_WIDTH+2, PTR2); + int err; - /* - * Unrecognized %p extensions are treated as plain %p, but the - * alphanumeric suffix is ignored (that is, does not occur in - * the output.) - */ - test("|"PTR1_ZEROES PTR1_STR"|", "|%p0y|", PTR1); - test("|"PTR2_STR"|", "|%p0y|", PTR2); + err = plain_hash(); + if (err) { + pr_warn("plain 'p' does not appear to be hashed\n"); + failed_tests++; + return; + } + + err = plain_format(); + if (err) { + pr_warn("hashing plain 'p' has unexpected format\n"); + failed_tests++; + } } static void __init @@ -251,6 +282,7 @@ symbol_ptr(void) static void __init kernel_ptr(void) { + /* We can't test this without access to kptr_restrict. */ } static void __init diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 4a990f3fd345..ac1f232152f0 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -33,6 +33,8 @@ #include <linux/uuid.h> #include <linux/of.h> #include <net/addrconf.h> +#include <linux/siphash.h> +#include <linux/compiler.h> #ifdef CONFIG_BLOCK #include <linux/blkdev.h> #endif @@ -1343,6 +1345,59 @@ char *uuid_string(char *buf, char *end, const u8 *addr, return string(buf, end, uuid, spec); } +int kptr_restrict __read_mostly; + +static noinline_for_stack +char *restricted_pointer(char *buf, char *end, const void *ptr, + struct printf_spec spec) +{ + spec.base = 16; + spec.flags |= SMALL; + if (spec.field_width == -1) { + spec.field_width = 2 * sizeof(ptr); + spec.flags |= ZEROPAD; + } + + switch (kptr_restrict) { + case 0: + /* Always print %pK values */ + break; + case 1: { + const struct cred *cred; + + /* + * kptr_restrict==1 cannot be used in IRQ context + * because its test for CAP_SYSLOG would be meaningless. + */ + if (in_irq() || in_serving_softirq() || in_nmi()) + return string(buf, end, "pK-error", spec); + + /* + * Only print the real pointer value if the current + * process has CAP_SYSLOG and is running with the + * same credentials it started with. This is because + * access to files is checked at open() time, but %pK + * checks permission at read() time. We don't want to + * leak pointer values if a binary opens a file using + * %pK and then elevates privileges before reading it. + */ + cred = current_cred(); + if (!has_capability_noaudit(current, CAP_SYSLOG) || + !uid_eq(cred->euid, cred->uid) || + !gid_eq(cred->egid, cred->gid)) + ptr = NULL; + break; + } + case 2: + default: + /* Always print 0's for %pK */ + ptr = NULL; + break; + } + + return number(buf, end, (unsigned long)ptr, spec); +} + static noinline_for_stack char *netdev_bits(char *buf, char *end, const void *addr, const char *fmt) { @@ -1588,7 +1643,86 @@ char *device_node_string(char *buf, char *end, struct device_node *dn, return widen_string(buf, buf - buf_start, end, spec); } -int kptr_restrict __read_mostly; +static noinline_for_stack +char *pointer_string(char *buf, char *end, const void *ptr, + struct printf_spec spec) +{ + spec.base = 16; + spec.flags |= SMALL; + if (spec.field_width == -1) { + spec.field_width = 2 * sizeof(ptr); + spec.flags |= ZEROPAD; + } + + return number(buf, end, (unsigned long int)ptr, spec); +} + +static bool have_filled_random_ptr_key __read_mostly; +static siphash_key_t ptr_key __read_mostly; + +static void fill_random_ptr_key(struct random_ready_callback *unused) +{ + get_random_bytes(&ptr_key, sizeof(ptr_key)); + /* + * have_filled_random_ptr_key==true is dependent on get_random_bytes(). + * ptr_to_id() needs to see have_filled_random_ptr_key==true + * after get_random_bytes() returns. + */ + smp_mb(); + WRITE_ONCE(have_filled_random_ptr_key, true); +} + +static struct random_ready_callback random_ready = { + .func = fill_random_ptr_key +}; + +static int __init initialize_ptr_random(void) +{ + int ret = add_random_ready_callback(&random_ready); + + if (!ret) { + return 0; + } else if (ret == -EALREADY) { + fill_random_ptr_key(&random_ready); + return 0; + } + + return ret; +} +early_initcall(initialize_ptr_random); + +/* Maps a pointer to a 32 bit unique identifier. */ +static char *ptr_to_id(char *buf, char *end, void *ptr, struct printf_spec spec) +{ + unsigned long hashval; + const int default_width = 2 * sizeof(ptr); + + if (unlikely(!have_filled_random_ptr_key)) { + spec.field_width = default_width; + /* string length must be less than default_width */ + return string(buf, end, "(ptrval)", spec); + } + +#ifdef CONFIG_64BIT + hashval = (unsigned long)siphash_1u64((u64)ptr, &ptr_key); + /* + * Mask off the first 32 bits, this makes explicit that we have + * modified the address (and 32 bits is plenty for a unique ID). + */ + hashval = hashval & 0xffffffff; +#else + hashval = (unsigned long)siphash_1u32((u32)ptr, &ptr_key); +#endif + + spec.flags |= SMALL; + if (spec.field_width == -1) { + spec.field_width = default_width; + spec.flags |= ZEROPAD; + } + spec.base = 16; + + return number(buf, end, hashval, spec); +} /* * Show a '%p' thing. A kernel extension is that the '%p' is followed @@ -1695,11 +1829,16 @@ int kptr_restrict __read_mostly; * c major compatible string * C full compatible string * + * - 'x' For printing the address. Equivalent to "%lx". + * * ** Please update also Documentation/printk-formats.txt when making changes ** * * Note: The difference between 'S' and 'F' is that on ia64 and ppc64 * function pointers are really function descriptors, which contain a * pointer to the real address. + * + * Note: The default behaviour (unadorned %p) is to hash the address, + * rendering it useful as a unique identifier. */ static noinline_for_stack char *pointer(const char *fmt, char *buf, char *end, void *ptr, @@ -1789,47 +1928,7 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr, return buf; } case 'K': - switch (kptr_restrict) { - case 0: - /* Always print %pK values */ - break; - case 1: { - const struct cred *cred; - - /* - * kptr_restrict==1 cannot be used in IRQ context - * because its test for CAP_SYSLOG would be meaningless. - */ - if (in_irq() || in_serving_softirq() || in_nmi()) { - if (spec.field_width == -1) - spec.field_width = default_width; - return string(buf, end, "pK-error", spec); - } - - /* - * Only print the real pointer value if the current - * process has CAP_SYSLOG and is running with the - * same credentials it started with. This is because - * access to files is checked at open() time, but %pK - * checks permission at read() time. We don't want to - * leak pointer values if a binary opens a file using - * %pK and then elevates privileges before reading it. - */ - cred = current_cred(); - if (!has_capability_noaudit(current, CAP_SYSLOG) || - !uid_eq(cred->euid, cred->uid) || - !gid_eq(cred->egid, cred->gid)) - ptr = NULL; - break; - } - case 2: - default: - /* Always print 0's for %pK */ - ptr = NULL; - break; - } - break; - + return restricted_pointer(buf, end, ptr, spec); case 'N': return netdev_bits(buf, end, ptr, fmt); case 'a': @@ -1854,15 +1953,12 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr, case 'F': return device_node_string(buf, end, ptr, spec, fmt + 1); } + case 'x': + return pointer_string(buf, end, ptr, spec); } - spec.flags |= SMALL; - if (spec.field_width == -1) { - spec.field_width = default_width; - spec.flags |= ZEROPAD; - } - spec.base = 16; - return number(buf, end, (unsigned long) ptr, spec); + /* default is to _not_ leak addresses, hash before printing */ + return ptr_to_id(buf, end, ptr, spec); } /* diff --git a/mm/compaction.c b/mm/compaction.c index eb8e7f5d3a08..a9d94eef4bf6 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -22,6 +22,7 @@ #include <linux/kthread.h> #include <linux/freezer.h> #include <linux/page_owner.h> +#include <linux/psi.h> #include "internal.h" #ifdef CONFIG_COMPACTION @@ -2029,11 +2030,15 @@ static int kcompactd(void *p) pgdat->kcompactd_classzone_idx = pgdat->nr_zones - 1; while (!kthread_should_stop()) { + unsigned long pflags; + trace_mm_compaction_kcompactd_sleep(pgdat->node_id); wait_event_freezable(pgdat->kcompactd_wait, kcompactd_work_requested(pgdat)); + psi_memstall_enter(&pflags); kcompactd_do_work(pgdat); + psi_memstall_leave(&pflags); } return 0; diff --git a/mm/debug.c b/mm/debug.c index c55abc893fdc..97609290dd51 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -50,7 +50,7 @@ void __dump_page(struct page *page, const char *reason) */ int mapcount = PageSlab(page) ? 0 : page_mapcount(page); - pr_emerg("page:%p count:%d mapcount:%d mapping:%p index:%#lx", + pr_emerg("page:%px count:%d mapcount:%d mapping:%px index:%#lx", page, page_ref_count(page), mapcount, page->mapping, page_to_pgoff(page)); if (PageCompound(page)) @@ -69,7 +69,7 @@ void __dump_page(struct page *page, const char *reason) #ifdef CONFIG_MEMCG if (page->mem_cgroup) - pr_alert("page->mem_cgroup:%p\n", page->mem_cgroup); + pr_alert("page->mem_cgroup:%px\n", page->mem_cgroup); #endif } @@ -84,10 +84,10 @@ EXPORT_SYMBOL(dump_page); void dump_vma(const struct vm_area_struct *vma) { - pr_emerg("vma %p start %p end %p\n" - "next %p prev %p mm %p\n" - "prot %lx anon_vma %p vm_ops %p\n" - "pgoff %lx file %p private_data %p\n" + pr_emerg("vma %px start %px end %px\n" + "next %px prev %px mm %px\n" + "prot %lx anon_vma %px vm_ops %px\n" + "pgoff %lx file %px private_data %px\n" "flags: %#lx(%pGv)\n", vma, (void *)vma->vm_start, (void *)vma->vm_end, vma->vm_next, vma->vm_prev, vma->vm_mm, @@ -100,27 +100,27 @@ EXPORT_SYMBOL(dump_vma); void dump_mm(const struct mm_struct *mm) { - pr_emerg("mm %p mmap %p seqnum %llu task_size %lu\n" + pr_emerg("mm %px mmap %px seqnum %llu task_size %lu\n" #ifdef CONFIG_MMU - "get_unmapped_area %p\n" + "get_unmapped_area %px\n" #endif "mmap_base %lu mmap_legacy_base %lu highest_vm_end %lu\n" - "pgd %p mm_users %d mm_count %d nr_ptes %lu nr_pmds %lu map_count %d\n" + "pgd %px mm_users %d mm_count %d nr_ptes %lu nr_pmds %lu map_count %d\n" "hiwater_rss %lx hiwater_vm %lx total_vm %lx locked_vm %lx\n" "pinned_vm %lx data_vm %lx exec_vm %lx stack_vm %lx\n" "start_code %lx end_code %lx start_data %lx end_data %lx\n" "start_brk %lx brk %lx start_stack %lx\n" "arg_start %lx arg_end %lx env_start %lx env_end %lx\n" - "binfmt %p flags %lx core_state %p\n" + "binfmt %px flags %lx core_state %px\n" #ifdef CONFIG_AIO - "ioctx_table %p\n" + "ioctx_table %px\n" #endif #ifdef CONFIG_MEMCG - "owner %p " + "owner %px " #endif - "exe_file %p\n" + "exe_file %px\n" #ifdef CONFIG_MMU_NOTIFIER - "mmu_notifier_mm %p\n" + "mmu_notifier_mm %px\n" #endif #ifdef CONFIG_NUMA_BALANCING "numa_next_scan %lu numa_scan_offset %lu numa_scan_seq %d\n" diff --git a/mm/filemap.c b/mm/filemap.c index a30dbf93de99..ee283d76f44b 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -36,6 +36,8 @@ #include <linux/memcontrol.h> #include <linux/cleancache.h> #include <linux/rmap.h> +#include <linux/delayacct.h> +#include <linux/psi.h> #include "internal.h" #define CREATE_TRACE_POINTS @@ -421,19 +423,17 @@ static void __filemap_fdatawait_range(struct address_space *mapping, return; pagevec_init(&pvec, 0); - while ((index <= end) && - (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, - PAGECACHE_TAG_WRITEBACK, - min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1)) != 0) { + while (index <= end) { unsigned i; + nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, + end, PAGECACHE_TAG_WRITEBACK); + if (!nr_pages) + break; + for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; - /* until radix tree lookup accepts end_index */ - if (page->index > end) - continue; - wait_on_page_writeback(page); ClearPageError(page); } @@ -840,12 +840,9 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping, * data from the working set, only to cache data that will * get overwritten with something else, is a waste of memory. */ - if (!(gfp_mask & __GFP_WRITE) && - shadow && workingset_refault(shadow)) { - SetPageActive(page); - workingset_activation(page); - } else - ClearPageActive(page); + WARN_ON_ONCE(PageActive(page)); + if (!(gfp_mask & __GFP_WRITE) && shadow) + workingset_refault(page, shadow); lru_cache_add(page); } return ret; @@ -1001,8 +998,18 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, { struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; + bool thrashing = false; + unsigned long pflags; int ret = 0; + if (bit_nr == PG_locked && + !PageUptodate(page) && PageWorkingset(page)) { + if (!PageSwapBacked(page)) + delayacct_thrashing_start(); + psi_memstall_enter(&pflags); + thrashing = true; + } + init_wait(wait); wait->flags = lock ? WQ_FLAG_EXCLUSIVE : 0; wait->func = wake_page_function; @@ -1041,6 +1048,12 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, finish_wait(q, wait); + if (thrashing) { + if (!PageSwapBacked(page)) + delayacct_thrashing_end(); + psi_memstall_leave(&pflags); + } + /* * A signal could leave PageWaiters set. Clearing it here if * !waitqueue_active would be possible (by open-coding finish_wait), @@ -1449,7 +1462,10 @@ EXPORT_SYMBOL(find_lock_entry); * - FGP_CREAT: If page is not present then a new page is allocated using * @gfp_mask and added to the page cache and the VM's LRU * list. The page is returned locked and with an increased - * refcount. Otherwise, NULL is returned. + * refcount. + * - FGP_FOR_MMAP: Similar to FGP_CREAT, only we want to allow the caller to do + * its own locking dance if the page is already in cache, or unlock the page + * before returning if we had to add the page to pagecache. * * If FGP_LOCK or FGP_CREAT are specified then the function may sleep even * if the GFP flags specified for FGP_CREAT are atomic. @@ -1502,7 +1518,7 @@ no_page: if (!page) return NULL; - if (WARN_ON_ONCE(!(fgp_flags & FGP_LOCK))) + if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP)))) fgp_flags |= FGP_LOCK; /* Init accessed so avoid atomic mark_page_accessed later */ @@ -1516,6 +1532,13 @@ no_page: if (err == -EEXIST) goto repeat; } + + /* + * add_to_page_cache_lru locks the page, and for mmap we expect + * an unlocked page. + */ + if (page && (fgp_flags & FGP_FOR_MMAP)) + unlock_page(page); } return page; @@ -1776,9 +1799,10 @@ repeat: EXPORT_SYMBOL(find_get_pages_contig); /** - * find_get_pages_tag - find and return pages that match @tag + * find_get_pages_range_tag - find and return pages in given range matching @tag * @mapping: the address_space to search * @index: the starting page index + * @end: The final page index (inclusive) * @tag: the tag index * @nr_pages: the maximum number of pages * @pages: where the resulting pages are placed @@ -1786,8 +1810,9 @@ EXPORT_SYMBOL(find_get_pages_contig); * Like find_get_pages, except we only return pages which are tagged with * @tag. We update @index to index the next page for the traversal. */ -unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index, - int tag, unsigned int nr_pages, struct page **pages) +unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, + pgoff_t end, int tag, unsigned int nr_pages, + struct page **pages) { struct radix_tree_iter iter; void **slot; @@ -1800,6 +1825,9 @@ unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index, radix_tree_for_each_tagged(slot, &mapping->page_tree, &iter, *index, tag) { struct page *head, *page; + + if (iter.index > end) + break; repeat: page = radix_tree_deref_slot(slot); if (unlikely(!page)) @@ -1841,18 +1869,28 @@ repeat: } pages[ret] = page; - if (++ret == nr_pages) - break; + if (++ret == nr_pages) { + *index = pages[ret - 1]->index + 1; + goto out; + } } + /* + * We come here when we got at @end. We take care to not overflow the + * index @index as it confuses some of the callers. This breaks the + * iteration when there is page at index -1 but that is already broken + * anyway. + */ + if (end == (pgoff_t)-1) + *index = (pgoff_t)-1; + else + *index = end + 1; +out: rcu_read_unlock(); - if (ret) - *index = pages[ret - 1]->index + 1; - return ret; } -EXPORT_SYMBOL(find_get_pages_tag); +EXPORT_SYMBOL(find_get_pages_range_tag); /** * find_get_entries_tag - find and return entries that match @tag @@ -2277,62 +2315,98 @@ out: EXPORT_SYMBOL(generic_file_read_iter); #ifdef CONFIG_MMU -/** - * page_cache_read - adds requested page to the page cache if not already there - * @file: file to read - * @offset: page index - * @gfp_mask: memory allocation flags - * - * This adds the requested page to the page cache if it isn't already there, - * and schedules an I/O to read in its contents from disk. - */ -static int page_cache_read(struct file *file, pgoff_t offset, gfp_t gfp_mask) +#define MMAP_LOTSAMISS (100) +static struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, + struct file *fpin) { - struct address_space *mapping = file->f_mapping; - struct page *page; - int ret; + int flags = vmf->flags; - do { - page = __page_cache_alloc(gfp_mask|__GFP_COLD); - if (!page) - return -ENOMEM; + if (fpin) + return fpin; - ret = add_to_page_cache_lru(page, mapping, offset, gfp_mask); - if (ret == 0) - ret = mapping->a_ops->readpage(file, page); - else if (ret == -EEXIST) - ret = 0; /* losing race to add is OK */ + /* + * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or + * anything, so we only pin the file and drop the mmap_sem if only + * FAULT_FLAG_ALLOW_RETRY is set. + */ + if ((flags & (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT)) == + FAULT_FLAG_ALLOW_RETRY) { + fpin = get_file(vmf->vma->vm_file); + up_read(&vmf->vma->vm_mm->mmap_sem); + } + return fpin; +} - put_page(page); +/* + * lock_page_maybe_drop_mmap - lock the page, possibly dropping the mmap_sem + * @vmf - the vm_fault for this fault. + * @page - the page to lock. + * @fpin - the pointer to the file we may pin (or is already pinned). + * + * This works similar to lock_page_or_retry in that it can drop the mmap_sem. + * It differs in that it actually returns the page locked if it returns 1 and 0 + * if it couldn't lock the page. If we did have to drop the mmap_sem then fpin + * will point to the pinned file and needs to be fput()'ed at a later point. + */ +static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page, + struct file **fpin) +{ + if (trylock_page(page)) + return 1; - } while (ret == AOP_TRUNCATED_PAGE); + /* + * NOTE! This will make us return with VM_FAULT_RETRY, but with + * the mmap_sem still held. That's how FAULT_FLAG_RETRY_NOWAIT + * is supposed to work. We have way too many special cases.. + */ + if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) + return 0; - return ret; + *fpin = maybe_unlock_mmap_for_io(vmf, *fpin); + if (vmf->flags & FAULT_FLAG_KILLABLE) { + if (__lock_page_killable(page)) { + /* + * We didn't have the right flags to drop the mmap_sem, + * but all fault_handlers only check for fatal signals + * if we return VM_FAULT_RETRY, so we need to drop the + * mmap_sem here and return 0 if we don't have a fpin. + */ + if (*fpin == NULL) + up_read(&vmf->vma->vm_mm->mmap_sem); + return 0; + } + } else + __lock_page(page); + return 1; } -#define MMAP_LOTSAMISS (100) /* - * Synchronous readahead happens when we don't even find - * a page in the page cache at all. + * Synchronous readahead happens when we don't even find a page in the page + * cache at all. We don't want to perform IO under the mmap sem, so if we have + * to drop the mmap sem we return the file that was pinned in order for us to do + * that. If we didn't pin a file then we return NULL. The file that is + * returned needs to be fput()'ed when we're done with it. */ -static void do_sync_mmap_readahead(struct vm_area_struct *vma, - struct file_ra_state *ra, - struct file *file, - pgoff_t offset) +static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) { + struct file *file = vmf->vma->vm_file; + struct file_ra_state *ra = &file->f_ra; struct address_space *mapping = file->f_mapping; + struct file *fpin = NULL; + pgoff_t offset = vmf->pgoff; /* If we don't want any read-ahead, don't bother */ - if (vma->vm_flags & VM_RAND_READ) - return; + if (vmf->vma->vm_flags & VM_RAND_READ) + return fpin; if (!ra->ra_pages) - return; + return fpin; - if (vma->vm_flags & VM_SEQ_READ) { + if (vmf->vma->vm_flags & VM_SEQ_READ) { + fpin = maybe_unlock_mmap_for_io(vmf, fpin); page_cache_sync_readahead(mapping, ra, file, offset, ra->ra_pages); - return; + return fpin; } /* Avoid banging the cache line if not needed */ @@ -2344,37 +2418,44 @@ static void do_sync_mmap_readahead(struct vm_area_struct *vma, * stop bothering with read-ahead. It will only hurt. */ if (ra->mmap_miss > MMAP_LOTSAMISS) - return; + return fpin; /* * mmap read-around */ + fpin = maybe_unlock_mmap_for_io(vmf, fpin); ra->start = max_t(long, 0, offset - ra->ra_pages / 2); ra->size = ra->ra_pages; ra->async_size = ra->ra_pages / 4; ra_submit(ra, mapping, file); + return fpin; } /* * Asynchronous readahead happens when we find the page and PG_readahead, - * so we want to possibly extend the readahead further.. + * so we want to possibly extend the readahead further. We return the file that + * was pinned if we have to drop the mmap_sem in order to do IO. */ -static void do_async_mmap_readahead(struct vm_area_struct *vma, - struct file_ra_state *ra, - struct file *file, - struct page *page, - pgoff_t offset) +static struct file *do_async_mmap_readahead(struct vm_fault *vmf, + struct page *page) { + struct file *file = vmf->vma->vm_file; + struct file_ra_state *ra = &file->f_ra; struct address_space *mapping = file->f_mapping; + struct file *fpin = NULL; + pgoff_t offset = vmf->pgoff; /* If we don't want any read-ahead, don't bother */ - if (vma->vm_flags & VM_RAND_READ) - return; + if (vmf->vma->vm_flags & VM_RAND_READ) + return fpin; if (ra->mmap_miss > 0) ra->mmap_miss--; - if (PageReadahead(page)) + if (PageReadahead(page)) { + fpin = maybe_unlock_mmap_for_io(vmf, fpin); page_cache_async_readahead(mapping, ra, file, page, offset, ra->ra_pages); + } + return fpin; } /** @@ -2404,6 +2485,7 @@ int filemap_fault(struct vm_fault *vmf) { int error; struct file *file = vmf->vma->vm_file; + struct file *fpin = NULL; struct address_space *mapping = file->f_mapping; struct file_ra_state *ra = &file->f_ra; struct inode *inode = mapping->host; @@ -2425,23 +2507,26 @@ int filemap_fault(struct vm_fault *vmf) * We found the page, so try async readahead before * waiting for the lock. */ - do_async_mmap_readahead(vmf->vma, ra, file, page, offset); + fpin = do_async_mmap_readahead(vmf, page); } else if (!page) { /* No page in the page cache at all */ - do_sync_mmap_readahead(vmf->vma, ra, file, offset); count_vm_event(PGMAJFAULT); count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT); ret = VM_FAULT_MAJOR; + fpin = do_sync_mmap_readahead(vmf); retry_find: - page = find_get_page(mapping, offset); - if (!page) - goto no_cached_page; + page = pagecache_get_page(mapping, offset, + FGP_CREAT|FGP_FOR_MMAP, + vmf->gfp_mask); + if (!page) { + if (fpin) + goto out_retry; + return VM_FAULT_OOM; + } } - if (!lock_page_or_retry(page, vmf->vma->vm_mm, vmf->flags)) { - put_page(page); - return ret | VM_FAULT_RETRY; - } + if (!lock_page_maybe_drop_mmap(vmf, page, &fpin)) + goto out_retry; /* Did it get truncated? */ if (unlikely(page->mapping != mapping)) { @@ -2459,6 +2544,16 @@ retry_find: goto page_not_uptodate; /* + * We've made it this far and we had to drop our mmap_sem, now is the + * time to return to the upper layer and have it re-find the vma and + * redo the fault. + */ + if (fpin) { + unlock_page(page); + goto out_retry; + } + + /* * Found the page and have a reference on it. * We must recheck i_size under page lock. */ @@ -2472,30 +2567,6 @@ retry_find: vmf->page = page; return ret | VM_FAULT_LOCKED; -no_cached_page: - /* - * We're only likely to ever get here if MADV_RANDOM is in - * effect. - */ - error = page_cache_read(file, offset, vmf->gfp_mask); - - /* - * The page we want has now been added to the page cache. - * In the unlikely event that someone removed it in the - * meantime, we'll just come back here and read it again. - */ - if (error >= 0) - goto retry_find; - - /* - * An error return from page_cache_read can result if the - * system is low on memory, or a problem occurs while trying - * to schedule I/O. - */ - if (error == -ENOMEM) - return VM_FAULT_OOM; - return VM_FAULT_SIGBUS; - page_not_uptodate: /* * Umm, take care of errors if the page isn't up-to-date. @@ -2504,12 +2575,15 @@ page_not_uptodate: * and we need to check for errors. */ ClearPageError(page); + fpin = maybe_unlock_mmap_for_io(vmf, fpin); error = mapping->a_ops->readpage(file, page); if (!error) { wait_on_page_locked(page); if (!PageUptodate(page)) error = -EIO; } + if (fpin) + goto out_retry; put_page(page); if (!error || error == AOP_TRUNCATED_PAGE) @@ -2518,6 +2592,18 @@ page_not_uptodate: /* Things didn't work out. Return zero to tell the mm layer so. */ shrink_readahead_size_eio(file, ra); return VM_FAULT_SIGBUS; + +out_retry: + /* + * We dropped the mmap_sem, we need to return to the fault handler to + * re-find the vma and come back and find our hopefully still populated + * page. + */ + if (page) + put_page(page); + if (fpin) + fput(fpin); + return ret | VM_FAULT_RETRY; } EXPORT_SYMBOL(filemap_fault); @@ -2688,7 +2774,7 @@ static struct page *wait_on_page_read(struct page *page) static struct page *do_read_cache_page(struct address_space *mapping, pgoff_t index, - int (*filler)(void *, struct page *), + int (*filler)(struct file *, struct page *), void *data, gfp_t gfp) { @@ -2795,7 +2881,7 @@ out: */ struct page *read_cache_page(struct address_space *mapping, pgoff_t index, - int (*filler)(void *, struct page *), + int (*filler)(struct file *, struct page *), void *data) { return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping)); @@ -2817,7 +2903,7 @@ struct page *read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp) { - filler_t *filler = (filler_t *)mapping->a_ops->readpage; + filler_t *filler = mapping->a_ops->readpage; return do_read_cache_page(mapping, index, filler, NULL, gfp); } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 9f3d4f84032b..cef17d90421c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2355,6 +2355,7 @@ static void __split_huge_page_tail(struct page *head, int tail, (1L << PG_mlocked) | (1L << PG_uptodate) | (1L << PG_active) | + (1L << PG_workingset) | (1L << PG_locked) | (1L << PG_unevictable) | (1L << PG_dirty))); diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 6bcfb01ba038..410c8235e671 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -134,7 +134,7 @@ static void print_error_description(struct kasan_access_info *info) pr_err("BUG: KASAN: %s in %pS\n", bug_type, (void *)info->ip); - pr_err("%s of size %zu at addr %p by task %s/%d\n", + pr_err("%s of size %zu at addr %px by task %s/%d\n", info->is_write ? "Write" : "Read", info->access_size, info->access_addr, current->comm, task_pid_nr(current)); } @@ -206,7 +206,7 @@ static void describe_object_addr(struct kmem_cache *cache, void *object, const char *rel_type; int rel_bytes; - pr_err("The buggy address belongs to the object at %p\n" + pr_err("The buggy address belongs to the object at %px\n" " which belongs to the cache %s of size %d\n", object, cache->name, cache->object_size); @@ -225,7 +225,7 @@ static void describe_object_addr(struct kmem_cache *cache, void *object, } pr_err("The buggy address is located %d bytes %s of\n" - " %d-byte region [%p, %p)\n", + " %d-byte region [%px, %px)\n", rel_bytes, rel_type, cache->object_size, (void *)object_addr, (void *)(object_addr + cache->object_size)); } @@ -302,7 +302,7 @@ static void print_shadow_for_address(const void *addr) char shadow_buf[SHADOW_BYTES_PER_ROW]; snprintf(buffer, sizeof(buffer), - (i == 0) ? ">%p: " : " %p: ", kaddr); + (i == 0) ? ">%px: " : " %px: ", kaddr); /* * We should not pass a shadow pointer to generic * function, because generic functions may try to diff --git a/mm/madvise.c b/mm/madvise.c index 576b753be428..02c493890eec 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -138,7 +138,7 @@ static long madvise_behavior(struct vm_area_struct *vma, pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *prev = vma_merge(mm, *prev, start, end, new_flags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx); + vma->vm_userfaultfd_ctx, vma_get_anon_name(vma)); if (*prev) { vma = *prev; goto success; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index d857e4770cc8..576cda120d4a 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -755,7 +755,8 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, ((vmstart - vma->vm_start) >> PAGE_SHIFT); prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, - new_pol, vma->vm_userfaultfd_ctx); + new_pol, vma->vm_userfaultfd_ctx, + vma_get_anon_name(vma)); if (prev) { vma = prev; next = vma->vm_next; diff --git a/mm/migrate.c b/mm/migrate.c index 9a3ce8847308..e334b49592d6 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -671,6 +671,8 @@ void migrate_page_states(struct page *newpage, struct page *page) SetPageActive(newpage); } else if (TestClearPageUnevictable(page)) SetPageUnevictable(newpage); + if (PageWorkingset(page)) + SetPageWorkingset(newpage); if (PageChecked(page)) SetPageChecked(newpage); if (PageMappedToDisk(page)) diff --git a/mm/mlock.c b/mm/mlock.c index 1f9ee86672e8..94a11ac7c880 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -528,7 +528,7 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev, pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx); + vma->vm_userfaultfd_ctx, vma_get_anon_name(vma)); if (*prev) { vma = *prev; goto success; diff --git a/mm/mmap.c b/mm/mmap.c index 8c6ed06983f9..b036a7fd2c00 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -968,7 +968,8 @@ again: */ static inline int is_mergeable_vma(struct vm_area_struct *vma, struct file *file, unsigned long vm_flags, - struct vm_userfaultfd_ctx vm_userfaultfd_ctx) + struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + const char __user *anon_name) { /* * VM_SOFTDIRTY should not prevent from VMA merging, if we @@ -986,6 +987,8 @@ static inline int is_mergeable_vma(struct vm_area_struct *vma, return 0; if (!is_mergeable_vm_userfaultfd_ctx(vma, vm_userfaultfd_ctx)) return 0; + if (vma_get_anon_name(vma) != anon_name) + return 0; return 1; } @@ -1018,9 +1021,10 @@ static int can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff, - struct vm_userfaultfd_ctx vm_userfaultfd_ctx) + struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + const char __user *anon_name) { - if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) && + if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { if (vma->vm_pgoff == vm_pgoff) return 1; @@ -1039,9 +1043,10 @@ static int can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff, - struct vm_userfaultfd_ctx vm_userfaultfd_ctx) + struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + const char __user *anon_name) { - if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) && + if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { pgoff_t vm_pglen; vm_pglen = vma_pages(vma); @@ -1052,9 +1057,9 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, } /* - * Given a mapping request (addr,end,vm_flags,file,pgoff), figure out - * whether that can be merged with its predecessor or its successor. - * Or both (it neatly fills a hole). + * Given a mapping request (addr,end,vm_flags,file,pgoff,anon_name), + * figure out whether that can be merged with its predecessor or its + * successor. Or both (it neatly fills a hole). * * In most cases - when called for mmap, brk or mremap - [addr,end) is * certain not to be mapped by the time vma_merge is called; but when @@ -1096,7 +1101,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, unsigned long end, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t pgoff, struct mempolicy *policy, - struct vm_userfaultfd_ctx vm_userfaultfd_ctx) + struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + const char __user *anon_name) { pgoff_t pglen = (end - addr) >> PAGE_SHIFT; struct vm_area_struct *area, *next; @@ -1129,7 +1135,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, mpol_equal(vma_policy(prev), policy) && can_vma_merge_after(prev, vm_flags, anon_vma, file, pgoff, - vm_userfaultfd_ctx)) { + vm_userfaultfd_ctx, + anon_name)) { /* * OK, it can. Can we now merge in the successor as well? */ @@ -1138,7 +1145,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen, - vm_userfaultfd_ctx) && + vm_userfaultfd_ctx, + anon_name) && is_mergeable_anon_vma(prev->anon_vma, next->anon_vma, NULL)) { /* cases 1, 6 */ @@ -1161,7 +1169,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, mpol_equal(policy, vma_policy(next)) && can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen, - vm_userfaultfd_ctx)) { + vm_userfaultfd_ctx, + anon_name)) { if (prev && addr < prev->vm_end) /* case 4 */ err = __vma_adjust(prev, prev->vm_start, addr, prev->vm_pgoff, NULL, next); @@ -1673,7 +1682,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, * Can we just expand an old mapping? */ vma = vma_merge(mm, prev, addr, addr + len, vm_flags, - NULL, file, pgoff, NULL, NULL_VM_UFFD_CTX); + NULL, file, pgoff, NULL, NULL_VM_UFFD_CTX, NULL); if (vma) goto out; @@ -2747,6 +2756,7 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, return 0; } +EXPORT_SYMBOL(do_munmap); int vm_munmap(unsigned long start, size_t len) { @@ -2933,7 +2943,7 @@ static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long fla /* Can we just expand an old private anonymous mapping? */ vma = vma_merge(mm, prev, addr, addr + len, flags, - NULL, NULL, pgoff, NULL, NULL_VM_UFFD_CTX); + NULL, NULL, pgoff, NULL, NULL_VM_UFFD_CTX, NULL); if (vma) goto out; @@ -3134,7 +3144,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, return NULL; /* should never get here */ new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx); + vma->vm_userfaultfd_ctx, vma_get_anon_name(vma)); if (new_vma) { /* * Source vma may have been merged into new_vma diff --git a/mm/mprotect.c b/mm/mprotect.c index 18ecbd744978..17c2890ca01f 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -418,7 +418,7 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *pprev = vma_merge(mm, *pprev, start, end, newflags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx); + vma->vm_userfaultfd_ctx, vma_get_anon_name(vma)); if (*pprev) { vma = *pprev; VM_WARN_ON((vma->vm_flags ^ newflags) & ~VM_SOFTDIRTY); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 29f9980c13ac..5b405e9a2b89 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2195,30 +2195,14 @@ int write_cache_pages(struct address_space *mapping, while (!done && (index <= end)) { int i; - nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag, - min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); + nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end, + tag); if (nr_pages == 0) break; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; - /* - * At this point, the page may be truncated or - * invalidated (changing page->mapping to NULL), or - * even swizzled back from swapper_space to tmpfs file - * mapping. However, page->index will not change - * because we have a reference on the page. - */ - if (page->index > end) { - /* - * can't be range_cyclic (1st pass) because - * end == -1 in that case. - */ - done = 1; - break; - } - done_index = page->index; lock_page(page); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e992afe3a58e..39e8e8b9a450 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -67,6 +67,7 @@ #include <linux/ftrace.h> #include <linux/lockdep.h> #include <linux/nmi.h> +#include <linux/psi.h> #include <asm/sections.h> #include <asm/tlbflush.h> @@ -258,10 +259,22 @@ compound_page_dtor * const compound_page_dtors[] = { #endif }; +/* + * Try to keep at least this much lowmem free. Do not allow normal + * allocations below this point, only high priority ones. Automatically + * tuned according to the amount of memory in the system. + */ int min_free_kbytes = 1024; int user_min_free_kbytes = -1; int watermark_scale_factor = 10; +/* + * Extra memory for the system to try freeing. Used to temporarily + * free memory, to make space for new workloads. Anyone can allocate + * down to the min watermarks controlled by min_free_kbytes above. + */ +int extra_free_kbytes = 0; + static unsigned long __meminitdata nr_kernel_pages; static unsigned long __meminitdata nr_all_pages; static unsigned long __meminitdata dma_reserve; @@ -3372,15 +3385,20 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, enum compact_priority prio, enum compact_result *compact_result) { struct page *page; + unsigned long pflags; unsigned int noreclaim_flag; if (!order) return NULL; + psi_memstall_enter(&pflags); noreclaim_flag = memalloc_noreclaim_save(); + *compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac, prio); + memalloc_noreclaim_restore(noreclaim_flag); + psi_memstall_leave(&pflags); if (*compact_result <= COMPACT_INACTIVE) return NULL; @@ -3569,11 +3587,13 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order, struct reclaim_state reclaim_state; int progress; unsigned int noreclaim_flag; + unsigned long pflags; cond_resched(); /* We now go into synchronous reclaim */ cpuset_memory_pressure_bump(); + psi_memstall_enter(&pflags); noreclaim_flag = memalloc_noreclaim_save(); fs_reclaim_acquire(gfp_mask); reclaim_state.reclaimed_slab = 0; @@ -3585,6 +3605,7 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order, current->reclaim_state = NULL; fs_reclaim_release(gfp_mask); memalloc_noreclaim_restore(noreclaim_flag); + psi_memstall_leave(&pflags); cond_resched(); @@ -6891,6 +6912,7 @@ static void setup_per_zone_lowmem_reserve(void) static void __setup_per_zone_wmarks(void) { unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10); + unsigned long pages_low = extra_free_kbytes >> (PAGE_SHIFT - 10); unsigned long lowmem_pages = 0; struct zone *zone; unsigned long flags; @@ -6902,11 +6924,14 @@ static void __setup_per_zone_wmarks(void) } for_each_zone(zone) { - u64 tmp; + u64 min, low; spin_lock_irqsave(&zone->lock, flags); - tmp = (u64)pages_min * zone->managed_pages; - do_div(tmp, lowmem_pages); + min = (u64)pages_min * zone->managed_pages; + do_div(min, lowmem_pages); + low = (u64)pages_low * zone->managed_pages; + do_div(low, vm_total_pages); + if (is_highmem(zone)) { /* * __GFP_HIGH and PF_MEMALLOC allocations usually don't @@ -6927,7 +6952,7 @@ static void __setup_per_zone_wmarks(void) * If it's a lowmem zone, reserve a number of pages * proportionate to the zone's size. */ - zone->watermark[WMARK_MIN] = tmp; + zone->watermark[WMARK_MIN] = min; } /* @@ -6935,12 +6960,14 @@ static void __setup_per_zone_wmarks(void) * scale factor in proportion to available memory, but * ensure a minimum size on small systems. */ - tmp = max_t(u64, tmp >> 2, + min = max_t(u64, min >> 2, mult_frac(zone->managed_pages, watermark_scale_factor, 10000)); - zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + tmp; - zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + tmp * 2; + zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + + low + min; + zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + + low + min * 2; spin_unlock_irqrestore(&zone->lock, flags); } @@ -7023,7 +7050,7 @@ core_initcall(init_per_zone_wmark_min) /* * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so * that we can call two helper functions whenever min_free_kbytes - * changes. + * or extra_free_kbytes changes. */ int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) diff --git a/mm/page_io.c b/mm/page_io.c index 5d882de3fbfd..9f8fd8f42b0d 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -22,6 +22,7 @@ #include <linux/writeback.h> #include <linux/frontswap.h> #include <linux/blkdev.h> +#include <linux/psi.h> #include <linux/uio.h> #include <linux/sched/task.h> #include <asm/pgtable.h> @@ -354,10 +355,19 @@ int swap_readpage(struct page *page, bool do_poll) struct swap_info_struct *sis = page_swap_info(page); blk_qc_t qc; struct gendisk *disk; + unsigned long pflags; VM_BUG_ON_PAGE(!PageSwapCache(page), page); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageUptodate(page), page); + + /* + * Count submission time as memory stall. When the device is congested, + * or the submitting cgroup IO-throttled, submission can be a + * significant part of overall IO time. + */ + psi_memstall_enter(&pflags); + if (frontswap_load(page) == 0) { SetPageUptodate(page); unlock_page(page); @@ -371,7 +381,7 @@ int swap_readpage(struct page *page, bool do_poll) ret = mapping->a_ops->readpage(swap_file, page); if (!ret) count_vm_event(PSWPIN); - return ret; + goto out; } ret = bdev_read_page(sis->bdev, swap_page_sector(page), page); @@ -382,7 +392,7 @@ int swap_readpage(struct page *page, bool do_poll) } count_vm_event(PSWPIN); - return 0; + goto out; } ret = 0; @@ -415,6 +425,7 @@ int swap_readpage(struct page *page, bool do_poll) bio_put(bio); out: + psi_memstall_leave(&pflags); return ret; } diff --git a/mm/readahead.c b/mm/readahead.c index 59aa0d06f254..bf9db0fa4506 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -81,7 +81,7 @@ static void read_cache_pages_invalidate_pages(struct address_space *mapping, * Hides the details of the LRU cache etc from the filesystems. */ int read_cache_pages(struct address_space *mapping, struct list_head *pages, - int (*filler)(void *, struct page *), void *data) + int (*filler)(struct file *, struct page *), void *data) { struct page *page; int ret = 0; diff --git a/mm/shmem.c b/mm/shmem.c index 24005c3b345c..7145492f93dd 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2153,6 +2153,25 @@ out_nomem: static int shmem_mmap(struct file *file, struct vm_area_struct *vma) { + struct shmem_inode_info *info = SHMEM_I(file_inode(file)); + + + if (info->seals & F_SEAL_FUTURE_WRITE) { + /* + * New PROT_WRITE and MAP_SHARED mmaps are not allowed when + * "future write" seal active. + */ + if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) + return -EPERM; + + /* + * Since the F_SEAL_FUTURE_WRITE seals allow for a MAP_SHARED + * read-only mapping, take care to not allow mprotect to revert + * protections. + */ + vma->vm_flags &= ~(VM_MAYWRITE); + } + file_accessed(file); vma->vm_ops = &shmem_vm_ops; if (IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE) && @@ -2406,8 +2425,9 @@ shmem_write_begin(struct file *file, struct address_space *mapping, pgoff_t index = pos >> PAGE_SHIFT; /* i_mutex is held by caller */ - if (unlikely(info->seals & (F_SEAL_WRITE | F_SEAL_GROW))) { - if (info->seals & F_SEAL_WRITE) + if (unlikely(info->seals & (F_SEAL_GROW | + F_SEAL_WRITE | F_SEAL_FUTURE_WRITE))) { + if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) return -EPERM; if ((info->seals & F_SEAL_GROW) && pos + len > inode->i_size) return -EPERM; @@ -2766,7 +2786,8 @@ continue_resched: #define F_ALL_SEALS (F_SEAL_SEAL | \ F_SEAL_SHRINK | \ F_SEAL_GROW | \ - F_SEAL_WRITE) + F_SEAL_WRITE | \ + F_SEAL_FUTURE_WRITE) int shmem_add_seals(struct file *file, unsigned int seals) { @@ -2893,7 +2914,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, DECLARE_WAIT_QUEUE_HEAD_ONSTACK(shmem_falloc_waitq); /* protected by i_mutex */ - if (info->seals & F_SEAL_WRITE) { + if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) { error = -EPERM; goto out; } @@ -4316,6 +4337,14 @@ struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags } EXPORT_SYMBOL_GPL(shmem_file_setup); +void shmem_set_file(struct vm_area_struct *vma, struct file *file) +{ + if (vma->vm_file) + fput(vma->vm_file); + vma->vm_file = file; + vma->vm_ops = &shmem_vm_ops; +} + /** * shmem_zero_setup - setup a shared anonymous mapping * @vma: the vma to be mmapped is prepared by do_mmap_pgoff @@ -4335,10 +4364,7 @@ int shmem_zero_setup(struct vm_area_struct *vma) if (IS_ERR(file)) return PTR_ERR(file); - if (vma->vm_file) - fput(vma->vm_file); - vma->vm_file = file; - vma->vm_ops = &shmem_vm_ops; + shmem_set_file(vma, file); if (IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE) && ((vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK) < diff --git a/mm/slab.c b/mm/slab.c index a04aeae42306..7f2c993df195 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1590,11 +1590,8 @@ static void print_objinfo(struct kmem_cache *cachep, void *objp, int lines) *dbg_redzone2(cachep, objp)); } - if (cachep->flags & SLAB_STORE_USER) { - pr_err("Last user: [<%p>](%pSR)\n", - *dbg_userword(cachep, objp), - *dbg_userword(cachep, objp)); - } + if (cachep->flags & SLAB_STORE_USER) + pr_err("Last user: (%pSR)\n", *dbg_userword(cachep, objp)); realobj = (char *)objp + obj_offset(cachep); size = cachep->object_size; for (i = 0; i < size && lines; i += 16, lines--) { @@ -1627,7 +1624,7 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp) /* Mismatch ! */ /* Print header */ if (lines == 0) { - pr_err("Slab corruption (%s): %s start=%p, len=%d\n", + pr_err("Slab corruption (%s): %s start=%px, len=%d\n", print_tainted(), cachep->name, realobj, size); print_objinfo(cachep, objp, 0); @@ -1656,13 +1653,13 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp) if (objnr) { objp = index_to_obj(cachep, page, objnr - 1); realobj = (char *)objp + obj_offset(cachep); - pr_err("Prev obj: start=%p, len=%d\n", realobj, size); + pr_err("Prev obj: start=%px, len=%d\n", realobj, size); print_objinfo(cachep, objp, 2); } if (objnr + 1 < cachep->num) { objp = index_to_obj(cachep, page, objnr + 1); realobj = (char *)objp + obj_offset(cachep); - pr_err("Next obj: start=%p, len=%d\n", realobj, size); + pr_err("Next obj: start=%px, len=%d\n", realobj, size); print_objinfo(cachep, objp, 2); } } @@ -2613,7 +2610,7 @@ static void slab_put_obj(struct kmem_cache *cachep, /* Verify double free bug */ for (i = page->active; i < cachep->num; i++) { if (get_free_obj(page, i) == objnr) { - pr_err("slab: double free detected in cache '%s', objp %p\n", + pr_err("slab: double free detected in cache '%s', objp %px\n", cachep->name, objp); BUG(); } @@ -2777,7 +2774,7 @@ static inline void verify_redzone_free(struct kmem_cache *cache, void *obj) else slab_error(cache, "memory outside object was overwritten"); - pr_err("%p: redzone 1:0x%llx, redzone 2:0x%llx\n", + pr_err("%px: redzone 1:0x%llx, redzone 2:0x%llx\n", obj, redzone1, redzone2); } @@ -3083,7 +3080,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, if (*dbg_redzone1(cachep, objp) != RED_INACTIVE || *dbg_redzone2(cachep, objp) != RED_INACTIVE) { slab_error(cachep, "double free, or memory outside object was overwritten"); - pr_err("%p: redzone 1:0x%llx, redzone 2:0x%llx\n", + pr_err("%px: redzone 1:0x%llx, redzone 2:0x%llx\n", objp, *dbg_redzone1(cachep, objp), *dbg_redzone2(cachep, objp)); } @@ -3096,7 +3093,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, cachep->ctor(objp); if (ARCH_SLAB_MINALIGN && ((unsigned long)objp & (ARCH_SLAB_MINALIGN-1))) { - pr_err("0x%p: not aligned to ARCH_SLAB_MINALIGN=%d\n", + pr_err("0x%px: not aligned to ARCH_SLAB_MINALIGN=%d\n", objp, (int)ARCH_SLAB_MINALIGN); } return objp; @@ -4294,7 +4291,7 @@ static void show_symbol(struct seq_file *m, unsigned long address) return; } #endif - seq_printf(m, "%p", (void *)address); + seq_printf(m, "%px", (void *)address); } static int leaks_show(struct seq_file *m, void *p) diff --git a/mm/swap.c b/mm/swap.c index a77d68f2c1b6..4edac536fe24 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -986,15 +986,25 @@ unsigned pagevec_lookup_range(struct pagevec *pvec, } EXPORT_SYMBOL(pagevec_lookup_range); -unsigned pagevec_lookup_tag(struct pagevec *pvec, struct address_space *mapping, - pgoff_t *index, int tag, unsigned nr_pages) +unsigned pagevec_lookup_range_tag(struct pagevec *pvec, + struct address_space *mapping, pgoff_t *index, pgoff_t end, + int tag) { - pvec->nr = find_get_pages_tag(mapping, index, tag, - nr_pages, pvec->pages); + pvec->nr = find_get_pages_range_tag(mapping, index, end, tag, + PAGEVEC_SIZE, pvec->pages); return pagevec_count(pvec); } -EXPORT_SYMBOL(pagevec_lookup_tag); +EXPORT_SYMBOL(pagevec_lookup_range_tag); +unsigned pagevec_lookup_range_nr_tag(struct pagevec *pvec, + struct address_space *mapping, pgoff_t *index, pgoff_t end, + int tag, unsigned max_pages) +{ + pvec->nr = find_get_pages_range_tag(mapping, index, end, tag, + min_t(unsigned int, max_pages, PAGEVEC_SIZE), pvec->pages); + return pagevec_count(pvec); +} +EXPORT_SYMBOL(pagevec_lookup_range_nr_tag); /* * Perform any setup for the swap system */ diff --git a/mm/swap_state.c b/mm/swap_state.c index 755be95d52f9..57ba716017ea 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -436,6 +436,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, /* * Initiate read into locked page and return. */ + SetPageWorkingset(new_page); lru_cache_add_anon(new_page); *new_page_allocated = true; return new_page; diff --git a/mm/usercopy.c b/mm/usercopy.c index f8d74e09f8e4..dd5f42afc3c4 100644 --- a/mm/usercopy.c +++ b/mm/usercopy.c @@ -59,12 +59,11 @@ static noinline int check_stack_object(const void *obj, unsigned long len) return GOOD_STACK; } -static void report_usercopy(const void *ptr, unsigned long len, - bool to_user, const char *type) +static void report_usercopy(unsigned long len, bool to_user, const char *type) { - pr_emerg("kernel memory %s attempt detected %s %p (%s) (%lu bytes)\n", + pr_emerg("kernel memory %s attempt detected %s '%s' (%lu bytes)\n", to_user ? "exposure" : "overwrite", - to_user ? "from" : "to", ptr, type ? : "unknown", len); + to_user ? "from" : "to", type ? : "unknown", len); /* * For greater effect, it would be nice to do do_group_exit(), * but BUG() actually hooks all the lock-breaking and per-arch @@ -267,6 +266,6 @@ void __check_object_size(const void *ptr, unsigned long n, bool to_user) return; report: - report_usercopy(ptr, n, to_user, err); + report_usercopy(n, to_user, err); } EXPORT_SYMBOL(__check_object_size); diff --git a/mm/vmscan.c b/mm/vmscan.c index c6962aa5ddb4..46c0231b5745 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -49,6 +49,7 @@ #include <linux/prefetch.h> #include <linux/printk.h> #include <linux/dax.h> +#include <linux/psi.h> #include <asm/tlbflush.h> #include <asm/div64.h> @@ -2065,6 +2066,7 @@ static void shrink_active_list(unsigned long nr_to_scan, } ClearPageActive(page); /* we are de-activating */ + SetPageWorkingset(page); list_add(&page->lru, &l_inactive); } @@ -3134,6 +3136,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, { struct zonelist *zonelist; unsigned long nr_reclaimed; + unsigned long pflags; int nid; unsigned int noreclaim_flag; struct scan_control sc = { @@ -3162,9 +3165,13 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, sc.gfp_mask, sc.reclaim_idx); + psi_memstall_enter(&pflags); noreclaim_flag = memalloc_noreclaim_save(); + nr_reclaimed = do_try_to_free_pages(zonelist, &sc); + memalloc_noreclaim_restore(noreclaim_flag); + psi_memstall_leave(&pflags); trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed); @@ -3329,6 +3336,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) int i; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; + unsigned long pflags; struct zone *zone; struct scan_control sc = { .gfp_mask = GFP_KERNEL, @@ -3338,6 +3346,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) .may_unmap = 1, .may_swap = 1, }; + psi_memstall_enter(&pflags); count_vm_event(PAGEOUTRUN); do { @@ -3432,6 +3441,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) out: snapshot_refaults(NULL, pgdat); + psi_memstall_leave(&pflags); /* * Return the order kswapd stopped reclaiming at as * prepare_kswapd_sleep() takes it into account. If another caller diff --git a/mm/vmstat.c b/mm/vmstat.c index e2197b03da57..e779d7c696b8 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1074,6 +1074,7 @@ const char * const vmstat_text[] = { "nr_isolated_file", "workingset_refault", "workingset_activate", + "workingset_restore", "workingset_nodereclaim", "nr_anon_pages", "nr_mapped", diff --git a/mm/workingset.c b/mm/workingset.c index b997c9de28f6..808a69a4a9ef 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -121,7 +121,7 @@ * the only thing eating into inactive list space is active pages. * * - * Activating refaulting pages + * Refaulting inactive pages * * All that is known about the active list is that the pages have been * accessed more than once in the past. This means that at any given @@ -134,6 +134,10 @@ * used less frequently than the refaulting page - or even not used at * all anymore. * + * That means if inactive cache is refaulting with a suitable refault + * distance, we assume the cache workingset is transitioning and put + * pressure on the current active list. + * * If this is wrong and demotion kicks in, the pages which are truly * used more frequently will be reactivated while the less frequently * used once will be evicted from memory. @@ -141,6 +145,14 @@ * But if this is right, the stale pages will be pushed out of memory * and the used pages get to stay in cache. * + * Refaulting active pages + * + * If on the other hand the refaulting pages have recently been + * deactivated, it means that the active list is no longer protecting + * actively used cache from reclaim. The cache is NOT transitioning to + * a different workingset; the existing workingset is thrashing in the + * space allocated to the page cache. + * * * Implementation * @@ -156,8 +168,7 @@ */ #define EVICTION_SHIFT (RADIX_TREE_EXCEPTIONAL_ENTRY + \ - NODES_SHIFT + \ - MEM_CGROUP_ID_SHIFT) + 1 + NODES_SHIFT + MEM_CGROUP_ID_SHIFT) #define EVICTION_MASK (~0UL >> EVICTION_SHIFT) /* @@ -170,23 +181,28 @@ */ static unsigned int bucket_order __read_mostly; -static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction) +static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction, + bool workingset) { eviction >>= bucket_order; eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid; eviction = (eviction << NODES_SHIFT) | pgdat->node_id; + eviction = (eviction << 1) | workingset; eviction = (eviction << RADIX_TREE_EXCEPTIONAL_SHIFT); return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY); } static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, - unsigned long *evictionp) + unsigned long *evictionp, bool *workingsetp) { unsigned long entry = (unsigned long)shadow; int memcgid, nid; + bool workingset; entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT; + workingset = entry & 1; + entry >>= 1; nid = entry & ((1UL << NODES_SHIFT) - 1); entry >>= NODES_SHIFT; memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1); @@ -195,6 +211,7 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, *memcgidp = memcgid; *pgdat = NODE_DATA(nid); *evictionp = entry << bucket_order; + *workingsetp = workingset; } /** @@ -207,8 +224,8 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, */ void *workingset_eviction(struct address_space *mapping, struct page *page) { - struct mem_cgroup *memcg = page_memcg(page); struct pglist_data *pgdat = page_pgdat(page); + struct mem_cgroup *memcg = page_memcg(page); int memcgid = mem_cgroup_id(memcg); unsigned long eviction; struct lruvec *lruvec; @@ -220,30 +237,30 @@ void *workingset_eviction(struct address_space *mapping, struct page *page) lruvec = mem_cgroup_lruvec(pgdat, memcg); eviction = atomic_long_inc_return(&lruvec->inactive_age); - return pack_shadow(memcgid, pgdat, eviction); + return pack_shadow(memcgid, pgdat, eviction, PageWorkingset(page)); } /** * workingset_refault - evaluate the refault of a previously evicted page + * @page: the freshly allocated replacement page * @shadow: shadow entry of the evicted page * * Calculates and evaluates the refault distance of the previously * evicted page in the context of the node it was allocated in. - * - * Returns %true if the page should be activated, %false otherwise. */ -bool workingset_refault(void *shadow) +void workingset_refault(struct page *page, void *shadow) { unsigned long refault_distance; + struct pglist_data *pgdat; unsigned long active_file; struct mem_cgroup *memcg; unsigned long eviction; struct lruvec *lruvec; unsigned long refault; - struct pglist_data *pgdat; + bool workingset; int memcgid; - unpack_shadow(shadow, &memcgid, &pgdat, &eviction); + unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &workingset); rcu_read_lock(); /* @@ -263,41 +280,51 @@ bool workingset_refault(void *shadow) * configurations instead. */ memcg = mem_cgroup_from_id(memcgid); - if (!mem_cgroup_disabled() && !memcg) { - rcu_read_unlock(); - return false; - } + if (!mem_cgroup_disabled() && !memcg) + goto out; lruvec = mem_cgroup_lruvec(pgdat, memcg); refault = atomic_long_read(&lruvec->inactive_age); active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES); /* - * The unsigned subtraction here gives an accurate distance - * across inactive_age overflows in most cases. + * Calculate the refault distance * - * There is a special case: usually, shadow entries have a - * short lifetime and are either refaulted or reclaimed along - * with the inode before they get too old. But it is not - * impossible for the inactive_age to lap a shadow entry in - * the field, which can then can result in a false small - * refault distance, leading to a false activation should this - * old entry actually refault again. However, earlier kernels - * used to deactivate unconditionally with *every* reclaim - * invocation for the longest time, so the occasional - * inappropriate activation leading to pressure on the active - * list is not a problem. + * The unsigned subtraction here gives an accurate distance + * across inactive_age overflows in most cases. There is a + * special case: usually, shadow entries have a short lifetime + * and are either refaulted or reclaimed along with the inode + * before they get too old. But it is not impossible for the + * inactive_age to lap a shadow entry in the field, which can + * then result in a false small refault distance, leading to a + * false activation should this old entry actually refault + * again. However, earlier kernels used to deactivate + * unconditionally with *every* reclaim invocation for the + * longest time, so the occasional inappropriate activation + * leading to pressure on the active list is not a problem. */ refault_distance = (refault - eviction) & EVICTION_MASK; inc_lruvec_state(lruvec, WORKINGSET_REFAULT); - if (refault_distance <= active_file) { - inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE); - rcu_read_unlock(); - return true; + /* + * Compare the distance to the existing workingset size. We + * don't act on pages that couldn't stay resident even if all + * the memory was available to the page cache. + */ + if (refault_distance > active_file) + goto out; + + SetPageActive(page); + atomic_long_inc(&lruvec->inactive_age); + inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE); + + /* Page was active prior to eviction */ + if (workingset) { + SetPageWorkingset(page); + inc_lruvec_state(lruvec, WORKINGSET_RESTORE); } +out: rcu_read_unlock(); - return false; } /** diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index c6df483b3751..801afc0b8c36 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -191,6 +191,7 @@ static struct vfsmount *zsmalloc_mnt; * (see: fix_fullness_group()) */ static const int fullness_threshold_frac = 4; +static size_t huge_class_size; struct size_class { spinlock_t lock; @@ -1431,6 +1432,25 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle) } EXPORT_SYMBOL_GPL(zs_unmap_object); +/** + * zs_huge_class_size() - Returns the size (in bytes) of the first huge + * zsmalloc &size_class. + * @pool: zsmalloc pool to use + * + * The function returns the size of the first huge class - any object of equal + * or bigger size will be stored in zspage consisting of a single physical + * page. + * + * Context: Any context. + * + * Return: the size (in bytes) of the first huge zsmalloc &size_class. + */ +size_t zs_huge_class_size(struct zs_pool *pool) +{ + return huge_class_size; +} +EXPORT_SYMBOL_GPL(zs_huge_class_size); + static unsigned long obj_malloc(struct size_class *class, struct zspage *zspage, unsigned long handle) { @@ -2461,6 +2481,27 @@ struct zs_pool *zs_create_pool(const char *name) objs_per_zspage = pages_per_zspage * PAGE_SIZE / size; /* + * We iterate from biggest down to smallest classes, + * so huge_class_size holds the size of the first huge + * class. Any object bigger than or equal to that will + * endup in the huge class. + */ + if (pages_per_zspage != 1 && objs_per_zspage != 1 && + !huge_class_size) { + huge_class_size = size; + /* + * The object uses ZS_HANDLE_SIZE bytes to store the + * handle. We need to subtract it, because zs_malloc() + * unconditionally adds handle size before it performs + * size class search - so object may be smaller than + * huge class size, yet it still can end up in the huge + * class because it grows by ZS_HANDLE_SIZE extra bytes + * right before class lookup. + */ + huge_class_size -= (ZS_HANDLE_SIZE - 1); + } + + /* * size_class is used for normal zsmalloc operation such * as alloc/free for that size. Although it is natural that we * have one size_class for each size, there is a chance that we diff --git a/net/Kconfig b/net/Kconfig index 9dba2715919d..999cc6beacc3 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -91,6 +91,12 @@ source "net/netlabel/Kconfig" endif # if INET +config ANDROID_PARANOID_NETWORK + bool "Only allow certain groups to create sockets" + default y + help + none + config NETWORK_SECMARK bool "Security Marking" help @@ -284,6 +290,7 @@ config BPF_JIT bool "enable BPF Just In Time compiler" depends on HAVE_CBPF_JIT || HAVE_EBPF_JIT depends on MODULES + depends on !CFI ---help--- Berkeley Packet Filter filtering capabilities are normally handled by an interpreter. This option allows kernel to generate a native diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index b48d54783e5d..ba42b700aae2 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -108,11 +108,40 @@ void bt_sock_unregister(int proto) } EXPORT_SYMBOL(bt_sock_unregister); +#ifdef CONFIG_PARANOID_NETWORK +static inline int current_has_bt_admin(void) +{ + return !current_euid(); +} + +static inline int current_has_bt(void) +{ + return current_has_bt_admin(); +} +# else +static inline int current_has_bt_admin(void) +{ + return 1; +} + +static inline int current_has_bt(void) +{ + return 1; +} +#endif + static int bt_sock_create(struct net *net, struct socket *sock, int proto, int kern) { int err; + if (proto == BTPROTO_RFCOMM || proto == BTPROTO_SCO || + proto == BTPROTO_L2CAP) { + if (!current_has_bt()) + return -EPERM; + } else if (!current_has_bt_admin()) + return -EPERM; + if (net != &init_net) return -EAFNOSUPPORT; diff --git a/net/core/filter.c b/net/core/filter.c index a3646230fbee..b19fbab3395a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2281,6 +2281,8 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff) static u32 __bpf_skb_max_len(const struct sk_buff *skb) { + if (skb_at_tc_ingress(skb) || !skb->dev) + return SKB_MAX_ALLOC; return skb->dev->mtu + skb->dev->hard_header_len; } @@ -3260,6 +3262,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) return &bpf_skb_adjust_room_proto; case BPF_FUNC_skb_change_tail: return &bpf_skb_change_tail_proto; + case BPF_FUNC_skb_change_head: + return &bpf_skb_change_head_proto; case BPF_FUNC_skb_get_tunnel_key: return &bpf_skb_get_tunnel_key_proto; case BPF_FUNC_skb_set_tunnel_key: diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 884afb8e9fc4..bd98819b9c75 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2345,7 +2345,7 @@ static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow) x = xfrm_state_lookup_byspi(pn->net, htonl(pkt_dev->spi), AF_INET); } else { /* slow path: we dont already have xfrm_state */ - x = xfrm_stateonly_find(pn->net, DUMMY_MARK, + x = xfrm_stateonly_find(pn->net, DUMMY_MARK, 0, (xfrm_address_t *)&pkt_dev->cur_daddr, (xfrm_address_t *)&pkt_dev->cur_saddr, AF_INET, diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index f31c09873d0f..be2ba4da2197 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -121,7 +121,6 @@ #endif #include <net/l3mdev.h> - /* The inetsw table contains everything that inet_create needs to * build a new socket. */ @@ -303,8 +302,7 @@ lookup_protocol: } err = -EPERM; - if (sock->type == SOCK_RAW && !kern && - !ns_capable(net->user_ns, CAP_NET_RAW)) + if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW)) goto out_rcu_unlock; sock->ops = answer->ops; diff --git a/net/ipv4/netfilter/nf_socket_ipv4.c b/net/ipv4/netfilter/nf_socket_ipv4.c index 4824b1e183a1..0f4ed1bf9d77 100644 --- a/net/ipv4/netfilter/nf_socket_ipv4.c +++ b/net/ipv4/netfilter/nf_socket_ipv4.c @@ -100,6 +100,7 @@ struct sock *nf_sk_lookup_slow_v4(struct net *net, const struct sk_buff *skb, __be16 uninitialized_var(dport), uninitialized_var(sport); const struct iphdr *iph = ip_hdr(skb); struct sk_buff *data_skb = NULL; + struct sock *sk = skb->sk; u8 uninitialized_var(protocol); #if IS_ENABLED(CONFIG_NF_CONNTRACK) enum ip_conntrack_info ctinfo; @@ -155,8 +156,14 @@ struct sock *nf_sk_lookup_slow_v4(struct net *net, const struct sk_buff *skb, } #endif - return nf_socket_get_sock_v4(net, data_skb, doff, protocol, saddr, - daddr, sport, dport, indev); + if (sk) + refcount_inc(&sk->sk_refcnt); + else + sk = nf_socket_get_sock_v4(dev_net(skb->dev), data_skb, doff, + protocol, saddr, daddr, sport, + dport, indev); + + return sk; } EXPORT_SYMBOL_GPL(nf_sk_lookup_slow_v4); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 78771272f613..de4e6ca93241 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -201,6 +201,21 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write, return ret; } +/* Validate changes from /proc interface. */ +static int proc_tcp_default_init_rwnd(struct ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int old_value = *(int *)ctl->data; + int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); + int new_value = *(int *)ctl->data; + + if (write && ret == 0 && (new_value < 3 || new_value > 100)) + *(int *)ctl->data = old_value; + + return ret; +} + static int proc_tcp_congestion_control(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -729,6 +744,13 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_tcp_available_ulp, }, { + .procname = "tcp_default_init_rwnd", + .data = &sysctl_tcp_default_init_rwnd, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_tcp_default_init_rwnd + }, + { .procname = "icmp_msgs_per_sec", .data = &sysctl_icmp_msgs_per_sec, .maxlen = sizeof(int), diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 83d03340417a..8b6b65f2eaf5 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -95,6 +95,7 @@ int sysctl_tcp_min_rtt_wlen __read_mostly = 300; int sysctl_tcp_moderate_rcvbuf __read_mostly = 1; int sysctl_tcp_early_retrans __read_mostly = 3; int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2; +int sysctl_tcp_default_init_rwnd __read_mostly = TCP_INIT_CWND * 2; #define FLAG_DATA 0x01 /* Incoming frame contained data. */ #define FLAG_WIN_UPDATE 0x02 /* Incoming ACK was a window update. */ diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 355ebae883c1..06eab04e9491 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -194,7 +194,7 @@ u32 tcp_default_init_rwnd(u32 mss) * (RFC 3517, Section 4, NextSeg() rule (2)). Further place a * limit when mss is larger than 1460. */ - u32 init_rwnd = TCP_INIT_CWND * 2; + u32 init_rwnd = sysctl_tcp_default_init_rwnd; if (mss > 1460) init_rwnd = max((1460 * init_rwnd) / mss, 2U); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index e58fdefcd2ca..67051d683e44 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -229,6 +229,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .accept_ra_rt_info_max_plen = 0, #endif #endif + .accept_ra_rt_table = 0, .proxy_ndp = 0, .accept_source_route = 0, /* we do not accept RH0 by default. */ .disable_ipv6 = 0, @@ -283,6 +284,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .accept_ra_rt_info_max_plen = 0, #endif #endif + .accept_ra_rt_table = 0, .proxy_ndp = 0, .accept_source_route = 0, /* we do not accept RH0 by default. */ .disable_ipv6 = 0, @@ -2275,6 +2277,31 @@ static void ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpad ipv6_regen_rndid(idev); } +u32 addrconf_rt_table(const struct net_device *dev, u32 default_table) { + /* Determines into what table to put autoconf PIO/RIO/default routes + * learned on this device. + * + * - If 0, use the same table for every device. This puts routes into + * one of RT_TABLE_{PREFIX,INFO,DFLT} depending on the type of route + * (but note that these three are currently all equal to + * RT6_TABLE_MAIN). + * - If > 0, use the specified table. + * - If < 0, put routes into table dev->ifindex + (-rt_table). + */ + struct inet6_dev *idev = in6_dev_get(dev); + u32 table; + int sysctl = idev->cnf.accept_ra_rt_table; + if (sysctl == 0) { + table = default_table; + } else if (sysctl > 0) { + table = (u32) sysctl; + } else { + table = (unsigned) dev->ifindex + (-sysctl); + } + in6_dev_put(idev); + return table; +} + /* * Add prefix route. */ @@ -2284,7 +2311,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev, unsigned long expires, u32 flags) { struct fib6_config cfg = { - .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX, + .fc_table = l3mdev_fib_table(dev) ? : addrconf_rt_table(dev, RT6_TABLE_PREFIX), .fc_metric = IP6_RT_PRIO_ADDRCONF, .fc_ifindex = dev->ifindex, .fc_expires = expires, @@ -2317,7 +2344,7 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, struct fib6_node *fn; struct rt6_info *rt = NULL; struct fib6_table *table; - u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX; + u32 tb_id = l3mdev_fib_table(dev) ? : addrconf_rt_table(dev, RT6_TABLE_PREFIX); table = fib6_get_table(dev_net(dev), tb_id); if (!table) @@ -5052,6 +5079,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_ACCEPT_RA_RT_INFO_MAX_PLEN] = cnf->accept_ra_rt_info_max_plen; #endif #endif + array[DEVCONF_ACCEPT_RA_RT_TABLE] = cnf->accept_ra_rt_table; array[DEVCONF_PROXY_NDP] = cnf->proxy_ndp; array[DEVCONF_ACCEPT_SOURCE_ROUTE] = cnf->accept_source_route; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD @@ -6219,6 +6247,13 @@ static const struct ctl_table addrconf_sysctl[] = { #endif #endif { + .procname = "accept_ra_rt_table", + .data = &ipv6_devconf.accept_ra_rt_table, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { .procname = "proxy_ndp", .data = &ipv6_devconf.proxy_ndp, .maxlen = sizeof(int), diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index e729c9c3aa49..7edfcf5e6d73 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -168,8 +168,7 @@ lookup_protocol: } err = -EPERM; - if (sock->type == SOCK_RAW && !kern && - !ns_capable(net->user_ns, CAP_NET_RAW)) + if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW)) goto out_rcu_unlock; sock->ops = answer->ops; diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index 305e2ed730bf..477692f80f0d 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -166,15 +166,15 @@ EXPORT_SYMBOL_GPL(ipv6_find_tlv); * to explore inner IPv6 header, eg. ICMPv6 error messages. * * If target header is found, its offset is set in *offset and return protocol - * number. Otherwise, return -1. + * number. Otherwise, return -ENOENT or -EBADMSG. * * If the first fragment doesn't contain the final protocol header or * NEXTHDR_NONE it is considered invalid. * * Note that non-1st fragment is special case that "the protocol number * of last header" is "next header" field in Fragment header. In this case, - * *offset is meaningless and fragment offset is stored in *fragoff if fragoff - * isn't NULL. + * *offset is meaningless. If fragoff is not NULL, the fragment offset is + * stored in *fragoff; if it is NULL, return -EINVAL. * * if flags is not NULL and it's a fragment, then the frag flag * IP6_FH_F_FRAG will be set. If it's an AH header, the @@ -253,9 +253,12 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, if (target < 0 && ((!ipv6_ext_hdr(hp->nexthdr)) || hp->nexthdr == NEXTHDR_NONE)) { - if (fragoff) + if (fragoff) { *fragoff = _frag_off; - return hp->nexthdr; + return hp->nexthdr; + } else { + return -EINVAL; + } } if (!found) return -ENOENT; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 5f80e57e93ed..2241c5f52394 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -196,6 +196,8 @@ static inline int ndisc_is_useropt(const struct net_device *dev, { return opt->nd_opt_type == ND_OPT_RDNSS || opt->nd_opt_type == ND_OPT_DNSSL || + opt->nd_opt_type == ND_OPT_CAPTIVE_PORTAL || + opt->nd_opt_type == ND_OPT_PREF64 || ndisc_ops_is_useropt(dev, opt->nd_opt_type); } diff --git a/net/ipv6/netfilter/nf_socket_ipv6.c b/net/ipv6/netfilter/nf_socket_ipv6.c index f14de4b6d639..be7ce4dfe18b 100644 --- a/net/ipv6/netfilter/nf_socket_ipv6.c +++ b/net/ipv6/netfilter/nf_socket_ipv6.c @@ -102,6 +102,7 @@ nf_socket_get_sock_v6(struct net *net, struct sk_buff *skb, int doff, struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb, const struct net_device *indev) { + struct sock *sk = skb->sk; __be16 uninitialized_var(dport), uninitialized_var(sport); const struct in6_addr *daddr = NULL, *saddr = NULL; struct ipv6hdr *iph = ipv6_hdr(skb); @@ -143,8 +144,14 @@ struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb, return NULL; } - return nf_socket_get_sock_v6(net, data_skb, doff, tproto, saddr, daddr, - sport, dport, indev); + if (sk) + refcount_inc(&sk->sk_refcnt); + else + sk = nf_socket_get_sock_v6(dev_net(skb->dev), data_skb, doff, + tproto, saddr, daddr, sport, dport, + indev); + + return sk; } EXPORT_SYMBOL_GPL(nf_sk_lookup_slow_v6); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index ddcaca5979b1..98ab1564aade 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2520,8 +2520,7 @@ static struct rt6_info *rt6_get_route_info(struct net *net, const struct in6_addr *gwaddr, struct net_device *dev) { - u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO; - int ifindex = dev->ifindex; + u32 tb_id = l3mdev_fib_table(dev) ? : addrconf_rt_table(dev, RT6_TABLE_INFO); struct fib6_node *fn; struct rt6_info *rt = NULL; struct fib6_table *table; @@ -2536,7 +2535,7 @@ static struct rt6_info *rt6_get_route_info(struct net *net, goto out; for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { - if (rt->dst.dev->ifindex != ifindex) + if (rt->dst.dev->ifindex != dev->ifindex) continue; if ((rt->rt6i_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY)) continue; @@ -2568,7 +2567,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net, .fc_nlinfo.nl_net = net, }; - cfg.fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO, + cfg.fc_table = l3mdev_fib_table(dev) ? : addrconf_rt_table(dev, RT6_TABLE_INFO), cfg.fc_dst = *prefix; cfg.fc_gateway = *gwaddr; @@ -2584,7 +2583,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net, struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_device *dev) { - u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT; + u32 tb_id = l3mdev_fib_table(dev) ? : addrconf_rt_table(dev, RT6_TABLE_MAIN); struct rt6_info *rt; struct fib6_table *table; @@ -2610,7 +2609,7 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr, unsigned int pref) { struct fib6_config cfg = { - .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT, + .fc_table = l3mdev_fib_table(dev) ? : addrconf_rt_table(dev, RT6_TABLE_DFLT), .fc_metric = IP6_RT_PRIO_USER, .fc_ifindex = dev->ifindex, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | @@ -2634,43 +2633,16 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr, return rt6_get_dflt_router(gwaddr, dev); } -static void __rt6_purge_dflt_routers(struct fib6_table *table) -{ - struct rt6_info *rt; - -restart: - read_lock_bh(&table->tb6_lock); - for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) { - if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) && - (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2)) { - dst_hold(&rt->dst); - read_unlock_bh(&table->tb6_lock); - ip6_del_rt(rt); - goto restart; - } - } - read_unlock_bh(&table->tb6_lock); - - table->flags &= ~RT6_TABLE_HAS_DFLT_ROUTER; +int rt6_addrconf_purge(struct rt6_info *rt, void *arg) { + if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) && + (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2)) + return -1; + return 0; } void rt6_purge_dflt_routers(struct net *net) { - struct fib6_table *table; - struct hlist_head *head; - unsigned int h; - - rcu_read_lock(); - - for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { - head = &net->ipv6.fib_table_hash[h]; - hlist_for_each_entry_rcu(table, head, tb6_hlist) { - if (table->flags & RT6_TABLE_HAS_DFLT_ROUTER) - __rt6_purge_dflt_routers(table); - } - } - - rcu_read_unlock(); + fib6_clean_all(net, rt6_addrconf_purge, NULL); } static void rtmsg_to_fib6_config(struct net *net, diff --git a/net/key/af_key.c b/net/key/af_key.c index f8f7065f7b62..2b09c2db0636 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1373,7 +1373,7 @@ static int pfkey_getspi(struct sock *sk, struct sk_buff *skb, const struct sadb_ } if (!x) - x = xfrm_find_acq(net, &dummy_mark, mode, reqid, proto, xdaddr, xsaddr, 1, family); + x = xfrm_find_acq(net, &dummy_mark, mode, reqid, 0, proto, xdaddr, xsaddr, 1, family); if (x == NULL) return -ENOENT; @@ -2404,7 +2404,7 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, const struct sa return err; } - xp = xfrm_policy_bysel_ctx(net, DUMMY_MARK, XFRM_POLICY_TYPE_MAIN, + xp = xfrm_policy_bysel_ctx(net, DUMMY_MARK, 0, XFRM_POLICY_TYPE_MAIN, pol->sadb_x_policy_dir - 1, &sel, pol_ctx, 1, &err); security_xfrm_policy_free(pol_ctx); @@ -2655,7 +2655,7 @@ static int pfkey_spdget(struct sock *sk, struct sk_buff *skb, const struct sadb_ return -EINVAL; delete = (hdr->sadb_msg_type == SADB_X_SPDDELETE2); - xp = xfrm_policy_byid(net, DUMMY_MARK, XFRM_POLICY_TYPE_MAIN, + xp = xfrm_policy_byid(net, DUMMY_MARK, 0, XFRM_POLICY_TYPE_MAIN, dir, pol->sadb_x_policy_id, delete, &err); if (xp == NULL) return -ENOENT; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 36512fbea130..a8aee0d15f5d 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -711,7 +711,7 @@ discard: */ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, unsigned char *ptr, unsigned char *optr, u16 hdrflags, - int length, int (*payload_hook)(struct sk_buff *skb)) + int length) { struct l2tp_tunnel *tunnel = session->tunnel; int offset; @@ -832,13 +832,6 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, __skb_pull(skb, offset); - /* If caller wants to process the payload before we queue the - * packet, do so now. - */ - if (payload_hook) - if ((*payload_hook)(skb)) - goto discard; - /* Prepare skb for adding to the session's reorder_q. Hold * packets for max reorder_timeout or 1 second if not * reordering. @@ -898,8 +891,7 @@ EXPORT_SYMBOL_GPL(l2tp_session_queue_purge); * Returns 1 if the packet was not a good data packet and could not be * forwarded. All such packets are passed up to userspace to deal with. */ -static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb, - int (*payload_hook)(struct sk_buff *skb)) +static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) { struct l2tp_session *session = NULL; unsigned char *ptr, *optr; @@ -997,7 +989,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb, l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) goto error; - l2tp_recv_common(session, skb, ptr, optr, hdrflags, length, payload_hook); + l2tp_recv_common(session, skb, ptr, optr, hdrflags, length); l2tp_session_dec_refcount(session); return 0; @@ -1026,7 +1018,7 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) l2tp_dbg(tunnel, L2TP_MSG_DATA, "%s: received %d bytes\n", tunnel->name, skb->len); - if (l2tp_udp_recv_core(tunnel, skb, tunnel->recv_payload_hook)) + if (l2tp_udp_recv_core(tunnel, skb)) goto pass_up_put; sock_put(sk); diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index e75748cdedb9..0cb1b57512ad 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -187,7 +187,6 @@ struct l2tp_tunnel { #ifdef CONFIG_DEBUG_FS void (*show)(struct seq_file *m, void *arg); #endif - int (*recv_payload_hook)(struct sk_buff *skb); void (*old_sk_destruct)(struct sock *); struct sock *sock; /* Parent socket */ int fd; /* Parent fd, if tunnel socket @@ -265,7 +264,7 @@ int l2tp_session_delete(struct l2tp_session *session); void l2tp_session_free(struct l2tp_session *session); void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, unsigned char *ptr, unsigned char *optr, u16 hdrflags, - int length, int (*payload_hook)(struct sk_buff *skb)); + int length); int l2tp_session_queue_purge(struct l2tp_session *session); int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb); void l2tp_session_set_header_len(struct l2tp_session *session, int version); diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 37a9f2a25263..c778f7f5c350 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -167,7 +167,7 @@ static int l2tp_ip_recv(struct sk_buff *skb) if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) goto discard_sess; - l2tp_recv_common(session, skb, ptr, optr, 0, skb->len, tunnel->recv_payload_hook); + l2tp_recv_common(session, skb, ptr, optr, 0, skb->len); l2tp_session_dec_refcount(session); return 0; diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 9c4670fb29d7..6f124af812aa 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -179,8 +179,7 @@ static int l2tp_ip6_recv(struct sk_buff *skb) if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) goto discard_sess; - l2tp_recv_common(session, skb, ptr, optr, 0, skb->len, - tunnel->recv_payload_hook); + l2tp_recv_common(session, skb, ptr, optr, 0, skb->len); l2tp_session_dec_refcount(session); return 0; diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index ad07b7cb6558..4ad821126776 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -185,25 +185,6 @@ out: * Receive data handling *****************************************************************************/ -static int pppol2tp_recv_payload_hook(struct sk_buff *skb) -{ - /* Skip PPP header, if present. In testing, Microsoft L2TP clients - * don't send the PPP header (PPP header compression enabled), but - * other clients can include the header. So we cope with both cases - * here. The PPP header is always FF03 when using L2TP. - * - * Note that skb->data[] isn't dereferenced from a u16 ptr here since - * the field may be unaligned. - */ - if (!pskb_may_pull(skb, 2)) - return 1; - - if ((skb->data[0] == PPP_ALLSTATIONS) && (skb->data[1] == PPP_UI)) - skb_pull(skb, 2); - - return 0; -} - /* Receive message. This is the recvmsg for the PPPoL2TP socket. */ static int pppol2tp_recvmsg(struct socket *sock, struct msghdr *msg, @@ -250,6 +231,17 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int if (sk == NULL) goto no_sock; + /* If the first two bytes are 0xFF03, consider that it is the PPP's + * Address and Control fields and skip them. The L2TP module has always + * worked this way, although, in theory, the use of these fields should + * be negociated and handled at the PPP layer. These fields are + * constant: 0xFF is the All-Stations Address and 0x03 the Unnumbered + * Information command with Poll/Final bit set to zero (RFC 1662). + */ + if (pskb_may_pull(skb, 2) && skb->data[0] == PPP_ALLSTATIONS && + skb->data[1] == PPP_UI) + skb_pull(skb, 2); + if (sk->sk_state & PPPOX_BOUND) { struct pppox_sock *po; @@ -746,9 +738,6 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, goto end; } - if (tunnel->recv_payload_hook == NULL) - tunnel->recv_payload_hook = pppol2tp_recv_payload_hook; - if (tunnel->peer_tunnel_id == 0) tunnel->peer_tunnel_id = peer_tunnel_id; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index e4a13cc8a2e7..1104351e7e87 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -1360,6 +1360,8 @@ config NETFILTER_XT_MATCH_OWNER based on who created the socket: the user or group. It is also possible to check whether a socket actually exists. + Conflicts with '"quota, tag, uid" match' + config NETFILTER_XT_MATCH_POLICY tristate 'IPsec "policy" match support' depends on XFRM @@ -1403,6 +1405,29 @@ config NETFILTER_XT_MATCH_QUOTA If you want to compile it as a module, say M here and read <file:Documentation/kbuild/modules.txt>. If unsure, say `N'. +config NETFILTER_XT_MATCH_QUOTA2 + tristate '"quota2" match support' + depends on NETFILTER_ADVANCED + help + This option adds a `quota2' match, which allows to match on a + byte counter correctly and not per CPU. + It allows naming the quotas. + This is based on http://xtables-addons.git.sourceforge.net + + If you want to compile it as a module, say M here and read + <file:Documentation/kbuild/modules.txt>. If unsure, say `N'. + +config NETFILTER_XT_MATCH_QUOTA2_LOG + bool '"quota2" Netfilter LOG support' + depends on NETFILTER_XT_MATCH_QUOTA2 + default n + help + This option allows `quota2' to log ONCE when a quota limit + is passed. It logs via NETLINK using the NETLINK_NFLOG family. + It logs similarly to how ipt_ULOG would without data. + + If unsure, say `N'. + config NETFILTER_XT_MATCH_RATEEST tristate '"rateest" match support' depends on NETFILTER_ADVANCED diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index f78ed2470831..775e3699c8bc 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -174,6 +174,7 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_PHYSDEV) += xt_physdev.o obj-$(CONFIG_NETFILTER_XT_MATCH_PKTTYPE) += xt_pkttype.o obj-$(CONFIG_NETFILTER_XT_MATCH_POLICY) += xt_policy.o obj-$(CONFIG_NETFILTER_XT_MATCH_QUOTA) += xt_quota.o +obj-$(CONFIG_NETFILTER_XT_MATCH_QUOTA2) += xt_quota2.o obj-$(CONFIG_NETFILTER_XT_MATCH_RATEEST) += xt_rateest.o obj-$(CONFIG_NETFILTER_XT_MATCH_REALM) += xt_realm.o obj-$(CONFIG_NETFILTER_XT_MATCH_RECENT) += xt_recent.o diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 8064d769c953..cbfcbcbda1c4 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -2016,7 +2016,7 @@ int nf_conntrack_hash_resize(unsigned int hashsize) return 0; } -int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) +int nf_conntrack_set_hashsize(const char *val, const struct kernel_param *kp) { unsigned int hashsize; int rc; diff --git a/net/netfilter/nf_nat_ftp.c b/net/netfilter/nf_nat_ftp.c index e84a578dbe35..d76afafdc699 100644 --- a/net/netfilter/nf_nat_ftp.c +++ b/net/netfilter/nf_nat_ftp.c @@ -134,7 +134,7 @@ static int __init nf_nat_ftp_init(void) } /* Prior to 2.6.11, we had a ports param. No longer, but don't break users. */ -static int warn_set(const char *val, struct kernel_param *kp) +static int warn_set(const char *val, const struct kernel_param *kp) { printk(KERN_INFO KBUILD_MODNAME ": kernel >= 2.6.10 only uses 'ports' for conntrack modules\n"); diff --git a/net/netfilter/nf_nat_irc.c b/net/netfilter/nf_nat_irc.c index 0648cb096bd8..dcb5f6375d9d 100644 --- a/net/netfilter/nf_nat_irc.c +++ b/net/netfilter/nf_nat_irc.c @@ -106,7 +106,7 @@ static int __init nf_nat_irc_init(void) } /* Prior to 2.6.11, we had a ports param. No longer, but don't break users. */ -static int warn_set(const char *val, struct kernel_param *kp) +static int warn_set(const char *val, const struct kernel_param *kp) { printk(KERN_INFO KBUILD_MODNAME ": kernel >= 2.6.10 only uses 'ports' for conntrack modules\n"); diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index 3fef8c2e545d..ff490161d107 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -5,6 +5,7 @@ * After timer expires a kevent will be sent. * * Copyright (C) 2004, 2010 Nokia Corporation + * * Written by Timo Teras <ext-timo.teras@nokia.com> * * Converted to x_tables and reworked for upstream inclusion @@ -38,8 +39,17 @@ #include <linux/netfilter/xt_IDLETIMER.h> #include <linux/kdev_t.h> #include <linux/kobject.h> +#include <linux/skbuff.h> #include <linux/workqueue.h> #include <linux/sysfs.h> +#include <linux/rtc.h> +#include <linux/time.h> +#include <linux/math64.h> +#include <linux/suspend.h> +#include <linux/notifier.h> +#include <net/net_namespace.h> +#include <net/sock.h> +#include <net/inet_sock.h> struct idletimer_tg_attr { struct attribute attr; @@ -55,14 +65,110 @@ struct idletimer_tg { struct kobject *kobj; struct idletimer_tg_attr attr; + struct timespec delayed_timer_trigger; + struct timespec last_modified_timer; + struct timespec last_suspend_time; + struct notifier_block pm_nb; + + int timeout; unsigned int refcnt; + bool work_pending; + bool send_nl_msg; + bool active; + uid_t uid; }; static LIST_HEAD(idletimer_tg_list); static DEFINE_MUTEX(list_mutex); +static DEFINE_SPINLOCK(timestamp_lock); static struct kobject *idletimer_tg_kobj; +static bool check_for_delayed_trigger(struct idletimer_tg *timer, + struct timespec *ts) +{ + bool state; + struct timespec temp; + spin_lock_bh(×tamp_lock); + timer->work_pending = false; + if ((ts->tv_sec - timer->last_modified_timer.tv_sec) > timer->timeout || + timer->delayed_timer_trigger.tv_sec != 0) { + state = false; + temp.tv_sec = timer->timeout; + temp.tv_nsec = 0; + if (timer->delayed_timer_trigger.tv_sec != 0) { + temp = timespec_add(timer->delayed_timer_trigger, temp); + ts->tv_sec = temp.tv_sec; + ts->tv_nsec = temp.tv_nsec; + timer->delayed_timer_trigger.tv_sec = 0; + timer->work_pending = true; + schedule_work(&timer->work); + } else { + temp = timespec_add(timer->last_modified_timer, temp); + ts->tv_sec = temp.tv_sec; + ts->tv_nsec = temp.tv_nsec; + } + } else { + state = timer->active; + } + spin_unlock_bh(×tamp_lock); + return state; +} + +static void notify_netlink_uevent(const char *iface, struct idletimer_tg *timer) +{ + char iface_msg[NLMSG_MAX_SIZE]; + char state_msg[NLMSG_MAX_SIZE]; + char timestamp_msg[NLMSG_MAX_SIZE]; + char uid_msg[NLMSG_MAX_SIZE]; + char *envp[] = { iface_msg, state_msg, timestamp_msg, uid_msg, NULL }; + int res; + struct timespec ts; + uint64_t time_ns; + bool state; + + res = snprintf(iface_msg, NLMSG_MAX_SIZE, "INTERFACE=%s", + iface); + if (NLMSG_MAX_SIZE <= res) { + pr_err("message too long (%d)", res); + return; + } + + get_monotonic_boottime(&ts); + state = check_for_delayed_trigger(timer, &ts); + res = snprintf(state_msg, NLMSG_MAX_SIZE, "STATE=%s", + state ? "active" : "inactive"); + + if (NLMSG_MAX_SIZE <= res) { + pr_err("message too long (%d)", res); + return; + } + + if (state) { + res = snprintf(uid_msg, NLMSG_MAX_SIZE, "UID=%u", timer->uid); + if (NLMSG_MAX_SIZE <= res) + pr_err("message too long (%d)", res); + } else { + res = snprintf(uid_msg, NLMSG_MAX_SIZE, "UID="); + if (NLMSG_MAX_SIZE <= res) + pr_err("message too long (%d)", res); + } + + time_ns = timespec_to_ns(&ts); + res = snprintf(timestamp_msg, NLMSG_MAX_SIZE, "TIME_NS=%llu", time_ns); + if (NLMSG_MAX_SIZE <= res) { + timestamp_msg[0] = '\0'; + pr_err("message too long (%d)", res); + } + + pr_debug("putting nlmsg: <%s> <%s> <%s> <%s>\n", iface_msg, state_msg, + timestamp_msg, uid_msg); + kobject_uevent_env(idletimer_tg_kobj, KOBJ_CHANGE, envp); + return; + + +} + static struct idletimer_tg *__idletimer_tg_find_by_label(const char *label) { @@ -83,6 +189,7 @@ static ssize_t idletimer_tg_show(struct kobject *kobj, struct attribute *attr, { struct idletimer_tg *timer; unsigned long expires = 0; + unsigned long now = jiffies; mutex_lock(&list_mutex); @@ -92,11 +199,15 @@ static ssize_t idletimer_tg_show(struct kobject *kobj, struct attribute *attr, mutex_unlock(&list_mutex); - if (time_after(expires, jiffies)) + if (time_after(expires, now)) return sprintf(buf, "%u\n", - jiffies_to_msecs(expires - jiffies) / 1000); + jiffies_to_msecs(expires - now) / 1000); - return sprintf(buf, "0\n"); + if (timer->send_nl_msg) + return sprintf(buf, "0 %d\n", + jiffies_to_msecs(now - expires) / 1000); + else + return sprintf(buf, "0\n"); } static void idletimer_tg_work(struct work_struct *work) @@ -105,6 +216,9 @@ static void idletimer_tg_work(struct work_struct *work) work); sysfs_notify(idletimer_tg_kobj, NULL, timer->attr.attr.name); + + if (timer->send_nl_msg) + notify_netlink_uevent(timer->attr.attr.name, timer); } static void idletimer_tg_expired(unsigned long data) @@ -112,8 +226,55 @@ static void idletimer_tg_expired(unsigned long data) struct idletimer_tg *timer = (struct idletimer_tg *) data; pr_debug("timer %s expired\n", timer->attr.attr.name); - + spin_lock_bh(×tamp_lock); + timer->active = false; + timer->work_pending = true; schedule_work(&timer->work); + spin_unlock_bh(×tamp_lock); +} + +static int idletimer_resume(struct notifier_block *notifier, + unsigned long pm_event, void *unused) +{ + struct timespec ts; + unsigned long time_diff, now = jiffies; + struct idletimer_tg *timer = container_of(notifier, + struct idletimer_tg, pm_nb); + if (!timer) + return NOTIFY_DONE; + switch (pm_event) { + case PM_SUSPEND_PREPARE: + get_monotonic_boottime(&timer->last_suspend_time); + break; + case PM_POST_SUSPEND: + spin_lock_bh(×tamp_lock); + if (!timer->active) { + spin_unlock_bh(×tamp_lock); + break; + } + /* since jiffies are not updated when suspended now represents + * the time it would have suspended */ + if (time_after(timer->timer.expires, now)) { + get_monotonic_boottime(&ts); + ts = timespec_sub(ts, timer->last_suspend_time); + time_diff = timespec_to_jiffies(&ts); + if (timer->timer.expires > (time_diff + now)) { + mod_timer_pending(&timer->timer, + (timer->timer.expires - time_diff)); + } else { + del_timer(&timer->timer); + timer->timer.expires = 0; + timer->active = false; + timer->work_pending = true; + schedule_work(&timer->work); + } + } + spin_unlock_bh(×tamp_lock); + break; + default: + break; + } + return NOTIFY_DONE; } static int idletimer_check_sysfs_name(const char *name, unsigned int size) @@ -166,6 +327,21 @@ static int idletimer_tg_create(struct idletimer_tg_info *info) setup_timer(&info->timer->timer, idletimer_tg_expired, (unsigned long) info->timer); info->timer->refcnt = 1; + info->timer->send_nl_msg = (info->send_nl_msg == 0) ? false : true; + info->timer->active = true; + info->timer->timeout = info->timeout; + + info->timer->delayed_timer_trigger.tv_sec = 0; + info->timer->delayed_timer_trigger.tv_nsec = 0; + info->timer->work_pending = false; + info->timer->uid = 0; + get_monotonic_boottime(&info->timer->last_modified_timer); + + info->timer->pm_nb.notifier_call = idletimer_resume; + ret = register_pm_notifier(&info->timer->pm_nb); + if (ret) + printk(KERN_WARNING "[%s] Failed to register pm notifier %d\n", + __func__, ret); INIT_WORK(&info->timer->work, idletimer_tg_work); @@ -182,6 +358,42 @@ out: return ret; } +static void reset_timer(const struct idletimer_tg_info *info, + struct sk_buff *skb) +{ + unsigned long now = jiffies; + struct idletimer_tg *timer = info->timer; + bool timer_prev; + + spin_lock_bh(×tamp_lock); + timer_prev = timer->active; + timer->active = true; + /* timer_prev is used to guard overflow problem in time_before*/ + if (!timer_prev || time_before(timer->timer.expires, now)) { + pr_debug("Starting Checkentry timer (Expired, Jiffies): %lu, %lu\n", + timer->timer.expires, now); + + /* Stores the uid resposible for waking up the radio */ + if (skb && (skb->sk)) { + timer->uid = from_kuid_munged(current_user_ns(), + sock_i_uid(skb_to_full_sk(skb))); + } + + /* checks if there is a pending inactive notification*/ + if (timer->work_pending) + timer->delayed_timer_trigger = timer->last_modified_timer; + else { + timer->work_pending = true; + schedule_work(&timer->work); + } + } + + get_monotonic_boottime(&timer->last_modified_timer); + mod_timer(&timer->timer, + msecs_to_jiffies(info->timeout * 1000) + now); + spin_unlock_bh(×tamp_lock); +} + /* * The actual xt_tables plugin. */ @@ -189,15 +401,23 @@ static unsigned int idletimer_tg_target(struct sk_buff *skb, const struct xt_action_param *par) { const struct idletimer_tg_info *info = par->targinfo; + unsigned long now = jiffies; pr_debug("resetting timer %s, timeout period %u\n", info->label, info->timeout); BUG_ON(!info->timer); - mod_timer(&info->timer->timer, - msecs_to_jiffies(info->timeout * 1000) + jiffies); + info->timer->active = true; + + if (time_before(info->timer->timer.expires, now)) { + schedule_work(&info->timer->work); + pr_debug("Starting timer %s (Expired, Jiffies): %lu, %lu\n", + info->label, info->timer->timer.expires, now); + } + /* TODO: Avoid modifying timers on each packet */ + reset_timer(info, skb); return XT_CONTINUE; } @@ -206,7 +426,7 @@ static int idletimer_tg_checkentry(const struct xt_tgchk_param *par) struct idletimer_tg_info *info = par->targinfo; int ret; - pr_debug("checkentry targinfo%s\n", info->label); + pr_debug("checkentry targinfo %s\n", info->label); if (info->timeout == 0) { pr_debug("timeout value is zero\n"); @@ -228,9 +448,7 @@ static int idletimer_tg_checkentry(const struct xt_tgchk_param *par) info->timer = __idletimer_tg_find_by_label(info->label); if (info->timer) { info->timer->refcnt++; - mod_timer(&info->timer->timer, - msecs_to_jiffies(info->timeout * 1000) + jiffies); - + reset_timer(info, NULL); pr_debug("increased refcnt of timer %s to %u\n", info->label, info->timer->refcnt); } else { @@ -243,6 +461,7 @@ static int idletimer_tg_checkentry(const struct xt_tgchk_param *par) } mutex_unlock(&list_mutex); + return 0; } @@ -259,13 +478,14 @@ static void idletimer_tg_destroy(const struct xt_tgdtor_param *par) list_del(&info->timer->entry); del_timer_sync(&info->timer->timer); - cancel_work_sync(&info->timer->work); sysfs_remove_file(idletimer_tg_kobj, &info->timer->attr.attr); + unregister_pm_notifier(&info->timer->pm_nb); + cancel_work_sync(&info->timer->work); kfree(info->timer->attr.attr.name); kfree(info->timer); } else { pr_debug("decreased refcnt of timer %s to %u\n", - info->label, info->timer->refcnt); + info->label, info->timer->refcnt); } mutex_unlock(&list_mutex); @@ -273,6 +493,7 @@ static void idletimer_tg_destroy(const struct xt_tgdtor_param *par) static struct xt_target idletimer_tg __read_mostly = { .name = "IDLETIMER", + .revision = 1, .family = NFPROTO_UNSPEC, .target = idletimer_tg_target, .targetsize = sizeof(struct idletimer_tg_info), @@ -339,3 +560,4 @@ MODULE_DESCRIPTION("Xtables: idle time monitor"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS("ipt_IDLETIMER"); MODULE_ALIAS("ip6t_IDLETIMER"); +MODULE_ALIAS("arpt_IDLETIMER"); diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c index 5185ff0f8f58..7e7746cc45d6 100644 --- a/net/netfilter/xt_bpf.c +++ b/net/netfilter/xt_bpf.c @@ -55,21 +55,12 @@ static int __bpf_mt_check_fd(int fd, struct bpf_prog **ret) static int __bpf_mt_check_path(const char *path, struct bpf_prog **ret) { - mm_segment_t oldfs = get_fs(); - int retval, fd; - if (strnlen(path, XT_BPF_PATH_MAX) == XT_BPF_PATH_MAX) return -EINVAL; - set_fs(KERNEL_DS); - fd = bpf_obj_get_user(path); - set_fs(oldfs); - if (fd < 0) - return fd; + *ret = bpf_prog_get_type_path(path, BPF_PROG_TYPE_SOCKET_FILTER); + return PTR_ERR_OR_ZERO(*ret); - retval = __bpf_mt_check_fd(fd, ret); - sys_close(fd); - return retval; } static int bpf_mt_check(const struct xt_mtchk_param *par) diff --git a/net/netfilter/xt_quota2.c b/net/netfilter/xt_quota2.c new file mode 100644 index 000000000000..c42724469759 --- /dev/null +++ b/net/netfilter/xt_quota2.c @@ -0,0 +1,401 @@ +/* + * xt_quota2 - enhanced xt_quota that can count upwards and in packets + * as a minimal accounting match. + * by Jan Engelhardt <jengelh@medozas.de>, 2008 + * + * Originally based on xt_quota.c: + * netfilter module to enforce network quotas + * Sam Johnston <samj@samj.net> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License; either + * version 2 of the License, as published by the Free Software Foundation. + */ +#include <linux/list.h> +#include <linux/module.h> +#include <linux/proc_fs.h> +#include <linux/skbuff.h> +#include <linux/spinlock.h> +#include <asm/atomic.h> +#include <net/netlink.h> + +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_quota2.h> + +#ifdef CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG +/* For compatibility, these definitions are copied from the + * deprecated header file <linux/netfilter_ipv4/ipt_ULOG.h> */ +#define ULOG_MAC_LEN 80 +#define ULOG_PREFIX_LEN 32 + +/* Format of the ULOG packets passed through netlink */ +typedef struct ulog_packet_msg { + unsigned long mark; + long timestamp_sec; + long timestamp_usec; + unsigned int hook; + char indev_name[IFNAMSIZ]; + char outdev_name[IFNAMSIZ]; + size_t data_len; + char prefix[ULOG_PREFIX_LEN]; + unsigned char mac_len; + unsigned char mac[ULOG_MAC_LEN]; + unsigned char payload[0]; +} ulog_packet_msg_t; +#endif + +/** + * @lock: lock to protect quota writers from each other + */ +struct xt_quota_counter { + u_int64_t quota; + spinlock_t lock; + struct list_head list; + atomic_t ref; + char name[sizeof(((struct xt_quota_mtinfo2 *)NULL)->name)]; + struct proc_dir_entry *procfs_entry; +}; + +#ifdef CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG +/* Harald's favorite number +1 :D From ipt_ULOG.C */ +static int qlog_nl_event = 112; +module_param_named(event_num, qlog_nl_event, uint, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(event_num, + "Event number for NETLINK_NFLOG message. 0 disables log." + "111 is what ipt_ULOG uses."); +static struct sock *nflognl; +#endif + +static LIST_HEAD(counter_list); +static DEFINE_SPINLOCK(counter_list_lock); + +static struct proc_dir_entry *proc_xt_quota; +static unsigned int quota_list_perms = S_IRUGO | S_IWUSR; +static kuid_t quota_list_uid = KUIDT_INIT(0); +static kgid_t quota_list_gid = KGIDT_INIT(0); +module_param_named(perms, quota_list_perms, uint, S_IRUGO | S_IWUSR); + +#ifdef CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG +static void quota2_log(unsigned int hooknum, + const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const char *prefix) +{ + ulog_packet_msg_t *pm; + struct sk_buff *log_skb; + size_t size; + struct nlmsghdr *nlh; + + if (!qlog_nl_event) + return; + + size = NLMSG_SPACE(sizeof(*pm)); + size = max(size, (size_t)NLMSG_GOODSIZE); + log_skb = alloc_skb(size, GFP_ATOMIC); + if (!log_skb) { + pr_err("xt_quota2: cannot alloc skb for logging\n"); + return; + } + + nlh = nlmsg_put(log_skb, /*pid*/0, /*seq*/0, qlog_nl_event, + sizeof(*pm), 0); + if (!nlh) { + pr_err("xt_quota2: nlmsg_put failed\n"); + kfree_skb(log_skb); + return; + } + pm = nlmsg_data(nlh); + if (skb->tstamp == 0) + __net_timestamp((struct sk_buff *)skb); + pm->data_len = 0; + pm->hook = hooknum; + if (prefix != NULL) + strlcpy(pm->prefix, prefix, sizeof(pm->prefix)); + else + *(pm->prefix) = '\0'; + if (in) + strlcpy(pm->indev_name, in->name, sizeof(pm->indev_name)); + else + pm->indev_name[0] = '\0'; + + if (out) + strlcpy(pm->outdev_name, out->name, sizeof(pm->outdev_name)); + else + pm->outdev_name[0] = '\0'; + + NETLINK_CB(log_skb).dst_group = 1; + pr_debug("throwing 1 packets to netlink group 1\n"); + netlink_broadcast(nflognl, log_skb, 0, 1, GFP_ATOMIC); +} +#else +static void quota2_log(unsigned int hooknum, + const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const char *prefix) +{ +} +#endif /* if+else CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG */ + +static ssize_t quota_proc_read(struct file *file, char __user *buf, + size_t size, loff_t *ppos) +{ + struct xt_quota_counter *e = PDE_DATA(file_inode(file)); + char tmp[24]; + size_t tmp_size; + + spin_lock_bh(&e->lock); + tmp_size = scnprintf(tmp, sizeof(tmp), "%llu\n", e->quota); + spin_unlock_bh(&e->lock); + return simple_read_from_buffer(buf, size, ppos, tmp, tmp_size); +} + +static ssize_t quota_proc_write(struct file *file, const char __user *input, + size_t size, loff_t *ppos) +{ + struct xt_quota_counter *e = PDE_DATA(file_inode(file)); + char buf[sizeof("18446744073709551616")]; + + if (size > sizeof(buf)) + size = sizeof(buf); + if (copy_from_user(buf, input, size) != 0) + return -EFAULT; + buf[sizeof(buf)-1] = '\0'; + + spin_lock_bh(&e->lock); + e->quota = simple_strtoull(buf, NULL, 0); + spin_unlock_bh(&e->lock); + return size; +} + +static const struct file_operations q2_counter_fops = { + .read = quota_proc_read, + .write = quota_proc_write, + .llseek = default_llseek, +}; + +static struct xt_quota_counter * +q2_new_counter(const struct xt_quota_mtinfo2 *q, bool anon) +{ + struct xt_quota_counter *e; + unsigned int size; + + /* Do not need all the procfs things for anonymous counters. */ + size = anon ? offsetof(typeof(*e), list) : sizeof(*e); + e = kmalloc(size, GFP_KERNEL); + if (e == NULL) + return NULL; + + e->quota = q->quota; + spin_lock_init(&e->lock); + if (!anon) { + INIT_LIST_HEAD(&e->list); + atomic_set(&e->ref, 1); + strlcpy(e->name, q->name, sizeof(e->name)); + } + return e; +} + +/** + * q2_get_counter - get ref to counter or create new + * @name: name of counter + */ +static struct xt_quota_counter * +q2_get_counter(const struct xt_quota_mtinfo2 *q) +{ + struct proc_dir_entry *p; + struct xt_quota_counter *e = NULL; + struct xt_quota_counter *new_e; + + if (*q->name == '\0') + return q2_new_counter(q, true); + + /* No need to hold a lock while getting a new counter */ + new_e = q2_new_counter(q, false); + if (new_e == NULL) + goto out; + + spin_lock_bh(&counter_list_lock); + list_for_each_entry(e, &counter_list, list) + if (strcmp(e->name, q->name) == 0) { + atomic_inc(&e->ref); + spin_unlock_bh(&counter_list_lock); + kfree(new_e); + pr_debug("xt_quota2: old counter name=%s", e->name); + return e; + } + e = new_e; + pr_debug("xt_quota2: new_counter name=%s", e->name); + list_add_tail(&e->list, &counter_list); + /* The entry having a refcount of 1 is not directly destructible. + * This func has not yet returned the new entry, thus iptables + * has not references for destroying this entry. + * For another rule to try to destroy it, it would 1st need for this + * func* to be re-invoked, acquire a new ref for the same named quota. + * Nobody will access the e->procfs_entry either. + * So release the lock. */ + spin_unlock_bh(&counter_list_lock); + + /* create_proc_entry() is not spin_lock happy */ + p = e->procfs_entry = proc_create_data(e->name, quota_list_perms, + proc_xt_quota, &q2_counter_fops, e); + + if (IS_ERR_OR_NULL(p)) { + spin_lock_bh(&counter_list_lock); + list_del(&e->list); + spin_unlock_bh(&counter_list_lock); + goto out; + } + proc_set_user(p, quota_list_uid, quota_list_gid); + return e; + + out: + kfree(e); + return NULL; +} + +static int quota_mt2_check(const struct xt_mtchk_param *par) +{ + struct xt_quota_mtinfo2 *q = par->matchinfo; + + pr_debug("xt_quota2: check() flags=0x%04x", q->flags); + + if (q->flags & ~XT_QUOTA_MASK) + return -EINVAL; + + q->name[sizeof(q->name)-1] = '\0'; + if (*q->name == '.' || strchr(q->name, '/') != NULL) { + printk(KERN_ERR "xt_quota.3: illegal name\n"); + return -EINVAL; + } + + q->master = q2_get_counter(q); + if (q->master == NULL) { + printk(KERN_ERR "xt_quota.3: memory alloc failure\n"); + return -ENOMEM; + } + + return 0; +} + +static void quota_mt2_destroy(const struct xt_mtdtor_param *par) +{ + struct xt_quota_mtinfo2 *q = par->matchinfo; + struct xt_quota_counter *e = q->master; + + if (*q->name == '\0') { + kfree(e); + return; + } + + spin_lock_bh(&counter_list_lock); + if (!atomic_dec_and_test(&e->ref)) { + spin_unlock_bh(&counter_list_lock); + return; + } + + list_del(&e->list); + spin_unlock_bh(&counter_list_lock); + remove_proc_entry(e->name, proc_xt_quota); + kfree(e); +} + +static bool +quota_mt2(const struct sk_buff *skb, struct xt_action_param *par) +{ + struct xt_quota_mtinfo2 *q = (void *)par->matchinfo; + struct xt_quota_counter *e = q->master; + bool ret = q->flags & XT_QUOTA_INVERT; + + spin_lock_bh(&e->lock); + if (q->flags & XT_QUOTA_GROW) { + /* + * While no_change is pointless in "grow" mode, we will + * implement it here simply to have a consistent behavior. + */ + if (!(q->flags & XT_QUOTA_NO_CHANGE)) { + e->quota += (q->flags & XT_QUOTA_PACKET) ? 1 : skb->len; + } + ret = true; + } else { + if (e->quota >= skb->len) { + if (!(q->flags & XT_QUOTA_NO_CHANGE)) + e->quota -= (q->flags & XT_QUOTA_PACKET) ? 1 : skb->len; + ret = !ret; + } else { + /* We are transitioning, log that fact. */ + if (e->quota) { + quota2_log(xt_hooknum(par), + skb, + xt_in(par), + xt_out(par), + q->name); + } + /* we do not allow even small packets from now on */ + e->quota = 0; + } + } + spin_unlock_bh(&e->lock); + return ret; +} + +static struct xt_match quota_mt2_reg[] __read_mostly = { + { + .name = "quota2", + .revision = 3, + .family = NFPROTO_IPV4, + .checkentry = quota_mt2_check, + .match = quota_mt2, + .destroy = quota_mt2_destroy, + .matchsize = sizeof(struct xt_quota_mtinfo2), + .me = THIS_MODULE, + }, + { + .name = "quota2", + .revision = 3, + .family = NFPROTO_IPV6, + .checkentry = quota_mt2_check, + .match = quota_mt2, + .destroy = quota_mt2_destroy, + .matchsize = sizeof(struct xt_quota_mtinfo2), + .me = THIS_MODULE, + }, +}; + +static int __init quota_mt2_init(void) +{ + int ret; + pr_debug("xt_quota2: init()"); + +#ifdef CONFIG_NETFILTER_XT_MATCH_QUOTA2_LOG + nflognl = netlink_kernel_create(&init_net, NETLINK_NFLOG, NULL); + if (!nflognl) + return -ENOMEM; +#endif + + proc_xt_quota = proc_mkdir("xt_quota", init_net.proc_net); + if (proc_xt_quota == NULL) + return -EACCES; + + ret = xt_register_matches(quota_mt2_reg, ARRAY_SIZE(quota_mt2_reg)); + if (ret < 0) + remove_proc_entry("xt_quota", init_net.proc_net); + pr_debug("xt_quota2: init() %d", ret); + return ret; +} + +static void __exit quota_mt2_exit(void) +{ + xt_unregister_matches(quota_mt2_reg, ARRAY_SIZE(quota_mt2_reg)); + remove_proc_entry("xt_quota", init_net.proc_net); +} + +module_init(quota_mt2_init); +module_exit(quota_mt2_exit); +MODULE_DESCRIPTION("Xtables: countdown quota match; up counter"); +MODULE_AUTHOR("Sam Johnston <samj@samj.net>"); +MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.de>"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("ipt_quota2"); +MODULE_ALIAS("ip6t_quota2"); diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 575d2153e3b8..cddd5cb81013 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -79,8 +79,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, transparent && sk_fullsock(sk)) pskb->mark = sk->sk_mark; - if (sk != skb->sk) - sock_gen_put(sk); + sock_gen_put(sk); if (wildcard || !transparent) sk = NULL; diff --git a/net/rfkill/Kconfig b/net/rfkill/Kconfig index 060600b03fad..7c33c8bb2cd9 100644 --- a/net/rfkill/Kconfig +++ b/net/rfkill/Kconfig @@ -10,6 +10,11 @@ menuconfig RFKILL To compile this driver as a module, choose M here: the module will be called rfkill. +config RFKILL_PM + bool "Power off on suspend" + depends on RFKILL && PM + default y + # LED trigger support config RFKILL_LEDS bool diff --git a/net/rfkill/core.c b/net/rfkill/core.c index e31b4288f32c..fdca887aa731 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -854,8 +854,7 @@ void rfkill_resume_polling(struct rfkill *rfkill) } EXPORT_SYMBOL(rfkill_resume_polling); -#ifdef CONFIG_PM_SLEEP -static int rfkill_suspend(struct device *dev) +static __maybe_unused int rfkill_suspend(struct device *dev) { struct rfkill *rfkill = to_rfkill(dev); @@ -865,7 +864,7 @@ static int rfkill_suspend(struct device *dev) return 0; } -static int rfkill_resume(struct device *dev) +static __maybe_unused int rfkill_resume(struct device *dev) { struct rfkill *rfkill = to_rfkill(dev); bool cur; @@ -885,17 +884,13 @@ static int rfkill_resume(struct device *dev) } static SIMPLE_DEV_PM_OPS(rfkill_pm_ops, rfkill_suspend, rfkill_resume); -#define RFKILL_PM_OPS (&rfkill_pm_ops) -#else -#define RFKILL_PM_OPS NULL -#endif static struct class rfkill_class = { .name = "rfkill", .dev_release = rfkill_release, .dev_groups = rfkill_dev_groups, .dev_uevent = rfkill_dev_uevent, - .pm = RFKILL_PM_OPS, + .pm = IS_ENABLED(CONFIG_RFKILL_PM) ? &rfkill_pm_ops : NULL, }; bool rfkill_blocked(struct rfkill *rfkill) diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 3a9a03717212..4eb470a9242e 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -50,7 +50,7 @@ EXPORT_SYMBOL_GPL(svc_pool_map); static DEFINE_MUTEX(svc_pool_map_mutex);/* protects svc_pool_map.count only */ static int -param_set_pool_mode(const char *val, struct kernel_param *kp) +param_set_pool_mode(const char *val, const struct kernel_param *kp) { int *ip = (int *)kp->arg; struct svc_pool_map *m = &svc_pool_map; @@ -80,7 +80,7 @@ out: } static int -param_get_pool_mode(char *buf, struct kernel_param *kp) +param_get_pool_mode(char *buf, const struct kernel_param *kp) { int *ip = (int *)kp->arg; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index ea47ef156e7d..f143fc13713e 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -71,7 +71,7 @@ module_param(bss_entries_limit, int, 0644); MODULE_PARM_DESC(bss_entries_limit, "limit to number of scan BSS entries (per wiphy, default 1000)"); -#define IEEE80211_SCAN_RESULT_EXPIRE (30 * HZ) +#define IEEE80211_SCAN_RESULT_EXPIRE (7 * HZ) static void bss_free(struct cfg80211_internal_bss *bss) { diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig index 2e747ae7dc89..41c804d7b0b8 100644 --- a/net/xfrm/Kconfig +++ b/net/xfrm/Kconfig @@ -27,6 +27,14 @@ config XFRM_USER If unsure, say Y. +config XFRM_INTERFACE + tristate "Transformation virtual interface" + depends on XFRM && IPV6 + ---help--- + This provides a virtual interface to route IPsec traffic. + + If unsure, say N. + config XFRM_SUB_POLICY bool "Transformation sub policy support" depends on XFRM diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile index 0bd2465a8c5a..fbc4552d17b8 100644 --- a/net/xfrm/Makefile +++ b/net/xfrm/Makefile @@ -10,3 +10,4 @@ obj-$(CONFIG_XFRM_STATISTICS) += xfrm_proc.o obj-$(CONFIG_XFRM_ALGO) += xfrm_algo.o obj-$(CONFIG_XFRM_USER) += xfrm_user.o obj-$(CONFIG_XFRM_IPCOMP) += xfrm_ipcomp.o +obj-$(CONFIG_XFRM_INTERFACE) += xfrm_interface.o diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c index 44ac85fe2bc9..d0ca0dbf494e 100644 --- a/net/xfrm/xfrm_algo.c +++ b/net/xfrm/xfrm_algo.c @@ -241,7 +241,7 @@ static struct xfrm_algo_desc aalg_list[] = { .uinfo = { .auth = { - .icv_truncbits = 96, + .icv_truncbits = 128, .icv_fullbits = 256, } }, diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index c58557193527..f8a71a5b4507 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -80,7 +80,8 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, } dst = __xfrm_dst_lookup(net, 0, 0, saddr, daddr, - x->props.family, x->props.output_mark); + x->props.family, + xfrm_smark_get(0, x)); if (IS_ERR(dst)) return 0; diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 874735742152..af87815b1bb3 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -323,6 +323,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) seq = 0; if (!spi && (err = xfrm_parse_spi(skb, nexthdr, &spi, &seq)) != 0) { + secpath_reset(skb); XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR); goto drop; } @@ -331,17 +332,21 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) XFRM_SPI_SKB_CB(skb)->daddroff); do { if (skb->sp->len == XFRM_MAX_DEPTH) { + secpath_reset(skb); XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR); goto drop; } x = xfrm_state_lookup(net, mark, daddr, spi, nexthdr, family); if (x == NULL) { + secpath_reset(skb); XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES); xfrm_audit_state_notfound(skb, family, spi, seq); goto drop; } + skb->mark = xfrm_smark_get(skb->mark, x); + skb->sp->xvec[skb->sp->len++] = x; skb_dst_force(skb); diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c new file mode 100644 index 000000000000..31acc6f33d98 --- /dev/null +++ b/net/xfrm/xfrm_interface.c @@ -0,0 +1,975 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * XFRM virtual interface + * + * Copyright (C) 2018 secunet Security Networks AG + * + * Author: + * Steffen Klassert <steffen.klassert@secunet.com> + */ + +#include <linux/module.h> +#include <linux/capability.h> +#include <linux/errno.h> +#include <linux/types.h> +#include <linux/sockios.h> +#include <linux/icmp.h> +#include <linux/if.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/net.h> +#include <linux/in6.h> +#include <linux/netdevice.h> +#include <linux/if_link.h> +#include <linux/if_arp.h> +#include <linux/icmpv6.h> +#include <linux/init.h> +#include <linux/route.h> +#include <linux/rtnetlink.h> +#include <linux/netfilter_ipv6.h> +#include <linux/slab.h> +#include <linux/hash.h> + +#include <linux/uaccess.h> +#include <linux/atomic.h> + +#include <net/icmp.h> +#include <net/ip.h> +#include <net/ipv6.h> +#include <net/ip6_route.h> +#include <net/addrconf.h> +#include <net/xfrm.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> +#include <linux/etherdevice.h> + +static int xfrmi_dev_init(struct net_device *dev); +static void xfrmi_dev_setup(struct net_device *dev); +static struct rtnl_link_ops xfrmi_link_ops __read_mostly; +static unsigned int xfrmi_net_id __read_mostly; + +struct xfrmi_net { + /* lists for storing interfaces in use */ + struct xfrm_if __rcu *xfrmi[1]; +}; + +#define for_each_xfrmi_rcu(start, xi) \ + for (xi = rcu_dereference(start); xi; xi = rcu_dereference(xi->next)) + +static struct xfrm_if *xfrmi_lookup(struct net *net, struct xfrm_state *x) +{ + struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); + struct xfrm_if *xi; + + for_each_xfrmi_rcu(xfrmn->xfrmi[0], xi) { + if (x->if_id == xi->p.if_id && + (xi->dev->flags & IFF_UP)) + return xi; + } + + return NULL; +} + +static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb) +{ + struct xfrmi_net *xfrmn; + int ifindex; + struct xfrm_if *xi; + + if (!skb->dev) + return NULL; + + xfrmn = net_generic(dev_net(skb->dev), xfrmi_net_id); + ifindex = skb->dev->ifindex; + + for_each_xfrmi_rcu(xfrmn->xfrmi[0], xi) { + if (ifindex == xi->dev->ifindex && + (xi->dev->flags & IFF_UP)) + return xi; + } + + return NULL; +} + +static void xfrmi_link(struct xfrmi_net *xfrmn, struct xfrm_if *xi) +{ + struct xfrm_if __rcu **xip = &xfrmn->xfrmi[0]; + + rcu_assign_pointer(xi->next , rtnl_dereference(*xip)); + rcu_assign_pointer(*xip, xi); +} + +static void xfrmi_unlink(struct xfrmi_net *xfrmn, struct xfrm_if *xi) +{ + struct xfrm_if __rcu **xip; + struct xfrm_if *iter; + + for (xip = &xfrmn->xfrmi[0]; + (iter = rtnl_dereference(*xip)) != NULL; + xip = &iter->next) { + if (xi == iter) { + rcu_assign_pointer(*xip, xi->next); + break; + } + } +} + +static void xfrmi_dev_free(struct net_device *dev) +{ + free_percpu(dev->tstats); +} + +static int xfrmi_create2(struct net_device *dev) +{ + struct xfrm_if *xi = netdev_priv(dev); + struct net *net = dev_net(dev); + struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); + int err; + + dev->rtnl_link_ops = &xfrmi_link_ops; + err = register_netdevice(dev); + if (err < 0) + goto out; + + strcpy(xi->p.name, dev->name); + + dev_hold(dev); + xfrmi_link(xfrmn, xi); + + return 0; + +out: + return err; +} + +static struct xfrm_if *xfrmi_create(struct net *net, struct xfrm_if_parms *p) +{ + struct net_device *dev; + struct xfrm_if *xi; + char name[IFNAMSIZ]; + int err; + + if (p->name[0]) { + strlcpy(name, p->name, IFNAMSIZ); + } else { + err = -EINVAL; + goto failed; + } + + dev = alloc_netdev(sizeof(*xi), name, NET_NAME_UNKNOWN, xfrmi_dev_setup); + if (!dev) { + err = -EAGAIN; + goto failed; + } + + dev_net_set(dev, net); + + xi = netdev_priv(dev); + xi->p = *p; + xi->net = net; + xi->dev = dev; + xi->phydev = dev_get_by_index(net, p->link); + if (!xi->phydev) { + err = -ENODEV; + goto failed_free; + } + + err = xfrmi_create2(dev); + if (err < 0) + goto failed_dev_put; + + return xi; + +failed_dev_put: + dev_put(xi->phydev); +failed_free: + free_netdev(dev); +failed: + return ERR_PTR(err); +} + +static struct xfrm_if *xfrmi_locate(struct net *net, struct xfrm_if_parms *p, + int create) +{ + struct xfrm_if __rcu **xip; + struct xfrm_if *xi; + struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); + + for (xip = &xfrmn->xfrmi[0]; + (xi = rtnl_dereference(*xip)) != NULL; + xip = &xi->next) { + if (xi->p.if_id == p->if_id) { + if (create) + return ERR_PTR(-EEXIST); + + return xi; + } + } + if (!create) + return ERR_PTR(-ENODEV); + return xfrmi_create(net, p); +} + +static void xfrmi_dev_uninit(struct net_device *dev) +{ + struct xfrm_if *xi = netdev_priv(dev); + struct xfrmi_net *xfrmn = net_generic(xi->net, xfrmi_net_id); + + xfrmi_unlink(xfrmn, xi); + dev_put(xi->phydev); + dev_put(dev); +} + +static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet) +{ + skb->tstamp = 0; + skb->pkt_type = PACKET_HOST; + skb->skb_iif = 0; + skb->ignore_df = 0; + skb_dst_drop(skb); + nf_reset(skb); + nf_reset_trace(skb); + + if (!xnet) + return; + + ipvs_reset(skb); + secpath_reset(skb); + skb_orphan(skb); + skb->mark = 0; +} + +static int xfrmi_rcv_cb(struct sk_buff *skb, int err) +{ + struct pcpu_sw_netstats *tstats; + struct xfrm_mode *inner_mode; + struct net_device *dev; + struct xfrm_state *x; + struct xfrm_if *xi; + bool xnet; + + if (err && !skb->sp) + return 0; + + x = xfrm_input_state(skb); + + xi = xfrmi_lookup(xs_net(x), x); + if (!xi) + return 1; + + dev = xi->dev; + skb->dev = dev; + + if (err) { + dev->stats.rx_errors++; + dev->stats.rx_dropped++; + + return 0; + } + + xnet = !net_eq(xi->net, dev_net(skb->dev)); + + if (xnet) { + inner_mode = x->inner_mode; + + if (x->sel.family == AF_UNSPEC) { + inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol); + if (inner_mode == NULL) { + XFRM_INC_STATS(dev_net(skb->dev), + LINUX_MIB_XFRMINSTATEMODEERROR); + return -EINVAL; + } + } + + if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, + inner_mode->afinfo->family)) + return -EPERM; + } + + xfrmi_scrub_packet(skb, xnet); + + tstats = this_cpu_ptr(dev->tstats); + + u64_stats_update_begin(&tstats->syncp); + tstats->rx_packets++; + tstats->rx_bytes += skb->len; + u64_stats_update_end(&tstats->syncp); + + return 0; +} + +static int +xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) +{ + struct xfrm_if *xi = netdev_priv(dev); + struct net_device_stats *stats = &xi->dev->stats; + struct dst_entry *dst = skb_dst(skb); + unsigned int length = skb->len; + struct net_device *tdev; + struct xfrm_state *x; + int err = -1; + int mtu; + + if (!dst) + goto tx_err_link_failure; + + dst_hold(dst); + dst = xfrm_lookup_with_ifid(xi->net, dst, fl, NULL, 0, xi->p.if_id); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); + dst = NULL; + goto tx_err_link_failure; + } + + x = dst->xfrm; + if (!x) + goto tx_err_link_failure; + + if (x->if_id != xi->p.if_id) + goto tx_err_link_failure; + + tdev = dst->dev; + + if (tdev == dev) { + stats->collisions++; + net_warn_ratelimited("%s: Local routing loop detected!\n", + xi->p.name); + goto tx_err_dst_release; + } + + mtu = dst_mtu(dst); + if (!skb->ignore_df && skb->len > mtu) { + skb_dst_update_pmtu(skb, mtu); + + if (skb->protocol == htons(ETH_P_IPV6)) { + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + } else { + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, + htonl(mtu)); + } + + dst_release(dst); + return -EMSGSIZE; + } + + xfrmi_scrub_packet(skb, !net_eq(xi->net, dev_net(dev))); + skb_dst_set(skb, dst); + skb->dev = tdev; + + err = dst_output(xi->net, skb->sk, skb); + if (net_xmit_eval(err) == 0) { + struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); + + u64_stats_update_begin(&tstats->syncp); + tstats->tx_bytes += length; + tstats->tx_packets++; + u64_stats_update_end(&tstats->syncp); + } else { + stats->tx_errors++; + stats->tx_aborted_errors++; + } + + return 0; +tx_err_link_failure: + stats->tx_carrier_errors++; + dst_link_failure(skb); +tx_err_dst_release: + dst_release(dst); + return err; +} + +static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct xfrm_if *xi = netdev_priv(dev); + struct net_device_stats *stats = &xi->dev->stats; + struct flowi fl; + int ret; + + memset(&fl, 0, sizeof(fl)); + + switch (skb->protocol) { + case htons(ETH_P_IPV6): + xfrm_decode_session(skb, &fl, AF_INET6); + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + break; + case htons(ETH_P_IP): + xfrm_decode_session(skb, &fl, AF_INET); + memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + break; + default: + goto tx_err; + } + + fl.flowi_oif = xi->phydev->ifindex; + + ret = xfrmi_xmit2(skb, dev, &fl); + if (ret < 0) + goto tx_err; + + return NETDEV_TX_OK; + +tx_err: + stats->tx_errors++; + stats->tx_dropped++; + kfree_skb(skb); + return NETDEV_TX_OK; +} + +static int xfrmi4_err(struct sk_buff *skb, u32 info) +{ + const struct iphdr *iph = (const struct iphdr *)skb->data; + struct net *net = dev_net(skb->dev); + int protocol = iph->protocol; + struct ip_comp_hdr *ipch; + struct ip_esp_hdr *esph; + struct ip_auth_hdr *ah ; + struct xfrm_state *x; + struct xfrm_if *xi; + __be32 spi; + + switch (protocol) { + case IPPROTO_ESP: + esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2)); + spi = esph->spi; + break; + case IPPROTO_AH: + ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2)); + spi = ah->spi; + break; + case IPPROTO_COMP: + ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2)); + spi = htonl(ntohs(ipch->cpi)); + break; + default: + return 0; + } + + switch (icmp_hdr(skb)->type) { + case ICMP_DEST_UNREACH: + if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) + return 0; + case ICMP_REDIRECT: + break; + default: + return 0; + } + + x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, + spi, protocol, AF_INET); + if (!x) + return 0; + + xi = xfrmi_lookup(net, x); + if (!xi) { + xfrm_state_put(x); + return -1; + } + + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) + ipv4_update_pmtu(skb, net, info, 0, 0, protocol, 0); + else + ipv4_redirect(skb, net, 0, 0, protocol, 0); + xfrm_state_put(x); + + return 0; +} + +static int xfrmi6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data; + struct net *net = dev_net(skb->dev); + int protocol = iph->nexthdr; + struct ip_comp_hdr *ipch; + struct ip_esp_hdr *esph; + struct ip_auth_hdr *ah; + struct xfrm_state *x; + struct xfrm_if *xi; + __be32 spi; + + switch (protocol) { + case IPPROTO_ESP: + esph = (struct ip_esp_hdr *)(skb->data + offset); + spi = esph->spi; + break; + case IPPROTO_AH: + ah = (struct ip_auth_hdr *)(skb->data + offset); + spi = ah->spi; + break; + case IPPROTO_COMP: + ipch = (struct ip_comp_hdr *)(skb->data + offset); + spi = htonl(ntohs(ipch->cpi)); + break; + default: + return 0; + } + + if (type != ICMPV6_PKT_TOOBIG && + type != NDISC_REDIRECT) + return 0; + + x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, + spi, protocol, AF_INET6); + if (!x) + return 0; + + xi = xfrmi_lookup(net, x); + if (!xi) { + xfrm_state_put(x); + return -1; + } + + if (type == NDISC_REDIRECT) + ip6_redirect(skb, net, skb->dev->ifindex, 0, + sock_net_uid(net, NULL)); + else + ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL)); + xfrm_state_put(x); + + return 0; +} + +static int xfrmi_change(struct xfrm_if *xi, const struct xfrm_if_parms *p) +{ + if (xi->p.link != p->link) + return -EINVAL; + + xi->p.if_id = p->if_id; + + return 0; +} + +static int xfrmi_update(struct xfrm_if *xi, struct xfrm_if_parms *p) +{ + struct net *net = dev_net(xi->dev); + struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); + int err; + + xfrmi_unlink(xfrmn, xi); + synchronize_net(); + err = xfrmi_change(xi, p); + xfrmi_link(xfrmn, xi); + netdev_state_change(xi->dev); + return err; +} + +static void xfrmi_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *s) +{ + int cpu; + + if (!dev->tstats) + return; + + for_each_possible_cpu(cpu) { + struct pcpu_sw_netstats *stats; + struct pcpu_sw_netstats tmp; + int start; + + stats = per_cpu_ptr(dev->tstats, cpu); + do { + start = u64_stats_fetch_begin_irq(&stats->syncp); + tmp.rx_packets = stats->rx_packets; + tmp.rx_bytes = stats->rx_bytes; + tmp.tx_packets = stats->tx_packets; + tmp.tx_bytes = stats->tx_bytes; + } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); + + s->rx_packets += tmp.rx_packets; + s->rx_bytes += tmp.rx_bytes; + s->tx_packets += tmp.tx_packets; + s->tx_bytes += tmp.tx_bytes; + } + + s->rx_dropped = dev->stats.rx_dropped; + s->tx_dropped = dev->stats.tx_dropped; +} + +static int xfrmi_get_iflink(const struct net_device *dev) +{ + struct xfrm_if *xi = netdev_priv(dev); + + return xi->phydev->ifindex; +} + + +static const struct net_device_ops xfrmi_netdev_ops = { + .ndo_init = xfrmi_dev_init, + .ndo_uninit = xfrmi_dev_uninit, + .ndo_start_xmit = xfrmi_xmit, + .ndo_get_stats64 = xfrmi_get_stats64, + .ndo_get_iflink = xfrmi_get_iflink, +}; + +static void xfrmi_dev_setup(struct net_device *dev) +{ + dev->netdev_ops = &xfrmi_netdev_ops; + dev->type = ARPHRD_NONE; + dev->hard_header_len = ETH_HLEN; + dev->min_header_len = ETH_HLEN; + dev->mtu = ETH_DATA_LEN; + dev->min_mtu = ETH_MIN_MTU; + dev->max_mtu = ETH_DATA_LEN; + dev->addr_len = ETH_ALEN; + dev->flags = IFF_NOARP; + dev->needs_free_netdev = true; + dev->priv_destructor = xfrmi_dev_free; + netif_keep_dst(dev); +} + +static int xfrmi_dev_init(struct net_device *dev) +{ + struct xfrm_if *xi = netdev_priv(dev); + struct net_device *phydev = xi->phydev; + int err; + + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + if (!dev->tstats) + return -ENOMEM; + + err = gro_cells_init(&xi->gro_cells, dev); + if (err) { + free_percpu(dev->tstats); + return err; + } + + dev->features |= NETIF_F_LLTX; + + dev->needed_headroom = phydev->needed_headroom; + dev->needed_tailroom = phydev->needed_tailroom; + + if (is_zero_ether_addr(dev->dev_addr)) + eth_hw_addr_inherit(dev, phydev); + if (is_zero_ether_addr(dev->broadcast)) + memcpy(dev->broadcast, phydev->broadcast, dev->addr_len); + + return 0; +} + +static int xfrmi_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + return 0; +} + +static void xfrmi_netlink_parms(struct nlattr *data[], + struct xfrm_if_parms *parms) +{ + memset(parms, 0, sizeof(*parms)); + + if (!data) + return; + + if (data[IFLA_XFRM_LINK]) + parms->link = nla_get_u32(data[IFLA_XFRM_LINK]); + + if (data[IFLA_XFRM_IF_ID]) + parms->if_id = nla_get_u32(data[IFLA_XFRM_IF_ID]); +} + +static int xfrmi_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct net *net = dev_net(dev); + struct xfrm_if_parms *p; + struct xfrm_if *xi; + + xi = netdev_priv(dev); + p = &xi->p; + + xfrmi_netlink_parms(data, p); + + if (!tb[IFLA_IFNAME]) + return -EINVAL; + + nla_strlcpy(p->name, tb[IFLA_IFNAME], IFNAMSIZ); + + xi = xfrmi_locate(net, p, 1); + return PTR_ERR_OR_ZERO(xi); +} + +static void xfrmi_dellink(struct net_device *dev, struct list_head *head) +{ + unregister_netdevice_queue(dev, head); +} + +static int xfrmi_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct xfrm_if *xi = netdev_priv(dev); + struct net *net = dev_net(dev); + + xfrmi_netlink_parms(data, &xi->p); + + xi = xfrmi_locate(net, &xi->p, 0); + + if (IS_ERR_OR_NULL(xi)) { + xi = netdev_priv(dev); + } else { + if (xi->dev != dev) + return -EEXIST; + } + + return xfrmi_update(xi, &xi->p); +} + +static size_t xfrmi_get_size(const struct net_device *dev) +{ + return + /* IFLA_XFRM_LINK */ + nla_total_size(4) + + /* IFLA_XFRM_IF_ID */ + nla_total_size(4) + + 0; +} + +static int xfrmi_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct xfrm_if *xi = netdev_priv(dev); + struct xfrm_if_parms *parm = &xi->p; + + if (nla_put_u32(skb, IFLA_XFRM_LINK, parm->link) || + nla_put_u32(skb, IFLA_XFRM_IF_ID, parm->if_id)) + goto nla_put_failure; + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +struct net *xfrmi_get_link_net(const struct net_device *dev) +{ + struct xfrm_if *xi = netdev_priv(dev); + + return dev_net(xi->phydev); +} + +static const struct nla_policy xfrmi_policy[IFLA_XFRM_MAX + 1] = { + [IFLA_XFRM_LINK] = { .type = NLA_U32 }, + [IFLA_XFRM_IF_ID] = { .type = NLA_U32 }, +}; + +static struct rtnl_link_ops xfrmi_link_ops __read_mostly = { + .kind = "xfrm", + .maxtype = IFLA_XFRM_MAX, + .policy = xfrmi_policy, + .priv_size = sizeof(struct xfrm_if), + .setup = xfrmi_dev_setup, + .validate = xfrmi_validate, + .newlink = xfrmi_newlink, + .dellink = xfrmi_dellink, + .changelink = xfrmi_changelink, + .get_size = xfrmi_get_size, + .fill_info = xfrmi_fill_info, + .get_link_net = xfrmi_get_link_net, +}; + +static void __net_exit xfrmi_destroy_interfaces(struct xfrmi_net *xfrmn) +{ + struct xfrm_if *xi; + LIST_HEAD(list); + + xi = rtnl_dereference(xfrmn->xfrmi[0]); + if (!xi) + return; + + unregister_netdevice_queue(xi->dev, &list); + unregister_netdevice_many(&list); +} + +static int __net_init xfrmi_init_net(struct net *net) +{ + return 0; +} + +static void __net_exit xfrmi_exit_net(struct net *net) +{ + struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); + + rtnl_lock(); + xfrmi_destroy_interfaces(xfrmn); + rtnl_unlock(); +} + +static struct pernet_operations xfrmi_net_ops = { + .init = xfrmi_init_net, + .exit = xfrmi_exit_net, + .id = &xfrmi_net_id, + .size = sizeof(struct xfrmi_net), +}; + +static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = { + .handler = xfrm6_rcv, + .cb_handler = xfrmi_rcv_cb, + .err_handler = xfrmi6_err, + .priority = 10, +}; + +static struct xfrm6_protocol xfrmi_ah6_protocol __read_mostly = { + .handler = xfrm6_rcv, + .cb_handler = xfrmi_rcv_cb, + .err_handler = xfrmi6_err, + .priority = 10, +}; + +static struct xfrm6_protocol xfrmi_ipcomp6_protocol __read_mostly = { + .handler = xfrm6_rcv, + .cb_handler = xfrmi_rcv_cb, + .err_handler = xfrmi6_err, + .priority = 10, +}; + +static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = { + .handler = xfrm4_rcv, + .input_handler = xfrm_input, + .cb_handler = xfrmi_rcv_cb, + .err_handler = xfrmi4_err, + .priority = 10, +}; + +static struct xfrm4_protocol xfrmi_ah4_protocol __read_mostly = { + .handler = xfrm4_rcv, + .input_handler = xfrm_input, + .cb_handler = xfrmi_rcv_cb, + .err_handler = xfrmi4_err, + .priority = 10, +}; + +static struct xfrm4_protocol xfrmi_ipcomp4_protocol __read_mostly = { + .handler = xfrm4_rcv, + .input_handler = xfrm_input, + .cb_handler = xfrmi_rcv_cb, + .err_handler = xfrmi4_err, + .priority = 10, +}; + +static int __init xfrmi4_init(void) +{ + int err; + + err = xfrm4_protocol_register(&xfrmi_esp4_protocol, IPPROTO_ESP); + if (err < 0) + goto xfrm_proto_esp_failed; + err = xfrm4_protocol_register(&xfrmi_ah4_protocol, IPPROTO_AH); + if (err < 0) + goto xfrm_proto_ah_failed; + err = xfrm4_protocol_register(&xfrmi_ipcomp4_protocol, IPPROTO_COMP); + if (err < 0) + goto xfrm_proto_comp_failed; + + return 0; + +xfrm_proto_comp_failed: + xfrm4_protocol_deregister(&xfrmi_ah4_protocol, IPPROTO_AH); +xfrm_proto_ah_failed: + xfrm4_protocol_deregister(&xfrmi_esp4_protocol, IPPROTO_ESP); +xfrm_proto_esp_failed: + return err; +} + +static void xfrmi4_fini(void) +{ + xfrm4_protocol_deregister(&xfrmi_ipcomp4_protocol, IPPROTO_COMP); + xfrm4_protocol_deregister(&xfrmi_ah4_protocol, IPPROTO_AH); + xfrm4_protocol_deregister(&xfrmi_esp4_protocol, IPPROTO_ESP); +} + +static int __init xfrmi6_init(void) +{ + int err; + + err = xfrm6_protocol_register(&xfrmi_esp6_protocol, IPPROTO_ESP); + if (err < 0) + goto xfrm_proto_esp_failed; + err = xfrm6_protocol_register(&xfrmi_ah6_protocol, IPPROTO_AH); + if (err < 0) + goto xfrm_proto_ah_failed; + err = xfrm6_protocol_register(&xfrmi_ipcomp6_protocol, IPPROTO_COMP); + if (err < 0) + goto xfrm_proto_comp_failed; + + return 0; + +xfrm_proto_comp_failed: + xfrm6_protocol_deregister(&xfrmi_ah6_protocol, IPPROTO_AH); +xfrm_proto_ah_failed: + xfrm6_protocol_deregister(&xfrmi_esp6_protocol, IPPROTO_ESP); +xfrm_proto_esp_failed: + return err; +} + +static void xfrmi6_fini(void) +{ + xfrm6_protocol_deregister(&xfrmi_ipcomp6_protocol, IPPROTO_COMP); + xfrm6_protocol_deregister(&xfrmi_ah6_protocol, IPPROTO_AH); + xfrm6_protocol_deregister(&xfrmi_esp6_protocol, IPPROTO_ESP); +} + +static const struct xfrm_if_cb xfrm_if_cb = { + .decode_session = xfrmi_decode_session, +}; + +static int __init xfrmi_init(void) +{ + const char *msg; + int err; + + pr_info("IPsec XFRM device driver\n"); + + msg = "tunnel device"; + err = register_pernet_device(&xfrmi_net_ops); + if (err < 0) + goto pernet_dev_failed; + + msg = "xfrm4 protocols"; + err = xfrmi4_init(); + if (err < 0) + goto xfrmi4_failed; + + msg = "xfrm6 protocols"; + err = xfrmi6_init(); + if (err < 0) + goto xfrmi6_failed; + + + msg = "netlink interface"; + err = rtnl_link_register(&xfrmi_link_ops); + if (err < 0) + goto rtnl_link_failed; + + xfrm_if_register_cb(&xfrm_if_cb); + + return err; + +rtnl_link_failed: + xfrmi6_fini(); +xfrmi6_failed: + xfrmi4_fini(); +xfrmi4_failed: + unregister_pernet_device(&xfrmi_net_ops); +pernet_dev_failed: + pr_err("xfrmi init: failed to register %s\n", msg); + return err; +} + +static void __exit xfrmi_fini(void) +{ + xfrm_if_unregister_cb(); + rtnl_link_unregister(&xfrmi_link_ops); + xfrmi4_fini(); + xfrmi6_fini(); + unregister_pernet_device(&xfrmi_net_ops); +} + +module_init(xfrmi_init); +module_exit(xfrmi_fini); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK("xfrm"); +MODULE_ALIAS_NETDEV("xfrm0"); +MODULE_AUTHOR("Steffen Klassert"); +MODULE_DESCRIPTION("XFRM virtual interface"); diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 80760a753d72..00ff2a1c5e5f 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -66,8 +66,7 @@ static int xfrm_output_one(struct sk_buff *skb, int err) goto error_nolock; } - if (x->props.output_mark) - skb->mark = x->props.output_mark; + skb->mark = xfrm_smark_get(skb->mark, x); err = x->outer_mode->output(x, skb); if (err) { diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index f8fd0aebf771..b0811d71eb43 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -45,6 +45,8 @@ struct xfrm_flo { u8 flags; }; +static DEFINE_SPINLOCK(xfrm_if_cb_lock); +static struct xfrm_if_cb const __rcu *xfrm_if_cb __read_mostly; static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock); static struct xfrm_policy_afinfo const __rcu *xfrm_policy_afinfo[AF_INET6 + 1] __read_mostly; @@ -117,6 +119,12 @@ static const struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short fa return afinfo; } +/* Called with rcu_read_lock(). */ +static const struct xfrm_if_cb *xfrm_if_get_cb(void) +{ + return rcu_dereference(xfrm_if_cb); +} + struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif, const xfrm_address_t *saddr, const xfrm_address_t *daddr, @@ -743,6 +751,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) newpos = NULL; hlist_for_each_entry(pol, chain, bydst) { if (pol->type == policy->type && + pol->if_id == policy->if_id && !selector_cmp(&pol->selector, &policy->selector) && xfrm_policy_mark_match(policy, pol) && xfrm_sec_ctx_match(pol->security, policy->security) && @@ -794,8 +803,9 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) } EXPORT_SYMBOL(xfrm_policy_insert); -struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type, - int dir, struct xfrm_selector *sel, +struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id, + u8 type, int dir, + struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx, int delete, int *err) { @@ -808,6 +818,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type, ret = NULL; hlist_for_each_entry(pol, chain, bydst) { if (pol->type == type && + pol->if_id == if_id && (mark & pol->mark.m) == pol->mark.v && !selector_cmp(sel, &pol->selector) && xfrm_sec_ctx_match(ctx, pol->security)) { @@ -833,8 +844,9 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type, } EXPORT_SYMBOL(xfrm_policy_bysel_ctx); -struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type, - int dir, u32 id, int delete, int *err) +struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id, + u8 type, int dir, u32 id, int delete, + int *err) { struct xfrm_policy *pol, *ret; struct hlist_head *chain; @@ -849,6 +861,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type, ret = NULL; hlist_for_each_entry(pol, chain, byidx) { if (pol->type == type && pol->index == id && + pol->if_id == if_id && (mark & pol->mark.m) == pol->mark.v) { xfrm_pol_hold(pol); if (delete) { @@ -1052,13 +1065,14 @@ EXPORT_SYMBOL(xfrm_policy_walk_done); */ static int xfrm_policy_match(const struct xfrm_policy *pol, const struct flowi *fl, - u8 type, u16 family, int dir) + u8 type, u16 family, int dir, u32 if_id) { const struct xfrm_selector *sel = &pol->selector; int ret = -ESRCH; bool match; if (pol->family != family || + pol->if_id != if_id || (fl->flowi_mark & pol->mark.m) != pol->mark.v || pol->type != type) return ret; @@ -1073,7 +1087,8 @@ static int xfrm_policy_match(const struct xfrm_policy *pol, static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, const struct flowi *fl, - u16 family, u8 dir) + u16 family, u8 dir, + u32 if_id) { int err; struct xfrm_policy *pol, *ret; @@ -1097,7 +1112,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, priority = ~0U; ret = NULL; hlist_for_each_entry_rcu(pol, chain, bydst) { - err = xfrm_policy_match(pol, fl, type, family, dir); + err = xfrm_policy_match(pol, fl, type, family, dir, if_id); if (err) { if (err == -ESRCH) continue; @@ -1116,7 +1131,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, if ((pol->priority >= priority) && ret) break; - err = xfrm_policy_match(pol, fl, type, family, dir); + err = xfrm_policy_match(pol, fl, type, family, dir, if_id); if (err) { if (err == -ESRCH) continue; @@ -1141,21 +1156,25 @@ fail: return ret; } -static struct xfrm_policy * -xfrm_policy_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir) +static struct xfrm_policy *xfrm_policy_lookup(struct net *net, + const struct flowi *fl, + u16 family, u8 dir, u32 if_id) { #ifdef CONFIG_XFRM_SUB_POLICY struct xfrm_policy *pol; - pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_SUB, fl, family, dir); + pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_SUB, fl, family, + dir, if_id); if (pol != NULL) return pol; #endif - return xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, fl, family, dir); + return xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, fl, family, + dir, if_id); } static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, - const struct flowi *fl, u16 family) + const struct flowi *fl, + u16 family, u32 if_id) { struct xfrm_policy *pol; @@ -1173,7 +1192,8 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, match = xfrm_selector_match(&pol->selector, fl, family); if (match) { - if ((sk->sk_mark & pol->mark.m) != pol->mark.v) { + if ((sk->sk_mark & pol->mark.m) != pol->mark.v || + pol->if_id != if_id) { pol = NULL; goto out; } @@ -1301,6 +1321,7 @@ static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir) newp->lft = old->lft; newp->curlft = old->curlft; newp->mark = old->mark; + newp->if_id = old->if_id; newp->action = old->action; newp->flags = old->flags; newp->xfrm_nr = old->xfrm_nr; @@ -1386,7 +1407,8 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl, } } - x = xfrm_state_find(remote, local, fl, tmpl, policy, &error, family); + x = xfrm_state_find(remote, local, fl, tmpl, policy, &error, + family, policy->if_id); if (x && x->km.state == XFRM_STATE_VALID) { xfrm[nx++] = x; @@ -1600,10 +1622,14 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, dst_copy_metrics(dst1, dst); if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) { + __u32 mark = 0; + + if (xfrm[i]->props.smark.v || xfrm[i]->props.smark.m) + mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]); + family = xfrm[i]->props.family; dst = xfrm_dst_lookup(xfrm[i], tos, fl->flowi_oif, - &saddr, &daddr, family, - xfrm[i]->props.output_mark); + &saddr, &daddr, family, mark); err = PTR_ERR(dst); if (IS_ERR(dst)) goto put_states; @@ -1688,7 +1714,8 @@ static int xfrm_expand_policies(const struct flowi *fl, u16 family, pols[1] = xfrm_policy_lookup_bytype(xp_net(pols[0]), XFRM_POLICY_TYPE_MAIN, fl, family, - XFRM_POLICY_OUT); + XFRM_POLICY_OUT, + pols[0]->if_id); if (pols[1]) { if (IS_ERR(pols[1])) { xfrm_pols_put(pols, *num_pols); @@ -1924,8 +1951,10 @@ free_dst: goto out; } -static struct xfrm_dst * -xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, struct xfrm_flo *xflo) +static struct xfrm_dst *xfrm_bundle_lookup(struct net *net, + const struct flowi *fl, + u16 family, u8 dir, + struct xfrm_flo *xflo, u32 if_id) { struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; int num_pols = 0, num_xfrms = 0, err; @@ -1934,7 +1963,7 @@ xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, /* Resolve policies to use if we couldn't get them from * previous cache entry */ num_pols = 1; - pols[0] = xfrm_policy_lookup(net, fl, family, dir); + pols[0] = xfrm_policy_lookup(net, fl, family, dir, if_id); err = xfrm_expand_policies(fl, family, pols, &num_pols, &num_xfrms); if (err < 0) @@ -1948,6 +1977,11 @@ xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, xflo->dst_orig); if (IS_ERR(xdst)) { err = PTR_ERR(xdst); + if (err == -EREMOTE) { + xfrm_pols_put(pols, num_pols); + return NULL; + } + if (err != -EAGAIN) goto error; goto make_dummy_bundle; @@ -1997,14 +2031,19 @@ static struct dst_entry *make_blackhole(struct net *net, u16 family, return ret; } -/* Main function: finds/creates a bundle for given flow. +/* Finds/creates a bundle for given flow and if_id * * At the moment we eat a raw IP route. Mostly to speed up lookups * on interfaces with disabled IPsec. + * + * xfrm_lookup uses an if_id of 0 by default, and is provided for + * compatibility */ -struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, - const struct flowi *fl, - const struct sock *sk, int flags) +struct dst_entry *xfrm_lookup_with_ifid(struct net *net, + struct dst_entry *dst_orig, + const struct flowi *fl, + const struct sock *sk, + int flags, u32 if_id) { struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; struct xfrm_dst *xdst; @@ -2020,7 +2059,8 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, sk = sk_const_to_full_sk(sk); if (sk && sk->sk_policy[XFRM_POLICY_OUT]) { num_pols = 1; - pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl, family); + pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl, family, + if_id); err = xfrm_expand_policies(fl, family, pols, &num_pols, &num_xfrms); if (err < 0) @@ -2039,6 +2079,9 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, if (IS_ERR(xdst)) { xfrm_pols_put(pols, num_pols); err = PTR_ERR(xdst); + if (err == -EREMOTE) + goto nopol; + goto dropdst; } else if (xdst == NULL) { num_xfrms = 0; @@ -2061,7 +2104,7 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, !net->xfrm.policy_count[XFRM_POLICY_OUT]) goto nopol; - xdst = xfrm_bundle_lookup(net, fl, family, dir, &xflo); + xdst = xfrm_bundle_lookup(net, fl, family, dir, &xflo, if_id); if (xdst == NULL) goto nopol; if (IS_ERR(xdst)) { @@ -2142,6 +2185,19 @@ dropdst: xfrm_pols_put(pols, drop_pols); return ERR_PTR(err); } +EXPORT_SYMBOL(xfrm_lookup_with_ifid); + +/* Main function: finds/creates a bundle for given flow. + * + * At the moment we eat a raw IP route. Mostly to speed up lookups + * on interfaces with disabled IPsec. + */ +struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, + const struct flowi *fl, const struct sock *sk, + int flags) +{ + return xfrm_lookup_with_ifid(net, dst_orig, fl, sk, flags, 0); +} EXPORT_SYMBOL(xfrm_lookup); /* Callers of xfrm_lookup_route() must ensure a call to dst_output(). @@ -2240,6 +2296,7 @@ int __xfrm_decode_session(struct sk_buff *skb, struct flowi *fl, return -EAFNOSUPPORT; afinfo->decode_session(skb, fl, reverse); + err = security_xfrm_decode_session(skb, &fl->flowi_secid); rcu_read_unlock(); return err; @@ -2270,6 +2327,19 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, int reverse; struct flowi fl; int xerr_idx = -1; + const struct xfrm_if_cb *ifcb; + struct xfrm_if *xi; + u32 if_id = 0; + + rcu_read_lock(); + ifcb = xfrm_if_get_cb(); + + if (ifcb) { + xi = ifcb->decode_session(skb); + if (xi) + if_id = xi->p.if_id; + } + rcu_read_unlock(); reverse = dir & ~XFRM_POLICY_MASK; dir &= XFRM_POLICY_MASK; @@ -2297,7 +2367,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, pol = NULL; sk = sk_to_full_sk(sk); if (sk && sk->sk_policy[dir]) { - pol = xfrm_sk_policy_lookup(sk, dir, &fl, family); + pol = xfrm_sk_policy_lookup(sk, dir, &fl, family, if_id); if (IS_ERR(pol)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); return 0; @@ -2305,7 +2375,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, } if (!pol) - pol = xfrm_policy_lookup(net, &fl, family, dir); + pol = xfrm_policy_lookup(net, &fl, family, dir, if_id); if (IS_ERR(pol)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); @@ -2329,7 +2399,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, if (pols[0]->type != XFRM_POLICY_TYPE_MAIN) { pols[1] = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, &fl, family, - XFRM_POLICY_IN); + XFRM_POLICY_IN, if_id); if (pols[1]) { if (IS_ERR(pols[1])) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); @@ -2693,6 +2763,21 @@ void xfrm_policy_unregister_afinfo(const struct xfrm_policy_afinfo *afinfo) } EXPORT_SYMBOL(xfrm_policy_unregister_afinfo); +void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb) +{ + spin_lock(&xfrm_if_cb_lock); + rcu_assign_pointer(xfrm_if_cb, ifcb); + spin_unlock(&xfrm_if_cb_lock); +} +EXPORT_SYMBOL(xfrm_if_register_cb); + +void xfrm_if_unregister_cb(void) +{ + RCU_INIT_POINTER(xfrm_if_cb, NULL); + synchronize_rcu(); +} +EXPORT_SYMBOL(xfrm_if_unregister_cb); + #ifdef CONFIG_XFRM_STATISTICS static int __net_init xfrm_statistics_init(struct net *net) { @@ -2865,6 +2950,9 @@ void __init xfrm_init(void) register_pernet_subsys(&xfrm_net_ops); seqcount_init(&xfrm_policy_hash_generation); xfrm_input_init(); + + RCU_INIT_POINTER(xfrm_if_cb, NULL); + synchronize_rcu(); } #ifdef CONFIG_AUDITSYSCALL diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 190ca59d5ba3..1d1049a8c683 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -932,7 +932,7 @@ struct xfrm_state * xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, const struct flowi *fl, struct xfrm_tmpl *tmpl, struct xfrm_policy *pol, int *err, - unsigned short family) + unsigned short family, u32 if_id) { static xfrm_address_t saddr_wildcard = { }; struct net *net = xp_net(pol); @@ -956,6 +956,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && + x->if_id == if_id && !(x->props.flags & XFRM_STATE_WILDRECV) && xfrm_state_addr_check(x, daddr, saddr, encap_family) && tmpl->mode == x->props.mode && @@ -972,6 +973,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && + x->if_id == if_id && !(x->props.flags & XFRM_STATE_WILDRECV) && xfrm_addr_equal(&x->id.daddr, daddr, encap_family) && tmpl->mode == x->props.mode && @@ -1011,6 +1013,7 @@ found: * to current session. */ xfrm_init_tempstate(x, fl, tmpl, daddr, saddr, family); memcpy(&x->mark, &pol->mark, sizeof(x->mark)); + x->if_id = if_id; error = security_xfrm_state_alloc_acquire(x, pol->security, fl->flowi_secid); if (error) { @@ -1068,7 +1071,7 @@ out: } struct xfrm_state * -xfrm_stateonly_find(struct net *net, u32 mark, +xfrm_stateonly_find(struct net *net, u32 mark, u32 if_id, xfrm_address_t *daddr, xfrm_address_t *saddr, unsigned short family, u8 mode, u8 proto, u32 reqid) { @@ -1081,6 +1084,7 @@ xfrm_stateonly_find(struct net *net, u32 mark, if (x->props.family == family && x->props.reqid == reqid && (mark & x->mark.m) == x->mark.v && + x->if_id == if_id && !(x->props.flags & XFRM_STATE_WILDRECV) && xfrm_state_addr_check(x, daddr, saddr, family) && mode == x->props.mode && @@ -1161,11 +1165,13 @@ static void __xfrm_state_bump_genids(struct xfrm_state *xnew) struct xfrm_state *x; unsigned int h; u32 mark = xnew->mark.v & xnew->mark.m; + u32 if_id = xnew->if_id; h = xfrm_dst_hash(net, &xnew->id.daddr, &xnew->props.saddr, reqid, family); hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.family == family && x->props.reqid == reqid && + x->if_id == if_id && (mark & x->mark.m) == x->mark.v && xfrm_addr_equal(&x->id.daddr, &xnew->id.daddr, family) && xfrm_addr_equal(&x->props.saddr, &xnew->props.saddr, family)) @@ -1188,7 +1194,7 @@ EXPORT_SYMBOL(xfrm_state_insert); static struct xfrm_state *__find_acq_core(struct net *net, const struct xfrm_mark *m, unsigned short family, u8 mode, - u32 reqid, u8 proto, + u32 reqid, u32 if_id, u8 proto, const xfrm_address_t *daddr, const xfrm_address_t *saddr, int create) @@ -1243,6 +1249,7 @@ static struct xfrm_state *__find_acq_core(struct net *net, x->props.family = family; x->props.mode = mode; x->props.reqid = reqid; + x->if_id = if_id; x->mark.v = m->v; x->mark.m = m->m; x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires; @@ -1297,7 +1304,7 @@ int xfrm_state_add(struct xfrm_state *x) if (use_spi && !x1) x1 = __find_acq_core(net, &x->mark, family, x->props.mode, - x->props.reqid, x->id.proto, + x->props.reqid, x->if_id, x->id.proto, &x->id.daddr, &x->props.saddr, 0); __xfrm_state_bump_genids(x); @@ -1396,6 +1403,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, x->props.flags = orig->props.flags; x->props.extra_flags = orig->props.extra_flags; + x->if_id = orig->if_id; x->tfcpad = orig->tfcpad; x->replay_maxdiff = orig->replay_maxdiff; x->replay_maxage = orig->replay_maxage; @@ -1551,6 +1559,19 @@ out: if (x1->curlft.use_time) xfrm_state_check_expire(x1); + if (x->props.smark.m || x->props.smark.v || x->if_id) { + spin_lock_bh(&net->xfrm.xfrm_state_lock); + + if (x->props.smark.m || x->props.smark.v) + x1->props.smark = x->props.smark; + + if (x->if_id) + x1->if_id = x->if_id; + + __xfrm_state_bump_genids(x1); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); + } + err = 0; x->km.state = XFRM_STATE_DEAD; __xfrm_state_put(x); @@ -1614,13 +1635,13 @@ EXPORT_SYMBOL(xfrm_state_lookup_byaddr); struct xfrm_state * xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, u8 mode, u32 reqid, - u8 proto, const xfrm_address_t *daddr, + u32 if_id, u8 proto, const xfrm_address_t *daddr, const xfrm_address_t *saddr, int create, unsigned short family) { struct xfrm_state *x; spin_lock_bh(&net->xfrm.xfrm_state_lock); - x = __find_acq_core(net, mark, family, mode, reqid, proto, daddr, saddr, create); + x = __find_acq_core(net, mark, family, mode, reqid, if_id, proto, daddr, saddr, create); spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; @@ -2052,11 +2073,6 @@ int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen struct xfrm_mgr *km; struct xfrm_policy *pol = NULL; -#ifdef CONFIG_COMPAT - if (in_compat_syscall()) - return -EOPNOTSUPP; -#endif - if (!optval && !optlen) { xfrm_sk_policy_insert(sk, XFRM_POLICY_IN, NULL); xfrm_sk_policy_insert(sk, XFRM_POLICY_OUT, NULL); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 86084086a472..cf220e77a59d 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -553,6 +553,19 @@ static void xfrm_update_ae_params(struct xfrm_state *x, struct nlattr **attrs, x->replay_maxdiff = nla_get_u32(rt); } +static void xfrm_smark_init(struct nlattr **attrs, struct xfrm_mark *m) +{ + if (attrs[XFRMA_SET_MARK]) { + m->v = nla_get_u32(attrs[XFRMA_SET_MARK]); + if (attrs[XFRMA_SET_MARK_MASK]) + m->m = nla_get_u32(attrs[XFRMA_SET_MARK_MASK]); + else + m->m = 0xffffffff; + } else { + m->v = m->m = 0; + } +} + static struct xfrm_state *xfrm_state_construct(struct net *net, struct xfrm_usersa_info *p, struct nlattr **attrs, @@ -605,8 +618,10 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, xfrm_mark_get(attrs, &x->mark); - if (attrs[XFRMA_OUTPUT_MARK]) - x->props.output_mark = nla_get_u32(attrs[XFRMA_OUTPUT_MARK]); + xfrm_smark_init(attrs, &x->props.smark); + + if (attrs[XFRMA_IF_ID]) + x->if_id = nla_get_u32(attrs[XFRMA_IF_ID]); err = __xfrm_init_state(x, false, attrs[XFRMA_OFFLOAD_DEV]); if (err) @@ -846,6 +861,18 @@ static int copy_to_user_auth(struct xfrm_algo_auth *auth, struct sk_buff *skb) return 0; } +static int xfrm_smark_put(struct sk_buff *skb, struct xfrm_mark *m) +{ + int ret = 0; + + if (m->v | m->m) { + ret = nla_put_u32(skb, XFRMA_SET_MARK, m->v); + if (!ret) + ret = nla_put_u32(skb, XFRMA_SET_MARK_MASK, m->m); + } + return ret; +} + /* Don't change this without updating xfrm_sa_len! */ static int copy_to_user_state_extra(struct xfrm_state *x, struct xfrm_usersa_info *p, @@ -909,6 +936,11 @@ static int copy_to_user_state_extra(struct xfrm_state *x, ret = xfrm_mark_put(skb, &x->mark); if (ret) goto out; + + ret = xfrm_smark_put(skb, &x->props.smark); + if (ret) + goto out; + if (x->replay_esn) ret = nla_put(skb, XFRMA_REPLAY_ESN_VAL, xfrm_replay_state_esn_len(x->replay_esn), @@ -922,8 +954,8 @@ static int copy_to_user_state_extra(struct xfrm_state *x, ret = copy_user_offload(&x->xso, skb); if (ret) goto out; - if (x->props.output_mark) { - ret = nla_put_u32(skb, XFRMA_OUTPUT_MARK, x->props.output_mark); + if (x->if_id) { + ret = nla_put_u32(skb, XFRMA_IF_ID, x->if_id); if (ret) goto out; } @@ -1275,6 +1307,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, int err; u32 mark; struct xfrm_mark m; + u32 if_id = 0; p = nlmsg_data(nlh); err = verify_spi_info(p->info.id.proto, p->min, p->max); @@ -1287,6 +1320,10 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, x = NULL; mark = xfrm_mark_get(attrs, &m); + + if (attrs[XFRMA_IF_ID]) + if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + if (p->info.seq) { x = xfrm_find_acq_byseq(net, mark, p->info.seq); if (x && !xfrm_addr_equal(&x->id.daddr, daddr, family)) { @@ -1297,7 +1334,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, if (!x) x = xfrm_find_acq(net, &m, p->info.mode, p->info.reqid, - p->info.id.proto, daddr, + if_id, p->info.id.proto, daddr, &p->info.saddr, 1, family); err = -ENOENT; @@ -1587,6 +1624,9 @@ static struct xfrm_policy *xfrm_policy_construct(struct net *net, struct xfrm_us xfrm_mark_get(attrs, &xp->mark); + if (attrs[XFRMA_IF_ID]) + xp->if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + return xp; error: *errp = err; @@ -1734,6 +1774,8 @@ static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr err = copy_to_user_policy_type(xp->type, skb); if (!err) err = xfrm_mark_put(skb, &xp->mark); + if (!err) + err = xfrm_if_id_put(skb, xp->if_id); if (err) { nlmsg_cancel(skb, nlh); return err; @@ -1815,6 +1857,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, int delete; struct xfrm_mark m; u32 mark = xfrm_mark_get(attrs, &m); + u32 if_id = 0; p = nlmsg_data(nlh); delete = nlh->nlmsg_type == XFRM_MSG_DELPOLICY; @@ -1827,8 +1870,11 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; + if (attrs[XFRMA_IF_ID]) + if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + if (p->index) - xp = xfrm_policy_byid(net, mark, type, p->dir, p->index, delete, &err); + xp = xfrm_policy_byid(net, mark, if_id, type, p->dir, p->index, delete, &err); else { struct nlattr *rt = attrs[XFRMA_SEC_CTX]; struct xfrm_sec_ctx *ctx; @@ -1845,7 +1891,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; } - xp = xfrm_policy_bysel_ctx(net, mark, type, p->dir, &p->sel, + xp = xfrm_policy_bysel_ctx(net, mark, if_id, type, p->dir, &p->sel, ctx, delete, &err); security_xfrm_policy_free(ctx); } @@ -1968,6 +2014,10 @@ static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct if (err) goto out_cancel; + err = xfrm_if_id_put(skb, x->if_id); + if (err) + goto out_cancel; + nlmsg_end(skb, nlh); return 0; @@ -2109,6 +2159,7 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, int err = -ENOENT; struct xfrm_mark m; u32 mark = xfrm_mark_get(attrs, &m); + u32 if_id = 0; err = copy_from_user_policy_type(&type, attrs); if (err) @@ -2118,8 +2169,11 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; + if (attrs[XFRMA_IF_ID]) + if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + if (p->index) - xp = xfrm_policy_byid(net, mark, type, p->dir, p->index, 0, &err); + xp = xfrm_policy_byid(net, mark, if_id, type, p->dir, p->index, 0, &err); else { struct nlattr *rt = attrs[XFRMA_SEC_CTX]; struct xfrm_sec_ctx *ctx; @@ -2136,7 +2190,7 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; } - xp = xfrm_policy_bysel_ctx(net, mark, type, p->dir, + xp = xfrm_policy_bysel_ctx(net, mark, if_id, type, p->dir, &p->sel, ctx, 0, &err); security_xfrm_policy_free(ctx); } @@ -2520,7 +2574,9 @@ static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_PROTO] = { .type = NLA_U8 }, [XFRMA_ADDRESS_FILTER] = { .len = sizeof(struct xfrm_address_filter) }, [XFRMA_OFFLOAD_DEV] = { .len = sizeof(struct xfrm_user_offload) }, - [XFRMA_OUTPUT_MARK] = { .len = NLA_U32 }, + [XFRMA_SET_MARK] = { .type = NLA_U32 }, + [XFRMA_SET_MARK_MASK] = { .type = NLA_U32 }, + [XFRMA_IF_ID] = { .type = NLA_U32 }, }; static const struct nla_policy xfrma_spd_policy[XFRMA_SPD_MAX+1] = { @@ -2573,11 +2629,6 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, const struct xfrm_link *link; int type, err; -#ifdef CONFIG_COMPAT - if (in_compat_syscall()) - return -EOPNOTSUPP; -#endif - type = nlh->nlmsg_type; if (type > XFRM_MSG_MAX) return -EINVAL; @@ -2652,6 +2703,10 @@ static int build_expire(struct sk_buff *skb, struct xfrm_state *x, const struct if (err) return err; + err = xfrm_if_id_put(skb, x->if_id); + if (err) + return err; + nlmsg_end(skb, nlh); return 0; } @@ -2745,8 +2800,12 @@ static inline size_t xfrm_sa_len(struct xfrm_state *x) l += nla_total_size(sizeof(x->props.extra_flags)); if (x->xso.dev) l += nla_total_size(sizeof(x->xso)); - if (x->props.output_mark) - l += nla_total_size(sizeof(x->props.output_mark)); + if (x->props.smark.v | x->props.smark.m) { + l += nla_total_size(sizeof(x->props.smark.v)); + l += nla_total_size(sizeof(x->props.smark.m)); + } + if (x->if_id) + l += nla_total_size(sizeof(x->if_id)); /* Must count x->lastused as it may become non-zero behind our back. */ l += nla_total_size_64bit(sizeof(u64)); @@ -2875,6 +2934,8 @@ static int build_acquire(struct sk_buff *skb, struct xfrm_state *x, err = copy_to_user_policy_type(xp->type, skb); if (!err) err = xfrm_mark_put(skb, &xp->mark); + if (!err) + err = xfrm_if_id_put(skb, xp->if_id); if (err) { nlmsg_cancel(skb, nlh); return err; @@ -2990,6 +3051,8 @@ static int build_polexpire(struct sk_buff *skb, struct xfrm_policy *xp, err = copy_to_user_policy_type(xp->type, skb); if (!err) err = xfrm_mark_put(skb, &xp->mark); + if (!err) + err = xfrm_if_id_put(skb, xp->if_id); if (err) { nlmsg_cancel(skb, nlh); return err; @@ -3069,6 +3132,8 @@ static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, const struct km_e err = copy_to_user_policy_type(xp->type, skb); if (!err) err = xfrm_mark_put(skb, &xp->mark); + if (!err) + err = xfrm_if_id_put(skb, xp->if_id); if (err) goto out_free_skb; diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include index 28bfb4378dbd..e8574c3fcb07 100644 --- a/scripts/Kbuild.include +++ b/scripts/Kbuild.include @@ -144,6 +144,37 @@ cc-disable-warning = $(call try-run,\ # Expands to either gcc or clang cc-name = $(shell $(CC) -v 2>&1 | grep -q "clang version" && echo clang || echo gcc) +# __cc-version +# Returns compiler version +__cc-version = $(shell $(CONFIG_SHELL) $(srctree)/scripts/$(cc-name)-version.sh $(CC)) + +# __cc-fullversion +# Returns full compiler version +__cc-fullversion = $(shell $(CONFIG_SHELL) \ + $(srctree)/scripts/$(cc-name)-version.sh -p $(CC)) + +# __cc-ifversion +# Matches compiler name and version +# Usage: EXTRA_CFLAGS += $(call cc-if-name-version, gcc, -lt, 0402, -O1) +__cc-ifversion = $(shell [ $(cc-name) = $(1) ] && [ $(__cc-version) $(2) $(3) ] && echo $(4) || echo $(5)) + +# __cc-if-fullversion +# Matches compiler name and full version +# Usage: EXTRA_CFLAGS += $(call cc-if-name-fullversion, gcc, -lt, 040502, -O1) +__cc-if-fullversion = $(shell [ $(cc-name) = $(1) ] && [ $(__cc-fullversion) $(2) $(3) ] && echo $(4) || echo $(5)) + +# gcc-ifversion +gcc-ifversion = $(call __cc-ifversion, gcc, $(1), $(2), $(3), $(4)) + +# gcc-if-fullversion +gcc-if-fullversion = (call __cc-if-fullversion, gcc, $(1), $(2), $(3), $(4)) + +# clang-ifversion +clang-ifversion = $(call __cc-ifversion, clang, $(1), $(2), $(3), $(4)) + +# clang-if-fullversion +clang-if-fullversion = (call __cc-if-fullversion, clang, $(1), $(2), $(3), $(4)) + # cc-version cc-version = $(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-version.sh $(CC)) @@ -151,9 +182,9 @@ cc-version = $(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-version.sh $(CC)) cc-fullversion = $(shell $(CONFIG_SHELL) \ $(srctree)/scripts/gcc-version.sh -p $(CC)) -# cc-ifversion -# Usage: EXTRA_CFLAGS += $(call cc-ifversion, -lt, 0402, -O1) -cc-ifversion = $(shell [ $(cc-version) $(1) $(2) ] && echo $(3) || echo $(4)) +# backward compatibility +cc-ifversion = $(gcc-ifversion) +cc-if-fullversion = $(gcc-if-fullversion) # cc-if-fullversion # Usage: EXTRA_CFLAGS += $(call cc-if-fullversion, -lt, 040502, -O1) @@ -173,6 +204,10 @@ ld-option = $(call try-run, $(LD) $(LDFLAGS) $(1) -v,$(1),$(2)) # Important: no spaces around options ar-option = $(call try-run, $(AR) rc$(1) "$$TMP",$(1),$(2)) +# ld-name +# Expands to either bfd or gold +ld-name = $(shell $(LD) -v 2>&1 | grep -q "GNU gold" && echo gold || echo bfd) + # ld-version # Note this is mainly for HJ Lu's 3 number binutil versions ld-version = $(shell $(LD) --version | $(srctree)/scripts/ld-version.sh) @@ -181,6 +216,18 @@ ld-version = $(shell $(LD) --version | $(srctree)/scripts/ld-version.sh) # Usage: $(call ld-ifversion, -ge, 22252, y) ld-ifversion = $(shell [ $(ld-version) $(1) $(2) ] && echo $(3) || echo $(4)) +# __ld-ifversion +# Usage: $(call __ld-ifversion, gold, -ge, 112000000, y) +__ld-ifversion = $(shell [ $(ld-name) = $(1) ] && [ $(ld-version) $(2) $(3) ] && echo $(4) || echo $(5)) + +# bfd-ifversion +# Usage: $(call bfd-ifversion, -ge, 227000000, y) +bfd-ifversion = $(call __ld-ifversion, bfd, $(1), $(2), $(3), $(4)) + +# gold-ifversion +# Usage: $(call gold-ifversion, -ge, 112000000, y) +gold-ifversion = $(call __ld-ifversion, gold, $(1), $(2), $(3), $(4)) + ###### ### diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 3edc9c04cb46..48622d8c0e31 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -210,6 +210,23 @@ else cmd_cc_o_c = $(CC) $(c_flags) -c -o $(@D)/.tmp_$(@F) $< +ifdef CONFIG_LTO_CLANG +# Generate .o.symversions files for each .o with exported symbols, and link these +# to the kernel and/or modules at the end. +cmd_modversions_c = \ + if $(OBJDUMP) -h $(@D)/.tmp_$(@F) >/dev/null 2>/dev/null; then \ + if $(OBJDUMP) -h $(@D)/.tmp_$(@F) | grep -q __ksymtab; then \ + $(call cmd_gensymtypes_c,$(KBUILD_SYMTYPES),$(@:.o=.symtypes)) \ + > $(@D)/$(@F).symversions; \ + fi; \ + else \ + if $(LLVM_DIS) -o=- $(@D)/.tmp_$(@F) | grep -q __ksymtab; then \ + $(call cmd_gensymtypes_c,$(KBUILD_SYMTYPES),$(@:.o=.symtypes)) \ + > $(@D)/$(@F).symversions; \ + fi; \ + fi; \ + mv -f $(@D)/.tmp_$(@F) $@; +else cmd_modversions_c = \ if $(OBJDUMP) -h $(@D)/.tmp_$(@F) | grep -q __ksymtab; then \ $(call cmd_gensymtypes_c,$(KBUILD_SYMTYPES),$(@:.o=.symtypes)) \ @@ -222,12 +239,19 @@ cmd_modversions_c = \ mv -f $(@D)/.tmp_$(@F) $@; \ fi; endif +endif ifdef CONFIG_FTRACE_MCOUNT_RECORD ifdef BUILD_C_RECORDMCOUNT ifeq ("$(origin RECORDMCOUNT_WARN)", "command line") RECORDMCOUNT_FLAGS = -w endif + +ifdef CONFIG_LTO_CLANG +# With LTO, we postpone running recordmcount until after the LTO link step, so +# let's export the parameters for the link script. +export RECORDMCOUNT_FLAGS +else # Due to recursion, we must skip empty.o. # The empty.o file is created in the make process in order to determine # the target endianness and word size. It is made before all other C @@ -236,22 +260,28 @@ sub_cmd_record_mcount = \ if [ $(@) != "scripts/mod/empty.o" ]; then \ $(objtree)/scripts/recordmcount $(RECORDMCOUNT_FLAGS) "$(@)"; \ fi; +endif + recordmcount_source := $(srctree)/scripts/recordmcount.c \ $(srctree)/scripts/recordmcount.h -else +else # !BUILD_C_RECORDMCOUNT sub_cmd_record_mcount = set -e ; perl $(srctree)/scripts/recordmcount.pl "$(ARCH)" \ "$(if $(CONFIG_CPU_BIG_ENDIAN),big,little)" \ "$(if $(CONFIG_64BIT),64,32)" \ "$(OBJDUMP)" "$(OBJCOPY)" "$(CC) $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS)" \ "$(LD)" "$(NM)" "$(RM)" "$(MV)" \ "$(if $(part-of-module),1,0)" "$(@)"; + recordmcount_source := $(srctree)/scripts/recordmcount.pl endif # BUILD_C_RECORDMCOUNT + +ifndef CONFIG_LTO_CLANG cmd_record_mcount = \ if [ "$(findstring $(CC_FLAGS_FTRACE),$(_c_flags))" = \ "$(CC_FLAGS_FTRACE)" ]; then \ $(sub_cmd_record_mcount) \ fi; +endif endif # CONFIG_FTRACE_MCOUNT_RECORD ifdef CONFIG_STACK_VALIDATION @@ -460,8 +490,29 @@ $(sort $(subdir-obj-y)): $(subdir-ym) ; # ifdef builtin-target +ifdef CONFIG_LTO_CLANG + ifdef CONFIG_MODVERSIONS + # combine symversions for later processing + update_lto_symversions = \ + rm -f $@.symversions; \ + for i in $(filter-out FORCE,$^); do \ + if [ -f $$i.symversions ]; then \ + cat $$i.symversions \ + >> $@.symversions; \ + fi; \ + done; + endif + # rebuild the symbol table with llvm-ar to include IR files + update_lto_symtable = ; \ + mv -f $@ $@.tmp; \ + $(LLVM_AR) rcsT$(KBUILD_ARFLAGS) $@ \ + $$($(AR) t $@.tmp); \ + rm -f $@.tmp +endif + ifdef CONFIG_THIN_ARCHIVES - cmd_make_builtin = rm -f $@; $(AR) rcSTP$(KBUILD_ARFLAGS) + cmd_make_builtin = $(update_lto_symversions) \ + rm -f $@; $(AR) rcSTP$(KBUILD_ARFLAGS) cmd_make_empty_builtin = rm -f $@; $(AR) rcSTP$(KBUILD_ARFLAGS) quiet_cmd_link_o_target = AR $@ else @@ -502,7 +553,11 @@ ifdef lib-target quiet_cmd_link_l_target = AR $@ ifdef CONFIG_THIN_ARCHIVES - cmd_link_l_target = rm -f $@; $(AR) rcsTP$(KBUILD_ARFLAGS) $@ $(lib-y) + cmd_link_l_target = \ + $(update_lto_symversions) \ + rm -f $@; \ + $(AR) rcsTP$(KBUILD_ARFLAGS) $@ $(lib-y) \ + $(update_lto_symtable) else cmd_link_l_target = rm -f $@; $(AR) rcs$(KBUILD_ARFLAGS) $@ $(lib-y) endif @@ -520,14 +575,36 @@ else ref_prefix = EXTERN( endif -quiet_cmd_export_list = EXPORTS $@ -cmd_export_list = $(OBJDUMP) -h $< | \ - sed -ne '/___ksymtab/s/.*+\([^ ]*\).*/$(ref_prefix)\1)/p' >$(ksyms-lds);\ - rm -f $(dummy-object);\ +filter_export_list = sed -ne '/___ksymtab/s/.*+\([^ "]*\).*/$(ref_prefix)\1)/p' +link_export_list = rm -f $(dummy-object);\ echo | $(CC) $(a_flags) -c -o $(dummy-object) -x assembler -;\ $(LD) $(ld_flags) -r -o $@ -T $(ksyms-lds) $(dummy-object);\ rm $(dummy-object) $(ksyms-lds) +quiet_cmd_export_list = EXPORTS $@ + +ifdef CONFIG_LTO_CLANG +# objdump doesn't understand IR files and llvm-dis doesn't support archives, +# so we'll walk through each file in the archive separately +cmd_export_list = \ + rm -f $(ksyms-lds); \ + for o in $$($(AR) t $<); do \ + if $(OBJDUMP) -h $$o >/dev/null 2>/dev/null; then \ + $(OBJDUMP) -h $$o | \ + $(filter_export_list) \ + >>$(ksyms-lds); \ + else \ + $(LLVM_DIS) -o=- $$o | \ + $(filter_export_list) \ + >>$(ksyms-lds); \ + fi; \ + done; \ + $(link_export_list) +else +cmd_export_list = $(OBJDUMP) -h $< | $(filter_export_list) >$(ksyms-lds); \ + $(link_export_list) +endif + $(obj)/lib-ksyms.o: $(lib-target) FORCE $(call if_changed,export_list) @@ -555,23 +632,32 @@ cmd_link_multi-link = $(LD) $(ld_flags) -r -o $@ $(link_multi_deps) $(cmd_secana ifdef CONFIG_THIN_ARCHIVES quiet_cmd_link_multi-y = AR $@ - cmd_link_multi-y = rm -f $@; $(AR) rcSTP$(KBUILD_ARFLAGS) $@ $(link_multi_deps) + cmd_link_multi-y = $(update_lto_symversions) \ + rm -f $@; $(AR) rcSTP$(KBUILD_ARFLAGS) $@ $(link_multi_deps) \ + $(update_lto_symtable) else quiet_cmd_link_multi-y = LD $@ cmd_link_multi-y = $(cmd_link_multi-link) endif quiet_cmd_link_multi-m = LD [M] $@ -cmd_link_multi-m = $(cmd_link_multi-link) + +ifdef CONFIG_LTO_CLANG + # don't compile IR until needed + cmd_link_multi-m = $(cmd_link_multi-y) +else + cmd_link_multi-m = $(cmd_link_multi-link) +endif $(multi-used-y): FORCE $(call if_changed,link_multi-y) -$(call multi_depend, $(multi-used-y), .o, -objs -y) $(multi-used-m): FORCE $(call if_changed,link_multi-m) @{ echo $(@:.o=.ko); echo $(link_multi_deps); \ $(cmd_undef_syms); } > $(MODVERDIR)/$(@F:.o=.mod) + +$(call multi_depend, $(multi-used-y), .o, -objs -y) $(call multi_depend, $(multi-used-m), .o, -objs -y -m) targets += $(multi-used-y) $(multi-used-m) diff --git a/scripts/Makefile.clean b/scripts/Makefile.clean index 808d09f27ad4..11f4067f03e8 100644 --- a/scripts/Makefile.clean +++ b/scripts/Makefile.clean @@ -12,7 +12,7 @@ include scripts/Kbuild.include # The filename Kbuild has precedence over Makefile kbuild-dir := $(if $(filter /%,$(src)),$(src),$(srctree)/$(src)) -include $(if $(wildcard $(kbuild-dir)/Kbuild), $(kbuild-dir)/Kbuild, $(kbuild-dir)/Makefile) +-include $(if $(wildcard $(kbuild-dir)/Kbuild), $(kbuild-dir)/Kbuild, $(kbuild-dir)/Makefile) # Figure out what we need to build from the various variables # ========================================================================== diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index aac94d962ed6..36fa07a8f979 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -318,6 +318,12 @@ $(obj)/%.dtb: $(src)/%.dts FORCE dtc-tmp = $(subst $(comma),_,$(dot-target).dts.tmp) +# cat +# --------------------------------------------------------------------------- +# Concatentate multiple files together +quiet_cmd_cat = CAT $@ +cmd_cat = (cat $(filter-out FORCE,$^) > $@) || (rm -f $@; false) + # Bzip2 # --------------------------------------------------------------------------- diff --git a/scripts/Makefile.modinst b/scripts/Makefile.modinst index 51ca0244fc8a..96524c6fa7a5 100644 --- a/scripts/Makefile.modinst +++ b/scripts/Makefile.modinst @@ -30,7 +30,7 @@ quiet_cmd_modules_install = INSTALL $@ INSTALL_MOD_DIR ?= extra ext-mod-dir = $(INSTALL_MOD_DIR)$(subst $(patsubst %/,%,$(KBUILD_EXTMOD)),,$(@D)) -modinst_dir = $(if $(KBUILD_EXTMOD),$(ext-mod-dir),kernel/$(@D)) +modinst_dir ?= $(if $(KBUILD_EXTMOD),$(ext-mod-dir),kernel/$(@D)) $(modules): $(call cmd,modules_install,$(MODLIB)/$(modinst_dir)) diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost index cf6f33b2633d..2fd5d98afbbc 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -83,12 +83,28 @@ modpost = scripts/mod/modpost \ MODPOST_OPT=$(subst -i,-n,$(filter -i,$(MAKEFLAGS))) +# If CONFIG_LTO_CLANG is enabled, .o files are either LLVM IR, or empty, so we +# need to link them into actual objects before passing them to modpost +modpost-ext = $(if $(CONFIG_LTO_CLANG),.lto,) + +ifdef CONFIG_LTO_CLANG +quiet_cmd_cc_lto_link_modules = LD [M] $@ +cmd_cc_lto_link_modules = \ + $(LD) $(ld_flags) -r -o $(@) \ + $(shell [ -s $(@:$(modpost-ext).o=.o.symversions) ] && \ + echo -T $(@:$(modpost-ext).o=.o.symversions)) \ + --whole-archive $(filter-out FORCE,$^) + +$(modules:.ko=$(modpost-ext).o): %$(modpost-ext).o: %.o FORCE + $(call if_changed,cc_lto_link_modules) +endif + # We can go over command line length here, so be careful. quiet_cmd_modpost = MODPOST $(words $(filter-out vmlinux FORCE, $^)) modules - cmd_modpost = $(MODLISTCMD) | sed 's/\.ko$$/.o/' | $(modpost) $(MODPOST_OPT) -s -T - + cmd_modpost = $(MODLISTCMD) | sed 's/\.ko$$/$(modpost-ext)\.o/' | $(modpost) $(MODPOST_OPT) -s -T - PHONY += __modpost -__modpost: $(modules:.ko=.o) FORCE +__modpost: $(modules:.ko=$(modpost-ext).o) FORCE $(call cmd,modpost) $(wildcard vmlinux) quiet_cmd_kernel-mod = MODPOST $@ @@ -98,8 +114,7 @@ vmlinux.o: FORCE $(call cmd,kernel-mod) # Declare generated files as targets for modpost -$(modules:.ko=.mod.c): __modpost ; - +$(modules:.ko=$(modpost-ext).mod.c): __modpost ; # Step 5), compile all *.mod.c files @@ -110,22 +125,37 @@ quiet_cmd_cc_o_c = CC $@ cmd_cc_o_c = $(CC) $(c_flags) $(KBUILD_CFLAGS_MODULE) $(CFLAGS_MODULE) \ -c -o $@ $< -$(modules:.ko=.mod.o): %.mod.o: %.mod.c FORCE +$(modules:.ko=.mod.o): %.mod.o: %$(modpost-ext).mod.c FORCE $(call if_changed_dep,cc_o_c) -targets += $(modules:.ko=.mod.o) +targets += $(modules:.ko=$(modpost-ext).mod.o) ARCH_POSTLINK := $(wildcard $(srctree)/arch/$(SRCARCH)/Makefile.postlink) # Step 6), final link of the modules with optional arch pass after final link quiet_cmd_ld_ko_o = LD [M] $@ + +ifdef CONFIG_LTO_CLANG + cmd_ld_ko_o = \ + $(LD) -r $(LDFLAGS) \ + $(KBUILD_LDFLAGS_MODULE) $(LDFLAGS_MODULE) \ + $(shell [ -s $(@:.ko=.o.symversions) ] && \ + echo -T $(@:.ko=.o.symversions)) \ + -o $@ --whole-archive \ + $(filter-out FORCE,$(^:$(modpost-ext).o=.o)) + + ifdef CONFIG_FTRACE_MCOUNT_RECORD + cmd_ld_ko_o += ; $(objtree)/scripts/recordmcount $(RECORDMCOUNT_FLAGS) $@ + endif +else cmd_ld_ko_o = \ $(LD) -r $(LDFLAGS) \ $(KBUILD_LDFLAGS_MODULE) $(LDFLAGS_MODULE) \ -o $@ $(filter-out FORCE,$^) ; \ $(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) $@, true) +endif -$(modules): %.ko :%.o %.mod.o FORCE +$(modules): %.ko: %$(modpost-ext).o %.mod.o FORCE +$(call if_changed,ld_ko_o) targets += $(modules) diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 8b80bac055e4..bfc5dfcbbc9c 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -5762,7 +5762,7 @@ sub process { for (my $count = $linenr; $count <= $lc; $count++) { my $fmt = get_quoted_string($lines[$count - 1], raw_line($count, 0)); $fmt =~ s/%%//g; - if ($fmt =~ /(\%[\*\d\.]*p(?![\WFfSsBKRraEhMmIiUDdgVCbGNO]).)/) { + if ($fmt =~ /(\%[\*\d\.]*p(?![\WFfSsBKRraEhMmIiUDdgVCbGNOx]).)/) { $bad_extension = $1; last; } diff --git a/scripts/clang-android.sh b/scripts/clang-android.sh new file mode 100755 index 000000000000..9186c4f48576 --- /dev/null +++ b/scripts/clang-android.sh @@ -0,0 +1,4 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +$* -dM -E - </dev/null 2>&1 | grep -q __ANDROID__ && echo "y" diff --git a/scripts/clang-version.sh b/scripts/clang-version.sh new file mode 100755 index 000000000000..9780efa56980 --- /dev/null +++ b/scripts/clang-version.sh @@ -0,0 +1,33 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# clang-version [-p] clang-command +# +# Prints the compiler version of `clang-command' in a canonical 4-digit form +# such as `0500' for clang-5.0 etc. +# +# With the -p option, prints the patchlevel as well, for example `050001' for +# clang-5.0.1 etc. +# + +if [ "$1" = "-p" ] ; then + with_patchlevel=1; + shift; +fi + +compiler="$*" + +if [ ${#compiler} -eq 0 ]; then + echo "Error: No compiler specified." + printf "Usage:\n\t$0 <clang-command>\n" + exit 1 +fi + +MAJOR=$(echo __clang_major__ | $compiler -E -x c - | tail -n 1) +MINOR=$(echo __clang_minor__ | $compiler -E -x c - | tail -n 1) +if [ "x$with_patchlevel" != "x" ] ; then + PATCHLEVEL=$(echo __clang_patchlevel__ | $compiler -E -x c - | tail -n 1) + printf "%02d%02d%02d\\n" $MAJOR $MINOR $PATCHLEVEL +else + printf "%02d%02d\\n" $MAJOR $MINOR +fi diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index e6818b8e7141..cfa44718cef7 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -61,9 +61,40 @@ archive_builtin() ${AR} rcsTP${KBUILD_ARFLAGS} built-in.o \ ${KBUILD_VMLINUX_INIT} \ ${KBUILD_VMLINUX_MAIN} + + if [ -n "${CONFIG_LTO_CLANG}" ]; then + mv -f built-in.o built-in.o.tmp + ${LLVM_AR} rcsT${KBUILD_ARFLAGS} built-in.o $(${AR} t built-in.o.tmp) + rm -f built-in.o.tmp + fi fi } +# If CONFIG_LTO_CLANG is selected, collect generated symbol versions into +# .tmp_symversions +modversions() +{ + if [ -z "${CONFIG_LTO_CLANG}" ]; then + return + fi + + if [ -z "${CONFIG_MODVERSIONS}" ]; then + return + fi + + rm -f .tmp_symversions + + for a in built-in.o ${KBUILD_VMLINUX_LIBS}; do + for o in $(${AR} t $a); do + if [ -f ${o}.symversions ]; then + cat ${o}.symversions >> .tmp_symversions + fi + done + done + + echo "-T .tmp_symversions" +} + # Link of vmlinux.o used for section mismatch analysis # ${1} output file modpost_link() @@ -84,7 +115,29 @@ modpost_link() ${KBUILD_VMLINUX_LIBS} \ --end-group" fi - ${LD} ${LDFLAGS} -r -o ${1} ${objects} + + if [ -n "${CONFIG_LTO_CLANG}" ]; then + # This might take a while, so indicate that we're doing + # an LTO link + info LTO vmlinux.o + else + info LD vmlinux.o + fi + + ${LD} ${LDFLAGS} -r -o ${1} $(modversions) ${objects} +} + +# If CONFIG_LTO_CLANG is selected, we postpone running recordmcount until +# we have compiled LLVM IR to an object file. +recordmcount() +{ + if [ -z "${CONFIG_LTO_CLANG}" ]; then + return + fi + + if [ -n "${CONFIG_FTRACE_MCOUNT_RECORD}" ]; then + scripts/recordmcount ${RECORDMCOUNT_FLAGS} $* + fi } # Link of vmlinux @@ -96,8 +149,16 @@ vmlinux_link() local objects if [ "${SRCARCH}" != "um" ]; then - if [ -n "${CONFIG_THIN_ARCHIVES}" ]; then - objects="--whole-archive \ + local ld=${LD} + local ldflags="${LDFLAGS} ${LDFLAGS_vmlinux}" + + if [ -n "${LDFINAL_vmlinux}" ]; then + ld=${LDFINAL_vmlinux} + ldflags="${LDFLAGS_FINAL_vmlinux} ${LDFLAGS_vmlinux}" + fi + + if [[ -n "${CONFIG_THIN_ARCHIVES}" && -z "${CONFIG_LTO_CLANG}" ]]; then + objects="--whole-archive \ built-in.o \ --no-whole-archive \ --start-group \ @@ -113,8 +174,7 @@ vmlinux_link() ${1}" fi - ${LD} ${LDFLAGS} ${LDFLAGS_vmlinux} -o ${2} \ - -T ${lds} ${objects} + ${ld} ${ldflags} -o ${2} -T ${lds} ${objects} else if [ -n "${CONFIG_THIN_ARCHIVES}" ]; then objects="-Wl,--whole-archive \ @@ -141,7 +201,6 @@ vmlinux_link() fi } - # Create ${2} .o file with all symbols from the ${1} object file kallsyms() { @@ -192,6 +251,7 @@ cleanup() rm -f .tmp_System.map rm -f .tmp_kallsyms* rm -f .tmp_version + rm -f .tmp_symversions rm -f .tmp_vmlinux* rm -f built-in.o rm -f System.map @@ -253,12 +313,22 @@ ${MAKE} -f "${srctree}/scripts/Makefile.build" obj=init GCC_PLUGINS_CFLAGS="${GC archive_builtin #link vmlinux.o -info LD vmlinux.o modpost_link vmlinux.o # modpost vmlinux.o to check for section mismatches ${MAKE} -f "${srctree}/scripts/Makefile.modpost" vmlinux.o +if [ -n "${CONFIG_LTO_CLANG}" ]; then + # Re-use vmlinux.o, so we can avoid the slow LTO link step in + # vmlinux_link + KBUILD_VMLINUX_INIT= + KBUILD_VMLINUX_MAIN=vmlinux.o + KBUILD_VMLINUX_LIBS= + + # Call recordmcount if needed + recordmcount vmlinux.o +fi + kallsymso="" kallsyms_vmlinux="" if [ -n "${CONFIG_KALLSYMS}" ]; then diff --git a/scripts/mod/Makefile b/scripts/mod/Makefile index 42c5d50f2bcc..e014b2fdd069 100644 --- a/scripts/mod/Makefile +++ b/scripts/mod/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 OBJECT_FILES_NON_STANDARD := y +CFLAGS_empty.o += $(DISABLE_LTO) hostprogs-y := modpost mk_elfconfig always := $(hostprogs-y) empty.o diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index b6eb929899c5..b522afbc3a3b 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -953,6 +953,7 @@ static const char *const head_sections[] = { ".head.text*", NULL }; static const char *const linker_symbols[] = { "__init_begin", "_sinittext", "_einittext", NULL }; static const char *const optim_symbols[] = { "*.constprop.*", NULL }; +static const char *const cfi_symbols[] = { "*.cfi", NULL }; enum mismatch { TEXT_TO_ANY_INIT, @@ -1182,6 +1183,17 @@ static const struct sectioncheck *section_mismatch( * whitelisting, which relies on pattern-matching against symbol * names to work. (One situation where gcc can autogenerate ELF * local symbols is when "-fsection-anchors" is used.) + * + * Pattern 7: + * With CONFIG_CFI_CLANG, clang appends .cfi to all indirectly called + * functions and creates a function stub with the original name. This + * stub is always placed in .text, even if the actual function with the + * .cfi postfix is in .init.text or .exit.text. + * This pattern is identified by + * tosec = init or exit section + * fromsec = text section + * tosym = *.cfi + * **/ static int secref_whitelist(const struct sectioncheck *mismatch, const char *fromsec, const char *fromsym, @@ -1224,6 +1236,12 @@ static int secref_whitelist(const struct sectioncheck *mismatch, if (strstarts(fromsym, ".L")) return 0; + /* Check for pattern 7 */ + if (match(fromsec, text_sections) && + match(tosec, init_exit_sections) && + match(tosym, cfi_symbols)) + return 0; + return 1; } diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c index a4888e955466..d4e674f6ffaf 100644 --- a/scripts/recordmcount.c +++ b/scripts/recordmcount.c @@ -424,7 +424,8 @@ is_mcounted_section_name(char const *const txtname) strcmp(".softirqentry.text", txtname) == 0 || strcmp(".kprobes.text", txtname) == 0 || strcmp(".cpuidle.text", txtname) == 0 || - strcmp(".text.unlikely", txtname) == 0; + (strncmp(".text.", txtname, 6) == 0 && + strcmp(".text..ftrace", txtname) != 0); } /* 32 bit and 64 bit are very similar */ diff --git a/security/Kconfig b/security/Kconfig index 87f2a6f842fd..8b6c5e9528e0 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -18,6 +18,15 @@ config SECURITY_DMESG_RESTRICT If you are unsure how to answer this question, answer N. +config SECURITY_PERF_EVENTS_RESTRICT + bool "Restrict unprivileged use of performance events" + depends on PERF_EVENTS + help + If you say Y here, the kernel.perf_event_paranoid sysctl + will be set to 3 by default, and no unprivileged use of the + perf_event_open syscall will be permitted unless it is + changed. + config SECURITY bool "Enable different security models" depends on SYSFS @@ -263,5 +272,7 @@ config DEFAULT_SECURITY default "apparmor" if DEFAULT_SECURITY_APPARMOR default "" if DEFAULT_SECURITY_DAC +source "security/Kconfig.hardening" + endmenu diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening new file mode 100644 index 000000000000..f3784bca35ea --- /dev/null +++ b/security/Kconfig.hardening @@ -0,0 +1,41 @@ +menu "Kernel hardening options" + +menu "Memory initialization" + +choice + prompt "Initialize kernel stack variables at function entry" + default INIT_STACK_NONE + help + This option enables initialization of stack variables at + function entry time. This has the possibility to have the + greatest coverage (since all functions can have their + variables initialized), but the performance impact depends + on the function calling complexity of a given workload's + syscalls. + + This chooses the level of coverage over classes of potentially + uninitialized variables. The selected class will be + initialized before use in a function. + + config INIT_STACK_NONE + bool "no automatic initialization (weakest)" + help + Disable automatic stack variable initialization. + This leaves the kernel vulnerable to the standard + classes of uninitialized stack variable exploits + and information exposures. + + config INIT_STACK_ALL + bool "0xAA-init everything on the stack (strongest)" + help + Initializes everything on the stack with a 0xAA + pattern. This is intended to eliminate all classes + of uninitialized stack variable exploits and information + exposures, even variables that were warned to have been + left uninitialized. + +endchoice + +endmenu + +endmenu diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 1c6b389ad8f9..b9dcf7ec95a0 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -813,11 +813,11 @@ static const struct kernel_param_ops param_ops_aalockpolicy = { .get = param_get_aalockpolicy }; -static int param_set_audit(const char *val, struct kernel_param *kp); -static int param_get_audit(char *buffer, struct kernel_param *kp); +static int param_set_audit(const char *val, const struct kernel_param *kp); +static int param_get_audit(char *buffer, const struct kernel_param *kp); -static int param_set_mode(const char *val, struct kernel_param *kp); -static int param_get_mode(char *buffer, struct kernel_param *kp); +static int param_set_mode(const char *val, const struct kernel_param *kp); +static int param_get_mode(char *buffer, const struct kernel_param *kp); /* Flag values, also controllable via /sys/module/apparmor/parameters * We define special types as we want to do additional mediation. @@ -951,7 +951,7 @@ static int param_get_aauint(char *buffer, const struct kernel_param *kp) return param_get_uint(buffer, kp); } -static int param_get_audit(char *buffer, struct kernel_param *kp) +static int param_get_audit(char *buffer, const struct kernel_param *kp) { if (!apparmor_enabled) return -EINVAL; @@ -960,7 +960,7 @@ static int param_get_audit(char *buffer, struct kernel_param *kp) return sprintf(buffer, "%s", audit_mode_names[aa_g_audit]); } -static int param_set_audit(const char *val, struct kernel_param *kp) +static int param_set_audit(const char *val, const struct kernel_param *kp) { int i; @@ -981,7 +981,7 @@ static int param_set_audit(const char *val, struct kernel_param *kp) return -EINVAL; } -static int param_get_mode(char *buffer, struct kernel_param *kp) +static int param_get_mode(char *buffer, const struct kernel_param *kp) { if (!apparmor_enabled) return -EINVAL; @@ -991,7 +991,7 @@ static int param_get_mode(char *buffer, struct kernel_param *kp) return sprintf(buffer, "%s", aa_profile_mode_names[aa_g_profile_mode]); } -static int param_set_mode(const char *val, struct kernel_param *kp) +static int param_set_mode(const char *val, const struct kernel_param *kp) { int i; diff --git a/security/commoncap.c b/security/commoncap.c index ac031fa39190..6cbf41d1e77d 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -31,6 +31,10 @@ #include <linux/binfmts.h> #include <linux/personality.h> +#ifdef CONFIG_ANDROID_PARANOID_NETWORK +#include <linux/android_aid.h> +#endif + /* * If a non-root user executes a setuid-root binary in * !secure(SECURE_NOROOT) mode, then we raise capabilities. @@ -54,7 +58,7 @@ static void warn_setuid_and_fcaps_mixed(const char *fname) } /** - * cap_capable - Determine whether a task has a particular effective capability + * __cap_capable - Determine whether a task has a particular effective capability * @cred: The credentials to use * @ns: The user namespace in which we need the capability * @cap: The capability to check for @@ -68,7 +72,7 @@ static void warn_setuid_and_fcaps_mixed(const char *fname) * cap_has_capability() returns 0 when a task has a capability, but the * kernel's capable() and has_capability() returns 1 for this case. */ -int cap_capable(const struct cred *cred, struct user_namespace *targ_ns, +int __cap_capable(const struct cred *cred, struct user_namespace *targ_ns, int cap, int audit) { struct user_namespace *ns = targ_ns; @@ -106,6 +110,27 @@ int cap_capable(const struct cred *cred, struct user_namespace *targ_ns, /* We never get here */ } +int cap_capable(const struct cred *cred, struct user_namespace *targ_ns, + int cap, int audit) +{ + int ret = __cap_capable(cred, targ_ns, cap, audit); + +#ifdef CONFIG_ANDROID_PARANOID_NETWORK + if (ret != 0 && cap == CAP_NET_RAW && in_egroup_p(AID_NET_RAW)) { + printk("Process %s granted CAP_NET_RAW from Android group net_raw.\n", current->comm); + printk(" Please update the .rc file to explictly set 'capabilities NET_RAW'\n"); + printk(" Implicit grants are deprecated and will be removed in the future.\n"); + return 0; + } + if (ret != 0 && cap == CAP_NET_ADMIN && in_egroup_p(AID_NET_ADMIN)) { + printk("Process %s granted CAP_NET_ADMIN from Android group net_admin.\n", current->comm); + printk(" Please update the .rc file to explictly set 'capabilities NET_ADMIN'\n"); + printk(" Implicit grants are deprecated and will be removed in the future.\n"); + return 0; + } +#endif + return ret; +} /** * cap_settime - Determine whether the current process may set the system clock * @ts: The time to set diff --git a/security/inode.c b/security/inode.c index 829f15672e01..0107dc7d3232 100644 --- a/security/inode.c +++ b/security/inode.c @@ -127,7 +127,7 @@ static struct dentry *securityfs_create_dentry(const char *name, umode_t mode, dir = d_inode(parent); inode_lock(dir); - dentry = lookup_one_len(name, parent, strlen(name)); + dentry = lookup_one_len2(name, mount, parent, strlen(name)); if (IS_ERR(dentry)) goto out; diff --git a/security/security.c b/security/security.c index 4fbe4e495c02..fb4910f0d0e2 100644 --- a/security/security.c +++ b/security/security.c @@ -12,6 +12,7 @@ * (at your option) any later version. */ +#include <linux/bpf.h> #include <linux/capability.h> #include <linux/dcache.h> #include <linux/module.h> @@ -597,6 +598,7 @@ int security_path_chown(const struct path *path, kuid_t uid, kgid_t gid) return 0; return call_int_hook(path_chown, 0, path, uid, gid); } +EXPORT_SYMBOL(security_path_chown); int security_path_chroot(const struct path *path) { @@ -1712,3 +1714,34 @@ int security_audit_rule_match(u32 secid, u32 field, u32 op, void *lsmrule, actx); } #endif /* CONFIG_AUDIT */ + +#ifdef CONFIG_BPF_SYSCALL +int security_bpf(int cmd, union bpf_attr *attr, unsigned int size) +{ + return call_int_hook(bpf, 0, cmd, attr, size); +} +int security_bpf_map(struct bpf_map *map, fmode_t fmode) +{ + return call_int_hook(bpf_map, 0, map, fmode); +} +int security_bpf_prog(struct bpf_prog *prog) +{ + return call_int_hook(bpf_prog, 0, prog); +} +int security_bpf_map_alloc(struct bpf_map *map) +{ + return call_int_hook(bpf_map_alloc_security, 0, map); +} +int security_bpf_prog_alloc(struct bpf_prog_aux *aux) +{ + return call_int_hook(bpf_prog_alloc_security, 0, aux); +} +void security_bpf_map_free(struct bpf_map *map) +{ + call_void_hook(bpf_map_free_security, map); +} +void security_bpf_prog_free(struct bpf_prog_aux *aux) +{ + call_void_hook(bpf_prog_free_security, aux); +} +#endif /* CONFIG_BPF_SYSCALL */ diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 5def19ec1179..3bbfca4accd8 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -85,6 +85,7 @@ #include <linux/export.h> #include <linux/msg.h> #include <linux/shm.h> +#include <linux/bpf.h> #include "avc.h" #include "objsec.h" @@ -1839,6 +1840,10 @@ static inline int file_path_has_perm(const struct cred *cred, return inode_has_perm(cred, file_inode(file), av, &ad); } +#ifdef CONFIG_BPF_SYSCALL +static int bpf_fd_pass(struct file *file, u32 sid); +#endif + /* Check whether a task can use an open file descriptor to access an inode in a given way. Check access to the descriptor itself, and then use dentry_has_perm to @@ -1869,6 +1874,12 @@ static int file_has_perm(const struct cred *cred, goto out; } +#ifdef CONFIG_BPF_SYSCALL + rc = bpf_fd_pass(file, cred_sid(cred)); + if (rc) + return rc; +#endif + /* av is zero if only checking access to the descriptor. */ rc = 0; if (av) @@ -2189,6 +2200,12 @@ static int selinux_binder_transfer_file(struct task_struct *from, return rc; } +#ifdef CONFIG_BPF_SYSCALL + rc = bpf_fd_pass(file, sid); + if (rc) + return rc; +#endif + if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; @@ -6304,6 +6321,139 @@ static void selinux_ib_free_security(void *ib_sec) } #endif +#ifdef CONFIG_BPF_SYSCALL +static int selinux_bpf(int cmd, union bpf_attr *attr, + unsigned int size) +{ + u32 sid = current_sid(); + int ret; + + switch (cmd) { + case BPF_MAP_CREATE: + ret = avc_has_perm(sid, sid, SECCLASS_BPF, BPF__MAP_CREATE, + NULL); + break; + case BPF_PROG_LOAD: + ret = avc_has_perm(sid, sid, SECCLASS_BPF, BPF__PROG_LOAD, + NULL); + break; + default: + ret = 0; + break; + } + + return ret; +} + +static u32 bpf_map_fmode_to_av(fmode_t fmode) +{ + u32 av = 0; + + if (fmode & FMODE_READ) + av |= BPF__MAP_READ; + if (fmode & FMODE_WRITE) + av |= BPF__MAP_WRITE; + return av; +} + +/* This function will check the file pass through unix socket or binder to see + * if it is a bpf related object. And apply correspinding checks on the bpf + * object based on the type. The bpf maps and programs, not like other files and + * socket, are using a shared anonymous inode inside the kernel as their inode. + * So checking that inode cannot identify if the process have privilege to + * access the bpf object and that's why we have to add this additional check in + * selinux_file_receive and selinux_binder_transfer_files. + */ +static int bpf_fd_pass(struct file *file, u32 sid) +{ + struct bpf_security_struct *bpfsec; + struct bpf_prog *prog; + struct bpf_map *map; + int ret; + + if (file->f_op == &bpf_map_fops) { + map = file->private_data; + bpfsec = map->security; + ret = avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF, + bpf_map_fmode_to_av(file->f_mode), NULL); + if (ret) + return ret; + } else if (file->f_op == &bpf_prog_fops) { + prog = file->private_data; + bpfsec = prog->aux->security; + ret = avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF, + BPF__PROG_RUN, NULL); + if (ret) + return ret; + } + return 0; +} + +static int selinux_bpf_map(struct bpf_map *map, fmode_t fmode) +{ + u32 sid = current_sid(); + struct bpf_security_struct *bpfsec; + + bpfsec = map->security; + return avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF, + bpf_map_fmode_to_av(fmode), NULL); +} + +static int selinux_bpf_prog(struct bpf_prog *prog) +{ + u32 sid = current_sid(); + struct bpf_security_struct *bpfsec; + + bpfsec = prog->aux->security; + return avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF, + BPF__PROG_RUN, NULL); +} + +static int selinux_bpf_map_alloc(struct bpf_map *map) +{ + struct bpf_security_struct *bpfsec; + + bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL); + if (!bpfsec) + return -ENOMEM; + + bpfsec->sid = current_sid(); + map->security = bpfsec; + + return 0; +} + +static void selinux_bpf_map_free(struct bpf_map *map) +{ + struct bpf_security_struct *bpfsec = map->security; + + map->security = NULL; + kfree(bpfsec); +} + +static int selinux_bpf_prog_alloc(struct bpf_prog_aux *aux) +{ + struct bpf_security_struct *bpfsec; + + bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL); + if (!bpfsec) + return -ENOMEM; + + bpfsec->sid = current_sid(); + aux->security = bpfsec; + + return 0; +} + +static void selinux_bpf_prog_free(struct bpf_prog_aux *aux) +{ + struct bpf_security_struct *bpfsec = aux->security; + + aux->security = NULL; + kfree(bpfsec); +} +#endif + static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(binder_set_context_mgr, selinux_binder_set_context_mgr), LSM_HOOK_INIT(binder_transaction, selinux_binder_transaction), @@ -6523,6 +6673,16 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(audit_rule_match, selinux_audit_rule_match), LSM_HOOK_INIT(audit_rule_free, selinux_audit_rule_free), #endif + +#ifdef CONFIG_BPF_SYSCALL + LSM_HOOK_INIT(bpf, selinux_bpf), + LSM_HOOK_INIT(bpf_map, selinux_bpf_map), + LSM_HOOK_INIT(bpf_prog, selinux_bpf_prog), + LSM_HOOK_INIT(bpf_map_alloc_security, selinux_bpf_map_alloc), + LSM_HOOK_INIT(bpf_prog_alloc_security, selinux_bpf_prog_alloc), + LSM_HOOK_INIT(bpf_map_free_security, selinux_bpf_map_free), + LSM_HOOK_INIT(bpf_prog_free_security, selinux_bpf_prog_free), +#endif }; static __init int selinux_init(void) diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h index 45ef6a0c17cc..702bdaf07252 100644 --- a/security/selinux/include/classmap.h +++ b/security/selinux/include/classmap.h @@ -115,7 +115,7 @@ struct security_class_mapping secclass_map[] = { { COMMON_IPC_PERMS, NULL } }, { "netlink_route_socket", { COMMON_SOCK_PERMS, - "nlmsg_read", "nlmsg_write", NULL } }, + "nlmsg_read", "nlmsg_write", "nlmsg_readpriv", NULL } }, { "netlink_tcpdiag_socket", { COMMON_SOCK_PERMS, "nlmsg_read", "nlmsg_write", NULL } }, @@ -239,6 +239,8 @@ struct security_class_mapping secclass_map[] = { { "access", NULL } }, { "infiniband_endport", { "manage_subnet", NULL } }, + { "bpf", + {"map_create", "map_read", "map_write", "prog_load", "prog_run"} }, { NULL } }; diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h index 1649cd18eb0b..3d54468ce334 100644 --- a/security/selinux/include/objsec.h +++ b/security/selinux/include/objsec.h @@ -150,6 +150,10 @@ struct pkey_security_struct { u32 sid; /* SID of pkey */ }; +struct bpf_security_struct { + u32 sid; /*SID of bpf obj creater*/ +}; + extern unsigned int selinux_checkreqprot; #endif /* _SELINUX_OBJSEC_H_ */ diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h index 02f0412d42f2..45cc615fddae 100644 --- a/security/selinux/include/security.h +++ b/security/selinux/include/security.h @@ -81,6 +81,7 @@ enum { extern char *selinux_policycap_names[__POLICYDB_CAPABILITY_MAX]; +extern int selinux_android_netlink_route; extern int selinux_policycap_netpeer; extern int selinux_policycap_openperm; extern int selinux_policycap_extsockclass; @@ -276,6 +277,7 @@ extern struct vfsmount *selinuxfs_mount; extern void selnl_notify_setenforce(int val); extern void selnl_notify_policyload(u32 seqno); extern int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm); +extern void selinux_nlmsg_init(void); #endif /* _SELINUX_SECURITY_H_ */ diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c index 7b7433a1a34c..963930b4e2f8 100644 --- a/security/selinux/nlmsgtab.c +++ b/security/selinux/nlmsgtab.c @@ -28,7 +28,7 @@ struct nlmsg_perm { u32 perm; }; -static const struct nlmsg_perm nlmsg_route_perms[] = +static struct nlmsg_perm nlmsg_route_perms[] = { { RTM_NEWLINK, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_DELLINK, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, @@ -195,3 +195,27 @@ int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm) return err; } + +static void nlmsg_set_getlink_perm(u32 perm) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(nlmsg_route_perms); i++) { + if (nlmsg_route_perms[i].nlmsg_type == RTM_GETLINK) { + nlmsg_route_perms[i].perm = perm; + break; + } + } +} + +/** + * Use nlmsg_readpriv as the permission for RTM_GETLINK messages if the + * netlink_route_getlink policy capability is set. Otherwise use nlmsg_read. + */ +void selinux_nlmsg_init(void) +{ + if (selinux_android_netlink_route) + nlmsg_set_getlink_perm(NETLINK_ROUTE_SOCKET__NLMSG_READPRIV); + else + nlmsg_set_getlink_perm(NETLINK_ROUTE_SOCKET__NLMSG_READ); +} diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c index 9d9f6bb1e56e..51564b2aba9e 100644 --- a/security/selinux/ss/policydb.c +++ b/security/selinux/ss/policydb.c @@ -2386,6 +2386,10 @@ int policydb_read(struct policydb *p, void *fp) p->reject_unknown = !!(le32_to_cpu(buf[1]) & REJECT_UNKNOWN); p->allow_unknown = !!(le32_to_cpu(buf[1]) & ALLOW_UNKNOWN); + if ((le32_to_cpu(buf[1]) & POLICYDB_CONFIG_ANDROID_NETLINK_ROUTE)) { + p->android_netlink_route = 1; + } + if (p->policyvers >= POLICYDB_VERSION_POLCAP) { rc = ebitmap_read(&p->policycaps, fp); if (rc) diff --git a/security/selinux/ss/policydb.h b/security/selinux/ss/policydb.h index 215f8f30ac5a..dbb0ed57ed8b 100644 --- a/security/selinux/ss/policydb.h +++ b/security/selinux/ss/policydb.h @@ -238,6 +238,7 @@ struct genfs { /* The policy database */ struct policydb { int mls_enabled; + int android_netlink_route; /* symbol tables */ struct symtab symtab[SYM_NUM]; @@ -324,6 +325,7 @@ extern int policydb_write(struct policydb *p, void *fp); #define PERM_SYMTAB_SIZE 32 #define POLICYDB_CONFIG_MLS 1 +#define POLICYDB_CONFIG_ANDROID_NETLINK_ROUTE (1 << 31) /* the config flags related to unknown classes/perms are bits 2 and 3 */ #define REJECT_UNKNOWN 0x00000002 diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index 0158cde957ee..37a4ec12d74a 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -80,6 +80,7 @@ char *selinux_policycap_names[__POLICYDB_CAPABILITY_MAX] = { "nnp_nosuid_transition" }; +int selinux_android_netlink_route; int selinux_policycap_netpeer; int selinux_policycap_openperm; int selinux_policycap_extsockclass; @@ -2026,6 +2027,9 @@ static void security_load_policycaps(void) pr_info("SELinux: unknown policy capability %u\n", i); } + + selinux_android_netlink_route = policydb.android_netlink_route; + selinux_nlmsg_init(); } static int security_preserve_bools(struct policydb *p); diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c index 6bf6a204341e..5ef1c15e88ad 100644 --- a/tools/accounting/getdelays.c +++ b/tools/accounting/getdelays.c @@ -203,6 +203,8 @@ static void print_delayacct(struct taskstats *t) "SWAP %15s%15s%15s\n" " %15llu%15llu%15llums\n" "RECLAIM %12s%15s%15s\n" + " %15llu%15llu%15llums\n" + "THRASHING%12s%15s%15s\n" " %15llu%15llu%15llums\n", "count", "real total", "virtual total", "delay total", "delay average", @@ -222,7 +224,11 @@ static void print_delayacct(struct taskstats *t) "count", "delay total", "delay average", (unsigned long long)t->freepages_count, (unsigned long long)t->freepages_delay_total, - average_ms(t->freepages_delay_total, t->freepages_count)); + average_ms(t->freepages_delay_total, t->freepages_count), + "count", "delay total", "delay average", + (unsigned long long)t->thrashing_count, + (unsigned long long)t->thrashing_delay_total, + average_ms(t->thrashing_delay_total, t->thrashing_count)); } static void task_context_switch_counts(struct taskstats *t) diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h index 6448cdd9a350..44cdb652e0da 100644 --- a/tools/include/uapi/linux/fcntl.h +++ b/tools/include/uapi/linux/fcntl.h @@ -41,6 +41,7 @@ #define F_SEAL_SHRINK 0x0002 /* prevent file from shrinking */ #define F_SEAL_GROW 0x0004 /* prevent file from growing */ #define F_SEAL_WRITE 0x0008 /* prevent writes */ +#define F_SEAL_FUTURE_WRITE 0x0010 /* prevent future writes */ /* (1U << 31) is reserved for signed error codes */ /* diff --git a/verity_dev_keys.x509 b/verity_dev_keys.x509 new file mode 100644 index 000000000000..86399c3c1dd7 --- /dev/null +++ b/verity_dev_keys.x509 @@ -0,0 +1,24 @@ +-----BEGIN CERTIFICATE----- +MIID/TCCAuWgAwIBAgIJAJcPmDkJqolJMA0GCSqGSIb3DQEBBQUAMIGUMQswCQYD +VQQGEwJVUzETMBEGA1UECAwKQ2FsaWZvcm5pYTEWMBQGA1UEBwwNTW91bnRhaW4g +VmlldzEQMA4GA1UECgwHQW5kcm9pZDEQMA4GA1UECwwHQW5kcm9pZDEQMA4GA1UE +AwwHQW5kcm9pZDEiMCAGCSqGSIb3DQEJARYTYW5kcm9pZEBhbmRyb2lkLmNvbTAe +Fw0xNDExMDYxOTA3NDBaFw00MjAzMjQxOTA3NDBaMIGUMQswCQYDVQQGEwJVUzET +MBEGA1UECAwKQ2FsaWZvcm5pYTEWMBQGA1UEBwwNTW91bnRhaW4gVmlldzEQMA4G +A1UECgwHQW5kcm9pZDEQMA4GA1UECwwHQW5kcm9pZDEQMA4GA1UEAwwHQW5kcm9p +ZDEiMCAGCSqGSIb3DQEJARYTYW5kcm9pZEBhbmRyb2lkLmNvbTCCASIwDQYJKoZI +hvcNAQEBBQADggEPADCCAQoCggEBAOjreE0vTVSRenuzO9vnaWfk0eQzYab0gqpi +6xAzi6dmD+ugoEKJmbPiuE5Dwf21isZ9uhUUu0dQM46dK4ocKxMRrcnmGxydFn6o +fs3ODJMXOkv2gKXL/FdbEPdDbxzdu8z3yk+W67udM/fW7WbaQ3DO0knu+izKak/3 +T41c5uoXmQ81UNtAzRGzGchNVXMmWuTGOkg6U+0I2Td7K8yvUMWhAWPPpKLtVH9r +AL5TzjYNR92izdKcz3AjRsI3CTjtpiVABGeX0TcjRSuZB7K9EK56HV+OFNS6I1NP +jdD7FIShyGlqqZdUOkAUZYanbpgeT5N7QL6uuqcGpoTOkalu6kkCAwEAAaNQME4w +HQYDVR0OBBYEFH5DM/m7oArf4O3peeKO0ZIEkrQPMB8GA1UdIwQYMBaAFH5DM/m7 +oArf4O3peeKO0ZIEkrQPMAwGA1UdEwQFMAMBAf8wDQYJKoZIhvcNAQEFBQADggEB +AHO3NSvDE5jFvMehGGtS8BnFYdFKRIglDMc4niWSzhzOVYRH4WajxdtBWc5fx0ix +NF/+hVKVhP6AIOQa+++sk+HIi7RvioPPbhjcsVlZe7cUEGrLSSveGouQyc+j0+m6 +JF84kszIl5GGNMTnx0XRPO+g8t6h5LWfnVydgZfpGRRg+WHewk1U2HlvTjIceb0N +dcoJ8WKJAFWdcuE7VIm4w+vF/DYX/A2Oyzr2+QRhmYSv1cusgAeC1tvH4ap+J1Lg +UnOu5Kh/FqPLLSwNVQp4Bu7b9QFfqK8Moj84bj88NqRGZgDyqzuTrFxn6FW7dmyA +yttuAJAEAymk1mipd9+zp38= +-----END CERTIFICATE----- |