diff options
268 files changed, 2664 insertions, 1585 deletions
@@ -160,6 +160,7 @@ Jeff Layton <jlayton@kernel.org> <jlayton@primarydata.com> Jeff Layton <jlayton@kernel.org> <jlayton@redhat.com> Jens Axboe <axboe@suse.de> Jens Osterkamp <Jens.Osterkamp@de.ibm.com> +Jernej Skrabec <jernej.skrabec@gmail.com> <jernej.skrabec@siol.net> Jiri Slaby <jirislaby@kernel.org> <jirislaby@gmail.com> Jiri Slaby <jirislaby@kernel.org> <jslaby@novell.com> Jiri Slaby <jirislaby@kernel.org> <jslaby@suse.com> diff --git a/Documentation/ABI/obsolete/sysfs-class-dax b/Documentation/ABI/obsolete/sysfs-class-dax index 0faf1354cd05..5bcce27458e3 100644 --- a/Documentation/ABI/obsolete/sysfs-class-dax +++ b/Documentation/ABI/obsolete/sysfs-class-dax @@ -1,7 +1,7 @@ What: /sys/class/dax/ Date: May, 2016 KernelVersion: v4.7 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: Device DAX is the device-centric analogue of Filesystem DAX (CONFIG_FS_DAX). It allows memory ranges to be allocated and mapped without need of an intervening file diff --git a/Documentation/ABI/obsolete/sysfs-kernel-fadump_registered b/Documentation/ABI/obsolete/sysfs-kernel-fadump_registered index 0360be39c98e..dae880b1a5d5 100644 --- a/Documentation/ABI/obsolete/sysfs-kernel-fadump_registered +++ b/Documentation/ABI/obsolete/sysfs-kernel-fadump_registered @@ -1,4 +1,4 @@ -This ABI is renamed and moved to a new location /sys/kernel/fadump/registered.¬ +This ABI is renamed and moved to a new location /sys/kernel/fadump/registered. What: /sys/kernel/fadump_registered Date: Feb 2012 diff --git a/Documentation/ABI/obsolete/sysfs-kernel-fadump_release_mem b/Documentation/ABI/obsolete/sysfs-kernel-fadump_release_mem index 6ce0b129ab12..ca2396edb5f1 100644 --- a/Documentation/ABI/obsolete/sysfs-kernel-fadump_release_mem +++ b/Documentation/ABI/obsolete/sysfs-kernel-fadump_release_mem @@ -1,4 +1,4 @@ -This ABI is renamed and moved to a new location /sys/kernel/fadump/release_mem.¬ +This ABI is renamed and moved to a new location /sys/kernel/fadump/release_mem. What: /sys/kernel/fadump_release_mem Date: Feb 2012 diff --git a/Documentation/ABI/removed/sysfs-bus-nfit b/Documentation/ABI/removed/sysfs-bus-nfit index ae8c1ca53828..277437005def 100644 --- a/Documentation/ABI/removed/sysfs-bus-nfit +++ b/Documentation/ABI/removed/sysfs-bus-nfit @@ -1,7 +1,7 @@ What: /sys/bus/nd/devices/regionX/nfit/ecc_unit_size Date: Aug, 2017 KernelVersion: v4.14 (Removed v4.18) -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) Size of a write request to a DIMM that will not incur a read-modify-write cycle at the memory controller. diff --git a/Documentation/ABI/testing/sysfs-bus-nfit b/Documentation/ABI/testing/sysfs-bus-nfit index 63ef0b9ecce7..e7282d184a74 100644 --- a/Documentation/ABI/testing/sysfs-bus-nfit +++ b/Documentation/ABI/testing/sysfs-bus-nfit @@ -5,7 +5,7 @@ Interface Table (NFIT)' section in the ACPI specification What: /sys/bus/nd/devices/nmemX/nfit/serial Date: Jun, 2015 KernelVersion: v4.2 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) Serial number of the NVDIMM (non-volatile dual in-line memory module), assigned by the module vendor. @@ -14,7 +14,7 @@ Description: What: /sys/bus/nd/devices/nmemX/nfit/handle Date: Apr, 2015 KernelVersion: v4.2 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) The address (given by the _ADR object) of the device on its parent bus of the NVDIMM device containing the NVDIMM region. @@ -23,7 +23,7 @@ Description: What: /sys/bus/nd/devices/nmemX/nfit/device Date: Apr, 2015 KernelVersion: v4.1 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) Device id for the NVDIMM, assigned by the module vendor. @@ -31,7 +31,7 @@ Description: What: /sys/bus/nd/devices/nmemX/nfit/rev_id Date: Jun, 2015 KernelVersion: v4.2 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) Revision of the NVDIMM, assigned by the module vendor. @@ -39,7 +39,7 @@ Description: What: /sys/bus/nd/devices/nmemX/nfit/phys_id Date: Apr, 2015 KernelVersion: v4.2 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) Handle (i.e., instance number) for the SMBIOS (system management BIOS) Memory Device structure describing the NVDIMM @@ -49,7 +49,7 @@ Description: What: /sys/bus/nd/devices/nmemX/nfit/flags Date: Jun, 2015 KernelVersion: v4.2 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) The flags in the NFIT memory device sub-structure indicate the state of the data on the nvdimm relative to its energy @@ -68,7 +68,7 @@ What: /sys/bus/nd/devices/nmemX/nfit/format1 What: /sys/bus/nd/devices/nmemX/nfit/formats Date: Apr, 2016 KernelVersion: v4.7 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) The interface codes indicate support for persistent memory mapped directly into system physical address space and / or a @@ -84,7 +84,7 @@ Description: What: /sys/bus/nd/devices/nmemX/nfit/vendor Date: Apr, 2016 KernelVersion: v4.7 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) Vendor id of the NVDIMM. @@ -92,7 +92,7 @@ Description: What: /sys/bus/nd/devices/nmemX/nfit/dsm_mask Date: May, 2016 KernelVersion: v4.7 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) The bitmask indicates the supported device specific control functions relative to the NVDIMM command family supported by the @@ -102,7 +102,7 @@ Description: What: /sys/bus/nd/devices/nmemX/nfit/family Date: Apr, 2016 KernelVersion: v4.7 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) Displays the NVDIMM family command sets. Values 0, 1, 2 and 3 correspond to NVDIMM_FAMILY_INTEL, @@ -118,7 +118,7 @@ Description: What: /sys/bus/nd/devices/nmemX/nfit/id Date: Apr, 2016 KernelVersion: v4.7 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) ACPI specification 6.2 section 5.2.25.9, defines an identifier for an NVDIMM, which refelects the id attribute. @@ -127,7 +127,7 @@ Description: What: /sys/bus/nd/devices/nmemX/nfit/subsystem_vendor Date: Apr, 2016 KernelVersion: v4.7 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) Sub-system vendor id of the NVDIMM non-volatile memory subsystem controller. @@ -136,7 +136,7 @@ Description: What: /sys/bus/nd/devices/nmemX/nfit/subsystem_rev_id Date: Apr, 2016 KernelVersion: v4.7 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) Sub-system revision id of the NVDIMM non-volatile memory subsystem controller, assigned by the non-volatile memory subsystem @@ -146,7 +146,7 @@ Description: What: /sys/bus/nd/devices/nmemX/nfit/subsystem_device Date: Apr, 2016 KernelVersion: v4.7 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) Sub-system device id for the NVDIMM non-volatile memory subsystem controller, assigned by the non-volatile memory @@ -156,7 +156,7 @@ Description: What: /sys/bus/nd/devices/ndbusX/nfit/revision Date: Jun, 2015 KernelVersion: v4.2 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) ACPI NFIT table revision number. @@ -164,7 +164,7 @@ Description: What: /sys/bus/nd/devices/ndbusX/nfit/scrub Date: Sep, 2016 KernelVersion: v4.9 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RW) This shows the number of full Address Range Scrubs (ARS) that have been completed since driver load time. Userspace can @@ -177,7 +177,7 @@ Description: What: /sys/bus/nd/devices/ndbusX/nfit/hw_error_scrub Date: Sep, 2016 KernelVersion: v4.9 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RW) Provides a way to toggle the behavior between just adding the address (cache line) where the MCE happened to the poison @@ -196,7 +196,7 @@ Description: What: /sys/bus/nd/devices/ndbusX/nfit/dsm_mask Date: Jun, 2017 KernelVersion: v4.13 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) The bitmask indicates the supported bus specific control functions. See the section named 'NVDIMM Root Device _DSMs' in @@ -205,7 +205,7 @@ Description: What: /sys/bus/nd/devices/ndbusX/nfit/firmware_activate_noidle Date: Apr, 2020 KernelVersion: v5.8 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RW) The Intel platform implementation of firmware activate support exposes an option let the platform force idle devices in @@ -225,7 +225,7 @@ Description: What: /sys/bus/nd/devices/regionX/nfit/range_index Date: Jun, 2015 KernelVersion: v4.2 -Contact: linux-nvdimm@lists.01.org +Contact: nvdimm@lists.linux.dev Description: (RO) A unique number provided by the BIOS to identify an address range. Used by NVDIMM Region Mapping Structure to uniquely refer diff --git a/Documentation/ABI/testing/sysfs-bus-papr-pmem b/Documentation/ABI/testing/sysfs-bus-papr-pmem index 8316c33862a0..92e2db0e2d3d 100644 --- a/Documentation/ABI/testing/sysfs-bus-papr-pmem +++ b/Documentation/ABI/testing/sysfs-bus-papr-pmem @@ -1,7 +1,7 @@ What: /sys/bus/nd/devices/nmemX/papr/flags Date: Apr, 2020 KernelVersion: v5.8 -Contact: linuxppc-dev <linuxppc-dev@lists.ozlabs.org>, linux-nvdimm@lists.01.org, +Contact: linuxppc-dev <linuxppc-dev@lists.ozlabs.org>, nvdimm@lists.linux.dev, Description: (RO) Report flags indicating various states of a papr-pmem NVDIMM device. Each flag maps to a one or @@ -36,7 +36,7 @@ Description: What: /sys/bus/nd/devices/nmemX/papr/perf_stats Date: May, 2020 KernelVersion: v5.9 -Contact: linuxppc-dev <linuxppc-dev@lists.ozlabs.org>, linux-nvdimm@lists.01.org, +Contact: linuxppc-dev <linuxppc-dev@lists.ozlabs.org>, nvdimm@lists.linux.dev, Description: (RO) Report various performance stats related to papr-scm NVDIMM device. Each stat is reported on a new line with each line diff --git a/Documentation/ABI/testing/sysfs-module b/Documentation/ABI/testing/sysfs-module index a485434d2a0f..88bddf192ceb 100644 --- a/Documentation/ABI/testing/sysfs-module +++ b/Documentation/ABI/testing/sysfs-module @@ -37,13 +37,13 @@ Description: Maximum time allowed for periodic transfers per microframe (μs) What: /sys/module/*/{coresize,initsize} Date: Jan 2012 -KernelVersion:»·3.3 +KernelVersion: 3.3 Contact: Kay Sievers <kay.sievers@vrfy.org> Description: Module size in bytes. What: /sys/module/*/taint Date: Jan 2012 -KernelVersion:»·3.3 +KernelVersion: 3.3 Contact: Kay Sievers <kay.sievers@vrfy.org> Description: Module taint flags: == ===================== diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst index 1d56a6b73a4e..7ca8df5451d4 100644 --- a/Documentation/admin-guide/sysctl/kernel.rst +++ b/Documentation/admin-guide/sysctl/kernel.rst @@ -483,10 +483,11 @@ modprobe ======== The full path to the usermode helper for autoloading kernel modules, -by default "/sbin/modprobe". This binary is executed when the kernel -requests a module. For example, if userspace passes an unknown -filesystem type to mount(), then the kernel will automatically request -the corresponding filesystem module by executing this usermode helper. +by default ``CONFIG_MODPROBE_PATH``, which in turn defaults to +"/sbin/modprobe". This binary is executed when the kernel requests a +module. For example, if userspace passes an unknown filesystem type +to mount(), then the kernel will automatically request the +corresponding filesystem module by executing this usermode helper. This usermode helper should insert the needed module into the kernel. This sysctl only affects module autoloading. It has no effect on the diff --git a/Documentation/block/data-integrity.rst b/Documentation/block/data-integrity.rst index 4f2452a95c43..07a97aa26668 100644 --- a/Documentation/block/data-integrity.rst +++ b/Documentation/block/data-integrity.rst @@ -1,4 +1,4 @@ -============== +============== Data Integrity ============== diff --git a/Documentation/cdrom/cdrom-standard.rst b/Documentation/cdrom/cdrom-standard.rst index 70500b189cc8..5845960ca382 100644 --- a/Documentation/cdrom/cdrom-standard.rst +++ b/Documentation/cdrom/cdrom-standard.rst @@ -146,18 +146,18 @@ with the kernel as a block device by registering the following general *struct file_operations*:: struct file_operations cdrom_fops = { - NULL, /∗ lseek ∗/ - block _read , /∗ read—general block-dev read ∗/ - block _write, /∗ write—general block-dev write ∗/ - NULL, /∗ readdir ∗/ - NULL, /∗ select ∗/ - cdrom_ioctl, /∗ ioctl ∗/ - NULL, /∗ mmap ∗/ - cdrom_open, /∗ open ∗/ - cdrom_release, /∗ release ∗/ - NULL, /∗ fsync ∗/ - NULL, /∗ fasync ∗/ - NULL /∗ revalidate ∗/ + NULL, /* lseek */ + block _read , /* read--general block-dev read */ + block _write, /* write--general block-dev write */ + NULL, /* readdir */ + NULL, /* select */ + cdrom_ioctl, /* ioctl */ + NULL, /* mmap */ + cdrom_open, /* open */ + cdrom_release, /* release */ + NULL, /* fsync */ + NULL, /* fasync */ + NULL /* revalidate */ }; Every active CD-ROM device shares this *struct*. The routines @@ -250,12 +250,12 @@ The drive-specific, minor-like information that is registered with `cdrom.c`, currently contains the following fields:: struct cdrom_device_info { - const struct cdrom_device_ops * ops; /* device operations for this major */ + const struct cdrom_device_ops * ops; /* device operations for this major */ struct list_head list; /* linked list of all device_info */ struct gendisk * disk; /* matching block layer disk */ void * handle; /* driver-dependent data */ - int mask; /* mask of capability: disables them */ + int mask; /* mask of capability: disables them */ int speed; /* maximum speed for reading data */ int capacity; /* number of discs in a jukebox */ @@ -569,7 +569,7 @@ the *CDC_CLOSE_TRAY* bit in *mask*. In the file `cdrom.c` you will encounter many constructions of the type:: - if (cdo->capability & ∼cdi->mask & CDC _⟨capability⟩) ... + if (cdo->capability & ~cdi->mask & CDC _<capability>) ... There is no *ioctl* to set the mask... The reason is that I think it is better to control the **behavior** rather than the diff --git a/Documentation/driver-api/nvdimm/nvdimm.rst b/Documentation/driver-api/nvdimm/nvdimm.rst index ef6d59e0978e..1d8302b89bd4 100644 --- a/Documentation/driver-api/nvdimm/nvdimm.rst +++ b/Documentation/driver-api/nvdimm/nvdimm.rst @@ -4,7 +4,7 @@ LIBNVDIMM: Non-Volatile Devices libnvdimm - kernel / libndctl - userspace helper library -linux-nvdimm@lists.01.org +nvdimm@lists.linux.dev Version 13 diff --git a/Documentation/driver-api/serial/index.rst b/Documentation/driver-api/serial/index.rst index 21351b8c95a4..8f7d7af3b90b 100644 --- a/Documentation/driver-api/serial/index.rst +++ b/Documentation/driver-api/serial/index.rst @@ -19,7 +19,6 @@ Serial drivers moxa-smartio n_gsm - rocket serial-iso7816 serial-rs485 diff --git a/Documentation/filesystems/erofs.rst b/Documentation/filesystems/erofs.rst index bf145171c2bf..832839fcf4c3 100644 --- a/Documentation/filesystems/erofs.rst +++ b/Documentation/filesystems/erofs.rst @@ -50,8 +50,8 @@ Here is the main features of EROFS: - Support POSIX.1e ACLs by using xattrs; - - Support transparent file compression as an option: - LZ4 algorithm with 4 KB fixed-sized output compression for high performance. + - Support transparent data compression as an option: + LZ4 algorithm with the fixed-sized output compression for high performance. The following git tree provides the file system user-space tools under development (ex, formatting tool mkfs.erofs): @@ -113,31 +113,31 @@ may not. All metadatas can be now observed in two different spaces (views): :: - |-> aligned with 8B - |-> followed closely - + meta_blkaddr blocks |-> another slot - _____________________________________________________________________ - | ... | inode | xattrs | extents | data inline | ... | inode ... - |________|_______|(optional)|(optional)|__(optional)_|_____|__________ - |-> aligned with the inode slot size - . . - . . - . . - . . - . . - . . - .____________________________________________________|-> aligned with 4B - | xattr_ibody_header | shared xattrs | inline xattrs | - |____________________|_______________|_______________| - |-> 12 bytes <-|->x * 4 bytes<-| . - . . . - . . . - . . . - ._______________________________.______________________. - | id | id | id | id | ... | id | ent | ... | ent| ... | - |____|____|____|____|______|____|_____|_____|____|_____| - |-> aligned with 4B - |-> aligned with 4B + |-> aligned with 8B + |-> followed closely + + meta_blkaddr blocks |-> another slot + _____________________________________________________________________ + | ... | inode | xattrs | extents | data inline | ... | inode ... + |________|_______|(optional)|(optional)|__(optional)_|_____|__________ + |-> aligned with the inode slot size + . . + . . + . . + . . + . . + . . + .____________________________________________________|-> aligned with 4B + | xattr_ibody_header | shared xattrs | inline xattrs | + |____________________|_______________|_______________| + |-> 12 bytes <-|->x * 4 bytes<-| . + . . . + . . . + . . . + ._______________________________.______________________. + | id | id | id | id | ... | id | ent | ... | ent| ... | + |____|____|____|____|______|____|_____|_____|____|_____| + |-> aligned with 4B + |-> aligned with 4B Inode could be 32 or 64 bytes, which can be distinguished from a common field which all inode versions have -- i_format:: @@ -175,13 +175,13 @@ may not. All metadatas can be now observed in two different spaces (views): Each share xattr can also be directly found by the following formula: xattr offset = xattr_blkaddr * block_size + 4 * xattr_id - :: +:: - |-> aligned by 4 bytes - + xattr_blkaddr blocks |-> aligned with 4 bytes - _________________________________________________________________________ - | ... | xattr_entry | xattr data | ... | xattr_entry | xattr data ... - |________|_____________|_____________|_____|______________|_______________ + |-> aligned by 4 bytes + + xattr_blkaddr blocks |-> aligned with 4 bytes + _________________________________________________________________________ + | ... | xattr_entry | xattr data | ... | xattr_entry | xattr data ... + |________|_____________|_____________|_____|______________|_______________ Directories ----------- @@ -193,48 +193,77 @@ algorithm (could refer to the related source code). :: - ___________________________ - / | - / ______________|________________ - / / | nameoff1 | nameoffN-1 - ____________.______________._______________v________________v__________ - | dirent | dirent | ... | dirent | filename | filename | ... | filename | - |___.0___|____1___|_____|___N-1__|____0_____|____1_____|_____|___N-1____| - \ ^ - \ | * could have - \ | trailing '\0' - \________________________| nameoff0 - - Directory block + ___________________________ + / | + / ______________|________________ + / / | nameoff1 | nameoffN-1 + ____________.______________._______________v________________v__________ + | dirent | dirent | ... | dirent | filename | filename | ... | filename | + |___.0___|____1___|_____|___N-1__|____0_____|____1_____|_____|___N-1____| + \ ^ + \ | * could have + \ | trailing '\0' + \________________________| nameoff0 + Directory block Note that apart from the offset of the first filename, nameoff0 also indicates the total number of directory entries in this block since it is no need to introduce another on-disk field at all. -Compression ------------ -Currently, EROFS supports 4KB fixed-sized output transparent file compression, -as illustrated below:: - - |---- Variant-Length Extent ----|-------- VLE --------|----- VLE ----- - clusterofs clusterofs clusterofs - | | | logical data - _________v_______________________________v_____________________v_______________ - ... | . | | . | | . | ... - ____|____.________|_____________|________.____|_____________|__.__________|____ - |-> cluster <-|-> cluster <-|-> cluster <-|-> cluster <-|-> cluster <-| - size size size size size - . . . . - . . . . - . . . . - _______._____________._____________._____________._____________________ - ... | | | | ... physical data - _______|_____________|_____________|_____________|_____________________ - |-> cluster <-|-> cluster <-|-> cluster <-| - size size size - -Currently each on-disk physical cluster can contain 4KB (un)compressed data -at most. For each logical cluster, there is a corresponding on-disk index to -describe its cluster type, physical cluster address, etc. - -See "struct z_erofs_vle_decompressed_index" in erofs_fs.h for more details. +Data compression +---------------- +EROFS implements LZ4 fixed-sized output compression which generates fixed-sized +compressed data blocks from variable-sized input in contrast to other existing +fixed-sized input solutions. Relatively higher compression ratios can be gotten +by using fixed-sized output compression since nowadays popular data compression +algorithms are mostly LZ77-based and such fixed-sized output approach can be +benefited from the historical dictionary (aka. sliding window). + +In details, original (uncompressed) data is turned into several variable-sized +extents and in the meanwhile, compressed into physical clusters (pclusters). +In order to record each variable-sized extent, logical clusters (lclusters) are +introduced as the basic unit of compress indexes to indicate whether a new +extent is generated within the range (HEAD) or not (NONHEAD). Lclusters are now +fixed in block size, as illustrated below:: + + |<- variable-sized extent ->|<- VLE ->| + clusterofs clusterofs clusterofs + | | | + _________v_________________________________v_______________________v________ + ... | . | | . | | . ... + ____|____._________|______________|________.___ _|______________|__.________ + |-> lcluster <-|-> lcluster <-|-> lcluster <-|-> lcluster <-| + (HEAD) (NONHEAD) (HEAD) (NONHEAD) . + . CBLKCNT . . + . . . + . . . + _______._____________________________.______________._________________ + ... | | | | ... + _______|______________|______________|______________|_________________ + |-> big pcluster <-|-> pcluster <-| + +A physical cluster can be seen as a container of physical compressed blocks +which contains compressed data. Previously, only lcluster-sized (4KB) pclusters +were supported. After big pcluster feature is introduced (available since +Linux v5.13), pcluster can be a multiple of lcluster size. + +For each HEAD lcluster, clusterofs is recorded to indicate where a new extent +starts and blkaddr is used to seek the compressed data. For each NONHEAD +lcluster, delta0 and delta1 are available instead of blkaddr to indicate the +distance to its HEAD lcluster and the next HEAD lcluster. A PLAIN lcluster is +also a HEAD lcluster except that its data is uncompressed. See the comments +around "struct z_erofs_vle_decompressed_index" in erofs_fs.h for more details. + +If big pcluster is enabled, pcluster size in lclusters needs to be recorded as +well. Let the delta0 of the first NONHEAD lcluster store the compressed block +count with a special flag as a new called CBLKCNT NONHEAD lcluster. It's easy +to understand its delta0 is constantly 1, as illustrated below:: + + __________________________________________________________ + | HEAD | NONHEAD | NONHEAD | ... | NONHEAD | HEAD | HEAD | + |__:___|_(CBLKCNT)_|_________|_____|_________|__:___|____:_| + |<----- a big pcluster (with CBLKCNT) ------>|<-- -->| + a lcluster-sized pcluster (without CBLKCNT) ^ + +If another HEAD follows a HEAD lcluster, there is no room to record CBLKCNT, +but it's easy to know the size of such pcluster is 1 lcluster as well. diff --git a/Documentation/hwmon/tmp103.rst b/Documentation/hwmon/tmp103.rst index e195a7d14309..b3ef81475cf8 100644 --- a/Documentation/hwmon/tmp103.rst +++ b/Documentation/hwmon/tmp103.rst @@ -21,10 +21,10 @@ Description The TMP103 is a digital output temperature sensor in a four-ball wafer chip-scale package (WCSP). The TMP103 is capable of reading temperatures to a resolution of 1°C. The TMP103 is specified for -operation over a temperature range of –40°C to +125°C. +operation over a temperature range of -40°C to +125°C. Resolution: 8 Bits -Accuracy: ±1°C Typ (–10°C to +100°C) +Accuracy: ±1°C Typ (-10°C to +100°C) The driver provides the common sysfs-interface for temperatures (see Documentation/hwmon/sysfs-interface.rst under Temperatures). diff --git a/Documentation/networking/device_drivers/ethernet/intel/i40e.rst b/Documentation/networking/device_drivers/ethernet/intel/i40e.rst index 8a9b18573688..2d3f6bd969a2 100644 --- a/Documentation/networking/device_drivers/ethernet/intel/i40e.rst +++ b/Documentation/networking/device_drivers/ethernet/intel/i40e.rst @@ -173,7 +173,7 @@ Director rule is added from ethtool (Sideband filter), ATR is turned off by the driver. To re-enable ATR, the sideband can be disabled with the ethtool -K option. For example:: - ethtool –K [adapter] ntuple [off|on] + ethtool -K [adapter] ntuple [off|on] If sideband is re-enabled after ATR is re-enabled, ATR remains enabled until a TCP-IP flow is added. When all TCP-IP sideband rules are deleted, ATR is @@ -688,7 +688,7 @@ shaper bw_rlimit: for each tc, sets minimum and maximum bandwidth rates. Totals must be equal or less than port speed. For example: min_rate 1Gbit 3Gbit: Verify bandwidth limit using network -monitoring tools such as ifstat or sar –n DEV [interval] [number of samples] +monitoring tools such as `ifstat` or `sar -n DEV [interval] [number of samples]` 2. Enable HW TC offload on interface:: diff --git a/Documentation/networking/device_drivers/ethernet/intel/iavf.rst b/Documentation/networking/device_drivers/ethernet/intel/iavf.rst index 52e037b11c97..25330b7b5168 100644 --- a/Documentation/networking/device_drivers/ethernet/intel/iavf.rst +++ b/Documentation/networking/device_drivers/ethernet/intel/iavf.rst @@ -179,7 +179,7 @@ shaper bw_rlimit: for each tc, sets minimum and maximum bandwidth rates. Totals must be equal or less than port speed. For example: min_rate 1Gbit 3Gbit: Verify bandwidth limit using network -monitoring tools such as ifstat or sar –n DEV [interval] [number of samples] +monitoring tools such as ``ifstat`` or ``sar -n DEV [interval] [number of samples]`` NOTE: Setting up channels via ethtool (ethtool -L) is not supported when the diff --git a/Documentation/process/kernel-enforcement-statement.rst b/Documentation/process/kernel-enforcement-statement.rst index e5a1be476047..dc2d813b2e79 100644 --- a/Documentation/process/kernel-enforcement-statement.rst +++ b/Documentation/process/kernel-enforcement-statement.rst @@ -1,4 +1,4 @@ -.. _process_statement_kernel: +.. _process_statement_kernel: Linux Kernel Enforcement Statement ---------------------------------- diff --git a/Documentation/security/tpm/xen-tpmfront.rst b/Documentation/security/tpm/xen-tpmfront.rst index 00d5b1db227d..31c67522f2ad 100644 --- a/Documentation/security/tpm/xen-tpmfront.rst +++ b/Documentation/security/tpm/xen-tpmfront.rst @@ -1,4 +1,4 @@ -============================= +============================= Virtual TPM interface for Xen ============================= diff --git a/Documentation/timers/no_hz.rst b/Documentation/timers/no_hz.rst index c4c70e1aada3..6cadad7c3aad 100644 --- a/Documentation/timers/no_hz.rst +++ b/Documentation/timers/no_hz.rst @@ -1,4 +1,4 @@ -====================================== +====================================== NO_HZ: Reducing Scheduling-Clock Ticks ====================================== diff --git a/Documentation/translations/zh_CN/SecurityBugs b/Documentation/translations/zh_CN/SecurityBugs deleted file mode 100644 index 2d0fffd122ce..000000000000 --- a/Documentation/translations/zh_CN/SecurityBugs +++ /dev/null @@ -1,50 +0,0 @@ -Chinese translated version of Documentation/admin-guide/security-bugs.rst - -If you have any comment or update to the content, please contact the -original document maintainer directly. However, if you have a problem -communicating in English you can also ask the Chinese maintainer for -help. Contact the Chinese maintainer if this translation is outdated -or if there is a problem with the translation. - -Chinese maintainer: Harry Wei <harryxiyou@gmail.com> ---------------------------------------------------------------------- -Documentation/admin-guide/security-bugs.rst 的中文翻译 - -如果想评论或更新本文的内容，请直接联系原文档的维护者。如果你使用英文 -交流有困难的话，也可以向中文版维护者求助。如果本翻译更新不及时或者翻 -译存在问题，请联系中文版维护者。 - -中文版维护者： 贾威威 Harry Wei <harryxiyou@gmail.com> -中文版翻译者： 贾威威 Harry Wei <harryxiyou@gmail.com> -中文版校译者： 贾威威 Harry Wei <harryxiyou@gmail.com> - - -以下为正文 ---------------------------------------------------------------------- -Linux内核开发者认为安全非常重要。因此，我们想要知道当一个有关于 -安全的漏洞被发现的时候，并且它可能会被尽快的修复或者公开。请把这个安全 -漏洞报告给Linux内核安全团队。 - -1) 联系 - -linux内核安全团队可以通过email<security@kernel.org>来联系。这是 -一组独立的安全工作人员，可以帮助改善漏洞报告并且公布和取消一个修复。安 -全团队有可能会从部分的维护者那里引进额外的帮助来了解并且修复安全漏洞。 -当遇到任何漏洞，所能提供的信息越多就越能诊断和修复。如果你不清楚什么 -是有帮助的信息，那就请重温一下admin-guide/reporting-bugs.rst文件中的概述过程。任 -何攻击性的代码都是非常有用的，未经报告者的同意不会被取消，除非它已经 -被公布于众。 - -2) 公开 - -Linux内核安全团队的宗旨就是和漏洞提交者一起处理漏洞的解决方案直 -到公开。我们喜欢尽快地完全公开漏洞。当一个漏洞或者修复还没有被完全地理 -解，解决方案没有通过测试或者供应商协调，可以合理地延迟公开。然而，我们 -期望这些延迟尽可能的短些，是可数的几天，而不是几个星期或者几个月。公开 -日期是通过安全团队和漏洞提供者以及供应商洽谈后的结果。公开时间表是从很 -短（特殊的，它已经被公众所知道）到几个星期。作为一个基本的默认政策，我 -们所期望通知公众的日期是7天的安排。 - -3) 保密协议 - -Linux内核安全团队不是一个正式的团体，因此不能加入任何的保密协议。 diff --git a/Documentation/usb/mtouchusb.rst b/Documentation/usb/mtouchusb.rst index d1111b74bf75..5ae1f74fe74b 100644 --- a/Documentation/usb/mtouchusb.rst +++ b/Documentation/usb/mtouchusb.rst @@ -1,4 +1,4 @@ -================ +================ mtouchusb driver ================ diff --git a/Documentation/usb/usb-serial.rst b/Documentation/usb/usb-serial.rst index 8fa7dbd3da9a..69586aeb60bb 100644 --- a/Documentation/usb/usb-serial.rst +++ b/Documentation/usb/usb-serial.rst @@ -1,4 +1,4 @@ -========== +========== USB serial ========== diff --git a/Documentation/virt/kvm/amd-memory-encryption.rst b/Documentation/virt/kvm/amd-memory-encryption.rst index 5ec8a1902e15..5c081c8c7164 100644 --- a/Documentation/virt/kvm/amd-memory-encryption.rst +++ b/Documentation/virt/kvm/amd-memory-encryption.rst @@ -22,7 +22,7 @@ to SEV:: [ecx]: Bits[31:0] Number of encrypted guests supported simultaneously -If support for SEV is present, MSR 0xc001_0010 (MSR_K8_SYSCFG) and MSR 0xc001_0015 +If support for SEV is present, MSR 0xc001_0010 (MSR_AMD64_SYSCFG) and MSR 0xc001_0015 (MSR_K7_HWCR) can be used to determine if it can be enabled:: 0xc001_0010: diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 22d077562149..7fcb2fd38f42 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -4803,7 +4803,7 @@ KVM_PV_VM_VERIFY 4.126 KVM_X86_SET_MSR_FILTER ---------------------------- -:Capability: KVM_X86_SET_MSR_FILTER +:Capability: KVM_CAP_X86_MSR_FILTER :Architectures: x86 :Type: vm ioctl :Parameters: struct kvm_msr_filter @@ -6715,7 +6715,7 @@ accesses that would usually trigger a #GP by KVM into the guest will instead get bounced to user space through the KVM_EXIT_X86_RDMSR and KVM_EXIT_X86_WRMSR exit notifications. -8.27 KVM_X86_SET_MSR_FILTER +8.27 KVM_CAP_X86_MSR_FILTER --------------------------- :Architectures: x86 diff --git a/Documentation/x86/amd-memory-encryption.rst b/Documentation/x86/amd-memory-encryption.rst index c48d452d0718..a1940ebe7be5 100644 --- a/Documentation/x86/amd-memory-encryption.rst +++ b/Documentation/x86/amd-memory-encryption.rst @@ -53,7 +53,7 @@ CPUID function 0x8000001f reports information related to SME:: system physical addresses, not guest physical addresses) -If support for SME is present, MSR 0xc00100010 (MSR_K8_SYSCFG) can be used to +If support for SME is present, MSR 0xc00100010 (MSR_AMD64_SYSCFG) can be used to determine if SME is enabled and/or to enable memory encryption:: 0xc0010010: @@ -79,7 +79,7 @@ The state of SME in the Linux kernel can be documented as follows: The CPU supports SME (determined through CPUID instruction). - Enabled: - Supported and bit 23 of MSR_K8_SYSCFG is set. + Supported and bit 23 of MSR_AMD64_SYSCFG is set. - Active: Supported, Enabled and the Linux kernel is actively applying @@ -89,7 +89,7 @@ The state of SME in the Linux kernel can be documented as follows: SME can also be enabled and activated in the BIOS. If SME is enabled and activated in the BIOS, then all memory accesses will be encrypted and it will not be necessary to activate the Linux memory encryption support. If the BIOS -merely enables SME (sets bit 23 of the MSR_K8_SYSCFG), then Linux can activate +merely enables SME (sets bit 23 of the MSR_AMD64_SYSCFG), then Linux can activate memory encryption by default (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=y) or by supplying mem_encrypt=on on the kernel command line. However, if BIOS does not enable SME, then Linux will not be able to activate memory encryption, even diff --git a/MAINTAINERS b/MAINTAINERS index bd7aff0c120f..008fcad7ac00 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1578,7 +1578,7 @@ F: drivers/clk/sunxi/ ARM/Allwinner sunXi SoC support M: Maxime Ripard <mripard@kernel.org> M: Chen-Yu Tsai <wens@csie.org> -R: Jernej Skrabec <jernej.skrabec@siol.net> +R: Jernej Skrabec <jernej.skrabec@gmail.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/sunxi/linux.git @@ -5089,7 +5089,7 @@ S: Maintained F: drivers/net/fddi/defza.* DEINTERLACE DRIVERS FOR ALLWINNER H3 -M: Jernej Skrabec <jernej.skrabec@siol.net> +M: Jernej Skrabec <jernej.skrabec@gmail.com> L: linux-media@vger.kernel.org S: Maintained T: git git://linuxtv.org/media_tree.git @@ -5237,7 +5237,7 @@ DEVICE DIRECT ACCESS (DAX) M: Dan Williams <dan.j.williams@intel.com> M: Vishal Verma <vishal.l.verma@intel.com> M: Dave Jiang <dave.jiang@intel.com> -L: linux-nvdimm@lists.01.org +L: nvdimm@lists.linux.dev S: Supported F: drivers/dax/ @@ -5632,14 +5632,14 @@ F: include/linux/power/smartreflex.h DRM DRIVER FOR ALLWINNER DE2 AND DE3 ENGINE M: Maxime Ripard <mripard@kernel.org> M: Chen-Yu Tsai <wens@csie.org> -R: Jernej Skrabec <jernej.skrabec@siol.net> +R: Jernej Skrabec <jernej.skrabec@gmail.com> L: dri-devel@lists.freedesktop.org S: Supported T: git git://anongit.freedesktop.org/drm/drm-misc F: drivers/gpu/drm/sun4i/sun8i* DRM DRIVER FOR ARM PL111 CLCD -M: Eric Anholt <eric@anholt.net> +M: Emma Anholt <emma@anholt.net> S: Supported T: git git://anongit.freedesktop.org/drm/drm-misc F: drivers/gpu/drm/pl111/ @@ -5719,7 +5719,7 @@ T: git git://anongit.freedesktop.org/drm/drm-misc F: drivers/gpu/drm/tiny/gm12u320.c DRM DRIVER FOR HX8357D PANELS -M: Eric Anholt <eric@anholt.net> +M: Emma Anholt <emma@anholt.net> S: Maintained T: git git://anongit.freedesktop.org/drm/drm-misc F: Documentation/devicetree/bindings/display/himax,hx8357d.txt @@ -6023,7 +6023,7 @@ M: Neil Armstrong <narmstrong@baylibre.com> M: Robert Foss <robert.foss@linaro.org> R: Laurent Pinchart <Laurent.pinchart@ideasonboard.com> R: Jonas Karlman <jonas@kwiboo.se> -R: Jernej Skrabec <jernej.skrabec@siol.net> +R: Jernej Skrabec <jernej.skrabec@gmail.com> S: Maintained T: git git://anongit.freedesktop.org/drm/drm-misc F: drivers/gpu/drm/bridge/ @@ -6177,7 +6177,7 @@ F: Documentation/devicetree/bindings/display/ti/ F: drivers/gpu/drm/omapdrm/ DRM DRIVERS FOR V3D -M: Eric Anholt <eric@anholt.net> +M: Emma Anholt <emma@anholt.net> S: Supported T: git git://anongit.freedesktop.org/drm/drm-misc F: Documentation/devicetree/bindings/gpu/brcm,bcm-v3d.yaml @@ -6185,7 +6185,7 @@ F: drivers/gpu/drm/v3d/ F: include/uapi/drm/v3d_drm.h DRM DRIVERS FOR VC4 -M: Eric Anholt <eric@anholt.net> +M: Emma Anholt <emma@anholt.net> M: Maxime Ripard <mripard@kernel.org> S: Supported T: git git://github.com/anholt/linux @@ -7006,7 +7006,7 @@ M: Dan Williams <dan.j.williams@intel.com> R: Matthew Wilcox <willy@infradead.org> R: Jan Kara <jack@suse.cz> L: linux-fsdevel@vger.kernel.org -L: linux-nvdimm@lists.01.org +L: nvdimm@lists.linux.dev S: Supported F: fs/dax.c F: include/linux/dax.h @@ -10378,7 +10378,7 @@ LIBNVDIMM BLK: MMIO-APERTURE DRIVER M: Dan Williams <dan.j.williams@intel.com> M: Vishal Verma <vishal.l.verma@intel.com> M: Dave Jiang <dave.jiang@intel.com> -L: linux-nvdimm@lists.01.org +L: nvdimm@lists.linux.dev S: Supported Q: https://patchwork.kernel.org/project/linux-nvdimm/list/ P: Documentation/nvdimm/maintainer-entry-profile.rst @@ -10389,7 +10389,7 @@ LIBNVDIMM BTT: BLOCK TRANSLATION TABLE M: Vishal Verma <vishal.l.verma@intel.com> M: Dan Williams <dan.j.williams@intel.com> M: Dave Jiang <dave.jiang@intel.com> -L: linux-nvdimm@lists.01.org +L: nvdimm@lists.linux.dev S: Supported Q: https://patchwork.kernel.org/project/linux-nvdimm/list/ P: Documentation/nvdimm/maintainer-entry-profile.rst @@ -10399,7 +10399,7 @@ LIBNVDIMM PMEM: PERSISTENT MEMORY DRIVER M: Dan Williams <dan.j.williams@intel.com> M: Vishal Verma <vishal.l.verma@intel.com> M: Dave Jiang <dave.jiang@intel.com> -L: linux-nvdimm@lists.01.org +L: nvdimm@lists.linux.dev S: Supported Q: https://patchwork.kernel.org/project/linux-nvdimm/list/ P: Documentation/nvdimm/maintainer-entry-profile.rst @@ -10407,7 +10407,7 @@ F: drivers/nvdimm/pmem* LIBNVDIMM: DEVICETREE BINDINGS M: Oliver O'Halloran <oohall@gmail.com> -L: linux-nvdimm@lists.01.org +L: nvdimm@lists.linux.dev S: Supported Q: https://patchwork.kernel.org/project/linux-nvdimm/list/ F: Documentation/devicetree/bindings/pmem/pmem-region.txt @@ -10418,7 +10418,7 @@ M: Dan Williams <dan.j.williams@intel.com> M: Vishal Verma <vishal.l.verma@intel.com> M: Dave Jiang <dave.jiang@intel.com> M: Ira Weiny <ira.weiny@intel.com> -L: linux-nvdimm@lists.01.org +L: nvdimm@lists.linux.dev S: Supported Q: https://patchwork.kernel.org/project/linux-nvdimm/list/ P: Documentation/nvdimm/maintainer-entry-profile.rst @@ -15815,7 +15815,7 @@ F: include/uapi/linux/rose.h F: net/rose/ ROTATION DRIVER FOR ALLWINNER A83T -M: Jernej Skrabec <jernej.skrabec@siol.net> +M: Jernej Skrabec <jernej.skrabec@gmail.com> L: linux-media@vger.kernel.org S: Maintained T: git git://linuxtv.org/media_tree.git diff --git a/arch/arc/Makefile b/arch/arc/Makefile index 4392c9c189c4..e47adc97a89b 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -31,7 +31,7 @@ endif ifdef CONFIG_ARC_CURR_IN_REG -# For a global register defintion, make sure it gets passed to every file +# For a global register definition, make sure it gets passed to every file # We had a customer reported bug where some code built in kernel was NOT using # any kernel headers, and missing the r25 global register # Can't do unconditionally because of recursive include issues diff --git a/arch/arc/include/asm/cmpxchg.h b/arch/arc/include/asm/cmpxchg.h index 9b87e162e539..dfeffa25499b 100644 --- a/arch/arc/include/asm/cmpxchg.h +++ b/arch/arc/include/asm/cmpxchg.h @@ -116,7 +116,7 @@ static inline unsigned long __xchg(unsigned long val, volatile void *ptr, * * Technically the lock is also needed for UP (boils down to irq save/restore) * but we can cheat a bit since cmpxchg() atomic_ops_lock() would cause irqs to - * be disabled thus can't possibly be interrpted/preempted/clobbered by xchg() + * be disabled thus can't possibly be interrupted/preempted/clobbered by xchg() * Other way around, xchg is one instruction anyways, so can't be interrupted * as such */ @@ -143,7 +143,7 @@ static inline unsigned long __xchg(unsigned long val, volatile void *ptr, /* * "atomic" variant of xchg() * REQ: It needs to follow the same serialization rules as other atomic_xxx() - * Since xchg() doesn't always do that, it would seem that following defintion + * Since xchg() doesn't always do that, it would seem that following definition * is incorrect. But here's the rationale: * SMP : Even xchg() takes the atomic_ops_lock, so OK. * LLSC: atomic_ops_lock are not relevant at all (even if SMP, since LLSC diff --git a/arch/arc/include/asm/page.h b/arch/arc/include/asm/page.h index ad9b7fe4dba3..4a9d33372fe2 100644 --- a/arch/arc/include/asm/page.h +++ b/arch/arc/include/asm/page.h @@ -7,6 +7,18 @@ #include <uapi/asm/page.h> +#ifdef CONFIG_ARC_HAS_PAE40 + +#define MAX_POSSIBLE_PHYSMEM_BITS 40 +#define PAGE_MASK_PHYS (0xff00000000ull | PAGE_MASK) + +#else /* CONFIG_ARC_HAS_PAE40 */ + +#define MAX_POSSIBLE_PHYSMEM_BITS 32 +#define PAGE_MASK_PHYS PAGE_MASK + +#endif /* CONFIG_ARC_HAS_PAE40 */ + #ifndef __ASSEMBLY__ #define clear_page(paddr) memset((paddr), 0, PAGE_SIZE) diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index 163641726a2b..5878846f00cf 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -107,8 +107,8 @@ #define ___DEF (_PAGE_PRESENT | _PAGE_CACHEABLE) /* Set of bits not changed in pte_modify */ -#define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_SPECIAL) - +#define _PAGE_CHG_MASK (PAGE_MASK_PHYS | _PAGE_ACCESSED | _PAGE_DIRTY | \ + _PAGE_SPECIAL) /* More Abbrevaited helpers */ #define PAGE_U_NONE __pgprot(___DEF) #define PAGE_U_R __pgprot(___DEF | _PAGE_READ) @@ -132,13 +132,7 @@ #define PTE_BITS_IN_PD0 (_PAGE_GLOBAL | _PAGE_PRESENT | _PAGE_HW_SZ) #define PTE_BITS_RWX (_PAGE_EXECUTE | _PAGE_WRITE | _PAGE_READ) -#ifdef CONFIG_ARC_HAS_PAE40 -#define PTE_BITS_NON_RWX_IN_PD1 (0xff00000000 | PAGE_MASK | _PAGE_CACHEABLE) -#define MAX_POSSIBLE_PHYSMEM_BITS 40 -#else -#define PTE_BITS_NON_RWX_IN_PD1 (PAGE_MASK | _PAGE_CACHEABLE) -#define MAX_POSSIBLE_PHYSMEM_BITS 32 -#endif +#define PTE_BITS_NON_RWX_IN_PD1 (PAGE_MASK_PHYS | _PAGE_CACHEABLE) /************************************************************************** * Mapping of vm_flags (Generic VM) to PTE flags (arch specific) diff --git a/arch/arc/include/uapi/asm/page.h b/arch/arc/include/uapi/asm/page.h index 2a97e2718a21..2a4ad619abfb 100644 --- a/arch/arc/include/uapi/asm/page.h +++ b/arch/arc/include/uapi/asm/page.h @@ -33,5 +33,4 @@ #define PAGE_MASK (~(PAGE_SIZE-1)) - #endif /* _UAPI__ASM_ARC_PAGE_H */ diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S index 1743506081da..2cb8dfe866b6 100644 --- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -177,7 +177,7 @@ tracesys: ; Do the Sys Call as we normally would. ; Validate the Sys Call number - cmp r8, NR_syscalls + cmp r8, NR_syscalls - 1 mov.hi r0, -ENOSYS bhi tracesys_exit @@ -255,7 +255,7 @@ ENTRY(EV_Trap) ;============ Normal syscall case ; syscall num shd not exceed the total system calls avail - cmp r8, NR_syscalls + cmp r8, NR_syscalls - 1 mov.hi r0, -ENOSYS bhi .Lret_from_system_call diff --git a/arch/arc/kernel/kgdb.c b/arch/arc/kernel/kgdb.c index ecfbc42d3a40..345a0000554c 100644 --- a/arch/arc/kernel/kgdb.c +++ b/arch/arc/kernel/kgdb.c @@ -140,6 +140,7 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code, ptr = &remcomInBuffer[1]; if (kgdb_hex2long(&ptr, &addr)) regs->ret = addr; + fallthrough; case 'D': case 'k': diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index d838d0d57696..3793876f42d9 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -50,14 +50,14 @@ SYSCALL_DEFINE3(arc_usr_cmpxchg, int *, uaddr, int, expected, int, new) int ret; /* - * This is only for old cores lacking LLOCK/SCOND, which by defintion + * This is only for old cores lacking LLOCK/SCOND, which by definition * can't possibly be SMP. Thus doesn't need to be SMP safe. * And this also helps reduce the overhead for serializing in * the UP case */ WARN_ON_ONCE(IS_ENABLED(CONFIG_SMP)); - /* Z indicates to userspace if operation succeded */ + /* Z indicates to userspace if operation succeeded */ regs->status32 &= ~STATUS_Z_MASK; ret = access_ok(uaddr, sizeof(*uaddr)); @@ -107,7 +107,7 @@ fail: void arch_cpu_idle(void) { - /* Re-enable interrupts <= default irq priority before commiting SLEEP */ + /* Re-enable interrupts <= default irq priority before committing SLEEP */ const unsigned int arg = 0x10 | ARCV2_IRQ_DEF_PRIO; __asm__ __volatile__( @@ -120,7 +120,7 @@ void arch_cpu_idle(void) void arch_cpu_idle(void) { - /* sleep, but enable both set E1/E2 (levels of interrutps) before committing */ + /* sleep, but enable both set E1/E2 (levels of interrupts) before committing */ __asm__ __volatile__("sleep 0x3 \n"); } diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c index fdbe06c98895..b3ccb9e5ffe4 100644 --- a/arch/arc/kernel/signal.c +++ b/arch/arc/kernel/signal.c @@ -259,7 +259,7 @@ setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs) regs->r2 = (unsigned long)&sf->uc; /* - * small optim to avoid unconditonally calling do_sigaltstack + * small optim to avoid unconditionally calling do_sigaltstack * in sigreturn path, now that we only have rt_sigreturn */ magic = MAGIC_SIGALTSTK; @@ -391,7 +391,7 @@ void do_signal(struct pt_regs *regs) void do_notify_resume(struct pt_regs *regs) { /* - * ASM glue gaurantees that this is only called when returning to + * ASM glue guarantees that this is only called when returning to * user mode */ if (test_thread_flag(TIF_NOTIFY_RESUME)) diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index 33832e36bdb7..e2ed355438c9 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -157,7 +157,16 @@ void __init setup_arch_memory(void) min_high_pfn = PFN_DOWN(high_mem_start); max_high_pfn = PFN_DOWN(high_mem_start + high_mem_sz); - max_zone_pfn[ZONE_HIGHMEM] = min_low_pfn; + /* + * max_high_pfn should be ok here for both HIGHMEM and HIGHMEM+PAE. + * For HIGHMEM without PAE max_high_pfn should be less than + * min_low_pfn to guarantee that these two regions don't overlap. + * For PAE case highmem is greater than lowmem, so it is natural + * to use max_high_pfn. + * + * In both cases, holes should be handled by pfn_valid(). + */ + max_zone_pfn[ZONE_HIGHMEM] = max_high_pfn; high_memory = (void *)(min_high_pfn << PAGE_SHIFT); diff --git a/arch/arc/mm/ioremap.c b/arch/arc/mm/ioremap.c index fac4adc90204..95c649fbc95a 100644 --- a/arch/arc/mm/ioremap.c +++ b/arch/arc/mm/ioremap.c @@ -53,9 +53,10 @@ EXPORT_SYMBOL(ioremap); void __iomem *ioremap_prot(phys_addr_t paddr, unsigned long size, unsigned long flags) { + unsigned int off; unsigned long vaddr; struct vm_struct *area; - phys_addr_t off, end; + phys_addr_t end; pgprot_t prot = __pgprot(flags); /* Don't allow wraparound, zero size */ @@ -72,7 +73,7 @@ void __iomem *ioremap_prot(phys_addr_t paddr, unsigned long size, /* Mappings have to be page-aligned */ off = paddr & ~PAGE_MASK; - paddr &= PAGE_MASK; + paddr &= PAGE_MASK_PHYS; size = PAGE_ALIGN(end + 1) - paddr; /* diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c index 9bb3c24f3677..9c7c68247289 100644 --- a/arch/arc/mm/tlb.c +++ b/arch/arc/mm/tlb.c @@ -576,7 +576,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long vaddr_unaligned, pte_t *ptep) { unsigned long vaddr = vaddr_unaligned & PAGE_MASK; - phys_addr_t paddr = pte_val(*ptep) & PAGE_MASK; + phys_addr_t paddr = pte_val(*ptep) & PAGE_MASK_PHYS; struct page *page = pfn_to_page(pte_pfn(*ptep)); create_tlb(vma, vaddr, ptep); diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c index f8f07469d259..a7e54a087b80 100644 --- a/arch/arm/xen/mm.c +++ b/arch/arm/xen/mm.c @@ -135,24 +135,18 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order) return; } -int xen_swiotlb_detect(void) -{ - if (!xen_domain()) - return 0; - if (xen_feature(XENFEAT_direct_mapped)) - return 1; - /* legacy case */ - if (!xen_feature(XENFEAT_not_direct_mapped) && xen_initial_domain()) - return 1; - return 0; -} - static int __init xen_mm_init(void) { struct gnttab_cache_flush cflush; + int rc; + if (!xen_swiotlb_detect()) return 0; - xen_swiotlb_init(); + + rc = xen_swiotlb_init(); + /* we can work with the default swiotlb */ + if (rc < 0 && rc != -EEXIST) + return rc; cflush.op = 0; cflush.a.dev_bus_addr = 0; diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 7ef44478560d..b52481f0605d 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -175,6 +175,9 @@ vdso_install: $(if $(CONFIG_COMPAT_VDSO), \ $(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso32 $@) +archprepare: + $(Q)$(MAKE) $(build)=arch/arm64/tools kapi + # We use MRPROPER_FILES and CLEAN_FILES now archclean: $(Q)$(MAKE) $(clean)=$(boot) diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index 07ac208edc89..26889dbfe904 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -5,3 +5,5 @@ generic-y += qrwlock.h generic-y += qspinlock.h generic-y += set_memory.h generic-y += user.h + +generated-y += cpucaps.h diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h deleted file mode 100644 index b0c5eda0498f..000000000000 --- a/arch/arm64/include/asm/cpucaps.h +++ /dev/null @@ -1,74 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * arch/arm64/include/asm/cpucaps.h - * - * Copyright (C) 2016 ARM Ltd. - */ -#ifndef __ASM_CPUCAPS_H -#define __ASM_CPUCAPS_H - -#define ARM64_WORKAROUND_CLEAN_CACHE 0 -#define ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE 1 -#define ARM64_WORKAROUND_845719 2 -#define ARM64_HAS_SYSREG_GIC_CPUIF 3 -#define ARM64_HAS_PAN 4 -#define ARM64_HAS_LSE_ATOMICS 5 -#define ARM64_WORKAROUND_CAVIUM_23154 6 -#define ARM64_WORKAROUND_834220 7 -#define ARM64_HAS_NO_HW_PREFETCH 8 -#define ARM64_HAS_VIRT_HOST_EXTN 11 -#define ARM64_WORKAROUND_CAVIUM_27456 12 -#define ARM64_HAS_32BIT_EL0 13 -#define ARM64_SPECTRE_V3A 14 -#define ARM64_HAS_CNP 15 -#define ARM64_HAS_NO_FPSIMD 16 -#define ARM64_WORKAROUND_REPEAT_TLBI 17 -#define ARM64_WORKAROUND_QCOM_FALKOR_E1003 18 -#define ARM64_WORKAROUND_858921 19 -#define ARM64_WORKAROUND_CAVIUM_30115 20 -#define ARM64_HAS_DCPOP 21 -#define ARM64_SVE 22 -#define ARM64_UNMAP_KERNEL_AT_EL0 23 -#define ARM64_SPECTRE_V2 24 -#define ARM64_HAS_RAS_EXTN 25 -#define ARM64_WORKAROUND_843419 26 -#define ARM64_HAS_CACHE_IDC 27 -#define ARM64_HAS_CACHE_DIC 28 -#define ARM64_HW_DBM 29 -#define ARM64_SPECTRE_V4 30 -#define ARM64_MISMATCHED_CACHE_TYPE 31 -#define ARM64_HAS_STAGE2_FWB 32 -#define ARM64_HAS_CRC32 33 -#define ARM64_SSBS 34 -#define ARM64_WORKAROUND_1418040 35 -#define ARM64_HAS_SB 36 -#define ARM64_WORKAROUND_SPECULATIVE_AT 37 -#define ARM64_HAS_ADDRESS_AUTH_ARCH 38 -#define ARM64_HAS_ADDRESS_AUTH_IMP_DEF 39 -#define ARM64_HAS_GENERIC_AUTH_ARCH 40 -#define ARM64_HAS_GENERIC_AUTH_IMP_DEF 41 -#define ARM64_HAS_IRQ_PRIO_MASKING 42 -#define ARM64_HAS_DCPODP 43 -#define ARM64_WORKAROUND_1463225 44 -#define ARM64_WORKAROUND_CAVIUM_TX2_219_TVM 45 -#define ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM 46 -#define ARM64_WORKAROUND_1542419 47 -#define ARM64_HAS_E0PD 48 -#define ARM64_HAS_RNG 49 -#define ARM64_HAS_AMU_EXTN 50 -#define ARM64_HAS_ADDRESS_AUTH 51 -#define ARM64_HAS_GENERIC_AUTH 52 -#define ARM64_HAS_32BIT_EL1 53 -#define ARM64_BTI 54 -#define ARM64_HAS_ARMv8_4_TTL 55 -#define ARM64_HAS_TLB_RANGE 56 -#define ARM64_MTE 57 -#define ARM64_WORKAROUND_1508412 58 -#define ARM64_HAS_LDAPR 59 -#define ARM64_KVM_PROTECTED_MODE 60 -#define ARM64_WORKAROUND_NVIDIA_CARMEL_CNP 61 -#define ARM64_HAS_EPAN 62 - -#define ARM64_NCAPS 63 - -#endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c index ac485163a4a7..6d44c028d1c9 100644 --- a/arch/arm64/mm/flush.c +++ b/arch/arm64/mm/flush.c @@ -55,8 +55,10 @@ void __sync_icache_dcache(pte_t pte) { struct page *page = pte_page(pte); - if (!test_and_set_bit(PG_dcache_clean, &page->flags)) + if (!test_bit(PG_dcache_clean, &page->flags)) { sync_icache_aliases(page_address(page), page_size(page)); + set_bit(PG_dcache_clean, &page->flags); + } } EXPORT_SYMBOL_GPL(__sync_icache_dcache); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 16a2b2b1c54d..e55409caaee3 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -43,6 +43,7 @@ #include <linux/sizes.h> #include <asm/tlb.h> #include <asm/alternative.h> +#include <asm/xen/swiotlb-xen.h> /* * We need to be able to catch inadvertent references to memstart_addr @@ -482,7 +483,7 @@ void __init mem_init(void) if (swiotlb_force == SWIOTLB_FORCE || max_pfn > PFN_DOWN(arm64_dma_phys_limit)) swiotlb_init(1); - else + else if (!xen_swiotlb_detect()) swiotlb_force = SWIOTLB_NO_FORCE; set_max_mapnr(max_pfn - PHYS_PFN_OFFSET); diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 0a48191534ff..97d7bcd8d4f2 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -447,6 +447,18 @@ SYM_FUNC_START(__cpu_setup) mov x10, #(SYS_GCR_EL1_RRND | SYS_GCR_EL1_EXCL_MASK) msr_s SYS_GCR_EL1, x10 + /* + * If GCR_EL1.RRND=1 is implemented the same way as RRND=0, then + * RGSR_EL1.SEED must be non-zero for IRG to produce + * pseudorandom numbers. As RGSR_EL1 is UNKNOWN out of reset, we + * must initialize it. + */ + mrs x10, CNTVCT_EL0 + ands x10, x10, #SYS_RGSR_EL1_SEED_MASK + csinc x10, x10, xzr, ne + lsl x10, x10, #SYS_RGSR_EL1_SEED_SHIFT + msr_s SYS_RGSR_EL1, x10 + /* clear any pending tag check faults in TFSR*_EL1 */ msr_s SYS_TFSR_EL1, xzr msr_s SYS_TFSRE0_EL1, xzr diff --git a/arch/arm64/tools/Makefile b/arch/arm64/tools/Makefile new file mode 100644 index 000000000000..932b4fe5c768 --- /dev/null +++ b/arch/arm64/tools/Makefile @@ -0,0 +1,22 @@ +# SPDX-License-Identifier: GPL-2.0 + +gen := arch/$(ARCH)/include/generated +kapi := $(gen)/asm + +kapi-hdrs-y := $(kapi)/cpucaps.h + +targets += $(addprefix ../../../,$(gen-y) $(kapi-hdrs-y)) + +PHONY += kapi + +kapi: $(kapi-hdrs-y) $(gen-y) + +# Create output directory if not already present +_dummy := $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)') + +quiet_cmd_gen_cpucaps = GEN $@ + cmd_gen_cpucaps = mkdir -p $(dir $@) && \ + $(AWK) -f $(filter-out $(PHONY),$^) > $@ + +$(kapi)/cpucaps.h: $(src)/gen-cpucaps.awk $(src)/cpucaps FORCE + $(call if_changed,gen_cpucaps) diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps new file mode 100644 index 000000000000..21fbdda7086e --- /dev/null +++ b/arch/arm64/tools/cpucaps @@ -0,0 +1,65 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Internal CPU capabilities constants, keep this list sorted + +BTI +HAS_32BIT_EL0 +HAS_32BIT_EL1 +HAS_ADDRESS_AUTH +HAS_ADDRESS_AUTH_ARCH +HAS_ADDRESS_AUTH_IMP_DEF +HAS_AMU_EXTN +HAS_ARMv8_4_TTL +HAS_CACHE_DIC +HAS_CACHE_IDC +HAS_CNP +HAS_CRC32 +HAS_DCPODP +HAS_DCPOP +HAS_E0PD +HAS_EPAN +HAS_GENERIC_AUTH +HAS_GENERIC_AUTH_ARCH +HAS_GENERIC_AUTH_IMP_DEF +HAS_IRQ_PRIO_MASKING +HAS_LDAPR +HAS_LSE_ATOMICS +HAS_NO_FPSIMD +HAS_NO_HW_PREFETCH +HAS_PAN +HAS_RAS_EXTN +HAS_RNG +HAS_SB +HAS_STAGE2_FWB +HAS_SYSREG_GIC_CPUIF +HAS_TLB_RANGE +HAS_VIRT_HOST_EXTN +HW_DBM +KVM_PROTECTED_MODE +MISMATCHED_CACHE_TYPE +MTE +SPECTRE_V2 +SPECTRE_V3A +SPECTRE_V4 +SSBS +SVE +UNMAP_KERNEL_AT_EL0 +WORKAROUND_834220 +WORKAROUND_843419 +WORKAROUND_845719 +WORKAROUND_858921 +WORKAROUND_1418040 +WORKAROUND_1463225 +WORKAROUND_1508412 +WORKAROUND_1542419 +WORKAROUND_CAVIUM_23154 +WORKAROUND_CAVIUM_27456 +WORKAROUND_CAVIUM_30115 +WORKAROUND_CAVIUM_TX2_219_PRFM +WORKAROUND_CAVIUM_TX2_219_TVM +WORKAROUND_CLEAN_CACHE +WORKAROUND_DEVICE_LOAD_ACQUIRE +WORKAROUND_NVIDIA_CARMEL_CNP +WORKAROUND_QCOM_FALKOR_E1003 +WORKAROUND_REPEAT_TLBI +WORKAROUND_SPECULATIVE_AT diff --git a/arch/arm64/tools/gen-cpucaps.awk b/arch/arm64/tools/gen-cpucaps.awk new file mode 100755 index 000000000000..00c9e72a200a --- /dev/null +++ b/arch/arm64/tools/gen-cpucaps.awk @@ -0,0 +1,40 @@ +#!/bin/awk -f +# SPDX-License-Identifier: GPL-2.0 +# gen-cpucaps.awk: arm64 cpucaps header generator +# +# Usage: awk -f gen-cpucaps.awk cpucaps.txt + +# Log an error and terminate +function fatal(msg) { + print "Error at line " NR ": " msg > "/dev/stderr" + exit 1 +} + +# skip blank lines and comment lines +/^$/ { next } +/^#/ { next } + +BEGIN { + print "#ifndef __ASM_CPUCAPS_H" + print "#define __ASM_CPUCAPS_H" + print "" + print "/* Generated file - do not edit */" + cap_num = 0 + print "" +} + +/^[vA-Z0-9_]+$/ { + printf("#define ARM64_%-30s\t%d\n", $0, cap_num++) + next +} + +END { + printf("#define ARM64_NCAPS\t\t\t\t%d\n", cap_num) + print "" + print "#endif /* __ASM_CPUCAPS_H */" +} + +# Any lines not handled by previous rules are unexpected +{ + fatal("unhandled statement") +} diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 443050906018..e3b29eda8074 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -448,6 +448,9 @@ */ long plpar_hcall_norets(unsigned long opcode, ...); +/* Variant which does not do hcall tracing */ +long plpar_hcall_norets_notrace(unsigned long opcode, ...); + /** * plpar_hcall: - Make a pseries hypervisor call * @opcode: The hypervisor call to make. diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h index 44cde2e129b8..59f704408d65 100644 --- a/arch/powerpc/include/asm/interrupt.h +++ b/arch/powerpc/include/asm/interrupt.h @@ -153,8 +153,6 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrup */ static inline void interrupt_exit_prepare(struct pt_regs *regs, struct interrupt_state *state) { - if (user_mode(regs)) - kuep_unlock(); } static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct interrupt_state *state) @@ -222,6 +220,13 @@ static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct inte local_paca->irq_soft_mask = IRQS_ALL_DISABLED; local_paca->irq_happened |= PACA_IRQ_HARD_DIS; + if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && !(regs->msr & MSR_PR) && + regs->nip < (unsigned long)__end_interrupts) { + // Kernel code running below __end_interrupts is + // implicitly soft-masked. + regs->softe = IRQS_ALL_DISABLED; + } + /* Don't do any per-CPU operations until interrupt state is fixed */ if (nmi_disables_ftrace(regs)) { diff --git a/arch/powerpc/include/asm/paravirt.h b/arch/powerpc/include/asm/paravirt.h index 5d1726bb28e7..bcb7b5f917be 100644 --- a/arch/powerpc/include/asm/paravirt.h +++ b/arch/powerpc/include/asm/paravirt.h @@ -28,19 +28,35 @@ static inline u32 yield_count_of(int cpu) return be32_to_cpu(yield_count); } +/* + * Spinlock code confers and prods, so don't trace the hcalls because the + * tracing code takes spinlocks which can cause recursion deadlocks. + * + * These calls are made while the lock is not held: the lock slowpath yields if + * it can not acquire the lock, and unlock slow path might prod if a waiter has + * yielded). So this may not be a problem for simple spin locks because the + * tracing does not technically recurse on the lock, but we avoid it anyway. + * + * However the queued spin lock contended path is more strictly ordered: the + * H_CONFER hcall is made after the task has queued itself on the lock, so then + * recursing on that lock will cause the task to then queue up again behind the + * first instance (or worse: queued spinlocks use tricks that assume a context + * never waits on more than one spinlock, so such recursion may cause random + * corruption in the lock code). + */ static inline void yield_to_preempted(int cpu, u32 yield_count) { - plpar_hcall_norets(H_CONFER, get_hard_smp_processor_id(cpu), yield_count); + plpar_hcall_norets_notrace(H_CONFER, get_hard_smp_processor_id(cpu), yield_count); } static inline void prod_cpu(int cpu) { - plpar_hcall_norets(H_PROD, get_hard_smp_processor_id(cpu)); + plpar_hcall_norets_notrace(H_PROD, get_hard_smp_processor_id(cpu)); } static inline void yield_to_any(void) { - plpar_hcall_norets(H_CONFER, -1, 0); + plpar_hcall_norets_notrace(H_CONFER, -1, 0); } #else static inline bool is_shared_processor(void) diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h index ece84a430701..83e0f701ebc6 100644 --- a/arch/powerpc/include/asm/plpar_wrappers.h +++ b/arch/powerpc/include/asm/plpar_wrappers.h @@ -28,7 +28,11 @@ static inline void set_cede_latency_hint(u8 latency_hint) static inline long cede_processor(void) { - return plpar_hcall_norets(H_CEDE); + /* + * We cannot call tracepoints inside RCU idle regions which + * means we must not trace H_CEDE. + */ + return plpar_hcall_norets_notrace(H_CEDE); } static inline long extended_cede_processor(unsigned long latency_hint) diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index a09e4240c5b1..22c79ab40006 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -157,7 +157,7 @@ do { \ "2: lwz%X1 %L0, %L1\n" \ EX_TABLE(1b, %l2) \ EX_TABLE(2b, %l2) \ - : "=r" (x) \ + : "=&r" (x) \ : "m" (*addr) \ : \ : label) diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 7c3654b0d0f4..f1ae710274bc 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -340,6 +340,12 @@ ret_from_mc_except: andi. r10,r10,IRQS_DISABLED; /* yes -> go out of line */ \ bne masked_interrupt_book3e_##n +/* + * Additional regs must be re-loaded from paca before EXCEPTION_COMMON* is + * called, because that does SAVE_NVGPRS which must see the original register + * values, otherwise the scratch values might be restored when exiting the + * interrupt. + */ #define PROLOG_ADDITION_2REGS_GEN(n) \ std r14,PACA_EXGEN+EX_R14(r13); \ std r15,PACA_EXGEN+EX_R15(r13) @@ -535,6 +541,10 @@ __end_interrupts: PROLOG_ADDITION_2REGS) mfspr r14,SPRN_DEAR mfspr r15,SPRN_ESR + std r14,_DAR(r1) + std r15,_DSISR(r1) + ld r14,PACA_EXGEN+EX_R14(r13) + ld r15,PACA_EXGEN+EX_R15(r13) EXCEPTION_COMMON(0x300) b storage_fault_common @@ -544,6 +554,10 @@ __end_interrupts: PROLOG_ADDITION_2REGS) li r15,0 mr r14,r10 + std r14,_DAR(r1) + std r15,_DSISR(r1) + ld r14,PACA_EXGEN+EX_R14(r13) + ld r15,PACA_EXGEN+EX_R15(r13) EXCEPTION_COMMON(0x400) b storage_fault_common @@ -557,6 +571,10 @@ __end_interrupts: PROLOG_ADDITION_2REGS) mfspr r14,SPRN_DEAR mfspr r15,SPRN_ESR + std r14,_DAR(r1) + std r15,_DSISR(r1) + ld r14,PACA_EXGEN+EX_R14(r13) + ld r15,PACA_EXGEN+EX_R15(r13) EXCEPTION_COMMON(0x600) b alignment_more /* no room, go out of line */ @@ -565,10 +583,10 @@ __end_interrupts: NORMAL_EXCEPTION_PROLOG(0x700, BOOKE_INTERRUPT_PROGRAM, PROLOG_ADDITION_1REG) mfspr r14,SPRN_ESR - EXCEPTION_COMMON(0x700) std r14,_DSISR(r1) - addi r3,r1,STACK_FRAME_OVERHEAD ld r14,PACA_EXGEN+EX_R14(r13) + EXCEPTION_COMMON(0x700) + addi r3,r1,STACK_FRAME_OVERHEAD bl program_check_exception REST_NVGPRS(r1) b interrupt_return @@ -725,11 +743,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) * normal exception */ mfspr r14,SPRN_DBSR - EXCEPTION_COMMON_CRIT(0xd00) std r14,_DSISR(r1) - addi r3,r1,STACK_FRAME_OVERHEAD ld r14,PACA_EXCRIT+EX_R14(r13) ld r15,PACA_EXCRIT+EX_R15(r13) + EXCEPTION_COMMON_CRIT(0xd00) + addi r3,r1,STACK_FRAME_OVERHEAD bl DebugException REST_NVGPRS(r1) b interrupt_return @@ -796,11 +814,11 @@ kernel_dbg_exc: * normal exception */ mfspr r14,SPRN_DBSR - EXCEPTION_COMMON_DBG(0xd08) std r14,_DSISR(r1) - addi r3,r1,STACK_FRAME_OVERHEAD ld r14,PACA_EXDBG+EX_R14(r13) ld r15,PACA_EXDBG+EX_R15(r13) + EXCEPTION_COMMON_DBG(0xd08) + addi r3,r1,STACK_FRAME_OVERHEAD bl DebugException REST_NVGPRS(r1) b interrupt_return @@ -931,11 +949,7 @@ masked_interrupt_book3e_0x2c0: * original values stashed away in the PACA */ storage_fault_common: - std r14,_DAR(r1) - std r15,_DSISR(r1) addi r3,r1,STACK_FRAME_OVERHEAD - ld r14,PACA_EXGEN+EX_R14(r13) - ld r15,PACA_EXGEN+EX_R15(r13) bl do_page_fault b interrupt_return @@ -944,11 +958,7 @@ storage_fault_common: * continues here. */ alignment_more: - std r14,_DAR(r1) - std r15,_DSISR(r1) addi r3,r1,STACK_FRAME_OVERHEAD - ld r14,PACA_EXGEN+EX_R14(r13) - ld r15,PACA_EXGEN+EX_R15(r13) bl alignment_exception REST_NVGPRS(r1) b interrupt_return diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c index e4559f8914eb..e0938ba298f2 100644 --- a/arch/powerpc/kernel/interrupt.c +++ b/arch/powerpc/kernel/interrupt.c @@ -34,9 +34,6 @@ notrace long system_call_exception(long r3, long r4, long r5, syscall_fn f; kuep_lock(); -#ifdef CONFIG_PPC32 - kuap_save_and_lock(regs); -#endif regs->orig_gpr3 = r3; @@ -427,6 +424,7 @@ again: /* Restore user access locks last */ kuap_user_restore(regs); + kuep_unlock(); return ret; } diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index 8b2c1a8553a0..cfc03e016ff2 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -356,13 +356,16 @@ static void __init setup_legacy_serial_console(int console) static int __init ioremap_legacy_serial_console(void) { - struct legacy_serial_info *info = &legacy_serial_infos[legacy_serial_console]; - struct plat_serial8250_port *port = &legacy_serial_ports[legacy_serial_console]; + struct plat_serial8250_port *port; + struct legacy_serial_info *info; void __iomem *vaddr; if (legacy_serial_console < 0) return 0; + info = &legacy_serial_infos[legacy_serial_console]; + port = &legacy_serial_ports[legacy_serial_console]; + if (!info->early_addr) return 0; diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h index f4aafa337c2e..1f07317964e4 100644 --- a/arch/powerpc/kernel/signal.h +++ b/arch/powerpc/kernel/signal.h @@ -166,9 +166,9 @@ copy_ckfpr_from_user(struct task_struct *task, void __user *from) } #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ #else -#define unsafe_copy_fpr_to_user(to, task, label) do { } while (0) +#define unsafe_copy_fpr_to_user(to, task, label) do { if (0) goto label;} while (0) -#define unsafe_copy_fpr_from_user(task, from, label) do { } while (0) +#define unsafe_copy_fpr_from_user(task, from, label) do { if (0) goto label;} while (0) static inline unsigned long copy_fpr_to_user(void __user *to, struct task_struct *task) diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 2d9193cd73be..c63e263312a4 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -840,7 +840,7 @@ bool kvm_unmap_gfn_range_hv(struct kvm *kvm, struct kvm_gfn_range *range) kvm_unmap_radix(kvm, range->slot, gfn); } else { for (gfn = range->start; gfn < range->end; gfn++) - kvm_unmap_rmapp(kvm, range->slot, range->start); + kvm_unmap_rmapp(kvm, range->slot, gfn); } return false; diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index 1fd31b4b0e13..fe26f2fa0f3f 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -14,6 +14,7 @@ #include <linux/string.h> #include <linux/init.h> #include <linux/sched/mm.h> +#include <linux/stop_machine.h> #include <asm/cputable.h> #include <asm/code-patching.h> #include <asm/page.h> @@ -149,17 +150,17 @@ static void do_stf_entry_barrier_fixups(enum stf_barrier_type types) pr_devel("patching dest %lx\n", (unsigned long)dest); - patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); - - if (types & STF_BARRIER_FALLBACK) + // See comment in do_entry_flush_fixups() RE order of patching + if (types & STF_BARRIER_FALLBACK) { + patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); + patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); patch_branch((struct ppc_inst *)(dest + 1), - (unsigned long)&stf_barrier_fallback, - BRANCH_SET_LINK); - else - patch_instruction((struct ppc_inst *)(dest + 1), - ppc_inst(instrs[1])); - - patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + (unsigned long)&stf_barrier_fallback, BRANCH_SET_LINK); + } else { + patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1])); + patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); + } } printk(KERN_DEBUG "stf-barrier: patched %d entry locations (%s barrier)\n", i, @@ -227,11 +228,25 @@ static void do_stf_exit_barrier_fixups(enum stf_barrier_type types) : "unknown"); } +static int __do_stf_barrier_fixups(void *data) +{ + enum stf_barrier_type *types = data; + + do_stf_entry_barrier_fixups(*types); + do_stf_exit_barrier_fixups(*types); + + return 0; +} void do_stf_barrier_fixups(enum stf_barrier_type types) { - do_stf_entry_barrier_fixups(types); - do_stf_exit_barrier_fixups(types); + /* + * The call to the fallback entry flush, and the fallback/sync-ori exit + * flush can not be safely patched in/out while other CPUs are executing + * them. So call __do_stf_barrier_fixups() on one CPU while all other CPUs + * spin in the stop machine core with interrupts hard disabled. + */ + stop_machine(__do_stf_barrier_fixups, &types, NULL); } void do_uaccess_flush_fixups(enum l1d_flush_type types) @@ -284,8 +299,9 @@ void do_uaccess_flush_fixups(enum l1d_flush_type types) : "unknown"); } -void do_entry_flush_fixups(enum l1d_flush_type types) +static int __do_entry_flush_fixups(void *data) { + enum l1d_flush_type types = *(enum l1d_flush_type *)data; unsigned int instrs[3], *dest; long *start, *end; int i; @@ -309,6 +325,31 @@ void do_entry_flush_fixups(enum l1d_flush_type types) if (types & L1D_FLUSH_MTTRIG) instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */ + /* + * If we're patching in or out the fallback flush we need to be careful about the + * order in which we patch instructions. That's because it's possible we could + * take a page fault after patching one instruction, so the sequence of + * instructions must be safe even in a half patched state. + * + * To make that work, when patching in the fallback flush we patch in this order: + * - the mflr (dest) + * - the mtlr (dest + 2) + * - the branch (dest + 1) + * + * That ensures the sequence is safe to execute at any point. In contrast if we + * patch the mtlr last, it's possible we could return from the branch and not + * restore LR, leading to a crash later. + * + * When patching out the fallback flush (either with nops or another flush type), + * we patch in this order: + * - the branch (dest + 1) + * - the mtlr (dest + 2) + * - the mflr (dest) + * + * Note we are protected by stop_machine() from other CPUs executing the code in a + * semi-patched state. + */ + start = PTRRELOC(&__start___entry_flush_fixup); end = PTRRELOC(&__stop___entry_flush_fixup); for (i = 0; start < end; start++, i++) { @@ -316,15 +357,16 @@ void do_entry_flush_fixups(enum l1d_flush_type types) pr_devel("patching dest %lx\n", (unsigned long)dest); - patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); - - if (types == L1D_FLUSH_FALLBACK) - patch_branch((struct ppc_inst *)(dest + 1), (unsigned long)&entry_flush_fallback, - BRANCH_SET_LINK); - else + if (types == L1D_FLUSH_FALLBACK) { + patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); + patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + patch_branch((struct ppc_inst *)(dest + 1), + (unsigned long)&entry_flush_fallback, BRANCH_SET_LINK); + } else { patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1])); - - patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); + } } start = PTRRELOC(&__start___scv_entry_flush_fixup); @@ -334,15 +376,16 @@ void do_entry_flush_fixups(enum l1d_flush_type types) pr_devel("patching dest %lx\n", (unsigned long)dest); - patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); - - if (types == L1D_FLUSH_FALLBACK) - patch_branch((struct ppc_inst *)(dest + 1), (unsigned long)&scv_entry_flush_fallback, - BRANCH_SET_LINK); - else + if (types == L1D_FLUSH_FALLBACK) { + patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); + patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + patch_branch((struct ppc_inst *)(dest + 1), + (unsigned long)&scv_entry_flush_fallback, BRANCH_SET_LINK); + } else { patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1])); - - patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); + } } @@ -354,6 +397,19 @@ void do_entry_flush_fixups(enum l1d_flush_type types) : "ori type" : (types & L1D_FLUSH_MTTRIG) ? "mttrig type" : "unknown"); + + return 0; +} + +void do_entry_flush_fixups(enum l1d_flush_type types) +{ + /* + * The call to the fallback flush can not be safely patched in/out while + * other CPUs are executing it. So call __do_entry_flush_fixups() on one + * CPU while all other CPUs spin in the stop machine core with interrupts + * hard disabled. + */ + stop_machine(__do_entry_flush_fixups, &types, NULL); } void do_rfi_flush_fixups(enum l1d_flush_type types) diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S index 2136e42833af..8a2b8d64265b 100644 --- a/arch/powerpc/platforms/pseries/hvCall.S +++ b/arch/powerpc/platforms/pseries/hvCall.S @@ -102,6 +102,16 @@ END_FTR_SECTION(0, 1); \ #define HCALL_BRANCH(LABEL) #endif +_GLOBAL_TOC(plpar_hcall_norets_notrace) + HMT_MEDIUM + + mfcr r0 + stw r0,8(r1) + HVSC /* invoke the hypervisor */ + lwz r0,8(r1) + mtcrf 0xff,r0 + blr /* return r3 = status */ + _GLOBAL_TOC(plpar_hcall_norets) HMT_MEDIUM diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 1f3152ad7213..dab356e3ff87 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -1829,30 +1829,28 @@ void hcall_tracepoint_unregfunc(void) #endif /* - * Since the tracing code might execute hcalls we need to guard against - * recursion. One example of this are spinlocks calling H_YIELD on - * shared processor partitions. + * Keep track of hcall tracing depth and prevent recursion. Warn if any is + * detected because it may indicate a problem. This will not catch all + * problems with tracing code making hcalls, because the tracing might have + * been invoked from a non-hcall, so the first hcall could recurse into it + * without warning here, but this better than nothing. + * + * Hcalls with specific problems being traced should use the _notrace + * plpar_hcall variants. */ static DEFINE_PER_CPU(unsigned int, hcall_trace_depth); -void __trace_hcall_entry(unsigned long opcode, unsigned long *args) +notrace void __trace_hcall_entry(unsigned long opcode, unsigned long *args) { unsigned long flags; unsigned int *depth; - /* - * We cannot call tracepoints inside RCU idle regions which - * means we must not trace H_CEDE. - */ - if (opcode == H_CEDE) - return; - local_irq_save(flags); depth = this_cpu_ptr(&hcall_trace_depth); - if (*depth) + if (WARN_ON_ONCE(*depth)) goto out; (*depth)++; @@ -1864,19 +1862,16 @@ out: local_irq_restore(flags); } -void __trace_hcall_exit(long opcode, long retval, unsigned long *retbuf) +notrace void __trace_hcall_exit(long opcode, long retval, unsigned long *retbuf) { unsigned long flags; unsigned int *depth; - if (opcode == H_CEDE) - return; - local_irq_save(flags); depth = this_cpu_ptr(&hcall_trace_depth); - if (*depth) + if (*depth) /* Don't warn again on the way out */ goto out; (*depth)++; diff --git a/arch/sh/kernel/traps.c b/arch/sh/kernel/traps.c index f5beecdac693..e76b22157099 100644 --- a/arch/sh/kernel/traps.c +++ b/arch/sh/kernel/traps.c @@ -180,7 +180,6 @@ static inline void arch_ftrace_nmi_exit(void) { } BUILD_TRAP_HANDLER(nmi) { - unsigned int cpu = smp_processor_id(); TRAP_HANDLER_DECL; arch_ftrace_nmi_enter(); diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 6e5522aebbbd..431bf7f846c3 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -30,6 +30,7 @@ targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \ KBUILD_CFLAGS := -m$(BITS) -O2 KBUILD_CFLAGS += -fno-strict-aliasing -fPIE +KBUILD_CFLAGS += -Wundef KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING cflags-$(CONFIG_X86_32) := -march=i386 cflags-$(CONFIG_X86_64) := -mcmodel=small -mno-red-zone @@ -48,10 +49,10 @@ KBUILD_CFLAGS += $(call as-option,-Wa$(comma)-mrelax-relocations=no) KBUILD_CFLAGS += -include $(srctree)/include/linux/hidden.h KBUILD_CFLAGS += $(CLANG_FLAGS) -# sev-es.c indirectly inludes inat-table.h which is generated during +# sev.c indirectly inludes inat-table.h which is generated during # compilation and stored in $(objtree). Add the directory to the includes so # that the compiler finds it even with out-of-tree builds (make O=/some/path). -CFLAGS_sev-es.o += -I$(objtree)/arch/x86/lib/ +CFLAGS_sev.o += -I$(objtree)/arch/x86/lib/ KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ GCOV_PROFILE := n @@ -93,7 +94,7 @@ ifdef CONFIG_X86_64 vmlinux-objs-y += $(obj)/idt_64.o $(obj)/idt_handlers_64.o vmlinux-objs-y += $(obj)/mem_encrypt.o vmlinux-objs-y += $(obj)/pgtable_64.o - vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/sev-es.o + vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/sev.o endif vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index dde042f64cca..743f13ea25c1 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -172,7 +172,7 @@ void __puthex(unsigned long value) } } -#if CONFIG_X86_NEED_RELOCS +#ifdef CONFIG_X86_NEED_RELOCS static void handle_relocations(void *output, unsigned long output_len, unsigned long virt_addr) { diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index e5612f035498..31139256859f 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -79,7 +79,7 @@ struct mem_vector { u64 size; }; -#if CONFIG_RANDOMIZE_BASE +#ifdef CONFIG_RANDOMIZE_BASE /* kaslr.c */ void choose_random_location(unsigned long input, unsigned long input_size, diff --git a/arch/x86/boot/compressed/sev-es.c b/arch/x86/boot/compressed/sev.c index 82041bd380e5..670e998fe930 100644 --- a/arch/x86/boot/compressed/sev-es.c +++ b/arch/x86/boot/compressed/sev.c @@ -13,7 +13,7 @@ #include "misc.h" #include <asm/pgtable_types.h> -#include <asm/sev-es.h> +#include <asm/sev.h> #include <asm/trapnr.h> #include <asm/trap_pf.h> #include <asm/msr-index.h> @@ -117,7 +117,7 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, #include "../../lib/insn.c" /* Include code for early handlers */ -#include "../../kernel/sev-es-shared.c" +#include "../../kernel/sev-shared.c" static bool early_setup_sev_es(void) { diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index cbbcee0a84f9..55efbacfc244 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -113,6 +113,7 @@ #define VALID_PAGE(x) ((x) != INVALID_PAGE) #define UNMAPPED_GVA (~(gpa_t)0) +#define INVALID_GPA (~(gpa_t)0) /* KVM Hugepage definitions for x86 */ #define KVM_MAX_HUGEPAGE_LEVEL PG_LEVEL_1G @@ -199,6 +200,7 @@ enum x86_intercept_stage; #define KVM_NR_DB_REGS 4 +#define DR6_BUS_LOCK (1 << 11) #define DR6_BD (1 << 13) #define DR6_BS (1 << 14) #define DR6_BT (1 << 15) @@ -212,7 +214,7 @@ enum x86_intercept_stage; * DR6_ACTIVE_LOW is also used as the init/reset value for DR6. */ #define DR6_ACTIVE_LOW 0xffff0ff0 -#define DR6_VOLATILE 0x0001e00f +#define DR6_VOLATILE 0x0001e80f #define DR6_FIXED_1 (DR6_ACTIVE_LOW & ~DR6_VOLATILE) #define DR7_BP_EN_MASK 0x000000ff @@ -407,7 +409,7 @@ struct kvm_mmu { u32 pkru_mask; u64 *pae_root; - u64 *lm_root; + u64 *pml4_root; /* * check zero bits on shadow page table entries, these @@ -1417,6 +1419,7 @@ struct kvm_arch_async_pf { bool direct_map; }; +extern u32 __read_mostly kvm_nr_uret_msrs; extern u64 __read_mostly host_efer; extern bool __read_mostly allow_smaller_maxphyaddr; extern struct kvm_x86_ops kvm_x86_ops; @@ -1775,9 +1778,15 @@ int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, unsigned long ipi_bitmap_high, u32 min, unsigned long icr, int op_64_bit); -void kvm_define_user_return_msr(unsigned index, u32 msr); +int kvm_add_user_return_msr(u32 msr); +int kvm_find_user_return_msr(u32 msr); int kvm_set_user_return_msr(unsigned index, u64 val, u64 mask); +static inline bool kvm_is_supported_user_return_msr(u32 msr) +{ + return kvm_find_user_return_msr(msr) >= 0; +} + u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc); u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc); diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index 338119852512..69299878b200 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -7,8 +7,6 @@ #include <linux/interrupt.h> #include <uapi/asm/kvm_para.h> -extern void kvmclock_init(void); - #ifdef CONFIG_KVM_GUEST bool kvm_check_and_clear_guest_paused(void); #else @@ -86,13 +84,14 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1, } #ifdef CONFIG_KVM_GUEST +void kvmclock_init(void); +void kvmclock_disable(void); bool kvm_para_available(void); unsigned int kvm_arch_para_features(void); unsigned int kvm_arch_para_hints(void); void kvm_async_pf_task_wait_schedule(u32 token); void kvm_async_pf_task_wake(u32 token); u32 kvm_read_and_reset_apf_flags(void); -void kvm_disable_steal_time(void); bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token); DECLARE_STATIC_KEY_FALSE(kvm_async_pf_enabled); @@ -137,11 +136,6 @@ static inline u32 kvm_read_and_reset_apf_flags(void) return 0; } -static inline void kvm_disable_steal_time(void) -{ - return; -} - static __always_inline bool kvm_handle_async_pf(struct pt_regs *regs, u32 token) { return false; diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 742d89a00721..211ba3375ee9 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -537,9 +537,9 @@ /* K8 MSRs */ #define MSR_K8_TOP_MEM1 0xc001001a #define MSR_K8_TOP_MEM2 0xc001001d -#define MSR_K8_SYSCFG 0xc0010010 -#define MSR_K8_SYSCFG_MEM_ENCRYPT_BIT 23 -#define MSR_K8_SYSCFG_MEM_ENCRYPT BIT_ULL(MSR_K8_SYSCFG_MEM_ENCRYPT_BIT) +#define MSR_AMD64_SYSCFG 0xc0010010 +#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT 23 +#define MSR_AMD64_SYSCFG_MEM_ENCRYPT BIT_ULL(MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT) #define MSR_K8_INT_PENDING_MSG 0xc0010055 /* C1E active bits in int pending message */ #define K8_INTP_C1E_ACTIVE_MASK 0x18000000 diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 154321d29050..556b2b17c3e2 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -787,8 +787,10 @@ DECLARE_PER_CPU(u64, msr_misc_features_shadow); #ifdef CONFIG_CPU_SUP_AMD extern u32 amd_get_nodes_per_socket(void); +extern u32 amd_get_highest_perf(void); #else static inline u32 amd_get_nodes_per_socket(void) { return 0; } +static inline u32 amd_get_highest_perf(void) { return 0; } #endif static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves) diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h new file mode 100644 index 000000000000..629c3df243f0 --- /dev/null +++ b/arch/x86/include/asm/sev-common.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * AMD SEV header common between the guest and the hypervisor. + * + * Author: Brijesh Singh <brijesh.singh@amd.com> + */ + +#ifndef __ASM_X86_SEV_COMMON_H +#define __ASM_X86_SEV_COMMON_H + +#define GHCB_MSR_INFO_POS 0 +#define GHCB_MSR_INFO_MASK (BIT_ULL(12) - 1) + +#define GHCB_MSR_SEV_INFO_RESP 0x001 +#define GHCB_MSR_SEV_INFO_REQ 0x002 +#define GHCB_MSR_VER_MAX_POS 48 +#define GHCB_MSR_VER_MAX_MASK 0xffff +#define GHCB_MSR_VER_MIN_POS 32 +#define GHCB_MSR_VER_MIN_MASK 0xffff +#define GHCB_MSR_CBIT_POS 24 +#define GHCB_MSR_CBIT_MASK 0xff +#define GHCB_MSR_SEV_INFO(_max, _min, _cbit) \ + ((((_max) & GHCB_MSR_VER_MAX_MASK) << GHCB_MSR_VER_MAX_POS) | \ + (((_min) & GHCB_MSR_VER_MIN_MASK) << GHCB_MSR_VER_MIN_POS) | \ + (((_cbit) & GHCB_MSR_CBIT_MASK) << GHCB_MSR_CBIT_POS) | \ + GHCB_MSR_SEV_INFO_RESP) +#define GHCB_MSR_INFO(v) ((v) & 0xfffUL) +#define GHCB_MSR_PROTO_MAX(v) (((v) >> GHCB_MSR_VER_MAX_POS) & GHCB_MSR_VER_MAX_MASK) +#define GHCB_MSR_PROTO_MIN(v) (((v) >> GHCB_MSR_VER_MIN_POS) & GHCB_MSR_VER_MIN_MASK) + +#define GHCB_MSR_CPUID_REQ 0x004 +#define GHCB_MSR_CPUID_RESP 0x005 +#define GHCB_MSR_CPUID_FUNC_POS 32 +#define GHCB_MSR_CPUID_FUNC_MASK 0xffffffff +#define GHCB_MSR_CPUID_VALUE_POS 32 +#define GHCB_MSR_CPUID_VALUE_MASK 0xffffffff +#define GHCB_MSR_CPUID_REG_POS 30 +#define GHCB_MSR_CPUID_REG_MASK 0x3 +#define GHCB_CPUID_REQ_EAX 0 +#define GHCB_CPUID_REQ_EBX 1 +#define GHCB_CPUID_REQ_ECX 2 +#define GHCB_CPUID_REQ_EDX 3 +#define GHCB_CPUID_REQ(fn, reg) \ + (GHCB_MSR_CPUID_REQ | \ + (((unsigned long)reg & GHCB_MSR_CPUID_REG_MASK) << GHCB_MSR_CPUID_REG_POS) | \ + (((unsigned long)fn) << GHCB_MSR_CPUID_FUNC_POS)) + +#define GHCB_MSR_TERM_REQ 0x100 +#define GHCB_MSR_TERM_REASON_SET_POS 12 +#define GHCB_MSR_TERM_REASON_SET_MASK 0xf +#define GHCB_MSR_TERM_REASON_POS 16 +#define GHCB_MSR_TERM_REASON_MASK 0xff +#define GHCB_SEV_TERM_REASON(reason_set, reason_val) \ + (((((u64)reason_set) & GHCB_MSR_TERM_REASON_SET_MASK) << GHCB_MSR_TERM_REASON_SET_POS) | \ + ((((u64)reason_val) & GHCB_MSR_TERM_REASON_MASK) << GHCB_MSR_TERM_REASON_POS)) + +#define GHCB_SEV_ES_REASON_GENERAL_REQUEST 0 +#define GHCB_SEV_ES_REASON_PROTOCOL_UNSUPPORTED 1 + +#define GHCB_RESP_CODE(v) ((v) & GHCB_MSR_INFO_MASK) + +#endif diff --git a/arch/x86/include/asm/sev-es.h b/arch/x86/include/asm/sev.h index cf1d957c7091..fa5cd05d3b5b 100644 --- a/arch/x86/include/asm/sev-es.h +++ b/arch/x86/include/asm/sev.h @@ -10,34 +10,12 @@ #include <linux/types.h> #include <asm/insn.h> +#include <asm/sev-common.h> -#define GHCB_SEV_INFO 0x001UL -#define GHCB_SEV_INFO_REQ 0x002UL -#define GHCB_INFO(v) ((v) & 0xfffUL) -#define GHCB_PROTO_MAX(v) (((v) >> 48) & 0xffffUL) -#define GHCB_PROTO_MIN(v) (((v) >> 32) & 0xffffUL) -#define GHCB_PROTO_OUR 0x0001UL -#define GHCB_SEV_CPUID_REQ 0x004UL -#define GHCB_CPUID_REQ_EAX 0 -#define GHCB_CPUID_REQ_EBX 1 -#define GHCB_CPUID_REQ_ECX 2 -#define GHCB_CPUID_REQ_EDX 3 -#define GHCB_CPUID_REQ(fn, reg) (GHCB_SEV_CPUID_REQ | \ - (((unsigned long)reg & 3) << 30) | \ - (((unsigned long)fn) << 32)) +#define GHCB_PROTO_OUR 0x0001UL +#define GHCB_PROTOCOL_MAX 1ULL +#define GHCB_DEFAULT_USAGE 0ULL -#define GHCB_PROTOCOL_MAX 0x0001UL -#define GHCB_DEFAULT_USAGE 0x0000UL - -#define GHCB_SEV_CPUID_RESP 0x005UL -#define GHCB_SEV_TERMINATE 0x100UL -#define GHCB_SEV_TERMINATE_REASON(reason_set, reason_val) \ - (((((u64)reason_set) & 0x7) << 12) | \ - ((((u64)reason_val) & 0xff) << 16)) -#define GHCB_SEV_ES_REASON_GENERAL_REQUEST 0 -#define GHCB_SEV_ES_REASON_PROTOCOL_UNSUPPORTED 1 - -#define GHCB_SEV_GHCB_RESP_CODE(v) ((v) & 0xfff) #define VMGEXIT() { asm volatile("rep; vmmcall\n\r"); } enum es_result { diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 5a3022c8af82..0662f644aad9 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -437,6 +437,8 @@ struct kvm_vmx_nested_state_hdr { __u16 flags; } smm; + __u16 pad; + __u32 flags; __u64 preemption_timer_deadline; }; diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 0704c2a94272..0f66682ac02a 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -20,7 +20,7 @@ CFLAGS_REMOVE_kvmclock.o = -pg CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg CFLAGS_REMOVE_head64.o = -pg -CFLAGS_REMOVE_sev-es.o = -pg +CFLAGS_REMOVE_sev.o = -pg endif KASAN_SANITIZE_head$(BITS).o := n @@ -28,7 +28,7 @@ KASAN_SANITIZE_dumpstack.o := n KASAN_SANITIZE_dumpstack_$(BITS).o := n KASAN_SANITIZE_stacktrace.o := n KASAN_SANITIZE_paravirt.o := n -KASAN_SANITIZE_sev-es.o := n +KASAN_SANITIZE_sev.o := n # With some compiler versions the generated code results in boot hangs, caused # by several compilation units. To be safe, disable all instrumentation. @@ -148,7 +148,7 @@ obj-$(CONFIG_UNWINDER_ORC) += unwind_orc.o obj-$(CONFIG_UNWINDER_FRAME_POINTER) += unwind_frame.o obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o -obj-$(CONFIG_AMD_MEM_ENCRYPT) += sev-es.o +obj-$(CONFIG_AMD_MEM_ENCRYPT) += sev.o ### # 64 bit specific files ifeq ($(CONFIG_X86_64),y) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 2d11384dc9ab..c06ac56eae4d 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -593,8 +593,8 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c) */ if (cpu_has(c, X86_FEATURE_SME) || cpu_has(c, X86_FEATURE_SEV)) { /* Check if memory encryption is enabled */ - rdmsrl(MSR_K8_SYSCFG, msr); - if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT)) + rdmsrl(MSR_AMD64_SYSCFG, msr); + if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT)) goto clear_all; /* @@ -1165,3 +1165,19 @@ void set_dr_addr_mask(unsigned long mask, int dr) break; } } + +u32 amd_get_highest_perf(void) +{ + struct cpuinfo_x86 *c = &boot_cpu_data; + + if (c->x86 == 0x17 && ((c->x86_model >= 0x30 && c->x86_model < 0x40) || + (c->x86_model >= 0x70 && c->x86_model < 0x80))) + return 166; + + if (c->x86 == 0x19 && ((c->x86_model >= 0x20 && c->x86_model < 0x30) || + (c->x86_model >= 0x40 && c->x86_model < 0x70))) + return 166; + + return 255; +} +EXPORT_SYMBOL_GPL(amd_get_highest_perf); diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 0c3b372318b7..b5f43049fa5f 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -836,7 +836,7 @@ int __init amd_special_default_mtrr(void) if (boot_cpu_data.x86 < 0xf) return 0; /* In case some hypervisor doesn't pass SYSCFG through: */ - if (rdmsr_safe(MSR_K8_SYSCFG, &l, &h) < 0) + if (rdmsr_safe(MSR_AMD64_SYSCFG, &l, &h) < 0) return 0; /* * Memory between 4GB and top of mem is forced WB by this magic bit. diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index b90f3f437765..558108296f3c 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -53,13 +53,13 @@ static inline void k8_check_syscfg_dram_mod_en(void) (boot_cpu_data.x86 >= 0x0f))) return; - rdmsr(MSR_K8_SYSCFG, lo, hi); + rdmsr(MSR_AMD64_SYSCFG, lo, hi); if (lo & K8_MTRRFIXRANGE_DRAM_MODIFY) { pr_err(FW_WARN "MTRR: CPU %u: SYSCFG[MtrrFixDramModEn]" " not cleared by BIOS, clearing this bit\n", smp_processor_id()); lo &= ~K8_MTRRFIXRANGE_DRAM_MODIFY; - mtrr_wrmsr(MSR_K8_SYSCFG, lo, hi); + mtrr_wrmsr(MSR_AMD64_SYSCFG, lo, hi); } } diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 18be44163a50..de01903c3735 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -39,7 +39,7 @@ #include <asm/realmode.h> #include <asm/extable.h> #include <asm/trapnr.h> -#include <asm/sev-es.h> +#include <asm/sev.h> /* * Manage page tables very early on. diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index d307c22e5c18..a26643dc6bd6 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -26,6 +26,7 @@ #include <linux/kprobes.h> #include <linux/nmi.h> #include <linux/swait.h> +#include <linux/syscore_ops.h> #include <asm/timer.h> #include <asm/cpu.h> #include <asm/traps.h> @@ -37,6 +38,7 @@ #include <asm/tlb.h> #include <asm/cpuidle_haltpoll.h> #include <asm/ptrace.h> +#include <asm/reboot.h> #include <asm/svm.h> DEFINE_STATIC_KEY_FALSE(kvm_async_pf_enabled); @@ -345,7 +347,7 @@ static void kvm_guest_cpu_init(void) wrmsrl(MSR_KVM_ASYNC_PF_EN, pa); __this_cpu_write(apf_reason.enabled, 1); - pr_info("KVM setup async PF for cpu %d\n", smp_processor_id()); + pr_info("setup async PF for cpu %d\n", smp_processor_id()); } if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) { @@ -371,34 +373,17 @@ static void kvm_pv_disable_apf(void) wrmsrl(MSR_KVM_ASYNC_PF_EN, 0); __this_cpu_write(apf_reason.enabled, 0); - pr_info("Unregister pv shared memory for cpu %d\n", smp_processor_id()); + pr_info("disable async PF for cpu %d\n", smp_processor_id()); } -static void kvm_pv_guest_cpu_reboot(void *unused) +static void kvm_disable_steal_time(void) { - /* - * We disable PV EOI before we load a new kernel by kexec, - * since MSR_KVM_PV_EOI_EN stores a pointer into old kernel's memory. - * New kernel can re-enable when it boots. - */ - if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) - wrmsrl(MSR_KVM_PV_EOI_EN, 0); - kvm_pv_disable_apf(); - kvm_disable_steal_time(); -} + if (!has_steal_clock) + return; -static int kvm_pv_reboot_notify(struct notifier_block *nb, - unsigned long code, void *unused) -{ - if (code == SYS_RESTART) - on_each_cpu(kvm_pv_guest_cpu_reboot, NULL, 1); - return NOTIFY_DONE; + wrmsr(MSR_KVM_STEAL_TIME, 0, 0); } -static struct notifier_block kvm_pv_reboot_nb = { - .notifier_call = kvm_pv_reboot_notify, -}; - static u64 kvm_steal_clock(int cpu) { u64 steal; @@ -416,14 +401,6 @@ static u64 kvm_steal_clock(int cpu) return steal; } -void kvm_disable_steal_time(void) -{ - if (!has_steal_clock) - return; - - wrmsr(MSR_KVM_STEAL_TIME, 0, 0); -} - static inline void __set_percpu_decrypted(void *ptr, unsigned long size) { early_set_memory_decrypted((unsigned long) ptr, size); @@ -451,6 +428,27 @@ static void __init sev_map_percpu_data(void) } } +static void kvm_guest_cpu_offline(bool shutdown) +{ + kvm_disable_steal_time(); + if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) + wrmsrl(MSR_KVM_PV_EOI_EN, 0); + kvm_pv_disable_apf(); + if (!shutdown) + apf_task_wake_all(); + kvmclock_disable(); +} + +static int kvm_cpu_online(unsigned int cpu) +{ + unsigned long flags; + + local_irq_save(flags); + kvm_guest_cpu_init(); + local_irq_restore(flags); + return 0; +} + #ifdef CONFIG_SMP static DEFINE_PER_CPU(cpumask_var_t, __pv_cpu_mask); @@ -635,31 +633,64 @@ static void __init kvm_smp_prepare_boot_cpu(void) kvm_spinlock_init(); } -static void kvm_guest_cpu_offline(void) +static int kvm_cpu_down_prepare(unsigned int cpu) { - kvm_disable_steal_time(); - if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) - wrmsrl(MSR_KVM_PV_EOI_EN, 0); - kvm_pv_disable_apf(); - apf_task_wake_all(); + unsigned long flags; + + local_irq_save(flags); + kvm_guest_cpu_offline(false); + local_irq_restore(flags); + return 0; } -static int kvm_cpu_online(unsigned int cpu) +#endif + +static int kvm_suspend(void) { - local_irq_disable(); - kvm_guest_cpu_init(); - local_irq_enable(); + kvm_guest_cpu_offline(false); + return 0; } -static int kvm_cpu_down_prepare(unsigned int cpu) +static void kvm_resume(void) { - local_irq_disable(); - kvm_guest_cpu_offline(); - local_irq_enable(); - return 0; + kvm_cpu_online(raw_smp_processor_id()); +} + +static struct syscore_ops kvm_syscore_ops = { + .suspend = kvm_suspend, + .resume = kvm_resume, +}; + +static void kvm_pv_guest_cpu_reboot(void *unused) +{ + kvm_guest_cpu_offline(true); +} + +static int kvm_pv_reboot_notify(struct notifier_block *nb, + unsigned long code, void *unused) +{ + if (code == SYS_RESTART) + on_each_cpu(kvm_pv_guest_cpu_reboot, NULL, 1); + return NOTIFY_DONE; } +static struct notifier_block kvm_pv_reboot_nb = { + .notifier_call = kvm_pv_reboot_notify, +}; + +/* + * After a PV feature is registered, the host will keep writing to the + * registered memory location. If the guest happens to shutdown, this memory + * won't be valid. In cases like kexec, in which you install a new kernel, this + * means a random memory location will be kept being written. + */ +#ifdef CONFIG_KEXEC_CORE +static void kvm_crash_shutdown(struct pt_regs *regs) +{ + kvm_guest_cpu_offline(true); + native_machine_crash_shutdown(regs); +} #endif static void __init kvm_guest_init(void) @@ -704,6 +735,12 @@ static void __init kvm_guest_init(void) kvm_guest_cpu_init(); #endif +#ifdef CONFIG_KEXEC_CORE + machine_ops.crash_shutdown = kvm_crash_shutdown; +#endif + + register_syscore_ops(&kvm_syscore_ops); + /* * Hard lockup detection is enabled by default. Disable it, as guests * can get false positives too easily, for example if the host is diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index d37ed4e1d033..ad273e5861c1 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -20,7 +20,6 @@ #include <asm/hypervisor.h> #include <asm/mem_encrypt.h> #include <asm/x86_init.h> -#include <asm/reboot.h> #include <asm/kvmclock.h> static int kvmclock __initdata = 1; @@ -203,28 +202,9 @@ static void kvm_setup_secondary_clock(void) } #endif -/* - * After the clock is registered, the host will keep writing to the - * registered memory location. If the guest happens to shutdown, this memory - * won't be valid. In cases like kexec, in which you install a new kernel, this - * means a random memory location will be kept being written. So before any - * kind of shutdown from our side, we unregister the clock by writing anything - * that does not have the 'enable' bit set in the msr - */ -#ifdef CONFIG_KEXEC_CORE -static void kvm_crash_shutdown(struct pt_regs *regs) -{ - native_write_msr(msr_kvm_system_time, 0, 0); - kvm_disable_steal_time(); - native_machine_crash_shutdown(regs); -} -#endif - -static void kvm_shutdown(void) +void kvmclock_disable(void) { native_write_msr(msr_kvm_system_time, 0, 0); - kvm_disable_steal_time(); - native_machine_shutdown(); } static void __init kvmclock_init_mem(void) @@ -351,10 +331,6 @@ void __init kvmclock_init(void) #endif x86_platform.save_sched_clock_state = kvm_save_sched_clock_state; x86_platform.restore_sched_clock_state = kvm_restore_sched_clock_state; - machine_ops.shutdown = kvm_shutdown; -#ifdef CONFIG_KEXEC_CORE - machine_ops.crash_shutdown = kvm_crash_shutdown; -#endif kvm_get_preset_lpj(); /* diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c index b5cb49e57df8..c94dec6a1834 100644 --- a/arch/x86/kernel/mmconf-fam10h_64.c +++ b/arch/x86/kernel/mmconf-fam10h_64.c @@ -95,7 +95,7 @@ static void get_fam10h_pci_mmconf_base(void) return; /* SYS_CFG */ - address = MSR_K8_SYSCFG; + address = MSR_AMD64_SYSCFG; rdmsrl(address, val); /* TOP_MEM2 is not enabled? */ diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 2ef961cf4cfc..4bce802d25fb 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -33,7 +33,7 @@ #include <asm/reboot.h> #include <asm/cache.h> #include <asm/nospec-branch.h> -#include <asm/sev-es.h> +#include <asm/sev.h> #define CREATE_TRACE_POINTS #include <trace/events/nmi.h> diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-shared.c index 0aa9f13efd57..6ec8b3bfd76e 100644 --- a/arch/x86/kernel/sev-es-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -26,13 +26,13 @@ static bool __init sev_es_check_cpu_features(void) static void __noreturn sev_es_terminate(unsigned int reason) { - u64 val = GHCB_SEV_TERMINATE; + u64 val = GHCB_MSR_TERM_REQ; /* * Tell the hypervisor what went wrong - only reason-set 0 is * currently supported. */ - val |= GHCB_SEV_TERMINATE_REASON(0, reason); + val |= GHCB_SEV_TERM_REASON(0, reason); /* Request Guest Termination from Hypvervisor */ sev_es_wr_ghcb_msr(val); @@ -47,15 +47,15 @@ static bool sev_es_negotiate_protocol(void) u64 val; /* Do the GHCB protocol version negotiation */ - sev_es_wr_ghcb_msr(GHCB_SEV_INFO_REQ); + sev_es_wr_ghcb_msr(GHCB_MSR_SEV_INFO_REQ); VMGEXIT(); val = sev_es_rd_ghcb_msr(); - if (GHCB_INFO(val) != GHCB_SEV_INFO) + if (GHCB_MSR_INFO(val) != GHCB_MSR_SEV_INFO_RESP) return false; - if (GHCB_PROTO_MAX(val) < GHCB_PROTO_OUR || - GHCB_PROTO_MIN(val) > GHCB_PROTO_OUR) + if (GHCB_MSR_PROTO_MAX(val) < GHCB_PROTO_OUR || + GHCB_MSR_PROTO_MIN(val) > GHCB_PROTO_OUR) return false; return true; @@ -153,28 +153,28 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EAX)); VMGEXIT(); val = sev_es_rd_ghcb_msr(); - if (GHCB_SEV_GHCB_RESP_CODE(val) != GHCB_SEV_CPUID_RESP) + if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP) goto fail; regs->ax = val >> 32; sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EBX)); VMGEXIT(); val = sev_es_rd_ghcb_msr(); - if (GHCB_SEV_GHCB_RESP_CODE(val) != GHCB_SEV_CPUID_RESP) + if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP) goto fail; regs->bx = val >> 32; sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_ECX)); VMGEXIT(); val = sev_es_rd_ghcb_msr(); - if (GHCB_SEV_GHCB_RESP_CODE(val) != GHCB_SEV_CPUID_RESP) + if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP) goto fail; regs->cx = val >> 32; sev_es_wr_ghcb_msr(GHCB_CPUID_REQ(fn, GHCB_CPUID_REQ_EDX)); VMGEXIT(); val = sev_es_rd_ghcb_msr(); - if (GHCB_SEV_GHCB_RESP_CODE(val) != GHCB_SEV_CPUID_RESP) + if (GHCB_RESP_CODE(val) != GHCB_MSR_CPUID_RESP) goto fail; regs->dx = val >> 32; diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev.c index 73873b007838..9578c82832aa 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev.c @@ -22,7 +22,7 @@ #include <asm/cpu_entry_area.h> #include <asm/stacktrace.h> -#include <asm/sev-es.h> +#include <asm/sev.h> #include <asm/insn-eval.h> #include <asm/fpu/internal.h> #include <asm/processor.h> @@ -459,7 +459,7 @@ static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt } /* Include code shared with pre-decompression boot stage */ -#include "sev-es-shared.c" +#include "sev-shared.c" void noinstr __sev_es_nmi_complete(void) { diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 0ad5214f598a..7770245cc7fa 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -2043,7 +2043,7 @@ static bool amd_set_max_freq_ratio(void) return false; } - highest_perf = perf_caps.highest_perf; + highest_perf = amd_get_highest_perf(); nominal_perf = perf_caps.nominal_perf; if (!highest_perf || !nominal_perf) { diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 19606a341888..9a48f138832d 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -458,7 +458,7 @@ void kvm_set_cpu_caps(void) F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) | F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) | F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B) | 0 /*WAITPKG*/ | - F(SGX_LC) + F(SGX_LC) | F(BUS_LOCK_DETECT) ); /* Set LA57 based on hardware capability. */ if (cpuid_ecx(7) & F(LA57)) @@ -567,6 +567,21 @@ void kvm_set_cpu_caps(void) F(ACE2) | F(ACE2_EN) | F(PHE) | F(PHE_EN) | F(PMM) | F(PMM_EN) ); + + /* + * Hide RDTSCP and RDPID if either feature is reported as supported but + * probing MSR_TSC_AUX failed. This is purely a sanity check and + * should never happen, but the guest will likely crash if RDTSCP or + * RDPID is misreported, and KVM has botched MSR_TSC_AUX emulation in + * the past. For example, the sanity check may fire if this instance of + * KVM is running as L1 on top of an older, broken KVM. + */ + if (WARN_ON((kvm_cpu_cap_has(X86_FEATURE_RDTSCP) || + kvm_cpu_cap_has(X86_FEATURE_RDPID)) && + !kvm_is_supported_user_return_msr(MSR_TSC_AUX))) { + kvm_cpu_cap_clear(X86_FEATURE_RDTSCP); + kvm_cpu_cap_clear(X86_FEATURE_RDPID); + } } EXPORT_SYMBOL_GPL(kvm_set_cpu_caps); @@ -637,7 +652,8 @@ static int __do_cpuid_func_emulated(struct kvm_cpuid_array *array, u32 func) case 7: entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; entry->eax = 0; - entry->ecx = F(RDPID); + if (kvm_cpu_cap_has(X86_FEATURE_RDTSCP)) + entry->ecx = F(RDPID); ++array->nent; default: break; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 77e1c89a95a7..8a0ccdb56076 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -4502,7 +4502,7 @@ static const struct opcode group8[] = { * from the register case of group9. */ static const struct gprefix pfx_0f_c7_7 = { - N, N, N, II(DstMem | ModRM | Op3264 | EmulateOnUD, em_rdpid, rdtscp), + N, N, N, II(DstMem | ModRM | Op3264 | EmulateOnUD, em_rdpid, rdpid), }; diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index 0d359115429a..f016838faedd 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -468,6 +468,7 @@ enum x86_intercept { x86_intercept_clgi, x86_intercept_skinit, x86_intercept_rdtscp, + x86_intercept_rdpid, x86_intercept_icebp, x86_intercept_wbinvd, x86_intercept_monitor, diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 152591f9243a..c0ebef560bd1 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1913,8 +1913,8 @@ void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu) if (!apic->lapic_timer.hv_timer_in_use) goto out; WARN_ON(rcuwait_active(&vcpu->wait)); - cancel_hv_timer(apic); apic_timer_expired(apic, false); + cancel_hv_timer(apic); if (apic_lvtt_period(apic) && apic->lapic_timer.period) { advance_periodic_target_expiration(apic); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 4b3ee244ebe0..0144c40d09c7 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3310,12 +3310,12 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) if (mmu->shadow_root_level == PT64_ROOT_4LEVEL) { pm_mask |= PT_ACCESSED_MASK | PT_WRITABLE_MASK | PT_USER_MASK; - if (WARN_ON_ONCE(!mmu->lm_root)) { + if (WARN_ON_ONCE(!mmu->pml4_root)) { r = -EIO; goto out_unlock; } - mmu->lm_root[0] = __pa(mmu->pae_root) | pm_mask; + mmu->pml4_root[0] = __pa(mmu->pae_root) | pm_mask; } for (i = 0; i < 4; ++i) { @@ -3335,7 +3335,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) } if (mmu->shadow_root_level == PT64_ROOT_4LEVEL) - mmu->root_hpa = __pa(mmu->lm_root); + mmu->root_hpa = __pa(mmu->pml4_root); else mmu->root_hpa = __pa(mmu->pae_root); @@ -3350,7 +3350,7 @@ out_unlock: static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.mmu; - u64 *lm_root, *pae_root; + u64 *pml4_root, *pae_root; /* * When shadowing 32-bit or PAE NPT with 64-bit NPT, the PML4 and PDP @@ -3369,14 +3369,14 @@ static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu) if (WARN_ON_ONCE(mmu->shadow_root_level != PT64_ROOT_4LEVEL)) return -EIO; - if (mmu->pae_root && mmu->lm_root) + if (mmu->pae_root && mmu->pml4_root) return 0; /* * The special roots should always be allocated in concert. Yell and * bail if KVM ends up in a state where only one of the roots is valid. */ - if (WARN_ON_ONCE(!tdp_enabled || mmu->pae_root || mmu->lm_root)) + if (WARN_ON_ONCE(!tdp_enabled || mmu->pae_root || mmu->pml4_root)) return -EIO; /* @@ -3387,14 +3387,14 @@ static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu) if (!pae_root) return -ENOMEM; - lm_root = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); - if (!lm_root) { + pml4_root = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); + if (!pml4_root) { free_page((unsigned long)pae_root); return -ENOMEM; } mmu->pae_root = pae_root; - mmu->lm_root = lm_root; + mmu->pml4_root = pml4_root; return 0; } @@ -5261,7 +5261,7 @@ static void free_mmu_pages(struct kvm_mmu *mmu) if (!tdp_enabled && mmu->pae_root) set_memory_encrypted((unsigned long)mmu->pae_root, 1); free_page((unsigned long)mmu->pae_root); - free_page((unsigned long)mmu->lm_root); + free_page((unsigned long)mmu->pml4_root); } static int __kvm_mmu_create(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 88f69a6cc492..95eeb5ac6a8a 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -388,7 +388,7 @@ static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt, } /** - * handle_changed_spte - handle bookkeeping associated with an SPTE change + * __handle_changed_spte - handle bookkeeping associated with an SPTE change * @kvm: kvm instance * @as_id: the address space of the paging structure the SPTE was a part of * @gfn: the base GFN that was mapped by the SPTE @@ -444,6 +444,13 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, trace_kvm_tdp_mmu_spte_changed(as_id, gfn, level, old_spte, new_spte); + if (is_large_pte(old_spte) != is_large_pte(new_spte)) { + if (is_large_pte(old_spte)) + atomic64_sub(1, (atomic64_t*)&kvm->stat.lpages); + else + atomic64_add(1, (atomic64_t*)&kvm->stat.lpages); + } + /* * The only times a SPTE should be changed from a non-present to * non-present state is when an MMIO entry is installed/modified/ @@ -1009,6 +1016,14 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, } if (!is_shadow_present_pte(iter.old_spte)) { + /* + * If SPTE has been forzen by another thread, just + * give up and retry, avoiding unnecessary page table + * allocation and free. + */ + if (is_removed_spte(iter.old_spte)) + break; + sp = alloc_tdp_mmu_page(vcpu, iter.gfn, iter.level); child_pt = sp->spt; diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 540d43ba2cf4..5e8d8443154e 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -764,7 +764,6 @@ int nested_svm_vmexit(struct vcpu_svm *svm) nested_svm_copy_common_state(svm->nested.vmcb02.ptr, svm->vmcb01.ptr); svm_switch_vmcb(svm, &svm->vmcb01); - WARN_ON_ONCE(svm->vmcb->control.exit_code != SVM_EXIT_VMRUN); /* * On vmexit the GIF is set to false and @@ -872,6 +871,15 @@ void svm_free_nested(struct vcpu_svm *svm) __free_page(virt_to_page(svm->nested.vmcb02.ptr)); svm->nested.vmcb02.ptr = NULL; + /* + * When last_vmcb12_gpa matches the current vmcb12 gpa, + * some vmcb12 fields are not loaded if they are marked clean + * in the vmcb12, since in this case they are up to date already. + * + * When the vmcb02 is freed, this optimization becomes invalid. + */ + svm->nested.last_vmcb12_gpa = INVALID_GPA; + svm->nested.initialized = false; } @@ -884,9 +892,11 @@ void svm_leave_nested(struct vcpu_svm *svm) if (is_guest_mode(vcpu)) { svm->nested.nested_run_pending = 0; + svm->nested.vmcb12_gpa = INVALID_GPA; + leave_guest_mode(vcpu); - svm_switch_vmcb(svm, &svm->nested.vmcb02); + svm_switch_vmcb(svm, &svm->vmcb01); nested_svm_uninit_mmu_context(vcpu); vmcb_mark_all_dirty(svm->vmcb); @@ -1298,12 +1308,17 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, * L2 registers if needed are moved from the current VMCB to VMCB02. */ + if (is_guest_mode(vcpu)) + svm_leave_nested(svm); + else + svm->nested.vmcb02.ptr->save = svm->vmcb01.ptr->save; + + svm_set_gif(svm, !!(kvm_state->flags & KVM_STATE_NESTED_GIF_SET)); + svm->nested.nested_run_pending = !!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING); svm->nested.vmcb12_gpa = kvm_state->hdr.svm.vmcb_pa; - if (svm->current_vmcb == &svm->vmcb01) - svm->nested.vmcb02.ptr->save = svm->vmcb01.ptr->save; svm->vmcb01.ptr->save.es = save->es; svm->vmcb01.ptr->save.cs = save->cs; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 1356ee095cd5..5bc887e9a986 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -763,7 +763,7 @@ static int __sev_dbg_decrypt(struct kvm *kvm, unsigned long src_paddr, } static int __sev_dbg_decrypt_user(struct kvm *kvm, unsigned long paddr, - unsigned long __user dst_uaddr, + void __user *dst_uaddr, unsigned long dst_paddr, int size, int *err) { @@ -787,8 +787,7 @@ static int __sev_dbg_decrypt_user(struct kvm *kvm, unsigned long paddr, if (tpage) { offset = paddr & 15; - if (copy_to_user((void __user *)(uintptr_t)dst_uaddr, - page_address(tpage) + offset, size)) + if (copy_to_user(dst_uaddr, page_address(tpage) + offset, size)) ret = -EFAULT; } @@ -800,9 +799,9 @@ e_free: } static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr, - unsigned long __user vaddr, + void __user *vaddr, unsigned long dst_paddr, - unsigned long __user dst_vaddr, + void __user *dst_vaddr, int size, int *error) { struct page *src_tpage = NULL; @@ -810,13 +809,12 @@ static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr, int ret, len = size; /* If source buffer is not aligned then use an intermediate buffer */ - if (!IS_ALIGNED(vaddr, 16)) { + if (!IS_ALIGNED((unsigned long)vaddr, 16)) { src_tpage = alloc_page(GFP_KERNEL); if (!src_tpage) return -ENOMEM; - if (copy_from_user(page_address(src_tpage), - (void __user *)(uintptr_t)vaddr, size)) { + if (copy_from_user(page_address(src_tpage), vaddr, size)) { __free_page(src_tpage); return -EFAULT; } @@ -830,7 +828,7 @@ static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr, * - copy the source buffer in an intermediate buffer * - use the intermediate buffer as source buffer */ - if (!IS_ALIGNED(dst_vaddr, 16) || !IS_ALIGNED(size, 16)) { + if (!IS_ALIGNED((unsigned long)dst_vaddr, 16) || !IS_ALIGNED(size, 16)) { int dst_offset; dst_tpage = alloc_page(GFP_KERNEL); @@ -855,7 +853,7 @@ static int __sev_dbg_encrypt_user(struct kvm *kvm, unsigned long paddr, page_address(src_tpage), size); else { if (copy_from_user(page_address(dst_tpage) + dst_offset, - (void __user *)(uintptr_t)vaddr, size)) { + vaddr, size)) { ret = -EFAULT; goto e_free; } @@ -935,15 +933,15 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) if (dec) ret = __sev_dbg_decrypt_user(kvm, __sme_page_pa(src_p[0]) + s_off, - dst_vaddr, + (void __user *)dst_vaddr, __sme_page_pa(dst_p[0]) + d_off, len, &argp->error); else ret = __sev_dbg_encrypt_user(kvm, __sme_page_pa(src_p[0]) + s_off, - vaddr, + (void __user *)vaddr, __sme_page_pa(dst_p[0]) + d_off, - dst_vaddr, + (void __user *)dst_vaddr, len, &argp->error); sev_unpin_memory(kvm, src_p, n); @@ -1764,7 +1762,8 @@ e_mirror_unlock: e_source_unlock: mutex_unlock(&source_kvm->lock); e_source_put: - fput(source_kvm_file); + if (source_kvm_file) + fput(source_kvm_file); return ret; } @@ -2198,7 +2197,7 @@ vmgexit_err: return -EINVAL; } -static void pre_sev_es_run(struct vcpu_svm *svm) +void sev_es_unmap_ghcb(struct vcpu_svm *svm) { if (!svm->ghcb) return; @@ -2234,9 +2233,6 @@ void pre_sev_run(struct vcpu_svm *svm, int cpu) struct svm_cpu_data *sd = per_cpu(svm_data, cpu); int asid = sev_get_asid(svm->vcpu.kvm); - /* Perform any SEV-ES pre-run actions */ - pre_sev_es_run(svm); - /* Assign the asid allocated with this SEV guest */ svm->asid = asid; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index b649f92287a2..05eca131eaf2 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -212,7 +212,7 @@ DEFINE_PER_CPU(struct svm_cpu_data *, svm_data); * RDTSCP and RDPID are not used in the kernel, specifically to allow KVM to * defer the restoration of TSC_AUX until the CPU returns to userspace. */ -#define TSC_AUX_URET_SLOT 0 +static int tsc_aux_uret_slot __read_mostly = -1; static const u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000}; @@ -447,6 +447,11 @@ static int has_svm(void) return 0; } + if (pgtable_l5_enabled()) { + pr_info("KVM doesn't yet support 5-level paging on AMD SVM\n"); + return 0; + } + return 1; } @@ -858,8 +863,8 @@ static __init void svm_adjust_mmio_mask(void) return; /* If memory encryption is not enabled, use existing mask */ - rdmsrl(MSR_K8_SYSCFG, msr); - if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT)) + rdmsrl(MSR_AMD64_SYSCFG, msr); + if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT)) return; enc_bit = cpuid_ebx(0x8000001f) & 0x3f; @@ -959,8 +964,7 @@ static __init int svm_hardware_setup(void) kvm_tsc_scaling_ratio_frac_bits = 32; } - if (boot_cpu_has(X86_FEATURE_RDTSCP)) - kvm_define_user_return_msr(TSC_AUX_URET_SLOT, MSR_TSC_AUX); + tsc_aux_uret_slot = kvm_add_user_return_msr(MSR_TSC_AUX); /* Check for pause filtering support */ if (!boot_cpu_has(X86_FEATURE_PAUSEFILTER)) { @@ -1100,7 +1104,9 @@ static u64 svm_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) return svm->vmcb->control.tsc_offset; } -static void svm_check_invpcid(struct vcpu_svm *svm) +/* Evaluate instruction intercepts that depend on guest CPUID features. */ +static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu, + struct vcpu_svm *svm) { /* * Intercept INVPCID if shadow paging is enabled to sync/free shadow @@ -1113,6 +1119,13 @@ static void svm_check_invpcid(struct vcpu_svm *svm) else svm_clr_intercept(svm, INTERCEPT_INVPCID); } + + if (kvm_cpu_cap_has(X86_FEATURE_RDTSCP)) { + if (guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) + svm_clr_intercept(svm, INTERCEPT_RDTSCP); + else + svm_set_intercept(svm, INTERCEPT_RDTSCP); + } } static void init_vmcb(struct kvm_vcpu *vcpu) @@ -1235,8 +1248,8 @@ static void init_vmcb(struct kvm_vcpu *vcpu) svm->current_vmcb->asid_generation = 0; svm->asid = 0; - svm->nested.vmcb12_gpa = 0; - svm->nested.last_vmcb12_gpa = 0; + svm->nested.vmcb12_gpa = INVALID_GPA; + svm->nested.last_vmcb12_gpa = INVALID_GPA; vcpu->arch.hflags = 0; if (!kvm_pause_in_guest(vcpu->kvm)) { @@ -1248,7 +1261,7 @@ static void init_vmcb(struct kvm_vcpu *vcpu) svm_clr_intercept(svm, INTERCEPT_PAUSE); } - svm_check_invpcid(svm); + svm_recalc_instruction_intercepts(vcpu, svm); /* * If the host supports V_SPEC_CTRL then disable the interception @@ -1424,6 +1437,9 @@ static void svm_prepare_guest_switch(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); struct svm_cpu_data *sd = per_cpu(svm_data, vcpu->cpu); + if (sev_es_guest(vcpu->kvm)) + sev_es_unmap_ghcb(svm); + if (svm->guest_state_loaded) return; @@ -1445,8 +1461,8 @@ static void svm_prepare_guest_switch(struct kvm_vcpu *vcpu) } } - if (static_cpu_has(X86_FEATURE_RDTSCP)) - kvm_set_user_return_msr(TSC_AUX_URET_SLOT, svm->tsc_aux, -1ull); + if (likely(tsc_aux_uret_slot >= 0)) + kvm_set_user_return_msr(tsc_aux_uret_slot, svm->tsc_aux, -1ull); svm->guest_state_loaded = true; } @@ -2655,11 +2671,6 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data |= (u64)svm->sysenter_esp_hi << 32; break; case MSR_TSC_AUX: - if (!boot_cpu_has(X86_FEATURE_RDTSCP)) - return 1; - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) - return 1; msr_info->data = svm->tsc_aux; break; /* @@ -2876,30 +2887,13 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) svm->sysenter_esp_hi = guest_cpuid_is_intel(vcpu) ? (data >> 32) : 0; break; case MSR_TSC_AUX: - if (!boot_cpu_has(X86_FEATURE_RDTSCP)) - return 1; - - if (!msr->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) - return 1; - - /* - * Per Intel's SDM, bits 63:32 are reserved, but AMD's APM has - * incomplete and conflicting architectural behavior. Current - * AMD CPUs completely ignore bits 63:32, i.e. they aren't - * reserved and always read as zeros. Emulate AMD CPU behavior - * to avoid explosions if the vCPU is migrated from an AMD host - * to an Intel host. - */ - data = (u32)data; - /* * TSC_AUX is usually changed only during boot and never read * directly. Intercept TSC_AUX instead of exposing it to the * guest via direct_access_msrs, and switch it via user return. */ preempt_disable(); - r = kvm_set_user_return_msr(TSC_AUX_URET_SLOT, data, -1ull); + r = kvm_set_user_return_msr(tsc_aux_uret_slot, data, -1ull); preempt_enable(); if (r) return 1; @@ -3084,6 +3078,7 @@ static int (*const svm_exit_handlers[])(struct kvm_vcpu *vcpu) = { [SVM_EXIT_STGI] = stgi_interception, [SVM_EXIT_CLGI] = clgi_interception, [SVM_EXIT_SKINIT] = skinit_interception, + [SVM_EXIT_RDTSCP] = kvm_handle_invalid_op, [SVM_EXIT_WBINVD] = kvm_emulate_wbinvd, [SVM_EXIT_MONITOR] = kvm_emulate_monitor, [SVM_EXIT_MWAIT] = kvm_emulate_mwait, @@ -3972,8 +3967,7 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) svm->nrips_enabled = kvm_cpu_cap_has(X86_FEATURE_NRIPS) && guest_cpuid_has(vcpu, X86_FEATURE_NRIPS); - /* Check again if INVPCID interception if required */ - svm_check_invpcid(svm); + svm_recalc_instruction_intercepts(vcpu, svm); /* For sev guests, the memory encryption bit is not reserved in CR3. */ if (sev_guest(vcpu->kvm)) { diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 84b3133c2251..2c9ece618b29 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -20,6 +20,7 @@ #include <linux/bits.h> #include <asm/svm.h> +#include <asm/sev-common.h> #define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT) @@ -525,40 +526,9 @@ void svm_vcpu_unblocking(struct kvm_vcpu *vcpu); /* sev.c */ -#define GHCB_VERSION_MAX 1ULL -#define GHCB_VERSION_MIN 1ULL - -#define GHCB_MSR_INFO_POS 0 -#define GHCB_MSR_INFO_MASK (BIT_ULL(12) - 1) - -#define GHCB_MSR_SEV_INFO_RESP 0x001 -#define GHCB_MSR_SEV_INFO_REQ 0x002 -#define GHCB_MSR_VER_MAX_POS 48 -#define GHCB_MSR_VER_MAX_MASK 0xffff -#define GHCB_MSR_VER_MIN_POS 32 -#define GHCB_MSR_VER_MIN_MASK 0xffff -#define GHCB_MSR_CBIT_POS 24 -#define GHCB_MSR_CBIT_MASK 0xff -#define GHCB_MSR_SEV_INFO(_max, _min, _cbit) \ - ((((_max) & GHCB_MSR_VER_MAX_MASK) << GHCB_MSR_VER_MAX_POS) | \ - (((_min) & GHCB_MSR_VER_MIN_MASK) << GHCB_MSR_VER_MIN_POS) | \ - (((_cbit) & GHCB_MSR_CBIT_MASK) << GHCB_MSR_CBIT_POS) | \ - GHCB_MSR_SEV_INFO_RESP) - -#define GHCB_MSR_CPUID_REQ 0x004 -#define GHCB_MSR_CPUID_RESP 0x005 -#define GHCB_MSR_CPUID_FUNC_POS 32 -#define GHCB_MSR_CPUID_FUNC_MASK 0xffffffff -#define GHCB_MSR_CPUID_VALUE_POS 32 -#define GHCB_MSR_CPUID_VALUE_MASK 0xffffffff -#define GHCB_MSR_CPUID_REG_POS 30 -#define GHCB_MSR_CPUID_REG_MASK 0x3 - -#define GHCB_MSR_TERM_REQ 0x100 -#define GHCB_MSR_TERM_REASON_SET_POS 12 -#define GHCB_MSR_TERM_REASON_SET_MASK 0xf -#define GHCB_MSR_TERM_REASON_POS 16 -#define GHCB_MSR_TERM_REASON_MASK 0xff +#define GHCB_VERSION_MAX 1ULL +#define GHCB_VERSION_MIN 1ULL + extern unsigned int max_sev_asid; @@ -581,6 +551,7 @@ void sev_es_init_vmcb(struct vcpu_svm *svm); void sev_es_create_vcpu(struct vcpu_svm *svm); void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); void sev_es_prepare_guest_switch(struct vcpu_svm *svm, unsigned int cpu); +void sev_es_unmap_ghcb(struct vcpu_svm *svm); /* vmenter.S */ diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index d1d77985e889..8dee8a5fbc17 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -398,6 +398,9 @@ static inline u64 vmx_supported_debugctl(void) { u64 debugctl = 0; + if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT)) + debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT; + if (vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT) debugctl |= DEBUGCTLMSR_LBR_MASK; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index bced76637823..6058a65a6ede 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -3098,15 +3098,8 @@ static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu) nested_vmx_handle_enlightened_vmptrld(vcpu, false); if (evmptrld_status == EVMPTRLD_VMFAIL || - evmptrld_status == EVMPTRLD_ERROR) { - pr_debug_ratelimited("%s: enlightened vmptrld failed\n", - __func__); - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = - KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; + evmptrld_status == EVMPTRLD_ERROR) return false; - } } return true; @@ -3194,8 +3187,16 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu) { - if (!nested_get_evmcs_page(vcpu)) + if (!nested_get_evmcs_page(vcpu)) { + pr_debug_ratelimited("%s: enlightened vmptrld failed\n", + __func__); + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = + KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; + return false; + } if (is_guest_mode(vcpu) && !nested_get_vmcs12_pages(vcpu)) return false; @@ -4435,7 +4436,15 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, /* Similarly, triple faults in L2 should never escape. */ WARN_ON_ONCE(kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)); - kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); + if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) { + /* + * KVM_REQ_GET_NESTED_STATE_PAGES is also used to map + * Enlightened VMCS after migration and we still need to + * do that when something is forcing L2->L1 exit prior to + * the first L2 run. + */ + (void)nested_get_evmcs_page(vcpu); + } /* Service the TLB flush request for L2 before switching to L1. */ if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index d000cddbd734..4bceb5ca3a89 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -455,21 +455,6 @@ static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx) static unsigned long host_idt_base; -/* - * Though SYSCALL is only supported in 64-bit mode on Intel CPUs, kvm - * will emulate SYSCALL in legacy mode if the vendor string in guest - * CPUID.0:{EBX,ECX,EDX} is "AuthenticAMD" or "AMDisbetter!" To - * support this emulation, IA32_STAR must always be included in - * vmx_uret_msrs_list[], even in i386 builds. - */ -static const u32 vmx_uret_msrs_list[] = { -#ifdef CONFIG_X86_64 - MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, -#endif - MSR_EFER, MSR_TSC_AUX, MSR_STAR, - MSR_IA32_TSX_CTRL, -}; - #if IS_ENABLED(CONFIG_HYPERV) static bool __read_mostly enlightened_vmcs = true; module_param(enlightened_vmcs, bool, 0444); @@ -697,21 +682,11 @@ static bool is_valid_passthrough_msr(u32 msr) return r; } -static inline int __vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr) -{ - int i; - - for (i = 0; i < vmx->nr_uret_msrs; ++i) - if (vmx_uret_msrs_list[vmx->guest_uret_msrs[i].slot] == msr) - return i; - return -1; -} - struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr) { int i; - i = __vmx_find_uret_msr(vmx, msr); + i = kvm_find_user_return_msr(msr); if (i >= 0) return &vmx->guest_uret_msrs[i]; return NULL; @@ -720,13 +695,14 @@ struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr) static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx, struct vmx_uret_msr *msr, u64 data) { + unsigned int slot = msr - vmx->guest_uret_msrs; int ret = 0; u64 old_msr_data = msr->data; msr->data = data; - if (msr - vmx->guest_uret_msrs < vmx->nr_active_uret_msrs) { + if (msr->load_into_hardware) { preempt_disable(); - ret = kvm_set_user_return_msr(msr->slot, msr->data, msr->mask); + ret = kvm_set_user_return_msr(slot, msr->data, msr->mask); preempt_enable(); if (ret) msr->data = old_msr_data; @@ -1078,7 +1054,7 @@ static bool update_transition_efer(struct vcpu_vmx *vmx) return false; } - i = __vmx_find_uret_msr(vmx, MSR_EFER); + i = kvm_find_user_return_msr(MSR_EFER); if (i < 0) return false; @@ -1240,11 +1216,14 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) */ if (!vmx->guest_uret_msrs_loaded) { vmx->guest_uret_msrs_loaded = true; - for (i = 0; i < vmx->nr_active_uret_msrs; ++i) - kvm_set_user_return_msr(vmx->guest_uret_msrs[i].slot, + for (i = 0; i < kvm_nr_uret_msrs; ++i) { + if (!vmx->guest_uret_msrs[i].load_into_hardware) + continue; + + kvm_set_user_return_msr(i, vmx->guest_uret_msrs[i].data, vmx->guest_uret_msrs[i].mask); - + } } if (vmx->nested.need_vmcs12_to_shadow_sync) @@ -1751,19 +1730,16 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu) vmx_clear_hlt(vcpu); } -static void vmx_setup_uret_msr(struct vcpu_vmx *vmx, unsigned int msr) +static void vmx_setup_uret_msr(struct vcpu_vmx *vmx, unsigned int msr, + bool load_into_hardware) { - struct vmx_uret_msr tmp; - int from, to; + struct vmx_uret_msr *uret_msr; - from = __vmx_find_uret_msr(vmx, msr); - if (from < 0) + uret_msr = vmx_find_uret_msr(vmx, msr); + if (!uret_msr) return; - to = vmx->nr_active_uret_msrs++; - tmp = vmx->guest_uret_msrs[to]; - vmx->guest_uret_msrs[to] = vmx->guest_uret_msrs[from]; - vmx->guest_uret_msrs[from] = tmp; + uret_msr->load_into_hardware = load_into_hardware; } /* @@ -1773,29 +1749,42 @@ static void vmx_setup_uret_msr(struct vcpu_vmx *vmx, unsigned int msr) */ static void setup_msrs(struct vcpu_vmx *vmx) { - vmx->guest_uret_msrs_loaded = false; - vmx->nr_active_uret_msrs = 0; #ifdef CONFIG_X86_64 + bool load_syscall_msrs; + /* * The SYSCALL MSRs are only needed on long mode guests, and only * when EFER.SCE is set. */ - if (is_long_mode(&vmx->vcpu) && (vmx->vcpu.arch.efer & EFER_SCE)) { - vmx_setup_uret_msr(vmx, MSR_STAR); - vmx_setup_uret_msr(vmx, MSR_LSTAR); - vmx_setup_uret_msr(vmx, MSR_SYSCALL_MASK); - } + load_syscall_msrs = is_long_mode(&vmx->vcpu) && + (vmx->vcpu.arch.efer & EFER_SCE); + + vmx_setup_uret_msr(vmx, MSR_STAR, load_syscall_msrs); + vmx_setup_uret_msr(vmx, MSR_LSTAR, load_syscall_msrs); + vmx_setup_uret_msr(vmx, MSR_SYSCALL_MASK, load_syscall_msrs); #endif - if (update_transition_efer(vmx)) - vmx_setup_uret_msr(vmx, MSR_EFER); + vmx_setup_uret_msr(vmx, MSR_EFER, update_transition_efer(vmx)); - if (guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP)) - vmx_setup_uret_msr(vmx, MSR_TSC_AUX); + vmx_setup_uret_msr(vmx, MSR_TSC_AUX, + guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP) || + guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDPID)); - vmx_setup_uret_msr(vmx, MSR_IA32_TSX_CTRL); + /* + * hle=0, rtm=0, tsx_ctrl=1 can be found with some combinations of new + * kernel and old userspace. If those guests run on a tsx=off host, do + * allow guests to use TSX_CTRL, but don't change the value in hardware + * so that TSX remains always disabled. + */ + vmx_setup_uret_msr(vmx, MSR_IA32_TSX_CTRL, boot_cpu_has(X86_FEATURE_RTM)); if (cpu_has_vmx_msr_bitmap()) vmx_update_msr_bitmap(&vmx->vcpu); + + /* + * The set of MSRs to load may have changed, reload MSRs before the + * next VM-Enter. + */ + vmx->guest_uret_msrs_loaded = false; } static u64 vmx_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) @@ -1993,11 +1982,6 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) else msr_info->data = vmx->pt_desc.guest.addr_a[index / 2]; break; - case MSR_TSC_AUX: - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) - return 1; - goto find_uret_msr; case MSR_IA32_DEBUGCTLMSR: msr_info->data = vmcs_read64(GUEST_IA32_DEBUGCTL); break; @@ -2031,6 +2015,9 @@ static u64 vcpu_supported_debugctl(struct kvm_vcpu *vcpu) if (!intel_pmu_lbr_is_enabled(vcpu)) debugctl &= ~DEBUGCTLMSR_LBR_MASK; + if (!guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)) + debugctl &= ~DEBUGCTLMSR_BUS_LOCK_DETECT; + return debugctl; } @@ -2313,14 +2300,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) else vmx->pt_desc.guest.addr_a[index / 2] = data; break; - case MSR_TSC_AUX: - if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) - return 1; - /* Check reserved bit, higher 32 bits should be zero */ - if ((data >> 32) != 0) - return 1; - goto find_uret_msr; case MSR_IA32_PERF_CAPABILITIES: if (data && !vcpu_to_pmu(vcpu)->version) return 1; @@ -4369,7 +4348,23 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx) xsaves_enabled, false); } - vmx_adjust_sec_exec_feature(vmx, &exec_control, rdtscp, RDTSCP); + /* + * RDPID is also gated by ENABLE_RDTSCP, turn on the control if either + * feature is exposed to the guest. This creates a virtualization hole + * if both are supported in hardware but only one is exposed to the + * guest, but letting the guest execute RDTSCP or RDPID when either one + * is advertised is preferable to emulating the advertised instruction + * in KVM on #UD, and obviously better than incorrectly injecting #UD. + */ + if (cpu_has_vmx_rdtscp()) { + bool rdpid_or_rdtscp_enabled = + guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) || + guest_cpuid_has(vcpu, X86_FEATURE_RDPID); + + vmx_adjust_secondary_exec_control(vmx, &exec_control, + SECONDARY_EXEC_ENABLE_RDTSCP, + rdpid_or_rdtscp_enabled, false); + } vmx_adjust_sec_exec_feature(vmx, &exec_control, invpcid, INVPCID); vmx_adjust_sec_exec_exiting(vmx, &exec_control, rdrand, RDRAND); @@ -6855,6 +6850,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) static int vmx_create_vcpu(struct kvm_vcpu *vcpu) { + struct vmx_uret_msr *tsx_ctrl; struct vcpu_vmx *vmx; int i, cpu, err; @@ -6877,43 +6873,19 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) goto free_vpid; } - BUILD_BUG_ON(ARRAY_SIZE(vmx_uret_msrs_list) != MAX_NR_USER_RETURN_MSRS); - - for (i = 0; i < ARRAY_SIZE(vmx_uret_msrs_list); ++i) { - u32 index = vmx_uret_msrs_list[i]; - u32 data_low, data_high; - int j = vmx->nr_uret_msrs; - - if (rdmsr_safe(index, &data_low, &data_high) < 0) - continue; - if (wrmsr_safe(index, data_low, data_high) < 0) - continue; - - vmx->guest_uret_msrs[j].slot = i; - vmx->guest_uret_msrs[j].data = 0; - switch (index) { - case MSR_IA32_TSX_CTRL: - /* - * TSX_CTRL_CPUID_CLEAR is handled in the CPUID - * interception. Keep the host value unchanged to avoid - * changing CPUID bits under the host kernel's feet. - * - * hle=0, rtm=0, tsx_ctrl=1 can be found with some - * combinations of new kernel and old userspace. If - * those guests run on a tsx=off host, do allow guests - * to use TSX_CTRL, but do not change the value on the - * host so that TSX remains always disabled. - */ - if (boot_cpu_has(X86_FEATURE_RTM)) - vmx->guest_uret_msrs[j].mask = ~(u64)TSX_CTRL_CPUID_CLEAR; - else - vmx->guest_uret_msrs[j].mask = 0; - break; - default: - vmx->guest_uret_msrs[j].mask = -1ull; - break; - } - ++vmx->nr_uret_msrs; + for (i = 0; i < kvm_nr_uret_msrs; ++i) { + vmx->guest_uret_msrs[i].data = 0; + vmx->guest_uret_msrs[i].mask = -1ull; + } + if (boot_cpu_has(X86_FEATURE_RTM)) { + /* + * TSX_CTRL_CPUID_CLEAR is handled in the CPUID interception. + * Keep the host value unchanged to avoid changing CPUID bits + * under the host kernel's feet. + */ + tsx_ctrl = vmx_find_uret_msr(vmx, MSR_IA32_TSX_CTRL); + if (tsx_ctrl) + vmx->guest_uret_msrs[i].mask = ~(u64)TSX_CTRL_CPUID_CLEAR; } err = alloc_loaded_vmcs(&vmx->vmcs01); @@ -7344,9 +7316,11 @@ static __init void vmx_set_cpu_caps(void) if (!cpu_has_vmx_xsaves()) kvm_cpu_cap_clear(X86_FEATURE_XSAVES); - /* CPUID 0x80000001 */ - if (!cpu_has_vmx_rdtscp()) + /* CPUID 0x80000001 and 0x7 (RDPID) */ + if (!cpu_has_vmx_rdtscp()) { kvm_cpu_cap_clear(X86_FEATURE_RDTSCP); + kvm_cpu_cap_clear(X86_FEATURE_RDPID); + } if (cpu_has_vmx_waitpkg()) kvm_cpu_cap_check_and_set(X86_FEATURE_WAITPKG); @@ -7402,8 +7376,9 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu, /* * RDPID causes #UD if disabled through secondary execution controls. * Because it is marked as EmulateOnUD, we need to intercept it here. + * Note, RDPID is hidden behind ENABLE_RDTSCP. */ - case x86_intercept_rdtscp: + case x86_intercept_rdpid: if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_RDTSCP)) { exception->vector = UD_VECTOR; exception->error_code_valid = false; @@ -7769,17 +7744,42 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector, }; +static __init void vmx_setup_user_return_msrs(void) +{ + + /* + * Though SYSCALL is only supported in 64-bit mode on Intel CPUs, kvm + * will emulate SYSCALL in legacy mode if the vendor string in guest + * CPUID.0:{EBX,ECX,EDX} is "AuthenticAMD" or "AMDisbetter!" To + * support this emulation, MSR_STAR is included in the list for i386, + * but is never loaded into hardware. MSR_CSTAR is also never loaded + * into hardware and is here purely for emulation purposes. + */ + const u32 vmx_uret_msrs_list[] = { + #ifdef CONFIG_X86_64 + MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, + #endif + MSR_EFER, MSR_TSC_AUX, MSR_STAR, + MSR_IA32_TSX_CTRL, + }; + int i; + + BUILD_BUG_ON(ARRAY_SIZE(vmx_uret_msrs_list) != MAX_NR_USER_RETURN_MSRS); + + for (i = 0; i < ARRAY_SIZE(vmx_uret_msrs_list); ++i) + kvm_add_user_return_msr(vmx_uret_msrs_list[i]); +} + static __init int hardware_setup(void) { unsigned long host_bndcfgs; struct desc_ptr dt; - int r, i, ept_lpage_level; + int r, ept_lpage_level; store_idt(&dt); host_idt_base = dt.address; - for (i = 0; i < ARRAY_SIZE(vmx_uret_msrs_list); ++i) - kvm_define_user_return_msr(i, vmx_uret_msrs_list[i]); + vmx_setup_user_return_msrs(); if (setup_vmcs_config(&vmcs_config, &vmx_capability) < 0) return -EIO; diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 008cb87ff088..16e4e457ba23 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -36,7 +36,7 @@ struct vmx_msrs { }; struct vmx_uret_msr { - unsigned int slot; /* The MSR's slot in kvm_user_return_msrs. */ + bool load_into_hardware; u64 data; u64 mask; }; @@ -245,8 +245,16 @@ struct vcpu_vmx { u32 idt_vectoring_info; ulong rflags; + /* + * User return MSRs are always emulated when enabled in the guest, but + * only loaded into hardware when necessary, e.g. SYSCALL #UDs outside + * of 64-bit mode or if EFER.SCE=1, thus the SYSCALL MSRs don't need to + * be loaded into hardware if those conditions aren't met. + * nr_active_uret_msrs tracks the number of MSRs that need to be loaded + * into hardware when running the guest. guest_uret_msrs[] is resorted + * whenever the number of "active" uret MSRs is modified. + */ struct vmx_uret_msr guest_uret_msrs[MAX_NR_USER_RETURN_MSRS]; - int nr_uret_msrs; int nr_active_uret_msrs; bool guest_uret_msrs_loaded; #ifdef CONFIG_X86_64 diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6eda2834fc05..bbc4e04e67ad 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -184,11 +184,6 @@ module_param(pi_inject_timer, bint, S_IRUGO | S_IWUSR); */ #define KVM_MAX_NR_USER_RETURN_MSRS 16 -struct kvm_user_return_msrs_global { - int nr; - u32 msrs[KVM_MAX_NR_USER_RETURN_MSRS]; -}; - struct kvm_user_return_msrs { struct user_return_notifier urn; bool registered; @@ -198,7 +193,9 @@ struct kvm_user_return_msrs { } values[KVM_MAX_NR_USER_RETURN_MSRS]; }; -static struct kvm_user_return_msrs_global __read_mostly user_return_msrs_global; +u32 __read_mostly kvm_nr_uret_msrs; +EXPORT_SYMBOL_GPL(kvm_nr_uret_msrs); +static u32 __read_mostly kvm_uret_msrs_list[KVM_MAX_NR_USER_RETURN_MSRS]; static struct kvm_user_return_msrs __percpu *user_return_msrs; #define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \ @@ -330,23 +327,53 @@ static void kvm_on_user_return(struct user_return_notifier *urn) user_return_notifier_unregister(urn); } local_irq_restore(flags); - for (slot = 0; slot < user_return_msrs_global.nr; ++slot) { + for (slot = 0; slot < kvm_nr_uret_msrs; ++slot) { values = &msrs->values[slot]; if (values->host != values->curr) { - wrmsrl(user_return_msrs_global.msrs[slot], values->host); + wrmsrl(kvm_uret_msrs_list[slot], values->host); values->curr = values->host; } } } -void kvm_define_user_return_msr(unsigned slot, u32 msr) +static int kvm_probe_user_return_msr(u32 msr) +{ + u64 val; + int ret; + + preempt_disable(); + ret = rdmsrl_safe(msr, &val); + if (ret) + goto out; + ret = wrmsrl_safe(msr, val); +out: + preempt_enable(); + return ret; +} + +int kvm_add_user_return_msr(u32 msr) { - BUG_ON(slot >= KVM_MAX_NR_USER_RETURN_MSRS); - user_return_msrs_global.msrs[slot] = msr; - if (slot >= user_return_msrs_global.nr) - user_return_msrs_global.nr = slot + 1; + BUG_ON(kvm_nr_uret_msrs >= KVM_MAX_NR_USER_RETURN_MSRS); + + if (kvm_probe_user_return_msr(msr)) + return -1; + + kvm_uret_msrs_list[kvm_nr_uret_msrs] = msr; + return kvm_nr_uret_msrs++; } -EXPORT_SYMBOL_GPL(kvm_define_user_return_msr); +EXPORT_SYMBOL_GPL(kvm_add_user_return_msr); + +int kvm_find_user_return_msr(u32 msr) +{ + int i; + + for (i = 0; i < kvm_nr_uret_msrs; ++i) { + if (kvm_uret_msrs_list[i] == msr) + return i; + } + return -1; +} +EXPORT_SYMBOL_GPL(kvm_find_user_return_msr); static void kvm_user_return_msr_cpu_online(void) { @@ -355,8 +382,8 @@ static void kvm_user_return_msr_cpu_online(void) u64 value; int i; - for (i = 0; i < user_return_msrs_global.nr; ++i) { - rdmsrl_safe(user_return_msrs_global.msrs[i], &value); + for (i = 0; i < kvm_nr_uret_msrs; ++i) { + rdmsrl_safe(kvm_uret_msrs_list[i], &value); msrs->values[i].host = value; msrs->values[i].curr = value; } @@ -371,7 +398,7 @@ int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask) value = (value & mask) | (msrs->values[slot].host & ~mask); if (value == msrs->values[slot].curr) return 0; - err = wrmsrl_safe(user_return_msrs_global.msrs[slot], value); + err = wrmsrl_safe(kvm_uret_msrs_list[slot], value); if (err) return 1; @@ -1149,6 +1176,9 @@ static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu) if (!guest_cpuid_has(vcpu, X86_FEATURE_RTM)) fixed |= DR6_RTM; + + if (!guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)) + fixed |= DR6_BUS_LOCK; return fixed; } @@ -1615,6 +1645,30 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, * invokes 64-bit SYSENTER. */ data = get_canonical(data, vcpu_virt_addr_bits(vcpu)); + break; + case MSR_TSC_AUX: + if (!kvm_is_supported_user_return_msr(MSR_TSC_AUX)) + return 1; + + if (!host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) && + !guest_cpuid_has(vcpu, X86_FEATURE_RDPID)) + return 1; + + /* + * Per Intel's SDM, bits 63:32 are reserved, but AMD's APM has + * incomplete and conflicting architectural behavior. Current + * AMD CPUs completely ignore bits 63:32, i.e. they aren't + * reserved and always read as zeros. Enforce Intel's reserved + * bits check if and only if the guest CPU is Intel, and clear + * the bits in all other cases. This ensures cross-vendor + * migration will provide consistent behavior for the guest. + */ + if (guest_cpuid_is_intel(vcpu) && (data >> 32) != 0) + return 1; + + data = (u32)data; + break; } msr.data = data; @@ -1651,6 +1705,18 @@ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ)) return KVM_MSR_RET_FILTERED; + switch (index) { + case MSR_TSC_AUX: + if (!kvm_is_supported_user_return_msr(MSR_TSC_AUX)) + return 1; + + if (!host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) && + !guest_cpuid_has(vcpu, X86_FEATURE_RDPID)) + return 1; + break; + } + msr.index = index; msr.host_initiated = host_initiated; @@ -3402,7 +3468,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_LASTBRANCHTOIP: case MSR_IA32_LASTINTFROMIP: case MSR_IA32_LASTINTTOIP: - case MSR_K8_SYSCFG: + case MSR_AMD64_SYSCFG: case MSR_K8_TSEG_ADDR: case MSR_K8_TSEG_MASK: case MSR_VM_HSAVE_PA: @@ -5468,14 +5534,18 @@ static void kvm_free_msr_filter(struct kvm_x86_msr_filter *msr_filter) static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter, struct kvm_msr_filter_range *user_range) { - struct msr_bitmap_range range; unsigned long *bitmap = NULL; size_t bitmap_size; - int r; if (!user_range->nmsrs) return 0; + if (user_range->flags & ~(KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE)) + return -EINVAL; + + if (!user_range->flags) + return -EINVAL; + bitmap_size = BITS_TO_LONGS(user_range->nmsrs) * sizeof(long); if (!bitmap_size || bitmap_size > KVM_MSR_FILTER_MAX_BITMAP_SIZE) return -EINVAL; @@ -5484,31 +5554,15 @@ static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter, if (IS_ERR(bitmap)) return PTR_ERR(bitmap); - range = (struct msr_bitmap_range) { + msr_filter->ranges[msr_filter->count] = (struct msr_bitmap_range) { .flags = user_range->flags, .base = user_range->base, .nmsrs = user_range->nmsrs, .bitmap = bitmap, }; - if (range.flags & ~(KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE)) { - r = -EINVAL; - goto err; - } - - if (!range.flags) { - r = -EINVAL; - goto err; - } - - /* Everything ok, add this range identifier. */ - msr_filter->ranges[msr_filter->count] = range; msr_filter->count++; - return 0; -err: - kfree(bitmap); - return r; } static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) @@ -5937,7 +5991,8 @@ static void kvm_init_msr_list(void) continue; break; case MSR_TSC_AUX: - if (!kvm_cpu_cap_has(X86_FEATURE_RDTSCP)) + if (!kvm_cpu_cap_has(X86_FEATURE_RDTSCP) && + !kvm_cpu_cap_has(X86_FEATURE_RDPID)) continue; break; case MSR_IA32_UMWAIT_CONTROL: @@ -8040,6 +8095,18 @@ static void pvclock_gtod_update_fn(struct work_struct *work) static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn); /* + * Indirection to move queue_work() out of the tk_core.seq write held + * region to prevent possible deadlocks against time accessors which + * are invoked with work related locks held. + */ +static void pvclock_irq_work_fn(struct irq_work *w) +{ + queue_work(system_long_wq, &pvclock_gtod_work); +} + +static DEFINE_IRQ_WORK(pvclock_irq_work, pvclock_irq_work_fn); + +/* * Notification about pvclock gtod data update. */ static int pvclock_gtod_notify(struct notifier_block *nb, unsigned long unused, @@ -8050,13 +8117,14 @@ static int pvclock_gtod_notify(struct notifier_block *nb, unsigned long unused, update_pvclock_gtod(tk); - /* disable master clock if host does not trust, or does not - * use, TSC based clocksource. + /* + * Disable master clock if host does not trust, or does not use, + * TSC based clocksource. Delegate queue_work() to irq_work as + * this is invoked with tk_core.seq write held. */ if (!gtod_is_based_on_tsc(gtod->clock.vclock_mode) && atomic_read(&kvm_guest_has_master_clock) != 0) - queue_work(system_long_wq, &pvclock_gtod_work); - + irq_work_queue(&pvclock_irq_work); return 0; } @@ -8118,6 +8186,7 @@ int kvm_arch_init(void *opaque) printk(KERN_ERR "kvm: failed to allocate percpu kvm_user_return_msrs\n"); goto out_free_x86_emulator_cache; } + kvm_nr_uret_msrs = 0; r = kvm_mmu_module_init(); if (r) @@ -8168,6 +8237,8 @@ void kvm_arch_exit(void) cpuhp_remove_state_nocalls(CPUHP_AP_X86_KVM_CLK_ONLINE); #ifdef CONFIG_X86_64 pvclock_gtod_unregister_notifier(&pvclock_gtod_notifier); + irq_work_sync(&pvclock_irq_work); + cancel_work_sync(&pvclock_gtod_work); #endif kvm_x86_ops.hardware_enable = NULL; kvm_mmu_module_exit(); diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index b93d6cd08a7f..121921b2927c 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -5,7 +5,7 @@ #include <xen/xen.h> #include <asm/fpu/internal.h> -#include <asm/sev-es.h> +#include <asm/sev.h> #include <asm/traps.h> #include <asm/kdebug.h> diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index 04aba7e80a36..a9639f663d25 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -529,7 +529,7 @@ void __init sme_enable(struct boot_params *bp) /* * No SME if Hypervisor bit is set. This check is here to * prevent a guest from trying to enable SME. For running as a - * KVM guest the MSR_K8_SYSCFG will be sufficient, but there + * KVM guest the MSR_AMD64_SYSCFG will be sufficient, but there * might be other hypervisors which emulate that MSR as non-zero * or even pass it through to the guest. * A malicious hypervisor can still trick a guest into this @@ -542,8 +542,8 @@ void __init sme_enable(struct boot_params *bp) return; /* For SME, check the SYSCFG MSR */ - msr = __rdmsr(MSR_K8_SYSCFG); - if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT)) + msr = __rdmsr(MSR_AMD64_SYSCFG); + if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT)) return; } else { /* SEV state cannot be controlled by a command line option */ diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c index ae744b6a0785..dd40d3fea74e 100644 --- a/arch/x86/pci/amd_bus.c +++ b/arch/x86/pci/amd_bus.c @@ -284,7 +284,7 @@ static int __init early_root_info_init(void) /* need to take out [4G, TOM2) for RAM*/ /* SYS_CFG */ - address = MSR_K8_SYSCFG; + address = MSR_AMD64_SYSCFG; rdmsrl(address, val); /* TOP_MEM2 is enabled? */ if (val & (1<<21)) { diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index df7b5477fc4f..7515e78ef898 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -47,7 +47,7 @@ #include <asm/realmode.h> #include <asm/time.h> #include <asm/pgalloc.h> -#include <asm/sev-es.h> +#include <asm/sev.h> /* * We allocate runtime services regions top-down, starting from -4G, i.e. diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 1be71ef5e4c4..2e1c1bec0f9e 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -9,7 +9,7 @@ #include <asm/realmode.h> #include <asm/tlbflush.h> #include <asm/crash.h> -#include <asm/sev-es.h> +#include <asm/sev.h> struct real_mode_header *real_mode_header; u32 *trampoline_cr4_features; diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S index 84c5d1b33d10..cc8391f86cdb 100644 --- a/arch/x86/realmode/rm/trampoline_64.S +++ b/arch/x86/realmode/rm/trampoline_64.S @@ -123,9 +123,9 @@ SYM_CODE_START(startup_32) */ btl $TH_FLAGS_SME_ACTIVE_BIT, pa_tr_flags jnc .Ldone - movl $MSR_K8_SYSCFG, %ecx + movl $MSR_AMD64_SYSCFG, %ecx rdmsr - bts $MSR_K8_SYSCFG_MEM_ENCRYPT_BIT, %eax + bts $MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT, %eax jc .Ldone /* diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 0270cd7ca165..acd1f881273e 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -372,9 +372,38 @@ struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync) return bic->bfqq[is_sync]; } +static void bfq_put_stable_ref(struct bfq_queue *bfqq); + void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync) { + /* + * If bfqq != NULL, then a non-stable queue merge between + * bic->bfqq and bfqq is happening here. This causes troubles + * in the following case: bic->bfqq has also been scheduled + * for a possible stable merge with bic->stable_merge_bfqq, + * and bic->stable_merge_bfqq == bfqq happens to + * hold. Troubles occur because bfqq may then undergo a split, + * thereby becoming eligible for a stable merge. Yet, if + * bic->stable_merge_bfqq points exactly to bfqq, then bfqq + * would be stably merged with itself. To avoid this anomaly, + * we cancel the stable merge if + * bic->stable_merge_bfqq == bfqq. + */ bic->bfqq[is_sync] = bfqq; + + if (bfqq && bic->stable_merge_bfqq == bfqq) { + /* + * Actually, these same instructions are executed also + * in bfq_setup_cooperator, in case of abort or actual + * execution of a stable merge. We could avoid + * repeating these instructions there too, but if we + * did so, we would nest even more complexity in this + * function. + */ + bfq_put_stable_ref(bic->stable_merge_bfqq); + + bic->stable_merge_bfqq = NULL; + } } struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic) @@ -2263,10 +2292,9 @@ static void bfq_remove_request(struct request_queue *q, } -static bool bfq_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio, +static bool bfq_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs) { - struct request_queue *q = hctx->queue; struct bfq_data *bfqd = q->elevator->elevator_data; struct request *free = NULL; /* @@ -2631,8 +2659,6 @@ static bool bfq_may_be_close_cooperator(struct bfq_queue *bfqq, static bool idling_boosts_thr_without_issues(struct bfq_data *bfqd, struct bfq_queue *bfqq); -static void bfq_put_stable_ref(struct bfq_queue *bfqq); - /* * Attempt to schedule a merge of bfqq with the currently in-service * queue or with a close queue among the scheduled queues. Return diff --git a/block/blk-iocost.c b/block/blk-iocost.c index e0c4baa01857..c2d6bc88d3f1 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -1069,7 +1069,17 @@ static void __propagate_weights(struct ioc_gq *iocg, u32 active, u32 inuse, lockdep_assert_held(&ioc->lock); - inuse = clamp_t(u32, inuse, 1, active); + /* + * For an active leaf node, its inuse shouldn't be zero or exceed + * @active. An active internal node's inuse is solely determined by the + * inuse to active ratio of its children regardless of @inuse. + */ + if (list_empty(&iocg->active_list) && iocg->child_active_sum) { + inuse = DIV64_U64_ROUND_UP(active * iocg->child_inuse_sum, + iocg->child_active_sum); + } else { + inuse = clamp_t(u32, inuse, 1, active); + } iocg->last_inuse = iocg->inuse; if (save) @@ -1086,7 +1096,7 @@ static void __propagate_weights(struct ioc_gq *iocg, u32 active, u32 inuse, /* update the level sums */ parent->child_active_sum += (s32)(active - child->active); parent->child_inuse_sum += (s32)(inuse - child->inuse); - /* apply the udpates */ + /* apply the updates */ child->active = active; child->inuse = inuse; diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 42a365b1b9c0..996a4b2f73aa 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -358,14 +358,16 @@ bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs) { struct elevator_queue *e = q->elevator; - struct blk_mq_ctx *ctx = blk_mq_get_ctx(q); - struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, bio->bi_opf, ctx); + struct blk_mq_ctx *ctx; + struct blk_mq_hw_ctx *hctx; bool ret = false; enum hctx_type type; if (e && e->type->ops.bio_merge) - return e->type->ops.bio_merge(hctx, bio, nr_segs); + return e->type->ops.bio_merge(q, bio, nr_segs); + ctx = blk_mq_get_ctx(q); + hctx = blk_mq_map_queue(q, bio->bi_opf, ctx); type = hctx->type; if (!(hctx->flags & BLK_MQ_F_SHOULD_MERGE) || list_empty_careful(&ctx->rq_lists[type])) diff --git a/block/blk-mq.c b/block/blk-mq.c index 466676bc2f0b..c86c01bfecdb 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2232,8 +2232,9 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio) /* Bypass scheduler for flush requests */ blk_insert_flush(rq); blk_mq_run_hw_queue(data.hctx, true); - } else if (plug && (q->nr_hw_queues == 1 || q->mq_ops->commit_rqs || - !blk_queue_nonrot(q))) { + } else if (plug && (q->nr_hw_queues == 1 || + blk_mq_is_sbitmap_shared(rq->mq_hctx->flags) || + q->mq_ops->commit_rqs || !blk_queue_nonrot(q))) { /* * Use plugging if we have a ->commit_rqs() hook as well, as * we know the driver uses bd->last in a smart fashion. @@ -3285,10 +3286,12 @@ EXPORT_SYMBOL(blk_mq_init_allocated_queue); /* tags can _not_ be used after returning from blk_mq_exit_queue */ void blk_mq_exit_queue(struct request_queue *q) { - struct blk_mq_tag_set *set = q->tag_set; + struct blk_mq_tag_set *set = q->tag_set; - blk_mq_del_queue_tag_set(q); + /* Checks hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED. */ blk_mq_exit_hw_queues(q, set, set->nr_hw_queues); + /* May clear BLK_MQ_F_TAG_QUEUE_SHARED in hctx->flags. */ + blk_mq_del_queue_tag_set(q); } static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set) diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c index 8969e122f081..81e3279ecd57 100644 --- a/block/kyber-iosched.c +++ b/block/kyber-iosched.c @@ -561,11 +561,12 @@ static void kyber_limit_depth(unsigned int op, struct blk_mq_alloc_data *data) } } -static bool kyber_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio, +static bool kyber_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs) { + struct blk_mq_ctx *ctx = blk_mq_get_ctx(q); + struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, bio->bi_opf, ctx); struct kyber_hctx_data *khd = hctx->sched_data; - struct blk_mq_ctx *ctx = blk_mq_get_ctx(hctx->queue); struct kyber_ctx_queue *kcq = &khd->kcqs[ctx->index_hw[hctx->type]]; unsigned int sched_domain = kyber_sched_domain(bio->bi_opf); struct list_head *rq_list = &kcq->rq_list[sched_domain]; diff --git a/block/mq-deadline.c b/block/mq-deadline.c index 04aded71ead2..8eea2cbf2bf4 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -461,10 +461,9 @@ static int dd_request_merge(struct request_queue *q, struct request **rq, return ELEVATOR_NO_MERGE; } -static bool dd_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio, +static bool dd_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs) { - struct request_queue *q = hctx->queue; struct deadline_data *dd = q->elevator->elevator_data; struct request *free = NULL; bool ret; diff --git a/block/partitions/efi.c b/block/partitions/efi.c index b64bfdd4326c..e2716792ecc1 100644 --- a/block/partitions/efi.c +++ b/block/partitions/efi.c @@ -682,7 +682,7 @@ static void utf16_le_to_7bit(const __le16 *in, unsigned int size, u8 *out) } /** - * efi_partition(struct parsed_partitions *state) + * efi_partition - scan for GPT partitions * @state: disk parsed partitions * * Description: called from check.c, if the disk contains GPT diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index 16c0fe8a72a7..d260bc1f3e6e 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -1313,6 +1313,7 @@ int acpi_dev_pm_attach(struct device *dev, bool power_on) {"PNP0C0B", }, /* Generic ACPI fan */ {"INT3404", }, /* Fan */ {"INTC1044", }, /* Fan for Tiger Lake generation */ + {"INTC1048", }, /* Fan for Alder Lake generation */ {} }; struct acpi_device *adev = ACPI_COMPANION(dev); diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index b852cff80287..f973bbe90e5e 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -142,6 +142,7 @@ int acpi_device_sleep_wake(struct acpi_device *dev, int acpi_power_get_inferred_state(struct acpi_device *device, int *state); int acpi_power_on_resources(struct acpi_device *device, int state); int acpi_power_transition(struct acpi_device *device, int state); +void acpi_turn_off_unused_power_resources(void); /* -------------------------------------------------------------------------- Device Power Management diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 958aaac869e8..23d9a09d7060 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -686,6 +686,13 @@ int nfit_spa_type(struct acpi_nfit_system_address *spa) return -1; } +static size_t sizeof_spa(struct acpi_nfit_system_address *spa) +{ + if (spa->flags & ACPI_NFIT_LOCATION_COOKIE_VALID) + return sizeof(*spa); + return sizeof(*spa) - 8; +} + static bool add_spa(struct acpi_nfit_desc *acpi_desc, struct nfit_table_prev *prev, struct acpi_nfit_system_address *spa) @@ -693,22 +700,22 @@ static bool add_spa(struct acpi_nfit_desc *acpi_desc, struct device *dev = acpi_desc->dev; struct nfit_spa *nfit_spa; - if (spa->header.length != sizeof(*spa)) + if (spa->header.length != sizeof_spa(spa)) return false; list_for_each_entry(nfit_spa, &prev->spas, list) { - if (memcmp(nfit_spa->spa, spa, sizeof(*spa)) == 0) { + if (memcmp(nfit_spa->spa, spa, sizeof_spa(spa)) == 0) { list_move_tail(&nfit_spa->list, &acpi_desc->spas); return true; } } - nfit_spa = devm_kzalloc(dev, sizeof(*nfit_spa) + sizeof(*spa), + nfit_spa = devm_kzalloc(dev, sizeof(*nfit_spa) + sizeof_spa(spa), GFP_KERNEL); if (!nfit_spa) return false; INIT_LIST_HEAD(&nfit_spa->list); - memcpy(nfit_spa->spa, spa, sizeof(*spa)); + memcpy(nfit_spa->spa, spa, sizeof_spa(spa)); list_add_tail(&nfit_spa->list, &acpi_desc->spas); dev_dbg(dev, "spa index: %d type: %s\n", spa->range_index, diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c index 32974b575e46..56102eaaa2da 100644 --- a/drivers/acpi/power.c +++ b/drivers/acpi/power.c @@ -995,6 +995,7 @@ void acpi_resume_power_resources(void) mutex_unlock(&power_resource_list_lock); } +#endif void acpi_turn_off_unused_power_resources(void) { @@ -1015,4 +1016,3 @@ void acpi_turn_off_unused_power_resources(void) mutex_unlock(&power_resource_list_lock); } -#endif diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index a22778e880c2..453eff8ec8c3 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -700,6 +700,7 @@ int acpi_device_add(struct acpi_device *device, result = acpi_device_set_name(device, acpi_device_bus_id); if (result) { + kfree_const(acpi_device_bus_id->bus_id); kfree(acpi_device_bus_id); goto err_unlock; } @@ -2359,6 +2360,8 @@ int __init acpi_scan_init(void) } } + acpi_turn_off_unused_power_resources(); + acpi_scan_initialized = true; out: diff --git a/drivers/acpi/sleep.h b/drivers/acpi/sleep.h index 1856f76ac83f..7fe41ee489d6 100644 --- a/drivers/acpi/sleep.h +++ b/drivers/acpi/sleep.h @@ -8,7 +8,6 @@ extern struct list_head acpi_wakeup_device_list; extern struct mutex acpi_device_lock; extern void acpi_resume_power_resources(void); -extern void acpi_turn_off_unused_power_resources(void); static inline acpi_status acpi_set_waking_vector(u32 wakeup_address) { diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 1fc1a992f90c..b570848d23e0 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -1637,6 +1637,7 @@ void pm_runtime_init(struct device *dev) dev->power.request_pending = false; dev->power.request = RPM_REQ_NONE; dev->power.deferred_resume = false; + dev->power.needs_force_resume = 0; INIT_WORK(&dev->power.work, pm_runtime_work); dev->power.timer_expires = 0; @@ -1804,10 +1805,12 @@ int pm_runtime_force_suspend(struct device *dev) * its parent, but set its status to RPM_SUSPENDED anyway in case this * function will be called again for it in the meantime. */ - if (pm_runtime_need_not_resume(dev)) + if (pm_runtime_need_not_resume(dev)) { pm_runtime_set_suspended(dev); - else + } else { __update_runtime_status(dev, RPM_SUSPENDED); + dev->power.needs_force_resume = 1; + } return 0; @@ -1834,7 +1837,7 @@ int pm_runtime_force_resume(struct device *dev) int (*callback)(struct device *); int ret = 0; - if (!pm_runtime_status_suspended(dev) || pm_runtime_need_not_resume(dev)) + if (!pm_runtime_status_suspended(dev) || !dev->power.needs_force_resume) goto out; /* @@ -1853,6 +1856,7 @@ int pm_runtime_force_resume(struct device *dev) pm_runtime_mark_last_busy(dev); out: + dev->power.needs_force_resume = 0; pm_runtime_enable(dev); return ret; } diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 4ff71b579cfc..45d2c28c8fc8 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1980,7 +1980,8 @@ static void nbd_disconnect_and_put(struct nbd_device *nbd) * config ref and try to destroy the workqueue from inside the work * queue. */ - flush_workqueue(nbd->recv_workq); + if (nbd->recv_workq) + flush_workqueue(nbd->recv_workq); if (test_and_clear_bit(NBD_RT_HAS_CONFIG_REF, &nbd->config->runtime_flags)) nbd_config_put(nbd); @@ -2014,12 +2015,11 @@ static int nbd_genl_disconnect(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } mutex_unlock(&nbd_index_mutex); - if (!refcount_inc_not_zero(&nbd->config_refs)) { - nbd_put(nbd); - return 0; - } + if (!refcount_inc_not_zero(&nbd->config_refs)) + goto put_nbd; nbd_disconnect_and_put(nbd); nbd_config_put(nbd); +put_nbd: nbd_put(nbd); return 0; } diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index eff1f12d981a..c84d23951219 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -656,6 +656,7 @@ int tpm2_get_cc_attrs_tbl(struct tpm_chip *chip) if (nr_commands != be32_to_cpup((__be32 *)&buf.data[TPM_HEADER_SIZE + 5])) { + rc = -EFAULT; tpm_buf_destroy(&buf); goto out; } diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index a2e0395cbe61..55b9d3965ae1 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -709,16 +709,14 @@ static int tpm_tis_gen_interrupt(struct tpm_chip *chip) cap_t cap; int ret; - /* TPM 2.0 */ - if (chip->flags & TPM_CHIP_FLAG_TPM2) - return tpm2_get_tpm_pt(chip, 0x100, &cap2, desc); - - /* TPM 1.2 */ ret = request_locality(chip, 0); if (ret < 0) return ret; - ret = tpm1_getcap(chip, TPM_CAP_PROP_TIS_TIMEOUT, &cap, desc, 0); + if (chip->flags & TPM_CHIP_FLAG_TPM2) + ret = tpm2_get_tpm_pt(chip, 0x100, &cap2, desc); + else + ret = tpm1_getcap(chip, TPM_CAP_PROP_TIS_TIMEOUT, &cap, desc, 0); release_locality(chip, 0); @@ -1127,12 +1125,20 @@ int tpm_tis_resume(struct device *dev) if (ret) return ret; - /* TPM 1.2 requires self-test on resume. This function actually returns + /* + * TPM 1.2 requires self-test on resume. This function actually returns * an error code but for unknown reason it isn't handled. */ - if (!(chip->flags & TPM_CHIP_FLAG_TPM2)) + if (!(chip->flags & TPM_CHIP_FLAG_TPM2)) { + ret = request_locality(chip, 0); + if (ret < 0) + return ret; + tpm1_do_selftest(chip); + release_locality(chip, 0); + } + return 0; } EXPORT_SYMBOL_GPL(tpm_tis_resume); diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index d1bbc16fba4b..7e7450453714 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -646,7 +646,11 @@ static u64 get_max_boost_ratio(unsigned int cpu) return 0; } - highest_perf = perf_caps.highest_perf; + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + highest_perf = amd_get_highest_perf(); + else + highest_perf = perf_caps.highest_perf; + nominal_perf = perf_caps.nominal_perf; if (!highest_perf || !nominal_perf) { diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index f0401064d7aa..0e69dffd5a76 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -3033,6 +3033,14 @@ static const struct x86_cpu_id hwp_support_ids[] __initconst = { {} }; +static bool intel_pstate_hwp_is_enabled(void) +{ + u64 value; + + rdmsrl(MSR_PM_ENABLE, value); + return !!(value & 0x1); +} + static int __init intel_pstate_init(void) { const struct x86_cpu_id *id; @@ -3051,8 +3059,12 @@ static int __init intel_pstate_init(void) * Avoid enabling HWP for processors without EPP support, * because that means incomplete HWP implementation which is a * corner case and supporting it is generally problematic. + * + * If HWP is enabled already, though, there is no choice but to + * deal with it. */ - if (!no_hwp && boot_cpu_has(X86_FEATURE_HWP_EPP)) { + if ((!no_hwp && boot_cpu_has(X86_FEATURE_HWP_EPP)) || + intel_pstate_hwp_is_enabled()) { hwp_active++; hwp_mode_bdw = id->driver_data; intel_pstate.attr = hwp_cpufreq_attrs; diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 9fa4dfc6ebee..f0d8f60acee1 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -3083,7 +3083,7 @@ static void read_mc_regs(struct amd64_pvt *pvt) edac_dbg(0, " TOP_MEM: 0x%016llx\n", pvt->top_mem); /* Check first whether TOP_MEM2 is enabled: */ - rdmsrl(MSR_K8_SYSCFG, msr_val); + rdmsrl(MSR_AMD64_SYSCFG, msr_val); if (msr_val & BIT(21)) { rdmsrl(MSR_K8_TOP_MEM2, pvt->top_mem2); edac_dbg(0, " TOP_MEM2: 0x%016llx\n", pvt->top_mem2); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index dc3a69296321..264176a01e16 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1006,6 +1006,7 @@ struct amdgpu_device { struct amdgpu_df df; struct amdgpu_ip_block ip_blocks[AMDGPU_MAX_IP_NUM]; + uint32_t harvest_ip_mask; int num_ip_blocks; struct mutex mn_lock; DECLARE_HASHTABLE(mn_hash, 7); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 7d3b54615147..8b2a37bf2adf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1683,6 +1683,19 @@ int amdgpu_device_ip_block_add(struct amdgpu_device *adev, if (!ip_block_version) return -EINVAL; + switch (ip_block_version->type) { + case AMD_IP_BLOCK_TYPE_VCN: + if (adev->harvest_ip_mask & AMD_HARVEST_IP_VCN_MASK) + return 0; + break; + case AMD_IP_BLOCK_TYPE_JPEG: + if (adev->harvest_ip_mask & AMD_HARVEST_IP_JPEG_MASK) + return 0; + break; + default: + break; + } + DRM_INFO("add ip block number %d <%s>\n", adev->num_ip_blocks, ip_block_version->funcs->name); @@ -3111,7 +3124,6 @@ bool amdgpu_device_has_dc_support(struct amdgpu_device *adev) return amdgpu_device_asic_has_dc_support(adev->asic_type); } - static void amdgpu_device_xgmi_reset_func(struct work_struct *__work) { struct amdgpu_device *adev = @@ -3276,6 +3288,7 @@ int amdgpu_device_init(struct amdgpu_device *adev, adev->vm_manager.vm_pte_funcs = NULL; adev->vm_manager.vm_pte_num_scheds = 0; adev->gmc.gmc_funcs = NULL; + adev->harvest_ip_mask = 0x0; adev->fence_context = dma_fence_context_alloc(AMDGPU_MAX_RINGS); bitmap_zero(adev->gfx.pipe_reserve_bitmap, AMDGPU_MAX_COMPUTE_QUEUES); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index b2dbcb4df020..e1b6f5891759 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -373,6 +373,34 @@ int amdgpu_discovery_get_ip_version(struct amdgpu_device *adev, int hw_id, return -EINVAL; } +void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev) +{ + struct binary_header *bhdr; + struct harvest_table *harvest_info; + int i; + + bhdr = (struct binary_header *)adev->mman.discovery_bin; + harvest_info = (struct harvest_table *)(adev->mman.discovery_bin + + le16_to_cpu(bhdr->table_list[HARVEST_INFO].offset)); + + for (i = 0; i < 32; i++) { + if (le32_to_cpu(harvest_info->list[i].hw_id) == 0) + break; + + switch (le32_to_cpu(harvest_info->list[i].hw_id)) { + case VCN_HWID: + adev->harvest_ip_mask |= AMD_HARVEST_IP_VCN_MASK; + adev->harvest_ip_mask |= AMD_HARVEST_IP_JPEG_MASK; + break; + case DMU_HWID: + adev->harvest_ip_mask |= AMD_HARVEST_IP_DMU_MASK; + break; + default: + break; + } + } +} + int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev) { struct binary_header *bhdr; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h index 8f6183801cb3..1b1ae21b1037 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h @@ -29,6 +29,7 @@ void amdgpu_discovery_fini(struct amdgpu_device *adev); int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev); +void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev); int amdgpu_discovery_get_ip_version(struct amdgpu_device *adev, int hw_id, int *major, int *minor, int *revision); int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index d54af7f8801b..d290ca0b06da 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -623,6 +623,16 @@ static const struct amdgpu_ip_block_version nv_common_ip_block = .funcs = &nv_common_ip_funcs, }; +static bool nv_is_headless_sku(struct pci_dev *pdev) +{ + if ((pdev->device == 0x731E && + (pdev->revision == 0xC6 || pdev->revision == 0xC7)) || + (pdev->device == 0x7340 && pdev->revision == 0xC9) || + (pdev->device == 0x7360 && pdev->revision == 0xC7)) + return true; + return false; +} + static int nv_reg_base_init(struct amdgpu_device *adev) { int r; @@ -635,6 +645,12 @@ static int nv_reg_base_init(struct amdgpu_device *adev) goto legacy_init; } + amdgpu_discovery_harvest_ip(adev); + if (nv_is_headless_sku(adev->pdev)) { + adev->harvest_ip_mask |= AMD_HARVEST_IP_VCN_MASK; + adev->harvest_ip_mask |= AMD_HARVEST_IP_JPEG_MASK; + } + return 0; } @@ -671,16 +687,6 @@ void nv_set_virt_ops(struct amdgpu_device *adev) adev->virt.ops = &xgpu_nv_virt_ops; } -static bool nv_is_headless_sku(struct pci_dev *pdev) -{ - if ((pdev->device == 0x731E && - (pdev->revision == 0xC6 || pdev->revision == 0xC7)) || - (pdev->device == 0x7340 && pdev->revision == 0xC9) || - (pdev->device == 0x7360 && pdev->revision == 0xC7)) - return true; - return false; -} - int nv_set_ip_blocks(struct amdgpu_device *adev) { int r; @@ -728,8 +734,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev) if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT && !amdgpu_sriov_vf(adev)) amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block); - if (!nv_is_headless_sku(adev->pdev)) - amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block); + amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block); amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block); if (adev->enable_mes) amdgpu_device_ip_block_add(adev, &mes_v10_1_ip_block); @@ -752,8 +757,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev) if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT && !amdgpu_sriov_vf(adev)) amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block); - if (!nv_is_headless_sku(adev->pdev)) - amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block); + amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block); if (!amdgpu_sriov_vf(adev)) amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block); break; @@ -777,7 +781,6 @@ int nv_set_ip_blocks(struct amdgpu_device *adev) amdgpu_device_ip_block_add(adev, &vcn_v3_0_ip_block); if (!amdgpu_sriov_vf(adev)) amdgpu_device_ip_block_add(adev, &jpeg_v3_0_ip_block); - if (adev->enable_mes) amdgpu_device_ip_block_add(adev, &mes_v10_1_ip_block); break; @@ -1149,6 +1152,11 @@ static int nv_common_early_init(void *handle) return -EINVAL; } + if (adev->harvest_ip_mask & AMD_HARVEST_IP_VCN_MASK) + adev->pg_flags &= ~(AMD_PG_SUPPORT_VCN | + AMD_PG_SUPPORT_VCN_DPG | + AMD_PG_SUPPORT_JPEG); + if (amdgpu_sriov_vf(adev)) { amdgpu_virt_init_setting(adev); xgpu_nv_mailbox_set_irq_funcs(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index d80e12b80c7e..8e1b9a40839f 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -1401,7 +1401,8 @@ static int soc15_common_early_init(void *handle) AMD_CG_SUPPORT_MC_MGCG | AMD_CG_SUPPORT_MC_LS | AMD_CG_SUPPORT_SDMA_MGCG | - AMD_CG_SUPPORT_SDMA_LS; + AMD_CG_SUPPORT_SDMA_LS | + AMD_CG_SUPPORT_VCN_MGCG; adev->pg_flags = AMD_PG_SUPPORT_SDMA | AMD_PG_SUPPORT_MMHUB | diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c index 51a773a37a35..0c1beefa3e49 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c @@ -1119,10 +1119,10 @@ static int vcn_v1_0_stop_spg_mode(struct amdgpu_device *adev) UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK; SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_LMI_STATUS, tmp, tmp); - /* put VCPU into reset */ - WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_SOFT_RESET), - UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK, - ~UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK); + /* stall UMC channel */ + WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_CTRL2), + UVD_LMI_CTRL2__STALL_ARB_UMC_MASK, + ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK); tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK | UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK; @@ -1141,6 +1141,11 @@ static int vcn_v1_0_stop_spg_mode(struct amdgpu_device *adev) UVD_SOFT_RESET__LMI_SOFT_RESET_MASK, ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK); + /* put VCPU into reset */ + WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_SOFT_RESET), + UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK, + ~UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK); + WREG32_SOC15(UVD, 0, mmUVD_STATUS, 0); vcn_v1_0_enable_clock_gating(adev); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c index 616f5b1ea3a8..666796a0067c 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c @@ -650,6 +650,7 @@ struct hdcp_workqueue *hdcp_create_workqueue(struct amdgpu_device *adev, struct /* File created at /sys/class/drm/card0/device/hdcp_srm*/ hdcp_work[0].attr = data_attr; + sysfs_bin_attr_init(&hdcp_work[0].attr); if (sysfs_create_bin_file(&adev->dev->kobj, &hdcp_work[0].attr)) DRM_WARN("Failed to create device file hdcp_srm"); diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h index 43ed6291b2b8..9ab706cd07ff 100644 --- a/drivers/gpu/drm/amd/include/amd_shared.h +++ b/drivers/gpu/drm/amd/include/amd_shared.h @@ -216,6 +216,12 @@ enum PP_FEATURE_MASK { PP_GFX_DCS_MASK = 0x80000, }; +enum amd_harvest_ip_mask { + AMD_HARVEST_IP_VCN_MASK = 0x1, + AMD_HARVEST_IP_JPEG_MASK = 0x2, + AMD_HARVEST_IP_DMU_MASK = 0x4, +}; + enum DC_FEATURE_MASK { DC_FBC_MASK = 0x1, DC_MULTI_MON_PP_MCLK_SWITCH_MASK = 0x2, diff --git a/drivers/gpu/drm/amd/pm/powerplay/si_dpm.c b/drivers/gpu/drm/amd/pm/powerplay/si_dpm.c index 26a5321e621b..15c0b8af376f 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/si_dpm.c +++ b/drivers/gpu/drm/amd/pm/powerplay/si_dpm.c @@ -4817,70 +4817,70 @@ static int si_populate_smc_initial_state(struct amdgpu_device *adev, u32 reg; int ret; - table->initialState.levels[0].mclk.vDLL_CNTL = + table->initialState.level.mclk.vDLL_CNTL = cpu_to_be32(si_pi->clock_registers.dll_cntl); - table->initialState.levels[0].mclk.vMCLK_PWRMGT_CNTL = + table->initialState.level.mclk.vMCLK_PWRMGT_CNTL = cpu_to_be32(si_pi->clock_registers.mclk_pwrmgt_cntl); - table->initialState.levels[0].mclk.vMPLL_AD_FUNC_CNTL = + table->initialState.level.mclk.vMPLL_AD_FUNC_CNTL = cpu_to_be32(si_pi->clock_registers.mpll_ad_func_cntl); - table->initialState.levels[0].mclk.vMPLL_DQ_FUNC_CNTL = + table->initialState.level.mclk.vMPLL_DQ_FUNC_CNTL = cpu_to_be32(si_pi->clock_registers.mpll_dq_func_cntl); - table->initialState.levels[0].mclk.vMPLL_FUNC_CNTL = + table->initialState.level.mclk.vMPLL_FUNC_CNTL = cpu_to_be32(si_pi->clock_registers.mpll_func_cntl); - table->initialState.levels[0].mclk.vMPLL_FUNC_CNTL_1 = + table->initialState.level.mclk.vMPLL_FUNC_CNTL_1 = cpu_to_be32(si_pi->clock_registers.mpll_func_cntl_1); - table->initialState.levels[0].mclk.vMPLL_FUNC_CNTL_2 = + table->initialState.level.mclk.vMPLL_FUNC_CNTL_2 = cpu_to_be32(si_pi->clock_registers.mpll_func_cntl_2); - table->initialState.levels[0].mclk.vMPLL_SS = + table->initialState.level.mclk.vMPLL_SS = cpu_to_be32(si_pi->clock_registers.mpll_ss1); - table->initialState.levels[0].mclk.vMPLL_SS2 = + table->initialState.level.mclk.vMPLL_SS2 = cpu_to_be32(si_pi->clock_registers.mpll_ss2); - table->initialState.levels[0].mclk.mclk_value = + table->initialState.level.mclk.mclk_value = cpu_to_be32(initial_state->performance_levels[0].mclk); - table->initialState.levels[0].sclk.vCG_SPLL_FUNC_CNTL = + table->initialState.level.sclk.vCG_SPLL_FUNC_CNTL = cpu_to_be32(si_pi->clock_registers.cg_spll_func_cntl); - table->initialState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_2 = + table->initialState.level.sclk.vCG_SPLL_FUNC_CNTL_2 = cpu_to_be32(si_pi->clock_registers.cg_spll_func_cntl_2); - table->initialState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_3 = + table->initialState.level.sclk.vCG_SPLL_FUNC_CNTL_3 = cpu_to_be32(si_pi->clock_registers.cg_spll_func_cntl_3); - table->initialState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_4 = + table->initialState.level.sclk.vCG_SPLL_FUNC_CNTL_4 = cpu_to_be32(si_pi->clock_registers.cg_spll_func_cntl_4); - table->initialState.levels[0].sclk.vCG_SPLL_SPREAD_SPECTRUM = + table->initialState.level.sclk.vCG_SPLL_SPREAD_SPECTRUM = cpu_to_be32(si_pi->clock_registers.cg_spll_spread_spectrum); - table->initialState.levels[0].sclk.vCG_SPLL_SPREAD_SPECTRUM_2 = + table->initialState.level.sclk.vCG_SPLL_SPREAD_SPECTRUM_2 = cpu_to_be32(si_pi->clock_registers.cg_spll_spread_spectrum_2); - table->initialState.levels[0].sclk.sclk_value = + table->initialState.level.sclk.sclk_value = cpu_to_be32(initial_state->performance_levels[0].sclk); - table->initialState.levels[0].arbRefreshState = + table->initialState.level.arbRefreshState = SISLANDS_INITIAL_STATE_ARB_INDEX; - table->initialState.levels[0].ACIndex = 0; + table->initialState.level.ACIndex = 0; ret = si_populate_voltage_value(adev, &eg_pi->vddc_voltage_table, initial_state->performance_levels[0].vddc, - &table->initialState.levels[0].vddc); + &table->initialState.level.vddc); if (!ret) { u16 std_vddc; ret = si_get_std_voltage_value(adev, - &table->initialState.levels[0].vddc, + &table->initialState.level.vddc, &std_vddc); if (!ret) si_populate_std_voltage_value(adev, std_vddc, - table->initialState.levels[0].vddc.index, - &table->initialState.levels[0].std_vddc); + table->initialState.level.vddc.index, + &table->initialState.level.std_vddc); } if (eg_pi->vddci_control) si_populate_voltage_value(adev, &eg_pi->vddci_voltage_table, initial_state->performance_levels[0].vddci, - &table->initialState.levels[0].vddci); + &table->initialState.level.vddci); if (si_pi->vddc_phase_shed_control) si_populate_phase_shedding_value(adev, @@ -4888,41 +4888,41 @@ static int si_populate_smc_initial_state(struct amdgpu_device *adev, initial_state->performance_levels[0].vddc, initial_state->performance_levels[0].sclk, initial_state->performance_levels[0].mclk, - &table->initialState.levels[0].vddc); + &table->initialState.level.vddc); - si_populate_initial_mvdd_value(adev, &table->initialState.levels[0].mvdd); + si_populate_initial_mvdd_value(adev, &table->initialState.level.mvdd); reg = CG_R(0xffff) | CG_L(0); - table->initialState.levels[0].aT = cpu_to_be32(reg); - table->initialState.levels[0].bSP = cpu_to_be32(pi->dsp); - table->initialState.levels[0].gen2PCIE = (u8)si_pi->boot_pcie_gen; + table->initialState.level.aT = cpu_to_be32(reg); + table->initialState.level.bSP = cpu_to_be32(pi->dsp); + table->initialState.level.gen2PCIE = (u8)si_pi->boot_pcie_gen; if (adev->gmc.vram_type == AMDGPU_VRAM_TYPE_GDDR5) { - table->initialState.levels[0].strobeMode = + table->initialState.level.strobeMode = si_get_strobe_mode_settings(adev, initial_state->performance_levels[0].mclk); if (initial_state->performance_levels[0].mclk > pi->mclk_edc_enable_threshold) - table->initialState.levels[0].mcFlags = SISLANDS_SMC_MC_EDC_RD_FLAG | SISLANDS_SMC_MC_EDC_WR_FLAG; + table->initialState.level.mcFlags = SISLANDS_SMC_MC_EDC_RD_FLAG | SISLANDS_SMC_MC_EDC_WR_FLAG; else - table->initialState.levels[0].mcFlags = 0; + table->initialState.level.mcFlags = 0; } table->initialState.levelCount = 1; table->initialState.flags |= PPSMC_SWSTATE_FLAG_DC; - table->initialState.levels[0].dpm2.MaxPS = 0; - table->initialState.levels[0].dpm2.NearTDPDec = 0; - table->initialState.levels[0].dpm2.AboveSafeInc = 0; - table->initialState.levels[0].dpm2.BelowSafeInc = 0; - table->initialState.levels[0].dpm2.PwrEfficiencyRatio = 0; + table->initialState.level.dpm2.MaxPS = 0; + table->initialState.level.dpm2.NearTDPDec = 0; + table->initialState.level.dpm2.AboveSafeInc = 0; + table->initialState.level.dpm2.BelowSafeInc = 0; + table->initialState.level.dpm2.PwrEfficiencyRatio = 0; reg = MIN_POWER_MASK | MAX_POWER_MASK; - table->initialState.levels[0].SQPowerThrottle = cpu_to_be32(reg); + table->initialState.level.SQPowerThrottle = cpu_to_be32(reg); reg = MAX_POWER_DELTA_MASK | STI_SIZE_MASK | LTI_RATIO_MASK; - table->initialState.levels[0].SQPowerThrottle_2 = cpu_to_be32(reg); + table->initialState.level.SQPowerThrottle_2 = cpu_to_be32(reg); return 0; } @@ -4953,18 +4953,18 @@ static int si_populate_smc_acpi_state(struct amdgpu_device *adev, if (pi->acpi_vddc) { ret = si_populate_voltage_value(adev, &eg_pi->vddc_voltage_table, - pi->acpi_vddc, &table->ACPIState.levels[0].vddc); + pi->acpi_vddc, &table->ACPIState.level.vddc); if (!ret) { u16 std_vddc; ret = si_get_std_voltage_value(adev, - &table->ACPIState.levels[0].vddc, &std_vddc); + &table->ACPIState.level.vddc, &std_vddc); if (!ret) si_populate_std_voltage_value(adev, std_vddc, - table->ACPIState.levels[0].vddc.index, - &table->ACPIState.levels[0].std_vddc); + table->ACPIState.level.vddc.index, + &table->ACPIState.level.std_vddc); } - table->ACPIState.levels[0].gen2PCIE = si_pi->acpi_pcie_gen; + table->ACPIState.level.gen2PCIE = si_pi->acpi_pcie_gen; if (si_pi->vddc_phase_shed_control) { si_populate_phase_shedding_value(adev, @@ -4972,23 +4972,23 @@ static int si_populate_smc_acpi_state(struct amdgpu_device *adev, pi->acpi_vddc, 0, 0, - &table->ACPIState.levels[0].vddc); + &table->ACPIState.level.vddc); } } else { ret = si_populate_voltage_value(adev, &eg_pi->vddc_voltage_table, - pi->min_vddc_in_table, &table->ACPIState.levels[0].vddc); + pi->min_vddc_in_table, &table->ACPIState.level.vddc); if (!ret) { u16 std_vddc; ret = si_get_std_voltage_value(adev, - &table->ACPIState.levels[0].vddc, &std_vddc); + &table->ACPIState.level.vddc, &std_vddc); if (!ret) si_populate_std_voltage_value(adev, std_vddc, - table->ACPIState.levels[0].vddc.index, - &table->ACPIState.levels[0].std_vddc); + table->ACPIState.level.vddc.index, + &table->ACPIState.level.std_vddc); } - table->ACPIState.levels[0].gen2PCIE = + table->ACPIState.level.gen2PCIE = (u8)amdgpu_get_pcie_gen_support(adev, si_pi->sys_pcie_mask, si_pi->boot_pcie_gen, @@ -5000,14 +5000,14 @@ static int si_populate_smc_acpi_state(struct amdgpu_device *adev, pi->min_vddc_in_table, 0, 0, - &table->ACPIState.levels[0].vddc); + &table->ACPIState.level.vddc); } if (pi->acpi_vddc) { if (eg_pi->acpi_vddci) si_populate_voltage_value(adev, &eg_pi->vddci_voltage_table, eg_pi->acpi_vddci, - &table->ACPIState.levels[0].vddci); + &table->ACPIState.level.vddci); } mclk_pwrmgt_cntl |= MRDCK0_RESET | MRDCK1_RESET; @@ -5018,59 +5018,59 @@ static int si_populate_smc_acpi_state(struct amdgpu_device *adev, spll_func_cntl_2 &= ~SCLK_MUX_SEL_MASK; spll_func_cntl_2 |= SCLK_MUX_SEL(4); - table->ACPIState.levels[0].mclk.vDLL_CNTL = + table->ACPIState.level.mclk.vDLL_CNTL = cpu_to_be32(dll_cntl); - table->ACPIState.levels[0].mclk.vMCLK_PWRMGT_CNTL = + table->ACPIState.level.mclk.vMCLK_PWRMGT_CNTL = cpu_to_be32(mclk_pwrmgt_cntl); - table->ACPIState.levels[0].mclk.vMPLL_AD_FUNC_CNTL = + table->ACPIState.level.mclk.vMPLL_AD_FUNC_CNTL = cpu_to_be32(mpll_ad_func_cntl); - table->ACPIState.levels[0].mclk.vMPLL_DQ_FUNC_CNTL = + table->ACPIState.level.mclk.vMPLL_DQ_FUNC_CNTL = cpu_to_be32(mpll_dq_func_cntl); - table->ACPIState.levels[0].mclk.vMPLL_FUNC_CNTL = + table->ACPIState.level.mclk.vMPLL_FUNC_CNTL = cpu_to_be32(mpll_func_cntl); - table->ACPIState.levels[0].mclk.vMPLL_FUNC_CNTL_1 = + table->ACPIState.level.mclk.vMPLL_FUNC_CNTL_1 = cpu_to_be32(mpll_func_cntl_1); - table->ACPIState.levels[0].mclk.vMPLL_FUNC_CNTL_2 = + table->ACPIState.level.mclk.vMPLL_FUNC_CNTL_2 = cpu_to_be32(mpll_func_cntl_2); - table->ACPIState.levels[0].mclk.vMPLL_SS = + table->ACPIState.level.mclk.vMPLL_SS = cpu_to_be32(si_pi->clock_registers.mpll_ss1); - table->ACPIState.levels[0].mclk.vMPLL_SS2 = + table->ACPIState.level.mclk.vMPLL_SS2 = cpu_to_be32(si_pi->clock_registers.mpll_ss2); - table->ACPIState.levels[0].sclk.vCG_SPLL_FUNC_CNTL = + table->ACPIState.level.sclk.vCG_SPLL_FUNC_CNTL = cpu_to_be32(spll_func_cntl); - table->ACPIState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_2 = + table->ACPIState.level.sclk.vCG_SPLL_FUNC_CNTL_2 = cpu_to_be32(spll_func_cntl_2); - table->ACPIState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_3 = + table->ACPIState.level.sclk.vCG_SPLL_FUNC_CNTL_3 = cpu_to_be32(spll_func_cntl_3); - table->ACPIState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_4 = + table->ACPIState.level.sclk.vCG_SPLL_FUNC_CNTL_4 = cpu_to_be32(spll_func_cntl_4); - table->ACPIState.levels[0].mclk.mclk_value = 0; - table->ACPIState.levels[0].sclk.sclk_value = 0; + table->ACPIState.level.mclk.mclk_value = 0; + table->ACPIState.level.sclk.sclk_value = 0; - si_populate_mvdd_value(adev, 0, &table->ACPIState.levels[0].mvdd); + si_populate_mvdd_value(adev, 0, &table->ACPIState.level.mvdd); if (eg_pi->dynamic_ac_timing) - table->ACPIState.levels[0].ACIndex = 0; + table->ACPIState.level.ACIndex = 0; - table->ACPIState.levels[0].dpm2.MaxPS = 0; - table->ACPIState.levels[0].dpm2.NearTDPDec = 0; - table->ACPIState.levels[0].dpm2.AboveSafeInc = 0; - table->ACPIState.levels[0].dpm2.BelowSafeInc = 0; - table->ACPIState.levels[0].dpm2.PwrEfficiencyRatio = 0; + table->ACPIState.level.dpm2.MaxPS = 0; + table->ACPIState.level.dpm2.NearTDPDec = 0; + table->ACPIState.level.dpm2.AboveSafeInc = 0; + table->ACPIState.level.dpm2.BelowSafeInc = 0; + table->ACPIState.level.dpm2.PwrEfficiencyRatio = 0; reg = MIN_POWER_MASK | MAX_POWER_MASK; - table->ACPIState.levels[0].SQPowerThrottle = cpu_to_be32(reg); + table->ACPIState.level.SQPowerThrottle = cpu_to_be32(reg); reg = MAX_POWER_DELTA_MASK | STI_SIZE_MASK | LTI_RATIO_MASK; - table->ACPIState.levels[0].SQPowerThrottle_2 = cpu_to_be32(reg); + table->ACPIState.level.SQPowerThrottle_2 = cpu_to_be32(reg); return 0; } static int si_populate_ulv_state(struct amdgpu_device *adev, - SISLANDS_SMC_SWSTATE *state) + struct SISLANDS_SMC_SWSTATE_SINGLE *state) { struct evergreen_power_info *eg_pi = evergreen_get_pi(adev); struct si_power_info *si_pi = si_get_pi(adev); @@ -5079,19 +5079,19 @@ static int si_populate_ulv_state(struct amdgpu_device *adev, int ret; ret = si_convert_power_level_to_smc(adev, &ulv->pl, - &state->levels[0]); + &state->level); if (!ret) { if (eg_pi->sclk_deep_sleep) { if (sclk_in_sr <= SCLK_MIN_DEEPSLEEP_FREQ) - state->levels[0].stateFlags |= PPSMC_STATEFLAG_DEEPSLEEP_BYPASS; + state->level.stateFlags |= PPSMC_STATEFLAG_DEEPSLEEP_BYPASS; else - state->levels[0].stateFlags |= PPSMC_STATEFLAG_DEEPSLEEP_THROTTLE; + state->level.stateFlags |= PPSMC_STATEFLAG_DEEPSLEEP_THROTTLE; } if (ulv->one_pcie_lane_in_ulv) state->flags |= PPSMC_SWSTATE_FLAG_PCIE_X1; - state->levels[0].arbRefreshState = (u8)(SISLANDS_ULV_STATE_ARB_INDEX); - state->levels[0].ACIndex = 1; - state->levels[0].std_vddc = state->levels[0].vddc; + state->level.arbRefreshState = (u8)(SISLANDS_ULV_STATE_ARB_INDEX); + state->level.ACIndex = 1; + state->level.std_vddc = state->level.vddc; state->levelCount = 1; state->flags |= PPSMC_SWSTATE_FLAG_DC; @@ -5190,7 +5190,9 @@ static int si_init_smc_table(struct amdgpu_device *adev) if (ret) return ret; - table->driverState = table->initialState; + table->driverState.flags = table->initialState.flags; + table->driverState.levelCount = table->initialState.levelCount; + table->driverState.levels[0] = table->initialState.level; ret = si_do_program_memory_timing_parameters(adev, amdgpu_boot_state, SISLANDS_INITIAL_STATE_ARB_INDEX); @@ -5737,8 +5739,8 @@ static int si_upload_ulv_state(struct amdgpu_device *adev) if (ulv->supported && ulv->pl.vddc) { u32 address = si_pi->state_table_start + offsetof(SISLANDS_SMC_STATETABLE, ULVState); - SISLANDS_SMC_SWSTATE *smc_state = &si_pi->smc_statetable.ULVState; - u32 state_size = sizeof(SISLANDS_SMC_SWSTATE); + struct SISLANDS_SMC_SWSTATE_SINGLE *smc_state = &si_pi->smc_statetable.ULVState; + u32 state_size = sizeof(struct SISLANDS_SMC_SWSTATE_SINGLE); memset(smc_state, 0, state_size); diff --git a/drivers/gpu/drm/amd/pm/powerplay/sislands_smc.h b/drivers/gpu/drm/amd/pm/powerplay/sislands_smc.h index 0f7554052c90..c7dc117a688c 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/sislands_smc.h +++ b/drivers/gpu/drm/amd/pm/powerplay/sislands_smc.h @@ -191,6 +191,14 @@ struct SISLANDS_SMC_SWSTATE typedef struct SISLANDS_SMC_SWSTATE SISLANDS_SMC_SWSTATE; +struct SISLANDS_SMC_SWSTATE_SINGLE { + uint8_t flags; + uint8_t levelCount; + uint8_t padding2; + uint8_t padding3; + SISLANDS_SMC_HW_PERFORMANCE_LEVEL level; +}; + #define SISLANDS_SMC_VOLTAGEMASK_VDDC 0 #define SISLANDS_SMC_VOLTAGEMASK_MVDD 1 #define SISLANDS_SMC_VOLTAGEMASK_VDDCI 2 @@ -208,19 +216,19 @@ typedef struct SISLANDS_SMC_VOLTAGEMASKTABLE SISLANDS_SMC_VOLTAGEMASKTABLE; struct SISLANDS_SMC_STATETABLE { - uint8_t thermalProtectType; - uint8_t systemFlags; - uint8_t maxVDDCIndexInPPTable; - uint8_t extraFlags; - uint32_t lowSMIO[SISLANDS_MAX_NO_VREG_STEPS]; - SISLANDS_SMC_VOLTAGEMASKTABLE voltageMaskTable; - SISLANDS_SMC_VOLTAGEMASKTABLE phaseMaskTable; - PP_SIslands_DPM2Parameters dpm2Params; - SISLANDS_SMC_SWSTATE initialState; - SISLANDS_SMC_SWSTATE ACPIState; - SISLANDS_SMC_SWSTATE ULVState; - SISLANDS_SMC_SWSTATE driverState; - SISLANDS_SMC_HW_PERFORMANCE_LEVEL dpmLevels[SISLANDS_MAX_SMC_PERFORMANCE_LEVELS_PER_SWSTATE - 1]; + uint8_t thermalProtectType; + uint8_t systemFlags; + uint8_t maxVDDCIndexInPPTable; + uint8_t extraFlags; + uint32_t lowSMIO[SISLANDS_MAX_NO_VREG_STEPS]; + SISLANDS_SMC_VOLTAGEMASKTABLE voltageMaskTable; + SISLANDS_SMC_VOLTAGEMASKTABLE phaseMaskTable; + PP_SIslands_DPM2Parameters dpm2Params; + struct SISLANDS_SMC_SWSTATE_SINGLE initialState; + struct SISLANDS_SMC_SWSTATE_SINGLE ACPIState; + struct SISLANDS_SMC_SWSTATE_SINGLE ULVState; + SISLANDS_SMC_SWSTATE driverState; + SISLANDS_SMC_HW_PERFORMANCE_LEVEL dpmLevels[SISLANDS_MAX_SMC_PERFORMANCE_LEVELS_PER_SWSTATE]; }; typedef struct SISLANDS_SMC_STATETABLE SISLANDS_SMC_STATETABLE; diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 6a2dee8cef1f..642c60f3d9b1 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -1095,44 +1095,6 @@ intel_dp_compute_link_config_wide(struct intel_dp *intel_dp, return -EINVAL; } -/* Optimize link config in order: max bpp, min lanes, min clock */ -static int -intel_dp_compute_link_config_fast(struct intel_dp *intel_dp, - struct intel_crtc_state *pipe_config, - const struct link_config_limits *limits) -{ - const struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode; - int bpp, clock, lane_count; - int mode_rate, link_clock, link_avail; - - for (bpp = limits->max_bpp; bpp >= limits->min_bpp; bpp -= 2 * 3) { - int output_bpp = intel_dp_output_bpp(pipe_config->output_format, bpp); - - mode_rate = intel_dp_link_required(adjusted_mode->crtc_clock, - output_bpp); - - for (lane_count = limits->min_lane_count; - lane_count <= limits->max_lane_count; - lane_count <<= 1) { - for (clock = limits->min_clock; clock <= limits->max_clock; clock++) { - link_clock = intel_dp->common_rates[clock]; - link_avail = intel_dp_max_data_rate(link_clock, - lane_count); - - if (mode_rate <= link_avail) { - pipe_config->lane_count = lane_count; - pipe_config->pipe_bpp = bpp; - pipe_config->port_clock = link_clock; - - return 0; - } - } - } - } - - return -EINVAL; -} - static int intel_dp_dsc_compute_bpp(struct intel_dp *intel_dp, u8 dsc_max_bpc) { int i, num_bpc; @@ -1382,22 +1344,11 @@ intel_dp_compute_link_config(struct intel_encoder *encoder, intel_dp_can_bigjoiner(intel_dp)) pipe_config->bigjoiner = true; - if (intel_dp_is_edp(intel_dp)) - /* - * Optimize for fast and narrow. eDP 1.3 section 3.3 and eDP 1.4 - * section A.1: "It is recommended that the minimum number of - * lanes be used, using the minimum link rate allowed for that - * lane configuration." - * - * Note that we fall back to the max clock and lane count for eDP - * panels that fail with the fast optimal settings (see - * intel_dp->use_max_params), in which case the fast vs. wide - * choice doesn't matter. - */ - ret = intel_dp_compute_link_config_fast(intel_dp, pipe_config, &limits); - else - /* Optimize for slow and wide. */ - ret = intel_dp_compute_link_config_wide(intel_dp, pipe_config, &limits); + /* + * Optimize for slow and wide for everything, because there are some + * eDP 1.3 and 1.4 panels don't work well with fast and narrow. + */ + ret = intel_dp_compute_link_config_wide(intel_dp, pipe_config, &limits); /* enable compression if the mode doesn't fit available BW */ drm_dbg_kms(&i915->drm, "Force DSC en = %d\n", intel_dp->force_dsc_en); @@ -2160,7 +2111,7 @@ void intel_dp_check_frl_training(struct intel_dp *intel_dp) * -PCON supports SRC_CTL_MODE (VESA DP2.0-HDMI2.1 PCON Spec Draft-1 Sec-7) * -sink is HDMI2.1 */ - if (!(intel_dp->dpcd[2] & DP_PCON_SOURCE_CTL_MODE) || + if (!(intel_dp->downstream_ports[2] & DP_PCON_SOURCE_CTL_MODE) || !intel_dp_is_hdmi_2_1_sink(intel_dp) || intel_dp->frl.is_trained) return; diff --git a/drivers/gpu/drm/i915/display/intel_overlay.c b/drivers/gpu/drm/i915/display/intel_overlay.c index e5dadde422f7..bbaf05515e88 100644 --- a/drivers/gpu/drm/i915/display/intel_overlay.c +++ b/drivers/gpu/drm/i915/display/intel_overlay.c @@ -383,7 +383,7 @@ static void intel_overlay_off_tail(struct intel_overlay *overlay) i830_overlay_clock_gating(dev_priv, true); } -static void +__i915_active_call static void intel_overlay_last_flip_retire(struct i915_active *active) { struct intel_overlay *overlay = diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index 23f6b00e08e2..f6fe5cb01438 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -189,7 +189,7 @@ compute_partial_view(const struct drm_i915_gem_object *obj, struct i915_ggtt_view view; if (i915_gem_object_is_tiled(obj)) - chunk = roundup(chunk, tile_row_pages(obj)); + chunk = roundup(chunk, tile_row_pages(obj) ?: 1); view.type = I915_GGTT_VIEW_PARTIAL; view.partial.offset = rounddown(page_offset, chunk); diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c index 176c19633412..74bf6fc8461f 100644 --- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c @@ -641,7 +641,6 @@ static int gen8_preallocate_top_level_pdp(struct i915_ppgtt *ppgtt) err = pin_pt_dma(vm, pde->pt.base); if (err) { - i915_gem_object_put(pde->pt.base); free_pd(vm, pde); return err; } diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c index e72b7a0dc316..8a322594210c 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c @@ -653,8 +653,8 @@ static void detect_bit_6_swizzle(struct i915_ggtt *ggtt) * banks of memory are paired and unswizzled on the * uneven portion, so leave that as unknown. */ - if (intel_uncore_read(uncore, C0DRB3) == - intel_uncore_read(uncore, C1DRB3)) { + if (intel_uncore_read16(uncore, C0DRB3) == + intel_uncore_read16(uncore, C1DRB3)) { swizzle_x = I915_BIT_6_SWIZZLE_9_10; swizzle_y = I915_BIT_6_SWIZZLE_9; } diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c index cf9a3d384971..aa573b078ae7 100644 --- a/drivers/gpu/drm/i915/i915_active.c +++ b/drivers/gpu/drm/i915/i915_active.c @@ -1156,7 +1156,8 @@ static int auto_active(struct i915_active *ref) return 0; } -static void auto_retire(struct i915_active *ref) +__i915_active_call static void +auto_retire(struct i915_active *ref) { i915_active_put(ref); } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index d553f62f4eeb..b4d8e1b01ee4 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -1153,10 +1153,6 @@ static void a6xx_llc_slices_init(struct platform_device *pdev, { struct device_node *phandle; - a6xx_gpu->llc_mmio = msm_ioremap(pdev, "cx_mem", "gpu_cx"); - if (IS_ERR(a6xx_gpu->llc_mmio)) - return; - /* * There is a different programming path for targets with an mmu500 * attached, so detect if that is the case @@ -1166,6 +1162,11 @@ static void a6xx_llc_slices_init(struct platform_device *pdev, of_device_is_compatible(phandle, "arm,mmu-500")); of_node_put(phandle); + if (a6xx_gpu->have_mmu500) + a6xx_gpu->llc_mmio = NULL; + else + a6xx_gpu->llc_mmio = msm_ioremap(pdev, "cx_mem", "gpu_cx"); + a6xx_gpu->llc_slice = llcc_slice_getd(LLCC_GPU); a6xx_gpu->htw_llc_slice = llcc_slice_getd(LLCC_GPUHTW); diff --git a/drivers/gpu/drm/msm/dp/dp_audio.c b/drivers/gpu/drm/msm/dp/dp_audio.c index 82a8673ab8da..d7e4a39a904e 100644 --- a/drivers/gpu/drm/msm/dp/dp_audio.c +++ b/drivers/gpu/drm/msm/dp/dp_audio.c @@ -527,6 +527,7 @@ int dp_audio_hw_params(struct device *dev, dp_audio_setup_acr(audio); dp_audio_safe_to_exit_level(audio); dp_audio_enable(audio, true); + dp_display_signal_audio_start(dp_display); dp_display->audio_enabled = true; end: diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index 5a39da6e1eaf..1784e119269b 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -178,6 +178,15 @@ static int dp_del_event(struct dp_display_private *dp_priv, u32 event) return 0; } +void dp_display_signal_audio_start(struct msm_dp *dp_display) +{ + struct dp_display_private *dp; + + dp = container_of(dp_display, struct dp_display_private, dp_display); + + reinit_completion(&dp->audio_comp); +} + void dp_display_signal_audio_complete(struct msm_dp *dp_display) { struct dp_display_private *dp; @@ -586,10 +595,8 @@ static int dp_connect_pending_timeout(struct dp_display_private *dp, u32 data) mutex_lock(&dp->event_mutex); state = dp->hpd_state; - if (state == ST_CONNECT_PENDING) { - dp_display_enable(dp, 0); + if (state == ST_CONNECT_PENDING) dp->hpd_state = ST_CONNECTED; - } mutex_unlock(&dp->event_mutex); @@ -651,7 +658,6 @@ static int dp_hpd_unplug_handle(struct dp_display_private *dp, u32 data) dp_add_event(dp, EV_DISCONNECT_PENDING_TIMEOUT, 0, DP_TIMEOUT_5_SECOND); /* signal the disconnect event early to ensure proper teardown */ - reinit_completion(&dp->audio_comp); dp_display_handle_plugged_change(g_dp_display, false); dp_catalog_hpd_config_intr(dp->catalog, DP_DP_HPD_PLUG_INT_MASK | @@ -669,10 +675,8 @@ static int dp_disconnect_pending_timeout(struct dp_display_private *dp, u32 data mutex_lock(&dp->event_mutex); state = dp->hpd_state; - if (state == ST_DISCONNECT_PENDING) { - dp_display_disable(dp, 0); + if (state == ST_DISCONNECT_PENDING) dp->hpd_state = ST_DISCONNECTED; - } mutex_unlock(&dp->event_mutex); @@ -898,7 +902,6 @@ static int dp_display_disable(struct dp_display_private *dp, u32 data) /* wait only if audio was enabled */ if (dp_display->audio_enabled) { /* signal the disconnect event */ - reinit_completion(&dp->audio_comp); dp_display_handle_plugged_change(dp_display, false); if (!wait_for_completion_timeout(&dp->audio_comp, HZ * 5)) @@ -1272,7 +1275,12 @@ static int dp_pm_resume(struct device *dev) status = dp_catalog_link_is_connected(dp->catalog); - if (status) + /* + * can not declared display is connected unless + * HDMI cable is plugged in and sink_count of + * dongle become 1 + */ + if (status && dp->link->sink_count) dp->dp_display.is_connected = true; else dp->dp_display.is_connected = false; diff --git a/drivers/gpu/drm/msm/dp/dp_display.h b/drivers/gpu/drm/msm/dp/dp_display.h index 6092ba1ed85e..5173c89eedf7 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.h +++ b/drivers/gpu/drm/msm/dp/dp_display.h @@ -34,6 +34,7 @@ int dp_display_get_modes(struct msm_dp *dp_display, int dp_display_request_irq(struct msm_dp *dp_display); bool dp_display_check_video_test(struct msm_dp *dp_display); int dp_display_get_test_bpp(struct msm_dp *dp_display); +void dp_display_signal_audio_start(struct msm_dp *dp_display); void dp_display_signal_audio_complete(struct msm_dp *dp_display); #endif /* _DP_DISPLAY_H_ */ diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c index f0a2ddf96a4b..ff7f2ec42030 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c @@ -843,7 +843,7 @@ int msm_dsi_phy_get_clk_provider(struct msm_dsi_phy *phy, if (pixel_clk_provider) *pixel_clk_provider = phy->provided_clocks->hws[DSI_PIXEL_PLL_CLK]->clk; - return -EINVAL; + return 0; } void msm_dsi_phy_pll_save_state(struct msm_dsi_phy *phy) diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c index 582b1428f971..86e40a0d41a3 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c @@ -405,6 +405,10 @@ static int pll_28nm_register(struct dsi_pll_28nm *pll_28nm, struct clk_hw **prov if (!vco_name) return -ENOMEM; + parent_name = devm_kzalloc(dev, 32, GFP_KERNEL); + if (!parent_name) + return -ENOMEM; + clk_name = devm_kzalloc(dev, 32, GFP_KERNEL); if (!clk_name) return -ENOMEM; diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index e1104d2454e2..fe7d17cd35ec 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -42,7 +42,7 @@ * - 1.7.0 - Add MSM_PARAM_SUSPENDS to access suspend count */ #define MSM_VERSION_MAJOR 1 -#define MSM_VERSION_MINOR 6 +#define MSM_VERSION_MINOR 7 #define MSM_VERSION_PATCHLEVEL 0 static const struct drm_mode_config_funcs mode_config_funcs = { diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index b199942266a2..56df86e5f740 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -190,13 +190,25 @@ struct page **msm_gem_get_pages(struct drm_gem_object *obj) } p = get_pages(obj); + + if (!IS_ERR(p)) { + msm_obj->pin_count++; + update_inactive(msm_obj); + } + msm_gem_unlock(obj); return p; } void msm_gem_put_pages(struct drm_gem_object *obj) { - /* when we start tracking the pin count, then do something here */ + struct msm_gem_object *msm_obj = to_msm_bo(obj); + + msm_gem_lock(obj); + msm_obj->pin_count--; + GEM_WARN_ON(msm_obj->pin_count < 0); + update_inactive(msm_obj); + msm_gem_unlock(obj); } int msm_gem_mmap_obj(struct drm_gem_object *obj, @@ -646,6 +658,8 @@ static void *get_vaddr(struct drm_gem_object *obj, unsigned madv) ret = -ENOMEM; goto fail; } + + update_inactive(msm_obj); } return msm_obj->vaddr; diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h index a6480d2c81b2..03e2cc2a2ce1 100644 --- a/drivers/gpu/drm/msm/msm_gem.h +++ b/drivers/gpu/drm/msm/msm_gem.h @@ -221,7 +221,7 @@ static inline bool is_active(struct msm_gem_object *msm_obj) /* imported/exported objects are not purgeable: */ static inline bool is_unpurgeable(struct msm_gem_object *msm_obj) { - return msm_obj->base.dma_buf && msm_obj->base.import_attach; + return msm_obj->base.import_attach || msm_obj->pin_count; } static inline bool is_purgeable(struct msm_gem_object *msm_obj) @@ -271,7 +271,7 @@ static inline void mark_unpurgeable(struct msm_gem_object *msm_obj) static inline bool is_unevictable(struct msm_gem_object *msm_obj) { - return is_unpurgeable(msm_obj) || msm_obj->pin_count || msm_obj->vaddr; + return is_unpurgeable(msm_obj) || msm_obj->vaddr; } static inline void mark_evictable(struct msm_gem_object *msm_obj) diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c index dd5ef6493723..769f666335ac 100644 --- a/drivers/gpu/drm/radeon/ni_dpm.c +++ b/drivers/gpu/drm/radeon/ni_dpm.c @@ -1687,102 +1687,102 @@ static int ni_populate_smc_initial_state(struct radeon_device *rdev, u32 reg; int ret; - table->initialState.levels[0].mclk.vMPLL_AD_FUNC_CNTL = + table->initialState.level.mclk.vMPLL_AD_FUNC_CNTL = cpu_to_be32(ni_pi->clock_registers.mpll_ad_func_cntl); - table->initialState.levels[0].mclk.vMPLL_AD_FUNC_CNTL_2 = + table->initialState.level.mclk.vMPLL_AD_FUNC_CNTL_2 = cpu_to_be32(ni_pi->clock_registers.mpll_ad_func_cntl_2); - table->initialState.levels[0].mclk.vMPLL_DQ_FUNC_CNTL = + table->initialState.level.mclk.vMPLL_DQ_FUNC_CNTL = cpu_to_be32(ni_pi->clock_registers.mpll_dq_func_cntl); - table->initialState.levels[0].mclk.vMPLL_DQ_FUNC_CNTL_2 = + table->initialState.level.mclk.vMPLL_DQ_FUNC_CNTL_2 = cpu_to_be32(ni_pi->clock_registers.mpll_dq_func_cntl_2); - table->initialState.levels[0].mclk.vMCLK_PWRMGT_CNTL = + table->initialState.level.mclk.vMCLK_PWRMGT_CNTL = cpu_to_be32(ni_pi->clock_registers.mclk_pwrmgt_cntl); - table->initialState.levels[0].mclk.vDLL_CNTL = + table->initialState.level.mclk.vDLL_CNTL = cpu_to_be32(ni_pi->clock_registers.dll_cntl); - table->initialState.levels[0].mclk.vMPLL_SS = + table->initialState.level.mclk.vMPLL_SS = cpu_to_be32(ni_pi->clock_registers.mpll_ss1); - table->initialState.levels[0].mclk.vMPLL_SS2 = + table->initialState.level.mclk.vMPLL_SS2 = cpu_to_be32(ni_pi->clock_registers.mpll_ss2); - table->initialState.levels[0].mclk.mclk_value = + table->initialState.level.mclk.mclk_value = cpu_to_be32(initial_state->performance_levels[0].mclk); - table->initialState.levels[0].sclk.vCG_SPLL_FUNC_CNTL = + table->initialState.level.sclk.vCG_SPLL_FUNC_CNTL = cpu_to_be32(ni_pi->clock_registers.cg_spll_func_cntl); - table->initialState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_2 = + table->initialState.level.sclk.vCG_SPLL_FUNC_CNTL_2 = cpu_to_be32(ni_pi->clock_registers.cg_spll_func_cntl_2); - table->initialState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_3 = + table->initialState.level.sclk.vCG_SPLL_FUNC_CNTL_3 = cpu_to_be32(ni_pi->clock_registers.cg_spll_func_cntl_3); - table->initialState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_4 = + table->initialState.level.sclk.vCG_SPLL_FUNC_CNTL_4 = cpu_to_be32(ni_pi->clock_registers.cg_spll_func_cntl_4); - table->initialState.levels[0].sclk.vCG_SPLL_SPREAD_SPECTRUM = + table->initialState.level.sclk.vCG_SPLL_SPREAD_SPECTRUM = cpu_to_be32(ni_pi->clock_registers.cg_spll_spread_spectrum); - table->initialState.levels[0].sclk.vCG_SPLL_SPREAD_SPECTRUM_2 = + table->initialState.level.sclk.vCG_SPLL_SPREAD_SPECTRUM_2 = cpu_to_be32(ni_pi->clock_registers.cg_spll_spread_spectrum_2); - table->initialState.levels[0].sclk.sclk_value = + table->initialState.level.sclk.sclk_value = cpu_to_be32(initial_state->performance_levels[0].sclk); - table->initialState.levels[0].arbRefreshState = + table->initialState.level.arbRefreshState = NISLANDS_INITIAL_STATE_ARB_INDEX; - table->initialState.levels[0].ACIndex = 0; + table->initialState.level.ACIndex = 0; ret = ni_populate_voltage_value(rdev, &eg_pi->vddc_voltage_table, initial_state->performance_levels[0].vddc, - &table->initialState.levels[0].vddc); + &table->initialState.level.vddc); if (!ret) { u16 std_vddc; ret = ni_get_std_voltage_value(rdev, - &table->initialState.levels[0].vddc, + &table->initialState.level.vddc, &std_vddc); if (!ret) ni_populate_std_voltage_value(rdev, std_vddc, - table->initialState.levels[0].vddc.index, - &table->initialState.levels[0].std_vddc); + table->initialState.level.vddc.index, + &table->initialState.level.std_vddc); } if (eg_pi->vddci_control) ni_populate_voltage_value(rdev, &eg_pi->vddci_voltage_table, initial_state->performance_levels[0].vddci, - &table->initialState.levels[0].vddci); + &table->initialState.level.vddci); - ni_populate_initial_mvdd_value(rdev, &table->initialState.levels[0].mvdd); + ni_populate_initial_mvdd_value(rdev, &table->initialState.level.mvdd); reg = CG_R(0xffff) | CG_L(0); - table->initialState.levels[0].aT = cpu_to_be32(reg); + table->initialState.level.aT = cpu_to_be32(reg); - table->initialState.levels[0].bSP = cpu_to_be32(pi->dsp); + table->initialState.level.bSP = cpu_to_be32(pi->dsp); if (pi->boot_in_gen2) - table->initialState.levels[0].gen2PCIE = 1; + table->initialState.level.gen2PCIE = 1; else - table->initialState.levels[0].gen2PCIE = 0; + table->initialState.level.gen2PCIE = 0; if (pi->mem_gddr5) { - table->initialState.levels[0].strobeMode = + table->initialState.level.strobeMode = cypress_get_strobe_mode_settings(rdev, initial_state->performance_levels[0].mclk); if (initial_state->performance_levels[0].mclk > pi->mclk_edc_enable_threshold) - table->initialState.levels[0].mcFlags = NISLANDS_SMC_MC_EDC_RD_FLAG | NISLANDS_SMC_MC_EDC_WR_FLAG; + table->initialState.level.mcFlags = NISLANDS_SMC_MC_EDC_RD_FLAG | NISLANDS_SMC_MC_EDC_WR_FLAG; else - table->initialState.levels[0].mcFlags = 0; + table->initialState.level.mcFlags = 0; } table->initialState.levelCount = 1; table->initialState.flags |= PPSMC_SWSTATE_FLAG_DC; - table->initialState.levels[0].dpm2.MaxPS = 0; - table->initialState.levels[0].dpm2.NearTDPDec = 0; - table->initialState.levels[0].dpm2.AboveSafeInc = 0; - table->initialState.levels[0].dpm2.BelowSafeInc = 0; + table->initialState.level.dpm2.MaxPS = 0; + table->initialState.level.dpm2.NearTDPDec = 0; + table->initialState.level.dpm2.AboveSafeInc = 0; + table->initialState.level.dpm2.BelowSafeInc = 0; reg = MIN_POWER_MASK | MAX_POWER_MASK; - table->initialState.levels[0].SQPowerThrottle = cpu_to_be32(reg); + table->initialState.level.SQPowerThrottle = cpu_to_be32(reg); reg = MAX_POWER_DELTA_MASK | STI_SIZE_MASK | LTI_RATIO_MASK; - table->initialState.levels[0].SQPowerThrottle_2 = cpu_to_be32(reg); + table->initialState.level.SQPowerThrottle_2 = cpu_to_be32(reg); return 0; } @@ -1813,43 +1813,43 @@ static int ni_populate_smc_acpi_state(struct radeon_device *rdev, if (pi->acpi_vddc) { ret = ni_populate_voltage_value(rdev, &eg_pi->vddc_voltage_table, - pi->acpi_vddc, &table->ACPIState.levels[0].vddc); + pi->acpi_vddc, &table->ACPIState.level.vddc); if (!ret) { u16 std_vddc; ret = ni_get_std_voltage_value(rdev, - &table->ACPIState.levels[0].vddc, &std_vddc); + &table->ACPIState.level.vddc, &std_vddc); if (!ret) ni_populate_std_voltage_value(rdev, std_vddc, - table->ACPIState.levels[0].vddc.index, - &table->ACPIState.levels[0].std_vddc); + table->ACPIState.level.vddc.index, + &table->ACPIState.level.std_vddc); } if (pi->pcie_gen2) { if (pi->acpi_pcie_gen2) - table->ACPIState.levels[0].gen2PCIE = 1; + table->ACPIState.level.gen2PCIE = 1; else - table->ACPIState.levels[0].gen2PCIE = 0; + table->ACPIState.level.gen2PCIE = 0; } else { - table->ACPIState.levels[0].gen2PCIE = 0; + table->ACPIState.level.gen2PCIE = 0; } } else { ret = ni_populate_voltage_value(rdev, &eg_pi->vddc_voltage_table, pi->min_vddc_in_table, - &table->ACPIState.levels[0].vddc); + &table->ACPIState.level.vddc); if (!ret) { u16 std_vddc; ret = ni_get_std_voltage_value(rdev, - &table->ACPIState.levels[0].vddc, + &table->ACPIState.level.vddc, &std_vddc); if (!ret) ni_populate_std_voltage_value(rdev, std_vddc, - table->ACPIState.levels[0].vddc.index, - &table->ACPIState.levels[0].std_vddc); + table->ACPIState.level.vddc.index, + &table->ACPIState.level.std_vddc); } - table->ACPIState.levels[0].gen2PCIE = 0; + table->ACPIState.level.gen2PCIE = 0; } if (eg_pi->acpi_vddci) { @@ -1857,7 +1857,7 @@ static int ni_populate_smc_acpi_state(struct radeon_device *rdev, ni_populate_voltage_value(rdev, &eg_pi->vddci_voltage_table, eg_pi->acpi_vddci, - &table->ACPIState.levels[0].vddci); + &table->ACPIState.level.vddci); } @@ -1900,37 +1900,37 @@ static int ni_populate_smc_acpi_state(struct radeon_device *rdev, spll_func_cntl_2 &= ~SCLK_MUX_SEL_MASK; spll_func_cntl_2 |= SCLK_MUX_SEL(4); - table->ACPIState.levels[0].mclk.vMPLL_AD_FUNC_CNTL = cpu_to_be32(mpll_ad_func_cntl); - table->ACPIState.levels[0].mclk.vMPLL_AD_FUNC_CNTL_2 = cpu_to_be32(mpll_ad_func_cntl_2); - table->ACPIState.levels[0].mclk.vMPLL_DQ_FUNC_CNTL = cpu_to_be32(mpll_dq_func_cntl); - table->ACPIState.levels[0].mclk.vMPLL_DQ_FUNC_CNTL_2 = cpu_to_be32(mpll_dq_func_cntl_2); - table->ACPIState.levels[0].mclk.vMCLK_PWRMGT_CNTL = cpu_to_be32(mclk_pwrmgt_cntl); - table->ACPIState.levels[0].mclk.vDLL_CNTL = cpu_to_be32(dll_cntl); + table->ACPIState.level.mclk.vMPLL_AD_FUNC_CNTL = cpu_to_be32(mpll_ad_func_cntl); + table->ACPIState.level.mclk.vMPLL_AD_FUNC_CNTL_2 = cpu_to_be32(mpll_ad_func_cntl_2); + table->ACPIState.level.mclk.vMPLL_DQ_FUNC_CNTL = cpu_to_be32(mpll_dq_func_cntl); + table->ACPIState.level.mclk.vMPLL_DQ_FUNC_CNTL_2 = cpu_to_be32(mpll_dq_func_cntl_2); + table->ACPIState.level.mclk.vMCLK_PWRMGT_CNTL = cpu_to_be32(mclk_pwrmgt_cntl); + table->ACPIState.level.mclk.vDLL_CNTL = cpu_to_be32(dll_cntl); - table->ACPIState.levels[0].mclk.mclk_value = 0; + table->ACPIState.level.mclk.mclk_value = 0; - table->ACPIState.levels[0].sclk.vCG_SPLL_FUNC_CNTL = cpu_to_be32(spll_func_cntl); - table->ACPIState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_2 = cpu_to_be32(spll_func_cntl_2); - table->ACPIState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_3 = cpu_to_be32(spll_func_cntl_3); - table->ACPIState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_4 = cpu_to_be32(spll_func_cntl_4); + table->ACPIState.level.sclk.vCG_SPLL_FUNC_CNTL = cpu_to_be32(spll_func_cntl); + table->ACPIState.level.sclk.vCG_SPLL_FUNC_CNTL_2 = cpu_to_be32(spll_func_cntl_2); + table->ACPIState.level.sclk.vCG_SPLL_FUNC_CNTL_3 = cpu_to_be32(spll_func_cntl_3); + table->ACPIState.level.sclk.vCG_SPLL_FUNC_CNTL_4 = cpu_to_be32(spll_func_cntl_4); - table->ACPIState.levels[0].sclk.sclk_value = 0; + table->ACPIState.level.sclk.sclk_value = 0; - ni_populate_mvdd_value(rdev, 0, &table->ACPIState.levels[0].mvdd); + ni_populate_mvdd_value(rdev, 0, &table->ACPIState.level.mvdd); if (eg_pi->dynamic_ac_timing) - table->ACPIState.levels[0].ACIndex = 1; + table->ACPIState.level.ACIndex = 1; - table->ACPIState.levels[0].dpm2.MaxPS = 0; - table->ACPIState.levels[0].dpm2.NearTDPDec = 0; - table->ACPIState.levels[0].dpm2.AboveSafeInc = 0; - table->ACPIState.levels[0].dpm2.BelowSafeInc = 0; + table->ACPIState.level.dpm2.MaxPS = 0; + table->ACPIState.level.dpm2.NearTDPDec = 0; + table->ACPIState.level.dpm2.AboveSafeInc = 0; + table->ACPIState.level.dpm2.BelowSafeInc = 0; reg = MIN_POWER_MASK | MAX_POWER_MASK; - table->ACPIState.levels[0].SQPowerThrottle = cpu_to_be32(reg); + table->ACPIState.level.SQPowerThrottle = cpu_to_be32(reg); reg = MAX_POWER_DELTA_MASK | STI_SIZE_MASK | LTI_RATIO_MASK; - table->ACPIState.levels[0].SQPowerThrottle_2 = cpu_to_be32(reg); + table->ACPIState.level.SQPowerThrottle_2 = cpu_to_be32(reg); return 0; } @@ -1980,7 +1980,9 @@ static int ni_init_smc_table(struct radeon_device *rdev) if (ret) return ret; - table->driverState = table->initialState; + table->driverState.flags = table->initialState.flags; + table->driverState.levelCount = table->initialState.levelCount; + table->driverState.levels[0] = table->initialState.level; table->ULVState = table->initialState; diff --git a/drivers/gpu/drm/radeon/nislands_smc.h b/drivers/gpu/drm/radeon/nislands_smc.h index 7395cb6b3cac..42f3bab0f9ee 100644 --- a/drivers/gpu/drm/radeon/nislands_smc.h +++ b/drivers/gpu/drm/radeon/nislands_smc.h @@ -143,6 +143,14 @@ struct NISLANDS_SMC_SWSTATE typedef struct NISLANDS_SMC_SWSTATE NISLANDS_SMC_SWSTATE; +struct NISLANDS_SMC_SWSTATE_SINGLE { + uint8_t flags; + uint8_t levelCount; + uint8_t padding2; + uint8_t padding3; + NISLANDS_SMC_HW_PERFORMANCE_LEVEL level; +}; + #define NISLANDS_SMC_VOLTAGEMASK_VDDC 0 #define NISLANDS_SMC_VOLTAGEMASK_MVDD 1 #define NISLANDS_SMC_VOLTAGEMASK_VDDCI 2 @@ -160,19 +168,19 @@ typedef struct NISLANDS_SMC_VOLTAGEMASKTABLE NISLANDS_SMC_VOLTAGEMASKTABLE; struct NISLANDS_SMC_STATETABLE { - uint8_t thermalProtectType; - uint8_t systemFlags; - uint8_t maxVDDCIndexInPPTable; - uint8_t extraFlags; - uint8_t highSMIO[NISLANDS_MAX_NO_VREG_STEPS]; - uint32_t lowSMIO[NISLANDS_MAX_NO_VREG_STEPS]; - NISLANDS_SMC_VOLTAGEMASKTABLE voltageMaskTable; - PP_NIslands_DPM2Parameters dpm2Params; - NISLANDS_SMC_SWSTATE initialState; - NISLANDS_SMC_SWSTATE ACPIState; - NISLANDS_SMC_SWSTATE ULVState; - NISLANDS_SMC_SWSTATE driverState; - NISLANDS_SMC_HW_PERFORMANCE_LEVEL dpmLevels[NISLANDS_MAX_SMC_PERFORMANCE_LEVELS_PER_SWSTATE - 1]; + uint8_t thermalProtectType; + uint8_t systemFlags; + uint8_t maxVDDCIndexInPPTable; + uint8_t extraFlags; + uint8_t highSMIO[NISLANDS_MAX_NO_VREG_STEPS]; + uint32_t lowSMIO[NISLANDS_MAX_NO_VREG_STEPS]; + NISLANDS_SMC_VOLTAGEMASKTABLE voltageMaskTable; + PP_NIslands_DPM2Parameters dpm2Params; + struct NISLANDS_SMC_SWSTATE_SINGLE initialState; + struct NISLANDS_SMC_SWSTATE_SINGLE ACPIState; + struct NISLANDS_SMC_SWSTATE_SINGLE ULVState; + NISLANDS_SMC_SWSTATE driverState; + NISLANDS_SMC_HW_PERFORMANCE_LEVEL dpmLevels[NISLANDS_MAX_SMC_PERFORMANCE_LEVELS_PER_SWSTATE]; }; typedef struct NISLANDS_SMC_STATETABLE NISLANDS_SMC_STATETABLE; diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 42281fce552e..56ed5634cebe 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -1549,6 +1549,7 @@ struct radeon_dpm { void *priv; u32 new_active_crtcs; int new_active_crtc_count; + int high_pixelclock_count; u32 current_active_crtcs; int current_active_crtc_count; bool single_display; diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index 0c1950f4e146..3861c0b98fcf 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -1767,6 +1767,7 @@ static void radeon_pm_compute_clocks_dpm(struct radeon_device *rdev) struct drm_device *ddev = rdev->ddev; struct drm_crtc *crtc; struct radeon_crtc *radeon_crtc; + struct radeon_connector *radeon_connector; if (!rdev->pm.dpm_enabled) return; @@ -1776,6 +1777,7 @@ static void radeon_pm_compute_clocks_dpm(struct radeon_device *rdev) /* update active crtc counts */ rdev->pm.dpm.new_active_crtcs = 0; rdev->pm.dpm.new_active_crtc_count = 0; + rdev->pm.dpm.high_pixelclock_count = 0; if (rdev->num_crtc && rdev->mode_info.mode_config_initialized) { list_for_each_entry(crtc, &ddev->mode_config.crtc_list, head) { @@ -1783,6 +1785,12 @@ static void radeon_pm_compute_clocks_dpm(struct radeon_device *rdev) if (crtc->enabled) { rdev->pm.dpm.new_active_crtcs |= (1 << radeon_crtc->crtc_id); rdev->pm.dpm.new_active_crtc_count++; + if (!radeon_crtc->connector) + continue; + + radeon_connector = to_radeon_connector(radeon_crtc->connector); + if (radeon_connector->pixelclock_for_modeset > 297000) + rdev->pm.dpm.high_pixelclock_count++; } } } diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index 918609551804..3add39c1a689 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -2979,6 +2979,9 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev, (rdev->pdev->device == 0x6605)) { max_sclk = 75000; } + + if (rdev->pm.dpm.high_pixelclock_count > 1) + disable_sclk_switching = true; } if (rps->vce_active) { @@ -4350,70 +4353,70 @@ static int si_populate_smc_initial_state(struct radeon_device *rdev, u32 reg; int ret; - table->initialState.levels[0].mclk.vDLL_CNTL = + table->initialState.level.mclk.vDLL_CNTL = cpu_to_be32(si_pi->clock_registers.dll_cntl); - table->initialState.levels[0].mclk.vMCLK_PWRMGT_CNTL = + table->initialState.level.mclk.vMCLK_PWRMGT_CNTL = cpu_to_be32(si_pi->clock_registers.mclk_pwrmgt_cntl); - table->initialState.levels[0].mclk.vMPLL_AD_FUNC_CNTL = + table->initialState.level.mclk.vMPLL_AD_FUNC_CNTL = cpu_to_be32(si_pi->clock_registers.mpll_ad_func_cntl); - table->initialState.levels[0].mclk.vMPLL_DQ_FUNC_CNTL = + table->initialState.level.mclk.vMPLL_DQ_FUNC_CNTL = cpu_to_be32(si_pi->clock_registers.mpll_dq_func_cntl); - table->initialState.levels[0].mclk.vMPLL_FUNC_CNTL = + table->initialState.level.mclk.vMPLL_FUNC_CNTL = cpu_to_be32(si_pi->clock_registers.mpll_func_cntl); - table->initialState.levels[0].mclk.vMPLL_FUNC_CNTL_1 = + table->initialState.level.mclk.vMPLL_FUNC_CNTL_1 = cpu_to_be32(si_pi->clock_registers.mpll_func_cntl_1); - table->initialState.levels[0].mclk.vMPLL_FUNC_CNTL_2 = + table->initialState.level.mclk.vMPLL_FUNC_CNTL_2 = cpu_to_be32(si_pi->clock_registers.mpll_func_cntl_2); - table->initialState.levels[0].mclk.vMPLL_SS = + table->initialState.level.mclk.vMPLL_SS = cpu_to_be32(si_pi->clock_registers.mpll_ss1); - table->initialState.levels[0].mclk.vMPLL_SS2 = + table->initialState.level.mclk.vMPLL_SS2 = cpu_to_be32(si_pi->clock_registers.mpll_ss2); - table->initialState.levels[0].mclk.mclk_value = + table->initialState.level.mclk.mclk_value = cpu_to_be32(initial_state->performance_levels[0].mclk); - table->initialState.levels[0].sclk.vCG_SPLL_FUNC_CNTL = + table->initialState.level.sclk.vCG_SPLL_FUNC_CNTL = cpu_to_be32(si_pi->clock_registers.cg_spll_func_cntl); - table->initialState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_2 = + table->initialState.level.sclk.vCG_SPLL_FUNC_CNTL_2 = cpu_to_be32(si_pi->clock_registers.cg_spll_func_cntl_2); - table->initialState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_3 = + table->initialState.level.sclk.vCG_SPLL_FUNC_CNTL_3 = cpu_to_be32(si_pi->clock_registers.cg_spll_func_cntl_3); - table->initialState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_4 = + table->initialState.level.sclk.vCG_SPLL_FUNC_CNTL_4 = cpu_to_be32(si_pi->clock_registers.cg_spll_func_cntl_4); - table->initialState.levels[0].sclk.vCG_SPLL_SPREAD_SPECTRUM = + table->initialState.level.sclk.vCG_SPLL_SPREAD_SPECTRUM = cpu_to_be32(si_pi->clock_registers.cg_spll_spread_spectrum); - table->initialState.levels[0].sclk.vCG_SPLL_SPREAD_SPECTRUM_2 = + table->initialState.level.sclk.vCG_SPLL_SPREAD_SPECTRUM_2 = cpu_to_be32(si_pi->clock_registers.cg_spll_spread_spectrum_2); - table->initialState.levels[0].sclk.sclk_value = + table->initialState.level.sclk.sclk_value = cpu_to_be32(initial_state->performance_levels[0].sclk); - table->initialState.levels[0].arbRefreshState = + table->initialState.level.arbRefreshState = SISLANDS_INITIAL_STATE_ARB_INDEX; - table->initialState.levels[0].ACIndex = 0; + table->initialState.level.ACIndex = 0; ret = si_populate_voltage_value(rdev, &eg_pi->vddc_voltage_table, initial_state->performance_levels[0].vddc, - &table->initialState.levels[0].vddc); + &table->initialState.level.vddc); if (!ret) { u16 std_vddc; ret = si_get_std_voltage_value(rdev, - &table->initialState.levels[0].vddc, + &table->initialState.level.vddc, &std_vddc); if (!ret) si_populate_std_voltage_value(rdev, std_vddc, - table->initialState.levels[0].vddc.index, - &table->initialState.levels[0].std_vddc); + table->initialState.level.vddc.index, + &table->initialState.level.std_vddc); } if (eg_pi->vddci_control) si_populate_voltage_value(rdev, &eg_pi->vddci_voltage_table, initial_state->performance_levels[0].vddci, - &table->initialState.levels[0].vddci); + &table->initialState.level.vddci); if (si_pi->vddc_phase_shed_control) si_populate_phase_shedding_value(rdev, @@ -4421,43 +4424,43 @@ static int si_populate_smc_initial_state(struct radeon_device *rdev, initial_state->performance_levels[0].vddc, initial_state->performance_levels[0].sclk, initial_state->performance_levels[0].mclk, - &table->initialState.levels[0].vddc); + &table->initialState.level.vddc); - si_populate_initial_mvdd_value(rdev, &table->initialState.levels[0].mvdd); + si_populate_initial_mvdd_value(rdev, &table->initialState.level.mvdd); reg = CG_R(0xffff) | CG_L(0); - table->initialState.levels[0].aT = cpu_to_be32(reg); + table->initialState.level.aT = cpu_to_be32(reg); - table->initialState.levels[0].bSP = cpu_to_be32(pi->dsp); + table->initialState.level.bSP = cpu_to_be32(pi->dsp); - table->initialState.levels[0].gen2PCIE = (u8)si_pi->boot_pcie_gen; + table->initialState.level.gen2PCIE = (u8)si_pi->boot_pcie_gen; if (pi->mem_gddr5) { - table->initialState.levels[0].strobeMode = + table->initialState.level.strobeMode = si_get_strobe_mode_settings(rdev, initial_state->performance_levels[0].mclk); if (initial_state->performance_levels[0].mclk > pi->mclk_edc_enable_threshold) - table->initialState.levels[0].mcFlags = SISLANDS_SMC_MC_EDC_RD_FLAG | SISLANDS_SMC_MC_EDC_WR_FLAG; + table->initialState.level.mcFlags = SISLANDS_SMC_MC_EDC_RD_FLAG | SISLANDS_SMC_MC_EDC_WR_FLAG; else - table->initialState.levels[0].mcFlags = 0; + table->initialState.level.mcFlags = 0; } table->initialState.levelCount = 1; table->initialState.flags |= PPSMC_SWSTATE_FLAG_DC; - table->initialState.levels[0].dpm2.MaxPS = 0; - table->initialState.levels[0].dpm2.NearTDPDec = 0; - table->initialState.levels[0].dpm2.AboveSafeInc = 0; - table->initialState.levels[0].dpm2.BelowSafeInc = 0; - table->initialState.levels[0].dpm2.PwrEfficiencyRatio = 0; + table->initialState.level.dpm2.MaxPS = 0; + table->initialState.level.dpm2.NearTDPDec = 0; + table->initialState.level.dpm2.AboveSafeInc = 0; + table->initialState.level.dpm2.BelowSafeInc = 0; + table->initialState.level.dpm2.PwrEfficiencyRatio = 0; reg = MIN_POWER_MASK | MAX_POWER_MASK; - table->initialState.levels[0].SQPowerThrottle = cpu_to_be32(reg); + table->initialState.level.SQPowerThrottle = cpu_to_be32(reg); reg = MAX_POWER_DELTA_MASK | STI_SIZE_MASK | LTI_RATIO_MASK; - table->initialState.levels[0].SQPowerThrottle_2 = cpu_to_be32(reg); + table->initialState.level.SQPowerThrottle_2 = cpu_to_be32(reg); return 0; } @@ -4488,18 +4491,18 @@ static int si_populate_smc_acpi_state(struct radeon_device *rdev, if (pi->acpi_vddc) { ret = si_populate_voltage_value(rdev, &eg_pi->vddc_voltage_table, - pi->acpi_vddc, &table->ACPIState.levels[0].vddc); + pi->acpi_vddc, &table->ACPIState.level.vddc); if (!ret) { u16 std_vddc; ret = si_get_std_voltage_value(rdev, - &table->ACPIState.levels[0].vddc, &std_vddc); + &table->ACPIState.level.vddc, &std_vddc); if (!ret) si_populate_std_voltage_value(rdev, std_vddc, - table->ACPIState.levels[0].vddc.index, - &table->ACPIState.levels[0].std_vddc); + table->ACPIState.level.vddc.index, + &table->ACPIState.level.std_vddc); } - table->ACPIState.levels[0].gen2PCIE = si_pi->acpi_pcie_gen; + table->ACPIState.level.gen2PCIE = si_pi->acpi_pcie_gen; if (si_pi->vddc_phase_shed_control) { si_populate_phase_shedding_value(rdev, @@ -4507,23 +4510,23 @@ static int si_populate_smc_acpi_state(struct radeon_device *rdev, pi->acpi_vddc, 0, 0, - &table->ACPIState.levels[0].vddc); + &table->ACPIState.level.vddc); } } else { ret = si_populate_voltage_value(rdev, &eg_pi->vddc_voltage_table, - pi->min_vddc_in_table, &table->ACPIState.levels[0].vddc); + pi->min_vddc_in_table, &table->ACPIState.level.vddc); if (!ret) { u16 std_vddc; ret = si_get_std_voltage_value(rdev, - &table->ACPIState.levels[0].vddc, &std_vddc); + &table->ACPIState.level.vddc, &std_vddc); if (!ret) si_populate_std_voltage_value(rdev, std_vddc, - table->ACPIState.levels[0].vddc.index, - &table->ACPIState.levels[0].std_vddc); + table->ACPIState.level.vddc.index, + &table->ACPIState.level.std_vddc); } - table->ACPIState.levels[0].gen2PCIE = (u8)r600_get_pcie_gen_support(rdev, + table->ACPIState.level.gen2PCIE = (u8)r600_get_pcie_gen_support(rdev, si_pi->sys_pcie_mask, si_pi->boot_pcie_gen, RADEON_PCIE_GEN1); @@ -4534,14 +4537,14 @@ static int si_populate_smc_acpi_state(struct radeon_device *rdev, pi->min_vddc_in_table, 0, 0, - &table->ACPIState.levels[0].vddc); + &table->ACPIState.level.vddc); } if (pi->acpi_vddc) { if (eg_pi->acpi_vddci) si_populate_voltage_value(rdev, &eg_pi->vddci_voltage_table, eg_pi->acpi_vddci, - &table->ACPIState.levels[0].vddci); + &table->ACPIState.level.vddci); } mclk_pwrmgt_cntl |= MRDCK0_RESET | MRDCK1_RESET; @@ -4552,59 +4555,59 @@ static int si_populate_smc_acpi_state(struct radeon_device *rdev, spll_func_cntl_2 &= ~SCLK_MUX_SEL_MASK; spll_func_cntl_2 |= SCLK_MUX_SEL(4); - table->ACPIState.levels[0].mclk.vDLL_CNTL = + table->ACPIState.level.mclk.vDLL_CNTL = cpu_to_be32(dll_cntl); - table->ACPIState.levels[0].mclk.vMCLK_PWRMGT_CNTL = + table->ACPIState.level.mclk.vMCLK_PWRMGT_CNTL = cpu_to_be32(mclk_pwrmgt_cntl); - table->ACPIState.levels[0].mclk.vMPLL_AD_FUNC_CNTL = + table->ACPIState.level.mclk.vMPLL_AD_FUNC_CNTL = cpu_to_be32(mpll_ad_func_cntl); - table->ACPIState.levels[0].mclk.vMPLL_DQ_FUNC_CNTL = + table->ACPIState.level.mclk.vMPLL_DQ_FUNC_CNTL = cpu_to_be32(mpll_dq_func_cntl); - table->ACPIState.levels[0].mclk.vMPLL_FUNC_CNTL = + table->ACPIState.level.mclk.vMPLL_FUNC_CNTL = cpu_to_be32(mpll_func_cntl); - table->ACPIState.levels[0].mclk.vMPLL_FUNC_CNTL_1 = + table->ACPIState.level.mclk.vMPLL_FUNC_CNTL_1 = cpu_to_be32(mpll_func_cntl_1); - table->ACPIState.levels[0].mclk.vMPLL_FUNC_CNTL_2 = + table->ACPIState.level.mclk.vMPLL_FUNC_CNTL_2 = cpu_to_be32(mpll_func_cntl_2); - table->ACPIState.levels[0].mclk.vMPLL_SS = + table->ACPIState.level.mclk.vMPLL_SS = cpu_to_be32(si_pi->clock_registers.mpll_ss1); - table->ACPIState.levels[0].mclk.vMPLL_SS2 = + table->ACPIState.level.mclk.vMPLL_SS2 = cpu_to_be32(si_pi->clock_registers.mpll_ss2); - table->ACPIState.levels[0].sclk.vCG_SPLL_FUNC_CNTL = + table->ACPIState.level.sclk.vCG_SPLL_FUNC_CNTL = cpu_to_be32(spll_func_cntl); - table->ACPIState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_2 = + table->ACPIState.level.sclk.vCG_SPLL_FUNC_CNTL_2 = cpu_to_be32(spll_func_cntl_2); - table->ACPIState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_3 = + table->ACPIState.level.sclk.vCG_SPLL_FUNC_CNTL_3 = cpu_to_be32(spll_func_cntl_3); - table->ACPIState.levels[0].sclk.vCG_SPLL_FUNC_CNTL_4 = + table->ACPIState.level.sclk.vCG_SPLL_FUNC_CNTL_4 = cpu_to_be32(spll_func_cntl_4); - table->ACPIState.levels[0].mclk.mclk_value = 0; - table->ACPIState.levels[0].sclk.sclk_value = 0; + table->ACPIState.level.mclk.mclk_value = 0; + table->ACPIState.level.sclk.sclk_value = 0; - si_populate_mvdd_value(rdev, 0, &table->ACPIState.levels[0].mvdd); + si_populate_mvdd_value(rdev, 0, &table->ACPIState.level.mvdd); if (eg_pi->dynamic_ac_timing) - table->ACPIState.levels[0].ACIndex = 0; + table->ACPIState.level.ACIndex = 0; - table->ACPIState.levels[0].dpm2.MaxPS = 0; - table->ACPIState.levels[0].dpm2.NearTDPDec = 0; - table->ACPIState.levels[0].dpm2.AboveSafeInc = 0; - table->ACPIState.levels[0].dpm2.BelowSafeInc = 0; - table->ACPIState.levels[0].dpm2.PwrEfficiencyRatio = 0; + table->ACPIState.level.dpm2.MaxPS = 0; + table->ACPIState.level.dpm2.NearTDPDec = 0; + table->ACPIState.level.dpm2.AboveSafeInc = 0; + table->ACPIState.level.dpm2.BelowSafeInc = 0; + table->ACPIState.level.dpm2.PwrEfficiencyRatio = 0; reg = MIN_POWER_MASK | MAX_POWER_MASK; - table->ACPIState.levels[0].SQPowerThrottle = cpu_to_be32(reg); + table->ACPIState.level.SQPowerThrottle = cpu_to_be32(reg); reg = MAX_POWER_DELTA_MASK | STI_SIZE_MASK | LTI_RATIO_MASK; - table->ACPIState.levels[0].SQPowerThrottle_2 = cpu_to_be32(reg); + table->ACPIState.level.SQPowerThrottle_2 = cpu_to_be32(reg); return 0; } static int si_populate_ulv_state(struct radeon_device *rdev, - SISLANDS_SMC_SWSTATE *state) + struct SISLANDS_SMC_SWSTATE_SINGLE *state) { struct evergreen_power_info *eg_pi = evergreen_get_pi(rdev); struct si_power_info *si_pi = si_get_pi(rdev); @@ -4613,19 +4616,19 @@ static int si_populate_ulv_state(struct radeon_device *rdev, int ret; ret = si_convert_power_level_to_smc(rdev, &ulv->pl, - &state->levels[0]); + &state->level); if (!ret) { if (eg_pi->sclk_deep_sleep) { if (sclk_in_sr <= SCLK_MIN_DEEPSLEEP_FREQ) - state->levels[0].stateFlags |= PPSMC_STATEFLAG_DEEPSLEEP_BYPASS; + state->level.stateFlags |= PPSMC_STATEFLAG_DEEPSLEEP_BYPASS; else - state->levels[0].stateFlags |= PPSMC_STATEFLAG_DEEPSLEEP_THROTTLE; + state->level.stateFlags |= PPSMC_STATEFLAG_DEEPSLEEP_THROTTLE; } if (ulv->one_pcie_lane_in_ulv) state->flags |= PPSMC_SWSTATE_FLAG_PCIE_X1; - state->levels[0].arbRefreshState = (u8)(SISLANDS_ULV_STATE_ARB_INDEX); - state->levels[0].ACIndex = 1; - state->levels[0].std_vddc = state->levels[0].vddc; + state->level.arbRefreshState = (u8)(SISLANDS_ULV_STATE_ARB_INDEX); + state->level.ACIndex = 1; + state->level.std_vddc = state->level.vddc; state->levelCount = 1; state->flags |= PPSMC_SWSTATE_FLAG_DC; @@ -4725,7 +4728,9 @@ static int si_init_smc_table(struct radeon_device *rdev) if (ret) return ret; - table->driverState = table->initialState; + table->driverState.flags = table->initialState.flags; + table->driverState.levelCount = table->initialState.levelCount; + table->driverState.levels[0] = table->initialState.level; ret = si_do_program_memory_timing_parameters(rdev, radeon_boot_state, SISLANDS_INITIAL_STATE_ARB_INDEX); @@ -5275,8 +5280,8 @@ static int si_upload_ulv_state(struct radeon_device *rdev) if (ulv->supported && ulv->pl.vddc) { u32 address = si_pi->state_table_start + offsetof(SISLANDS_SMC_STATETABLE, ULVState); - SISLANDS_SMC_SWSTATE *smc_state = &si_pi->smc_statetable.ULVState; - u32 state_size = sizeof(SISLANDS_SMC_SWSTATE); + struct SISLANDS_SMC_SWSTATE_SINGLE *smc_state = &si_pi->smc_statetable.ULVState; + u32 state_size = sizeof(struct SISLANDS_SMC_SWSTATE_SINGLE); memset(smc_state, 0, state_size); diff --git a/drivers/gpu/drm/radeon/sislands_smc.h b/drivers/gpu/drm/radeon/sislands_smc.h index fbd6589bdab9..4ea1cb2e45a3 100644 --- a/drivers/gpu/drm/radeon/sislands_smc.h +++ b/drivers/gpu/drm/radeon/sislands_smc.h @@ -191,6 +191,14 @@ struct SISLANDS_SMC_SWSTATE typedef struct SISLANDS_SMC_SWSTATE SISLANDS_SMC_SWSTATE; +struct SISLANDS_SMC_SWSTATE_SINGLE { + uint8_t flags; + uint8_t levelCount; + uint8_t padding2; + uint8_t padding3; + SISLANDS_SMC_HW_PERFORMANCE_LEVEL level; +}; + #define SISLANDS_SMC_VOLTAGEMASK_VDDC 0 #define SISLANDS_SMC_VOLTAGEMASK_MVDD 1 #define SISLANDS_SMC_VOLTAGEMASK_VDDCI 2 @@ -208,19 +216,19 @@ typedef struct SISLANDS_SMC_VOLTAGEMASKTABLE SISLANDS_SMC_VOLTAGEMASKTABLE; struct SISLANDS_SMC_STATETABLE { - uint8_t thermalProtectType; - uint8_t systemFlags; - uint8_t maxVDDCIndexInPPTable; - uint8_t extraFlags; - uint32_t lowSMIO[SISLANDS_MAX_NO_VREG_STEPS]; - SISLANDS_SMC_VOLTAGEMASKTABLE voltageMaskTable; - SISLANDS_SMC_VOLTAGEMASKTABLE phaseMaskTable; - PP_SIslands_DPM2Parameters dpm2Params; - SISLANDS_SMC_SWSTATE initialState; - SISLANDS_SMC_SWSTATE ACPIState; - SISLANDS_SMC_SWSTATE ULVState; - SISLANDS_SMC_SWSTATE driverState; - SISLANDS_SMC_HW_PERFORMANCE_LEVEL dpmLevels[SISLANDS_MAX_SMC_PERFORMANCE_LEVELS_PER_SWSTATE - 1]; + uint8_t thermalProtectType; + uint8_t systemFlags; + uint8_t maxVDDCIndexInPPTable; + uint8_t extraFlags; + uint32_t lowSMIO[SISLANDS_MAX_NO_VREG_STEPS]; + SISLANDS_SMC_VOLTAGEMASKTABLE voltageMaskTable; + SISLANDS_SMC_VOLTAGEMASKTABLE phaseMaskTable; + PP_SIslands_DPM2Parameters dpm2Params; + struct SISLANDS_SMC_SWSTATE_SINGLE initialState; + struct SISLANDS_SMC_SWSTATE_SINGLE ACPIState; + struct SISLANDS_SMC_SWSTATE_SINGLE ULVState; + SISLANDS_SMC_SWSTATE driverState; + SISLANDS_SMC_HW_PERFORMANCE_LEVEL dpmLevels[SISLANDS_MAX_SMC_PERFORMANCE_LEVELS_PER_SWSTATE]; }; typedef struct SISLANDS_SMC_STATETABLE SISLANDS_SMC_STATETABLE; diff --git a/drivers/gpu/drm/vc4/vc4_vec.c b/drivers/gpu/drm/vc4/vc4_vec.c index bd5b8eb58b18..090529d0d5dc 100644 --- a/drivers/gpu/drm/vc4/vc4_vec.c +++ b/drivers/gpu/drm/vc4/vc4_vec.c @@ -197,12 +197,6 @@ struct vc4_vec_connector { struct drm_encoder *encoder; }; -static inline struct vc4_vec_connector * -to_vc4_vec_connector(struct drm_connector *connector) -{ - return container_of(connector, struct vc4_vec_connector, base); -} - enum vc4_vec_tv_mode_id { VC4_VEC_TV_MODE_NTSC, VC4_VEC_TV_MODE_NTSC_J, diff --git a/drivers/hwmon/adm9240.c b/drivers/hwmon/adm9240.c index 5677263bcf0d..483cd757abd3 100644 --- a/drivers/hwmon/adm9240.c +++ b/drivers/hwmon/adm9240.c @@ -485,7 +485,7 @@ static int adm9240_in_write(struct device *dev, u32 attr, int channel, long val) reg = ADM9240_REG_IN_MIN(channel); break; case hwmon_in_max: - reg = ADM9240_REG_IN(channel); + reg = ADM9240_REG_IN_MAX(channel); break; default: return -EOPNOTSUPP; diff --git a/drivers/hwmon/corsair-psu.c b/drivers/hwmon/corsair-psu.c index 3a5807e4a2ef..02298b86b57b 100644 --- a/drivers/hwmon/corsair-psu.c +++ b/drivers/hwmon/corsair-psu.c @@ -355,7 +355,7 @@ static umode_t corsairpsu_hwmon_power_is_visible(const struct corsairpsu_data *p return 0444; default: return 0; - }; + } } static umode_t corsairpsu_hwmon_in_is_visible(const struct corsairpsu_data *priv, u32 attr, @@ -376,7 +376,7 @@ static umode_t corsairpsu_hwmon_in_is_visible(const struct corsairpsu_data *priv break; default: break; - }; + } return res; } diff --git a/drivers/hwmon/ltc2992.c b/drivers/hwmon/ltc2992.c index 4382105bf142..2a4bed0ab226 100644 --- a/drivers/hwmon/ltc2992.c +++ b/drivers/hwmon/ltc2992.c @@ -900,11 +900,15 @@ static int ltc2992_parse_dt(struct ltc2992_state *st) fwnode_for_each_available_child_node(fwnode, child) { ret = fwnode_property_read_u32(child, "reg", &addr); - if (ret < 0) + if (ret < 0) { + fwnode_handle_put(child); return ret; + } - if (addr > 1) + if (addr > 1) { + fwnode_handle_put(child); return -EINVAL; + } ret = fwnode_property_read_u32(child, "shunt-resistor-micro-ohms", &val); if (!ret) diff --git a/drivers/hwmon/occ/common.c b/drivers/hwmon/occ/common.c index f1ac153d0b56..967532afb1c0 100644 --- a/drivers/hwmon/occ/common.c +++ b/drivers/hwmon/occ/common.c @@ -217,9 +217,9 @@ int occ_update_response(struct occ *occ) return rc; /* limit the maximum rate of polling the OCC */ - if (time_after(jiffies, occ->last_update + OCC_UPDATE_FREQUENCY)) { + if (time_after(jiffies, occ->next_update)) { rc = occ_poll(occ); - occ->last_update = jiffies; + occ->next_update = jiffies + OCC_UPDATE_FREQUENCY; } else { rc = occ->last_error; } @@ -1165,6 +1165,7 @@ int occ_setup(struct occ *occ, const char *name) return rc; } + occ->next_update = jiffies + OCC_UPDATE_FREQUENCY; occ_parse_poll_response(occ); rc = occ_setup_sensor_attrs(occ); diff --git a/drivers/hwmon/occ/common.h b/drivers/hwmon/occ/common.h index 67e6968b8978..e6df719770e8 100644 --- a/drivers/hwmon/occ/common.h +++ b/drivers/hwmon/occ/common.h @@ -99,7 +99,7 @@ struct occ { u8 poll_cmd_data; /* to perform OCC poll command */ int (*send_cmd)(struct occ *occ, u8 *cmd); - unsigned long last_update; + unsigned long next_update; struct mutex lock; /* lock OCC access */ struct device *hwmon; diff --git a/drivers/hwmon/pmbus/fsp-3y.c b/drivers/hwmon/pmbus/fsp-3y.c index b177987286ae..e24842475254 100644 --- a/drivers/hwmon/pmbus/fsp-3y.c +++ b/drivers/hwmon/pmbus/fsp-3y.c @@ -57,7 +57,7 @@ static int page_log_to_page_real(int page_log, enum chips chip) case YH5151E_PAGE_12V_LOG: return YH5151E_PAGE_12V_REAL; case YH5151E_PAGE_5V_LOG: - return YH5151E_PAGE_5V_LOG; + return YH5151E_PAGE_5V_REAL; case YH5151E_PAGE_3V3_LOG: return YH5151E_PAGE_3V3_REAL; } @@ -103,8 +103,18 @@ static int set_page(struct i2c_client *client, int page_log) static int fsp3y_read_byte_data(struct i2c_client *client, int page, int reg) { + const struct pmbus_driver_info *info = pmbus_get_driver_info(client); + struct fsp3y_data *data = to_fsp3y_data(info); int rv; + /* + * YH5151-E outputs vout in linear11. The conversion is done when + * reading. Here, we have to inject pmbus_core with the correct + * exponent (it is -6). + */ + if (data->chip == yh5151e && reg == PMBUS_VOUT_MODE) + return 0x1A; + rv = set_page(client, page); if (rv < 0) return rv; @@ -114,6 +124,8 @@ static int fsp3y_read_byte_data(struct i2c_client *client, int page, int reg) static int fsp3y_read_word_data(struct i2c_client *client, int page, int phase, int reg) { + const struct pmbus_driver_info *info = pmbus_get_driver_info(client); + struct fsp3y_data *data = to_fsp3y_data(info); int rv; /* @@ -144,7 +156,18 @@ static int fsp3y_read_word_data(struct i2c_client *client, int page, int phase, if (rv < 0) return rv; - return i2c_smbus_read_word_data(client, reg); + rv = i2c_smbus_read_word_data(client, reg); + if (rv < 0) + return rv; + + /* + * YH-5151E is non-compliant and outputs output voltages in linear11 + * instead of linear16. + */ + if (data->chip == yh5151e && reg == PMBUS_READ_VOUT) + rv = sign_extend32(rv, 10) & 0xffff; + + return rv; } static struct pmbus_driver_info fsp3y_info[] = { diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 522c9b229f80..762125f2905f 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2901,7 +2901,7 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl) ctrl->hmmaxd = le16_to_cpu(id->hmmaxd); } - ret = nvme_mpath_init(ctrl, id); + ret = nvme_mpath_init_identify(ctrl, id); if (ret < 0) goto out_free; @@ -4364,6 +4364,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, min(default_ps_max_latency_us, (unsigned long)S32_MAX)); nvme_fault_inject_init(&ctrl->fault_inject, dev_name(ctrl->device)); + nvme_mpath_init_ctrl(ctrl); return 0; out_free_name: diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 0551796517e6..f81871c7128a 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -781,9 +781,18 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head) put_disk(head->disk); } -int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) +void nvme_mpath_init_ctrl(struct nvme_ctrl *ctrl) { - int error; + mutex_init(&ctrl->ana_lock); + timer_setup(&ctrl->anatt_timer, nvme_anatt_timeout, 0); + INIT_WORK(&ctrl->ana_work, nvme_ana_work); +} + +int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) +{ + size_t max_transfer_size = ctrl->max_hw_sectors << SECTOR_SHIFT; + size_t ana_log_size; + int error = 0; /* check if multipath is enabled and we have the capability */ if (!multipath || !ctrl->subsys || @@ -795,37 +804,31 @@ int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) ctrl->nanagrpid = le32_to_cpu(id->nanagrpid); ctrl->anagrpmax = le32_to_cpu(id->anagrpmax); - mutex_init(&ctrl->ana_lock); - timer_setup(&ctrl->anatt_timer, nvme_anatt_timeout, 0); - ctrl->ana_log_size = sizeof(struct nvme_ana_rsp_hdr) + - ctrl->nanagrpid * sizeof(struct nvme_ana_group_desc); - ctrl->ana_log_size += ctrl->max_namespaces * sizeof(__le32); - - if (ctrl->ana_log_size > ctrl->max_hw_sectors << SECTOR_SHIFT) { + ana_log_size = sizeof(struct nvme_ana_rsp_hdr) + + ctrl->nanagrpid * sizeof(struct nvme_ana_group_desc) + + ctrl->max_namespaces * sizeof(__le32); + if (ana_log_size > max_transfer_size) { dev_err(ctrl->device, - "ANA log page size (%zd) larger than MDTS (%d).\n", - ctrl->ana_log_size, - ctrl->max_hw_sectors << SECTOR_SHIFT); + "ANA log page size (%zd) larger than MDTS (%zd).\n", + ana_log_size, max_transfer_size); dev_err(ctrl->device, "disabling ANA support.\n"); - return 0; + goto out_uninit; } - - INIT_WORK(&ctrl->ana_work, nvme_ana_work); - kfree(ctrl->ana_log_buf); - ctrl->ana_log_buf = kmalloc(ctrl->ana_log_size, GFP_KERNEL); - if (!ctrl->ana_log_buf) { - error = -ENOMEM; - goto out; + if (ana_log_size > ctrl->ana_log_size) { + nvme_mpath_stop(ctrl); + kfree(ctrl->ana_log_buf); + ctrl->ana_log_buf = kmalloc(ana_log_size, GFP_KERNEL); + if (!ctrl->ana_log_buf) + return -ENOMEM; } - + ctrl->ana_log_size = ana_log_size; error = nvme_read_ana_log(ctrl); if (error) - goto out_free_ana_log_buf; + goto out_uninit; return 0; -out_free_ana_log_buf: - kfree(ctrl->ana_log_buf); - ctrl->ana_log_buf = NULL; -out: + +out_uninit: + nvme_mpath_uninit(ctrl); return error; } diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 05f31a2c64bb..0015860ec12b 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -712,7 +712,8 @@ void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl); int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head); void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id); void nvme_mpath_remove_disk(struct nvme_ns_head *head); -int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id); +int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id); +void nvme_mpath_init_ctrl(struct nvme_ctrl *ctrl); void nvme_mpath_uninit(struct nvme_ctrl *ctrl); void nvme_mpath_stop(struct nvme_ctrl *ctrl); bool nvme_mpath_clear_current_path(struct nvme_ns *ns); @@ -780,7 +781,10 @@ static inline void nvme_mpath_check_last_path(struct nvme_ns *ns) static inline void nvme_trace_bio_complete(struct request *req) { } -static inline int nvme_mpath_init(struct nvme_ctrl *ctrl, +static inline void nvme_mpath_init_ctrl(struct nvme_ctrl *ctrl) +{ +} +static inline int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) { if (ctrl->subsys->cmic & NVME_CTRL_CMIC_ANA) diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index e7a367cf6d36..dcd49a72f2f3 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -975,10 +975,7 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req) case nvme_admin_keep_alive: req->execute = nvmet_execute_keep_alive; return 0; + default: + return nvmet_report_invalid_opcode(req); } - - pr_debug("unhandled cmd %d on qid %d\n", cmd->common.opcode, - req->sq->qid); - req->error_loc = offsetof(struct nvme_common_command, opcode); - return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; } diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c index 4845d12e374a..fc3645fc2c24 100644 --- a/drivers/nvme/target/discovery.c +++ b/drivers/nvme/target/discovery.c @@ -379,7 +379,7 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req) req->execute = nvmet_execute_disc_identify; return 0; default: - pr_err("unhandled cmd %d\n", cmd->common.opcode); + pr_debug("unhandled cmd %d\n", cmd->common.opcode); req->error_loc = offsetof(struct nvme_common_command, opcode); return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; } diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index 1420a8e3e0b1..7d0f3523fdab 100644 --- a/drivers/nvme/target/fabrics-cmd.c +++ b/drivers/nvme/target/fabrics-cmd.c @@ -94,7 +94,7 @@ u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req) req->execute = nvmet_execute_prop_get; break; default: - pr_err("received unknown capsule type 0x%x\n", + pr_debug("received unknown capsule type 0x%x\n", cmd->fabrics.fctype); req->error_loc = offsetof(struct nvmf_common_command, fctype); return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; @@ -284,13 +284,13 @@ u16 nvmet_parse_connect_cmd(struct nvmet_req *req) struct nvme_command *cmd = req->cmd; if (!nvme_is_fabrics(cmd)) { - pr_err("invalid command 0x%x on unconnected queue.\n", + pr_debug("invalid command 0x%x on unconnected queue.\n", cmd->fabrics.opcode); req->error_loc = offsetof(struct nvme_common_command, opcode); return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; } if (cmd->fabrics.fctype != nvme_fabrics_type_connect) { - pr_err("invalid capsule type 0x%x on unconnected queue.\n", + pr_debug("invalid capsule type 0x%x on unconnected queue.\n", cmd->fabrics.fctype); req->error_loc = offsetof(struct nvmf_common_command, fctype); return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index 9a8b3726a37c..429263ca9b97 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -258,7 +258,7 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req) sector = nvmet_lba_to_sect(req->ns, req->cmd->rw.slba); - if (req->transfer_len <= NVMET_MAX_INLINE_DATA_LEN) { + if (nvmet_use_inline_bvec(req)) { bio = &req->b.inline_bio; bio_init(bio, req->inline_bvec, ARRAY_SIZE(req->inline_bvec)); } else { diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c index 715d4376c997..7fdbdc496597 100644 --- a/drivers/nvme/target/io-cmd-file.c +++ b/drivers/nvme/target/io-cmd-file.c @@ -49,9 +49,11 @@ int nvmet_file_ns_enable(struct nvmet_ns *ns) ns->file = filp_open(ns->device_path, flags, 0); if (IS_ERR(ns->file)) { - pr_err("failed to open file %s: (%ld)\n", - ns->device_path, PTR_ERR(ns->file)); - return PTR_ERR(ns->file); + ret = PTR_ERR(ns->file); + pr_err("failed to open file %s: (%d)\n", + ns->device_path, ret); + ns->file = NULL; + return ret; } ret = nvmet_file_ns_revalidate(ns); diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 5566ed403576..d69a409515d6 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -616,4 +616,10 @@ static inline sector_t nvmet_lba_to_sect(struct nvmet_ns *ns, __le64 lba) return le64_to_cpu(lba) << (ns->blksize_shift - SECTOR_SHIFT); } +static inline bool nvmet_use_inline_bvec(struct nvmet_req *req) +{ + return req->transfer_len <= NVMET_MAX_INLINE_DATA_LEN && + req->sg_cnt <= NVMET_MAX_INLINE_BIOVEC; +} + #endif /* _NVMET_H */ diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index 2798944899b7..39b1473f7204 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -194,7 +194,7 @@ static int nvmet_passthru_map_sg(struct nvmet_req *req, struct request *rq) if (req->sg_cnt > BIO_MAX_VECS) return -EINVAL; - if (req->transfer_len <= NVMET_MAX_INLINE_DATA_LEN) { + if (nvmet_use_inline_bvec(req)) { bio = &req->p.inline_bio; bio_init(bio, req->inline_bvec, ARRAY_SIZE(req->inline_bvec)); } else { diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 6c1f3ab7649c..7d607f435e36 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -700,7 +700,7 @@ static void nvmet_rdma_send_done(struct ib_cq *cq, struct ib_wc *wc) { struct nvmet_rdma_rsp *rsp = container_of(wc->wr_cqe, struct nvmet_rdma_rsp, send_cqe); - struct nvmet_rdma_queue *queue = cq->cq_context; + struct nvmet_rdma_queue *queue = wc->qp->qp_context; nvmet_rdma_release_rsp(rsp); @@ -786,7 +786,7 @@ static void nvmet_rdma_write_data_done(struct ib_cq *cq, struct ib_wc *wc) { struct nvmet_rdma_rsp *rsp = container_of(wc->wr_cqe, struct nvmet_rdma_rsp, write_cqe); - struct nvmet_rdma_queue *queue = cq->cq_context; + struct nvmet_rdma_queue *queue = wc->qp->qp_context; struct rdma_cm_id *cm_id = rsp->queue->cm_id; u16 status; diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 01645e87b3d5..fa1548d4f94b 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -1171,7 +1171,7 @@ static inline int resize_screen(struct vc_data *vc, int width, int height, /* Resizes the resolution of the display adapater */ int err = 0; - if (vc->vc_mode != KD_GRAPHICS && vc->vc_sw->con_resize) + if (vc->vc_sw->con_resize) err = vc->vc_sw->con_resize(vc, width, height, user); return err; diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c index 89aeaf3c1bca..0e0cd9e9e589 100644 --- a/drivers/tty/vt/vt_ioctl.c +++ b/drivers/tty/vt/vt_ioctl.c @@ -671,21 +671,58 @@ static int vt_resizex(struct vc_data *vc, struct vt_consize __user *cs) if (copy_from_user(&v, cs, sizeof(struct vt_consize))) return -EFAULT; - if (v.v_vlin) - pr_info_once("\"struct vt_consize\"->v_vlin is ignored. Please report if you need this.\n"); - if (v.v_clin) - pr_info_once("\"struct vt_consize\"->v_clin is ignored. Please report if you need this.\n"); + /* FIXME: Should check the copies properly */ + if (!v.v_vlin) + v.v_vlin = vc->vc_scan_lines; + + if (v.v_clin) { + int rows = v.v_vlin / v.v_clin; + if (v.v_rows != rows) { + if (v.v_rows) /* Parameters don't add up */ + return -EINVAL; + v.v_rows = rows; + } + } + + if (v.v_vcol && v.v_ccol) { + int cols = v.v_vcol / v.v_ccol; + if (v.v_cols != cols) { + if (v.v_cols) + return -EINVAL; + v.v_cols = cols; + } + } + + if (v.v_clin > 32) + return -EINVAL; - console_lock(); for (i = 0; i < MAX_NR_CONSOLES; i++) { - vc = vc_cons[i].d; + struct vc_data *vcp; - if (vc) { - vc->vc_resize_user = 1; - vc_resize(vc, v.v_cols, v.v_rows); + if (!vc_cons[i].d) + continue; + console_lock(); + vcp = vc_cons[i].d; + if (vcp) { + int ret; + int save_scan_lines = vcp->vc_scan_lines; + int save_cell_height = vcp->vc_cell_height; + + if (v.v_vlin) + vcp->vc_scan_lines = v.v_vlin; + if (v.v_clin) + vcp->vc_cell_height = v.v_clin; + vcp->vc_resize_user = 1; + ret = vc_resize(vcp, v.v_cols, v.v_rows); + if (ret) { + vcp->vc_scan_lines = save_scan_lines; + vcp->vc_cell_height = save_cell_height; + console_unlock(); + return ret; + } } + console_unlock(); } - console_unlock(); return 0; } diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c index 39258f9d36a0..ef9c57ce0906 100644 --- a/drivers/video/console/vgacon.c +++ b/drivers/video/console/vgacon.c @@ -380,7 +380,7 @@ static void vgacon_init(struct vc_data *c, int init) vc_resize(c, vga_video_num_columns, vga_video_num_lines); c->vc_scan_lines = vga_scan_lines; - c->vc_font.height = vga_video_font_height; + c->vc_font.height = c->vc_cell_height = vga_video_font_height; c->vc_complement_mask = 0x7700; if (vga_512_chars) c->vc_hi_font_mask = 0x0800; @@ -515,32 +515,32 @@ static void vgacon_cursor(struct vc_data *c, int mode) switch (CUR_SIZE(c->vc_cursor_type)) { case CUR_UNDERLINE: vgacon_set_cursor_size(c->state.x, - c->vc_font.height - - (c->vc_font.height < + c->vc_cell_height - + (c->vc_cell_height < 10 ? 2 : 3), - c->vc_font.height - - (c->vc_font.height < + c->vc_cell_height - + (c->vc_cell_height < 10 ? 1 : 2)); break; case CUR_TWO_THIRDS: vgacon_set_cursor_size(c->state.x, - c->vc_font.height / 3, - c->vc_font.height - - (c->vc_font.height < + c->vc_cell_height / 3, + c->vc_cell_height - + (c->vc_cell_height < 10 ? 1 : 2)); break; case CUR_LOWER_THIRD: vgacon_set_cursor_size(c->state.x, - (c->vc_font.height * 2) / 3, - c->vc_font.height - - (c->vc_font.height < + (c->vc_cell_height * 2) / 3, + c->vc_cell_height - + (c->vc_cell_height < 10 ? 1 : 2)); break; case CUR_LOWER_HALF: vgacon_set_cursor_size(c->state.x, - c->vc_font.height / 2, - c->vc_font.height - - (c->vc_font.height < + c->vc_cell_height / 2, + c->vc_cell_height - + (c->vc_cell_height < 10 ? 1 : 2)); break; case CUR_NONE: @@ -551,7 +551,7 @@ static void vgacon_cursor(struct vc_data *c, int mode) break; default: vgacon_set_cursor_size(c->state.x, 1, - c->vc_font.height); + c->vc_cell_height); break; } break; @@ -562,13 +562,13 @@ static int vgacon_doresize(struct vc_data *c, unsigned int width, unsigned int height) { unsigned long flags; - unsigned int scanlines = height * c->vc_font.height; + unsigned int scanlines = height * c->vc_cell_height; u8 scanlines_lo = 0, r7 = 0, vsync_end = 0, mode, max_scan; raw_spin_lock_irqsave(&vga_lock, flags); vgacon_xres = width * VGA_FONTWIDTH; - vgacon_yres = height * c->vc_font.height; + vgacon_yres = height * c->vc_cell_height; if (vga_video_type >= VIDEO_TYPE_VGAC) { outb_p(VGA_CRTC_MAX_SCAN, vga_video_port_reg); max_scan = inb_p(vga_video_port_val); @@ -623,9 +623,9 @@ static int vgacon_doresize(struct vc_data *c, static int vgacon_switch(struct vc_data *c) { int x = c->vc_cols * VGA_FONTWIDTH; - int y = c->vc_rows * c->vc_font.height; + int y = c->vc_rows * c->vc_cell_height; int rows = screen_info.orig_video_lines * vga_default_font_height/ - c->vc_font.height; + c->vc_cell_height; /* * We need to save screen size here as it's the only way * we can spot the screen has been resized and we need to @@ -1038,7 +1038,7 @@ static int vgacon_adjust_height(struct vc_data *vc, unsigned fontheight) cursor_size_lastto = 0; c->vc_sw->con_cursor(c, CM_DRAW); } - c->vc_font.height = fontheight; + c->vc_font.height = c->vc_cell_height = fontheight; vc_resize(c, 0, rows); /* Adjust console size */ } } @@ -1086,12 +1086,20 @@ static int vgacon_resize(struct vc_data *c, unsigned int width, if ((width << 1) * height > vga_vram_size) return -EINVAL; + if (user) { + /* + * Ho ho! Someone (svgatextmode, eh?) may have reprogrammed + * the video mode! Set the new defaults then and go away. + */ + screen_info.orig_video_cols = width; + screen_info.orig_video_lines = height; + vga_default_font_height = c->vc_cell_height; + return 0; + } if (width % 2 || width > screen_info.orig_video_cols || height > (screen_info.orig_video_lines * vga_default_font_height)/ - c->vc_font.height) - /* let svgatextmode tinker with video timings and - return success */ - return (user) ? 0 : -EINVAL; + c->vc_cell_height) + return -EINVAL; if (con_is_visible(c) && !vga_is_gfx) /* who knows */ vgacon_doresize(c, width, height); diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 3406067985b1..22bb3892f6bd 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -2019,7 +2019,7 @@ static int fbcon_resize(struct vc_data *vc, unsigned int width, return -EINVAL; pr_debug("resize now %ix%i\n", var.xres, var.yres); - if (con_is_visible(vc)) { + if (con_is_visible(vc) && vc->vc_mode == KD_TEXT) { var.activate = FB_ACTIVATE_NOW | FB_ACTIVATE_FORCE; fb_set_var(info, &var); diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index f01d58c7a042..a3e7be96527d 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -1017,8 +1017,10 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) err = mmu_interval_notifier_insert_locked( &map->notifier, vma->vm_mm, vma->vm_start, vma->vm_end - vma->vm_start, &gntdev_mmu_ops); - if (err) + if (err) { + map->vma = NULL; goto out_unlock_put; + } } mutex_unlock(&priv->lock); diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 4c89afc0df62..24d11861ac7d 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -164,6 +164,11 @@ int __ref xen_swiotlb_init(void) int rc = -ENOMEM; char *start; + if (io_tlb_default_mem != NULL) { + pr_warn("swiotlb buffer already initialized\n"); + return -EEXIST; + } + retry: m_ret = XEN_SWIOTLB_ENOMEM; order = get_order(bytes); diff --git a/drivers/xen/unpopulated-alloc.c b/drivers/xen/unpopulated-alloc.c index e64e6befc63b..87e6b7db892f 100644 --- a/drivers/xen/unpopulated-alloc.c +++ b/drivers/xen/unpopulated-alloc.c @@ -39,8 +39,10 @@ static int fill_list(unsigned int nr_pages) } pgmap = kzalloc(sizeof(*pgmap), GFP_KERNEL); - if (!pgmap) + if (!pgmap) { + ret = -ENOMEM; goto err_pgmap; + } pgmap->type = MEMORY_DEVICE_GENERIC; pgmap->range = (struct range) { diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index f83fd3cbf243..9fb76829a281 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3127,7 +3127,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, u64 new_size, u32 min_type); -int btrfs_start_delalloc_snapshot(struct btrfs_root *root); +int btrfs_start_delalloc_snapshot(struct btrfs_root *root, bool in_reclaim_context); int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr, bool in_reclaim_context); int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end, diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 7a28314189b4..f1d15b68994a 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1340,12 +1340,16 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr, stripe = bbio->stripes; for (i = 0; i < bbio->num_stripes; i++, stripe++) { u64 bytes; + struct btrfs_device *device = stripe->dev; - if (!stripe->dev->bdev) { + if (!device->bdev) { ASSERT(btrfs_test_opt(fs_info, DEGRADED)); continue; } + if (!test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) + continue; + ret = do_discard_extent(stripe, &bytes); if (!ret) { discarded_bytes += bytes; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 864c08d08a35..3b10d98b4ebb 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2067,6 +2067,30 @@ static int start_ordered_ops(struct inode *inode, loff_t start, loff_t end) return ret; } +static inline bool skip_inode_logging(const struct btrfs_log_ctx *ctx) +{ + struct btrfs_inode *inode = BTRFS_I(ctx->inode); + struct btrfs_fs_info *fs_info = inode->root->fs_info; + + if (btrfs_inode_in_log(inode, fs_info->generation) && + list_empty(&ctx->ordered_extents)) + return true; + + /* + * If we are doing a fast fsync we can not bail out if the inode's + * last_trans is <= then the last committed transaction, because we only + * update the last_trans of the inode during ordered extent completion, + * and for a fast fsync we don't wait for that, we only wait for the + * writeback to complete. + */ + if (inode->last_trans <= fs_info->last_trans_committed && + (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags) || + list_empty(&ctx->ordered_extents))) + return true; + + return false; +} + /* * fsync call for both files and directories. This logs the inode into * the tree log instead of forcing full commits whenever possible. @@ -2185,17 +2209,8 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) atomic_inc(&root->log_batch); - /* - * If we are doing a fast fsync we can not bail out if the inode's - * last_trans is <= then the last committed transaction, because we only - * update the last_trans of the inode during ordered extent completion, - * and for a fast fsync we don't wait for that, we only wait for the - * writeback to complete. - */ smp_mb(); - if (btrfs_inode_in_log(BTRFS_I(inode), fs_info->generation) || - (BTRFS_I(inode)->last_trans <= fs_info->last_trans_committed && - (full_sync || list_empty(&ctx.ordered_extents)))) { + if (skip_inode_logging(&ctx)) { /* * We've had everything committed since the last time we were * modified so clear this flag in case it was set for whatever diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index e54466fc101f..4806295116d8 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -3949,7 +3949,7 @@ static int cleanup_free_space_cache_v1(struct btrfs_fs_info *fs_info, { struct btrfs_block_group *block_group; struct rb_node *node; - int ret; + int ret = 0; btrfs_info(fs_info, "cleaning free space cache v1"); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 4af336008b12..eb6fddf40841 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9678,7 +9678,7 @@ out: return ret; } -int btrfs_start_delalloc_snapshot(struct btrfs_root *root) +int btrfs_start_delalloc_snapshot(struct btrfs_root *root, bool in_reclaim_context) { struct writeback_control wbc = { .nr_to_write = LONG_MAX, @@ -9691,7 +9691,7 @@ int btrfs_start_delalloc_snapshot(struct btrfs_root *root) if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) return -EROFS; - return start_delalloc_inodes(root, &wbc, true, false); + return start_delalloc_inodes(root, &wbc, true, in_reclaim_context); } int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index ee1dbabb5d3c..5dc2fd843ae3 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -259,6 +259,8 @@ int btrfs_fileattr_set(struct user_namespace *mnt_userns, if (!fa->flags_valid) { /* 1 item for the inode */ trans = btrfs_start_transaction(root, 1); + if (IS_ERR(trans)) + return PTR_ERR(trans); goto update_flags; } @@ -907,7 +909,7 @@ static noinline int btrfs_mksnapshot(const struct path *parent, */ btrfs_drew_read_lock(&root->snapshot_lock); - ret = btrfs_start_delalloc_snapshot(root); + ret = btrfs_start_delalloc_snapshot(root, false); if (ret) goto out; diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 07b0b4218791..6c413bb451a3 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -984,7 +984,7 @@ int btrfs_split_ordered_extent(struct btrfs_ordered_extent *ordered, u64 pre, if (pre) ret = clone_ordered_extent(ordered, 0, pre); - if (post) + if (ret == 0 && post) ret = clone_ordered_extent(ordered, pre + ordered->disk_num_bytes, post); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 2319c923c9e6..3ded812f522c 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -3545,11 +3545,15 @@ static int try_flush_qgroup(struct btrfs_root *root) struct btrfs_trans_handle *trans; int ret; - /* Can't hold an open transaction or we run the risk of deadlocking */ - ASSERT(current->journal_info == NULL || - current->journal_info == BTRFS_SEND_TRANS_STUB); - if (WARN_ON(current->journal_info && - current->journal_info != BTRFS_SEND_TRANS_STUB)) + /* + * Can't hold an open transaction or we run the risk of deadlocking, + * and can't either be under the context of a send operation (where + * current->journal_info is set to BTRFS_SEND_TRANS_STUB), as that + * would result in a crash when starting a transaction and does not + * make sense either (send is a read-only operation). + */ + ASSERT(current->journal_info == NULL); + if (WARN_ON(current->journal_info)) return 0; /* @@ -3562,7 +3566,7 @@ static int try_flush_qgroup(struct btrfs_root *root) return 0; } - ret = btrfs_start_delalloc_snapshot(root); + ret = btrfs_start_delalloc_snapshot(root, true); if (ret < 0) goto out; btrfs_wait_ordered_extents(root, U64_MAX, 0, (u64)-1); diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 55741adf9071..bd69db72acc5 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -7170,7 +7170,7 @@ static int flush_delalloc_roots(struct send_ctx *sctx) int i; if (root) { - ret = btrfs_start_delalloc_snapshot(root); + ret = btrfs_start_delalloc_snapshot(root, false); if (ret) return ret; btrfs_wait_ordered_extents(root, U64_MAX, 0, U64_MAX); @@ -7178,7 +7178,7 @@ static int flush_delalloc_roots(struct send_ctx *sctx) for (i = 0; i < sctx->clone_roots_cnt; i++) { root = sctx->clone_roots[i].root; - ret = btrfs_start_delalloc_snapshot(root); + ret = btrfs_start_delalloc_snapshot(root, false); if (ret) return ret; btrfs_wait_ordered_extents(root, U64_MAX, 0, U64_MAX); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index f67721d82e5d..95a600034d61 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -6061,7 +6061,8 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, * (since logging them is pointless, a link count of 0 means they * will never be accessible). */ - if (btrfs_inode_in_log(inode, trans->transid) || + if ((btrfs_inode_in_log(inode, trans->transid) && + list_empty(&ctx->ordered_extents)) || inode->vfs_inode.i_nlink == 0) { ret = BTRFS_NO_LOG_SYNC; goto end_no_trans; diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 70b23a0d03b1..304ce64c70a4 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1126,6 +1126,11 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) goto out; } + if (zone.type == BLK_ZONE_TYPE_CONVENTIONAL) { + ret = -EIO; + goto out; + } + switch (zone.cond) { case BLK_ZONE_COND_OFFLINE: case BLK_ZONE_COND_READONLY: @@ -144,6 +144,16 @@ struct wait_exceptional_entry_queue { struct exceptional_entry_key key; }; +/** + * enum dax_wake_mode: waitqueue wakeup behaviour + * @WAKE_ALL: wake all waiters in the waitqueue + * @WAKE_NEXT: wake only the first waiter in the waitqueue + */ +enum dax_wake_mode { + WAKE_ALL, + WAKE_NEXT, +}; + static wait_queue_head_t *dax_entry_waitqueue(struct xa_state *xas, void *entry, struct exceptional_entry_key *key) { @@ -182,7 +192,8 @@ static int wake_exceptional_entry_func(wait_queue_entry_t *wait, * The important information it's conveying is whether the entry at * this index used to be a PMD entry. */ -static void dax_wake_entry(struct xa_state *xas, void *entry, bool wake_all) +static void dax_wake_entry(struct xa_state *xas, void *entry, + enum dax_wake_mode mode) { struct exceptional_entry_key key; wait_queue_head_t *wq; @@ -196,7 +207,7 @@ static void dax_wake_entry(struct xa_state *xas, void *entry, bool wake_all) * must be in the waitqueue and the following check will see them. */ if (waitqueue_active(wq)) - __wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key); + __wake_up(wq, TASK_NORMAL, mode == WAKE_ALL ? 0 : 1, &key); } /* @@ -264,11 +275,11 @@ static void wait_entry_unlocked(struct xa_state *xas, void *entry) finish_wait(wq, &ewait.wait); } -static void put_unlocked_entry(struct xa_state *xas, void *entry) +static void put_unlocked_entry(struct xa_state *xas, void *entry, + enum dax_wake_mode mode) { - /* If we were the only waiter woken, wake the next one */ if (entry && !dax_is_conflict(entry)) - dax_wake_entry(xas, entry, false); + dax_wake_entry(xas, entry, mode); } /* @@ -286,7 +297,7 @@ static void dax_unlock_entry(struct xa_state *xas, void *entry) old = xas_store(xas, entry); xas_unlock_irq(xas); BUG_ON(!dax_is_locked(old)); - dax_wake_entry(xas, entry, false); + dax_wake_entry(xas, entry, WAKE_NEXT); } /* @@ -524,7 +535,7 @@ retry: dax_disassociate_entry(entry, mapping, false); xas_store(xas, NULL); /* undo the PMD join */ - dax_wake_entry(xas, entry, true); + dax_wake_entry(xas, entry, WAKE_ALL); mapping->nrpages -= PG_PMD_NR; entry = NULL; xas_set(xas, index); @@ -622,7 +633,7 @@ struct page *dax_layout_busy_page_range(struct address_space *mapping, entry = get_unlocked_entry(&xas, 0); if (entry) page = dax_busy_page(entry); - put_unlocked_entry(&xas, entry); + put_unlocked_entry(&xas, entry, WAKE_NEXT); if (page) break; if (++scanned % XA_CHECK_SCHED) @@ -664,7 +675,7 @@ static int __dax_invalidate_entry(struct address_space *mapping, mapping->nrpages -= 1UL << dax_entry_order(entry); ret = 1; out: - put_unlocked_entry(&xas, entry); + put_unlocked_entry(&xas, entry, WAKE_ALL); xas_unlock_irq(&xas); return ret; } @@ -937,13 +948,13 @@ static int dax_writeback_one(struct xa_state *xas, struct dax_device *dax_dev, xas_lock_irq(xas); xas_store(xas, entry); xas_clear_mark(xas, PAGECACHE_TAG_DIRTY); - dax_wake_entry(xas, entry, false); + dax_wake_entry(xas, entry, WAKE_NEXT); trace_dax_writeback_one(mapping->host, index, count); return ret; put_unlocked: - put_unlocked_entry(xas, entry); + put_unlocked_entry(xas, entry, WAKE_NEXT); return ret; } @@ -1684,7 +1695,7 @@ dax_insert_pfn_mkwrite(struct vm_fault *vmf, pfn_t pfn, unsigned int order) /* Did we race with someone splitting entry or so? */ if (!entry || dax_is_conflict(entry) || (order == 0 && !dax_is_pte_entry(entry))) { - put_unlocked_entry(&xas, entry); + put_unlocked_entry(&xas, entry, WAKE_NEXT); xas_unlock_irq(&xas); trace_dax_insert_pfn_mkwrite_no_entry(mapping->host, vmf, VM_FAULT_NOPAGE); diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index e62d813756f2..efaf32596b97 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -450,14 +450,31 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, lcn = m->lcn + 1; if (m->compressedlcs) goto out; - if (lcn == initial_lcn) - goto err_bonus_cblkcnt; err = z_erofs_load_cluster_from_disk(m, lcn); if (err) return err; + /* + * If the 1st NONHEAD lcluster has already been handled initially w/o + * valid compressedlcs, which means at least it mustn't be CBLKCNT, or + * an internal implemenatation error is detected. + * + * The following code can also handle it properly anyway, but let's + * BUG_ON in the debugging mode only for developers to notice that. + */ + DBG_BUGON(lcn == initial_lcn && + m->type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD); + switch (m->type) { + case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN: + case Z_EROFS_VLE_CLUSTER_TYPE_HEAD: + /* + * if the 1st NONHEAD lcluster is actually PLAIN or HEAD type + * rather than CBLKCNT, it's a 1 lcluster-sized pcluster. + */ + m->compressedlcs = 1; + break; case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD: if (m->delta[0] != 1) goto err_bonus_cblkcnt; diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 53b13787eb2c..925a5ca3744a 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -117,19 +117,6 @@ static void f2fs_unlock_rpages(struct compress_ctx *cc, int len) f2fs_drop_rpages(cc, len, true); } -static void f2fs_put_rpages_mapping(struct address_space *mapping, - pgoff_t start, int len) -{ - int i; - - for (i = 0; i < len; i++) { - struct page *page = find_get_page(mapping, start + i); - - put_page(page); - put_page(page); - } -} - static void f2fs_put_rpages_wbc(struct compress_ctx *cc, struct writeback_control *wbc, bool redirty, int unlock) { @@ -158,13 +145,14 @@ int f2fs_init_compress_ctx(struct compress_ctx *cc) return cc->rpages ? 0 : -ENOMEM; } -void f2fs_destroy_compress_ctx(struct compress_ctx *cc) +void f2fs_destroy_compress_ctx(struct compress_ctx *cc, bool reuse) { page_array_free(cc->inode, cc->rpages, cc->cluster_size); cc->rpages = NULL; cc->nr_rpages = 0; cc->nr_cpages = 0; - cc->cluster_idx = NULL_CLUSTER; + if (!reuse) + cc->cluster_idx = NULL_CLUSTER; } void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct page *page) @@ -1036,7 +1024,7 @@ retry: } if (PageUptodate(page)) - unlock_page(page); + f2fs_put_page(page, 1); else f2fs_compress_ctx_add_page(cc, page); } @@ -1046,33 +1034,35 @@ retry: ret = f2fs_read_multi_pages(cc, &bio, cc->cluster_size, &last_block_in_bio, false, true); - f2fs_destroy_compress_ctx(cc); + f2fs_put_rpages(cc); + f2fs_destroy_compress_ctx(cc, true); if (ret) - goto release_pages; + goto out; if (bio) f2fs_submit_bio(sbi, bio, DATA); ret = f2fs_init_compress_ctx(cc); if (ret) - goto release_pages; + goto out; } for (i = 0; i < cc->cluster_size; i++) { f2fs_bug_on(sbi, cc->rpages[i]); page = find_lock_page(mapping, start_idx + i); - f2fs_bug_on(sbi, !page); + if (!page) { + /* page can be truncated */ + goto release_and_retry; + } f2fs_wait_on_page_writeback(page, DATA, true, true); - f2fs_compress_ctx_add_page(cc, page); - f2fs_put_page(page, 0); if (!PageUptodate(page)) { +release_and_retry: + f2fs_put_rpages(cc); f2fs_unlock_rpages(cc, i + 1); - f2fs_put_rpages_mapping(mapping, start_idx, - cc->cluster_size); - f2fs_destroy_compress_ctx(cc); + f2fs_destroy_compress_ctx(cc, true); goto retry; } } @@ -1103,10 +1093,10 @@ retry: } unlock_pages: + f2fs_put_rpages(cc); f2fs_unlock_rpages(cc, i); -release_pages: - f2fs_put_rpages_mapping(mapping, start_idx, i); - f2fs_destroy_compress_ctx(cc); + f2fs_destroy_compress_ctx(cc, true); +out: return ret; } @@ -1141,7 +1131,7 @@ bool f2fs_compress_write_end(struct inode *inode, void *fsdata, set_cluster_dirty(&cc); f2fs_put_rpages_wbc(&cc, NULL, false, 1); - f2fs_destroy_compress_ctx(&cc); + f2fs_destroy_compress_ctx(&cc, false); return first_index; } @@ -1361,7 +1351,7 @@ unlock_continue: f2fs_put_rpages(cc); page_array_free(cc->inode, cc->cpages, cc->nr_cpages); cc->cpages = NULL; - f2fs_destroy_compress_ctx(cc); + f2fs_destroy_compress_ctx(cc, false); return 0; out_destroy_crypt: @@ -1372,7 +1362,8 @@ out_destroy_crypt: for (i = 0; i < cc->nr_cpages; i++) { if (!cc->cpages[i]) continue; - f2fs_put_page(cc->cpages[i], 1); + f2fs_compress_free_page(cc->cpages[i]); + cc->cpages[i] = NULL; } out_put_cic: kmem_cache_free(cic_entry_slab, cic); @@ -1522,7 +1513,7 @@ write: err = f2fs_write_raw_pages(cc, submitted, wbc, io_type); f2fs_put_rpages_wbc(cc, wbc, false, 0); destroy_out: - f2fs_destroy_compress_ctx(cc); + f2fs_destroy_compress_ctx(cc, false); return err; } diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 96f1a354f89f..009a09fb9d88 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -2287,7 +2287,7 @@ static int f2fs_mpage_readpages(struct inode *inode, max_nr_pages, &last_block_in_bio, rac != NULL, false); - f2fs_destroy_compress_ctx(&cc); + f2fs_destroy_compress_ctx(&cc, false); if (ret) goto set_error_page; } @@ -2332,7 +2332,7 @@ next_page: max_nr_pages, &last_block_in_bio, rac != NULL, false); - f2fs_destroy_compress_ctx(&cc); + f2fs_destroy_compress_ctx(&cc, false); } } #endif @@ -3033,7 +3033,7 @@ next: } } if (f2fs_compressed_file(inode)) - f2fs_destroy_compress_ctx(&cc); + f2fs_destroy_compress_ctx(&cc, false); #endif if (retry) { index = 0; @@ -3801,6 +3801,7 @@ static int f2fs_is_file_aligned(struct inode *inode) block_t pblock; unsigned long nr_pblocks; unsigned int blocks_per_sec = BLKS_PER_SEC(sbi); + unsigned int not_aligned = 0; int ret = 0; cur_lblock = 0; @@ -3833,13 +3834,20 @@ static int f2fs_is_file_aligned(struct inode *inode) if ((pblock - main_blkaddr) & (blocks_per_sec - 1) || nr_pblocks & (blocks_per_sec - 1)) { - f2fs_err(sbi, "Swapfile does not align to section"); - ret = -EINVAL; - goto out; + if (f2fs_is_pinned_file(inode)) { + f2fs_err(sbi, "Swapfile does not align to section"); + ret = -EINVAL; + goto out; + } + not_aligned++; } cur_lblock += nr_pblocks; } + if (not_aligned) + f2fs_warn(sbi, "Swapfile (%u) is not align to section: \n" + "\t1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate()", + not_aligned); out: return ret; } @@ -3858,6 +3866,7 @@ static int check_swap_activate_fast(struct swap_info_struct *sis, int nr_extents = 0; unsigned long nr_pblocks; unsigned int blocks_per_sec = BLKS_PER_SEC(sbi); + unsigned int not_aligned = 0; int ret = 0; /* @@ -3887,7 +3896,7 @@ static int check_swap_activate_fast(struct swap_info_struct *sis, /* hole */ if (!(map.m_flags & F2FS_MAP_FLAGS)) { f2fs_err(sbi, "Swapfile has holes\n"); - ret = -ENOENT; + ret = -EINVAL; goto out; } @@ -3896,9 +3905,12 @@ static int check_swap_activate_fast(struct swap_info_struct *sis, if ((pblock - SM_I(sbi)->main_blkaddr) & (blocks_per_sec - 1) || nr_pblocks & (blocks_per_sec - 1)) { - f2fs_err(sbi, "Swapfile does not align to section"); - ret = -EINVAL; - goto out; + if (f2fs_is_pinned_file(inode)) { + f2fs_err(sbi, "Swapfile does not align to section"); + ret = -EINVAL; + goto out; + } + not_aligned++; } if (cur_lblock + nr_pblocks >= sis->max) @@ -3927,6 +3939,11 @@ static int check_swap_activate_fast(struct swap_info_struct *sis, sis->max = cur_lblock; sis->pages = cur_lblock - 1; sis->highest_bit = cur_lblock - 1; + + if (not_aligned) + f2fs_warn(sbi, "Swapfile (%u) is not align to section: \n" + "\t1) creat(), 2) ioctl(F2FS_IOC_SET_PIN_FILE), 3) fallocate()", + not_aligned); out: return ret; } @@ -4035,7 +4052,7 @@ out: return ret; bad_bmap: f2fs_err(sbi, "Swapfile has holes\n"); - return -ENOENT; + return -EINVAL; } static int f2fs_swap_activate(struct swap_info_struct *sis, struct file *file, diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 044878866ca3..c83d90125ebd 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3956,7 +3956,7 @@ struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc); void f2fs_decompress_end_io(struct decompress_io_ctx *dic, bool failed); void f2fs_put_page_dic(struct page *page); int f2fs_init_compress_ctx(struct compress_ctx *cc); -void f2fs_destroy_compress_ctx(struct compress_ctx *cc); +void f2fs_destroy_compress_ctx(struct compress_ctx *cc, bool reuse); void f2fs_init_compress_info(struct f2fs_sb_info *sbi); int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi); void f2fs_destroy_page_array_cache(struct f2fs_sb_info *sbi); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 44a4650aea7b..ceb575f99048 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1817,7 +1817,8 @@ static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask) struct f2fs_inode_info *fi = F2FS_I(inode); u32 masked_flags = fi->i_flags & mask; - f2fs_bug_on(F2FS_I_SB(inode), (iflags & ~mask)); + /* mask can be shrunk by flags_valid selector */ + iflags &= mask; /* Is it quota file? Do not allow user to mess with it */ if (IS_NOQUOTA(inode)) diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index c605415840b5..51dc79fad4fe 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -3574,12 +3574,12 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio) return err; drop_bio: - if (fio->bio) { + if (fio->bio && *(fio->bio)) { struct bio *bio = *(fio->bio); bio->bi_status = BLK_STS_IOERR; bio_endio(bio); - fio->bio = NULL; + *(fio->bio) = NULL; } return err; } diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c index a930ddd15681..7054a542689f 100644 --- a/fs/hfsplus/extents.c +++ b/fs/hfsplus/extents.c @@ -598,13 +598,15 @@ void hfsplus_file_truncate(struct inode *inode) res = __hfsplus_ext_cache_extent(&fd, inode, alloc_cnt); if (res) break; - hfs_brec_remove(&fd); - mutex_unlock(&fd.tree->tree_lock); start = hip->cached_start; + if (blk_cnt <= start) + hfs_brec_remove(&fd); + mutex_unlock(&fd.tree->tree_lock); hfsplus_free_extents(sb, hip->cached_extents, alloc_cnt - start, alloc_cnt - blk_cnt); hfsplus_dump_extent(hip->cached_extents); + mutex_lock(&fd.tree->tree_lock); if (blk_cnt > start) { hip->extent_state |= HFSPLUS_EXT_DIRTY; break; @@ -612,7 +614,6 @@ void hfsplus_file_truncate(struct inode *inode) alloc_cnt = start; hip->cached_start = hip->cached_blocks = 0; hip->extent_state &= ~(HFSPLUS_EXT_DIRTY | HFSPLUS_EXT_NEW); - mutex_lock(&fd.tree->tree_lock); } hfs_find_exit(&fd); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index a2a42335e8fd..9d9e0097c1d3 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -131,6 +131,7 @@ static void huge_pagevec_release(struct pagevec *pvec) static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file_inode(file); + struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode); loff_t len, vma_len; int ret; struct hstate *h = hstate_file(file); @@ -146,6 +147,10 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND; vma->vm_ops = &hugetlb_vm_ops; + ret = seal_check_future_write(info->seals, vma); + if (ret) + return ret; + /* * page based offset in vm_pgoff could be sufficiently large to * overflow a loff_t when converted to byte offset. This can diff --git a/fs/io_uring.c b/fs/io_uring.c index f46acbbeed57..e481ac8a757a 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -100,6 +100,8 @@ #define IORING_MAX_RESTRICTIONS (IORING_RESTRICTION_LAST + \ IORING_REGISTER_LAST + IORING_OP_LAST) +#define IORING_MAX_REG_BUFFERS (1U << 14) + #define SQE_VALID_FLAGS (IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK| \ IOSQE_IO_HARDLINK | IOSQE_ASYNC | \ IOSQE_BUFFER_SELECT) @@ -4035,7 +4037,7 @@ static int io_epoll_ctl_prep(struct io_kiocb *req, #if defined(CONFIG_EPOLL) if (sqe->ioprio || sqe->buf_index) return -EINVAL; - if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL))) + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; req->epoll.epfd = READ_ONCE(sqe->fd); @@ -4150,7 +4152,7 @@ static int io_fadvise(struct io_kiocb *req, unsigned int issue_flags) static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL))) + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->ioprio || sqe->buf_index) return -EINVAL; @@ -5827,8 +5829,6 @@ done: static int io_rsrc_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - if (unlikely(req->ctx->flags & IORING_SETUP_SQPOLL)) - return -EINVAL; if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) return -EINVAL; if (sqe->ioprio || sqe->rw_flags) @@ -6354,19 +6354,20 @@ static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer) * We don't expect the list to be empty, that will only happen if we * race with the completion of the linked work. */ - if (prev && req_ref_inc_not_zero(prev)) + if (prev) { io_remove_next_linked(prev); - else - prev = NULL; + if (!req_ref_inc_not_zero(prev)) + prev = NULL; + } spin_unlock_irqrestore(&ctx->completion_lock, flags); if (prev) { io_async_find_and_cancel(ctx, req, prev->user_data, -ETIME); io_put_req_deferred(prev, 1); + io_put_req_deferred(req, 1); } else { io_req_complete_post(req, -ETIME, 0); } - io_put_req_deferred(req, 1); return HRTIMER_NORESTART; } @@ -8390,7 +8391,7 @@ static int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg, if (ctx->user_bufs) return -EBUSY; - if (!nr_args || nr_args > UIO_MAXIOV) + if (!nr_args || nr_args > IORING_MAX_REG_BUFFERS) return -EINVAL; ret = io_rsrc_node_switch_start(ctx); if (ret) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index f2cd2034a87b..9023717c5188 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -394,7 +394,7 @@ void iomap_readahead(struct readahead_control *rac, const struct iomap_ops *ops) { struct inode *inode = rac->mapping->host; loff_t pos = readahead_pos(rac); - loff_t length = readahead_length(rac); + size_t length = readahead_length(rac); struct iomap_readpage_ctx ctx = { .rac = rac, }; @@ -402,7 +402,7 @@ void iomap_readahead(struct readahead_control *rac, const struct iomap_ops *ops) trace_iomap_readahead(inode, readahead_count(rac)); while (length > 0) { - loff_t ret = iomap_apply(inode, pos, length, 0, ops, + ssize_t ret = iomap_apply(inode, pos, length, 0, ops, &ctx, iomap_readahead_actor); if (ret <= 0) { WARN_ON_ONCE(ret == 0); diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c index 7b1128398976..89d492916dea 100644 --- a/fs/squashfs/file.c +++ b/fs/squashfs/file.c @@ -211,11 +211,11 @@ failure: * If the skip factor is limited in this way then the file will use multiple * slots. */ -static inline int calculate_skip(int blocks) +static inline int calculate_skip(u64 blocks) { - int skip = blocks / ((SQUASHFS_META_ENTRIES + 1) + u64 skip = blocks / ((SQUASHFS_META_ENTRIES + 1) * SQUASHFS_META_INDEXES); - return min(SQUASHFS_CACHED_BLKS - 1, skip + 1); + return min((u64) SQUASHFS_CACHED_BLKS - 1, skip + 1); } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1255823b2bc0..f69c75bd6d27 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -676,11 +676,6 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); extern void blk_set_pm_only(struct request_queue *q); extern void blk_clear_pm_only(struct request_queue *q); -static inline bool blk_account_rq(struct request *rq) -{ - return (rq->rq_flags & RQF_STARTED) && !blk_rq_is_passthrough(rq); -} - #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) #define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ) diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h index 153734816b49..d5b9c8d40c18 100644 --- a/include/linux/console_struct.h +++ b/include/linux/console_struct.h @@ -101,6 +101,7 @@ struct vc_data { unsigned int vc_rows; unsigned int vc_size_row; /* Bytes per row */ unsigned int vc_scan_lines; /* # of scan lines */ + unsigned int vc_cell_height; /* CRTC character cell height */ unsigned long vc_origin; /* [!] Start of real screen */ unsigned long vc_scr_end; /* [!] End of real screen */ unsigned long vc_visible_origin; /* [!] Top of visible window */ diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 1fe8e105b83b..dcb2f9022c1d 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -34,7 +34,7 @@ struct elevator_mq_ops { void (*depth_updated)(struct blk_mq_hw_ctx *); bool (*allow_merge)(struct request_queue *, struct request *, struct bio *); - bool (*bio_merge)(struct blk_mq_hw_ctx *, struct bio *, unsigned int); + bool (*bio_merge)(struct request_queue *, struct bio *, unsigned int); int (*request_merge)(struct request_queue *q, struct request **, struct bio *); void (*request_merged)(struct request_queue *, struct request *, enum elv_merge); void (*requests_merged)(struct request_queue *, struct request *, struct request *); diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 01f251b6e36c..89b69e645ac7 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -141,7 +141,6 @@ static inline void __iomem *devm_nvdimm_ioremap(struct device *dev, struct nvdimm_bus; struct module; -struct device; struct nd_blk_region; struct nd_blk_region_desc { int (*enable)(struct nvdimm_bus *nvdimm_bus, struct device *dev); diff --git a/include/linux/mm.h b/include/linux/mm.h index 322ec61d0da7..c274f75efcf9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3216,5 +3216,37 @@ void mem_dump_obj(void *object); static inline void mem_dump_obj(void *object) {} #endif +/** + * seal_check_future_write - Check for F_SEAL_FUTURE_WRITE flag and handle it + * @seals: the seals to check + * @vma: the vma to operate on + * + * Check whether F_SEAL_FUTURE_WRITE is set; if so, do proper check/handling on + * the vma flags. Return 0 if check pass, or <0 for errors. + */ +static inline int seal_check_future_write(int seals, struct vm_area_struct *vma) +{ + if (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 an F_SEAL_FUTURE_WRITE sealed memfd can be mapped as + * MAP_SHARED and read-only, take care to not allow mprotect to + * revert protections on such mappings. Do this only for shared + * mappings. For private mappings, don't need to mask + * VM_MAYWRITE as we still want them to be COW-writable. + */ + if (vma->vm_flags & VM_SHARED) + vma->vm_flags &= ~(VM_MAYWRITE); + } + + return 0; +} + #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6613b26a8894..5aacc1c10a45 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -97,10 +97,10 @@ struct page { }; struct { /* page_pool used by netstack */ /** - * @dma_addr: might require a 64-bit value even on + * @dma_addr: might require a 64-bit value on * 32-bit architectures. */ - dma_addr_t dma_addr; + unsigned long dma_addr[2]; }; struct { /* slab, slob and slub */ union { diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index a4bd41128bf3..e89df447fae3 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -997,9 +997,9 @@ static inline loff_t readahead_pos(struct readahead_control *rac) * readahead_length - The number of bytes in this readahead request. * @rac: The readahead request. */ -static inline loff_t readahead_length(struct readahead_control *rac) +static inline size_t readahead_length(struct readahead_control *rac) { - return (loff_t)rac->_nr_pages * PAGE_SIZE; + return rac->_nr_pages * PAGE_SIZE; } /** @@ -1024,7 +1024,7 @@ static inline unsigned int readahead_count(struct readahead_control *rac) * readahead_batch_length - The number of bytes in the current batch. * @rac: The readahead request. */ -static inline loff_t readahead_batch_length(struct readahead_control *rac) +static inline size_t readahead_batch_length(struct readahead_control *rac) { return rac->_batch_count * PAGE_SIZE; } diff --git a/include/linux/pm.h b/include/linux/pm.h index c9657408fee1..1d8209c09686 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -601,6 +601,7 @@ struct dev_pm_info { unsigned int idle_notification:1; unsigned int request_pending:1; unsigned int deferred_resume:1; + unsigned int needs_force_resume:1; unsigned int runtime_auto:1; bool ignore_children:1; unsigned int no_callbacks:1; diff --git a/include/linux/randomize_kstack.h b/include/linux/randomize_kstack.h index fd80fab663a9..bebc911161b6 100644 --- a/include/linux/randomize_kstack.h +++ b/include/linux/randomize_kstack.h @@ -38,7 +38,7 @@ void *__builtin_alloca(size_t size); u32 offset = raw_cpu_read(kstack_offset); \ u8 *ptr = __builtin_alloca(KSTACK_OFFSET_MAX(offset)); \ /* Keep allocation even after "ptr" loses scope. */ \ - asm volatile("" : "=o"(*ptr) :: "memory"); \ + asm volatile("" :: "r"(ptr) : "memory"); \ } \ } while (0) diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 6d517a37c18b..b4b6de909c93 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -198,7 +198,17 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, static inline dma_addr_t page_pool_get_dma_addr(struct page *page) { - return page->dma_addr; + dma_addr_t ret = page->dma_addr[0]; + if (sizeof(dma_addr_t) > sizeof(unsigned long)) + ret |= (dma_addr_t)page->dma_addr[1] << 16 << 16; + return ret; +} + +static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr) +{ + page->dma_addr[0] = addr; + if (sizeof(dma_addr_t) > sizeof(unsigned long)) + page->dma_addr[1] = upper_32_bits(addr); } static inline bool is_page_pool_compiled_in(void) diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index f44eb0a04afd..4c32e97dcdf0 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -185,7 +185,7 @@ struct fsxattr { #define BLKROTATIONAL _IO(0x12,126) #define BLKZEROOUT _IO(0x12,127) /* - * A jump here: 130-131 are reserved for zoned block devices + * A jump here: 130-136 are reserved for zoned block devices * (see uapi/linux/blkzoned.h) */ diff --git a/include/xen/arm/swiotlb-xen.h b/include/xen/arm/swiotlb-xen.h index 2994fe6031a0..33336ab58afc 100644 --- a/include/xen/arm/swiotlb-xen.h +++ b/include/xen/arm/swiotlb-xen.h @@ -2,6 +2,19 @@ #ifndef _ASM_ARM_SWIOTLB_XEN_H #define _ASM_ARM_SWIOTLB_XEN_H -extern int xen_swiotlb_detect(void); +#include <xen/features.h> +#include <xen/xen.h> + +static inline int xen_swiotlb_detect(void) +{ + if (!xen_domain()) + return 0; + if (xen_feature(XENFEAT_direct_mapped)) + return 1; + /* legacy case */ + if (!xen_feature(XENFEAT_not_direct_mapped) && xen_initial_domain()) + return 1; + return 0; +} #endif /* _ASM_ARM_SWIOTLB_XEN_H */ diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 76f09456ec4b..2997ca600d18 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -170,6 +170,21 @@ void __ptrace_unlink(struct task_struct *child) spin_unlock(&child->sighand->siglock); } +static bool looks_like_a_spurious_pid(struct task_struct *task) +{ + if (task->exit_code != ((PTRACE_EVENT_EXEC << 8) | SIGTRAP)) + return false; + + if (task_pid_vnr(task) == task->ptrace_message) + return false; + /* + * The tracee changed its pid but the PTRACE_EVENT_EXEC event + * was not wait()'ed, most probably debugger targets the old + * leader which was destroyed in de_thread(). + */ + return true; +} + /* Ensure that nothing can wake it up, even SIGKILL */ static bool ptrace_freeze_traced(struct task_struct *task) { @@ -180,7 +195,8 @@ static bool ptrace_freeze_traced(struct task_struct *task) return ret; spin_lock_irq(&task->sighand->siglock); - if (task_is_traced(task) && !__fatal_signal_pending(task)) { + if (task_is_traced(task) && !looks_like_a_spurious_pid(task) && + !__fatal_signal_pending(task)) { task->state = __TASK_TRACED; ret = true; } diff --git a/kernel/resource.c b/kernel/resource.c index 028a5ab18818..ca9f5198a01f 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1805,7 +1805,7 @@ static struct resource *__request_free_mem_region(struct device *dev, REGION_DISJOINT) continue; - if (!__request_region_locked(res, &iomem_resource, addr, size, + if (__request_region_locked(res, &iomem_resource, addr, size, name, 0)) break; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 20aa234ffe04..3248e24a90b0 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6217,7 +6217,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool } if (has_idle_core) - set_idle_cores(this, false); + set_idle_cores(target, false); if (sched_feat(SIS_PROP) && !has_idle_core) { time = cpu_clock(this) - time; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 560e4c8d3825..a21ef9cd2aae 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3704,6 +3704,9 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, goto print; while (*p) { + bool star = false; + int len = 0; + j = 0; /* We only care about %s and variants */ @@ -3725,13 +3728,17 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, /* Need to test cases like %08.*s */ for (j = 1; p[i+j]; j++) { if (isdigit(p[i+j]) || - p[i+j] == '*' || p[i+j] == '.') continue; + if (p[i+j] == '*') { + star = true; + continue; + } break; } if (p[i+j] == 's') break; + star = false; } j = 0; } @@ -3744,6 +3751,9 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, iter->fmt[i] = '\0'; trace_seq_vprintf(&iter->seq, iter->fmt, ap); + if (star) + len = va_arg(ap, int); + /* The ap now points to the string data of the %s */ str = va_arg(ap, const char *); @@ -3762,8 +3772,18 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, int ret; /* Try to safely read the string */ - ret = strncpy_from_kernel_nofault(iter->fmt, str, - iter->fmt_size); + if (star) { + if (len + 1 > iter->fmt_size) + len = iter->fmt_size - 1; + if (len < 0) + len = 0; + ret = copy_from_kernel_nofault(iter->fmt, str, len); + iter->fmt[len] = 0; + star = false; + } else { + ret = strncpy_from_kernel_nofault(iter->fmt, str, + iter->fmt_size); + } if (ret < 0) trace_seq_printf(&iter->seq, "(0x%px)", str); else @@ -3775,7 +3795,10 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt, strncpy(iter->fmt, p + i, j + 1); iter->fmt[j+1] = '\0'; } - trace_seq_printf(&iter->seq, iter->fmt, str); + if (star) + trace_seq_printf(&iter->seq, iter->fmt, len, str); + else + trace_seq_printf(&iter->seq, iter->fmt, str); p += i + j + 1; } diff --git a/lib/test_kasan.c b/lib/test_kasan.c index dc05cfc2d12f..cacbbbdef768 100644 --- a/lib/test_kasan.c +++ b/lib/test_kasan.c @@ -654,8 +654,20 @@ static char global_array[10]; static void kasan_global_oob(struct kunit *test) { - volatile int i = 3; - char *p = &global_array[ARRAY_SIZE(global_array) + i]; + /* + * Deliberate out-of-bounds access. To prevent CONFIG_UBSAN_LOCAL_BOUNDS + * from failing here and panicing the kernel, access the array via a + * volatile pointer, which will prevent the compiler from being able to + * determine the array bounds. + * + * This access uses a volatile pointer to char (char *volatile) rather + * than the more conventional pointer to volatile char (volatile char *) + * because we want to prevent the compiler from making inferences about + * the pointer itself (i.e. its array bounds), not the data that it + * refers to. + */ + char *volatile array = global_array; + char *p = &array[ARRAY_SIZE(global_array) + 3]; /* Only generic mode instruments globals. */ KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_GENERIC); @@ -703,8 +715,9 @@ static void ksize_uaf(struct kunit *test) static void kasan_stack_oob(struct kunit *test) { char stack_array[10]; - volatile int i = OOB_TAG_OFF; - char *p = &stack_array[ARRAY_SIZE(stack_array) + i]; + /* See comment in kasan_global_oob. */ + char *volatile array = stack_array; + char *p = &array[ARRAY_SIZE(stack_array) + OOB_TAG_OFF]; KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_STACK); @@ -715,7 +728,9 @@ static void kasan_alloca_oob_left(struct kunit *test) { volatile int i = 10; char alloca_array[i]; - char *p = alloca_array - 1; + /* See comment in kasan_global_oob. */ + char *volatile array = alloca_array; + char *p = array - 1; /* Only generic mode instruments dynamic allocas. */ KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_GENERIC); @@ -728,7 +743,9 @@ static void kasan_alloca_oob_right(struct kunit *test) { volatile int i = 10; char alloca_array[i]; - char *p = alloca_array + i; + /* See comment in kasan_global_oob. */ + char *volatile array = alloca_array; + char *p = array + i; /* Only generic mode instruments dynamic allocas. */ KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_GENERIC); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3db405dea3dc..95918f410c0f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4056,6 +4056,7 @@ again: * See Documentation/vm/mmu_notifier.rst */ huge_ptep_set_wrprotect(src, addr, src_pte); + entry = huge_pte_wrprotect(entry); } page_dup_rmap(ptepage, true); diff --git a/mm/ioremap.c b/mm/ioremap.c index d1dcc7e744ac..8ee0136f8cb0 100644 --- a/mm/ioremap.c +++ b/mm/ioremap.c @@ -16,16 +16,16 @@ #include "pgalloc-track.h" #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP -static bool __ro_after_init iomap_max_page_shift = PAGE_SHIFT; +static unsigned int __ro_after_init iomap_max_page_shift = BITS_PER_LONG - 1; static int __init set_nohugeiomap(char *str) { - iomap_max_page_shift = P4D_SHIFT; + iomap_max_page_shift = PAGE_SHIFT; return 0; } early_param("nohugeiomap", set_nohugeiomap); #else /* CONFIG_HAVE_ARCH_HUGE_VMAP */ -static const bool iomap_max_page_shift = PAGE_SHIFT; +static const unsigned int iomap_max_page_shift = PAGE_SHIFT; #endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ int ioremap_page_range(unsigned long addr, @@ -776,11 +776,12 @@ static void remove_rmap_item_from_tree(struct rmap_item *rmap_item) struct page *page; stable_node = rmap_item->head; - page = get_ksm_page(stable_node, GET_KSM_PAGE_NOLOCK); + page = get_ksm_page(stable_node, GET_KSM_PAGE_LOCK); if (!page) goto out; hlist_del(&rmap_item->hlist); + unlock_page(page); put_page(page); if (!hlist_empty(&stable_node->hlist)) diff --git a/mm/shmem.c b/mm/shmem.c index a08cedefbfaa..5d46611cba8d 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2258,25 +2258,11 @@ out_nomem: static int shmem_mmap(struct file *file, struct vm_area_struct *vma) { struct shmem_inode_info *info = SHMEM_I(file_inode(file)); + int ret; - 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 an F_SEAL_FUTURE_WRITE sealed memfd can be mapped as - * MAP_SHARED and read-only, take care to not allow mprotect to - * revert protections on such mappings. Do this only for shared - * mappings. For private mappings, don't need to mask - * VM_MAYWRITE as we still want them to be COW-writable. - */ - if (vma->vm_flags & VM_SHARED) - vma->vm_flags &= ~(VM_MAYWRITE); - } + ret = seal_check_future_write(info->seals, vma); + if (ret) + return ret; /* arm64 - allow memory tagging on RAM-based files */ vma->vm_flags |= VM_MTE_ALLOWED; @@ -2375,8 +2361,18 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, pgoff_t offset, max_off; ret = -ENOMEM; - if (!shmem_inode_acct_block(inode, 1)) + if (!shmem_inode_acct_block(inode, 1)) { + /* + * We may have got a page, returned -ENOENT triggering a retry, + * and now we find ourselves with -ENOMEM. Release the page, to + * avoid a BUG_ON in our caller. + */ + if (unlikely(*pagep)) { + put_page(*pagep); + *pagep = NULL; + } goto out; + } if (!*pagep) { page = shmem_alloc_page(gfp, info, pgoff); diff --git a/mm/slab_common.c b/mm/slab_common.c index f8833d3e5d47..a4a571428c51 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -318,6 +318,16 @@ kmem_cache_create_usercopy(const char *name, const char *cache_name; int err; +#ifdef CONFIG_SLUB_DEBUG + /* + * If no slub_debug was enabled globally, the static key is not yet + * enabled by setup_slub_debug(). Enable it if the cache is being + * created with any of the debugging flags passed explicitly. + */ + if (flags & SLAB_DEBUG_FLAGS) + static_branch_enable(&slub_debug_enabled); +#endif + mutex_lock(&slab_mutex); err = kmem_cache_sanity_check(name, size); diff --git a/mm/slub.c b/mm/slub.c index feda53ae62ba..438fa8d4c970 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3828,15 +3828,6 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) static int kmem_cache_open(struct kmem_cache *s, slab_flags_t flags) { -#ifdef CONFIG_SLUB_DEBUG - /* - * If no slub_debug was enabled globally, the static key is not yet - * enabled by setup_slub_debug(). Enable it if the cache is being - * created with any of the debugging flags passed explicitly. - */ - if (flags & SLAB_DEBUG_FLAGS) - static_branch_enable(&slub_debug_enabled); -#endif s->flags = kmem_cache_flags(s->size, flags, s->name); #ifdef CONFIG_SLAB_FREELIST_HARDENED s->random = get_random_long(); diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 9ec1aa9640ad..3c4c4c7a0402 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -174,8 +174,10 @@ static void page_pool_dma_sync_for_device(struct page_pool *pool, struct page *page, unsigned int dma_sync_size) { + dma_addr_t dma_addr = page_pool_get_dma_addr(page); + dma_sync_size = min(dma_sync_size, pool->p.max_len); - dma_sync_single_range_for_device(pool->p.dev, page->dma_addr, + dma_sync_single_range_for_device(pool->p.dev, dma_addr, pool->p.offset, dma_sync_size, pool->p.dma_dir); } @@ -195,7 +197,7 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page) if (dma_mapping_error(pool->p.dev, dma)) return false; - page->dma_addr = dma; + page_pool_set_dma_addr(page, dma); if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) page_pool_dma_sync_for_device(pool, page, pool->p.max_len); @@ -331,13 +333,13 @@ void page_pool_release_page(struct page_pool *pool, struct page *page) */ goto skip_dma_unmap; - dma = page->dma_addr; + dma = page_pool_get_dma_addr(page); - /* When page is unmapped, it cannot be returned our pool */ + /* When page is unmapped, it cannot be returned to our pool */ dma_unmap_page_attrs(pool->p.dev, dma, PAGE_SIZE << pool->p.order, pool->p.dma_dir, DMA_ATTR_SKIP_CPU_SYNC); - page->dma_addr = 0; + page_pool_set_dma_addr(page, 0); skip_dma_unmap: /* This may be the last page returned, releasing the pool, so * it is not safe to reference pool afterwards. diff --git a/security/keys/trusted-keys/trusted_tpm1.c b/security/keys/trusted-keys/trusted_tpm1.c index 469394550801..aa108bea6739 100644 --- a/security/keys/trusted-keys/trusted_tpm1.c +++ b/security/keys/trusted-keys/trusted_tpm1.c @@ -493,10 +493,12 @@ static int tpm_seal(struct tpm_buf *tb, uint16_t keytype, ret = tpm_get_random(chip, td->nonceodd, TPM_NONCE_SIZE); if (ret < 0) - return ret; + goto out; - if (ret != TPM_NONCE_SIZE) - return -EIO; + if (ret != TPM_NONCE_SIZE) { + ret = -EIO; + goto out; + } ordinal = htonl(TPM_ORD_SEAL); datsize = htonl(datalen); diff --git a/security/keys/trusted-keys/trusted_tpm2.c b/security/keys/trusted-keys/trusted_tpm2.c index 617fabd4d913..0165da386289 100644 --- a/security/keys/trusted-keys/trusted_tpm2.c +++ b/security/keys/trusted-keys/trusted_tpm2.c @@ -336,9 +336,9 @@ out: rc = -EPERM; } if (blob_len < 0) - return blob_len; - - payload->blob_len = blob_len; + rc = blob_len; + else + payload->blob_len = blob_len; tpm_put_ops(chip); return rc; diff --git a/tools/arch/powerpc/include/uapi/asm/errno.h b/tools/arch/powerpc/include/uapi/asm/errno.h index cc79856896a1..4ba87de32be0 100644 --- a/tools/arch/powerpc/include/uapi/asm/errno.h +++ b/tools/arch/powerpc/include/uapi/asm/errno.h @@ -2,6 +2,7 @@ #ifndef _ASM_POWERPC_ERRNO_H #define _ASM_POWERPC_ERRNO_H +#undef EDEADLOCK #include <asm-generic/errno.h> #undef EDEADLOCK diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index cc96e26d69f7..ac37830ae941 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -84,7 +84,7 @@ /* CPU types for specific tunings: */ #define X86_FEATURE_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */ -#define X86_FEATURE_K7 ( 3*32+ 5) /* "" Athlon */ +/* FREE, was #define X86_FEATURE_K7 ( 3*32+ 5) "" Athlon */ #define X86_FEATURE_P3 ( 3*32+ 6) /* "" P3 */ #define X86_FEATURE_P4 ( 3*32+ 7) /* "" P4 */ #define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */ @@ -236,6 +236,8 @@ #define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */ #define X86_FEATURE_VMCALL ( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */ #define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */ +#define X86_FEATURE_PVUNLOCK ( 8*32+20) /* "" PV unlock function */ +#define X86_FEATURE_VCPUPREEMPT ( 8*32+21) /* "" PV vcpu_is_preempted function */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ #define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ @@ -290,6 +292,8 @@ #define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */ #define X86_FEATURE_SPLIT_LOCK_DETECT (11*32+ 6) /* #AC for split lock */ #define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */ +#define X86_FEATURE_SGX1 (11*32+ 8) /* "" Basic SGX */ +#define X86_FEATURE_SGX2 (11*32+ 9) /* "" SGX Enclave Dynamic Memory Management (EDMM) */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ @@ -336,6 +340,7 @@ #define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ #define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */ #define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */ +#define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* Virtual SPEC_CTRL */ #define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* "" SVME addr check */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */ @@ -354,6 +359,7 @@ #define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */ #define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */ #define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */ +#define X86_FEATURE_BUS_LOCK_DETECT (16*32+24) /* Bus Lock detect */ #define X86_FEATURE_CLDEMOTE (16*32+25) /* CLDEMOTE instruction */ #define X86_FEATURE_MOVDIRI (16*32+27) /* MOVDIRI instruction */ #define X86_FEATURE_MOVDIR64B (16*32+28) /* MOVDIR64B instruction */ @@ -374,6 +380,7 @@ #define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */ #define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */ #define X86_FEATURE_SERIALIZE (18*32+14) /* SERIALIZE instruction */ +#define X86_FEATURE_HYBRID_CPU (18*32+15) /* "" This part has CPUs of more than one type */ #define X86_FEATURE_TSXLDTRK (18*32+16) /* TSX Suspend Load Address Tracking */ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ #define X86_FEATURE_ARCH_LBR (18*32+19) /* Intel ARCH LBR */ diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 45029354e0a8..211ba3375ee9 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -185,6 +185,9 @@ #define MSR_PEBS_DATA_CFG 0x000003f2 #define MSR_IA32_DS_AREA 0x00000600 #define MSR_IA32_PERF_CAPABILITIES 0x00000345 +#define PERF_CAP_METRICS_IDX 15 +#define PERF_CAP_PT_IDX 16 + #define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6 #define MSR_IA32_RTIT_CTL 0x00000570 @@ -265,6 +268,7 @@ #define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */ #define DEBUGCTLMSR_BTF_SHIFT 1 #define DEBUGCTLMSR_BTF (1UL << 1) /* single-step on branches */ +#define DEBUGCTLMSR_BUS_LOCK_DETECT (1UL << 2) #define DEBUGCTLMSR_TR (1UL << 6) #define DEBUGCTLMSR_BTS (1UL << 7) #define DEBUGCTLMSR_BTINT (1UL << 8) @@ -533,9 +537,9 @@ /* K8 MSRs */ #define MSR_K8_TOP_MEM1 0xc001001a #define MSR_K8_TOP_MEM2 0xc001001d -#define MSR_K8_SYSCFG 0xc0010010 -#define MSR_K8_SYSCFG_MEM_ENCRYPT_BIT 23 -#define MSR_K8_SYSCFG_MEM_ENCRYPT BIT_ULL(MSR_K8_SYSCFG_MEM_ENCRYPT_BIT) +#define MSR_AMD64_SYSCFG 0xc0010010 +#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT 23 +#define MSR_AMD64_SYSCFG_MEM_ENCRYPT BIT_ULL(MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT) #define MSR_K8_INT_PENDING_MSG 0xc0010055 /* C1E active bits in int pending message */ #define K8_INTP_C1E_ACTIVE_MASK 0x18000000 diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h index b8e650a985e3..946d761adbd3 100644 --- a/tools/arch/x86/include/uapi/asm/vmx.h +++ b/tools/arch/x86/include/uapi/asm/vmx.h @@ -27,6 +27,7 @@ #define VMX_EXIT_REASONS_FAILED_VMENTRY 0x80000000 +#define VMX_EXIT_REASONS_SGX_ENCLAVE_MODE 0x08000000 #define EXIT_REASON_EXCEPTION_NMI 0 #define EXIT_REASON_EXTERNAL_INTERRUPT 1 diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index 1e299ac73c86..1cc9da6e29c7 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -4,7 +4,7 @@ #include <linux/linkage.h> #include <asm/errno.h> #include <asm/cpufeatures.h> -#include <asm/alternative-asm.h> +#include <asm/alternative.h> #include <asm/export.h> .pushsection .noinstr.text, "ax" diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S index 0bfd26e4ca9e..9827ae267f96 100644 --- a/tools/arch/x86/lib/memset_64.S +++ b/tools/arch/x86/lib/memset_64.S @@ -3,7 +3,7 @@ #include <linux/linkage.h> #include <asm/cpufeatures.h> -#include <asm/alternative-asm.h> +#include <asm/alternative.h> #include <asm/export.h> /* diff --git a/tools/include/asm/alternative-asm.h b/tools/include/asm/alternative.h index b54bd860dff6..b54bd860dff6 100644 --- a/tools/include/asm/alternative-asm.h +++ b/tools/include/asm/alternative.h diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index ce58cff99b66..6de5a7fc066b 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -863,9 +863,18 @@ __SYSCALL(__NR_process_madvise, sys_process_madvise) __SC_COMP(__NR_epoll_pwait2, sys_epoll_pwait2, compat_sys_epoll_pwait2) #define __NR_mount_setattr 442 __SYSCALL(__NR_mount_setattr, sys_mount_setattr) +#define __NR_quotactl_path 443 +__SYSCALL(__NR_quotactl_path, sys_quotactl_path) + +#define __NR_landlock_create_ruleset 444 +__SYSCALL(__NR_landlock_create_ruleset, sys_landlock_create_ruleset) +#define __NR_landlock_add_rule 445 +__SYSCALL(__NR_landlock_add_rule, sys_landlock_add_rule) +#define __NR_landlock_restrict_self 446 +__SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self) #undef __NR_syscalls -#define __NR_syscalls 443 +#define __NR_syscalls 447 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 0827037c5484..67b94bc3c885 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -625,30 +625,147 @@ struct drm_gem_open { __u64 size; }; +/** + * DRM_CAP_DUMB_BUFFER + * + * If set to 1, the driver supports creating dumb buffers via the + * &DRM_IOCTL_MODE_CREATE_DUMB ioctl. + */ #define DRM_CAP_DUMB_BUFFER 0x1 +/** + * DRM_CAP_VBLANK_HIGH_CRTC + * + * If set to 1, the kernel supports specifying a CRTC index in the high bits of + * &drm_wait_vblank_request.type. + * + * Starting kernel version 2.6.39, this capability is always set to 1. + */ #define DRM_CAP_VBLANK_HIGH_CRTC 0x2 +/** + * DRM_CAP_DUMB_PREFERRED_DEPTH + * + * The preferred bit depth for dumb buffers. + * + * The bit depth is the number of bits used to indicate the color of a single + * pixel excluding any padding. This is different from the number of bits per + * pixel. For instance, XRGB8888 has a bit depth of 24 but has 32 bits per + * pixel. + * + * Note that this preference only applies to dumb buffers, it's irrelevant for + * other types of buffers. + */ #define DRM_CAP_DUMB_PREFERRED_DEPTH 0x3 +/** + * DRM_CAP_DUMB_PREFER_SHADOW + * + * If set to 1, the driver prefers userspace to render to a shadow buffer + * instead of directly rendering to a dumb buffer. For best speed, userspace + * should do streaming ordered memory copies into the dumb buffer and never + * read from it. + * + * Note that this preference only applies to dumb buffers, it's irrelevant for + * other types of buffers. + */ #define DRM_CAP_DUMB_PREFER_SHADOW 0x4 +/** + * DRM_CAP_PRIME + * + * Bitfield of supported PRIME sharing capabilities. See &DRM_PRIME_CAP_IMPORT + * and &DRM_PRIME_CAP_EXPORT. + * + * PRIME buffers are exposed as dma-buf file descriptors. See + * Documentation/gpu/drm-mm.rst, section "PRIME Buffer Sharing". + */ #define DRM_CAP_PRIME 0x5 +/** + * DRM_PRIME_CAP_IMPORT + * + * If this bit is set in &DRM_CAP_PRIME, the driver supports importing PRIME + * buffers via the &DRM_IOCTL_PRIME_FD_TO_HANDLE ioctl. + */ #define DRM_PRIME_CAP_IMPORT 0x1 +/** + * DRM_PRIME_CAP_EXPORT + * + * If this bit is set in &DRM_CAP_PRIME, the driver supports exporting PRIME + * buffers via the &DRM_IOCTL_PRIME_HANDLE_TO_FD ioctl. + */ #define DRM_PRIME_CAP_EXPORT 0x2 +/** + * DRM_CAP_TIMESTAMP_MONOTONIC + * + * If set to 0, the kernel will report timestamps with ``CLOCK_REALTIME`` in + * struct drm_event_vblank. If set to 1, the kernel will report timestamps with + * ``CLOCK_MONOTONIC``. See ``clock_gettime(2)`` for the definition of these + * clocks. + * + * Starting from kernel version 2.6.39, the default value for this capability + * is 1. Starting kernel version 4.15, this capability is always set to 1. + */ #define DRM_CAP_TIMESTAMP_MONOTONIC 0x6 +/** + * DRM_CAP_ASYNC_PAGE_FLIP + * + * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC. + */ #define DRM_CAP_ASYNC_PAGE_FLIP 0x7 -/* - * The CURSOR_WIDTH and CURSOR_HEIGHT capabilities return a valid widthxheight - * combination for the hardware cursor. The intention is that a hardware - * agnostic userspace can query a cursor plane size to use. +/** + * DRM_CAP_CURSOR_WIDTH + * + * The ``CURSOR_WIDTH`` and ``CURSOR_HEIGHT`` capabilities return a valid + * width x height combination for the hardware cursor. The intention is that a + * hardware agnostic userspace can query a cursor plane size to use. * * Note that the cross-driver contract is to merely return a valid size; * drivers are free to attach another meaning on top, eg. i915 returns the * maximum plane size. */ #define DRM_CAP_CURSOR_WIDTH 0x8 +/** + * DRM_CAP_CURSOR_HEIGHT + * + * See &DRM_CAP_CURSOR_WIDTH. + */ #define DRM_CAP_CURSOR_HEIGHT 0x9 +/** + * DRM_CAP_ADDFB2_MODIFIERS + * + * If set to 1, the driver supports supplying modifiers in the + * &DRM_IOCTL_MODE_ADDFB2 ioctl. + */ #define DRM_CAP_ADDFB2_MODIFIERS 0x10 +/** + * DRM_CAP_PAGE_FLIP_TARGET + * + * If set to 1, the driver supports the &DRM_MODE_PAGE_FLIP_TARGET_ABSOLUTE and + * &DRM_MODE_PAGE_FLIP_TARGET_RELATIVE flags in + * &drm_mode_crtc_page_flip_target.flags for the &DRM_IOCTL_MODE_PAGE_FLIP + * ioctl. + */ #define DRM_CAP_PAGE_FLIP_TARGET 0x11 +/** + * DRM_CAP_CRTC_IN_VBLANK_EVENT + * + * If set to 1, the kernel supports reporting the CRTC ID in + * &drm_event_vblank.crtc_id for the &DRM_EVENT_VBLANK and + * &DRM_EVENT_FLIP_COMPLETE events. + * + * Starting kernel version 4.12, this capability is always set to 1. + */ #define DRM_CAP_CRTC_IN_VBLANK_EVENT 0x12 +/** + * DRM_CAP_SYNCOBJ + * + * If set to 1, the driver supports sync objects. See + * Documentation/gpu/drm-mm.rst, section "DRM Sync Objects". + */ #define DRM_CAP_SYNCOBJ 0x13 +/** + * DRM_CAP_SYNCOBJ_TIMELINE + * + * If set to 1, the driver supports timeline operations on sync objects. See + * Documentation/gpu/drm-mm.rst, section "DRM Sync Objects". + */ #define DRM_CAP_SYNCOBJ_TIMELINE 0x14 /* DRM_IOCTL_GET_CAP ioctl argument type */ diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 1987e2ea79a3..ddc47bbf48b6 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -943,6 +943,7 @@ struct drm_i915_gem_exec_object { __u64 offset; }; +/* DRM_IOCTL_I915_GEM_EXECBUFFER was removed in Linux 5.13 */ struct drm_i915_gem_execbuffer { /** * List of buffers to be validated with their relocations to be diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index f6afee209620..3fd9a7e9d90c 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1078,6 +1078,10 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_DIRTY_LOG_RING 192 #define KVM_CAP_X86_BUS_LOCK_EXIT 193 #define KVM_CAP_PPC_DAWR1 194 +#define KVM_CAP_SET_GUEST_DEBUG2 195 +#define KVM_CAP_SGX_ATTRIBUTE 196 +#define KVM_CAP_VM_COPY_ENC_CONTEXT_FROM 197 +#define KVM_CAP_PTP_KVM 198 #ifdef KVM_CAP_IRQ_ROUTING @@ -1671,6 +1675,8 @@ enum sev_cmd_id { KVM_SEV_CERT_EXPORT, /* Attestation report */ KVM_SEV_GET_ATTESTATION_REPORT, + /* Guest Migration Extension */ + KVM_SEV_SEND_CANCEL, KVM_SEV_NR_MAX, }; @@ -1729,6 +1735,45 @@ struct kvm_sev_attestation_report { __u32 len; }; +struct kvm_sev_send_start { + __u32 policy; + __u64 pdh_cert_uaddr; + __u32 pdh_cert_len; + __u64 plat_certs_uaddr; + __u32 plat_certs_len; + __u64 amd_certs_uaddr; + __u32 amd_certs_len; + __u64 session_uaddr; + __u32 session_len; +}; + +struct kvm_sev_send_update_data { + __u64 hdr_uaddr; + __u32 hdr_len; + __u64 guest_uaddr; + __u32 guest_len; + __u64 trans_uaddr; + __u32 trans_len; +}; + +struct kvm_sev_receive_start { + __u32 handle; + __u32 policy; + __u64 pdh_uaddr; + __u32 pdh_len; + __u64 session_uaddr; + __u32 session_len; +}; + +struct kvm_sev_receive_update_data { + __u64 hdr_uaddr; + __u32 hdr_len; + __u64 guest_uaddr; + __u32 guest_len; + __u64 trans_uaddr; + __u32 trans_len; +}; + #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) #define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1) #define KVM_DEV_ASSIGN_MASK_INTX (1 << 2) diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 14332f4cf816..bf8143505c49 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -127,6 +127,7 @@ enum perf_sw_ids { PERF_COUNT_SW_EMULATION_FAULTS = 8, PERF_COUNT_SW_DUMMY = 9, PERF_COUNT_SW_BPF_OUTPUT = 10, + PERF_COUNT_SW_CGROUP_SWITCHES = 11, PERF_COUNT_SW_MAX, /* non-ABI */ }; @@ -326,6 +327,7 @@ enum perf_event_read_format { #define PERF_ATTR_SIZE_VER4 104 /* add: sample_regs_intr */ #define PERF_ATTR_SIZE_VER5 112 /* add: aux_watermark */ #define PERF_ATTR_SIZE_VER6 120 /* add: aux_sample_size */ +#define PERF_ATTR_SIZE_VER7 128 /* add: sig_data */ /* * Hardware event_id to monitor via a performance monitoring event: @@ -404,7 +406,10 @@ struct perf_event_attr { cgroup : 1, /* include cgroup events */ text_poke : 1, /* include text poke events */ build_id : 1, /* use build id in mmap2 events */ - __reserved_1 : 29; + inherit_thread : 1, /* children only inherit if cloned with CLONE_THREAD */ + remove_on_exec : 1, /* event is removed from task on exec */ + sigtrap : 1, /* send synchronous SIGTRAP on event */ + __reserved_1 : 26; union { __u32 wakeup_events; /* wakeup every n events */ @@ -456,6 +461,12 @@ struct perf_event_attr { __u16 __reserved_2; __u32 aux_sample_size; __u32 __reserved_3; + + /* + * User provided data if sigtrap=1, passed back to user via + * siginfo_t::si_perf, e.g. to permit user to identify the event. + */ + __u64 sig_data; }; /* @@ -1171,10 +1182,15 @@ enum perf_callchain_context { /** * PERF_RECORD_AUX::flags bits */ -#define PERF_AUX_FLAG_TRUNCATED 0x01 /* record was truncated to fit */ -#define PERF_AUX_FLAG_OVERWRITE 0x02 /* snapshot from overwrite mode */ -#define PERF_AUX_FLAG_PARTIAL 0x04 /* record contains gaps */ -#define PERF_AUX_FLAG_COLLISION 0x08 /* sample collided with another */ +#define PERF_AUX_FLAG_TRUNCATED 0x01 /* record was truncated to fit */ +#define PERF_AUX_FLAG_OVERWRITE 0x02 /* snapshot from overwrite mode */ +#define PERF_AUX_FLAG_PARTIAL 0x04 /* record contains gaps */ +#define PERF_AUX_FLAG_COLLISION 0x08 /* sample collided with another */ +#define PERF_AUX_FLAG_PMU_FORMAT_TYPE_MASK 0xff00 /* PMU specific trace format type */ + +/* CoreSight PMU AUX buffer formats */ +#define PERF_AUX_FLAG_CORESIGHT_FORMAT_CORESIGHT 0x0000 /* Default for backward compatibility */ +#define PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW 0x0100 /* Raw format of the source */ #define PERF_FLAG_FD_NO_GROUP (1UL << 0) #define PERF_FLAG_FD_OUTPUT (1UL << 1) diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index 667f1aed091c..18a9f59dc067 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -255,4 +255,8 @@ struct prctl_mm_map { # define SYSCALL_DISPATCH_FILTER_ALLOW 0 # define SYSCALL_DISPATCH_FILTER_BLOCK 1 +/* Set/get enabled arm64 pointer authentication keys */ +#define PR_PAC_SET_ENABLED_KEYS 60 +#define PR_PAC_GET_ENABLED_KEYS 61 + #endif /* _LINUX_PRCTL_H */ diff --git a/tools/kvm/kvm_stat/kvm_stat.txt b/tools/kvm/kvm_stat/kvm_stat.txt index feaf46451e83..3a9f2037bd23 100644 --- a/tools/kvm/kvm_stat/kvm_stat.txt +++ b/tools/kvm/kvm_stat/kvm_stat.txt @@ -111,7 +111,7 @@ OPTIONS --tracepoints:: retrieve statistics from tracepoints -*z*:: +-z:: --skip-zero-records:: omit records with all zeros in logging mode diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index cedf3ede7545..24295d39713b 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -19,6 +19,7 @@ #include <objtool/elf.h> #include <objtool/arch.h> #include <objtool/warn.h> +#include <objtool/endianness.h> #include <arch/elf.h> static int is_x86_64(const struct elf *elf) @@ -725,7 +726,7 @@ static int elf_add_alternative(struct elf *elf, return -1; } - alt->cpuid = cpuid; + alt->cpuid = bswap_if_needed(cpuid); alt->instrlen = orig_len; alt->replacementlen = repl_len; diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index d08f5f3670f8..743c2e9d0f56 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -762,6 +762,7 @@ struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name) data->d_buf = &sym->sym; data->d_size = sizeof(sym->sym); data->d_align = 1; + data->d_type = ELF_T_SYM; sym->idx = symtab->len / sizeof(sym->sym); diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 0d6619064a83..406a9519145e 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -540,6 +540,7 @@ ifndef NO_LIBELF ifdef LIBBPF_DYNAMIC ifeq ($(feature-libbpf), 1) EXTLIBS += -lbpf + $(call detected,CONFIG_LIBBPF_DYNAMIC) else dummy := $(error Error: No libbpf devel library found, please install libbpf-devel); endif diff --git a/tools/perf/arch/arm64/util/kvm-stat.c b/tools/perf/arch/arm64/util/kvm-stat.c index 2303256b7d05..73d18e0ed6f6 100644 --- a/tools/perf/arch/arm64/util/kvm-stat.c +++ b/tools/perf/arch/arm64/util/kvm-stat.c @@ -71,7 +71,7 @@ struct kvm_reg_events_ops kvm_reg_events_ops[] = { .name = "vmexit", .ops = &exit_events, }, - { NULL }, + { NULL, NULL }, }; const char * const kvm_skip_events[] = { diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl index 91649690b52f..9974f5f8e49b 100644 --- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl +++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl @@ -356,3 +356,8 @@ 439 n64 faccessat2 sys_faccessat2 440 n64 process_madvise sys_process_madvise 441 n64 epoll_pwait2 sys_epoll_pwait2 +442 n64 mount_setattr sys_mount_setattr +443 n64 quotactl_path sys_quotactl_path +444 n64 landlock_create_ruleset sys_landlock_create_ruleset +445 n64 landlock_add_rule sys_landlock_add_rule +446 n64 landlock_restrict_self sys_landlock_restrict_self diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index 0b2480cf3e47..2e68fbb57cc6 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -522,3 +522,7 @@ 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr +443 common quotactl_path sys_quotactl_path +444 common landlock_create_ruleset sys_landlock_create_ruleset +445 common landlock_add_rule sys_landlock_add_rule +446 common landlock_restrict_self sys_landlock_restrict_self diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index 3abef2144dac..7e4a2aba366d 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -445,3 +445,7 @@ 440 common process_madvise sys_process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr sys_mount_setattr +443 common quotactl_path sys_quotactl_path sys_quotactl_path +444 common landlock_create_ruleset sys_landlock_create_ruleset sys_landlock_create_ruleset +445 common landlock_add_rule sys_landlock_add_rule sys_landlock_add_rule +446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 7bf01cbe582f..ecd551b08d05 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -364,6 +364,10 @@ 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr +443 common quotactl_path sys_quotactl_path +444 common landlock_create_ruleset sys_landlock_create_ruleset +445 common landlock_add_rule sys_landlock_add_rule +446 common landlock_restrict_self sys_landlock_restrict_self # # Due to a historical design error, certain syscalls are numbered differently diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index ed4f0bd72e5a..7422b0ea8790 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -1123,8 +1123,10 @@ static int process_one_file(const char *fpath, const struct stat *sb, mapfile = strdup(fpath); return 0; } - - pr_info("%s: Ignoring file %s\n", prog, fpath); + if (is_json_file(bname)) + pr_debug("%s: ArchStd json is preprocessed %s\n", prog, fpath); + else + pr_info("%s: Ignoring file %s\n", prog, fpath); return 0; } diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record index 645009c08b3c..4a7b8deef3fd 100644 --- a/tools/perf/tests/attr/base-record +++ b/tools/perf/tests/attr/base-record @@ -5,7 +5,7 @@ group_fd=-1 flags=0|8 cpu=* type=0|1 -size=120 +size=128 config=0 sample_period=* sample_type=263 diff --git a/tools/perf/tests/attr/base-stat b/tools/perf/tests/attr/base-stat index b0f42c34882e..408164456530 100644 --- a/tools/perf/tests/attr/base-stat +++ b/tools/perf/tests/attr/base-stat @@ -5,7 +5,7 @@ group_fd=-1 flags=0|8 cpu=* type=0 -size=120 +size=128 config=0 sample_period=0 sample_type=65536 diff --git a/tools/perf/tests/attr/system-wide-dummy b/tools/perf/tests/attr/system-wide-dummy index eba723cc0d38..86a15dd359d9 100644 --- a/tools/perf/tests/attr/system-wide-dummy +++ b/tools/perf/tests/attr/system-wide-dummy @@ -7,7 +7,7 @@ cpu=* pid=-1 flags=8 type=1 -size=120 +size=128 config=9 sample_period=4000 sample_type=455 diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 8c0d9f368ebc..b64bdc1a7026 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -145,7 +145,14 @@ perf-$(CONFIG_LIBELF) += symbol-elf.o perf-$(CONFIG_LIBELF) += probe-file.o perf-$(CONFIG_LIBELF) += probe-event.o +ifdef CONFIG_LIBBPF_DYNAMIC + hashmap := 1 +endif ifndef CONFIG_LIBBPF + hashmap := 1 +endif + +ifdef hashmap perf-y += hashmap.o endif diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c index f99852d54b14..43e5b563dee8 100644 --- a/tools/perf/util/record.c +++ b/tools/perf/util/record.c @@ -157,9 +157,15 @@ static int get_max_rate(unsigned int *rate) static int record_opts__config_freq(struct record_opts *opts) { bool user_freq = opts->user_freq != UINT_MAX; + bool user_interval = opts->user_interval != ULLONG_MAX; unsigned int max_rate; - if (opts->user_interval != ULLONG_MAX) + if (user_interval && user_freq) { + pr_err("cannot set frequency and period at the same time\n"); + return -1; + } + + if (user_interval) opts->default_interval = opts->user_interval; if (user_freq) opts->freq = opts->user_freq; diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index a12cf4f0e97a..106b3d60881a 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -904,7 +904,7 @@ static void perf_event__cpu_map_swap(union perf_event *event, struct perf_record_record_cpu_map *mask; unsigned i; - data->type = bswap_64(data->type); + data->type = bswap_16(data->type); switch (data->type) { case PERF_CPU_MAP__CPUS: @@ -937,7 +937,7 @@ static void perf_event__stat_config_swap(union perf_event *event, { u64 size; - size = event->stat_config.nr * sizeof(event->stat_config.data[0]); + size = bswap_64(event->stat_config.nr) * sizeof(event->stat_config.data[0]); size += 1; /* nr item itself */ mem_bswap_64(&event->stat_config.nr, size); } diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c index c62d372d426f..ed563bdd88f3 100644 --- a/tools/testing/nvdimm/test/iomap.c +++ b/tools/testing/nvdimm/test/iomap.c @@ -62,7 +62,7 @@ struct nfit_test_resource *get_nfit_res(resource_size_t resource) } EXPORT_SYMBOL(get_nfit_res); -void __iomem *__nfit_test_ioremap(resource_size_t offset, unsigned long size, +static void __iomem *__nfit_test_ioremap(resource_size_t offset, unsigned long size, void __iomem *(*fallback_fn)(resource_size_t, unsigned long)) { struct nfit_test_resource *nfit_res = get_nfit_res(offset); diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index 9b185bf82da8..54f367cbadae 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -1871,9 +1871,16 @@ static void smart_init(struct nfit_test *t) } } +static size_t sizeof_spa(struct acpi_nfit_system_address *spa) +{ + /* until spa location cookie support is added... */ + return sizeof(*spa) - 8; +} + static int nfit_test0_alloc(struct nfit_test *t) { - size_t nfit_size = sizeof(struct acpi_nfit_system_address) * NUM_SPA + struct acpi_nfit_system_address *spa = NULL; + size_t nfit_size = sizeof_spa(spa) * NUM_SPA + sizeof(struct acpi_nfit_memory_map) * NUM_MEM + sizeof(struct acpi_nfit_control_region) * NUM_DCR + offsetof(struct acpi_nfit_control_region, @@ -1937,7 +1944,8 @@ static int nfit_test0_alloc(struct nfit_test *t) static int nfit_test1_alloc(struct nfit_test *t) { - size_t nfit_size = sizeof(struct acpi_nfit_system_address) * 2 + struct acpi_nfit_system_address *spa = NULL; + size_t nfit_size = sizeof_spa(spa) * 2 + sizeof(struct acpi_nfit_memory_map) * 2 + offsetof(struct acpi_nfit_control_region, window_size) * 2; int i; @@ -2000,7 +2008,7 @@ static void nfit_test0_setup(struct nfit_test *t) */ spa = nfit_buf; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_PM), 16); spa->range_index = 0+1; spa->address = t->spa_set_dma[0]; @@ -2014,7 +2022,7 @@ static void nfit_test0_setup(struct nfit_test *t) */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_PM), 16); spa->range_index = 1+1; spa->address = t->spa_set_dma[1]; @@ -2024,7 +2032,7 @@ static void nfit_test0_setup(struct nfit_test *t) /* spa2 (dcr0) dimm0 */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16); spa->range_index = 2+1; spa->address = t->dcr_dma[0]; @@ -2034,7 +2042,7 @@ static void nfit_test0_setup(struct nfit_test *t) /* spa3 (dcr1) dimm1 */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16); spa->range_index = 3+1; spa->address = t->dcr_dma[1]; @@ -2044,7 +2052,7 @@ static void nfit_test0_setup(struct nfit_test *t) /* spa4 (dcr2) dimm2 */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16); spa->range_index = 4+1; spa->address = t->dcr_dma[2]; @@ -2054,7 +2062,7 @@ static void nfit_test0_setup(struct nfit_test *t) /* spa5 (dcr3) dimm3 */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16); spa->range_index = 5+1; spa->address = t->dcr_dma[3]; @@ -2064,7 +2072,7 @@ static void nfit_test0_setup(struct nfit_test *t) /* spa6 (bdw for dcr0) dimm0 */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16); spa->range_index = 6+1; spa->address = t->dimm_dma[0]; @@ -2074,7 +2082,7 @@ static void nfit_test0_setup(struct nfit_test *t) /* spa7 (bdw for dcr1) dimm1 */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16); spa->range_index = 7+1; spa->address = t->dimm_dma[1]; @@ -2084,7 +2092,7 @@ static void nfit_test0_setup(struct nfit_test *t) /* spa8 (bdw for dcr2) dimm2 */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16); spa->range_index = 8+1; spa->address = t->dimm_dma[2]; @@ -2094,7 +2102,7 @@ static void nfit_test0_setup(struct nfit_test *t) /* spa9 (bdw for dcr3) dimm3 */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16); spa->range_index = 9+1; spa->address = t->dimm_dma[3]; @@ -2581,7 +2589,7 @@ static void nfit_test0_setup(struct nfit_test *t) /* spa10 (dcr4) dimm4 */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16); spa->range_index = 10+1; spa->address = t->dcr_dma[4]; @@ -2595,7 +2603,7 @@ static void nfit_test0_setup(struct nfit_test *t) */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_PM), 16); spa->range_index = 11+1; spa->address = t->spa_set_dma[2]; @@ -2605,7 +2613,7 @@ static void nfit_test0_setup(struct nfit_test *t) /* spa12 (bdw for dcr4) dimm4 */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16); spa->range_index = 12+1; spa->address = t->dimm_dma[4]; @@ -2739,7 +2747,7 @@ static void nfit_test1_setup(struct nfit_test *t) /* spa0 (flat range with no bdw aliasing) */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_PM), 16); spa->range_index = 0+1; spa->address = t->spa_set_dma[0]; @@ -2749,7 +2757,7 @@ static void nfit_test1_setup(struct nfit_test *t) /* virtual cd region */ spa = nfit_buf + offset; spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS; - spa->header.length = sizeof(*spa); + spa->header.length = sizeof_spa(spa); memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_VCD), 16); spa->range_index = 0; spa->address = t->spa_set_dma[1]; diff --git a/tools/testing/selftests/arm64/bti/test.c b/tools/testing/selftests/arm64/bti/test.c index 656b04976ccc..67b77ab83c20 100644 --- a/tools/testing/selftests/arm64/bti/test.c +++ b/tools/testing/selftests/arm64/bti/test.c @@ -6,6 +6,7 @@ #include "system.h" +#include <stddef.h> #include <linux/errno.h> #include <linux/auxvec.h> #include <linux/signal.h> diff --git a/tools/testing/selftests/kvm/lib/x86_64/handlers.S b/tools/testing/selftests/kvm/lib/x86_64/handlers.S index aaf7bc7d2ce1..7629819734af 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/handlers.S +++ b/tools/testing/selftests/kvm/lib/x86_64/handlers.S @@ -54,9 +54,9 @@ idt_handlers: .align 8 /* Fetch current address and append it to idt_handlers. */ - current_handler = . +666 : .pushsection .rodata -.quad current_handler + .quad 666b .popsection .if ! \has_error diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c index ca22ee6d19cb..63096cea26c6 100644 --- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c +++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c @@ -18,6 +18,28 @@ #include "vmx.h" #define VCPU_ID 5 +#define NMI_VECTOR 2 + +static int ud_count; + +void enable_x2apic(void) +{ + uint32_t spiv_reg = APIC_BASE_MSR + (APIC_SPIV >> 4); + + wrmsr(MSR_IA32_APICBASE, rdmsr(MSR_IA32_APICBASE) | + MSR_IA32_APICBASE_ENABLE | MSR_IA32_APICBASE_EXTD); + wrmsr(spiv_reg, rdmsr(spiv_reg) | APIC_SPIV_APIC_ENABLED); +} + +static void guest_ud_handler(struct ex_regs *regs) +{ + ud_count++; + regs->rip += 3; /* VMLAUNCH */ +} + +static void guest_nmi_handler(struct ex_regs *regs) +{ +} void l2_guest_code(void) { @@ -25,15 +47,23 @@ void l2_guest_code(void) GUEST_SYNC(8); + /* Forced exit to L1 upon restore */ + GUEST_SYNC(9); + /* Done, exit to L1 and never come back. */ vmcall(); } -void l1_guest_code(struct vmx_pages *vmx_pages) +void guest_code(struct vmx_pages *vmx_pages) { #define L2_GUEST_STACK_SIZE 64 unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE]; + enable_x2apic(); + + GUEST_SYNC(1); + GUEST_SYNC(2); + enable_vp_assist(vmx_pages->vp_assist_gpa, vmx_pages->vp_assist); GUEST_ASSERT(vmx_pages->vmcs_gpa); @@ -55,27 +85,40 @@ void l1_guest_code(struct vmx_pages *vmx_pages) current_evmcs->revision_id = EVMCS_VERSION; GUEST_SYNC(6); + current_evmcs->pin_based_vm_exec_control |= + PIN_BASED_NMI_EXITING; GUEST_ASSERT(!vmlaunch()); GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa); - GUEST_SYNC(9); + + /* + * NMI forces L2->L1 exit, resuming L2 and hope that EVMCS is + * up-to-date (RIP points where it should and not at the beginning + * of l2_guest_code(). GUEST_SYNC(9) checkes that. + */ GUEST_ASSERT(!vmresume()); - GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); + GUEST_SYNC(10); + + GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL); + GUEST_SYNC(11); + + /* Try enlightened vmptrld with an incorrect GPA */ + evmcs_vmptrld(0xdeadbeef, vmx_pages->enlightened_vmcs); + GUEST_ASSERT(vmlaunch()); + GUEST_ASSERT(ud_count == 1); + GUEST_DONE(); } -void guest_code(struct vmx_pages *vmx_pages) +void inject_nmi(struct kvm_vm *vm) { - GUEST_SYNC(1); - GUEST_SYNC(2); + struct kvm_vcpu_events events; - if (vmx_pages) - l1_guest_code(vmx_pages); + vcpu_events_get(vm, VCPU_ID, &events); - GUEST_DONE(); + events.nmi.pending = 1; + events.flags |= KVM_VCPUEVENT_VALID_NMI_PENDING; - /* Try enlightened vmptrld with an incorrect GPA */ - evmcs_vmptrld(0xdeadbeef, vmx_pages->enlightened_vmcs); - GUEST_ASSERT(vmlaunch()); + vcpu_events_set(vm, VCPU_ID, &events); } int main(int argc, char *argv[]) @@ -109,6 +152,13 @@ int main(int argc, char *argv[]) vcpu_alloc_vmx(vm, &vmx_pages_gva); vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva); + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + vm_handle_exception(vm, UD_VECTOR, guest_ud_handler); + vm_handle_exception(vm, NMI_VECTOR, guest_nmi_handler); + + pr_info("Running L1 which uses EVMCS to run L2\n"); + for (stage = 1;; stage++) { _vcpu_run(vm, VCPU_ID); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, @@ -124,7 +174,7 @@ int main(int argc, char *argv[]) case UCALL_SYNC: break; case UCALL_DONE: - goto part1_done; + goto done; default: TEST_FAIL("Unknown ucall %lu", uc.cmd); } @@ -154,12 +204,14 @@ int main(int argc, char *argv[]) TEST_ASSERT(!memcmp(®s1, ®s2, sizeof(regs2)), "Unexpected register values after vcpu_load_state; rdi: %lx rsi: %lx", (ulong) regs2.rdi, (ulong) regs2.rsi); - } -part1_done: - _vcpu_run(vm, VCPU_ID); - TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN, - "Unexpected successful VMEnter with invalid eVMCS pointer!"); + /* Force immediate L2->L1 exit before resuming */ + if (stage == 8) { + pr_info("Injecting NMI into L1 before L2 had a chance to run after restore\n"); + inject_nmi(vm); + } + } +done: kvm_vm_free(vm); } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 2799c6660cce..6b4feb92dc79 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2893,8 +2893,8 @@ static void grow_halt_poll_ns(struct kvm_vcpu *vcpu) if (val < grow_start) val = grow_start; - if (val > halt_poll_ns) - val = halt_poll_ns; + if (val > vcpu->kvm->max_halt_poll_ns) + val = vcpu->kvm->max_halt_poll_ns; vcpu->halt_poll_ns = val; out: @@ -2973,7 +2973,8 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) goto out; } poll_end = cur = ktime_get(); - } while (single_task_running() && ktime_before(cur, stop)); + } while (single_task_running() && !need_resched() && + ktime_before(cur, stop)); } prepare_to_rcuwait(&vcpu->wait); |