diff options
author | Andrey Konovalov <andrey.konovalov@linaro.org> | 2012-06-15 23:33:58 +0400 |
---|---|---|
committer | Andrey Konovalov <andrey.konovalov@linaro.org> | 2012-06-15 23:33:58 +0400 |
commit | 6ea8992f7affaa40638b25a9604df049febe1254 (patch) | |
tree | d189c623780ba1306e49bb661fec8acc30e548fa | |
parent | 85e9db62d226809d2c36e82bd43e93c8681f1726 (diff) | |
parent | a8b0bdaa257a2c0ec4748d5ccc4feff2b60aa730 (diff) |
Merge branch 'tracking-ubuntu-sauce' into merge-linux-linaro-core-trackingllct-20120615.1
231 files changed, 40897 insertions, 207 deletions
diff --git a/.gitignore b/.gitignore index 57af07cf7e68..268fbfedc80b 100644 --- a/.gitignore +++ b/.gitignore @@ -48,7 +48,7 @@ modules.builtin # # Debian directory (make deb-pkg) # -/debian/ +#/debian/ # # git files that we don't want to ignore even it they are dot-files diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index 8e2da1e06e3b..d88588112b7e 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -62,6 +62,7 @@ ata *); int (*removexattr) (struct dentry *, const char *); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); void (*update_time)(struct inode *, struct timespec *, int); + struct file *(*open)(struct dentry *,struct file *,const struct cred *); locking rules: all may block @@ -89,7 +90,7 @@ listxattr: no removexattr: yes fiemap: no update_time: no - +open: no Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on victim. cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem. diff --git a/Documentation/filesystems/overlayfs.txt b/Documentation/filesystems/overlayfs.txt new file mode 100644 index 000000000000..7161dc391fa9 --- /dev/null +++ b/Documentation/filesystems/overlayfs.txt @@ -0,0 +1,199 @@ +Written by: Neil Brown <neilb@suse.de> + +Overlay Filesystem +================== + +This document describes a prototype for a new approach to providing +overlay-filesystem functionality in Linux (sometimes referred to as +union-filesystems). An overlay-filesystem tries to present a +filesystem which is the result over overlaying one filesystem on top +of the other. + +The result will inevitably fail to look exactly like a normal +filesystem for various technical reasons. The expectation is that +many use cases will be able to ignore these differences. + +This approach is 'hybrid' because the objects that appear in the +filesystem do not all appear to belong to that filesystem. In many +cases an object accessed in the union will be indistinguishable +from accessing the corresponding object from the original filesystem. +This is most obvious from the 'st_dev' field returned by stat(2). + +While directories will report an st_dev from the overlay-filesystem, +all non-directory objects will report an st_dev from the lower or +upper filesystem that is providing the object. Similarly st_ino will +only be unique when combined with st_dev, and both of these can change +over the lifetime of a non-directory object. Many applications and +tools ignore these values and will not be affected. + +Upper and Lower +--------------- + +An overlay filesystem combines two filesystems - an 'upper' filesystem +and a 'lower' filesystem. When a name exists in both filesystems, the +object in the 'upper' filesystem is visible while the object in the +'lower' filesystem is either hidden or, in the case of directories, +merged with the 'upper' object. + +It would be more correct to refer to an upper and lower 'directory +tree' rather than 'filesystem' as it is quite possible for both +directory trees to be in the same filesystem and there is no +requirement that the root of a filesystem be given for either upper or +lower. + +The lower filesystem can be any filesystem supported by Linux and does +not need to be writable. The lower filesystem can even be another +overlayfs. The upper filesystem will normally be writable and if it +is it must support the creation of trusted.* extended attributes, and +must provide valid d_type in readdir responses, at least for symbolic +links - so NFS is not suitable. + +A read-only overlay of two read-only filesystems may use any +filesystem type. + +Directories +----------- + +Overlaying mainly involved directories. If a given name appears in both +upper and lower filesystems and refers to a non-directory in either, +then the lower object is hidden - the name refers only to the upper +object. + +Where both upper and lower objects are directories, a merged directory +is formed. + +At mount time, the two directories given as mount options are combined +into a merged directory: + + mount -t overlayfs overlayfs -olowerdir=/lower,upperdir=/upper /overlay + +Then whenever a lookup is requested in such a merged directory, the +lookup is performed in each actual directory and the combined result +is cached in the dentry belonging to the overlay filesystem. If both +actual lookups find directories, both are stored and a merged +directory is created, otherwise only one is stored: the upper if it +exists, else the lower. + +Only the lists of names from directories are merged. Other content +such as metadata and extended attributes are reported for the upper +directory only. These attributes of the lower directory are hidden. + +whiteouts and opaque directories +-------------------------------- + +In order to support rm and rmdir without changing the lower +filesystem, an overlay filesystem needs to record in the upper filesystem +that files have been removed. This is done using whiteouts and opaque +directories (non-directories are always opaque). + +The overlay filesystem uses extended attributes with a +"trusted.overlay." prefix to record these details. + +A whiteout is created as a symbolic link with target +"(overlay-whiteout)" and with xattr "trusted.overlay.whiteout" set to "y". +When a whiteout is found in the upper level of a merged directory, any +matching name in the lower level is ignored, and the whiteout itself +is also hidden. + +A directory is made opaque by setting the xattr "trusted.overlay.opaque" +to "y". Where the upper filesystem contains an opaque directory, any +directory in the lower filesystem with the same name is ignored. + +readdir +------- + +When a 'readdir' request is made on a merged directory, the upper and +lower directories are each read and the name lists merged in the +obvious way (upper is read first, then lower - entries that already +exist are not re-added). This merged name list is cached in the +'struct file' and so remains as long as the file is kept open. If the +directory is opened and read by two processes at the same time, they +will each have separate caches. A seekdir to the start of the +directory (offset 0) followed by a readdir will cause the cache to be +discarded and rebuilt. + +This means that changes to the merged directory do not appear while a +directory is being read. This is unlikely to be noticed by many +programs. + +seek offsets are assigned sequentially when the directories are read. +Thus if + - read part of a directory + - remember an offset, and close the directory + - re-open the directory some time later + - seek to the remembered offset + +there may be little correlation between the old and new locations in +the list of filenames, particularly if anything has changed in the +directory. + +Readdir on directories that are not merged is simply handled by the +underlying directory (upper or lower). + + +Non-directories +--------------- + +Objects that are not directories (files, symlinks, device-special +files etc.) are presented either from the upper or lower filesystem as +appropriate. When a file in the lower filesystem is accessed in a way +the requires write-access, such as opening for write access, changing +some metadata etc., the file is first copied from the lower filesystem +to the upper filesystem (copy_up). Note that creating a hard-link +also requires copy_up, though of course creation of a symlink does +not. + +The copy_up may turn out to be unnecessary, for example if the file is +opened for read-write but the data is not modified. + +The copy_up process first makes sure that the containing directory +exists in the upper filesystem - creating it and any parents as +necessary. It then creates the object with the same metadata (owner, +mode, mtime, symlink-target etc.) and then if the object is a file, the +data is copied from the lower to the upper filesystem. Finally any +extended attributes are copied up. + +Once the copy_up is complete, the overlay filesystem simply +provides direct access to the newly created file in the upper +filesystem - future operations on the file are barely noticed by the +overlay filesystem (though an operation on the name of the file such as +rename or unlink will of course be noticed and handled). + + +Non-standard behavior +--------------------- + +The copy_up operation essentially creates a new, identical file and +moves it over to the old name. The new file may be on a different +filesystem, so both st_dev and st_ino of the file may change. + +Any open files referring to this inode will access the old data and +metadata. Similarly any file locks obtained before copy_up will not +apply to the copied up file. + +On a file is opened with O_RDONLY fchmod(2), fchown(2), futimesat(2) +and fsetxattr(2) will fail with EROFS. + +If a file with multiple hard links is copied up, then this will +"break" the link. Changes will not be propagated to other names +referring to the same inode. + +Symlinks in /proc/PID/ and /proc/PID/fd which point to a non-directory +object in overlayfs will not contain vaid absolute paths, only +relative paths leading up to the filesystem's root. This will be +fixed in the future. + +Some operations are not atomic, for example a crash during copy_up or +rename will leave the filesystem in an inconsitent state. This will +be addressed in the future. + +Changes to underlying filesystems +--------------------------------- + +Offline changes, when the overlay is not mounted, are allowed to either +the upper or the lower trees. + +Changes to the underlying filesystems while part of a mounted overlay +filesystem are not allowed. If the underlying filesystem is changed, +the behavior of the overlay is undefined, though it will not result in +a crash or deadlock. diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index efd23f481704..f586bc616391 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -364,6 +364,8 @@ struct inode_operations { ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*removexattr) (struct dentry *, const char *); void (*update_time)(struct inode *, struct timespec *, int); + struct file *(*open) (struct dentry *, struct file *, + const struct cred *); }; Again, all methods are called without any locks being held, unless @@ -476,6 +478,12 @@ otherwise noted. an inode. If this is not defined the VFS will update the inode itself and call mark_inode_dirty_sync. + open: this is an alternative to f_op->open(), the difference is that this + method may return any open file, not necessarily originating from the + same filesystem as the one i_op->open() was called on. It may be useful + for stacking filesystems which want to allow native I/O directly on + underlying files. + The Address Space Object ======================== diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index a92c5ebf373e..ef9af9a052c0 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -252,12 +252,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted. For broken nForce2 BIOS resulting in XT-PIC timer. acpi_sleep= [HW,ACPI] Sleep options - Format: { s3_bios, s3_mode, s3_beep, s4_nohwsig, + Format: { s3_bios, s3_mode, s3_beep, s3_leds, s4_nohwsig, old_ordering, nonvs, sci_force_enable } See Documentation/power/video.txt for information on s3_bios and s3_mode. s3_beep is for debugging; it makes the PC's speaker beep as soon as the kernel's real-mode entry point is called. + s3_leds is for debugging; it flashes the keyboard LEDs + 3 times as soon as the kernel's real-mode entry point is + called. s4_nohwsig prevents ACPI hardware signature from being used during resume from hibernation. old_ordering causes the ACPI 1.0 ordering of the _PTS @@ -585,6 +588,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted. /proc/<pid>/coredump_filter. See also Documentation/filesystems/proc.txt. + cpufreq_driver= [X86] Allow only the named cpu frequency scaling driver + to register. Example: cpufreq_driver=powernow-k8 + Format: { none | STRING } + cpuidle.off=1 [CPU_IDLE] disable the cpuidle sub-system diff --git a/Documentation/security/Yama.txt b/Documentation/security/Yama.txt index e369de2d48cd..b72884a0a76f 100644 --- a/Documentation/security/Yama.txt +++ b/Documentation/security/Yama.txt @@ -5,10 +5,54 @@ any other LSM). Yama is controlled through sysctl in /proc/sys/kernel/yama: +- protected_sticky_symlinks +- protected_nonaccess_hardlinks - ptrace_scope ============================================================== +protected_sticky_symlinks: + +A long-standing class of security issues is the symlink-based +time-of-check-time-of-use race, most commonly seen in world-writable +directories like /tmp. The common method of exploitation of this flaw +is to cross privilege boundaries when following a given symlink (i.e. a +root process follows a symlink belonging to another user). For a likely +incomplete list of hundreds of examples across the years, please see: +http://cve.mitre.org/cgi-bin/cvekey.cgi?keyword=/tmp + +When set to "0", symlink following behavior is unrestricted. + +When set to "1" symlinks are permitted to be followed only when outside +a sticky world-writable directory, or when the uid of the symlink and +follower match, or when the directory owner matches the symlink's owner. + +This protection is based on the restrictions in Openwall and grsecurity. + +============================================================== + +protected_nonaccess_hardlinks: + +Hardlinks can be abused in a similar fashion to symlinks in sticky +world-writable directories, but their weakness is not limited to +just that scenario. For example, if /etc and /home are on the same +partition, a regular user can create a hardlink to /etc/shadow in their +home directory. While it retains the original owner and permissions, +it is possible for privileged programs that are otherwise symlink-safe +to mistakenly access the file through its hardlink. Additionally, a very +minor untraceable quota-bypassing local denial of service is possible by +an attacker exhausting disk space by filling a world-writable directory +with hardlinks. + +When set to "0", hardlink creation behavior is unrestricted. + +When set to "1", hardlinks cannot be created to files that a given user +would be unable to read and write originally, or are otherwise sensitive. + +This protection is based on the restrictions in Openwall and grsecurity. + +============================================================== + ptrace_scope: As Linux grows in popularity, it will become a larger target for diff --git a/MAINTAINERS b/MAINTAINERS index f6e62def61cd..14f339aa3317 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5064,6 +5064,13 @@ F: drivers/scsi/osd/ F: include/scsi/osd_* F: fs/exofs/ +OVERLAYFS FILESYSTEM +M: Miklos Szeredi <miklos@szeredi.hu> +L: linux-fsdevel@vger.kernel.org +S: Supported +F: fs/overlayfs/* +F: Documentation/filesystems/overlayfs.txt + P54 WIRELESS DRIVER M: Christian Lamparter <chunkeey@googlemail.com> L: linux-wireless@vger.kernel.org @@ -349,14 +349,23 @@ CFLAGS_KERNEL = AFLAGS_KERNEL = CFLAGS_GCOV = -fprofile-arcs -ftest-coverage +# Prefer linux-backports-modules +ifneq ($(KBUILD_SRC),) +ifneq ($(shell if test -e $(KBUILD_OUTPUT)/ubuntu-build; then echo yes; fi),yes) +UBUNTUINCLUDE := -I/usr/src/linux-headers-lbm-$(KERNELRELEASE) +endif +endif # Use LINUXINCLUDE when you must reference the include/ directory. # Needed to be compatible with the O= option -LINUXINCLUDE := -I$(srctree)/arch/$(hdr-arch)/include \ +LINUXINCLUDE := $(UBUNTUINCLUDE) -I$(srctree)/arch/$(hdr-arch)/include \ -Iarch/$(hdr-arch)/include/generated -Iinclude \ $(if $(KBUILD_SRC), -I$(srctree)/include) \ -include $(srctree)/include/linux/kconfig.h +# UBUNTU: Include our third party driver stuff too +LINUXINCLUDE += -Iubuntu/include $(if $(KBUILD_SRC),-I$(srctree)/ubuntu/include) + KBUILD_CPPFLAGS := -D__KERNEL__ KBUILD_CFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ @@ -504,7 +513,7 @@ scripts: scripts_basic include/config/auto.conf include/config/tristate.conf # Objects we will link into vmlinux / subdirs we need to visit init-y := init/ -drivers-y := drivers/ sound/ firmware/ +drivers-y := drivers/ sound/ firmware/ ubuntu/ net-y := net/ libs-y := lib/ core-y := usr/ @@ -896,6 +905,7 @@ headers_install: __headers $(error Headers not exportable for the $(SRCARCH) architecture)) $(Q)$(MAKE) $(hdr-inst)=include $(Q)$(MAKE) $(hdr-inst)=arch/$(hdr-arch)/include/asm $(hdr-dst) + $(Q)$(MAKE) $(hdr-inst)=ubuntu/include dst=include oldheaders= PHONY += headers_check_all headers_check_all: headers_install_all @@ -905,6 +915,7 @@ PHONY += headers_check headers_check: headers_install $(Q)$(MAKE) $(hdr-inst)=include HDRCHECK=1 $(Q)$(MAKE) $(hdr-inst)=arch/$(hdr-arch)/include/asm $(hdr-dst) HDRCHECK=1 + $(Q)$(MAKE) $(hdr-inst)=ubuntu/include dst=include oldheaders= HDRCHECK=1 # --------------------------------------------------------------------------- # Modules diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index b4524b9bc191..9176e10249cd 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -2314,6 +2314,8 @@ source "net/Kconfig" source "drivers/Kconfig" +source "ubuntu/Kconfig" + source "fs/Kconfig" source "arch/arm/Kconfig.debug" diff --git a/arch/arm/boot/dts/highbank.dts b/arch/arm/boot/dts/highbank.dts index 83e72294aefb..e735731ae399 100644 --- a/arch/arm/boot/dts/highbank.dts +++ b/arch/arm/boot/dts/highbank.dts @@ -124,6 +124,10 @@ interrupts = <0 7 4>; }; + ipc-keys { + compatible = "calxeda,hb-keys"; + }; + gpioe: gpio@fff30000 { #gpio-cells = <2>; compatible = "arm,pl061", "arm,primecell"; diff --git a/arch/arm/include/asm/div64.h b/arch/arm/include/asm/div64.h index fe92ccf1d0b0..2dedab7ae089 100644 --- a/arch/arm/include/asm/div64.h +++ b/arch/arm/include/asm/div64.h @@ -73,6 +73,7 @@ #define do_div(n, base) \ ({ \ unsigned int __r, __b = (base); \ + asm("" : "+r" (__b)); \ if (!__builtin_constant_p(__b) || __b == 0 || \ (__LINUX_ARM_ARCH__ < 4 && (__b & (__b - 1)) != 0)) { \ /* non-constant divisor (or zero): slow path */ \ diff --git a/arch/arm/mach-highbank/Makefile b/arch/arm/mach-highbank/Makefile index f8437dd238c2..3d4126a9ed82 100644 --- a/arch/arm/mach-highbank/Makefile +++ b/arch/arm/mach-highbank/Makefile @@ -1,5 +1,11 @@ -obj-y := clock.o highbank.o system.o +obj-y := clock.o highbank.o system.o smc.o + +plus_sec := $(call as-instr,.arch_extension sec,+sec) +AFLAGS_smc.o :=-Wa,-march=armv7-a$(plus_sec) + obj-$(CONFIG_DEBUG_HIGHBANK_UART) += lluart.o obj-$(CONFIG_SMP) += platsmp.o obj-$(CONFIG_HOTPLUG_CPU) += hotplug.o obj-$(CONFIG_PM_SLEEP) += pm.o + +obj-y += pl320-ipc.o diff --git a/arch/arm/mach-highbank/core.h b/arch/arm/mach-highbank/core.h index d8e2d0be64ac..141ed5171826 100644 --- a/arch/arm/mach-highbank/core.h +++ b/arch/arm/mach-highbank/core.h @@ -8,3 +8,4 @@ extern void highbank_lluart_map_io(void); static inline void highbank_lluart_map_io(void) {} #endif +extern void highbank_smc1(int fn, int arg); diff --git a/arch/arm/mach-highbank/highbank.c b/arch/arm/mach-highbank/highbank.c index 410a112bb52e..0ab6b34ba031 100644 --- a/arch/arm/mach-highbank/highbank.c +++ b/arch/arm/mach-highbank/highbank.c @@ -85,10 +85,25 @@ const static struct of_device_id irq_match[] = { {} }; +#ifdef CONFIG_CACHE_L2X0 +static void highbank_l2x0_disable(void) +{ + /* Disable PL310 L2 Cache controller */ + highbank_smc1(0x102, 0x0); +} +#endif + + static void __init highbank_init_irq(void) { of_irq_init(irq_match); + +#ifdef CONFIG_CACHE_L2X0 + /* Enable PL310 L2 Cache controller */ + highbank_smc1(0x102, 0x1); l2x0_of_init(0, ~0UL); + outer_cache.disable = highbank_l2x0_disable; +#endif } static void __init highbank_timer_init(void) diff --git a/arch/arm/mach-highbank/include/mach/pl320-ipc.h b/arch/arm/mach-highbank/include/mach/pl320-ipc.h new file mode 100644 index 000000000000..a0e58eed4b0d --- /dev/null +++ b/arch/arm/mach-highbank/include/mach/pl320-ipc.h @@ -0,0 +1,20 @@ +/* + * Copyright 2010 Calxeda, Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ +int ipc_call_fast(u32 *data); +int ipc_call_slow(u32 *data); + +extern int pl320_ipc_register_notifier(struct notifier_block *nb); +extern int pl320_ipc_unregister_notifier(struct notifier_block *nb); diff --git a/arch/arm/mach-highbank/pl320-ipc.c b/arch/arm/mach-highbank/pl320-ipc.c new file mode 100644 index 000000000000..b68d85663954 --- /dev/null +++ b/arch/arm/mach-highbank/pl320-ipc.c @@ -0,0 +1,308 @@ +/* + * Copyright 2010 Calxeda, Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ +#include <linux/types.h> +#include <linux/err.h> +#include <linux/delay.h> +#include <linux/export.h> +#include <linux/io.h> +#include <linux/interrupt.h> +#include <linux/completion.h> +#include <linux/mutex.h> +#include <linux/notifier.h> +#include <linux/spinlock.h> +#include <linux/device.h> +#include <linux/amba/bus.h> + +#include <mach/pl320-ipc.h> + +#define IPCMxSOURCE(m) ((m) * 0x40) +#define IPCMxDSET(m) (((m) * 0x40) + 0x004) +#define IPCMxDCLEAR(m) (((m) * 0x40) + 0x008) +#define IPCMxDSTATUS(m) (((m) * 0x40) + 0x00C) +#define IPCMxMODE(m) (((m) * 0x40) + 0x010) +#define IPCMxMSET(m) (((m) * 0x40) + 0x014) +#define IPCMxMCLEAR(m) (((m) * 0x40) + 0x018) +#define IPCMxMSTATUS(m) (((m) * 0x40) + 0x01C) +#define IPCMxSEND(m) (((m) * 0x40) + 0x020) +#define IPCMxDR(m, dr) (((m) * 0x40) + ((dr) * 4) + 0x024) + +#define IPCMMIS(irq) (((irq) * 8) + 0x800) +#define IPCMRIS(irq) (((irq) * 8) + 0x804) + +#define MBOX_MASK(n) (1 << (n)) +#define IPC_FAST_MBOX 0 +#define IPC_SLOW_MBOX 1 +#define IPC_RX_MBOX 2 + +#define CHAN_MASK(n) (1 << (n)) +#define A9_SOURCE 1 +#define M3_SOURCE 0 + +static void __iomem *ipc_base; +static int ipc_irq; +static DEFINE_SPINLOCK(ipc_m0_lock); +static DEFINE_MUTEX(ipc_m1_lock); +static DECLARE_COMPLETION(ipc_completion); +static ATOMIC_NOTIFIER_HEAD(ipc_notifier); + +static inline void set_destination(int source, int mbox) +{ + __raw_writel(CHAN_MASK(source), ipc_base + IPCMxDSET(mbox)); + __raw_writel(CHAN_MASK(source), ipc_base + IPCMxMSET(mbox)); +} + +static inline void clear_destination(int source, int mbox) +{ + __raw_writel(CHAN_MASK(source), ipc_base + IPCMxDCLEAR(mbox)); + __raw_writel(CHAN_MASK(source), ipc_base + IPCMxMCLEAR(mbox)); +} + +static void __ipc_send(int mbox, u32 *data) +{ + int i; + for (i = 0; i < 7; i++) + __raw_writel(data[i], ipc_base + IPCMxDR(mbox, i)); + __raw_writel(0x1, ipc_base + IPCMxSEND(mbox)); +} + +static u32 __ipc_rcv(int mbox, u32 *data) +{ + int i; + for (i = 0; i < 7; i++) + data[i] = __raw_readl(ipc_base + IPCMxDR(mbox, i)); + return data[1]; +} + +/* non-blocking implementation from the A9 side, interrupt safe in theory */ +int ipc_call_fast(u32 *data) +{ + int timeout, ret; + + spin_lock(&ipc_m0_lock); + + __ipc_send(IPC_FAST_MBOX, data); + + for (timeout = 5000; timeout > 0; timeout--) { + if (__raw_readl(ipc_base + IPCMxSEND(IPC_FAST_MBOX)) == 0x2) + break; + udelay(100); + } + if (timeout == 0) { + ret = -ETIMEDOUT; + goto out; + } + + ret = __ipc_rcv(IPC_FAST_MBOX, data); +out: + __raw_writel(0, ipc_base + IPCMxSEND(IPC_FAST_MBOX)); + spin_unlock(&ipc_m0_lock); + return ret; +} +EXPORT_SYMBOL(ipc_call_fast); + +/* blocking implmentation from the A9 side, not usuable in interrupts! */ +int ipc_call_slow(u32 *data) +{ + int ret; + + mutex_lock(&ipc_m1_lock); + + init_completion(&ipc_completion); + __ipc_send(IPC_SLOW_MBOX, data); + ret = wait_for_completion_timeout(&ipc_completion, + msecs_to_jiffies(1000)); + if (ret == 0) + goto out; + + ret = __ipc_rcv(IPC_SLOW_MBOX, data); +out: + mutex_unlock(&ipc_m1_lock); + return ret; +} +EXPORT_SYMBOL(ipc_call_slow); + +irqreturn_t ipc_handler(int irq, void *dev) +{ + u32 irq_stat; + u32 data[7]; + + irq_stat = __raw_readl(ipc_base + IPCMMIS(1)); + if (irq_stat & MBOX_MASK(IPC_SLOW_MBOX)) { + __raw_writel(0, ipc_base + IPCMxSEND(IPC_SLOW_MBOX)); + complete(&ipc_completion); + } + if (irq_stat & MBOX_MASK(IPC_RX_MBOX)) { + __ipc_rcv(IPC_RX_MBOX, data); + atomic_notifier_call_chain(&ipc_notifier, data[0], data + 1); + __raw_writel(2, ipc_base + IPCMxSEND(IPC_RX_MBOX)); + } + + return IRQ_HANDLED; +} + +int pl320_ipc_register_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_register(&ipc_notifier, nb); +} + +int pl320_ipc_unregister_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&ipc_notifier, nb); +} + +static int __devinit pl320_probe(struct amba_device *adev, const struct amba_id *id) +{ + int ret; + + ipc_base = ioremap(adev->res.start, resource_size(&adev->res)); + if (ipc_base == NULL) + return -ENOMEM; + + __raw_writel(0, ipc_base + IPCMxSEND(IPC_FAST_MBOX)); + __raw_writel(0, ipc_base + IPCMxSEND(IPC_SLOW_MBOX)); + + ipc_irq = adev->irq[0]; + ret = request_irq(ipc_irq, ipc_handler, 0, dev_name(&adev->dev), NULL); + if (ret < 0) + goto err; + + /* Init fast mailbox */ + __raw_writel(CHAN_MASK(A9_SOURCE), ipc_base + IPCMxSOURCE(IPC_FAST_MBOX)); + set_destination(M3_SOURCE, IPC_FAST_MBOX); + + /* Init slow mailbox */ + __raw_writel(CHAN_MASK(A9_SOURCE), ipc_base + IPCMxSOURCE(IPC_SLOW_MBOX)); + __raw_writel(CHAN_MASK(M3_SOURCE), ipc_base + IPCMxDSET(IPC_SLOW_MBOX)); + __raw_writel(CHAN_MASK(M3_SOURCE) | CHAN_MASK(A9_SOURCE), + ipc_base + IPCMxMSET(IPC_SLOW_MBOX)); + + /* Init receive mailbox */ + __raw_writel(CHAN_MASK(M3_SOURCE), ipc_base + IPCMxSOURCE(IPC_RX_MBOX)); + __raw_writel(CHAN_MASK(A9_SOURCE), ipc_base + IPCMxDSET(IPC_RX_MBOX)); + __raw_writel(CHAN_MASK(M3_SOURCE) | CHAN_MASK(A9_SOURCE), + ipc_base + IPCMxMSET(IPC_RX_MBOX)); + + return 0; +err: + iounmap(ipc_base); + return ret; +} + +static struct amba_id pl320_ids[] = { + { + .id = 0x00041320, + .mask = 0x000fffff, + }, + { 0, 0 }, +}; + +static struct amba_driver pl320_driver = { + .drv = { + .name = "pl320", + }, + .id_table = pl320_ids, + .probe = pl320_probe, +}; + +static int __init ipc_init(void) +{ + return amba_driver_register(&pl320_driver); +} +module_init(ipc_init); + +irqreturn_t ipc_test_handler(int irq, void *dev) +{ + u32 irq_stat; + + irq_stat = __raw_readl(ipc_base + IPCMMIS(irq - (ipc_irq - 1))); + if (irq_stat & MBOX_MASK(IPC_FAST_MBOX)) { + if ((__raw_readl(ipc_base + IPCMxDR(IPC_FAST_MBOX, 0)) == 0x900dbeef) && + (__raw_readl(ipc_base + IPCMxDR(IPC_FAST_MBOX, 1)) == 1) && + (__raw_readl(ipc_base + IPCMxDR(IPC_FAST_MBOX, 2)) == 2) && + (__raw_readl(ipc_base + IPCMxDR(IPC_FAST_MBOX, 3)) == 3) && + (__raw_readl(ipc_base + IPCMxDR(IPC_FAST_MBOX, 4)) == 4) && + (__raw_readl(ipc_base + IPCMxDR(IPC_FAST_MBOX, 5)) == 5) && + (__raw_readl(ipc_base + IPCMxDR(IPC_FAST_MBOX, 6)) == 6)) { + printk(KERN_ERR "ipc fast mbox message %X received\n", __raw_readl(ipc_base + IPCMxDR(IPC_FAST_MBOX, 0))); + __raw_writel(0xBADBEEF, ipc_base + IPCMxDR(IPC_FAST_MBOX, 1)); + } + __raw_writel(0x2, ipc_base + IPCMxSEND(IPC_FAST_MBOX)); + } + if (irq_stat & MBOX_MASK(IPC_SLOW_MBOX)) { + if ((__raw_readl(ipc_base + IPCMxDR(IPC_SLOW_MBOX, 0)) == 0x12345678) && + (__raw_readl(ipc_base + IPCMxDR(IPC_SLOW_MBOX, 1)) == 6) && + (__raw_readl(ipc_base + IPCMxDR(IPC_SLOW_MBOX, 2)) == 5) && + (__raw_readl(ipc_base + IPCMxDR(IPC_SLOW_MBOX, 3)) == 4) && + (__raw_readl(ipc_base + IPCMxDR(IPC_SLOW_MBOX, 4)) == 3) && + (__raw_readl(ipc_base + IPCMxDR(IPC_SLOW_MBOX, 5)) == 2) && + (__raw_readl(ipc_base + IPCMxDR(IPC_SLOW_MBOX, 6)) == 1)) { + printk("slow mbox message %X received\n", __raw_readl(ipc_base + IPCMxDR(IPC_SLOW_MBOX, 0))); + __raw_writel(0x87654321, ipc_base + IPCMxDR(IPC_SLOW_MBOX, 1)); + } + __raw_writel(0x2, ipc_base + IPCMxSEND(IPC_SLOW_MBOX)); + } + if (irq_stat & MBOX_MASK(IPC_RX_MBOX)) { + __raw_writel(0, ipc_base + IPCMxSEND(IPC_RX_MBOX)); + // handle events + } + + return IRQ_HANDLED; +} + +static void __init ipc_test(void) +{ + int ret, i; + + printk("ipc test start\n"); + + for (i = 0; i < 8; i++) { + u32 data[7]; + int j; + if (i == 1) continue; + + if (request_irq(ipc_irq - 1 + i, ipc_test_handler, 0, "ipc", NULL) < 0) { + printk("ipc - request_irq failed - FAIL\n"); + return; + } + + set_destination(i, IPC_FAST_MBOX); + set_destination(i, IPC_SLOW_MBOX); + + for (j = 1; j < 7; j++) + data[j] = j; + data[0] = 0x900dbeef; + ret = ipc_call_fast(data); + if (ret == 0xbadbeef) + printk(KERN_ERR "ipc %d fast call - PASS\n", i); + else + printk(KERN_ERR "ipc %d fast call fail %d\n", i, ret); + for (j = 1; j < 7; j++) + data[j] = 7 - j; + data[0] = 0x12345678; + ret = ipc_call_slow(data); + if (ret == 0x87654321) + printk("ipc %d slow call - PASS\n", i); + + clear_destination(i, IPC_FAST_MBOX); + clear_destination(i, IPC_SLOW_MBOX); + + free_irq(ipc_irq - 1 + i, NULL); + } + set_destination(M3_SOURCE, IPC_FAST_MBOX); + set_destination(M3_SOURCE, IPC_SLOW_MBOX); +} +//late_initcall(ipc_test); + diff --git a/arch/arm/mach-highbank/smc.S b/arch/arm/mach-highbank/smc.S new file mode 100644 index 000000000000..8b116325c8cc --- /dev/null +++ b/arch/arm/mach-highbank/smc.S @@ -0,0 +1,31 @@ +/* + * Copied from omap44xx-smc.S + * Copyright (C) 2010 Texas Instruments, Inc. + * Written by Santosh Shilimkar <santosh.shilimkar@ti.com> + * + * + * This program is free software,you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/linkage.h> + +/* + * This is common routine to manage secure monitor API + * used to modify the PL310 secure registers. + * 'r0' contains the value to be modified and 'r12' contains + * the monitor API number. It uses few CPU registers + * internally and hence they need be backed up including + * link register "lr". + * Function signature : void omap_smc1(u32 fn, u32 arg) + */ + +ENTRY(highbank_smc1) + stmfd sp!, {r2-r12, lr} + mov r12, r0 + mov r0, r1 + dsb + smc #0 + ldmfd sp!, {r2-r12, pc} +ENDPROC(highbank_smc1) diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 28773e6211f6..cf10218b9062 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -843,7 +843,7 @@ config ARM_L1_CACHE_SHIFT config ARM_DMA_MEM_BUFFERABLE bool "Use non-cacheable memory for DMA" if (CPU_V6 || CPU_V6K) && !CPU_V7 depends on !(MACH_REALVIEW_PB1176 || REALVIEW_EB_ARM11MP || \ - MACH_REALVIEW_PB11MP) + MACH_REALVIEW_PB11MP || ARCH_HIGHBANK) default y if CPU_V6 || CPU_V6K || CPU_V7 help Historically, the kernel has used strongly ordered mappings to diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 050cb371a69e..a9363d28dbbd 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -986,6 +986,8 @@ source "net/Kconfig" source "drivers/Kconfig" +source "ubuntu/Kconfig" + source "fs/Kconfig" source "arch/powerpc/sysdev/qe_lib/Kconfig" diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index c70684f859e1..8e083c36f519 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -381,6 +381,12 @@ config X86_UV # Following is an alphabetically sorted list of 32 bit extended platforms # Please maintain the alphabetic order if and when there are additions +config X86_LPIA + bool "LPIA-compatible" + depends on X86_32 && X86_PC + help + Choose this option if your computer is an LPIA platform. + config X86_INTEL_CE bool "CE4100 TV platform" depends on PCI @@ -2220,6 +2226,8 @@ source "net/Kconfig" source "drivers/Kconfig" +source "ubuntu/Kconfig" + source "drivers/firmware/Kconfig" source "fs/Kconfig" diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index f7b4c7903e7e..fab11b0ab4ff 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -162,8 +162,6 @@ static inline void dma_free_attrs(struct device *dev, size_t size, { struct dma_map_ops *ops = get_dma_ops(dev); - WARN_ON(irqs_disabled()); /* for portability */ - if (dma_release_from_coherent(dev, get_order(size), vaddr)) return; diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 95bf99de9058..79357aae9f10 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -94,6 +94,8 @@ static int __init acpi_sleep_setup(char *str) acpi_realmode_flags |= 2; if (strncmp(str, "s3_beep", 7) == 0) acpi_realmode_flags |= 4; + if (strncmp(str, "s3_leds", 7) == 0) + acpi_realmode_flags |= 8; #ifdef CONFIG_HIBERNATION if (strncmp(str, "s4_nohwsig", 10) == 0) acpi_no_s4_hw_signature(); diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 25b48edb847c..a108d81539ea 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -435,6 +435,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E5420"), }, }, + { /* Handle problems with rebooting on the Latitude E6220. */ + .callback = set_pci_reboot, + .ident = "Dell Latitude E6220", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6220"), + }, + }, { /* Handle problems with rebooting on the Latitude E6420. */ .callback = set_pci_reboot, .ident = "Dell Latitude E6420", @@ -451,6 +459,30 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 990"), }, }, + { /* Handle problems with rebooting on the Latitude E6520. */ + .callback = set_pci_reboot, + .ident = "Dell Latitude E6520", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6520"), + }, + }, + { /* Handle problems with rebooting on the OptiPlex 790. */ + .callback = set_pci_reboot, + .ident = "Dell OptiPlex 790", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 790"), + }, + }, + { /* Handle problems with rebooting on the OptiPlex 990. */ + .callback = set_pci_reboot, + .ident = "Dell OptiPlex 990", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 990"), + }, + }, { } }; diff --git a/arch/x86/realmode/rm/wakemain.c b/arch/x86/realmode/rm/wakemain.c index 91405d515ec6..810b9c13c7ab 100644 --- a/arch/x86/realmode/rm/wakemain.c +++ b/arch/x86/realmode/rm/wakemain.c @@ -61,6 +61,30 @@ static void send_morse(const char *pattern) } } +#define I8042_STATUS_REG 0x64 +#define I8042_DATA_REG 0x60 +#define I8042_SET_LED_BITS 0xed +#define I8042_STR_IBF 0x02 + +static void flash_keyboard_leds(void) +{ + int i; + unsigned char leds = 7; + + /* Flash keyboard LEDs 3 times */ + for (i = 0; i < 6; i++) { + while (inb(I8042_STATUS_REG) & I8042_STR_IBF) + ; + outb(I8042_SET_LED_BITS, I8042_DATA_REG); + while (inb(I8042_STATUS_REG) & I8042_STR_IBF) + ; + outb(leds, I8042_DATA_REG); + leds ^= 7; + udelay(500000); + } +} + + void main(void) { /* Kill machine if structures are wrong */ @@ -79,4 +103,7 @@ void main(void) probe_cards(0); set_mode(wakeup_header.video_mode); } + + if (wakeup_header.realmode_flags & 8) + flash_keyboard_leds(); } diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index e74df9548a02..bfe6bc0c310d 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -941,6 +941,7 @@ static void xen_write_cr4(unsigned long cr4) { cr4 &= ~X86_CR4_PGE; cr4 &= ~X86_CR4_PSE; + cr4 &= ~X86_CR4_OSXSAVE; native_write_cr4(cr4); } diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index 260fa80ef575..becbc6f8619a 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -27,6 +27,9 @@ #include <linux/ratelimit.h> #include <linux/slab.h> #include <linux/times.h> +#include <linux/fd.h> +#include <linux/raid/md_u.h> +#include <linux/mtio.h> #include <asm/uaccess.h> #include <scsi/scsi.h> @@ -710,8 +713,17 @@ int scsi_verify_blk_ioctl(struct block_device *bd, unsigned int cmd) case SG_GET_RESERVED_SIZE: case SG_SET_RESERVED_SIZE: case SG_EMULATED_HOST: + case BLKFLSBUF: + case BLKROSET: return 0; case CDROM_GET_CAPABILITY: + case CDROM_DRIVE_STATUS: + case FDGETPRM: + case RAID_VERSION: + case MTIOCGET: +#ifdef CONFIG_COMPAT + case 0x801c6d02: /* MTIOCGET32 */ +#endif /* Keep this until we remove the printk below. udev sends it * and we do not want to spam dmesg about it. CD-ROMs do * not have partitions, so we get here only for disks. diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c index 7dd3f9fb9f3f..f22741069adb 100644 --- a/drivers/acpi/battery.c +++ b/drivers/acpi/battery.c @@ -976,6 +976,18 @@ static int battery_notify(struct notifier_block *nb, return 0; } +static LIST_HEAD(acpi_battery_domain); + +static void acpi_battery_update_async(struct acpi_device *device, async_cookie_t cookie) +{ + struct acpi_battery *battery = acpi_driver_data(device); + + acpi_battery_update(battery); + printk(KERN_INFO PREFIX "%s Slot [%s] (battery %s)\n", + ACPI_BATTERY_DEVICE_NAME, acpi_device_bid(device), + device->status.battery_present ? "present" : "absent"); +} + static int acpi_battery_add(struct acpi_device *device) { int result = 0; @@ -995,13 +1007,16 @@ static int acpi_battery_add(struct acpi_device *device) if (ACPI_SUCCESS(acpi_get_handle(battery->device->handle, "_BIX", &handle))) set_bit(ACPI_BATTERY_XINFO_PRESENT, &battery->flags); - result = acpi_battery_update(battery); - if (result) - goto fail; + + /* Mark the battery for update at first access. */ + battery->update_time = 0; #ifdef CONFIG_ACPI_PROCFS_POWER result = acpi_battery_add_fs(device); #endif - if (result) { + if (!result) { + async_schedule_domain(acpi_battery_update_async, device, &acpi_battery_domain); + + } else { #ifdef CONFIG_ACPI_PROCFS_POWER acpi_battery_remove_fs(device); #endif @@ -1031,6 +1046,10 @@ static int acpi_battery_remove(struct acpi_device *device, int type) if (!device || !acpi_driver_data(device)) return -EINVAL; + + /* Ensure all async updates are complete before freeing the battery. */ + async_synchronize_full_domain(&acpi_battery_domain); + battery = acpi_driver_data(device); unregister_pm_notifier(&battery->pm_nb); #ifdef CONFIG_ACPI_PROCFS_POWER @@ -1068,27 +1087,21 @@ static struct acpi_driver acpi_battery_driver = { }, }; -static void __init acpi_battery_init_async(void *unused, async_cookie_t cookie) +static int __init acpi_battery_init(void) { if (acpi_disabled) return; #ifdef CONFIG_ACPI_PROCFS_POWER acpi_battery_dir = acpi_lock_battery_dir(); if (!acpi_battery_dir) - return; + return -1; #endif if (acpi_bus_register_driver(&acpi_battery_driver) < 0) { #ifdef CONFIG_ACPI_PROCFS_POWER acpi_unlock_battery_dir(acpi_battery_dir); #endif - return; + return -1; } - return; -} - -static int __init acpi_battery_init(void) -{ - async_schedule(acpi_battery_init_async, NULL); return 0; } diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c index a576575617d7..e58b53c86ae6 100644 --- a/drivers/acpi/video.c +++ b/drivers/acpi/video.c @@ -73,6 +73,14 @@ static bool brightness_switch_enabled = 1; module_param(brightness_switch_enabled, bool, 0644); /* + * The Default is to let the OS handle brightness autoswitching due to + * AC/battery status changes. On some laptops (MSI Wind) this doesn't + * work so we need a workaround. + */ +static int brightness_autoswitch_via_bios = 0; +module_param(brightness_autoswitch_via_bios, bool, 0644); + +/* * By default, we don't allow duplicate ACPI video bus devices * under the same VGA controller */ @@ -1423,7 +1431,7 @@ static int acpi_video_bus_put_devices(struct acpi_video_bus *video) static int acpi_video_bus_start_devices(struct acpi_video_bus *video) { - return acpi_video_bus_DOS(video, 0, 0); + return acpi_video_bus_DOS(video, 0, !brightness_autoswitch_via_bios); } static int acpi_video_bus_stop_devices(struct acpi_video_bus *video) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 061427a75d37..bb8b53da1db7 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -57,7 +57,7 @@ static unsigned int debugflags; static unsigned int nbds_max = 16; static struct nbd_device *nbd_dev; -static int max_part; +static int max_part = 15; /* * Use just one lock (or at most 1 per NIC). Two arguments for this: diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 60eed4bdd2e4..31b3541f8096 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -73,7 +73,8 @@ struct blk_shadow { static DEFINE_MUTEX(blkfront_mutex); static const struct block_device_operations xlvbd_block_fops; -#define BLK_RING_SIZE __CONST_RING_SIZE(blkif, PAGE_SIZE) +#define BLK_MAX_RING_AREA_SIZE (BLKIF_MAX_NUM_RING_PAGES * PAGE_SIZE) +#define BLK_MAX_RING_SIZE __CONST_RING_SIZE(blkif, BLK_MAX_RING_AREA_SIZE) /* * We have one of these per vbd, whether ide, scsi or 'other'. They @@ -89,14 +90,15 @@ struct blkfront_info int vdevice; blkif_vdev_t handle; enum blkif_state connected; - int ring_ref; + int num_ring_pages; + int ring_ref[BLKIF_MAX_NUM_RING_PAGES]; struct blkif_front_ring ring; struct scatterlist sg[BLKIF_MAX_SEGMENTS_PER_REQUEST]; unsigned int evtchn, irq; struct request_queue *rq; struct work_struct work; struct gnttab_free_callback callback; - struct blk_shadow shadow[BLK_RING_SIZE]; + struct blk_shadow shadow[BLK_MAX_RING_SIZE]; unsigned long shadow_free; unsigned int feature_flush; unsigned int flush_op; @@ -135,7 +137,8 @@ static DEFINE_SPINLOCK(minor_lock); static int get_id_from_freelist(struct blkfront_info *info) { unsigned long free = info->shadow_free; - BUG_ON(free >= BLK_RING_SIZE); + int ring_size = __RING_SIZE((struct blkif_sring *)0, info->num_ring_pages * PAGE_SIZE); + BUG_ON(free >= ring_size); info->shadow_free = info->shadow[free].req.u.rw.id; info->shadow[free].req.u.rw.id = 0x0fffffee; /* debug */ return free; @@ -685,6 +688,8 @@ static void blkif_restart_queue(struct work_struct *work) static void blkif_free(struct blkfront_info *info, int suspend) { + int i; + /* Prevent new requests being issued until we fix things up. */ spin_lock_irq(&info->io_lock); info->connected = suspend ? @@ -700,10 +705,17 @@ static void blkif_free(struct blkfront_info *info, int suspend) flush_work_sync(&info->work); /* Free resources associated with old device channel. */ - if (info->ring_ref != GRANT_INVALID_REF) { - gnttab_end_foreign_access(info->ring_ref, 0, - (unsigned long)info->ring.sring); - info->ring_ref = GRANT_INVALID_REF; + for (i = 0; i < info->num_ring_pages; i++) { + /* Free resources associated with old device channel. */ + if (info->ring_ref[i] != GRANT_INVALID_REF) { + gnttab_end_foreign_access(info->ring_ref[i], 0, 0L); + info->ring_ref[i] = GRANT_INVALID_REF; + } + } + if (info->ring.sring) { + int ring_area_size = info->num_ring_pages * PAGE_SIZE; + free_pages((unsigned long)info->ring.sring, + get_order(ring_area_size)); info->ring.sring = NULL; } if (info->irq) @@ -828,27 +840,32 @@ static int setup_blkring(struct xenbus_device *dev, struct blkfront_info *info) { struct blkif_sring *sring; - int err; + int i, order, err; + int ring_area_size = info->num_ring_pages * PAGE_SIZE; - info->ring_ref = GRANT_INVALID_REF; + for (i = 0; i < info->num_ring_pages; i++) { + info->ring_ref[i] = GRANT_INVALID_REF; + } - sring = (struct blkif_sring *)__get_free_page(GFP_NOIO | __GFP_HIGH); + order = get_order(ring_area_size); + sring = (struct blkif_sring *)__get_free_pages(GFP_KERNEL, order); if (!sring) { xenbus_dev_fatal(dev, -ENOMEM, "allocating shared ring"); return -ENOMEM; } SHARED_RING_INIT(sring); - FRONT_RING_INIT(&info->ring, sring, PAGE_SIZE); - - sg_init_table(info->sg, BLKIF_MAX_SEGMENTS_PER_REQUEST); - - err = xenbus_grant_ring(dev, virt_to_mfn(info->ring.sring)); - if (err < 0) { - free_page((unsigned long)sring); - info->ring.sring = NULL; - goto fail; + FRONT_RING_INIT(&info->ring, sring, ring_area_size); + + for (i = 0; i < info->num_ring_pages; i++) { + unsigned long addr = (unsigned long)info->ring.sring + i * PAGE_SIZE; + err = xenbus_grant_ring(dev, virt_to_mfn(addr)); + if (err < 0) { + free_pages((unsigned long)sring, order); + info->ring.sring = NULL; + goto fail; + } + info->ring_ref[i] = err; } - info->ring_ref = err; err = xenbus_alloc_evtchn(dev, &info->evtchn); if (err) @@ -877,7 +894,13 @@ static int talk_to_blkback(struct xenbus_device *dev, { const char *message = NULL; struct xenbus_transaction xbt; - int err; + int err, i; + + BUILD_BUG_ON(BLKIF_MAX_NUM_RING_PAGES != 1 && + BLKIF_MAX_NUM_RING_PAGES != 2 && + BLKIF_MAX_NUM_RING_PAGES != 4 && + BLKIF_MAX_NUM_RING_PAGES != 8 && + BLKIF_MAX_NUM_RING_PAGES != 16); /* Create shared ring, alloc event channel. */ err = setup_blkring(dev, info); @@ -891,11 +914,30 @@ again: goto destroy_blkring; } - err = xenbus_printf(xbt, dev->nodename, - "ring-ref", "%u", info->ring_ref); - if (err) { - message = "writing ring-ref"; - goto abort_transaction; + if (info->num_ring_pages == 1) { + err = xenbus_printf(xbt, dev->nodename, + "ring-ref", "%u", info->ring_ref[0]); + if (err) { + message = "writing ring-ref"; + goto abort_transaction; + } + } else { + err = xenbus_printf(xbt, dev->nodename, "num-ring-pages", "%u", + info->num_ring_pages); + if (err) { + message = "writing num-ring-pages"; + goto abort_transaction; + } + for (i = 0; i < info->num_ring_pages; i++) { + char buf[16]; + snprintf(buf, sizeof(buf), "ring-ref%d", i); + err = xenbus_printf(xbt, dev->nodename, buf, "%u", + info->ring_ref[i]); + if (err) { + message = "writing ring-refs"; + goto abort_transaction; + } + } } err = xenbus_printf(xbt, dev->nodename, "event-channel", "%u", info->evtchn); @@ -943,6 +985,7 @@ static int blkfront_probe(struct xenbus_device *dev, { int err, vdevice, i; struct blkfront_info *info; + int ring_size, max_ring_pages; /* FIXME: Use dynamic device id if this is not set. */ err = xenbus_scanf(XBT_NIL, dev->nodename, @@ -956,6 +999,10 @@ static int blkfront_probe(struct xenbus_device *dev, return err; } } + err = xenbus_scanf(XBT_NIL, dev->otherend, + "max-ring-pages", "%u", &max_ring_pages); + if (err != 1) + max_ring_pages = 1; if (xen_hvm_domain()) { char *type; @@ -999,9 +1046,13 @@ static int blkfront_probe(struct xenbus_device *dev, info->connected = BLKIF_STATE_DISCONNECTED; INIT_WORK(&info->work, blkif_restart_queue); - for (i = 0; i < BLK_RING_SIZE; i++) + info->num_ring_pages = min(max_ring_pages, BLKIF_MAX_NUM_RING_PAGES); + + ring_size = __RING_SIZE((struct blkif_sring *)0, + info->num_ring_pages * PAGE_SIZE); + for (i = 0; i < ring_size; i++) info->shadow[i].req.u.rw.id = i+1; - info->shadow[BLK_RING_SIZE-1].req.u.rw.id = 0x0fffffff; + info->shadow[ring_size-1].req.u.rw.id = 0x0fffffff; /* Front end dir is a number, which is used as the id. */ info->handle = simple_strtoul(strrchr(dev->nodename, '/')+1, NULL, 0); @@ -1014,6 +1065,9 @@ static int blkfront_probe(struct xenbus_device *dev, return err; } + printk(KERN_INFO "blkfront %s num-ring-pages %d nr_ents %d.\n", + dev->nodename, info->num_ring_pages, ring_size); + return 0; } @@ -1024,6 +1078,7 @@ static int blkif_recover(struct blkfront_info *info) struct blkif_request *req; struct blk_shadow *copy; int j; + int ring_size = __RING_SIZE((struct blkif_sring *)0, info->num_ring_pages * PAGE_SIZE); /* Stage 1: Make a safe copy of the shadow state. */ copy = kmalloc(sizeof(info->shadow), @@ -1034,13 +1089,13 @@ static int blkif_recover(struct blkfront_info *info) /* Stage 2: Set up free list. */ memset(&info->shadow, 0, sizeof(info->shadow)); - for (i = 0; i < BLK_RING_SIZE; i++) + for (i = 0; i < ring_size; i++) info->shadow[i].req.u.rw.id = i+1; info->shadow_free = info->ring.req_prod_pvt; - info->shadow[BLK_RING_SIZE-1].req.u.rw.id = 0x0fffffff; + info->shadow[ring_size-1].req.u.rw.id = 0x0fffffff; /* Stage 3: Find pending requests and requeue them. */ - for (i = 0; i < BLK_RING_SIZE; i++) { + for (i = 0; i < ring_size; i++) { /* Not in use? */ if (!copy[i].request) continue; @@ -1511,3 +1566,4 @@ MODULE_LICENSE("GPL"); MODULE_ALIAS_BLOCKDEV_MAJOR(XENVBD_MAJOR); MODULE_ALIAS("xen:vbd"); MODULE_ALIAS("xenblk"); + diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index c9463af8e564..e9611d2cb440 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -102,10 +102,13 @@ static struct usb_device_id btusb_table[] = { /* Broadcom BCM20702A0 */ { USB_DEVICE(0x0489, 0xe042) }, + { USB_DEVICE(0x0a5c, 0x21e1) }, { USB_DEVICE(0x0a5c, 0x21e3) }, { USB_DEVICE(0x0a5c, 0x21e6) }, { USB_DEVICE(0x0a5c, 0x21e8) }, { USB_DEVICE(0x0a5c, 0x21f3) }, + { USB_DEVICE(0x0a5c, 0x21e6) }, + { USB_DEVICE(0x0a5c, 0x21f3) }, { USB_DEVICE(0x413c, 0x8197) }, /* Foxconn - Hon Hai */ diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index d620b4495745..72cf3159c67c 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -289,7 +289,7 @@ static bool debug; /* default compatibility mode */ static bool autoclose=1; static bool autoeject; -static bool lockdoor = 1; +static bool lockdoor = 0; /* will we ever get to use this... sigh. */ static bool check_media_type; /* automatically restart mrw format */ diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 7f2f149ae40f..222966f34432 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1817,6 +1817,20 @@ static struct notifier_block __refdata cpufreq_cpu_notifier = { * REGISTER / UNREGISTER CPUFREQ DRIVER * *********************************************************************/ +static char cpufreq_driver_name[CPUFREQ_NAME_LEN]; + +static int __init cpufreq_driver_setup(char *str) +{ + strlcpy(cpufreq_driver_name, str, CPUFREQ_NAME_LEN); + return 1; +} + +/* + * Set this name to only allow one specific cpu freq driver, e.g., + * cpufreq_driver=powernow-k8 + */ +__setup("cpufreq_driver=", cpufreq_driver_setup); + /** * cpufreq_register_driver - register a CPU Frequency driver * @driver_data: A struct cpufreq_driver containing the values# @@ -1839,7 +1853,13 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data) ((!driver_data->setpolicy) && (!driver_data->target))) return -EINVAL; - pr_debug("trying to register driver %s\n", driver_data->name); + pr_debug("trying to register driver %s, cpufreq_driver=%s\n", + driver_data->name, cpufreq_driver_name); + + if (cpufreq_driver_name[0]) + if (!driver_data->name || + strcmp(cpufreq_driver_name, driver_data->name)) + return -EINVAL; if (driver_data->setpolicy) driver_data->flags |= CPUFREQ_CONST_LOOPS; diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index c1af05e834b6..6ac61488082e 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -320,6 +320,8 @@ static const struct { {PCI_VENDOR_ID_VIA, PCI_ANY_ID, PCI_ANY_ID, QUIRK_CYCLE_TIMER | QUIRK_NO_MSI}, + {PCI_VENDOR_ID_O2, PCI_ANY_ID, PCI_ANY_ID, + QUIRK_NO_MSI}, }; /* This overrides anything that was found in ohci_quirks[]. */ diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c index 123de28f94ef..9c14f633772c 100644 --- a/drivers/gpu/drm/drm_fops.c +++ b/drivers/gpu/drm/drm_fops.c @@ -129,7 +129,8 @@ int drm_open(struct inode *inode, struct file *filp) minor = idr_find(&drm_minors_idr, minor_id); if (!minor) return -ENODEV; - + if (IS_ERR(minor)) + return PTR_ERR(minor); if (!(dev = minor->dev)) return -ENODEV; @@ -180,7 +181,10 @@ int drm_stub_open(struct inode *inode, struct file *filp) minor = idr_find(&drm_minors_idr, minor_id); if (!minor) goto out; - + if (IS_ERR(minor)) { + err = PTR_ERR(minor); + goto out; + } if (!(dev = minor->dev)) goto out; diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c index 13f3d936472f..b3216724122a 100644 --- a/drivers/gpu/drm/drm_pci.c +++ b/drivers/gpu/drm/drm_pci.c @@ -367,6 +367,10 @@ int drm_get_pci_dev(struct pci_dev *pdev, const struct pci_device_id *ent, list_add_tail(&dev->driver_item, &driver->device_list); + if (drm_core_check_feature(dev, DRIVER_MODESET)) + idr_replace(&drm_minors_idr, dev->control, dev->control->index); + idr_replace(&drm_minors_idr, dev->primary, dev->primary->index); + DRM_INFO("Initialized %s %d.%d.%d %s for %s on minor %d\n", driver->name, driver->major, driver->minor, driver->patchlevel, driver->date, pci_name(pdev), dev->primary->index); diff --git a/drivers/gpu/drm/drm_platform.c b/drivers/gpu/drm/drm_platform.c index 82431dcae37b..d749389a15a0 100644 --- a/drivers/gpu/drm/drm_platform.c +++ b/drivers/gpu/drm/drm_platform.c @@ -90,6 +90,10 @@ int drm_get_platform_dev(struct platform_device *platdev, list_add_tail(&dev->driver_item, &driver->device_list); + if (drm_core_check_feature(dev, DRIVER_MODESET)) + idr_replace(&drm_minors_idr, dev->control, dev->control->index); + idr_replace(&drm_minors_idr, dev->primary, dev->primary->index); + mutex_unlock(&drm_global_mutex); DRM_INFO("Initialized %s %d.%d.%d %s on minor %d\n", diff --git a/drivers/gpu/drm/drm_stub.c b/drivers/gpu/drm/drm_stub.c index 21bcd4a555d8..0251c38ac267 100644 --- a/drivers/gpu/drm/drm_stub.c +++ b/drivers/gpu/drm/drm_stub.c @@ -356,7 +356,7 @@ int drm_get_minor(struct drm_device *dev, struct drm_minor **minor, int type) new_minor->index = minor_id; INIT_LIST_HEAD(&new_minor->master_list); - idr_replace(&drm_minors_idr, new_minor, minor_id); + idr_replace(&drm_minors_idr, ERR_PTR(-EAGAIN), minor_id); if (type == DRM_MINOR_LEGACY) { ret = drm_proc_init(new_minor, minor_id, drm_proc_root); diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig index c0e11ecc646f..c99bf9065f75 100644 --- a/drivers/input/keyboard/Kconfig +++ b/drivers/input/keyboard/Kconfig @@ -204,6 +204,17 @@ config KEYBOARD_GPIO_POLLED To compile this driver as a module, choose M here: the module will be called gpio_keys_polled. +config KEYBOARD_HIGHBANK + tristate "Calxeda Highbank Virtual Keys" + depends on ARCH_HIGHBANK + default y + help + This driver implements support for virtual power keys on Calxeda + Highbank systems. + + To compile this driver as a module, choose M here: the + module will be called highbank_keys. + config KEYBOARD_TCA6416 tristate "TCA6416/TCA6408A Keypad Support" depends on I2C diff --git a/drivers/input/keyboard/Makefile b/drivers/input/keyboard/Makefile index b03b02456a82..5dc046906f3f 100644 --- a/drivers/input/keyboard/Makefile +++ b/drivers/input/keyboard/Makefile @@ -15,6 +15,7 @@ obj-$(CONFIG_KEYBOARD_DAVINCI) += davinci_keyscan.o obj-$(CONFIG_KEYBOARD_EP93XX) += ep93xx_keypad.o obj-$(CONFIG_KEYBOARD_GPIO) += gpio_keys.o obj-$(CONFIG_KEYBOARD_GPIO_POLLED) += gpio_keys_polled.o +obj-$(CONFIG_KEYBOARD_HIGHBANK) += highbank_keys.o obj-$(CONFIG_KEYBOARD_TCA6416) += tca6416-keypad.o obj-$(CONFIG_KEYBOARD_TCA8418) += tca8418_keypad.o obj-$(CONFIG_KEYBOARD_HIL) += hil_kbd.o diff --git a/drivers/input/keyboard/highbank_keys.c b/drivers/input/keyboard/highbank_keys.c new file mode 100644 index 000000000000..a84ecf371755 --- /dev/null +++ b/drivers/input/keyboard/highbank_keys.c @@ -0,0 +1,141 @@ +/* + * Copyright 2011 Calxeda, Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + */ +#include <linux/module.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/platform_device.h> +#include <linux/input.h> + +#include <mach/pl320-ipc.h> + +struct hb_keys_drvdata { + struct input_dev *input; + struct notifier_block nb; +}; + +int hb_keys_notifier(struct notifier_block *nb, unsigned long event, void *data) +{ + struct hb_keys_drvdata *ddata = container_of(nb, struct hb_keys_drvdata, nb); + struct input_dev *input = ddata->input; + u32 *d = data; + u32 key = d[0]; + + if (event != 0x1000 /*HB_IPC_KEY*/) + return 0; + + input_event(input, EV_KEY, key, 1); + input_event(input, EV_KEY, key, 0); + input_sync(input); + return 0; +} + +static int hb_keys_open(struct input_dev *input) +{ + struct hb_keys_drvdata *ddata = input_get_drvdata(input); + return pl320_ipc_register_notifier(&ddata->nb); +} + +static void hb_keys_close(struct input_dev *input) +{ + struct hb_keys_drvdata *ddata = input_get_drvdata(input); + pl320_ipc_unregister_notifier(&ddata->nb); +} + +static int __devinit hb_keys_probe(struct platform_device *pdev) +{ + struct hb_keys_drvdata *ddata; + struct device *dev = &pdev->dev; + struct input_dev *input; + int error; + + ddata = kzalloc(sizeof(*ddata), GFP_KERNEL); + if (!ddata) + return -ENOMEM; + + input = input_allocate_device(); + if (!input) { + dev_err(dev, "failed to allocate state\n"); + error = -ENOMEM; + goto fail1; + } + + platform_set_drvdata(pdev, ddata); + input_set_drvdata(input, ddata); + + ddata->input = input; + ddata->nb.notifier_call = hb_keys_notifier; + + input->name = pdev->name; + input->phys = "highbank/input0"; + input->dev.parent = &pdev->dev; + input->open = hb_keys_open; + input->close = hb_keys_close; + + input->id.bustype = BUS_HOST; + input->id.vendor = 0x0001; + input->id.product = 0x0001; + input->id.version = 0x0100; + + input_set_capability(input, EV_KEY, KEY_POWER); + input_set_capability(input, EV_KEY, KEY_SLEEP); + + error = input_register_device(input); + if (error) { + dev_err(dev, "Unable to register input device, error: %d\n", + error); + goto fail2; + } + + return 0; + + fail2: + input_free_device(input); + fail1: + kfree(ddata); + return error; +} + +static int __devexit hb_keys_remove(struct platform_device *pdev) +{ + struct hb_keys_drvdata *ddata = platform_get_drvdata(pdev); + input_unregister_device(ddata->input); + kfree(ddata); + return 0; +} + +static struct of_device_id hb_keys_of_match[] = { + { .compatible = "calxeda,hb-keys", }, + { }, +}; +MODULE_DEVICE_TABLE(of, hb_keys_of_match); + +static struct platform_driver hb_keys_driver = { + .probe = hb_keys_probe, + .remove = __devexit_p(hb_keys_remove), + .driver = { + .name = "hb-keys", + .of_match_table = hb_keys_of_match, + } +}; + +module_platform_driver(hb_keys_driver); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Calxeda, Inc."); +MODULE_DESCRIPTION("Keys driver for Calxeda Highbank"); diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index c703d53be3a0..c6d986963992 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -1223,7 +1223,9 @@ static void set_input_params(struct input_dev *dev, struct synaptics_data *priv) /* Clickpads report only left button */ __clear_bit(BTN_RIGHT, dev->keybit); __clear_bit(BTN_MIDDLE, dev->keybit); - } + } else if (SYN_CAP_CLICKPAD2BTN(priv->ext_cap_0c) || + SYN_CAP_CLICKPAD2BTN2(priv->ext_cap_0c)) + __set_bit(INPUT_PROP_BUTTONPAD, dev->propbit); } static ssize_t synaptics_show_disable_gesture(struct psmouse *psmouse, diff --git a/drivers/input/mouse/synaptics.h b/drivers/input/mouse/synaptics.h index fd26ccca13d7..816d7bd07d85 100644 --- a/drivers/input/mouse/synaptics.h +++ b/drivers/input/mouse/synaptics.h @@ -80,6 +80,7 @@ */ #define SYN_CAP_CLICKPAD(ex0c) ((ex0c) & 0x100000) /* 1-button ClickPad */ #define SYN_CAP_CLICKPAD2BTN(ex0c) ((ex0c) & 0x000100) /* 2-button ClickPad */ +#define SYN_CAP_CLICKPAD2BTN2(ex0c) ((ex0c) & 0x200000) /* 2-button ClickPad */ #define SYN_CAP_MAX_DIMENSIONS(ex0c) ((ex0c) & 0x020000) #define SYN_CAP_MIN_DIMENSIONS(ex0c) ((ex0c) & 0x002000) #define SYN_CAP_ADV_GESTURE(ex0c) ((ex0c) & 0x080000) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index e24143cc2040..ea1f089b128e 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2653,6 +2653,7 @@ struct gendisk *dm_disk(struct mapped_device *md) { return md->disk; } +EXPORT_SYMBOL_GPL(dm_disk); struct kobject *dm_kobject(struct mapped_device *md) { diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c index 9219ad0ed9a6..f67ab02f8e62 100644 --- a/drivers/mmc/host/omap_hsmmc.c +++ b/drivers/mmc/host/omap_hsmmc.c @@ -1858,7 +1858,7 @@ static int __devinit omap_hsmmc_probe(struct platform_device *pdev) host->slot_id = 0; host->mapbase = res->start + pdata->reg_offset; host->base = ioremap(host->mapbase, SZ_4K); - host->power_mode = MMC_POWER_OFF; + host->power_mode = -1; host->flags = AUTO_CMD12; host->next_data.cookie = 1; diff --git a/drivers/net/ethernet/calxeda/xgmac.c b/drivers/net/ethernet/calxeda/xgmac.c index 11f667f6131a..8fc5fd0fb76c 100644 --- a/drivers/net/ethernet/calxeda/xgmac.c +++ b/drivers/net/ethernet/calxeda/xgmac.c @@ -210,7 +210,7 @@ #define DMA_INTR_ENA_TIE 0x00000001 /* Transmit Interrupt */ #define DMA_INTR_NORMAL (DMA_INTR_ENA_NIE | DMA_INTR_ENA_RIE | \ - DMA_INTR_ENA_TUE) + DMA_INTR_ENA_TUE | DMA_INTR_ENA_TIE) #define DMA_INTR_ABNORMAL (DMA_INTR_ENA_AIE | DMA_INTR_ENA_FBE | \ DMA_INTR_ENA_RWE | DMA_INTR_ENA_RSE | \ @@ -933,6 +933,7 @@ static void xgmac_tx_err(struct xgmac_priv *priv) desc_init_tx_desc(priv->dma_tx, DMA_TX_RING_SZ); priv->tx_tail = 0; priv->tx_head = 0; + writel(priv->dma_tx_phy, priv->base + XGMAC_DMA_TX_BASE_ADDR); writel(reg | DMA_CONTROL_ST, priv->base + XGMAC_DMA_CONTROL); writel(DMA_STATUS_TU | DMA_STATUS_TPS | DMA_STATUS_NIS | DMA_STATUS_AIS, @@ -972,7 +973,7 @@ static int xgmac_hw_init(struct net_device *dev) writel(DMA_INTR_DEFAULT_MASK, ioaddr + XGMAC_DMA_INTR_ENA); /* XGMAC requires AXI bus init. This is a 'magic number' for now */ - writel(0x000100E, ioaddr + XGMAC_DMA_AXI_BUS); + writel(0x0077000E, ioaddr + XGMAC_DMA_AXI_BUS); ctrl |= XGMAC_CONTROL_DDIC | XGMAC_CONTROL_JE | XGMAC_CONTROL_ACS | XGMAC_CONTROL_CAR; diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c index c07cfe989f6e..2de44aee73cb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c @@ -23,7 +23,9 @@ *******************************************************************************/ #include <linux/kernel.h> +#include <stdarg.h> #include <linux/io.h> +#include <linux/printk.h> #include "mmc.h" /* MAC Management Counters register offset */ diff --git a/drivers/net/wireless/hostap/hostap_hw.c b/drivers/net/wireless/hostap/hostap_hw.c index 50f87b60b0bd..16e2fee4d246 100644 --- a/drivers/net/wireless/hostap/hostap_hw.c +++ b/drivers/net/wireless/hostap/hostap_hw.c @@ -68,7 +68,7 @@ static char essid[33] = "test"; module_param_string(essid, essid, sizeof(essid), 0444); MODULE_PARM_DESC(essid, "Host AP's ESSID"); -static int iw_mode[MAX_PARM_DEVICES] = { IW_MODE_MASTER, DEF_INTS }; +static int iw_mode[MAX_PARM_DEVICES] = { IW_MODE_INFRA, DEF_INTS }; module_param_array(iw_mode, int, NULL, 0444); MODULE_PARM_DESC(iw_mode, "Initial operation mode"); diff --git a/drivers/parport/Kconfig b/drivers/parport/Kconfig index d92185a5523b..9654a9e83200 100644 --- a/drivers/parport/Kconfig +++ b/drivers/parport/Kconfig @@ -36,7 +36,7 @@ if PARPORT config PARPORT_PC tristate "PC-style hardware" depends on (!SPARC64 || PCI) && !SPARC32 && !M32R && !FRV && \ - (!M68K || ISA) && !MN10300 && !AVR32 && !BLACKFIN + (!M68K || ISA) && !MN10300 && !AVR32 && !BLACKFIN && !ARCH_OMAP ---help--- You should say Y here if you have a PC-style parallel port. All IBM PC compatible computers and some Alphas have PC-style diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index b500840a143b..474f22f304e4 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -798,6 +798,9 @@ void pcie_clear_aspm(struct pci_bus *bus) { struct pci_dev *child; + if (aspm_force) + return; + /* * Clear any ASPM setup that the firmware has carried out on this bus */ diff --git a/drivers/platform/x86/dell-wmi.c b/drivers/platform/x86/dell-wmi.c index fa9a2171cc13..3ab412c18d23 100644 --- a/drivers/platform/x86/dell-wmi.c +++ b/drivers/platform/x86/dell-wmi.c @@ -165,7 +165,7 @@ static void dell_wmi_notify(u32 value, void *context) u16 *buffer_entry = (u16 *)obj->buffer.pointer; if (dell_new_hk_type && (buffer_entry[1] != 0x10)) { - pr_info("Received unknown WMI event (0x%x)\n", + pr_debug("Received unknown WMI event (0x%x)\n", buffer_entry[1]); kfree(obj); return; diff --git a/drivers/platform/x86/sony-laptop.c b/drivers/platform/x86/sony-laptop.c index 210d4ae547c2..9e9a55ec5e9c 100644 --- a/drivers/platform/x86/sony-laptop.c +++ b/drivers/platform/x86/sony-laptop.c @@ -2760,6 +2760,10 @@ struct sonypi_eventtypes { struct sonypi_event *events; }; +struct sony_pic_quirk_entry { + u8 set_wwan_power; +}; + struct sony_pic_dev { struct acpi_device *acpi_dev; struct sony_pic_irq *cur_irq; @@ -2770,6 +2774,7 @@ struct sony_pic_dev { struct sonypi_eventtypes *event_types; int (*handle_irq)(const u8, const u8); int model; + struct sony_pic_quirk_entry *quirks; u16 evport_offset; u8 camera_power; u8 bluetooth_power; @@ -4204,6 +4209,12 @@ static int sony_pic_add(struct acpi_device *device) if (result) goto err_remove_pf; + if (spic_dev.quirks && spic_dev.quirks->set_wwan_power) { + /* + * Power isn't enabled by default. + */ + __sony_pic_set_wwanpower(1); + } return 0; err_remove_pf: @@ -4274,6 +4285,16 @@ static struct acpi_driver sony_pic_driver = { }, }; +static struct sony_pic_quirk_entry sony_pic_vaio_vgn = { + .set_wwan_power = 1, +}; + +static int dmi_matched(const struct dmi_system_id *dmi) +{ + spic_dev.quirks = dmi->driver_data; + return 0; +} + static struct dmi_system_id __initdata sonypi_dmi_table[] = { { .ident = "Sony Vaio", @@ -4288,6 +4309,8 @@ static struct dmi_system_id __initdata sonypi_dmi_table[] = { DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"), DMI_MATCH(DMI_PRODUCT_NAME, "VGN-"), }, + .callback = dmi_matched, + .driver_data = &sony_pic_vaio_vgn, }, { } }; diff --git a/drivers/pnp/isapnp/core.c b/drivers/pnp/isapnp/core.c index 918d5f044865..972fde662338 100644 --- a/drivers/pnp/isapnp/core.c +++ b/drivers/pnp/isapnp/core.c @@ -41,6 +41,7 @@ #include <linux/init.h> #include <linux/isapnp.h> #include <linux/mutex.h> +#include <linux/async.h> #include <asm/io.h> #include "../base.h" @@ -1001,7 +1002,7 @@ struct pnp_protocol isapnp_protocol = { .disable = isapnp_disable_resources, }; -static int __init isapnp_init(void) +static int __init real_isapnp_init(void) { int cards; struct pnp_card *card; @@ -1095,6 +1096,15 @@ static int __init isapnp_init(void) return 0; } +static void __init async_isapnp_init(void *unused, async_cookie_t cookie) +{ + (void)real_isapnp_init(); +} + +static int __init isapnp_init(void) +{ + async_schedule(async_isapnp_init, NULL); +} device_initcall(isapnp_init); /* format is: noisapnp */ diff --git a/drivers/staging/Makefile b/drivers/staging/Makefile index a987b3ad380b..3b32dd97dae0 100644 --- a/drivers/staging/Makefile +++ b/drivers/staging/Makefile @@ -27,7 +27,7 @@ obj-$(CONFIG_LINE6_USB) += line6/ obj-$(CONFIG_USB_SERIAL_QUATECH2) += serqt_usb2/ obj-$(CONFIG_OCTEON_ETHERNET) += octeon/ obj-$(CONFIG_VT6655) += vt6655/ -obj-$(CONFIG_VT6656) += vt6656/ +#obj-$(CONFIG_VT6656) += vt6656/ obj-$(CONFIG_VME_BUS) += vme/ obj-$(CONFIG_IPACK_BUS) += ipack/ obj-$(CONFIG_DX_SEP) += sep/ diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 84cbf298c094..509037447161 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -102,6 +102,7 @@ #include <linux/uaccess.h> #include <linux/kdb.h> #include <linux/ctype.h> +#include <linux/screen_info.h> #define MAX_NR_CON_DRIVER 16 @@ -144,7 +145,7 @@ static const struct consw *con_driver_map[MAX_NR_CONSOLES]; static int con_open(struct tty_struct *, struct file *); static void vc_init(struct vc_data *vc, unsigned int rows, - unsigned int cols, int do_clear); + unsigned int cols, int do_clear, int mode); static void gotoxy(struct vc_data *vc, int new_x, int new_y); static void save_cur(struct vc_data *vc); static void reset_terminal(struct vc_data *vc, int do_clear); @@ -165,6 +166,9 @@ module_param(global_cursor_default, int, S_IRUGO | S_IWUSR); static int cur_default = CUR_DEFAULT; module_param(cur_default, int, S_IRUGO | S_IWUSR); +int vt_handoff = 0; +module_param_named(handoff, vt_handoff, int, S_IRUGO | S_IWUSR); + /* * ignore_poke: don't unblank the screen when things are typed. This is * mainly for the privacy of braille terminal users. @@ -694,6 +698,13 @@ void redraw_screen(struct vc_data *vc, int is_switch) } if (tty0dev) sysfs_notify(&tty0dev->kobj, NULL, "active"); + /* + * If we are switching away from a transparent VT the contents + * will be lost, convert it into a blank text console then + * it will be repainted blank if we ever switch back. + */ + if (old_vc->vc_mode == KD_TRANSPARENT) + old_vc->vc_mode = KD_TEXT; } else { hide_cursor(vc); redraw = 1; @@ -807,7 +818,7 @@ int vc_allocate(unsigned int currcons) /* return 0 on success */ if (global_cursor_default == -1) global_cursor_default = 1; - vc_init(vc, vc->vc_rows, vc->vc_cols, 1); + vc_init(vc, vc->vc_rows, vc->vc_cols, 1, KD_TEXT); vcs_make_sysfs(currcons); atomic_notifier_call_chain(&vt_notifier_list, VT_ALLOCATE, ¶m); } @@ -2848,7 +2859,7 @@ module_param_named(italic, default_italic_color, int, S_IRUGO | S_IWUSR); module_param_named(underline, default_underline_color, int, S_IRUGO | S_IWUSR); static void vc_init(struct vc_data *vc, unsigned int rows, - unsigned int cols, int do_clear) + unsigned int cols, int do_clear, int mode) { int j, k ; @@ -2859,7 +2870,7 @@ static void vc_init(struct vc_data *vc, unsigned int rows, set_origin(vc); vc->vc_pos = vc->vc_origin; - reset_vc(vc); + reset_vc(vc, mode); for (j=k=0; j<16; j++) { vc->vc_palette[k++] = default_red[j] ; vc->vc_palette[k++] = default_grn[j] ; @@ -2885,6 +2896,13 @@ static int __init con_init(void) struct vc_data *vc; unsigned int currcons = 0, i; + if (screen_info.flags & VIDEO_FLAGS_HANDOFF) { + if (vt_handoff == 0) + vt_handoff = 8; + printk(KERN_INFO "vt handoff: grub requested handoff (vt#%d)\n", + vt_handoff); + } + console_lock(); if (conswitchp) @@ -2916,16 +2934,31 @@ static int __init con_init(void) mod_timer(&console_timer, jiffies + (blankinterval * HZ)); } + if (vt_handoff > 0 && vt_handoff <= MAX_NR_CONSOLES) { + currcons = vt_handoff - 1; + vc_cons[currcons].d = vc = kzalloc(sizeof(struct vc_data), GFP_NOWAIT); + INIT_WORK(&vc_cons[currcons].SAK_work, vc_SAK); + visual_init(vc, currcons, 1); + vc->vc_screenbuf = kzalloc(vc->vc_screenbuf_size, GFP_NOWAIT); + vc_init(vc, vc->vc_rows, vc->vc_cols, 0, KD_TRANSPARENT); + } for (currcons = 0; currcons < MIN_NR_CONSOLES; currcons++) { + if (currcons == vt_handoff - 1) + continue; vc_cons[currcons].d = vc = kzalloc(sizeof(struct vc_data), GFP_NOWAIT); INIT_WORK(&vc_cons[currcons].SAK_work, vc_SAK); tty_port_init(&vc->port); visual_init(vc, currcons, 1); vc->vc_screenbuf = kzalloc(vc->vc_screenbuf_size, GFP_NOWAIT); vc_init(vc, vc->vc_rows, vc->vc_cols, - currcons || !vc->vc_sw->con_save_screen); + currcons || !vc->vc_sw->con_save_screen, KD_TEXT); } currcons = fg_console = 0; + if (vt_handoff > 0) { + printk(KERN_INFO "vt handoff: transparent VT on vt#%d\n", + vt_handoff); + currcons = fg_console = vt_handoff - 1; + } master_display_fg = vc = vc_cons[currcons].d; set_origin(vc); save_screen(vc); diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c index 64618547be11..ff5496af5faa 100644 --- a/drivers/tty/vt/vt_ioctl.c +++ b/drivers/tty/vt/vt_ioctl.c @@ -996,9 +996,9 @@ out: return ret; } -void reset_vc(struct vc_data *vc) +void reset_vc(struct vc_data *vc, int mode) { - vc->vc_mode = KD_TEXT; + vc->vc_mode = mode; vt_reset_unicode(vc->vc_num); vc->vt_mode.mode = VT_AUTO; vc->vt_mode.waitv = 0; @@ -1030,7 +1030,7 @@ void vc_SAK(struct work_struct *work) */ if (tty) __do_SAK(tty); - reset_vc(vc); + reset_vc(vc, KD_TEXT); } console_unlock(); } @@ -1287,7 +1287,7 @@ static void complete_change_console(struct vc_data *vc) * this outside of VT_PROCESS but there is no single process * to account for and tracking tty count may be undesirable. */ - reset_vc(vc); + reset_vc(vc, KD_TEXT); if (old_vc_mode != vc->vc_mode) { if (vc->vc_mode == KD_TEXT) @@ -1359,7 +1359,7 @@ void change_console(struct vc_data *new_vc) * this outside of VT_PROCESS but there is no single process * to account for and tracking tty count may be undesirable. */ - reset_vc(vc); + reset_vc(vc, KD_TEXT); /* * Fall through to normal (VT_AUTO) handling of the switch... diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 04fb834c3fa1..78c26de8d425 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -24,6 +24,7 @@ #include <linux/kthread.h> #include <linux/mutex.h> #include <linux/freezer.h> +#include <linux/rcupdate.h> #include <asm/uaccess.h> #include <asm/byteorder.h> @@ -2218,6 +2219,10 @@ fail: */ int usb_deauthorize_device(struct usb_device *usb_dev) { + char *product = NULL; + char *manufacturer = NULL; + char *serial = NULL; + usb_lock_device(usb_dev); if (usb_dev->authorized == 0) goto out_unauthorized; @@ -2225,11 +2230,12 @@ int usb_deauthorize_device(struct usb_device *usb_dev) usb_dev->authorized = 0; usb_set_configuration(usb_dev, -1); - kfree(usb_dev->product); + product = usb_dev->product; + manufacturer = usb_dev->manufacturer; + serial = usb_dev->serial; + usb_dev->product = kstrdup("n/a (unauthorized)", GFP_KERNEL); - kfree(usb_dev->manufacturer); usb_dev->manufacturer = kstrdup("n/a (unauthorized)", GFP_KERNEL); - kfree(usb_dev->serial); usb_dev->serial = kstrdup("n/a (unauthorized)", GFP_KERNEL); usb_destroy_configuration(usb_dev); @@ -2237,6 +2243,12 @@ int usb_deauthorize_device(struct usb_device *usb_dev) out_unauthorized: usb_unlock_device(usb_dev); + if (product || manufacturer || serial) { + synchronize_rcu(); + kfree(product); + kfree(manufacturer); + kfree(serial); + } return 0; } @@ -2244,6 +2256,9 @@ out_unauthorized: int usb_authorize_device(struct usb_device *usb_dev) { int result = 0, c; + char *product = NULL; + char *manufacturer = NULL; + char *serial = NULL; usb_lock_device(usb_dev); if (usb_dev->authorized == 1) @@ -2262,11 +2277,12 @@ int usb_authorize_device(struct usb_device *usb_dev) goto error_device_descriptor; } - kfree(usb_dev->product); + product = usb_dev->product; + manufacturer = usb_dev->manufacturer; + serial = usb_dev->serial; + usb_dev->product = NULL; - kfree(usb_dev->manufacturer); usb_dev->manufacturer = NULL; - kfree(usb_dev->serial); usb_dev->serial = NULL; usb_dev->authorized = 1; @@ -2294,6 +2310,12 @@ error_device_descriptor: error_autoresume: out_authorized: usb_unlock_device(usb_dev); // complements locktree + if (product || manufacturer || serial) { + synchronize_rcu(); + kfree(product); + kfree(manufacturer); + kfree(serial); + } return result; } diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c index 9a56e3adf476..45801b5678fc 100644 --- a/drivers/usb/core/sysfs.c +++ b/drivers/usb/core/sysfs.c @@ -85,9 +85,9 @@ static ssize_t show_##name(struct device *dev, \ int retval; \ \ udev = to_usb_device(dev); \ - usb_lock_device(udev); \ - retval = sprintf(buf, "%s\n", udev->name); \ - usb_unlock_device(udev); \ + rcu_read_lock(); \ + retval = sprintf(buf, "%s\n", rcu_dereference(udev->name)); \ + rcu_read_unlock(); \ return retval; \ } \ static DEVICE_ATTR(name, S_IRUGO, show_##name, NULL); diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index 1719886bb9be..d1630aeae363 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -1163,6 +1163,13 @@ UNUSUAL_DEV( 0x0af0, 0x6971, 0x0000, 0x9999, USB_SC_DEVICE, USB_PR_DEVICE, option_ms_init, 0), +/* Reported by Timo Aaltonen <tjaalton@ubuntu.com> */ +UNUSUAL_DEV( 0x0af0, 0x7011, 0x0000, 0x9999, + "Option", + "Mass Storage", + USB_SC_DEVICE, USB_PR_DEVICE, option_ms_init, + 0 ), + /* Reported by F. Aben <f.aben@option.com> * This device (wrongly) has a vendor-specific device descriptor. * The entry is needed so usb-storage can bind to it's mass-storage diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig index b6ea1b569100..b786a00023ab 100644 --- a/drivers/video/Kconfig +++ b/drivers/video/Kconfig @@ -755,8 +755,8 @@ config FB_UVESA If unsure, say N. config FB_VESA - bool "VESA VGA graphics support" - depends on (FB = y) && X86 + tristate "VESA VGA graphics support" + depends on FB && X86 select FB_CFB_FILLRECT select FB_CFB_COPYAREA select FB_CFB_IMAGEBLIT diff --git a/drivers/video/vesafb.c b/drivers/video/vesafb.c index 501b3406c6d5..eb78a5986c26 100644 --- a/drivers/video/vesafb.c +++ b/drivers/video/vesafb.c @@ -27,6 +27,12 @@ #define dac_reg (0x3c8) #define dac_val (0x3c9) +struct vesafb_info +{ + u32 pseudo_palette[256]; + int mtrr_hdl; +}; + /* --------------------------------------------------------------------- */ static struct fb_var_screeninfo vesafb_defined __initdata = { @@ -40,22 +46,43 @@ static struct fb_var_screeninfo vesafb_defined __initdata = { .vmode = FB_VMODE_NONINTERLACED, }; -static struct fb_fix_screeninfo vesafb_fix __initdata = { +static struct fb_fix_screeninfo vesafb_fix = { .id = "VESA VGA", .type = FB_TYPE_PACKED_PIXELS, .accel = FB_ACCEL_NONE, }; +#ifndef MODULE static int inverse __read_mostly; -static int mtrr __read_mostly; /* disable mtrr */ +#endif +static int mtrr __read_mostly = 3; /* disable mtrr */ static int vram_remap __initdata; /* Set amount of memory to be used */ static int vram_total __initdata; /* Set total amount of memory */ static int pmi_setpal __read_mostly = 1; /* pmi for palette changes ??? */ +static int redraw __read_mostly; static int ypan __read_mostly; /* 0..nothing, 1..ypan, 2..ywrap */ +static int ywrap __read_mostly; static void (*pmi_start)(void) __read_mostly; static void (*pmi_pal) (void) __read_mostly; static int depth __read_mostly; static int vga_compat __read_mostly; + +module_param(redraw, bool, 0); +module_param(ypan, bool, 0); +module_param(ywrap, bool, 0); +module_param_named(vgapal, pmi_setpal, invbool, 0); +MODULE_PARM_DESC(vgapal, "Use VGA for setting palette (default)"); +module_param_named(pmipal, pmi_setpal, bool, 0); +MODULE_PARM_DESC(pmipal, "Use PMI for setting palette"); +module_param(mtrr, uint, 0); +MODULE_PARM_DESC(mtrr, "Enable MTRR support (default)"); +module_param_named(nomtrr, mtrr, invbool, 0); +MODULE_PARM_DESC(nomtrr, "Disable MTRR support"); +module_param(vram_remap, int, 0); +MODULE_PARM_DESC(vram_remap, "Set total amount of memory to be used"); +module_param(vram_total, int, 0); +MODULE_PARM_DESC(vram_total, "Total amount of memory"); + /* --------------------------------------------------------------------- */ static int vesafb_pan_display(struct fb_var_screeninfo *var, @@ -192,6 +219,7 @@ static struct fb_ops vesafb_ops = { .fb_imageblit = cfb_imageblit, }; +#ifndef MODULE static int __init vesafb_setup(char *options) { char *this_opt; @@ -225,10 +253,12 @@ static int __init vesafb_setup(char *options) } return 0; } +#endif static int __init vesafb_probe(struct platform_device *dev) { struct fb_info *info; + struct vesafb_info *vfb_info; int i, err; unsigned int size_vmode; unsigned int size_remap; @@ -287,13 +317,14 @@ static int __init vesafb_probe(struct platform_device *dev) spaces our resource handlers simply don't know about */ } - info = framebuffer_alloc(sizeof(u32) * 256, &dev->dev); + info = framebuffer_alloc(sizeof(struct vesafb_info), &dev->dev); if (!info) { release_mem_region(vesafb_fix.smem_start, size_total); return -ENOMEM; } - info->pseudo_palette = info->par; - info->par = NULL; + vfb_info = (struct vesafb_info *) info->par; + vfb_info->mtrr_hdl = -1; + info->pseudo_palette = vfb_info->pseudo_palette; /* set vesafb aperture size for generic probing */ info->apertures = alloc_apertures(1); @@ -423,17 +454,15 @@ static int __init vesafb_probe(struct platform_device *dev) } if (type) { - int rc; - /* Find the largest power-of-two */ temp_size = roundup_pow_of_two(temp_size); /* Try and find a power of two to add */ do { - rc = mtrr_add(vesafb_fix.smem_start, temp_size, + vfb_info->mtrr_hdl = mtrr_add(vesafb_fix.smem_start, temp_size, type, 1); temp_size >>= 1; - } while (temp_size >= PAGE_SIZE && rc == -EINVAL); + } while (temp_size >= PAGE_SIZE && vfb_info->mtrr_hdl == -EINVAL); } } #endif @@ -495,7 +524,27 @@ err: return err; } +static int __exit vesafb_remove(struct platform_device *device) +{ + struct fb_info *info = dev_get_drvdata(&device->dev); + + unregister_framebuffer(info); +#ifdef CONFIG_MTRR + { + struct vesafb_info *vfb_info = (struct vesafb_info *) info->par; + if (vfb_info->mtrr_hdl >= 0) + mtrr_del(vfb_info->mtrr_hdl, 0, 0); + } +#endif + iounmap(info->screen_base); + framebuffer_release(info); + release_mem_region(vesafb_fix.smem_start, vesafb_fix.smem_len); + + return 0; +} + static struct platform_driver vesafb_driver = { + .remove = vesafb_remove, .driver = { .name = "vesafb", }, @@ -506,11 +555,18 @@ static struct platform_device *vesafb_device; static int __init vesafb_init(void) { int ret; +#ifndef MODULE char *option = NULL; /* ignore error return of fb_get_options */ fb_get_options("vesafb", &option); vesafb_setup(option); +#else + if (redraw) + ypan = 0; + if (ywrap) + ypan = 2; +#endif vesafb_device = platform_device_alloc("vesafb", 0); if (!vesafb_device) @@ -530,6 +586,14 @@ static int __init vesafb_init(void) return ret; } + +static void __exit vesafb_exit(void) +{ + platform_device_unregister(vesafb_device); + platform_driver_unregister(&vesafb_driver); +} + module_init(vesafb_init); +module_exit(vesafb_exit); MODULE_LICENSE("GPL"); diff --git a/fs/Kconfig b/fs/Kconfig index 1dd49481854d..390a2852c35c 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -67,6 +67,7 @@ source "fs/quota/Kconfig" source "fs/autofs4/Kconfig" source "fs/fuse/Kconfig" +source "fs/overlayfs/Kconfig" config CUSE tristate "Character device in Userspace support" diff --git a/fs/Makefile b/fs/Makefile index 95cf9de6ae02..73cc7c116b3c 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -106,6 +106,7 @@ obj-$(CONFIG_QNX6FS_FS) += qnx6/ obj-$(CONFIG_AUTOFS4_FS) += autofs4/ obj-$(CONFIG_ADFS_FS) += adfs/ obj-$(CONFIG_FUSE_FS) += fuse/ +obj-$(CONFIG_OVERLAYFS_FS) += overlayfs/ obj-$(CONFIG_UDF_FS) += udf/ obj-$(CONFIG_SUN_OPENPROMFS) += openpromfs/ obj-$(CONFIG_OMFS_FS) += omfs/ diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index 68954937a071..c54ea903a169 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -544,6 +544,13 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags s->s_maxbytes = path.dentry->d_sb->s_maxbytes; s->s_blocksize = path.dentry->d_sb->s_blocksize; s->s_magic = ECRYPTFS_SUPER_MAGIC; + s->s_stack_depth = path.dentry->d_sb->s_stack_depth + 1; + + rc = -EINVAL; + if (s->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) { + printk(KERN_ERR "eCryptfs: maximum fs stacking depth exceeded\n"); + goto out_free; + } inode = ecryptfs_get_inode(path.dentry->d_inode, s); rc = PTR_ERR(inode); diff --git a/fs/exec.c b/fs/exec.c index a79786a8d2c8..88af8a242f91 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -56,6 +56,8 @@ #include <linux/oom.h> #include <linux/compat.h> +#include <trace/events/fs.h> + #include <asm/uaccess.h> #include <asm/mmu_context.h> #include <asm/tlb.h> @@ -781,6 +783,8 @@ struct file *open_exec(const char *name) fsnotify_open(file); + trace_open_exec(name); + err = deny_write_access(file); if (err) goto exit; diff --git a/fs/file_table.c b/fs/file_table.c index a305d9e2d1b2..cc998cad4e83 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -441,6 +441,8 @@ void file_sb_list_del(struct file *file) } } +EXPORT_SYMBOL(file_sb_list_del); + #ifdef CONFIG_SMP /* diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 233d19b0bab4..bdb7e1c45b24 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -27,6 +27,7 @@ #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/tracepoint.h> +#include <trace/events/vfs.h> #include "internal.h" /* @@ -1171,6 +1172,8 @@ void __mark_inode_dirty(struct inode *inode, int flags) if ((inode->i_state & flags) == flags) return; + trace_dirty_inode(inode, current); + if (unlikely(block_dump > 1)) block_dump___mark_inode_dirty(inode); diff --git a/fs/inode.c b/fs/inode.c index c99163b1b310..0e99c4d8abfb 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -56,6 +56,7 @@ static struct hlist_head *inode_hashtable __read_mostly; static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock); __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_sb_list_lock); +EXPORT_SYMBOL(inode_sb_list_lock); /* * Empty aops. Can be used for the cases where the user does not @@ -1883,3 +1884,7 @@ void inode_dio_done(struct inode *inode) wake_up_bit(&inode->i_state, __I_DIO_WAKEUP); } EXPORT_SYMBOL(inode_dio_done); + +#define CREATE_TRACE_POINTS +#include <trace/events/vfs.h> + diff --git a/fs/namei.c b/fs/namei.c index 7d694194024a..caf090c48629 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -315,6 +315,36 @@ static inline int do_inode_permission(struct inode *inode, int mask) } /** + * inode_only_permission - check access rights to a given inode only + * @inode: inode to check permissions on + * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC, ...) + * + * Uses to check read/write/execute permissions on an inode directly, we do + * not check filesystem permissions. + */ +int inode_only_permission(struct inode *inode, int mask) +{ + int retval; + + /* + * Nobody gets write access to an immutable file. + */ + if (unlikely(mask & MAY_WRITE) && IS_IMMUTABLE(inode)) + return -EACCES; + + retval = do_inode_permission(inode, mask); + if (retval) + return retval; + + retval = devcgroup_inode_permission(inode, mask); + if (retval) + return retval; + + return security_inode_permission(inode, mask); +} +EXPORT_SYMBOL(inode_only_permission); + +/** * inode_permission - check for access rights to a given inode * @inode: inode to check permission on * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC, ...) @@ -328,8 +358,6 @@ static inline int do_inode_permission(struct inode *inode, int mask) */ int inode_permission(struct inode *inode, int mask) { - int retval; - if (unlikely(mask & MAY_WRITE)) { umode_t mode = inode->i_mode; @@ -339,23 +367,9 @@ int inode_permission(struct inode *inode, int mask) if (IS_RDONLY(inode) && (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) return -EROFS; - - /* - * Nobody gets write access to an immutable file. - */ - if (IS_IMMUTABLE(inode)) - return -EACCES; } - retval = do_inode_permission(inode, mask); - if (retval) - return retval; - - retval = devcgroup_inode_permission(inode, mask); - if (retval) - return retval; - - return security_inode_permission(inode, mask); + return inode_only_permission(inode, mask); } /** @@ -1864,10 +1878,11 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, * needs parent already locked. Doesn't follow mounts. * SMP-safe. */ -static struct dentry *lookup_hash(struct nameidata *nd) +struct dentry *lookup_hash(struct nameidata *nd) { return __lookup_hash(&nd->last, nd->path.dentry, nd); } +EXPORT_SYMBOL(lookup_hash); /** * lookup_one_len - filesystem helper to lookup single pathname component diff --git a/fs/namespace.c b/fs/namespace.c index 1e4a5fe3d7b7..6731fc258b3f 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1327,6 +1327,24 @@ void drop_collected_mounts(struct vfsmount *mnt) release_mounts(&umount_list); } +struct vfsmount *clone_private_mount(struct path *path) +{ + struct mount *old_mnt = real_mount(path->mnt); + struct mount *new_mnt; + + if (IS_MNT_UNBINDABLE(old_mnt)) + return ERR_PTR(-EINVAL); + + down_read(&namespace_sem); + new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE); + up_read(&namespace_sem); + if (!new_mnt) + return ERR_PTR(-ENOMEM); + + return &new_mnt->mnt; +} +EXPORT_SYMBOL_GPL(clone_private_mount); + int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg, struct vfsmount *root) { @@ -1341,6 +1359,7 @@ int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg, } return 0; } +EXPORT_SYMBOL(iterate_mounts); static void cleanup_group_ids(struct mount *mnt, struct mount *end) { diff --git a/fs/notify/group.c b/fs/notify/group.c index 63fc294a4692..6f4adcab9a5b 100644 --- a/fs/notify/group.c +++ b/fs/notify/group.c @@ -22,6 +22,7 @@ #include <linux/srcu.h> #include <linux/rculist.h> #include <linux/wait.h> +#include <linux/module.h> #include <linux/fsnotify_backend.h> #include "fsnotify.h" @@ -70,6 +71,7 @@ void fsnotify_put_group(struct fsnotify_group *group) if (atomic_dec_and_test(&group->refcnt)) fsnotify_destroy_group(group); } +EXPORT_SYMBOL(fsnotify_put_group); /* * Create a new fsnotify_group and hold a reference for the group returned. @@ -102,3 +104,4 @@ struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops) return group; } +EXPORT_SYMBOL(fsnotify_alloc_group); diff --git a/fs/notify/mark.c b/fs/notify/mark.c index f104d565b682..54f36db45def 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -112,6 +112,7 @@ void fsnotify_put_mark(struct fsnotify_mark *mark) if (atomic_dec_and_test(&mark->refcnt)) mark->free_mark(mark); } +EXPORT_SYMBOL(fsnotify_put_mark); /* * Any time a mark is getting freed we end up here. @@ -191,6 +192,7 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark) if (unlikely(atomic_dec_and_test(&group->num_marks))) fsnotify_final_destroy_group(group); } +EXPORT_SYMBOL(fsnotify_destroy_mark); void fsnotify_set_mark_mask_locked(struct fsnotify_mark *mark, __u32 mask) { @@ -278,6 +280,7 @@ err: return ret; } +EXPORT_SYMBOL(fsnotify_add_mark); /* * clear any marks in a group in which mark->flags & flags is true @@ -333,6 +336,7 @@ void fsnotify_init_mark(struct fsnotify_mark *mark, atomic_set(&mark->refcnt, 1); mark->free_mark = free_mark; } +EXPORT_SYMBOL(fsnotify_init_mark); static int fsnotify_mark_destroy(void *ignored) { diff --git a/fs/open.c b/fs/open.c index d6c79a0dffc7..21078e846219 100644 --- a/fs/open.c +++ b/fs/open.c @@ -33,6 +33,9 @@ #include "internal.h" +#define CREATE_TRACE_POINTS +#include <trace/events/fs.h> + int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs, struct file *filp) { @@ -60,6 +63,7 @@ int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs, mutex_unlock(&dentry->d_inode->i_mutex); return ret; } +EXPORT_SYMBOL(do_truncate); static long do_sys_truncate(const char __user *pathname, loff_t length) { @@ -667,24 +671,24 @@ int open_check_o_direct(struct file *f) return 0; } -static struct file *do_dentry_open(struct dentry *dentry, struct vfsmount *mnt, - struct file *f, - int (*open)(struct inode *, struct file *), - const struct cred *cred) +static struct file *do_dentry_open(struct path *path, struct file *f, + int (*open)(struct inode *, struct file *), + const struct cred *cred) { static const struct file_operations empty_fops = {}; struct inode *inode; int error; + path_get(path); f->f_mode = OPEN_FMODE(f->f_flags) | FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE; if (unlikely(f->f_flags & O_PATH)) f->f_mode = FMODE_PATH; - inode = dentry->d_inode; + inode = path->dentry->d_inode; if (f->f_mode & FMODE_WRITE) { - error = __get_file_write_access(inode, mnt); + error = __get_file_write_access(inode, path->mnt); if (error) goto cleanup_file; if (!special_file(inode->i_mode)) @@ -692,8 +696,7 @@ static struct file *do_dentry_open(struct dentry *dentry, struct vfsmount *mnt, } f->f_mapping = inode->i_mapping; - f->f_path.dentry = dentry; - f->f_path.mnt = mnt; + f->f_path = *path; f->f_pos = 0; file_sb_list_add(f, inode->i_sb); @@ -740,24 +743,22 @@ cleanup_all: * here, so just reset the state. */ file_reset_write(f); - mnt_drop_write(mnt); + mnt_drop_write(path->mnt); } } file_sb_list_del(f); f->f_path.dentry = NULL; f->f_path.mnt = NULL; cleanup_file: - dput(dentry); - mntput(mnt); + path_put(path); return ERR_PTR(error); } -static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt, - struct file *f, +static struct file *__dentry_open(struct path *path, struct file *f, int (*open)(struct inode *, struct file *), const struct cred *cred) { - struct file *res = do_dentry_open(dentry, mnt, f, open, cred); + struct file *res = do_dentry_open(path, f, open, cred); if (!IS_ERR(res)) { int error = open_check_o_direct(f); if (error) { @@ -792,14 +793,14 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt, struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry, int (*open)(struct inode *, struct file *)) { + struct path path = { .dentry = dentry, .mnt = nd->path.mnt }; const struct cred *cred = current_cred(); if (IS_ERR(nd->intent.open.file)) goto out; if (IS_ERR(dentry)) goto out_err; - nd->intent.open.file = __dentry_open(dget(dentry), mntget(nd->path.mnt), - nd->intent.open.file, + nd->intent.open.file = __dentry_open(&path, nd->intent.open.file, open, cred); out: return nd->intent.open.file; @@ -831,9 +832,7 @@ struct file *nameidata_to_filp(struct nameidata *nd) } else { struct file *res; - path_get(&nd->path); - res = do_dentry_open(nd->path.dentry, nd->path.mnt, - filp, NULL, cred); + res = vfs_open(&nd->path, filp, cred); if (!IS_ERR(res)) { int error; @@ -860,27 +859,48 @@ struct file *nameidata_to_filp(struct nameidata *nd) struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags, const struct cred *cred) { - int error; struct file *f; + struct file *ret; + struct path path = { .dentry = dentry, .mnt = mnt }; validate_creds(cred); /* We must always pass in a valid mount pointer. */ BUG_ON(!mnt); - error = -ENFILE; + ret = ERR_PTR(-ENFILE); f = get_empty_filp(); - if (f == NULL) { - dput(dentry); - mntput(mnt); - return ERR_PTR(error); + if (f != NULL) { + f->f_flags = flags; + ret = vfs_open(&path, f, cred); } + path_put(&path); - f->f_flags = flags; - return __dentry_open(dentry, mnt, f, NULL, cred); + return ret; } EXPORT_SYMBOL(dentry_open); +/** + * vfs_open - open the file at the given path + * @path: path to open + * @filp: newly allocated file with f_flag initialized + * @cred: credentials to use + * + * Open the file. If successful, the returned file will have acquired + * an additional reference for path. + */ +struct file *vfs_open(struct path *path, struct file *filp, + const struct cred *cred) +{ + struct inode *inode = path->dentry->d_inode; + + if (inode->i_op->open) + return inode->i_op->open(path->dentry, filp, cred); + else + return __dentry_open(path, filp, NULL, cred); +} +EXPORT_SYMBOL(vfs_open); + static void __put_unused_fd(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = files_fdtable(files); @@ -1035,6 +1055,7 @@ long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode) } else { fsnotify_open(f); fd_install(fd, f); + trace_do_sys_open(tmp, flags, mode); } } putname(tmp); diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig new file mode 100644 index 000000000000..c4517da01fa9 --- /dev/null +++ b/fs/overlayfs/Kconfig @@ -0,0 +1,4 @@ +config OVERLAYFS_FS + tristate "Overlay filesystem support" + help + Add support for overlay filesystem. diff --git a/fs/overlayfs/Makefile b/fs/overlayfs/Makefile new file mode 100644 index 000000000000..8f91889480d0 --- /dev/null +++ b/fs/overlayfs/Makefile @@ -0,0 +1,7 @@ +# +# Makefile for the overlay filesystem. +# + +obj-$(CONFIG_OVERLAYFS_FS) += overlayfs.o + +overlayfs-objs := super.o inode.o dir.o readdir.o copy_up.o diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c new file mode 100644 index 000000000000..87dbeee0a14e --- /dev/null +++ b/fs/overlayfs/copy_up.c @@ -0,0 +1,385 @@ +/* + * + * Copyright (C) 2011 Novell Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include <linux/fs.h> +#include <linux/slab.h> +#include <linux/file.h> +#include <linux/splice.h> +#include <linux/xattr.h> +#include <linux/security.h> +#include <linux/uaccess.h> +#include <linux/sched.h> +#include "overlayfs.h" + +#define OVL_COPY_UP_CHUNK_SIZE (1 << 20) + +static int ovl_copy_up_xattr(struct dentry *old, struct dentry *new) +{ + ssize_t list_size, size; + char *buf, *name, *value; + int error; + + if (!old->d_inode->i_op->getxattr || + !new->d_inode->i_op->getxattr) + return 0; + + list_size = vfs_listxattr(old, NULL, 0); + if (list_size <= 0) { + if (list_size == -EOPNOTSUPP) + return 0; + return list_size; + } + + buf = kzalloc(list_size, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + error = -ENOMEM; + value = kmalloc(XATTR_SIZE_MAX, GFP_KERNEL); + if (!value) + goto out; + + list_size = vfs_listxattr(old, buf, list_size); + if (list_size <= 0) { + error = list_size; + goto out_free_value; + } + + for (name = buf; name < (buf + list_size); name += strlen(name) + 1) { + size = vfs_getxattr(old, name, value, XATTR_SIZE_MAX); + if (size <= 0) { + error = size; + goto out_free_value; + } + error = vfs_setxattr(new, name, value, size, 0); + if (error) + goto out_free_value; + } + +out_free_value: + kfree(value); +out: + kfree(buf); + return error; +} + +static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len) +{ + struct file *old_file; + struct file *new_file; + int error = 0; + + if (len == 0) + return 0; + + old_file = ovl_path_open(old, O_RDONLY); + if (IS_ERR(old_file)) + return PTR_ERR(old_file); + + new_file = ovl_path_open(new, O_WRONLY); + if (IS_ERR(new_file)) { + error = PTR_ERR(new_file); + goto out_fput; + } + + /* FIXME: copy up sparse files efficiently */ + while (len) { + loff_t offset = new_file->f_pos; + size_t this_len = OVL_COPY_UP_CHUNK_SIZE; + long bytes; + + if (len < this_len) + this_len = len; + + if (signal_pending_state(TASK_KILLABLE, current)) { + error = -EINTR; + break; + } + + bytes = do_splice_direct(old_file, &offset, new_file, this_len, + SPLICE_F_MOVE); + if (bytes <= 0) { + error = bytes; + break; + } + + len -= bytes; + } + + fput(new_file); +out_fput: + fput(old_file); + return error; +} + +static char *ovl_read_symlink(struct dentry *realdentry) +{ + int res; + char *buf; + struct inode *inode = realdentry->d_inode; + mm_segment_t old_fs; + + res = -EINVAL; + if (!inode->i_op->readlink) + goto err; + + res = -ENOMEM; + buf = (char *) __get_free_page(GFP_KERNEL); + if (!buf) + goto err; + + old_fs = get_fs(); + set_fs(get_ds()); + /* The cast to a user pointer is valid due to the set_fs() */ + res = inode->i_op->readlink(realdentry, + (char __user *)buf, PAGE_SIZE - 1); + set_fs(old_fs); + if (res < 0) { + free_page((unsigned long) buf); + goto err; + } + buf[res] = '\0'; + + return buf; + +err: + return ERR_PTR(res); +} + +static int ovl_set_timestamps(struct dentry *upperdentry, struct kstat *stat) +{ + struct iattr attr = { + .ia_valid = + ATTR_ATIME | ATTR_MTIME | ATTR_ATIME_SET | ATTR_MTIME_SET, + .ia_atime = stat->atime, + .ia_mtime = stat->mtime, + }; + + return notify_change(upperdentry, &attr); +} + +static int ovl_set_mode(struct dentry *upperdentry, umode_t mode) +{ + struct iattr attr = { + .ia_valid = ATTR_MODE, + .ia_mode = mode, + }; + + return notify_change(upperdentry, &attr); +} + +static int ovl_copy_up_locked(struct dentry *upperdir, struct dentry *dentry, + struct path *lowerpath, struct kstat *stat, + const char *link) +{ + int err; + struct path newpath; + umode_t mode = stat->mode; + + /* Can't properly set mode on creation because of the umask */ + stat->mode &= S_IFMT; + + ovl_path_upper(dentry, &newpath); + WARN_ON(newpath.dentry); + newpath.dentry = ovl_upper_create(upperdir, dentry, stat, link); + if (IS_ERR(newpath.dentry)) + return PTR_ERR(newpath.dentry); + + if (S_ISREG(stat->mode)) { + err = ovl_copy_up_data(lowerpath, &newpath, stat->size); + if (err) + goto err_remove; + } + + err = ovl_copy_up_xattr(lowerpath->dentry, newpath.dentry); + if (err) + goto err_remove; + + mutex_lock(&newpath.dentry->d_inode->i_mutex); + if (!S_ISLNK(stat->mode)) + err = ovl_set_mode(newpath.dentry, mode); + if (!err) + err = ovl_set_timestamps(newpath.dentry, stat); + mutex_unlock(&newpath.dentry->d_inode->i_mutex); + if (err) + goto err_remove; + + ovl_dentry_update(dentry, newpath.dentry); + + /* + * Easiest way to get rid of the lower dentry reference is to + * drop this dentry. This is neither needed nor possible for + * directories. + */ + if (!S_ISDIR(stat->mode)) + d_drop(dentry); + + return 0; + +err_remove: + if (S_ISDIR(stat->mode)) + vfs_rmdir(upperdir->d_inode, newpath.dentry); + else + vfs_unlink(upperdir->d_inode, newpath.dentry); + + dput(newpath.dentry); + + return err; +} + +/* + * Copy up a single dentry + * + * Directory renames only allowed on "pure upper" (already created on + * upper filesystem, never copied up). Directories which are on lower or + * are merged may not be renamed. For these -EXDEV is returned and + * userspace has to deal with it. This means, when copying up a + * directory we can rely on it and ancestors being stable. + * + * Non-directory renames start with copy up of source if necessary. The + * actual rename will only proceed once the copy up was successful. Copy + * up uses upper parent i_mutex for exclusion. Since rename can change + * d_parent it is possible that the copy up will lock the old parent. At + * that point the file will have already been copied up anyway. + */ +static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry, + struct path *lowerpath, struct kstat *stat) +{ + int err; + struct kstat pstat; + struct path parentpath; + struct dentry *upperdir; + const struct cred *old_cred; + struct cred *override_cred; + char *link = NULL; + + ovl_path_upper(parent, &parentpath); + upperdir = parentpath.dentry; + + err = vfs_getattr(parentpath.mnt, parentpath.dentry, &pstat); + if (err) + return err; + + if (S_ISLNK(stat->mode)) { + link = ovl_read_symlink(lowerpath->dentry); + if (IS_ERR(link)) + return PTR_ERR(link); + } + + err = -ENOMEM; + override_cred = prepare_creds(); + if (!override_cred) + goto out_free_link; + + override_cred->fsuid = stat->uid; + override_cred->fsgid = stat->gid; + /* + * CAP_SYS_ADMIN for copying up extended attributes + * CAP_DAC_OVERRIDE for create + * CAP_FOWNER for chmod, timestamp update + * CAP_FSETID for chmod + * CAP_MKNOD for mknod + */ + cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN); + cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE); + cap_raise(override_cred->cap_effective, CAP_FOWNER); + cap_raise(override_cred->cap_effective, CAP_FSETID); + cap_raise(override_cred->cap_effective, CAP_MKNOD); + old_cred = override_creds(override_cred); + + mutex_lock_nested(&upperdir->d_inode->i_mutex, I_MUTEX_PARENT); + if (ovl_path_type(dentry) != OVL_PATH_LOWER) { + err = 0; + } else { + err = ovl_copy_up_locked(upperdir, dentry, lowerpath, + stat, link); + if (!err) { + /* Restore timestamps on parent (best effort) */ + ovl_set_timestamps(upperdir, &pstat); + } + } + + mutex_unlock(&upperdir->d_inode->i_mutex); + + revert_creds(old_cred); + put_cred(override_cred); + +out_free_link: + if (link) + free_page((unsigned long) link); + + return err; +} + +int ovl_copy_up(struct dentry *dentry) +{ + int err; + + err = 0; + while (!err) { + struct dentry *next; + struct dentry *parent; + struct path lowerpath; + struct kstat stat; + enum ovl_path_type type = ovl_path_type(dentry); + + if (type != OVL_PATH_LOWER) + break; + + next = dget(dentry); + /* find the topmost dentry not yet copied up */ + for (;;) { + parent = dget_parent(next); + + type = ovl_path_type(parent); + if (type != OVL_PATH_LOWER) + break; + + dput(next); + next = parent; + } + + ovl_path_lower(next, &lowerpath); + err = vfs_getattr(lowerpath.mnt, lowerpath.dentry, &stat); + if (!err) + err = ovl_copy_up_one(parent, next, &lowerpath, &stat); + + dput(parent); + dput(next); + } + + return err; +} + +/* Optimize by not copying up the file first and truncating later */ +int ovl_copy_up_truncate(struct dentry *dentry, loff_t size) +{ + int err; + struct kstat stat; + struct path lowerpath; + struct dentry *parent = dget_parent(dentry); + + err = ovl_copy_up(parent); + if (err) + goto out_dput_parent; + + ovl_path_lower(dentry, &lowerpath); + err = vfs_getattr(lowerpath.mnt, lowerpath.dentry, &stat); + if (err) + goto out_dput_parent; + + if (size < stat.size) + stat.size = size; + + err = ovl_copy_up_one(parent, dentry, &lowerpath, &stat); + +out_dput_parent: + dput(parent); + return err; +} diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c new file mode 100644 index 000000000000..c914c9770ca8 --- /dev/null +++ b/fs/overlayfs/dir.c @@ -0,0 +1,602 @@ +/* + * + * Copyright (C) 2011 Novell Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include <linux/fs.h> +#include <linux/namei.h> +#include <linux/xattr.h> +#include <linux/security.h> +#include <linux/cred.h> +#include "overlayfs.h" + +static const char *ovl_whiteout_symlink = "(overlay-whiteout)"; + +static int ovl_whiteout(struct dentry *upperdir, struct dentry *dentry) +{ + int err; + struct dentry *newdentry; + const struct cred *old_cred; + struct cred *override_cred; + + /* FIXME: recheck lower dentry to see if whiteout is really needed */ + + err = -ENOMEM; + override_cred = prepare_creds(); + if (!override_cred) + goto out; + + /* + * CAP_SYS_ADMIN for setxattr + * CAP_DAC_OVERRIDE for symlink creation + * CAP_FOWNER for unlink in sticky directory + */ + cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN); + cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE); + cap_raise(override_cred->cap_effective, CAP_FOWNER); + override_cred->fsuid = 0; + override_cred->fsgid = 0; + old_cred = override_creds(override_cred); + + newdentry = lookup_one_len(dentry->d_name.name, upperdir, + dentry->d_name.len); + err = PTR_ERR(newdentry); + if (IS_ERR(newdentry)) + goto out_put_cred; + + /* Just been removed within the same locked region */ + WARN_ON(newdentry->d_inode); + + err = vfs_symlink(upperdir->d_inode, newdentry, ovl_whiteout_symlink); + if (err) + goto out_dput; + + ovl_dentry_version_inc(dentry->d_parent); + + err = vfs_setxattr(newdentry, ovl_whiteout_xattr, "y", 1, 0); + if (err) + vfs_unlink(upperdir->d_inode, newdentry); + +out_dput: + dput(newdentry); +out_put_cred: + revert_creds(old_cred); + put_cred(override_cred); +out: + if (err) { + /* + * There's no way to recover from failure to whiteout. + * What should we do? Log a big fat error and... ? + */ + printk(KERN_ERR "overlayfs: ERROR - failed to whiteout '%s'\n", + dentry->d_name.name); + } + + return err; +} + +static struct dentry *ovl_lookup_create(struct dentry *upperdir, + struct dentry *template) +{ + int err; + struct dentry *newdentry; + struct qstr *name = &template->d_name; + + newdentry = lookup_one_len(name->name, upperdir, name->len); + if (IS_ERR(newdentry)) + return newdentry; + + if (newdentry->d_inode) { + const struct cred *old_cred; + struct cred *override_cred; + + /* No need to check whiteout if lower parent is non-existent */ + err = -EEXIST; + if (!ovl_dentry_lower(template->d_parent)) + goto out_dput; + + if (!S_ISLNK(newdentry->d_inode->i_mode)) + goto out_dput; + + err = -ENOMEM; + override_cred = prepare_creds(); + if (!override_cred) + goto out_dput; + + /* + * CAP_SYS_ADMIN for getxattr + * CAP_FOWNER for unlink in sticky directory + */ + cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN); + cap_raise(override_cred->cap_effective, CAP_FOWNER); + old_cred = override_creds(override_cred); + + err = -EEXIST; + if (ovl_is_whiteout(newdentry)) + err = vfs_unlink(upperdir->d_inode, newdentry); + + revert_creds(old_cred); + put_cred(override_cred); + if (err) + goto out_dput; + + dput(newdentry); + newdentry = lookup_one_len(name->name, upperdir, name->len); + if (IS_ERR(newdentry)) { + ovl_whiteout(upperdir, template); + return newdentry; + } + + /* + * Whiteout just been successfully removed, parent + * i_mutex is still held, there's no way the lookup + * could return positive. + */ + WARN_ON(newdentry->d_inode); + } + + return newdentry; + +out_dput: + dput(newdentry); + return ERR_PTR(err); +} + +struct dentry *ovl_upper_create(struct dentry *upperdir, struct dentry *dentry, + struct kstat *stat, const char *link) +{ + int err; + struct dentry *newdentry; + struct inode *dir = upperdir->d_inode; + + newdentry = ovl_lookup_create(upperdir, dentry); + if (IS_ERR(newdentry)) + goto out; + + switch (stat->mode & S_IFMT) { + case S_IFREG: + err = vfs_create(dir, newdentry, stat->mode, NULL); + break; + + case S_IFDIR: + err = vfs_mkdir(dir, newdentry, stat->mode); + break; + + case S_IFCHR: + case S_IFBLK: + case S_IFIFO: + case S_IFSOCK: + err = vfs_mknod(dir, newdentry, stat->mode, stat->rdev); + break; + + case S_IFLNK: + err = vfs_symlink(dir, newdentry, link); + break; + + default: + err = -EPERM; + } + if (err) { + if (ovl_dentry_is_opaque(dentry)) + ovl_whiteout(upperdir, dentry); + dput(newdentry); + newdentry = ERR_PTR(err); + } else if (WARN_ON(!newdentry->d_inode)) { + /* + * Not quite sure if non-instantiated dentry is legal or not. + * VFS doesn't seem to care so check and warn here. + */ + dput(newdentry); + newdentry = ERR_PTR(-ENOENT); + } + +out: + return newdentry; + +} + +static int ovl_set_opaque(struct dentry *upperdentry) +{ + int err; + const struct cred *old_cred; + struct cred *override_cred; + + override_cred = prepare_creds(); + if (!override_cred) + return -ENOMEM; + + /* CAP_SYS_ADMIN for setxattr of "trusted" namespace */ + cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN); + old_cred = override_creds(override_cred); + err = vfs_setxattr(upperdentry, ovl_opaque_xattr, "y", 1, 0); + revert_creds(old_cred); + put_cred(override_cred); + + return err; +} + +static int ovl_remove_opaque(struct dentry *upperdentry) +{ + int err; + const struct cred *old_cred; + struct cred *override_cred; + + override_cred = prepare_creds(); + if (!override_cred) + return -ENOMEM; + + /* CAP_SYS_ADMIN for removexattr of "trusted" namespace */ + cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN); + old_cred = override_creds(override_cred); + err = vfs_removexattr(upperdentry, ovl_opaque_xattr); + revert_creds(old_cred); + put_cred(override_cred); + + return err; +} + +static int ovl_dir_getattr(struct vfsmount *mnt, struct dentry *dentry, + struct kstat *stat) +{ + int err; + enum ovl_path_type type; + struct path realpath; + + type = ovl_path_real(dentry, &realpath); + err = vfs_getattr(realpath.mnt, realpath.dentry, stat); + if (err) + return err; + + stat->dev = dentry->d_sb->s_dev; + stat->ino = dentry->d_inode->i_ino; + + /* + * It's probably not worth it to count subdirs to get the + * correct link count. nlink=1 seems to pacify 'find' and + * other utilities. + */ + if (type == OVL_PATH_MERGE) + stat->nlink = 1; + + return 0; +} + +static int ovl_create_object(struct dentry *dentry, int mode, dev_t rdev, + const char *link) +{ + int err; + struct dentry *newdentry; + struct dentry *upperdir; + struct inode *inode; + struct kstat stat = { + .mode = mode, + .rdev = rdev, + }; + + err = -ENOMEM; + inode = ovl_new_inode(dentry->d_sb, mode, dentry->d_fsdata); + if (!inode) + goto out; + + err = ovl_copy_up(dentry->d_parent); + if (err) + goto out_iput; + + upperdir = ovl_dentry_upper(dentry->d_parent); + mutex_lock_nested(&upperdir->d_inode->i_mutex, I_MUTEX_PARENT); + + newdentry = ovl_upper_create(upperdir, dentry, &stat, link); + err = PTR_ERR(newdentry); + if (IS_ERR(newdentry)) + goto out_unlock; + + ovl_dentry_version_inc(dentry->d_parent); + if (ovl_dentry_is_opaque(dentry) && S_ISDIR(mode)) { + err = ovl_set_opaque(newdentry); + if (err) { + vfs_rmdir(upperdir->d_inode, newdentry); + ovl_whiteout(upperdir, dentry); + goto out_dput; + } + } + ovl_dentry_update(dentry, newdentry); + d_instantiate(dentry, inode); + inode = NULL; + newdentry = NULL; + err = 0; + +out_dput: + dput(newdentry); +out_unlock: + mutex_unlock(&upperdir->d_inode->i_mutex); +out_iput: + iput(inode); +out: + return err; +} + +static int ovl_create(struct inode *dir, struct dentry *dentry, umode_t mode, + struct nameidata *nd) +{ + return ovl_create_object(dentry, (mode & 07777) | S_IFREG, 0, NULL); +} + +static int ovl_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + return ovl_create_object(dentry, (mode & 07777) | S_IFDIR, 0, NULL); +} + +static int ovl_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, + dev_t rdev) +{ + return ovl_create_object(dentry, mode, rdev, NULL); +} + +static int ovl_symlink(struct inode *dir, struct dentry *dentry, + const char *link) +{ + return ovl_create_object(dentry, S_IFLNK, 0, link); +} + +static int ovl_do_remove(struct dentry *dentry, bool is_dir) +{ + int err; + enum ovl_path_type type; + struct path realpath; + struct dentry *upperdir; + + err = ovl_copy_up(dentry->d_parent); + if (err) + return err; + + upperdir = ovl_dentry_upper(dentry->d_parent); + mutex_lock_nested(&upperdir->d_inode->i_mutex, I_MUTEX_PARENT); + type = ovl_path_real(dentry, &realpath); + if (type != OVL_PATH_LOWER) { + err = -ESTALE; + if (realpath.dentry->d_parent != upperdir) + goto out_d_drop; + + /* FIXME: create whiteout up front and rename to target */ + + if (is_dir) + err = vfs_rmdir(upperdir->d_inode, realpath.dentry); + else + err = vfs_unlink(upperdir->d_inode, realpath.dentry); + if (err) + goto out_d_drop; + + ovl_dentry_version_inc(dentry->d_parent); + } + + if (type != OVL_PATH_UPPER || ovl_dentry_is_opaque(dentry)) + err = ovl_whiteout(upperdir, dentry); + + /* + * Keeping this dentry hashed would mean having to release + * upperpath/lowerpath, which could only be done if we are the + * sole user of this dentry. Too tricky... Just unhash for + * now. + */ +out_d_drop: + d_drop(dentry); + mutex_unlock(&upperdir->d_inode->i_mutex); + + return err; +} + +static int ovl_unlink(struct inode *dir, struct dentry *dentry) +{ + return ovl_do_remove(dentry, false); +} + + +static int ovl_rmdir(struct inode *dir, struct dentry *dentry) +{ + int err; + enum ovl_path_type type; + + type = ovl_path_type(dentry); + if (type != OVL_PATH_UPPER) { + err = ovl_check_empty_and_clear(dentry, type); + if (err) + return err; + } + + return ovl_do_remove(dentry, true); +} + +static int ovl_link(struct dentry *old, struct inode *newdir, + struct dentry *new) +{ + int err; + struct dentry *olddentry; + struct dentry *newdentry; + struct dentry *upperdir; + struct inode *newinode; + + err = ovl_copy_up(old); + if (err) + goto out; + + err = ovl_copy_up(new->d_parent); + if (err) + goto out; + + upperdir = ovl_dentry_upper(new->d_parent); + mutex_lock_nested(&upperdir->d_inode->i_mutex, I_MUTEX_PARENT); + newdentry = ovl_lookup_create(upperdir, new); + err = PTR_ERR(newdentry); + if (IS_ERR(newdentry)) + goto out_unlock; + + olddentry = ovl_dentry_upper(old); + err = vfs_link(olddentry, upperdir->d_inode, newdentry); + if (!err) { + if (WARN_ON(!newdentry->d_inode)) { + dput(newdentry); + err = -ENOENT; + goto out_unlock; + } + newinode = ovl_new_inode(old->d_sb, newdentry->d_inode->i_mode, + new->d_fsdata); + if (!newinode) + goto link_fail; + + ovl_dentry_version_inc(new->d_parent); + ovl_dentry_update(new, newdentry); + + d_instantiate(new, newinode); + } else { +link_fail: + if (ovl_dentry_is_opaque(new)) + ovl_whiteout(upperdir, new); + dput(newdentry); + } +out_unlock: + mutex_unlock(&upperdir->d_inode->i_mutex); +out: + return err; + +} + +static int ovl_rename(struct inode *olddir, struct dentry *old, + struct inode *newdir, struct dentry *new) +{ + int err; + enum ovl_path_type old_type; + enum ovl_path_type new_type; + struct dentry *old_upperdir; + struct dentry *new_upperdir; + struct dentry *olddentry; + struct dentry *newdentry; + struct dentry *trap; + bool old_opaque; + bool new_opaque; + bool new_create = false; + bool is_dir = S_ISDIR(old->d_inode->i_mode); + + /* Don't copy up directory trees */ + old_type = ovl_path_type(old); + if (old_type != OVL_PATH_UPPER && is_dir) + return -EXDEV; + + if (new->d_inode) { + new_type = ovl_path_type(new); + + if (new_type == OVL_PATH_LOWER && old_type == OVL_PATH_LOWER) { + if (ovl_dentry_lower(old)->d_inode == + ovl_dentry_lower(new)->d_inode) + return 0; + } + if (new_type != OVL_PATH_LOWER && old_type != OVL_PATH_LOWER) { + if (ovl_dentry_upper(old)->d_inode == + ovl_dentry_upper(new)->d_inode) + return 0; + } + + if (new_type != OVL_PATH_UPPER && + S_ISDIR(new->d_inode->i_mode)) { + err = ovl_check_empty_and_clear(new, new_type); + if (err) + return err; + } + } else { + new_type = OVL_PATH_UPPER; + } + + err = ovl_copy_up(old); + if (err) + return err; + + err = ovl_copy_up(new->d_parent); + if (err) + return err; + + old_upperdir = ovl_dentry_upper(old->d_parent); + new_upperdir = ovl_dentry_upper(new->d_parent); + + trap = lock_rename(new_upperdir, old_upperdir); + + olddentry = ovl_dentry_upper(old); + newdentry = ovl_dentry_upper(new); + if (newdentry) { + dget(newdentry); + } else { + new_create = true; + newdentry = ovl_lookup_create(new_upperdir, new); + err = PTR_ERR(newdentry); + if (IS_ERR(newdentry)) + goto out_unlock; + } + + err = -ESTALE; + if (olddentry->d_parent != old_upperdir) + goto out_dput; + if (newdentry->d_parent != new_upperdir) + goto out_dput; + if (olddentry == trap) + goto out_dput; + if (newdentry == trap) + goto out_dput; + + old_opaque = ovl_dentry_is_opaque(old); + new_opaque = ovl_dentry_is_opaque(new) || new_type != OVL_PATH_UPPER; + + if (is_dir && !old_opaque && new_opaque) { + err = ovl_set_opaque(olddentry); + if (err) + goto out_dput; + } + + err = vfs_rename(old_upperdir->d_inode, olddentry, + new_upperdir->d_inode, newdentry); + + if (err) { + if (new_create && ovl_dentry_is_opaque(new)) + ovl_whiteout(new_upperdir, new); + if (is_dir && !old_opaque && new_opaque) + ovl_remove_opaque(olddentry); + goto out_dput; + } + + if (old_type != OVL_PATH_UPPER || old_opaque) + err = ovl_whiteout(old_upperdir, old); + if (is_dir && old_opaque && !new_opaque) + ovl_remove_opaque(olddentry); + + if (old_opaque != new_opaque) + ovl_dentry_set_opaque(old, new_opaque); + + ovl_dentry_version_inc(old->d_parent); + ovl_dentry_version_inc(new->d_parent); + +out_dput: + dput(newdentry); +out_unlock: + unlock_rename(new_upperdir, old_upperdir); + return err; +} + +const struct inode_operations ovl_dir_inode_operations = { + .lookup = ovl_lookup, + .mkdir = ovl_mkdir, + .symlink = ovl_symlink, + .unlink = ovl_unlink, + .rmdir = ovl_rmdir, + .rename = ovl_rename, + .link = ovl_link, + .setattr = ovl_setattr, + .create = ovl_create, + .mknod = ovl_mknod, + .permission = ovl_permission, + .getattr = ovl_dir_getattr, + .setxattr = ovl_setxattr, + .getxattr = ovl_getxattr, + .listxattr = ovl_listxattr, + .removexattr = ovl_removexattr, +}; diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c new file mode 100644 index 000000000000..1a8e232e2c6e --- /dev/null +++ b/fs/overlayfs/inode.c @@ -0,0 +1,375 @@ +/* + * + * Copyright (C) 2011 Novell Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include <linux/fs.h> +#include <linux/slab.h> +#include <linux/xattr.h> +#include "overlayfs.h" + +int ovl_setattr(struct dentry *dentry, struct iattr *attr) +{ + struct dentry *upperdentry; + int err; + + if ((attr->ia_valid & ATTR_SIZE) && !ovl_dentry_upper(dentry)) + err = ovl_copy_up_truncate(dentry, attr->ia_size); + else + err = ovl_copy_up(dentry); + if (err) + return err; + + upperdentry = ovl_dentry_upper(dentry); + + if (attr->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID)) + attr->ia_valid &= ~ATTR_MODE; + + mutex_lock(&upperdentry->d_inode->i_mutex); + err = notify_change(upperdentry, attr); + mutex_unlock(&upperdentry->d_inode->i_mutex); + + return err; +} + +static int ovl_getattr(struct vfsmount *mnt, struct dentry *dentry, + struct kstat *stat) +{ + struct path realpath; + + ovl_path_real(dentry, &realpath); + return vfs_getattr(realpath.mnt, realpath.dentry, stat); +} + +int ovl_permission(struct inode *inode, int mask) +{ + struct ovl_entry *oe; + struct dentry *alias = NULL; + struct inode *realinode; + struct dentry *realdentry; + bool is_upper; + int err; + + if (S_ISDIR(inode->i_mode)) { + oe = inode->i_private; + } else if (mask & MAY_NOT_BLOCK) { + return -ECHILD; + } else { + /* + * For non-directories find an alias and get the info + * from there. + */ + spin_lock(&inode->i_lock); + if (WARN_ON(list_empty(&inode->i_dentry))) { + spin_unlock(&inode->i_lock); + return -ENOENT; + } + alias = list_entry(inode->i_dentry.next, + struct dentry, d_alias); + dget(alias); + spin_unlock(&inode->i_lock); + oe = alias->d_fsdata; + } + + realdentry = ovl_entry_real(oe, &is_upper); + + /* Careful in RCU walk mode */ + realinode = ACCESS_ONCE(realdentry->d_inode); + if (!realinode) { + WARN_ON(!(mask & MAY_NOT_BLOCK)); + err = -ENOENT; + goto out_dput; + } + + if (mask & MAY_WRITE) { + umode_t mode = realinode->i_mode; + + /* + * Writes will always be redirected to upper layer, so + * ignore lower layer being read-only. + * + * If the overlay itself is read-only then proceed + * with the permission check, don't return EROFS. + * This will only happen if this is the lower layer of + * another overlayfs. + * + * If upper fs becomes read-only after the overlay was + * constructed return EROFS to prevent modification of + * upper layer. + */ + err = -EROFS; + if (is_upper && !IS_RDONLY(inode) && IS_RDONLY(realinode) && + (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) + goto out_dput; + } + + err = inode_only_permission(realinode, mask); +out_dput: + dput(alias); + return err; +} + + +struct ovl_link_data { + struct dentry *realdentry; + void *cookie; +}; + +static void *ovl_follow_link(struct dentry *dentry, struct nameidata *nd) +{ + void *ret; + struct dentry *realdentry; + struct inode *realinode; + + realdentry = ovl_dentry_real(dentry); + realinode = realdentry->d_inode; + + if (WARN_ON(!realinode->i_op->follow_link)) + return ERR_PTR(-EPERM); + + ret = realinode->i_op->follow_link(realdentry, nd); + if (IS_ERR(ret)) + return ret; + + if (realinode->i_op->put_link) { + struct ovl_link_data *data; + + data = kmalloc(sizeof(struct ovl_link_data), GFP_KERNEL); + if (!data) { + realinode->i_op->put_link(realdentry, nd, ret); + return ERR_PTR(-ENOMEM); + } + data->realdentry = realdentry; + data->cookie = ret; + + return data; + } else { + return NULL; + } +} + +static void ovl_put_link(struct dentry *dentry, struct nameidata *nd, void *c) +{ + struct inode *realinode; + struct ovl_link_data *data = c; + + if (!data) + return; + + realinode = data->realdentry->d_inode; + realinode->i_op->put_link(data->realdentry, nd, data->cookie); + kfree(data); +} + +static int ovl_readlink(struct dentry *dentry, char __user *buf, int bufsiz) +{ + struct path realpath; + struct inode *realinode; + + ovl_path_real(dentry, &realpath); + realinode = realpath.dentry->d_inode; + + if (!realinode->i_op->readlink) + return -EINVAL; + + touch_atime(&realpath); + + return realinode->i_op->readlink(realpath.dentry, buf, bufsiz); +} + + +static bool ovl_is_private_xattr(const char *name) +{ + return strncmp(name, "trusted.overlay.", 14) == 0; +} + +int ovl_setxattr(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags) +{ + int err; + struct dentry *upperdentry; + + if (ovl_is_private_xattr(name)) + return -EPERM; + + err = ovl_copy_up(dentry); + if (err) + return err; + + upperdentry = ovl_dentry_upper(dentry); + return vfs_setxattr(upperdentry, name, value, size, flags); +} + +ssize_t ovl_getxattr(struct dentry *dentry, const char *name, + void *value, size_t size) +{ + if (ovl_path_type(dentry->d_parent) == OVL_PATH_MERGE && + ovl_is_private_xattr(name)) + return -ENODATA; + + return vfs_getxattr(ovl_dentry_real(dentry), name, value, size); +} + +ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) +{ + ssize_t res; + int off; + + res = vfs_listxattr(ovl_dentry_real(dentry), list, size); + if (res <= 0 || size == 0) + return res; + + if (ovl_path_type(dentry->d_parent) != OVL_PATH_MERGE) + return res; + + /* filter out private xattrs */ + for (off = 0; off < res;) { + char *s = list + off; + size_t slen = strlen(s) + 1; + + BUG_ON(off + slen > res); + + if (ovl_is_private_xattr(s)) { + res -= slen; + memmove(s, s + slen, res - off); + } else { + off += slen; + } + } + + return res; +} + +int ovl_removexattr(struct dentry *dentry, const char *name) +{ + int err; + struct path realpath; + enum ovl_path_type type; + + if (ovl_path_type(dentry->d_parent) == OVL_PATH_MERGE && + ovl_is_private_xattr(name)) + return -ENODATA; + + type = ovl_path_real(dentry, &realpath); + if (type == OVL_PATH_LOWER) { + err = vfs_getxattr(realpath.dentry, name, NULL, 0); + if (err < 0) + return err; + + err = ovl_copy_up(dentry); + if (err) + return err; + + ovl_path_upper(dentry, &realpath); + } + + return vfs_removexattr(realpath.dentry, name); +} + +static bool ovl_open_need_copy_up(int flags, enum ovl_path_type type, + struct dentry *realdentry) +{ + if (type != OVL_PATH_LOWER) + return false; + + if (special_file(realdentry->d_inode->i_mode)) + return false; + + if (!(OPEN_FMODE(flags) & FMODE_WRITE) && !(flags & O_TRUNC)) + return false; + + return true; +} + +static struct file *ovl_open(struct dentry *dentry, struct file *file, + const struct cred *cred) +{ + int err; + struct path realpath; + enum ovl_path_type type; + + type = ovl_path_real(dentry, &realpath); + if (ovl_open_need_copy_up(file->f_flags, type, realpath.dentry)) { + if (file->f_flags & O_TRUNC) + err = ovl_copy_up_truncate(dentry, 0); + else + err = ovl_copy_up(dentry); + if (err) + return ERR_PTR(err); + + ovl_path_upper(dentry, &realpath); + } + + return vfs_open(&realpath, file, cred); +} + +static const struct inode_operations ovl_file_inode_operations = { + .setattr = ovl_setattr, + .permission = ovl_permission, + .getattr = ovl_getattr, + .setxattr = ovl_setxattr, + .getxattr = ovl_getxattr, + .listxattr = ovl_listxattr, + .removexattr = ovl_removexattr, + .open = ovl_open, +}; + +static const struct inode_operations ovl_symlink_inode_operations = { + .setattr = ovl_setattr, + .follow_link = ovl_follow_link, + .put_link = ovl_put_link, + .readlink = ovl_readlink, + .getattr = ovl_getattr, + .setxattr = ovl_setxattr, + .getxattr = ovl_getxattr, + .listxattr = ovl_listxattr, + .removexattr = ovl_removexattr, +}; + +struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, + struct ovl_entry *oe) +{ + struct inode *inode; + + inode = new_inode(sb); + if (!inode) + return NULL; + + mode &= S_IFMT; + + inode->i_ino = get_next_ino(); + inode->i_mode = mode; + inode->i_flags |= S_NOATIME | S_NOCMTIME; + + switch (mode) { + case S_IFDIR: + inode->i_private = oe; + inode->i_op = &ovl_dir_inode_operations; + inode->i_fop = &ovl_dir_operations; + break; + + case S_IFLNK: + inode->i_op = &ovl_symlink_inode_operations; + break; + + case S_IFREG: + case S_IFSOCK: + case S_IFBLK: + case S_IFCHR: + case S_IFIFO: + inode->i_op = &ovl_file_inode_operations; + break; + + default: + WARN(1, "illegal file type: %i\n", mode); + iput(inode); + inode = NULL; + } + + return inode; + +} diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h new file mode 100644 index 000000000000..1dd05f76604b --- /dev/null +++ b/fs/overlayfs/overlayfs.h @@ -0,0 +1,64 @@ +/* + * + * Copyright (C) 2011 Novell Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +struct ovl_entry; + +enum ovl_path_type { + OVL_PATH_UPPER, + OVL_PATH_MERGE, + OVL_PATH_LOWER, +}; + +extern const char *ovl_opaque_xattr; +extern const char *ovl_whiteout_xattr; +extern const struct dentry_operations ovl_dentry_operations; + +enum ovl_path_type ovl_path_type(struct dentry *dentry); +u64 ovl_dentry_version_get(struct dentry *dentry); +void ovl_dentry_version_inc(struct dentry *dentry); +void ovl_path_upper(struct dentry *dentry, struct path *path); +void ovl_path_lower(struct dentry *dentry, struct path *path); +enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path); +struct dentry *ovl_dentry_upper(struct dentry *dentry); +struct dentry *ovl_dentry_lower(struct dentry *dentry); +struct dentry *ovl_dentry_real(struct dentry *dentry); +struct dentry *ovl_entry_real(struct ovl_entry *oe, bool *is_upper); +bool ovl_dentry_is_opaque(struct dentry *dentry); +void ovl_dentry_set_opaque(struct dentry *dentry, bool opaque); +bool ovl_is_whiteout(struct dentry *dentry); +void ovl_dentry_update(struct dentry *dentry, struct dentry *upperdentry); +struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, + struct nameidata *nd); +struct file *ovl_path_open(struct path *path, int flags); + +struct dentry *ovl_upper_create(struct dentry *upperdir, struct dentry *dentry, + struct kstat *stat, const char *link); + +/* readdir.c */ +extern const struct file_operations ovl_dir_operations; +int ovl_check_empty_and_clear(struct dentry *dentry, enum ovl_path_type type); + +/* inode.c */ +int ovl_setattr(struct dentry *dentry, struct iattr *attr); +int ovl_permission(struct inode *inode, int mask); +int ovl_setxattr(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags); +ssize_t ovl_getxattr(struct dentry *dentry, const char *name, + void *value, size_t size); +ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size); +int ovl_removexattr(struct dentry *dentry, const char *name); + +struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, + struct ovl_entry *oe); +/* dir.c */ +extern const struct inode_operations ovl_dir_inode_operations; + +/* copy_up.c */ +int ovl_copy_up(struct dentry *dentry); +int ovl_copy_up_truncate(struct dentry *dentry, loff_t size); diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c new file mode 100644 index 000000000000..0797efbc7be4 --- /dev/null +++ b/fs/overlayfs/readdir.c @@ -0,0 +1,566 @@ +/* + * + * Copyright (C) 2011 Novell Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include <linux/fs.h> +#include <linux/slab.h> +#include <linux/namei.h> +#include <linux/file.h> +#include <linux/xattr.h> +#include <linux/rbtree.h> +#include <linux/security.h> +#include <linux/cred.h> +#include "overlayfs.h" + +struct ovl_cache_entry { + const char *name; + unsigned int len; + unsigned int type; + u64 ino; + bool is_whiteout; + struct list_head l_node; + struct rb_node node; +}; + +struct ovl_readdir_data { + struct rb_root *root; + struct list_head *list; + struct list_head *middle; + struct dentry *dir; + int count; + int err; +}; + +struct ovl_dir_file { + bool is_real; + bool is_cached; + struct list_head cursor; + u64 cache_version; + struct list_head cache; + struct file *realfile; +}; + +static struct ovl_cache_entry *ovl_cache_entry_from_node(struct rb_node *n) +{ + return container_of(n, struct ovl_cache_entry, node); +} + +static struct ovl_cache_entry *ovl_cache_entry_find(struct rb_root *root, + const char *name, int len) +{ + struct rb_node *node = root->rb_node; + int cmp; + + while (node) { + struct ovl_cache_entry *p = ovl_cache_entry_from_node(node); + + cmp = strncmp(name, p->name, len); + if (cmp > 0) + node = p->node.rb_right; + else if (cmp < 0 || len < p->len) + node = p->node.rb_left; + else + return p; + } + + return NULL; +} + +static struct ovl_cache_entry *ovl_cache_entry_new(const char *name, int len, + u64 ino, unsigned int d_type) +{ + struct ovl_cache_entry *p; + + p = kmalloc(sizeof(*p) + len + 1, GFP_KERNEL); + if (p) { + char *name_copy = (char *) (p + 1); + memcpy(name_copy, name, len); + name_copy[len] = '\0'; + p->name = name_copy; + p->len = len; + p->type = d_type; + p->ino = ino; + p->is_whiteout = false; + } + + return p; +} + +static int ovl_cache_entry_add_rb(struct ovl_readdir_data *rdd, + const char *name, int len, u64 ino, + unsigned int d_type) +{ + struct rb_node **newp = &rdd->root->rb_node; + struct rb_node *parent = NULL; + struct ovl_cache_entry *p; + + while (*newp) { + int cmp; + struct ovl_cache_entry *tmp; + + parent = *newp; + tmp = ovl_cache_entry_from_node(*newp); + cmp = strncmp(name, tmp->name, len); + if (cmp > 0) + newp = &tmp->node.rb_right; + else if (cmp < 0 || len < tmp->len) + newp = &tmp->node.rb_left; + else + return 0; + } + + p = ovl_cache_entry_new(name, len, ino, d_type); + if (p == NULL) + return -ENOMEM; + + list_add_tail(&p->l_node, rdd->list); + rb_link_node(&p->node, parent, newp); + rb_insert_color(&p->node, rdd->root); + + return 0; +} + +static int ovl_fill_lower(void *buf, const char *name, int namelen, + loff_t offset, u64 ino, unsigned int d_type) +{ + struct ovl_readdir_data *rdd = buf; + struct ovl_cache_entry *p; + + rdd->count++; + p = ovl_cache_entry_find(rdd->root, name, namelen); + if (p) { + list_move_tail(&p->l_node, rdd->middle); + } else { + p = ovl_cache_entry_new(name, namelen, ino, d_type); + if (p == NULL) + rdd->err = -ENOMEM; + else + list_add_tail(&p->l_node, rdd->middle); + } + + return rdd->err; +} + +static void ovl_cache_free(struct list_head *list) +{ + struct ovl_cache_entry *p; + struct ovl_cache_entry *n; + + list_for_each_entry_safe(p, n, list, l_node) + kfree(p); + + INIT_LIST_HEAD(list); +} + +static int ovl_fill_upper(void *buf, const char *name, int namelen, + loff_t offset, u64 ino, unsigned int d_type) +{ + struct ovl_readdir_data *rdd = buf; + + rdd->count++; + return ovl_cache_entry_add_rb(rdd, name, namelen, ino, d_type); +} + +static inline int ovl_dir_read(struct path *realpath, + struct ovl_readdir_data *rdd, filldir_t filler) +{ + struct file *realfile; + int err; + + realfile = ovl_path_open(realpath, O_RDONLY | O_DIRECTORY); + if (IS_ERR(realfile)) + return PTR_ERR(realfile); + + do { + rdd->count = 0; + rdd->err = 0; + err = vfs_readdir(realfile, filler, rdd); + if (err >= 0) + err = rdd->err; + } while (!err && rdd->count); + fput(realfile); + + return 0; +} + +static void ovl_dir_reset(struct file *file) +{ + struct ovl_dir_file *od = file->private_data; + enum ovl_path_type type = ovl_path_type(file->f_path.dentry); + + if (ovl_dentry_version_get(file->f_path.dentry) != od->cache_version) { + list_del_init(&od->cursor); + ovl_cache_free(&od->cache); + od->is_cached = false; + } + WARN_ON(!od->is_real && type != OVL_PATH_MERGE); + if (od->is_real && type == OVL_PATH_MERGE) { + fput(od->realfile); + od->realfile = NULL; + od->is_real = false; + } +} + +static int ovl_dir_mark_whiteouts(struct ovl_readdir_data *rdd) +{ + struct ovl_cache_entry *p; + struct dentry *dentry; + const struct cred *old_cred; + struct cred *override_cred; + + override_cred = prepare_creds(); + if (!override_cred) { + ovl_cache_free(rdd->list); + return -ENOMEM; + } + + /* + * CAP_SYS_ADMIN for getxattr + * CAP_DAC_OVERRIDE for lookup + */ + cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN); + cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE); + old_cred = override_creds(override_cred); + + mutex_lock(&rdd->dir->d_inode->i_mutex); + list_for_each_entry(p, rdd->list, l_node) { + if (p->type != DT_LNK) + continue; + + dentry = lookup_one_len(p->name, rdd->dir, p->len); + if (IS_ERR(dentry)) + continue; + + p->is_whiteout = ovl_is_whiteout(dentry); + dput(dentry); + } + mutex_unlock(&rdd->dir->d_inode->i_mutex); + + revert_creds(old_cred); + put_cred(override_cred); + + return 0; +} + +static inline int ovl_dir_read_merged(struct path *upperpath, + struct path *lowerpath, + struct ovl_readdir_data *rdd) +{ + int err; + struct rb_root root = RB_ROOT; + struct list_head middle; + + rdd->root = &root; + if (upperpath->dentry) { + rdd->dir = upperpath->dentry; + err = ovl_dir_read(upperpath, rdd, ovl_fill_upper); + if (err) + goto out; + + err = ovl_dir_mark_whiteouts(rdd); + if (err) + goto out; + } + /* + * Insert lowerpath entries before upperpath ones, this allows + * offsets to be reasonably constant + */ + list_add(&middle, rdd->list); + rdd->middle = &middle; + err = ovl_dir_read(lowerpath, rdd, ovl_fill_lower); + list_del(&middle); +out: + rdd->root = NULL; + + return err; +} + +static void ovl_seek_cursor(struct ovl_dir_file *od, loff_t pos) +{ + struct list_head *l; + loff_t off; + + l = od->cache.next; + for (off = 0; off < pos; off++) { + if (l == &od->cache) + break; + l = l->next; + } + list_move_tail(&od->cursor, l); +} + +static int ovl_readdir(struct file *file, void *buf, filldir_t filler) +{ + struct ovl_dir_file *od = file->private_data; + int res; + + if (!file->f_pos) + ovl_dir_reset(file); + + if (od->is_real) { + res = vfs_readdir(od->realfile, filler, buf); + file->f_pos = od->realfile->f_pos; + + return res; + } + + if (!od->is_cached) { + struct path lowerpath; + struct path upperpath; + struct ovl_readdir_data rdd = { .list = &od->cache }; + + ovl_path_lower(file->f_path.dentry, &lowerpath); + ovl_path_upper(file->f_path.dentry, &upperpath); + + res = ovl_dir_read_merged(&upperpath, &lowerpath, &rdd); + if (res) { + ovl_cache_free(rdd.list); + return res; + } + + od->cache_version = ovl_dentry_version_get(file->f_path.dentry); + od->is_cached = true; + + ovl_seek_cursor(od, file->f_pos); + } + + while (od->cursor.next != &od->cache) { + int over; + loff_t off; + struct ovl_cache_entry *p; + + p = list_entry(od->cursor.next, struct ovl_cache_entry, l_node); + off = file->f_pos; + if (!p->is_whiteout) { + over = filler(buf, p->name, p->len, off, p->ino, + p->type); + if (over) + break; + } + file->f_pos++; + list_move(&od->cursor, &p->l_node); + } + + return 0; +} + +static loff_t ovl_dir_llseek(struct file *file, loff_t offset, int origin) +{ + loff_t res; + struct ovl_dir_file *od = file->private_data; + + mutex_lock(&file->f_dentry->d_inode->i_mutex); + if (!file->f_pos) + ovl_dir_reset(file); + + if (od->is_real) { + res = vfs_llseek(od->realfile, offset, origin); + file->f_pos = od->realfile->f_pos; + } else { + res = -EINVAL; + + switch (origin) { + case SEEK_CUR: + offset += file->f_pos; + break; + case SEEK_SET: + break; + default: + goto out_unlock; + } + if (offset < 0) + goto out_unlock; + + if (offset != file->f_pos) { + file->f_pos = offset; + if (od->is_cached) + ovl_seek_cursor(od, offset); + } + res = offset; + } +out_unlock: + mutex_unlock(&file->f_dentry->d_inode->i_mutex); + + return res; +} + +static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end, + int datasync) +{ + struct ovl_dir_file *od = file->private_data; + + /* May need to reopen directory if it got copied up */ + if (!od->realfile) { + struct path upperpath; + + ovl_path_upper(file->f_path.dentry, &upperpath); + od->realfile = ovl_path_open(&upperpath, O_RDONLY); + if (IS_ERR(od->realfile)) + return PTR_ERR(od->realfile); + } + + return vfs_fsync_range(od->realfile, start, end, datasync); +} + +static int ovl_dir_release(struct inode *inode, struct file *file) +{ + struct ovl_dir_file *od = file->private_data; + + list_del(&od->cursor); + ovl_cache_free(&od->cache); + if (od->realfile) + fput(od->realfile); + kfree(od); + + return 0; +} + +static int ovl_dir_open(struct inode *inode, struct file *file) +{ + struct path realpath; + struct file *realfile; + struct ovl_dir_file *od; + enum ovl_path_type type; + + od = kzalloc(sizeof(struct ovl_dir_file), GFP_KERNEL); + if (!od) + return -ENOMEM; + + type = ovl_path_real(file->f_path.dentry, &realpath); + realfile = ovl_path_open(&realpath, file->f_flags); + if (IS_ERR(realfile)) { + kfree(od); + return PTR_ERR(realfile); + } + INIT_LIST_HEAD(&od->cache); + INIT_LIST_HEAD(&od->cursor); + od->is_cached = false; + od->realfile = realfile; + od->is_real = (type != OVL_PATH_MERGE); + file->private_data = od; + + return 0; +} + +const struct file_operations ovl_dir_operations = { + .read = generic_read_dir, + .open = ovl_dir_open, + .readdir = ovl_readdir, + .llseek = ovl_dir_llseek, + .fsync = ovl_dir_fsync, + .release = ovl_dir_release, +}; + +static int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list) +{ + int err; + struct path lowerpath; + struct path upperpath; + struct ovl_cache_entry *p; + struct ovl_readdir_data rdd = { .list = list }; + + ovl_path_upper(dentry, &upperpath); + ovl_path_lower(dentry, &lowerpath); + + err = ovl_dir_read_merged(&upperpath, &lowerpath, &rdd); + if (err) + return err; + + err = 0; + + list_for_each_entry(p, list, l_node) { + if (p->is_whiteout) + continue; + + if (p->name[0] == '.') { + if (p->len == 1) + continue; + if (p->len == 2 && p->name[1] == '.') + continue; + } + err = -ENOTEMPTY; + break; + } + + return err; +} + +static int ovl_remove_whiteouts(struct dentry *dir, struct list_head *list) +{ + struct path upperpath; + struct dentry *upperdir; + struct ovl_cache_entry *p; + const struct cred *old_cred; + struct cred *override_cred; + int err; + + ovl_path_upper(dir, &upperpath); + upperdir = upperpath.dentry; + + override_cred = prepare_creds(); + if (!override_cred) + return -ENOMEM; + + /* + * CAP_DAC_OVERRIDE for lookup and unlink + * CAP_SYS_ADMIN for setxattr of "trusted" namespace + * CAP_FOWNER for unlink in sticky directory + */ + cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE); + cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN); + cap_raise(override_cred->cap_effective, CAP_FOWNER); + old_cred = override_creds(override_cred); + + err = vfs_setxattr(upperdir, ovl_opaque_xattr, "y", 1, 0); + if (err) + goto out_revert_creds; + + mutex_lock_nested(&upperdir->d_inode->i_mutex, I_MUTEX_PARENT); + list_for_each_entry(p, list, l_node) { + struct dentry *dentry; + int ret; + + if (!p->is_whiteout) + continue; + + dentry = lookup_one_len(p->name, upperdir, p->len); + if (IS_ERR(dentry)) { + printk(KERN_WARNING + "overlayfs: failed to lookup whiteout %.*s: %li\n", + p->len, p->name, PTR_ERR(dentry)); + continue; + } + ret = vfs_unlink(upperdir->d_inode, dentry); + dput(dentry); + if (ret) + printk(KERN_WARNING + "overlayfs: failed to unlink whiteout %.*s: %i\n", + p->len, p->name, ret); + } + mutex_unlock(&upperdir->d_inode->i_mutex); + +out_revert_creds: + revert_creds(old_cred); + put_cred(override_cred); + + return err; +} + +int ovl_check_empty_and_clear(struct dentry *dentry, enum ovl_path_type type) +{ + int err; + LIST_HEAD(list); + + err = ovl_check_empty_dir(dentry, &list); + if (!err && type == OVL_PATH_MERGE) + err = ovl_remove_whiteouts(dentry, &list); + + ovl_cache_free(&list); + + return err; +} diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c new file mode 100644 index 000000000000..1d2d1e273696 --- /dev/null +++ b/fs/overlayfs/super.c @@ -0,0 +1,664 @@ +/* + * + * Copyright (C) 2011 Novell Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include <linux/fs.h> +#include <linux/namei.h> +#include <linux/xattr.h> +#include <linux/security.h> +#include <linux/mount.h> +#include <linux/slab.h> +#include <linux/parser.h> +#include <linux/module.h> +#include <linux/cred.h> +#include <linux/sched.h> +#include <linux/seq_file.h> +#include "overlayfs.h" + +MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>"); +MODULE_DESCRIPTION("Overlay filesystem"); +MODULE_LICENSE("GPL"); + +struct ovl_config { + char *lowerdir; + char *upperdir; +}; + +/* private information held for overlayfs's superblock */ +struct ovl_fs { + struct vfsmount *upper_mnt; + struct vfsmount *lower_mnt; + /* pathnames of lower and upper dirs, for show_options */ + struct ovl_config config; +}; + +/* private information held for every overlayfs dentry */ +struct ovl_entry { + /* + * Keep "double reference" on upper dentries, so that + * d_delete() doesn't think it's OK to reset d_inode to NULL. + */ + struct dentry *__upperdentry; + struct dentry *lowerdentry; + union { + struct { + u64 version; + bool opaque; + }; + struct rcu_head rcu; + }; +}; + +const char *ovl_whiteout_xattr = "trusted.overlay.whiteout"; +const char *ovl_opaque_xattr = "trusted.overlay.opaque"; + + +enum ovl_path_type ovl_path_type(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + if (oe->__upperdentry) { + if (oe->lowerdentry && S_ISDIR(dentry->d_inode->i_mode)) + return OVL_PATH_MERGE; + else + return OVL_PATH_UPPER; + } else { + return OVL_PATH_LOWER; + } +} + +static struct dentry *ovl_upperdentry_dereference(struct ovl_entry *oe) +{ + struct dentry *upperdentry = ACCESS_ONCE(oe->__upperdentry); + smp_read_barrier_depends(); + return upperdentry; +} + +void ovl_path_upper(struct dentry *dentry, struct path *path) +{ + struct ovl_fs *ofs = dentry->d_sb->s_fs_info; + struct ovl_entry *oe = dentry->d_fsdata; + + path->mnt = ofs->upper_mnt; + path->dentry = ovl_upperdentry_dereference(oe); +} + +void ovl_path_lower(struct dentry *dentry, struct path *path) +{ + struct ovl_fs *ofs = dentry->d_sb->s_fs_info; + struct ovl_entry *oe = dentry->d_fsdata; + + path->mnt = ofs->lower_mnt; + path->dentry = oe->lowerdentry; +} + +enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path) +{ + + enum ovl_path_type type = ovl_path_type(dentry); + + if (type == OVL_PATH_LOWER) + ovl_path_lower(dentry, path); + else + ovl_path_upper(dentry, path); + + return type; +} + +struct dentry *ovl_dentry_upper(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + return ovl_upperdentry_dereference(oe); +} + +struct dentry *ovl_dentry_lower(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + return oe->lowerdentry; +} + +struct dentry *ovl_dentry_real(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + struct dentry *realdentry; + + realdentry = ovl_upperdentry_dereference(oe); + if (!realdentry) + realdentry = oe->lowerdentry; + + return realdentry; +} + +struct dentry *ovl_entry_real(struct ovl_entry *oe, bool *is_upper) +{ + struct dentry *realdentry; + + realdentry = ovl_upperdentry_dereference(oe); + if (realdentry) { + *is_upper = true; + } else { + realdentry = oe->lowerdentry; + *is_upper = false; + } + return realdentry; +} + +bool ovl_dentry_is_opaque(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + return oe->opaque; +} + +void ovl_dentry_set_opaque(struct dentry *dentry, bool opaque) +{ + struct ovl_entry *oe = dentry->d_fsdata; + oe->opaque = opaque; +} + +void ovl_dentry_update(struct dentry *dentry, struct dentry *upperdentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + WARN_ON(!mutex_is_locked(&upperdentry->d_parent->d_inode->i_mutex)); + WARN_ON(oe->__upperdentry); + BUG_ON(!upperdentry->d_inode); + smp_wmb(); + oe->__upperdentry = dget(upperdentry); +} + +void ovl_dentry_version_inc(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + WARN_ON(!mutex_is_locked(&dentry->d_inode->i_mutex)); + oe->version++; +} + +u64 ovl_dentry_version_get(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + WARN_ON(!mutex_is_locked(&dentry->d_inode->i_mutex)); + return oe->version; +} + +bool ovl_is_whiteout(struct dentry *dentry) +{ + int res; + char val; + + if (!dentry) + return false; + if (!dentry->d_inode) + return false; + if (!S_ISLNK(dentry->d_inode->i_mode)) + return false; + + res = vfs_getxattr(dentry, ovl_whiteout_xattr, &val, 1); + if (res == 1 && val == 'y') + return true; + + return false; +} + +static bool ovl_is_opaquedir(struct dentry *dentry) +{ + int res; + char val; + + if (!S_ISDIR(dentry->d_inode->i_mode)) + return false; + + res = vfs_getxattr(dentry, ovl_opaque_xattr, &val, 1); + if (res == 1 && val == 'y') + return true; + + return false; +} + +static void ovl_entry_free(struct rcu_head *head) +{ + struct ovl_entry *oe = container_of(head, struct ovl_entry, rcu); + kfree(oe); +} + +static void ovl_dentry_release(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + if (oe) { + dput(oe->__upperdentry); + dput(oe->__upperdentry); + dput(oe->lowerdentry); + call_rcu(&oe->rcu, ovl_entry_free); + } +} + +const struct dentry_operations ovl_dentry_operations = { + .d_release = ovl_dentry_release, +}; + +static struct ovl_entry *ovl_alloc_entry(void) +{ + return kzalloc(sizeof(struct ovl_entry), GFP_KERNEL); +} + +static inline struct dentry *ovl_lookup_real(struct dentry *dir, + struct qstr *name) +{ + struct dentry *dentry; + + mutex_lock(&dir->d_inode->i_mutex); + dentry = lookup_one_len(name->name, dir, name->len); + mutex_unlock(&dir->d_inode->i_mutex); + + if (IS_ERR(dentry)) { + if (PTR_ERR(dentry) == -ENOENT) + dentry = NULL; + } else if (!dentry->d_inode) { + dput(dentry); + dentry = NULL; + } + return dentry; +} + +static int ovl_do_lookup(struct dentry *dentry) +{ + struct ovl_entry *oe; + struct dentry *upperdir; + struct dentry *lowerdir; + struct dentry *upperdentry = NULL; + struct dentry *lowerdentry = NULL; + struct inode *inode = NULL; + int err; + + err = -ENOMEM; + oe = ovl_alloc_entry(); + if (!oe) + goto out; + + upperdir = ovl_dentry_upper(dentry->d_parent); + lowerdir = ovl_dentry_lower(dentry->d_parent); + + if (upperdir) { + upperdentry = ovl_lookup_real(upperdir, &dentry->d_name); + err = PTR_ERR(upperdentry); + if (IS_ERR(upperdentry)) + goto out_put_dir; + + if (lowerdir && upperdentry && + (S_ISLNK(upperdentry->d_inode->i_mode) || + S_ISDIR(upperdentry->d_inode->i_mode))) { + const struct cred *old_cred; + struct cred *override_cred; + + err = -ENOMEM; + override_cred = prepare_creds(); + if (!override_cred) + goto out_dput_upper; + + /* CAP_SYS_ADMIN needed for getxattr */ + cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN); + old_cred = override_creds(override_cred); + + if (ovl_is_opaquedir(upperdentry)) { + oe->opaque = true; + } else if (ovl_is_whiteout(upperdentry)) { + dput(upperdentry); + upperdentry = NULL; + oe->opaque = true; + } + revert_creds(old_cred); + put_cred(override_cred); + } + } + if (lowerdir && !oe->opaque) { + lowerdentry = ovl_lookup_real(lowerdir, &dentry->d_name); + err = PTR_ERR(lowerdentry); + if (IS_ERR(lowerdentry)) + goto out_dput_upper; + } + + if (lowerdentry && upperdentry && + (!S_ISDIR(upperdentry->d_inode->i_mode) || + !S_ISDIR(lowerdentry->d_inode->i_mode))) { + dput(lowerdentry); + lowerdentry = NULL; + oe->opaque = true; + } + + if (lowerdentry || upperdentry) { + struct dentry *realdentry; + + realdentry = upperdentry ? upperdentry : lowerdentry; + err = -ENOMEM; + inode = ovl_new_inode(dentry->d_sb, realdentry->d_inode->i_mode, + oe); + if (!inode) + goto out_dput; + } + + if (upperdentry) + oe->__upperdentry = dget(upperdentry); + + if (lowerdentry) + oe->lowerdentry = lowerdentry; + + dentry->d_fsdata = oe; + dentry->d_op = &ovl_dentry_operations; + d_add(dentry, inode); + + return 0; + +out_dput: + dput(lowerdentry); +out_dput_upper: + dput(upperdentry); +out_put_dir: + kfree(oe); +out: + return err; +} + +struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, + struct nameidata *nd) +{ + int err = ovl_do_lookup(dentry); + + if (err) + return ERR_PTR(err); + + return NULL; +} + +struct file *ovl_path_open(struct path *path, int flags) +{ + path_get(path); + return dentry_open(path->dentry, path->mnt, flags, current_cred()); +} + +static void ovl_put_super(struct super_block *sb) +{ + struct ovl_fs *ufs = sb->s_fs_info; + + if (!(sb->s_flags & MS_RDONLY)) + mnt_drop_write(ufs->upper_mnt); + + mntput(ufs->upper_mnt); + mntput(ufs->lower_mnt); + + kfree(ufs->config.lowerdir); + kfree(ufs->config.upperdir); + kfree(ufs); +} + +static int ovl_remount_fs(struct super_block *sb, int *flagsp, char *data) +{ + int flags = *flagsp; + struct ovl_fs *ufs = sb->s_fs_info; + + /* When remounting rw or ro, we need to adjust the write access to the + * upper fs. + */ + if (((flags ^ sb->s_flags) & MS_RDONLY) == 0) + /* No change to readonly status */ + return 0; + + if (flags & MS_RDONLY) { + mnt_drop_write(ufs->upper_mnt); + return 0; + } else + return mnt_want_write(ufs->upper_mnt); +} + +/** + * ovl_statfs + * @sb: The overlayfs super block + * @buf: The struct kstatfs to fill in with stats + * + * Get the filesystem statistics. As writes always target the upper layer + * filesystem pass the statfs to the same filesystem. + */ +static int ovl_statfs(struct dentry *dentry, struct kstatfs *buf) +{ + struct dentry *root_dentry = dentry->d_sb->s_root; + struct path path; + ovl_path_upper(root_dentry, &path); + + if (!path.dentry->d_sb->s_op->statfs) + return -ENOSYS; + return path.dentry->d_sb->s_op->statfs(path.dentry, buf); +} + +/** + * ovl_show_options + * + * Prints the mount options for a given superblock. + * Returns zero; does not fail. + */ +static int ovl_show_options(struct seq_file *m, struct dentry *dentry) +{ + struct super_block *sb = dentry->d_sb; + struct ovl_fs *ufs = sb->s_fs_info; + + seq_printf(m, ",lowerdir=%s", ufs->config.lowerdir); + seq_printf(m, ",upperdir=%s", ufs->config.upperdir); + return 0; +} + +static const struct super_operations ovl_super_operations = { + .put_super = ovl_put_super, + .remount_fs = ovl_remount_fs, + .statfs = ovl_statfs, + .show_options = ovl_show_options, +}; + +enum { + Opt_lowerdir, + Opt_upperdir, + Opt_err, +}; + +static const match_table_t ovl_tokens = { + {Opt_lowerdir, "lowerdir=%s"}, + {Opt_upperdir, "upperdir=%s"}, + {Opt_err, NULL} +}; + +static int ovl_parse_opt(char *opt, struct ovl_config *config) +{ + char *p; + + config->upperdir = NULL; + config->lowerdir = NULL; + + while ((p = strsep(&opt, ",")) != NULL) { + int token; + substring_t args[MAX_OPT_ARGS]; + + if (!*p) + continue; + + token = match_token(p, ovl_tokens, args); + switch (token) { + case Opt_upperdir: + kfree(config->upperdir); + config->upperdir = match_strdup(&args[0]); + if (!config->upperdir) + return -ENOMEM; + break; + + case Opt_lowerdir: + kfree(config->lowerdir); + config->lowerdir = match_strdup(&args[0]); + if (!config->lowerdir) + return -ENOMEM; + break; + + default: + return -EINVAL; + } + } + return 0; +} + +static int ovl_fill_super(struct super_block *sb, void *data, int silent) +{ + struct path lowerpath; + struct path upperpath; + struct inode *root_inode; + struct dentry *root_dentry; + struct ovl_entry *oe; + struct ovl_fs *ufs; + int err; + + err = -ENOMEM; + ufs = kmalloc(sizeof(struct ovl_fs), GFP_KERNEL); + if (!ufs) + goto out; + + err = ovl_parse_opt((char *) data, &ufs->config); + if (err) + goto out_free_ufs; + + err = -EINVAL; + if (!ufs->config.upperdir || !ufs->config.lowerdir) { + printk(KERN_ERR "overlayfs: missing upperdir or lowerdir\n"); + goto out_free_config; + } + + oe = ovl_alloc_entry(); + if (oe == NULL) + goto out_free_config; + + err = kern_path(ufs->config.upperdir, LOOKUP_FOLLOW, &upperpath); + if (err) + goto out_free_oe; + + err = kern_path(ufs->config.lowerdir, LOOKUP_FOLLOW, &lowerpath); + if (err) + goto out_put_upperpath; + + err = -ENOTDIR; + if (!S_ISDIR(upperpath.dentry->d_inode->i_mode) || + !S_ISDIR(lowerpath.dentry->d_inode->i_mode)) + goto out_put_lowerpath; + + sb->s_stack_depth = max(upperpath.mnt->mnt_sb->s_stack_depth, + lowerpath.mnt->mnt_sb->s_stack_depth) + 1; + + err = -EINVAL; + if (sb->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) { + printk(KERN_ERR "overlayfs: maximum fs stacking depth exceeded\n"); + goto out_put_lowerpath; + } + + + ufs->upper_mnt = clone_private_mount(&upperpath); + err = PTR_ERR(ufs->upper_mnt); + if (IS_ERR(ufs->upper_mnt)) { + printk(KERN_ERR "overlayfs: failed to clone upperpath\n"); + goto out_put_lowerpath; + } + + ufs->lower_mnt = clone_private_mount(&lowerpath); + err = PTR_ERR(ufs->lower_mnt); + if (IS_ERR(ufs->lower_mnt)) { + printk(KERN_ERR "overlayfs: failed to clone lowerpath\n"); + goto out_put_upper_mnt; + } + + /* + * Make lower_mnt R/O. That way fchmod/fchown on lower file + * will fail instead of modifying lower fs. + */ + ufs->lower_mnt->mnt_flags |= MNT_READONLY; + + /* If the upper fs is r/o, we mark overlayfs r/o too */ + if (ufs->upper_mnt->mnt_sb->s_flags & MS_RDONLY) + sb->s_flags |= MS_RDONLY; + + if (!(sb->s_flags & MS_RDONLY)) { + err = mnt_want_write(ufs->upper_mnt); + if (err) + goto out_put_lower_mnt; + } + + err = -ENOMEM; + root_inode = ovl_new_inode(sb, S_IFDIR, oe); + if (!root_inode) + goto out_drop_write; + + root_dentry = d_make_root(root_inode); + if (!root_dentry) + goto out_drop_write; + + mntput(upperpath.mnt); + mntput(lowerpath.mnt); + + oe->__upperdentry = dget(upperpath.dentry); + oe->lowerdentry = lowerpath.dentry; + + root_dentry->d_fsdata = oe; + root_dentry->d_op = &ovl_dentry_operations; + + sb->s_op = &ovl_super_operations; + sb->s_root = root_dentry; + sb->s_fs_info = ufs; + + return 0; + +out_drop_write: + if (!(sb->s_flags & MS_RDONLY)) + mnt_drop_write(ufs->upper_mnt); +out_put_lower_mnt: + mntput(ufs->lower_mnt); +out_put_upper_mnt: + mntput(ufs->upper_mnt); +out_put_lowerpath: + path_put(&lowerpath); +out_put_upperpath: + path_put(&upperpath); +out_free_oe: + kfree(oe); +out_free_config: + kfree(ufs->config.lowerdir); + kfree(ufs->config.upperdir); +out_free_ufs: + kfree(ufs); +out: + return err; +} + +static struct dentry *ovl_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *raw_data) +{ + return mount_nodev(fs_type, flags, raw_data, ovl_fill_super); +} + +static struct file_system_type ovl_fs_type = { + .owner = THIS_MODULE, + .name = "overlayfs", + .mount = ovl_mount, + .kill_sb = kill_anon_super, +}; + +static int __init ovl_init(void) +{ + return register_filesystem(&ovl_fs_type); +} + +static void __exit ovl_exit(void) +{ + unregister_filesystem(&ovl_fs_type); +} + +module_init(ovl_init); +module_exit(ovl_exit); diff --git a/fs/proc/Makefile b/fs/proc/Makefile index c1c729335924..cc68b63d572b 100644 --- a/fs/proc/Makefile +++ b/fs/proc/Makefile @@ -28,3 +28,4 @@ proc-$(CONFIG_PROC_VMCORE) += vmcore.o proc-$(CONFIG_PROC_DEVICETREE) += proc_devtree.o proc-$(CONFIG_PRINTK) += kmsg.o proc-$(CONFIG_PROC_PAGE_MONITOR) += page.o +proc-y += version_signature.o diff --git a/fs/proc/version_signature.c b/fs/proc/version_signature.c new file mode 100644 index 000000000000..859fb6092a6c --- /dev/null +++ b/fs/proc/version_signature.c @@ -0,0 +1,31 @@ +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/utsname.h> + +static int version_signature_proc_show(struct seq_file *m, void *v) +{ + seq_printf(m, "%s\n", CONFIG_VERSION_SIGNATURE); + return 0; +} + +static int version_signature_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, version_signature_proc_show, NULL); +} + +static const struct file_operations version_signature_proc_fops = { + .open = version_signature_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init proc_version_signature_init(void) +{ + proc_create("version_signature", 0, NULL, &version_signature_proc_fops); + return 0; +} +module_init(proc_version_signature_init); diff --git a/fs/splice.c b/fs/splice.c index c9f1318a3b82..ce525f34e1d6 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1086,8 +1086,8 @@ EXPORT_SYMBOL(generic_splice_sendpage); /* * Attempt to initiate a splice from pipe to file. */ -static long do_splice_from(struct pipe_inode_info *pipe, struct file *out, - loff_t *ppos, size_t len, unsigned int flags) +long do_splice_from(struct pipe_inode_info *pipe, struct file *out, + loff_t *ppos, size_t len, unsigned int flags) { ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); @@ -1110,13 +1110,14 @@ static long do_splice_from(struct pipe_inode_info *pipe, struct file *out, return splice_write(pipe, out, ppos, len, flags); } +EXPORT_SYMBOL(do_splice_from); /* * Attempt to initiate a splice from a file to a pipe. */ -static long do_splice_to(struct file *in, loff_t *ppos, - struct pipe_inode_info *pipe, size_t len, - unsigned int flags) +long do_splice_to(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) { ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); @@ -1136,6 +1137,7 @@ static long do_splice_to(struct file *in, loff_t *ppos, return splice_read(in, ppos, pipe, len, flags); } +EXPORT_SYMBOL(do_splice_to); /** * splice_direct_to_actor - splices data directly between two non-pipes @@ -1301,6 +1303,7 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out, return ret; } +EXPORT_SYMBOL(do_splice_direct); static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe, struct pipe_inode_info *opipe, diff --git a/include/Kbuild b/include/Kbuild index 8d226bfa2696..fe36accd4328 100644 --- a/include/Kbuild +++ b/include/Kbuild @@ -9,4 +9,3 @@ header-y += rdma/ header-y += video/ header-y += drm/ header-y += xen/ -header-y += scsi/ diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 4e2e1cc505ab..b5590e10b3a7 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -626,6 +626,7 @@ *(.initcallearly.init) \ INIT_CALLS_LEVEL(0) \ INIT_CALLS_LEVEL(1) \ + INIT_CALLS_LEVEL(earlyrootfs) \ INIT_CALLS_LEVEL(2) \ INIT_CALLS_LEVEL(3) \ INIT_CALLS_LEVEL(4) \ diff --git a/include/linux/audit.h b/include/linux/audit.h index 22f292a917a3..4a2f0d6acfb4 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -510,8 +510,7 @@ void audit_core_dumps(long signr); static inline void audit_seccomp(unsigned long syscall, long signr, int code) { - if (unlikely(!audit_dummy_context())) - __audit_seccomp(syscall, signr, code); + __audit_seccomp(syscall, signr, code); } static inline void audit_ptrace(struct task_struct *t) diff --git a/include/linux/fs.h b/include/linux/fs.h index 17fd887c798f..e99bb48293d5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -499,6 +499,12 @@ struct iattr { */ #include <linux/quota.h> +/* + * Maximum number of layers of fs stack. Needs to be limited to + * prevent kernel stack overflow + */ +#define FILESYSTEM_MAX_STACK_DEPTH 2 + /** * enum positive_aop_returns - aop return codes with specific semantics * @@ -1542,6 +1548,11 @@ struct super_block { /* Being remounted read-only */ int s_readonly_remount; + + /* + * Indicates how deep in a filesystem stack this SB is + */ + int s_stack_depth; }; /* superblock cache pruning functions */ @@ -1693,6 +1704,8 @@ struct inode_operations { int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); int (*update_time)(struct inode *, struct timespec *, int); + struct file *(*open) (struct dentry *, struct file *, + const struct cred *); } ____cacheline_aligned; struct seq_file; @@ -2057,6 +2070,7 @@ extern long do_sys_open(int dfd, const char __user *filename, int flags, extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(struct dentry *, struct vfsmount *, const char *, int); +extern struct file *vfs_open(struct path *, struct file *, const struct cred *); extern struct file * dentry_open(struct dentry *, struct vfsmount *, int, const struct cred *); extern int filp_close(struct file *, fl_owner_t id); @@ -2249,6 +2263,7 @@ extern sector_t bmap(struct inode *, sector_t); #endif extern int notify_change(struct dentry *, struct iattr *); extern int inode_permission(struct inode *, int); +extern int inode_only_permission(struct inode *, int); extern int generic_permission(struct inode *, int); static inline bool execute_ok(struct inode *inode) diff --git a/include/linux/init.h b/include/linux/init.h index 6b951095a42f..bc7379f6625f 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -196,6 +196,7 @@ extern bool initcall_debug; #define core_initcall(fn) __define_initcall("1",fn,1) #define core_initcall_sync(fn) __define_initcall("1s",fn,1s) +#define earlyrootfs_initcall(fn) __define_initcall("earlyrootfs",fn,rootfs) #define postcore_initcall(fn) __define_initcall("2",fn,2) #define postcore_initcall_sync(fn) __define_initcall("2s",fn,2s) #define arch_initcall(fn) __define_initcall("3",fn,3) diff --git a/include/linux/kd.h b/include/linux/kd.h index c36d8476db55..5cc3c171d5b9 100644 --- a/include/linux/kd.h +++ b/include/linux/kd.h @@ -45,6 +45,7 @@ struct consolefontdesc { #define KD_GRAPHICS 0x01 #define KD_TEXT0 0x02 /* obsolete */ #define KD_TEXT1 0x03 /* obsolete */ +#define KD_TRANSPARENT 0x04 #define KDGETMODE 0x4B3B /* get current mode */ #define KDMAPDISP 0x4B3C /* map display into address space */ diff --git a/include/linux/kmod.h b/include/linux/kmod.h index 5398d5807075..6f571b1be39e 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -71,6 +71,8 @@ call_usermodehelper_fns(char *path, char **argv, char **envp, int wait, int (*init)(struct subprocess_info *info, struct cred *new), void (*cleanup)(struct subprocess_info *), void *data); +void populate_rootfs_wait(void); + static inline int call_usermodehelper(char *path, char **argv, char **envp, int wait) { diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index d6a58065c09c..66cbc87d7636 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -320,8 +320,8 @@ extern int parse_args(const char *name, unsigned num, s16 level_min, s16 level_max, - int (*unknown)(char *param, char *val, - const char *doing)); + int (*handle)(char *param, char *val, + const char *doing, int known)); /* Called by module remove. */ #ifdef CONFIG_SYSFS diff --git a/include/linux/mount.h b/include/linux/mount.h index d7029f4a191a..344a2623eb2a 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -66,6 +66,9 @@ extern void mnt_pin(struct vfsmount *mnt); extern void mnt_unpin(struct vfsmount *mnt); extern int __mnt_is_readonly(struct vfsmount *mnt); +struct path; +extern struct vfsmount *clone_private_mount(struct path *path); + struct file_system_type; extern struct vfsmount *vfs_kern_mount(struct file_system_type *type, int flags, const char *name, diff --git a/include/linux/namei.h b/include/linux/namei.h index ffc02135c483..ef35a3198c94 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -85,6 +85,7 @@ extern int vfs_path_lookup(struct dentry *, struct vfsmount *, extern struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry, int (*open)(struct inode *, struct file *)); +extern struct dentry *lookup_hash(struct nameidata *nd); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); extern int follow_down_one(struct path *); diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index c88d2a9451af..3610ab7659f9 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -108,6 +108,7 @@ enum pageflags { #ifdef CONFIG_TRANSPARENT_HUGEPAGE PG_compound_lock, #endif + PG_readaheadunused, /* user oriented readahead as yet unused*/ __NR_PAGEFLAGS, /* Filesystems */ @@ -231,6 +232,8 @@ PAGEFLAG(MappedToDisk, mappedtodisk) PAGEFLAG(Reclaim, reclaim) TESTCLEARFLAG(Reclaim, reclaim) PAGEFLAG(Readahead, reclaim) /* Reminder to do async read-ahead */ +PAGEFLAG(ReadaheadUnused, readaheadunused) + #ifdef CONFIG_HIGHMEM /* * Must use a macro here due to header dependency issues. page_zone() is not diff --git a/include/linux/screen_info.h b/include/linux/screen_info.h index 899fbb487c94..e699dd416f91 100644 --- a/include/linux/screen_info.h +++ b/include/linux/screen_info.h @@ -67,6 +67,7 @@ struct screen_info { #define VIDEO_TYPE_EFI 0x70 /* EFI graphic mode */ #define VIDEO_FLAGS_NOCURSOR (1 << 0) /* The video mode has no cursor set */ +#define VIDEO_FLAGS_HANDOFF (1 << 1) /* Video buffer is alredy painted */ #ifdef __KERNEL__ extern struct screen_info screen_info; diff --git a/include/linux/security.h b/include/linux/security.h index 4e5a73cdbbef..6ae2a7f42cac 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -3023,5 +3023,47 @@ static inline void free_secdata(void *secdata) { } #endif /* CONFIG_SECURITY */ +#ifdef CONFIG_SECURITY_YAMA +extern int yama_ptrace_access_check(struct task_struct *child, + unsigned int mode); +extern int yama_path_link(struct dentry *old_dentry, struct path *new_dir, + struct dentry *new_dentry); +extern int yama_inode_follow_link(struct dentry *dentry, + struct nameidata *nameidata); +extern void yama_task_free(struct task_struct *task); +extern int yama_task_prctl(int option, unsigned long arg2, unsigned long arg3, + unsigned long arg4, unsigned long arg5); +#else +static inline int yama_ptrace_access_check(struct task_struct *child, + unsigned int mode) +{ + return 0; +} + +static inline int yama_path_link(struct dentry *old_dentry, + struct path *new_dir, + struct dentry *new_dentry) +{ + return 0; +} + +static inline int yama_inode_follow_link(struct dentry *dentry, + struct nameidata *nameidata) +{ + return 0; +} + +static inline void yama_task_free(struct task_struct *task) +{ +} + +static inline int yama_task_prctl(int option, unsigned long arg2, + unsigned long arg3, unsigned long arg4, + unsigned long arg5) +{ + return -ENOSYS; +} +#endif /* CONFIG_SECURITY_YAMA */ + #endif /* ! __LINUX_SECURITY_H */ diff --git a/include/linux/splice.h b/include/linux/splice.h index 26e5b613deda..3ffef2fe0fd2 100644 --- a/include/linux/splice.h +++ b/include/linux/splice.h @@ -91,4 +91,10 @@ extern void splice_shrink_spd(struct pipe_inode_info *, extern void spd_release_page(struct splice_pipe_desc *, unsigned int); extern const struct pipe_buf_operations page_cache_pipe_buf_ops; + +extern long do_splice_from(struct pipe_inode_info *pipe, struct file *out, + loff_t *ppos, size_t len, unsigned int flags); +extern long do_splice_to(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags); #endif diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h index 50ae7d0c279e..8f227f735b2f 100644 --- a/include/linux/vt_kern.h +++ b/include/linux/vt_kern.h @@ -129,7 +129,7 @@ int con_copy_unimap(struct vc_data *dst_vc, struct vc_data *src_vc) void vt_event_post(unsigned int event, unsigned int old, unsigned int new); int vt_waitactive(int n); void change_console(struct vc_data *new_vc); -void reset_vc(struct vc_data *vc); +void reset_vc(struct vc_data *vc, int mode); extern int unbind_con_driver(const struct consw *csw, int first, int last, int deflt); int vty_init(const struct file_operations *console_fops); diff --git a/include/scsi/Kbuild b/include/scsi/Kbuild deleted file mode 100644 index f2b94918994d..000000000000 --- a/include/scsi/Kbuild +++ /dev/null @@ -1,4 +0,0 @@ -header-y += scsi_netlink.h -header-y += scsi_netlink_fc.h -header-y += scsi_bsg_fc.h -header-y += fc/ diff --git a/include/trace/events/fs.h b/include/trace/events/fs.h new file mode 100644 index 000000000000..2cbb8fed1ae6 --- /dev/null +++ b/include/trace/events/fs.h @@ -0,0 +1,53 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM fs + +#if !defined(_TRACE_FS_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_FS_H + +#include <linux/fs.h> +#include <linux/tracepoint.h> + +TRACE_EVENT(do_sys_open, + + TP_PROTO(char *filename, int flags, int mode), + + TP_ARGS(filename, flags, mode), + + TP_STRUCT__entry( + __string( filename, filename ) + __field( int, flags ) + __field( int, mode ) + ), + + TP_fast_assign( + __assign_str(filename, filename); + __entry->flags = flags; + __entry->mode = mode; + ), + + TP_printk("\"%s\" %x %o", + __get_str(filename), __entry->flags, __entry->mode) +); + +TRACE_EVENT(open_exec, + + TP_PROTO(char *filename), + + TP_ARGS(filename), + + TP_STRUCT__entry( + __string( filename, filename ) + ), + + TP_fast_assign( + __assign_str(filename, filename); + ), + + TP_printk("\"%s\"", + __get_str(filename)) +); + +#endif /* _TRACE_FS_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/vfs.h b/include/trace/events/vfs.h new file mode 100644 index 000000000000..261112909819 --- /dev/null +++ b/include/trace/events/vfs.h @@ -0,0 +1,55 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM vfs + +#include <linux/module.h> + +#if !defined(_TRACE_VFS_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_VFS_H + +/* + * Tracepoint for dirtying an inode: + */ +TRACE_EVENT(dirty_inode, + + TP_PROTO(struct inode *inode, struct task_struct *task), + + TP_ARGS(inode, task), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN ) + __field( pid_t, pid ) + __array( char, dev, 16 ) + __array( char, file, 32 ) + ), + + TP_fast_assign( + if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) { + struct dentry *dentry; + const char *name = "?"; + + dentry = d_find_alias(inode); + if (dentry) { + spin_lock(&dentry->d_lock); + name = (const char *) dentry->d_name.name; + } + + memcpy(__entry->comm, task->comm, TASK_COMM_LEN); + __entry->pid = task->pid; + strlcpy(__entry->file, name, 32); + strlcpy(__entry->dev, inode->i_sb->s_id, 16); + + if (dentry) { + spin_unlock(&dentry->d_lock); + dput(dentry); + } + } + ), + + TP_printk("task=%i (%s) file=%s dev=%s", + __entry->pid, __entry->comm, __entry->file, __entry->dev) +); + +#endif /* _TRACE_VFS_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/xen/interface/io/blkif.h b/include/xen/interface/io/blkif.h index ee338bfde18b..31063bd1b691 100644 --- a/include/xen/interface/io/blkif.h +++ b/include/xen/interface/io/blkif.h @@ -168,6 +168,18 @@ struct blkif_response { DEFINE_RING_TYPES(blkif, struct blkif_request, struct blkif_response); +/* + * Maximum number of pages used for a blkif ring + * max-ring-pages advertised by blkback to blkfront may be lowered at blkback + * mod load time. Load time param set to default. + */ +#define BLKIF_MAX_NUM_RING_PAGES 16 +#define BLKIF_MAX_NUM_RING_PAGES_DFLT 4 +#if BLKIF_MAX_NUM_RING_PAGES < BLKIF_MAX_NUM_RING_PAGES_DFLT +#undef BLKIF_MAX_NUM_RING_PAGES_DFLT +#define BLKIF_MAX_NUM_RING_PAGES_DFLT BLKIF_MAX_NUM_RING_PAGES +#endif + #define VDISK_CDROM 0x1 #define VDISK_REMOVABLE 0x2 #define VDISK_READONLY 0x4 diff --git a/init/Kconfig b/init/Kconfig index 7c329b6d4a13..6a6878189265 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -79,6 +79,13 @@ config INIT_ENV_ARG_LIMIT Maximum of each of the number of arguments and environment variables passed to init from the kernel command line. +config INIT_PASS_ALL_PARAMS + bool "Pass all (known and unknown) kernel parameters to init" + default n + help + Pass all kernel command line parameters to init, this includes + those consumed by kernel modules. This is useful for upstart + based systems. If in doubt say N. config CROSS_COMPILE string "Cross-compiler tool prefix" @@ -214,6 +221,15 @@ config DEFAULT_HOSTNAME but you may wish to use a different default here to make a minimal system more usable with less configuration. +config VERSION_SIGNATURE + string "Arbitrary version signature" + help + This string will be created in a file, /proc/version_signature. It + is useful in determining arbitrary data about your kernel. For instance, + if you have several kernels of the same version, but need to keep track + of a revision of the same kernel, but not affect it's ability to load + compatible modules, this is the easiest way to do that. + config SWAP bool "Support for paging of anonymous memory (swap)" depends on MMU && BLOCK diff --git a/init/initramfs.c b/init/initramfs.c index 84c6bf111300..a9ea4066e2ef 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -18,6 +18,8 @@ #include <linux/dirent.h> #include <linux/syscalls.h> #include <linux/utime.h> +#include <linux/async.h> +#include <linux/export.h> static __initdata char *message; static void __init error(char *x) @@ -579,7 +581,15 @@ static void __init clean_rootfs(void) } #endif -static int __init populate_rootfs(void) +LIST_HEAD(populate_rootfs_domain); + +void populate_rootfs_wait(void) +{ + async_synchronize_full_domain(&populate_rootfs_domain); +} +EXPORT_SYMBOL(populate_rootfs_wait); + +static void __init async_populate_rootfs(void *data, async_cookie_t cookie) { char *err = unpack_to_rootfs(__initramfs_start, __initramfs_size); if (err) @@ -592,7 +602,7 @@ static int __init populate_rootfs(void) initrd_end - initrd_start); if (!err) { free_initrd(); - return 0; + return; } else { clean_rootfs(); unpack_to_rootfs(__initramfs_start, __initramfs_size); @@ -616,6 +626,27 @@ static int __init populate_rootfs(void) free_initrd(); #endif } + return; +} + +static int __initdata rootfs_populated; + +static int __init populate_rootfs_early(void) +{ + if (num_online_cpus() > 1) { + rootfs_populated = 1; + async_schedule_domain(async_populate_rootfs, NULL, + &populate_rootfs_domain); + } + return 0; +} +static int __init populate_rootfs(void) +{ + if (!rootfs_populated) + async_schedule_domain(async_populate_rootfs, NULL, + &populate_rootfs_domain); return 0; } + +earlyrootfs_initcall(populate_rootfs_early); rootfs_initcall(populate_rootfs); diff --git a/init/main.c b/init/main.c index b5cc0a7c4708..d0c1cfeb6084 100644 --- a/init/main.c +++ b/init/main.c @@ -112,6 +112,11 @@ EXPORT_SYMBOL(system_state); */ #define MAX_INIT_ARGS CONFIG_INIT_ENV_ARG_LIMIT #define MAX_INIT_ENVS CONFIG_INIT_ENV_ARG_LIMIT +#ifdef CONFIG_INIT_PASS_ALL_PARAMS +#define INIT_PASS_FUNCTION pass_all_bootoptions +#else +#define INIT_PASS_FUNCTION pass_unknown_bootoptions +#endif extern void time_init(void); /* Default late time init is NULL. archs can override this later. */ @@ -199,7 +204,7 @@ static int __init debug_kernel(char *str) static int __init quiet_kernel(char *str) { - console_loglevel = 4; + console_loglevel = 2; return 0; } @@ -243,19 +248,20 @@ static int __init repair_env_string(char *param, char *val, const char *unused) } /* - * Unknown boot options get handed to init, unless they look like - * unused parameters (modprobe will find them in /proc/cmdline). + * Select boot options to hand to init. If all is set hand off them all + * otherwise only hand off unused ones which do not apply to modules + * (modprobe will find them in /proc/cmdline). */ -static int __init unknown_bootoption(char *param, char *val, const char *unused) +static int __init pass_bootoption(char *param, char *val, const char *unused, int all) { repair_env_string(param, val, unused); /* Handle obsolete-style parameters */ - if (obsolete_checksetup(param)) + if (obsolete_checksetup(param) && !all) return 0; /* Unused module parameter. */ - if (strchr(param, '.') && (!val || strchr(param, '.') < val)) + if (!all && strchr(param, '.') && (!val || strchr(param, '.') < val)) return 0; if (panic_later) @@ -286,6 +292,16 @@ static int __init unknown_bootoption(char *param, char *val, const char *unused) } return 0; } +static int __init pass_unknown_bootoptions(char *param, char *val, const char *unused, int known) +{ + if (known) + return 0; + return pass_bootoption(param, val, unused, 0); +} +static int __init pass_all_bootoptions(char *param, char *val, const char *unused, int known) +{ + return pass_bootoption(param, val, unused, 1); +} static int __init init_setup(char *str) { @@ -385,10 +401,13 @@ static noinline void __init_refok rest_init(void) } /* Check for early params. */ -static int __init do_early_param(char *param, char *val, const char *unused) +static int __init do_early_param(char *param, char *val, const char *unused, int known) { const struct obs_kernel_param *p; + if (known) + return 0; + for (p = __setup_start; p < __setup_end; p++) { if ((p->early && parameq(param, p->str)) || (strcmp(param, "console") == 0 && @@ -508,7 +527,7 @@ asmlinkage void __init start_kernel(void) parse_early_param(); parse_args("Booting kernel", static_command_line, __start___param, __stop___param - __start___param, - -1, -1, &unknown_bootoption); + -1, -1, &INIT_PASS_FUNCTION); jump_label_init(); @@ -871,6 +890,12 @@ static int __init kernel_init(void * unused) (void) sys_dup(0); (void) sys_dup(0); /* + * We need to ensure that the filesystem is ready by this point, wait for + * async_populate_rootfs to complete. + */ + populate_rootfs_wait(); + + /* * check if there is an early userspace init. If yes, let it do all * the work */ diff --git a/init/noinitramfs.c b/init/noinitramfs.c index 267739d85179..e0f648cad6e6 100644 --- a/init/noinitramfs.c +++ b/init/noinitramfs.c @@ -22,6 +22,8 @@ #include <linux/kdev_t.h> #include <linux/syscalls.h> +LIST_HEAD(populate_rootfs_domain); + /* * Create a simple rootfs that is similar to the default initramfs */ diff --git a/init/version.c b/init/version.c index 86fe0ccb997a..3a9433a39d2c 100644 --- a/init/version.c +++ b/init/version.c @@ -40,7 +40,11 @@ EXPORT_SYMBOL_GPL(init_uts_ns); /* FIXED STRINGS! Don't touch! */ const char linux_banner[] = "Linux version " UTS_RELEASE " (" LINUX_COMPILE_BY "@" - LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION "\n"; + LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION +#ifdef CONFIG_VERSION_SIGNATURE + " (" CONFIG_VERSION_SIGNATURE ")" +#endif + "\n"; const char linux_proc_banner[] = "%s version %s" diff --git a/kernel/kmod.c b/kernel/kmod.c index ff2c7cb86d77..9d1b6b26dd96 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -585,6 +585,8 @@ int call_usermodehelper_fns( struct subprocess_info *info; gfp_t gfp_mask = (wait == UMH_NO_WAIT) ? GFP_ATOMIC : GFP_KERNEL; + populate_rootfs_wait(); + info = call_usermodehelper_setup(path, argv, envp, gfp_mask); if (info == NULL) diff --git a/kernel/params.c b/kernel/params.c index ed35345be536..8b8b3144793e 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -90,8 +90,8 @@ static int parse_one(char *param, unsigned num_params, s16 min_level, s16 max_level, - int (*handle_unknown)(char *param, char *val, - const char *doing)) + int (*handle_arg)(char *param, char *val, + const char *doing, int known)) { unsigned int i; int err; @@ -106,6 +106,14 @@ static int parse_one(char *param, if (!val && params[i].ops->set != param_set_bool && params[i].ops->set != param_set_bint) return -EINVAL; + if (handle_arg) { + int ret; + pr_debug("Valid argument: calling %p\n", + handle_arg); + ret = handle_arg(param, val, doing, 1); + if (ret) + return ret; + } pr_debug("handling %s with %p\n", param, params[i].ops->set); mutex_lock(¶m_lock); @@ -115,9 +123,9 @@ static int parse_one(char *param, } } - if (handle_unknown) { + if (handle_arg) { pr_debug("doing %s: %s='%s'\n", doing, param, val); - return handle_unknown(param, val, doing); + return handle_arg(param, val, doing, 0); } pr_debug("Unknown argument '%s'\n", param); @@ -183,7 +191,7 @@ int parse_args(const char *doing, unsigned num, s16 min_level, s16 max_level, - int (*unknown)(char *param, char *val, const char *doing)) + int (*handle_arg)(char *param, char *val, const char *doing, int arg)) { char *param, *val; @@ -200,7 +208,7 @@ int parse_args(const char *doing, args = next_arg(args, ¶m, &val); irq_was_disabled = irqs_disabled(); ret = parse_one(param, val, doing, params, num, - min_level, max_level, unknown); + min_level, max_level, handle_arg); if (irq_was_disabled && !irqs_disabled()) pr_warn("%s: option '%s' enabled irq's!\n", doing, param); diff --git a/mm/filemap.c b/mm/filemap.c index a4a5260b0279..c97ce2627a8a 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1304,6 +1304,9 @@ int file_read_actor(read_descriptor_t *desc, struct page *page, if (size > count) size = count; + if (PageReadaheadUnused(page)) + ClearPageReadaheadUnused(page); + /* * Faults on the destination of a read are common, so do it before * taking the kmap. diff --git a/mm/memory.c b/mm/memory.c index 1b7dc662bf9f..fcee128452b0 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3231,10 +3231,15 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, else VM_BUG_ON(!PageLocked(vmf.page)); + page = vmf.page; + + /* Mark the page as used on fault. */ + if (PageReadaheadUnused(page)) + ClearPageReadaheadUnused(page); + /* * Should we do an early C-O-W break? */ - page = vmf.page; if (flags & FAULT_FLAG_WRITE) { if (!(vma->vm_flags & VM_SHARED)) { page = cow_page; diff --git a/mm/mincore.c b/mm/mincore.c index 936b4cee8cb1..7c2874a9a731 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -80,6 +80,8 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff) #endif if (page) { present = PageUptodate(page); + if (present) + present |= (PageReadaheadUnused(page) << 7); page_cache_release(page); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index bbfaa29232f1..e08dc611d74a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5971,6 +5971,7 @@ static const struct trace_print_flags pageflag_names[] = { #ifdef CONFIG_TRANSPARENT_HUGEPAGE {1UL << PG_compound_lock, "compound_lock" }, #endif + {1UL << PG_readaheadunused, "readaheadunused"}, }; static void dump_page_flags(unsigned long flags) diff --git a/mm/readahead.c b/mm/readahead.c index ea8f8fa21649..3de0a1975735 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -189,6 +189,7 @@ __do_page_cache_readahead(struct address_space *mapping, struct file *filp, list_add(&page->lru, &page_pool); if (page_idx == nr_to_read - lookahead_size) SetPageReadahead(page); + SetPageReadaheadUnused(page); ret++; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 8f6411c97189..246b533ad5a7 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4360,6 +4360,84 @@ int addrconf_sysctl_disable(ctl_table *ctl, int write, return ret; } +#ifdef CONFIG_IPV6_PRIVACY +static void dev_tempaddr_change(struct inet6_dev *idev) +{ + if (!idev || !idev->dev) + return; + + if (!idev->cnf.disable_ipv6) { + /* If ipv6 is enabled, try to bring down and back up the + * interface to get new temporary addresses created + */ + addrconf_notify(NULL, NETDEV_DOWN, idev->dev); + addrconf_notify(NULL, NETDEV_UP, idev->dev); + } +} + +static void addrconf_tempaddr_change(struct net *net, __s32 newf) +{ + struct net_device *dev; + struct inet6_dev *idev; + + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { + idev = __in6_dev_get(dev); + if (idev) { + int changed = (!idev->cnf.use_tempaddr) ^ (!newf); + idev->cnf.use_tempaddr = newf; + if (changed) + dev_tempaddr_change(idev); + } + } + rcu_read_unlock(); +} + +static int addrconf_use_tempaddr(struct ctl_table *table, int *p, int old) +{ + struct net *net; + + net = (struct net *)table->extra2; + + if (p == &net->ipv6.devconf_dflt->use_tempaddr) + return 0; + + if (!rtnl_trylock()) { + /* Restore the original values before restarting */ + *p = old; + return restart_syscall(); + } + + if (p == &net->ipv6.devconf_all->use_tempaddr) { + __s32 newf = net->ipv6.devconf_all->use_tempaddr; + net->ipv6.devconf_dflt->use_tempaddr = newf; + addrconf_tempaddr_change(net, newf); + } else if ((!*p) ^ (!old)) + dev_tempaddr_change((struct inet6_dev *)table->extra1); + + rtnl_unlock(); + return 0; +} + +static +int addrconf_sysctl_tempaddr(ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int *valp = ctl->data; + int val = *valp; + loff_t pos = *ppos; + int ret; + + ret = proc_dointvec(ctl, write, buffer, lenp, ppos); + + if (write) + ret = addrconf_use_tempaddr(ctl, valp, val); + if (ret) + *ppos = pos; + return ret; +} +#endif + static struct addrconf_sysctl_table { struct ctl_table_header *sysctl_header; @@ -4450,7 +4528,7 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.use_tempaddr, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = addrconf_sysctl_tempaddr, }, { .procname = "temp_valid_lft", diff --git a/scripts/Makefile.headersinst b/scripts/Makefile.headersinst index d3bae5e7b601..2a3c1b79b862 100644 --- a/scripts/Makefile.headersinst +++ b/scripts/Makefile.headersinst @@ -55,9 +55,9 @@ printdir = $(patsubst $(INSTALL_HDR_PATH)/%/,%,$(dir $@)) quiet_cmd_install = INSTALL $(printdir) ($(words $(all-files))\ file$(if $(word 2, $(all-files)),s)) cmd_install = \ - $(PERL) $< $(srctree)/$(obj) $(install) $(SRCARCH) $(header-y); \ - $(PERL) $< $(objtree)/$(obj) $(install) $(SRCARCH) $(objhdr-y); \ - $(PERL) $< $(objtree)/$(gen) $(install) $(SRCARCH) $(genhdr-y); \ + $(PERL) $< $(srctree)/$(obj) $(install) $(SRCARCH) $(printdir) $(header-y); \ + $(PERL) $< $(objtree)/$(obj) $(install) $(SRCARCH) $(printdir) $(objhdr-y); \ + $(PERL) $< $(objtree)/$(gen) $(install) $(SRCARCH) $(printdir) $(genhdr-y); \ for F in $(wrapper-files); do \ echo "\#include <asm-generic/$$F>" > $(install)/$$F; \ done; \ diff --git a/scripts/headers_install.pl b/scripts/headers_install.pl index 48462be328bb..9f56fc501168 100644 --- a/scripts/headers_install.pl +++ b/scripts/headers_install.pl @@ -18,7 +18,9 @@ use strict; -my ($readdir, $installdir, $arch, @files) = @ARGV; +my ($readdir, $installdir, $arch, $printdir, @files) = @ARGV; + +$printdir =~ s@^include/@@; my $unifdef = "scripts/unifdef -U__KERNEL__ -D__EXPORTED_HEADERS__"; @@ -30,6 +32,10 @@ foreach my $file (@files) { open(my $out, '>', $tmpfile) or die "$tmpfile: $!\n"; while (my $line = <$in>) { + # Any #include which uses "" and does not have a path needs + # rewriting so that the resultant user space headers are + # safe against the use of -I-. + $line =~ s/^(\s*#\s*include\s+)"([^\/]*?)"/$1<$printdir\/$2>/; $line =~ s/([\s(])__user\s/$1/g; $line =~ s/([\s(])__force\s/$1/g; $line =~ s/([\s(])__iomem\s/$1/g; diff --git a/scripts/kconfig/lkc.h b/scripts/kconfig/lkc.h index c18f2bd9c095..608cf6558bdb 100644 --- a/scripts/kconfig/lkc.h +++ b/scripts/kconfig/lkc.h @@ -90,7 +90,9 @@ struct conf_printer { /* confdata.c and expr.c */ static inline void xfwrite(const void *str, size_t len, size_t count, FILE *out) { - assert(len != 0); + //assert(len != 0); + if (len == 0) + return; if (fwrite(str, len, count, out) != count) fprintf(stderr, "Error in writing or end of file.\n"); diff --git a/security/apparmor/.gitignore b/security/apparmor/.gitignore index 4d995aeaebc0..d5b291e94264 100644 --- a/security/apparmor/.gitignore +++ b/security/apparmor/.gitignore @@ -1,6 +1,6 @@ # # Generated include files # -af_names.h +net_names.h capability_names.h rlim_names.h diff --git a/security/apparmor/Makefile b/security/apparmor/Makefile index 806bd19af7f2..c575af92c8ba 100644 --- a/security/apparmor/Makefile +++ b/security/apparmor/Makefile @@ -4,10 +4,9 @@ obj-$(CONFIG_SECURITY_APPARMOR) += apparmor.o apparmor-y := apparmorfs.o audit.o capability.o context.o ipc.o lib.o match.o \ path.o domain.o policy.o policy_unpack.o procattr.o lsm.o \ - resource.o sid.o file.o - -clean-files := capability_names.h rlim_names.h + resource.o sid.o file.o mount.o net.o +clean-files := capability_names.h rlim_names.h net_names.h # Build a lower case string table of capability names # Transforms lines from @@ -20,6 +19,38 @@ cmd_make-caps = echo "static const char *const capability_names[] = {" > $@ ;\ -e 's/^\#define[ \t]+CAP_([A-Z0-9_]+)[ \t]+([0-9]+)/[\2] = "\L\1",/p';\ echo "};" >> $@ +# Build a lower case string table of address family names +# Transform lines from +# define AF_LOCAL 1 /* POSIX name for AF_UNIX */ +# #define AF_INET 2 /* Internet IP Protocol */ +# to +# [1] = "local", +# [2] = "inet", +# +# and build the securityfs entries for the mapping. +# Transforms lines from +# #define AF_INET 2 /* Internet IP Protocol */ +# to +# #define AA_FS_AF_MASK "local inet" +quiet_cmd_make-af = GEN $@ +cmd_make-af = echo "static const char *address_family_names[] = {" > $@ ;\ + sed $< >>$@ -r -n -e "/AF_MAX/d" -e "/AF_LOCAL/d" -e \ + 's/^\#define[ \t]+AF_([A-Z0-9_]+)[ \t]+([0-9]+)(.*)/[\2] = "\L\1",/p';\ + echo "};" >> $@ ;\ + echo -n '\#define AA_FS_AF_MASK "' >> $@ ;\ + sed -r -n 's/^\#define[ \t]+AF_([A-Z0-9_]+)[ \t]+([0-9]+)(.*)/\L\1/p'\ + $< | tr '\n' ' ' | sed -e 's/ $$/"\n/' >> $@ + +# Build a lower case string table of sock type names +# Transform lines from +# SOCK_STREAM = 1, +# to +# [1] = "stream", +quiet_cmd_make-sock = GEN $@ +cmd_make-sock = echo "static const char *sock_type_names[] = {" >> $@ ;\ + sed $^ >>$@ -r -n \ + -e 's/^\tSOCK_([A-Z0-9_]+)[\t]+=[ \t]+([0-9]+)(.*)/[\2] = "\L\1",/p';\ + echo "};" >> $@ # Build a lower case string table of rlimit names. # Transforms lines from @@ -56,6 +87,7 @@ cmd_make-rlim = echo "static const char *const rlim_names[RLIM_NLIMITS] = {" \ tr '\n' ' ' | sed -e 's/ $$/"\n/' >> $@ $(obj)/capability.o : $(obj)/capability_names.h +$(obj)/net.o : $(obj)/net_names.h $(obj)/resource.o : $(obj)/rlim_names.h $(obj)/capability_names.h : $(srctree)/include/linux/capability.h \ $(src)/Makefile @@ -63,3 +95,8 @@ $(obj)/capability_names.h : $(srctree)/include/linux/capability.h \ $(obj)/rlim_names.h : $(srctree)/include/asm-generic/resource.h \ $(src)/Makefile $(call cmd,make-rlim) +$(obj)/net_names.h : $(srctree)/include/linux/socket.h \ + $(srctree)/include/linux/net.h \ + $(src)/Makefile + $(call cmd,make-af) + $(call cmd,make-sock) diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index 16c15ec6f670..01a335d15c27 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -182,6 +182,232 @@ const struct file_operations aa_fs_seq_file_ops = { .release = single_release, }; +/** + * __next_namespace - find the next namespace to list + * @root: root namespace to stop search at (NOT NULL) + * @ns: current ns position (NOT NULL) + * + * Find the next namespace from @ns under @root and handle all locking needed + * while switching current namespace. + * + * Returns: next namespace or NULL if at last namespace under @root + * NOTE: will not unlock root->lock + */ +static struct aa_namespace *__next_namespace(struct aa_namespace *root, + struct aa_namespace *ns) +{ + struct aa_namespace *parent; + + /* is next namespace a child */ + if (!list_empty(&ns->sub_ns)) { + struct aa_namespace *next; + next = list_first_entry(&ns->sub_ns, typeof(*ns), base.list); + read_lock(&next->lock); + return next; + } + + /* check if the next ns is a sibling, parent, gp, .. */ + parent = ns->parent; + while (parent) { + read_unlock(&ns->lock); + list_for_each_entry_continue(ns, &parent->sub_ns, base.list) { + read_lock(&ns->lock); + return ns; + } + if (parent == root) + return NULL; + ns = parent; + parent = parent->parent; + } + + return NULL; +} + +/** + * __first_profile - find the first profile in a namespace + * @root: namespace that is root of profiles being displayed (NOT NULL) + * @ns: namespace to start in (NOT NULL) + * + * Returns: unrefcounted profile or NULL if no profile + */ +static struct aa_profile *__first_profile(struct aa_namespace *root, + struct aa_namespace *ns) +{ + for ( ; ns; ns = __next_namespace(root, ns)) { + if (!list_empty(&ns->base.profiles)) + return list_first_entry(&ns->base.profiles, + struct aa_profile, base.list); + } + return NULL; +} + +/** + * __next_profile - step to the next profile in a profile tree + * @profile: current profile in tree (NOT NULL) + * + * Perform a depth first taversal on the profile tree in a namespace + * + * Returns: next profile or NULL if done + * Requires: profile->ns.lock to be held + */ +static struct aa_profile *__next_profile(struct aa_profile *p) +{ + struct aa_profile *parent; + struct aa_namespace *ns = p->ns; + + /* is next profile a child */ + if (!list_empty(&p->base.profiles)) + return list_first_entry(&p->base.profiles, typeof(*p), + base.list); + + /* is next profile a sibling, parent sibling, gp, subling, .. */ + parent = p->parent; + while (parent) { + list_for_each_entry_continue(p, &parent->base.profiles, + base.list) + return p; + p = parent; + parent = parent->parent; + } + + /* is next another profile in the namespace */ + list_for_each_entry_continue(p, &ns->base.profiles, base.list) + return p; + + return NULL; +} + +/** + * next_profile - step to the next profile in where ever it may be + * @root: root namespace (NOT NULL) + * @profile: current profile (NOT NULL) + * + * Returns: next profile or NULL if there isn't one + */ +static struct aa_profile *next_profile(struct aa_namespace *root, + struct aa_profile *profile) +{ + struct aa_profile *next = __next_profile(profile); + if (next) + return next; + + /* finished all profiles in namespace move to next namespace */ + return __first_profile(root, __next_namespace(root, profile->ns)); +} + +/** + * p_start - start a depth first traversal of profile tree + * @f: seq_file to fill + * @pos: current position + * + * Returns: first profile under current namespace or NULL if none found + * + * acquires first ns->lock + */ +static void *p_start(struct seq_file *f, loff_t *pos) + __acquires(root->lock) +{ + struct aa_profile *profile = NULL; + struct aa_namespace *root = aa_current_profile()->ns; + loff_t l = *pos; + f->private = aa_get_namespace(root); + + + /* find the first profile */ + read_lock(&root->lock); + profile = __first_profile(root, root); + + /* skip to position */ + for (; profile && l > 0; l--) + profile = next_profile(root, profile); + + return profile; +} + +/** + * p_next - read the next profile entry + * @f: seq_file to fill + * @p: profile previously returned + * @pos: current position + * + * Returns: next profile after @p or NULL if none + * + * may acquire/release locks in namespace tree as necessary + */ +static void *p_next(struct seq_file *f, void *p, loff_t *pos) +{ + struct aa_profile *profile = p; + struct aa_namespace *root = f->private; + (*pos)++; + + return next_profile(root, profile); +} + +/** + * p_stop - stop depth first traversal + * @f: seq_file we are filling + * @p: the last profile writen + * + * Release all locking done by p_start/p_next on namespace tree + */ +static void p_stop(struct seq_file *f, void *p) + __releases(root->lock) +{ + struct aa_profile *profile = p; + struct aa_namespace *root = f->private, *ns; + + if (profile) { + for (ns = profile->ns; ns && ns != root; ns = ns->parent) + read_unlock(&ns->lock); + } + read_unlock(&root->lock); + aa_put_namespace(root); +} + +/** + * seq_show_profile - show a profile entry + * @f: seq_file to file + * @p: current position (profile) (NOT NULL) + * + * Returns: error on failure + */ +static int seq_show_profile(struct seq_file *f, void *p) +{ + struct aa_profile *profile = (struct aa_profile *)p; + struct aa_namespace *root = f->private; + + if (profile->ns != root) + seq_printf(f, ":%s://", aa_ns_name(root, profile->ns)); + seq_printf(f, "%s (%s)\n", profile->base.hname, + COMPLAIN_MODE(profile) ? "complain" : "enforce"); + + return 0; +} + +static const struct seq_operations aa_fs_profiles_op = { + .start = p_start, + .next = p_next, + .stop = p_stop, + .show = seq_show_profile, +}; + +static int profiles_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &aa_fs_profiles_op); +} + +static int profiles_release(struct inode *inode, struct file *file) +{ + return seq_release(inode, file); +} + +const struct file_operations aa_fs_profiles_fops = { + .open = profiles_open, + .read = seq_read, + .llseek = seq_lseek, + .release = profiles_release, +}; + /** Base file system setup **/ static struct aa_fs_entry aa_fs_entry_file[] = { @@ -198,9 +424,23 @@ static struct aa_fs_entry aa_fs_entry_domain[] = { { } }; +static struct aa_fs_entry aa_fs_entry_mount[] = { + AA_FS_FILE_STRING("mask", "mount umount"), + { } +}; + +static struct aa_fs_entry aa_fs_entry_namespaces[] = { + AA_FS_FILE_BOOLEAN("profile", 1), + AA_FS_FILE_BOOLEAN("pivot_root", 1), + { } +}; + static struct aa_fs_entry aa_fs_entry_features[] = { AA_FS_DIR("domain", aa_fs_entry_domain), AA_FS_DIR("file", aa_fs_entry_file), + AA_FS_DIR("network", aa_fs_entry_network), + AA_FS_DIR("mount", aa_fs_entry_mount), + AA_FS_DIR("namespaces", aa_fs_entry_namespaces), AA_FS_FILE_U64("capability", VFS_CAP_FLAGS_MASK), AA_FS_DIR("rlimit", aa_fs_entry_rlimit), { } @@ -210,6 +450,7 @@ static struct aa_fs_entry aa_fs_entry_apparmor[] = { AA_FS_FILE_FOPS(".load", 0640, &aa_fs_profile_load), AA_FS_FILE_FOPS(".replace", 0640, &aa_fs_profile_replace), AA_FS_FILE_FOPS(".remove", 0640, &aa_fs_profile_remove), + AA_FS_FILE_FOPS("profiles", 0640, &aa_fs_profiles_fops), AA_FS_DIR("features", aa_fs_entry_features), { } }; diff --git a/security/apparmor/audit.c b/security/apparmor/audit.c index 3ae28db5a64f..e26796312ec2 100644 --- a/security/apparmor/audit.c +++ b/security/apparmor/audit.c @@ -44,6 +44,10 @@ const char *const op_table[] = { "file_mmap", "file_mprotect", + "pivotroot", + "mount", + "umount", + "create", "post_create", "bind", diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c index b81ea10a17a3..31a3f5284a76 100644 --- a/security/apparmor/domain.c +++ b/security/apparmor/domain.c @@ -242,7 +242,7 @@ static const char *next_name(int xtype, const char *name) * * Returns: refcounted profile, or NULL on failure (MAYBE NULL) */ -static struct aa_profile *x_table_lookup(struct aa_profile *profile, u32 xindex) +struct aa_profile *x_table_lookup(struct aa_profile *profile, u32 xindex) { struct aa_profile *new_profile = NULL; struct aa_namespace *ns = profile->ns; @@ -360,6 +360,10 @@ int apparmor_bprm_set_creds(struct linux_binprm *bprm) if (bprm->cred_prepared) return 0; + /* XXX: no_new_privs is not usable with AppArmor yet */ + if (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS) + return -EPERM; + cxt = bprm->cred->security; BUG_ON(!cxt); diff --git a/security/apparmor/include/apparmor.h b/security/apparmor/include/apparmor.h index 40aedd9f73ea..e243d96ddbd9 100644 --- a/security/apparmor/include/apparmor.h +++ b/security/apparmor/include/apparmor.h @@ -29,8 +29,9 @@ #define AA_CLASS_NET 4 #define AA_CLASS_RLIMITS 5 #define AA_CLASS_DOMAIN 6 +#define AA_CLASS_MOUNT 7 -#define AA_CLASS_LAST AA_CLASS_DOMAIN +#define AA_CLASS_LAST AA_CLASS_MOUNT /* Control parameters settable through module/boot flags */ extern enum audit_mode aa_g_audit; diff --git a/security/apparmor/include/audit.h b/security/apparmor/include/audit.h index 4b7e18951aea..66a738c5c9c3 100644 --- a/security/apparmor/include/audit.h +++ b/security/apparmor/include/audit.h @@ -73,6 +73,10 @@ enum aa_ops { OP_FMMAP, OP_FMPROT, + OP_PIVOTROOT, + OP_MOUNT, + OP_UMOUNT, + OP_CREATE, OP_POST_CREATE, OP_BIND, @@ -122,11 +126,22 @@ struct apparmor_audit_data { unsigned long max; } rlim; struct { + const char *src_name; + const char *type; + const char *trans; + const char *data; + unsigned long flags; + } mnt; + struct { const char *target; u32 request; u32 denied; uid_t ouid; } fs; + struct { + int type, protocol; + struct sock *sk; + } net; }; }; diff --git a/security/apparmor/include/domain.h b/security/apparmor/include/domain.h index de04464f0a3f..a3f70c58ef3d 100644 --- a/security/apparmor/include/domain.h +++ b/security/apparmor/include/domain.h @@ -23,6 +23,8 @@ struct aa_domain { char **table; }; +struct aa_profile *x_table_lookup(struct aa_profile *profile, u32 xindex); + int apparmor_bprm_set_creds(struct linux_binprm *bprm); int apparmor_bprm_secureexec(struct linux_binprm *bprm); void apparmor_bprm_committing_creds(struct linux_binprm *bprm); diff --git a/security/apparmor/include/mount.h b/security/apparmor/include/mount.h new file mode 100644 index 000000000000..bc17a5388ae9 --- /dev/null +++ b/security/apparmor/include/mount.h @@ -0,0 +1,54 @@ +/* + * AppArmor security module + * + * This file contains AppArmor file mediation function definitions. + * + * Copyright 2012 Canonical Ltd. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation, version 2 of the + * License. + */ + +#ifndef __AA_MOUNT_H +#define __AA_MOUNT_H + +#include <linux/fs.h> +#include <linux/path.h> + +#include "domain.h" +#include "policy.h" + +/* mount perms */ +#define AA_MAY_PIVOTROOT 0x01 +#define AA_MAY_MOUNT 0x02 +#define AA_MAY_UMOUNT 0x04 +#define AA_AUDIT_DATA 0x40 +#define AA_CONT_MATCH 0x40 + +#define AA_MS_IGNORE_MASK (MS_KERNMOUNT | MS_NOSEC | MS_ACTIVE | MS_BORN) + +int aa_remount(struct aa_profile *profile, struct path *path, + unsigned long flags, void *data); + +int aa_bind_mount(struct aa_profile *profile, struct path *path, + const char *old_name, unsigned long flags); + + +int aa_mount_change_type(struct aa_profile *profile, struct path *path, + unsigned long flags); + +int aa_move_mount(struct aa_profile *profile, struct path *path, + const char *old_name); + +int aa_new_mount(struct aa_profile *profile, const char *dev_name, + struct path *path, const char *type, unsigned long flags, + void *data); + +int aa_umount(struct aa_profile *profile, struct vfsmount *mnt, int flags); + +int aa_pivotroot(struct aa_profile *profile, struct path *old_path, + struct path *new_path); + +#endif /* __AA_MOUNT_H */ diff --git a/security/apparmor/include/net.h b/security/apparmor/include/net.h new file mode 100644 index 000000000000..cb8a12109b7a --- /dev/null +++ b/security/apparmor/include/net.h @@ -0,0 +1,44 @@ +/* + * AppArmor security module + * + * This file contains AppArmor network mediation definitions. + * + * Copyright (C) 1998-2008 Novell/SUSE + * Copyright 2009-2012 Canonical Ltd. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation, version 2 of the + * License. + */ + +#ifndef __AA_NET_H +#define __AA_NET_H + +#include <net/sock.h> + +#include "apparmorfs.h" + +/* struct aa_net - network confinement data + * @allowed: basic network families permissions + * @audit_network: which network permissions to force audit + * @quiet_network: which network permissions to quiet rejects + */ +struct aa_net { + u16 allow[AF_MAX]; + u16 audit[AF_MAX]; + u16 quiet[AF_MAX]; +}; + +extern struct aa_fs_entry aa_fs_entry_network[]; + +extern int aa_net_perm(int op, struct aa_profile *profile, u16 family, + int type, int protocol, struct sock *sk); +extern int aa_revalidate_sk(int op, struct sock *sk); + +static inline void aa_free_net_rules(struct aa_net *new) +{ + /* NOP */ +} + +#endif /* __AA_NET_H */ diff --git a/security/apparmor/include/policy.h b/security/apparmor/include/policy.h index bda4569fdd83..eb13a73f7383 100644 --- a/security/apparmor/include/policy.h +++ b/security/apparmor/include/policy.h @@ -27,6 +27,7 @@ #include "capability.h" #include "domain.h" #include "file.h" +#include "net.h" #include "resource.h" extern const char *const profile_mode_names[]; @@ -157,6 +158,7 @@ struct aa_policydb { * @policy: general match rules governing policy * @file: The set of rules governing basic file access and domain transitions * @caps: capabilities for the profile + * @net: network controls for the profile * @rlimits: rlimits for the profile * * The AppArmor profile contains the basic confinement data. Each profile @@ -194,6 +196,7 @@ struct aa_profile { struct aa_policydb policy; struct aa_file_rules file; struct aa_caps caps; + struct aa_net net; struct aa_rlimit rlimits; }; diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 8ea39aabe948..65ff9e4a841b 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -32,9 +32,11 @@ #include "include/context.h" #include "include/file.h" #include "include/ipc.h" +#include "include/net.h" #include "include/path.h" #include "include/policy.h" #include "include/procattr.h" +#include "include/mount.h" /* Flag indicating whether initialization completed */ int apparmor_initialized __initdata; @@ -503,6 +505,60 @@ static int apparmor_file_mprotect(struct vm_area_struct *vma, !(vma->vm_flags & VM_SHARED) ? MAP_PRIVATE : 0); } +static int apparmor_sb_mount(char *dev_name, struct path *path, char *type, + unsigned long flags, void *data) +{ + struct aa_profile *profile; + int error = 0; + + /* Discard magic */ + if ((flags & MS_MGC_MSK) == MS_MGC_VAL) + flags &= ~MS_MGC_MSK; + + flags &= ~AA_MS_IGNORE_MASK; + + profile = __aa_current_profile(); + if (!unconfined(profile)) { + if (flags & MS_REMOUNT) + error = aa_remount(profile, path, flags, data); + else if (flags & MS_BIND) + error = aa_bind_mount(profile, path, dev_name, flags); + else if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | + MS_UNBINDABLE)) + error = aa_mount_change_type(profile, path, flags); + else if (flags & MS_MOVE) + error = aa_move_mount(profile, path, dev_name); + else + error = aa_new_mount(profile, dev_name, path, type, + flags, data); + } + return error; +} + +static int apparmor_sb_umount(struct vfsmount *mnt, int flags) +{ + struct aa_profile *profile; + int error = 0; + + profile = __aa_current_profile(); + if (!unconfined(profile)) + error = aa_umount(profile, mnt, flags); + + return error; +} + +static int apparmor_sb_pivotroot(struct path *old_path, struct path *new_path) +{ + struct aa_profile *profile; + int error = 0; + + profile = __aa_current_profile(); + if (!unconfined(profile)) + error = aa_pivotroot(profile, old_path, new_path); + + return error; +} + static int apparmor_getprocattr(struct task_struct *task, char *name, char **value) { @@ -614,6 +670,104 @@ static int apparmor_task_setrlimit(struct task_struct *task, return error; } +static int apparmor_socket_create(int family, int type, int protocol, int kern) +{ + struct aa_profile *profile; + int error = 0; + + if (kern) + return 0; + + profile = __aa_current_profile(); + if (!unconfined(profile)) + error = aa_net_perm(OP_CREATE, profile, family, type, protocol, + NULL); + return error; +} + +static int apparmor_socket_bind(struct socket *sock, + struct sockaddr *address, int addrlen) +{ + struct sock *sk = sock->sk; + + return aa_revalidate_sk(OP_BIND, sk); +} + +static int apparmor_socket_connect(struct socket *sock, + struct sockaddr *address, int addrlen) +{ + struct sock *sk = sock->sk; + + return aa_revalidate_sk(OP_CONNECT, sk); +} + +static int apparmor_socket_listen(struct socket *sock, int backlog) +{ + struct sock *sk = sock->sk; + + return aa_revalidate_sk(OP_LISTEN, sk); +} + +static int apparmor_socket_accept(struct socket *sock, struct socket *newsock) +{ + struct sock *sk = sock->sk; + + return aa_revalidate_sk(OP_ACCEPT, sk); +} + +static int apparmor_socket_sendmsg(struct socket *sock, + struct msghdr *msg, int size) +{ + struct sock *sk = sock->sk; + + return aa_revalidate_sk(OP_SENDMSG, sk); +} + +static int apparmor_socket_recvmsg(struct socket *sock, + struct msghdr *msg, int size, int flags) +{ + struct sock *sk = sock->sk; + + return aa_revalidate_sk(OP_RECVMSG, sk); +} + +static int apparmor_socket_getsockname(struct socket *sock) +{ + struct sock *sk = sock->sk; + + return aa_revalidate_sk(OP_GETSOCKNAME, sk); +} + +static int apparmor_socket_getpeername(struct socket *sock) +{ + struct sock *sk = sock->sk; + + return aa_revalidate_sk(OP_GETPEERNAME, sk); +} + +static int apparmor_socket_getsockopt(struct socket *sock, int level, + int optname) +{ + struct sock *sk = sock->sk; + + return aa_revalidate_sk(OP_GETSOCKOPT, sk); +} + +static int apparmor_socket_setsockopt(struct socket *sock, int level, + int optname) +{ + struct sock *sk = sock->sk; + + return aa_revalidate_sk(OP_SETSOCKOPT, sk); +} + +static int apparmor_socket_shutdown(struct socket *sock, int how) +{ + struct sock *sk = sock->sk; + + return aa_revalidate_sk(OP_SOCK_SHUTDOWN, sk); +} + static struct security_operations apparmor_ops = { .name = "apparmor", @@ -622,6 +776,10 @@ static struct security_operations apparmor_ops = { .capget = apparmor_capget, .capable = apparmor_capable, + .sb_mount = apparmor_sb_mount, + .sb_umount = apparmor_sb_umount, + .sb_pivotroot = apparmor_sb_pivotroot, + .path_link = apparmor_path_link, .path_unlink = apparmor_path_unlink, .path_symlink = apparmor_path_symlink, @@ -646,6 +804,19 @@ static struct security_operations apparmor_ops = { .getprocattr = apparmor_getprocattr, .setprocattr = apparmor_setprocattr, + .socket_create = apparmor_socket_create, + .socket_bind = apparmor_socket_bind, + .socket_connect = apparmor_socket_connect, + .socket_listen = apparmor_socket_listen, + .socket_accept = apparmor_socket_accept, + .socket_sendmsg = apparmor_socket_sendmsg, + .socket_recvmsg = apparmor_socket_recvmsg, + .socket_getsockname = apparmor_socket_getsockname, + .socket_getpeername = apparmor_socket_getpeername, + .socket_getsockopt = apparmor_socket_getsockopt, + .socket_setsockopt = apparmor_socket_setsockopt, + .socket_shutdown = apparmor_socket_shutdown, + .cred_alloc_blank = apparmor_cred_alloc_blank, .cred_free = apparmor_cred_free, .cred_prepare = apparmor_cred_prepare, diff --git a/security/apparmor/mount.c b/security/apparmor/mount.c new file mode 100644 index 000000000000..315979b269c4 --- /dev/null +++ b/security/apparmor/mount.c @@ -0,0 +1,620 @@ +/* + * AppArmor security module + * + * This file contains AppArmor mediation of files + * + * Copyright (C) 1998-2008 Novell/SUSE + * Copyright 2009-2012 Canonical Ltd. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation, version 2 of the + * License. + */ + +#include <linux/fs.h> +#include <linux/mount.h> +#include <linux/namei.h> + +#include "include/apparmor.h" +#include "include/audit.h" +#include "include/context.h" +#include "include/domain.h" +#include "include/file.h" +#include "include/match.h" +#include "include/mount.h" +#include "include/path.h" +#include "include/policy.h" + + +static void audit_mnt_flags(struct audit_buffer *ab, unsigned long flags) +{ + if (flags & MS_RDONLY) + audit_log_format(ab, "ro"); + else + audit_log_format(ab, "rw"); + if (flags & MS_NOSUID) + audit_log_format(ab, ", nosuid"); + if (flags & MS_NODEV) + audit_log_format(ab, ", nodev"); + if (flags & MS_NOEXEC) + audit_log_format(ab, ", noexec"); + if (flags & MS_SYNCHRONOUS) + audit_log_format(ab, ", sync"); + if (flags & MS_REMOUNT) + audit_log_format(ab, ", remount"); + if (flags & MS_MANDLOCK) + audit_log_format(ab, ", mand"); + if (flags & MS_DIRSYNC) + audit_log_format(ab, ", dirsync"); + if (flags & MS_NOATIME) + audit_log_format(ab, ", noatime"); + if (flags & MS_NODIRATIME) + audit_log_format(ab, ", nodiratime"); + if (flags & MS_BIND) + audit_log_format(ab, flags & MS_REC ? ", rbind" : ", bind"); + if (flags & MS_MOVE) + audit_log_format(ab, ", move"); + if (flags & MS_SILENT) + audit_log_format(ab, ", silent"); + if (flags & MS_POSIXACL) + audit_log_format(ab, ", acl"); + if (flags & MS_UNBINDABLE) + audit_log_format(ab, flags & MS_REC ? ", runbindable" : + ", unbindable"); + if (flags & MS_PRIVATE) + audit_log_format(ab, flags & MS_REC ? ", rprivate" : + ", private"); + if (flags & MS_SLAVE) + audit_log_format(ab, flags & MS_REC ? ", rslave" : + ", slave"); + if (flags & MS_SHARED) + audit_log_format(ab, flags & MS_REC ? ", rshared" : + ", shared"); + if (flags & MS_RELATIME) + audit_log_format(ab, ", relatime"); + if (flags & MS_I_VERSION) + audit_log_format(ab, ", iversion"); + if (flags & MS_STRICTATIME) + audit_log_format(ab, ", strictatime"); + if (flags & MS_NOUSER) + audit_log_format(ab, ", nouser"); +} + +/** + * audit_cb - call back for mount specific audit fields + * @ab: audit_buffer (NOT NULL) + * @va: audit struct to audit values of (NOT NULL) + */ +static void audit_cb(struct audit_buffer *ab, void *va) +{ + struct common_audit_data *sa = va; + + if (sa->aad->mnt.type) { + audit_log_format(ab, " fstype="); + audit_log_untrustedstring(ab, sa->aad->mnt.type); + } + if (sa->aad->mnt.src_name) { + audit_log_format(ab, " srcname="); + audit_log_untrustedstring(ab, sa->aad->mnt.src_name); + } + if (sa->aad->mnt.trans) { + audit_log_format(ab, " trans="); + audit_log_untrustedstring(ab, sa->aad->mnt.trans); + } + if (sa->aad->mnt.flags || sa->aad->op == OP_MOUNT) { + audit_log_format(ab, " flags=\""); + audit_mnt_flags(ab, sa->aad->mnt.flags); + audit_log_format(ab, "\""); + } + if (sa->aad->mnt.data) { + audit_log_format(ab, " options="); + audit_log_untrustedstring(ab, sa->aad->mnt.data); + } +} + +/** + * audit_mount - handle the auditing of mount operations + * @profile: the profile being enforced (NOT NULL) + * @gfp: allocation flags + * @op: operation being mediated (NOT NULL) + * @name: name of object being mediated (MAYBE NULL) + * @src_name: src_name of object being mediated (MAYBE_NULL) + * @type: type of filesystem (MAYBE_NULL) + * @trans: name of trans (MAYBE NULL) + * @flags: filesystem idependent mount flags + * @data: filesystem mount flags + * @request: permissions requested + * @perms: the permissions computed for the request (NOT NULL) + * @info: extra information message (MAYBE NULL) + * @error: 0 if operation allowed else failure error code + * + * Returns: %0 or error on failure + */ +static int audit_mount(struct aa_profile *profile, gfp_t gfp, int op, + const char *name, const char *src_name, + const char *type, const char *trans, + unsigned long flags, const void *data, u32 request, + struct file_perms *perms, const char *info, int error) +{ + int audit_type = AUDIT_APPARMOR_AUTO; + struct common_audit_data sa; + struct apparmor_audit_data aad = { }; + + if (likely(!error)) { + u32 mask = perms->audit; + + if (unlikely(AUDIT_MODE(profile) == AUDIT_ALL)) + mask = 0xffff; + + /* mask off perms that are not being force audited */ + request &= mask; + + if (likely(!request)) + return 0; + audit_type = AUDIT_APPARMOR_AUDIT; + } else { + /* only report permissions that were denied */ + request = request & ~perms->allow; + + if (request & perms->kill) + audit_type = AUDIT_APPARMOR_KILL; + + /* quiet known rejects, assumes quiet and kill do not overlap */ + if ((request & perms->quiet) && + AUDIT_MODE(profile) != AUDIT_NOQUIET && + AUDIT_MODE(profile) != AUDIT_ALL) + request &= ~perms->quiet; + + if (!request) + return COMPLAIN_MODE(profile) ? + complain_error(error) : error; + } + + sa.type = LSM_AUDIT_DATA_NONE; + sa.aad = &aad; + sa.aad->op = op; + sa.aad->name = name; + sa.aad->mnt.src_name = src_name; + sa.aad->mnt.type = type; + sa.aad->mnt.trans = trans; + sa.aad->mnt.flags = flags; + if (data && (perms->audit & AA_AUDIT_DATA)) + sa.aad->mnt.data = data; + sa.aad->info = info; + sa.aad->error = error; + + return aa_audit(audit_type, profile, gfp, &sa, audit_cb); +} + +/** + * match_mnt_flags - Do an ordered match on mount flags + * @dfa: dfa to match against + * @state: state to start in + * @flags: mount flags to match against + * + * Mount flags are encoded as an ordered match. This is done instead of + * checking against a simple bitmask, to allow for logical operations + * on the flags. + * + * Returns: next state after flags match + */ +static unsigned int match_mnt_flags(struct aa_dfa *dfa, unsigned int state, + unsigned long flags) +{ + unsigned int i; + + for (i = 0; i <= 31 ; ++i) { + if ((1 << i) & flags) + state = aa_dfa_next(dfa, state, i + 1); + } + + return state; +} + +/** + * compute_mnt_perms - compute mount permission associated with @state + * @dfa: dfa to match against (NOT NULL) + * @state: state match finished in + * + * Returns: mount permissions + */ +static struct file_perms compute_mnt_perms(struct aa_dfa *dfa, + unsigned int state) +{ + struct file_perms perms; + + perms.kill = 0; + perms.allow = dfa_user_allow(dfa, state); + perms.audit = dfa_user_audit(dfa, state); + perms.quiet = dfa_user_quiet(dfa, state); + perms.xindex = dfa_user_xindex(dfa, state); + + return perms; +} + +static const char const *mnt_info_table[] = { + "match succeeded", + "failed mntpnt match", + "failed srcname match", + "failed type match", + "failed flags match", + "failed data match" +}; + +/* + * Returns 0 on success else element that match failed in, this is the + * index into the mnt_info_table above + */ +static int do_match_mnt(struct aa_dfa *dfa, unsigned int start, + const char *mntpnt, const char *devname, + const char *type, unsigned long flags, + void *data, bool binary, struct file_perms *perms) +{ + unsigned int state; + + state = aa_dfa_match(dfa, start, mntpnt); + state = aa_dfa_null_transition(dfa, state); + if (!state) + return 1; + + if (devname) + state = aa_dfa_match(dfa, state, devname); + state = aa_dfa_null_transition(dfa, state); + if (!state) + return 2; + + if (type) + state = aa_dfa_match(dfa, state, type); + state = aa_dfa_null_transition(dfa, state); + if (!state) + return 3; + + state = match_mnt_flags(dfa, state, flags); + if (!state) + return 4; + *perms = compute_mnt_perms(dfa, state); + if (perms->allow & AA_MAY_MOUNT) + return 0; + + /* only match data if not binary and the DFA flags data is expected */ + if (data && !binary && (perms->allow & AA_CONT_MATCH)) { + state = aa_dfa_null_transition(dfa, state); + if (!state) + return 4; + + state = aa_dfa_match(dfa, state, data); + if (!state) + return 5; + *perms = compute_mnt_perms(dfa, state); + if (perms->allow & AA_MAY_MOUNT) + return 0; + } + + /* failed at end of flags match */ + return 4; +} + +/** + * match_mnt - handle path matching for mount + * @profile: the confining profile + * @mntpnt: string for the mntpnt (NOT NULL) + * @devname: string for the devname/src_name (MAYBE NULL) + * @type: string for the dev type (MAYBE NULL) + * @flags: mount flags to match + * @data: fs mount data (MAYBE NULL) + * @binary: whether @data is binary + * @perms: Returns: permission found by the match + * @info: Returns: infomation string about the match for logging + * + * Returns: 0 on success else error + */ +static int match_mnt(struct aa_profile *profile, const char *mntpnt, + const char *devname, const char *type, + unsigned long flags, void *data, bool binary, + struct file_perms *perms, const char **info) +{ + int pos; + + if (!profile->policy.dfa) + return -EACCES; + + pos = do_match_mnt(profile->policy.dfa, + profile->policy.start[AA_CLASS_MOUNT], + mntpnt, devname, type, flags, data, binary, perms); + if (pos) { + *info = mnt_info_table[pos]; + return -EACCES; + } + + return 0; +} + +static int path_flags(struct aa_profile *profile, struct path *path) +{ + return profile->path_flags | + S_ISDIR(path->dentry->d_inode->i_mode) ? PATH_IS_DIR : 0; +} + +int aa_remount(struct aa_profile *profile, struct path *path, + unsigned long flags, void *data) +{ + struct file_perms perms = { }; + const char *name, *info = NULL; + char *buffer = NULL; + int binary, error; + + binary = path->dentry->d_sb->s_type->fs_flags & FS_BINARY_MOUNTDATA; + + error = aa_path_name(path, path_flags(profile, path), &buffer, &name, + &info); + if (error) + goto audit; + + error = match_mnt(profile, name, NULL, NULL, flags, data, binary, + &perms, &info); + +audit: + error = audit_mount(profile, GFP_KERNEL, OP_MOUNT, name, NULL, NULL, + NULL, flags, data, AA_MAY_MOUNT, &perms, info, + error); + kfree(buffer); + + return error; +} + +int aa_bind_mount(struct aa_profile *profile, struct path *path, + const char *dev_name, unsigned long flags) +{ + struct file_perms perms = { }; + char *buffer = NULL, *old_buffer = NULL; + const char *name, *old_name = NULL, *info = NULL; + struct path old_path; + int error; + + if (!dev_name || !*dev_name) + return -EINVAL; + + flags &= MS_REC | MS_BIND; + + error = aa_path_name(path, path_flags(profile, path), &buffer, &name, + &info); + if (error) + goto audit; + + error = kern_path(dev_name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &old_path); + if (error) + goto audit; + + error = aa_path_name(&old_path, path_flags(profile, &old_path), + &old_buffer, &old_name, &info); + path_put(&old_path); + if (error) + goto audit; + + error = match_mnt(profile, name, old_name, NULL, flags, NULL, 0, + &perms, &info); + +audit: + error = audit_mount(profile, GFP_KERNEL, OP_MOUNT, name, old_name, + NULL, NULL, flags, NULL, AA_MAY_MOUNT, &perms, + info, error); + kfree(buffer); + kfree(old_buffer); + + return error; +} + +int aa_mount_change_type(struct aa_profile *profile, struct path *path, + unsigned long flags) +{ + struct file_perms perms = { }; + char *buffer = NULL; + const char *name, *info = NULL; + int error; + + /* These are the flags allowed by do_change_type() */ + flags &= (MS_REC | MS_SILENT | MS_SHARED | MS_PRIVATE | MS_SLAVE | + MS_UNBINDABLE); + + error = aa_path_name(path, path_flags(profile, path), &buffer, &name, + &info); + if (error) + goto audit; + + error = match_mnt(profile, name, NULL, NULL, flags, NULL, 0, &perms, + &info); + +audit: + error = audit_mount(profile, GFP_KERNEL, OP_MOUNT, name, NULL, NULL, + NULL, flags, NULL, AA_MAY_MOUNT, &perms, info, + error); + kfree(buffer); + + return error; +} + +int aa_move_mount(struct aa_profile *profile, struct path *path, + const char *orig_name) +{ + struct file_perms perms = { }; + char *buffer = NULL, *old_buffer = NULL; + const char *name, *old_name = NULL, *info = NULL; + struct path old_path; + int error; + + if (!orig_name || !*orig_name) + return -EINVAL; + + error = aa_path_name(path, path_flags(profile, path), &buffer, &name, + &info); + if (error) + goto audit; + + error = kern_path(orig_name, LOOKUP_FOLLOW, &old_path); + if (error) + goto audit; + + error = aa_path_name(&old_path, path_flags(profile, &old_path), + &old_buffer, &old_name, &info); + path_put(&old_path); + if (error) + goto audit; + + error = match_mnt(profile, name, old_name, NULL, MS_MOVE, NULL, 0, + &perms, &info); + +audit: + error = audit_mount(profile, GFP_KERNEL, OP_MOUNT, name, old_name, + NULL, NULL, MS_MOVE, NULL, AA_MAY_MOUNT, &perms, + info, error); + kfree(buffer); + kfree(old_buffer); + + return error; +} + +int aa_new_mount(struct aa_profile *profile, const char *orig_dev_name, + struct path *path, const char *type, unsigned long flags, + void *data) +{ + struct file_perms perms = { }; + char *buffer = NULL, *dev_buffer = NULL; + const char *name = NULL, *dev_name = NULL, *info = NULL; + int binary = 1; + int error; + + dev_name = orig_dev_name; + if (type) { + int requires_dev; + struct file_system_type *fstype = get_fs_type(type); + if (!fstype) + return -ENODEV; + + binary = fstype->fs_flags & FS_BINARY_MOUNTDATA; + requires_dev = fstype->fs_flags & FS_REQUIRES_DEV; + put_filesystem(fstype); + + if (requires_dev) { + struct path dev_path; + + if (!dev_name || !*dev_name) { + error = -ENOENT; + goto out; + } + + error = kern_path(dev_name, LOOKUP_FOLLOW, &dev_path); + if (error) + goto audit; + + error = aa_path_name(&dev_path, + path_flags(profile, &dev_path), + &dev_buffer, &dev_name, &info); + path_put(&dev_path); + if (error) + goto audit; + } + } + + error = aa_path_name(path, path_flags(profile, path), &buffer, &name, + &info); + if (error) + goto audit; + + error = match_mnt(profile, name, dev_name, type, flags, data, binary, + &perms, &info); + +audit: + error = audit_mount(profile, GFP_KERNEL, OP_MOUNT, name, dev_name, + type, NULL, flags, data, AA_MAY_MOUNT, &perms, info, + error); + kfree(buffer); + kfree(dev_buffer); + +out: + return error; + +} + +int aa_umount(struct aa_profile *profile, struct vfsmount *mnt, int flags) +{ + struct file_perms perms = { }; + char *buffer = NULL; + const char *name, *info = NULL; + int error; + + struct path path = { mnt, mnt->mnt_root }; + error = aa_path_name(&path, path_flags(profile, &path), &buffer, &name, + &info); + if (error) + goto audit; + + if (!error && profile->policy.dfa) { + unsigned int state; + state = aa_dfa_match(profile->policy.dfa, + profile->policy.start[AA_CLASS_MOUNT], + name); + perms = compute_mnt_perms(profile->policy.dfa, state); + } + + if (AA_MAY_UMOUNT & ~perms.allow) + error = -EACCES; + +audit: + error = audit_mount(profile, GFP_KERNEL, OP_UMOUNT, name, NULL, NULL, + NULL, 0, NULL, AA_MAY_UMOUNT, &perms, info, error); + kfree(buffer); + + return error; +} + +int aa_pivotroot(struct aa_profile *profile, struct path *old_path, + struct path *new_path) +{ + struct file_perms perms = { }; + struct aa_profile *target = NULL; + char *old_buffer = NULL, *new_buffer = NULL; + const char *old_name, *new_name = NULL, *info = NULL; + int error; + + error = aa_path_name(old_path, path_flags(profile, old_path), + &old_buffer, &old_name, &info); + if (error) + goto audit; + + error = aa_path_name(new_path, path_flags(profile, new_path), + &new_buffer, &new_name, &info); + if (error) + goto audit; + + if (profile->policy.dfa) { + unsigned int state; + state = aa_dfa_match(profile->policy.dfa, + profile->policy.start[AA_CLASS_MOUNT], + new_name); + state = aa_dfa_null_transition(profile->policy.dfa, state); + state = aa_dfa_match(profile->policy.dfa, state, old_name); + perms = compute_mnt_perms(profile->policy.dfa, state); + } + + if (AA_MAY_PIVOTROOT & perms.allow) { + if ((perms.xindex & AA_X_TYPE_MASK) == AA_X_TABLE) { + target = x_table_lookup(profile, perms.xindex); + if (!target) + error = -ENOENT; + else + error = aa_replace_current_profile(target); + } + } else + error = -EACCES; + +audit: + error = audit_mount(profile, GFP_KERNEL, OP_PIVOTROOT, new_name, + old_name, NULL, target ? target->base.name : NULL, + 0, NULL, AA_MAY_PIVOTROOT, &perms, info, error); + aa_put_profile(target); + kfree(old_buffer); + kfree(new_buffer); + + return error; +} diff --git a/security/apparmor/net.c b/security/apparmor/net.c new file mode 100644 index 000000000000..003dd18c61a5 --- /dev/null +++ b/security/apparmor/net.c @@ -0,0 +1,162 @@ +/* + * AppArmor security module + * + * This file contains AppArmor network mediation + * + * Copyright (C) 1998-2008 Novell/SUSE + * Copyright 2009-2012 Canonical Ltd. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation, version 2 of the + * License. + */ + +#include "include/apparmor.h" +#include "include/audit.h" +#include "include/context.h" +#include "include/net.h" +#include "include/policy.h" + +#include "net_names.h" + +struct aa_fs_entry aa_fs_entry_network[] = { + AA_FS_FILE_STRING("af_mask", AA_FS_AF_MASK), + { } +}; + +/* audit callback for net specific fields */ +static void audit_cb(struct audit_buffer *ab, void *va) +{ + struct common_audit_data *sa = va; + + audit_log_format(ab, " family="); + if (address_family_names[sa->u.net->family]) { + audit_log_string(ab, address_family_names[sa->u.net->family]); + } else { + audit_log_format(ab, "\"unknown(%d)\"", sa->u.net->family); + } + audit_log_format(ab, " sock_type="); + if (sock_type_names[sa->aad->net.type]) { + audit_log_string(ab, sock_type_names[sa->aad->net.type]); + } else { + audit_log_format(ab, "\"unknown(%d)\"", sa->aad->net.type); + } + audit_log_format(ab, " protocol=%d", sa->aad->net.protocol); +} + +/** + * audit_net - audit network access + * @profile: profile being enforced (NOT NULL) + * @op: operation being checked + * @family: network family + * @type: network type + * @protocol: network protocol + * @sk: socket auditing is being applied to + * @error: error code for failure else 0 + * + * Returns: %0 or sa->error else other errorcode on failure + */ +static int audit_net(struct aa_profile *profile, int op, u16 family, int type, + int protocol, struct sock *sk, int error) +{ + int audit_type = AUDIT_APPARMOR_AUTO; + struct common_audit_data sa; + struct apparmor_audit_data aad = { }; + struct lsm_network_audit net = { }; + if (sk) { + sa.type = LSM_AUDIT_DATA_NET; + } else { + sa.type = LSM_AUDIT_DATA_NONE; + } + /* todo fill in socket addr info */ + sa.aad = &aad; + sa.u.net = &net; + sa.aad->op = op, + sa.u.net->family = family; + sa.u.net->sk = sk; + sa.aad->net.type = type; + sa.aad->net.protocol = protocol; + sa.aad->error = error; + + if (likely(!sa.aad->error)) { + u16 audit_mask = profile->net.audit[sa.u.net->family]; + if (likely((AUDIT_MODE(profile) != AUDIT_ALL) && + !(1 << sa.aad->net.type & audit_mask))) + return 0; + audit_type = AUDIT_APPARMOR_AUDIT; + } else { + u16 quiet_mask = profile->net.quiet[sa.u.net->family]; + u16 kill_mask = 0; + u16 denied = (1 << sa.aad->net.type) & ~quiet_mask; + + if (denied & kill_mask) + audit_type = AUDIT_APPARMOR_KILL; + + if ((denied & quiet_mask) && + AUDIT_MODE(profile) != AUDIT_NOQUIET && + AUDIT_MODE(profile) != AUDIT_ALL) + return COMPLAIN_MODE(profile) ? 0 : sa.aad->error; + } + + return aa_audit(audit_type, profile, GFP_KERNEL, &sa, audit_cb); +} + +/** + * aa_net_perm - very course network access check + * @op: operation being checked + * @profile: profile being enforced (NOT NULL) + * @family: network family + * @type: network type + * @protocol: network protocol + * + * Returns: %0 else error if permission denied + */ +int aa_net_perm(int op, struct aa_profile *profile, u16 family, int type, + int protocol, struct sock *sk) +{ + u16 family_mask; + int error; + + if ((family < 0) || (family >= AF_MAX)) + return -EINVAL; + + if ((type < 0) || (type >= SOCK_MAX)) + return -EINVAL; + + /* unix domain and netlink sockets are handled by ipc */ + if (family == AF_UNIX || family == AF_NETLINK) + return 0; + + family_mask = profile->net.allow[family]; + + error = (family_mask & (1 << type)) ? 0 : -EACCES; + + return audit_net(profile, op, family, type, protocol, sk, error); +} + +/** + * aa_revalidate_sk - Revalidate access to a sock + * @op: operation being checked + * @sk: sock being revalidated (NOT NULL) + * + * Returns: %0 else error if permission denied + */ +int aa_revalidate_sk(int op, struct sock *sk) +{ + struct aa_profile *profile; + int error = 0; + + /* aa_revalidate_sk should not be called from interrupt context + * don't mediate these calls as they are not task related + */ + if (in_interrupt()) + return 0; + + profile = __aa_current_profile(); + if (!unconfined(profile)) + error = aa_net_perm(op, profile, sk->sk_family, sk->sk_type, + sk->sk_protocol, sk); + + return error; +} diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c index cf5fd220309b..27c8161691ba 100644 --- a/security/apparmor/policy.c +++ b/security/apparmor/policy.c @@ -745,6 +745,7 @@ static void free_profile(struct aa_profile *profile) aa_free_file_rules(&profile->file); aa_free_cap_rules(&profile->caps); + aa_free_net_rules(&profile->net); aa_free_rlimit_rules(&profile->rlimits); aa_free_sid(profile->sid); diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c index 329b1fd30749..1b90dfaa5517 100644 --- a/security/apparmor/policy_unpack.c +++ b/security/apparmor/policy_unpack.c @@ -193,6 +193,19 @@ fail: return 0; } +static bool unpack_u16(struct aa_ext *e, u16 *data, const char *name) +{ + if (unpack_nameX(e, AA_U16, name)) { + if (!inbounds(e, sizeof(u16))) + return 0; + if (data) + *data = le16_to_cpu(get_unaligned((u16 *) e->pos)); + e->pos += sizeof(u16); + return 1; + } + return 0; +} + static bool unpack_u32(struct aa_ext *e, u32 *data, const char *name) { if (unpack_nameX(e, AA_U32, name)) { @@ -471,6 +484,7 @@ static struct aa_profile *unpack_profile(struct aa_ext *e) { struct aa_profile *profile = NULL; const char *name = NULL; + size_t size = 0; int i, error = -EPROTO; kernel_cap_t tmpcap; u32 tmp; @@ -564,6 +578,38 @@ static struct aa_profile *unpack_profile(struct aa_ext *e) if (!unpack_rlimits(e, profile)) goto fail; + size = unpack_array(e, "net_allowed_af"); + if (size) { + + for (i = 0; i < size; i++) { + /* discard extraneous rules that this kernel will + * never request + */ + if (i >= AF_MAX) { + u16 tmp; + if (!unpack_u16(e, &tmp, NULL) || + !unpack_u16(e, &tmp, NULL) || + !unpack_u16(e, &tmp, NULL)) + goto fail; + continue; + } + if (!unpack_u16(e, &profile->net.allow[i], NULL)) + goto fail; + if (!unpack_u16(e, &profile->net.audit[i], NULL)) + goto fail; + if (!unpack_u16(e, &profile->net.quiet[i], NULL)) + goto fail; + } + if (!unpack_nameX(e, AA_ARRAYEND, NULL)) + goto fail; + } + /* + * allow unix domain and netlink sockets they are handled + * by IPC + */ + profile->net.allow[AF_UNIX] = 0xffff; + profile->net.allow[AF_NETLINK] = 0xffff; + if (unpack_nameX(e, AA_STRUCT, "policydb")) { /* generic policy dfa - optional and may be NULL */ profile->policy.dfa = unpack_dfa(e); diff --git a/security/commoncap.c b/security/commoncap.c index 8b431e4e5916..107919d99b08 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -996,3 +996,5 @@ int cap_mmap_file(struct file *file, unsigned long reqprot, { return 0; } + +EXPORT_SYMBOL(cap_mmap_file); diff --git a/security/device_cgroup.c b/security/device_cgroup.c index 442204cc22d9..74aa1f9ac7ad 100644 --- a/security/device_cgroup.c +++ b/security/device_cgroup.c @@ -13,6 +13,7 @@ #include <linux/slab.h> #include <linux/rcupdate.h> #include <linux/mutex.h> +#include <linux/export.h> #define ACC_MKNOD 1 #define ACC_READ 2 @@ -493,6 +494,7 @@ found: return -EPERM; } +EXPORT_SYMBOL(__devcgroup_inode_permission); int devcgroup_inode_mknod(int mode, dev_t dev) { diff --git a/security/security.c b/security/security.c index 3efc9b12aef4..7fb3683fdad9 100644 --- a/security/security.c +++ b/security/security.c @@ -135,6 +135,10 @@ int __init register_security(struct security_operations *ops) int security_ptrace_access_check(struct task_struct *child, unsigned int mode) { + int rc; + rc = yama_ptrace_access_check(child, mode); + if (rc) + return rc; return security_ops->ptrace_access_check(child, mode); } @@ -383,6 +387,7 @@ int security_path_rmdir(struct path *dir, struct dentry *dentry) return 0; return security_ops->path_rmdir(dir, dentry); } +EXPORT_SYMBOL(security_path_rmdir); int security_path_unlink(struct path *dir, struct dentry *dentry) { @@ -399,14 +404,20 @@ int security_path_symlink(struct path *dir, struct dentry *dentry, return 0; return security_ops->path_symlink(dir, dentry, old_name); } +EXPORT_SYMBOL(security_path_symlink); int security_path_link(struct dentry *old_dentry, struct path *new_dir, struct dentry *new_dentry) { + int rc; if (unlikely(IS_PRIVATE(old_dentry->d_inode))) return 0; + rc = yama_path_link(old_dentry, new_dir, new_dentry); + if (rc) + return rc; return security_ops->path_link(old_dentry, new_dir, new_dentry); } +EXPORT_SYMBOL(security_path_link); int security_path_rename(struct path *old_dir, struct dentry *old_dentry, struct path *new_dir, struct dentry *new_dentry) @@ -425,6 +436,7 @@ int security_path_truncate(struct path *path) return 0; return security_ops->path_truncate(path); } +EXPORT_SYMBOL(security_path_truncate); int security_path_chmod(struct path *path, umode_t mode) { @@ -432,6 +444,7 @@ int security_path_chmod(struct path *path, umode_t mode) return 0; return security_ops->path_chmod(path, mode); } +EXPORT_SYMBOL(security_path_chmod); int security_path_chown(struct path *path, uid_t uid, gid_t gid) { @@ -439,6 +452,7 @@ int security_path_chown(struct path *path, uid_t uid, gid_t gid) return 0; return security_ops->path_chown(path, uid, gid); } +EXPORT_SYMBOL(security_path_chown); int security_path_chroot(struct path *path) { @@ -515,11 +529,16 @@ int security_inode_readlink(struct dentry *dentry) return 0; return security_ops->inode_readlink(dentry); } +EXPORT_SYMBOL(security_inode_readlink); int security_inode_follow_link(struct dentry *dentry, struct nameidata *nd) { + int rc; if (unlikely(IS_PRIVATE(dentry->d_inode))) return 0; + rc = yama_inode_follow_link(dentry, nd); + if (rc) + return rc; return security_ops->inode_follow_link(dentry, nd); } @@ -529,6 +548,7 @@ int security_inode_permission(struct inode *inode, int mask) return 0; return security_ops->inode_permission(inode, mask); } +EXPORT_SYMBOL(security_inode_permission); int security_inode_setattr(struct dentry *dentry, struct iattr *attr) { @@ -644,6 +664,7 @@ int security_file_permission(struct file *file, int mask) return fsnotify_perm(file, mask); } +EXPORT_SYMBOL(security_file_permission); int security_file_alloc(struct file *file) { @@ -704,6 +725,7 @@ int security_mmap_file(struct file *file, unsigned long prot, return ret; return ima_file_mmap(file, prot); } +EXPORT_SYMBOL(security_mmap_file); int security_mmap_addr(unsigned long addr) { @@ -760,6 +782,7 @@ int security_task_create(unsigned long clone_flags) void security_task_free(struct task_struct *task) { + yama_task_free(task); security_ops->task_free(task); } @@ -875,6 +898,10 @@ int security_task_wait(struct task_struct *p) int security_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { + int rc; + rc = yama_task_prctl(option, arg2, arg3, arg4, arg5); + if (rc != -ENOSYS) + return rc; return security_ops->task_prctl(option, arg2, arg3, arg4, arg5); } diff --git a/security/yama/Kconfig b/security/yama/Kconfig index 51d6709d8bbd..1a5d1c1a7db4 100644 --- a/security/yama/Kconfig +++ b/security/yama/Kconfig @@ -7,7 +7,8 @@ config SECURITY_YAMA help This selects Yama, which extends DAC support with additional system-wide security settings beyond regular Linux discretionary - access controls. Currently available is ptrace scope restriction. - Further information can be found in Documentation/security/Yama.txt. + access controls. Currently available are symlink, hardlink, and + ptrace scope restrictions. Further information can be found in + Documentation/security/Yama.txt. If you are unsure how to answer this question, answer N. diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c index 83554ee8a587..8694b0e3f8e1 100644 --- a/security/yama/yama_lsm.c +++ b/security/yama/yama_lsm.c @@ -17,6 +17,9 @@ #include <linux/ptrace.h> #include <linux/prctl.h> #include <linux/ratelimit.h> +#include <linux/stat.h> +#include <linux/dcache.h> +#include <linux/fs.h> #define YAMA_SCOPE_DISABLED 0 #define YAMA_SCOPE_RELATIONAL 1 @@ -24,6 +27,8 @@ #define YAMA_SCOPE_NO_ATTACH 3 static int ptrace_scope = YAMA_SCOPE_RELATIONAL; +static int protected_sticky_symlinks = 1; +static int protected_nonaccess_hardlinks = 1; /* describe a ptrace relationship for potential exception */ struct ptrace_relation { @@ -100,7 +105,7 @@ static void yama_ptracer_del(struct task_struct *tracer, * yama_task_free - check for task_pid to remove from exception list * @task: task being removed */ -static void yama_task_free(struct task_struct *task) +void yama_task_free(struct task_struct *task) { yama_ptracer_del(task, task); } @@ -116,7 +121,7 @@ static void yama_task_free(struct task_struct *task) * Return 0 on success, -ve on error. -ENOSYS is returned when Yama * does not handle the given option. */ -static int yama_task_prctl(int option, unsigned long arg2, unsigned long arg3, +int yama_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { int rc; @@ -243,7 +248,7 @@ static int ptracer_exception_found(struct task_struct *tracer, * * Returns 0 if following the ptrace is allowed, -ve on error. */ -static int yama_ptrace_access_check(struct task_struct *child, +int yama_ptrace_access_check(struct task_struct *child, unsigned int mode) { int rc; @@ -290,13 +295,118 @@ static int yama_ptrace_access_check(struct task_struct *child, return rc; } -static struct security_operations yama_ops = { - .name = "yama", +/** + * yama_inode_follow_link - check for symlinks in sticky world-writeable dirs + * @dentry: The inode/dentry of the symlink + * @nameidata: The path data of the symlink + * + * In the case of the protected_sticky_symlinks sysctl being enabled, + * CAP_DAC_OVERRIDE needs to be specifically ignored if the symlink is + * in a sticky world-writable directory. This is to protect privileged + * processes from failing races against path names that may change out + * from under them by way of other users creating malicious symlinks. + * It will permit symlinks to only be followed when outside a sticky + * world-writable directory, or when the uid of the symlink and follower + * match, or when the directory owner matches the symlink's owner. + * + * Returns 0 if following the symlink is allowed, -ve on error. + */ +int yama_inode_follow_link(struct dentry *dentry, + struct nameidata *nameidata) +{ + int rc = 0; + const struct inode *parent; + const struct inode *inode; + const struct cred *cred; - .ptrace_access_check = yama_ptrace_access_check, - .task_prctl = yama_task_prctl, - .task_free = yama_task_free, -}; + if (!protected_sticky_symlinks) + return 0; + + /* if inode isn't a symlink, don't try to evaluate blocking it */ + inode = dentry->d_inode; + if (!S_ISLNK(inode->i_mode)) + return 0; + + /* owner and follower match? */ + cred = current_cred(); + if (cred->fsuid == inode->i_uid) + return 0; + + /* check parent directory mode and owner */ + spin_lock(&dentry->d_lock); + parent = dentry->d_parent->d_inode; + if ((parent->i_mode & (S_ISVTX|S_IWOTH)) == (S_ISVTX|S_IWOTH) && + parent->i_uid != inode->i_uid) { + rc = -EACCES; + } + spin_unlock(&dentry->d_lock); + + if (rc) { + char name[sizeof(current->comm)]; + printk_ratelimited(KERN_NOTICE "non-matching-uid symlink " + "following attempted in sticky world-writable " + "directory by %s (fsuid %d != %d)\n", + get_task_comm(name, current), + cred->fsuid, inode->i_uid); + } + + return rc; +} + +static int yama_generic_permission(struct inode *inode, int mask) +{ + int retval; + + if (inode->i_op->permission) + retval = inode->i_op->permission(inode, mask); + else + retval = generic_permission(inode, mask); + return retval; +} + +/** + * yama_path_link - verify that hardlinking is allowed + * @old_dentry: the source inode/dentry to hardlink from + * @new_dir: target directory + * @new_dentry: the target inode/dentry to hardlink to + * + * Block hardlink when all of: + * - fsuid does not match inode + * - not CAP_FOWNER + * - and at least one of: + * - inode is not a regular file + * - inode is setuid + * - inode is setgid and group-exec + * - access failure for read and write + * + * Returns 0 if successful, -ve on error. + */ +int yama_path_link(struct dentry *old_dentry, struct path *new_dir, + struct dentry *new_dentry) +{ + int rc = 0; + struct inode *inode = old_dentry->d_inode; + const int mode = inode->i_mode; + const struct cred *cred = current_cred(); + + if (!protected_nonaccess_hardlinks) + return 0; + + if (cred->fsuid != inode->i_uid && + (!S_ISREG(mode) || (mode & S_ISUID) || + ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) || + (yama_generic_permission(inode, MAY_READ | MAY_WRITE))) && + !capable(CAP_FOWNER)) { + char name[sizeof(current->comm)]; + printk_ratelimited(KERN_NOTICE "non-accessible hardlink" + " creation was attempted by: %s (fsuid %d)\n", + get_task_comm(name, current), + cred->fsuid); + rc = -EPERM; + } + + return rc; +} #ifdef CONFIG_SYSCTL static int yama_dointvec_minmax(struct ctl_table *table, int write, @@ -329,6 +439,24 @@ struct ctl_path yama_sysctl_path[] = { static struct ctl_table yama_sysctl_table[] = { { + .procname = "protected_sticky_symlinks", + .data = &protected_sticky_symlinks, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &max_scope, + }, + { + .procname = "protected_nonaccess_hardlinks", + .data = &protected_nonaccess_hardlinks, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &max_scope, + }, + { .procname = "ptrace_scope", .data = &ptrace_scope, .maxlen = sizeof(int), @@ -343,14 +471,8 @@ static struct ctl_table yama_sysctl_table[] = { static __init int yama_init(void) { - if (!security_module_enable(&yama_ops)) - return 0; - printk(KERN_INFO "Yama: becoming mindful.\n"); - if (register_security(&yama_ops)) - panic("Yama: kernel registration failed.\n"); - #ifdef CONFIG_SYSCTL if (!register_sysctl_paths(yama_sysctl_path, yama_sysctl_table)) panic("Yama: sysctl registration failed.\n"); diff --git a/tools/hv/Makefile b/tools/hv/Makefile new file mode 100644 index 000000000000..ef87f85849dc --- /dev/null +++ b/tools/hv/Makefile @@ -0,0 +1,7 @@ +hv_kvp_daemon: hv_kvp_daemon.c + +clean: + rm -f hv_kvp_daemon + +install: + install hv_kvp_daemon /usr/sbin/ diff --git a/tools/hv/hv_kvp_daemon.8 b/tools/hv/hv_kvp_daemon.8 new file mode 100644 index 000000000000..0fb4577a1f07 --- /dev/null +++ b/tools/hv/hv_kvp_daemon.8 @@ -0,0 +1,26 @@ +.\" This page Copyright (C) 2012 Andy Whitcroft <apw@canonical.com> +.\" Distributed under the GPL v2 or later. +.TH HV_KVP_DAEMON 8 +.SH NAME +hv_kvp_daemon \- Hyper-V Key Value Pair daemon +.SH SYNOPSIS +.ft B +.B hv_kvp_daemon +.br +.SH DESCRIPTION +\fBhv_kvp_daemon\fP +is the userspace component of the Hyper-V key value pair functionality, +communicating via a netlink socket with the kernel HV-KVP driver. +This pairing allows the Hyper-V host to pass configuration information +(such as IP addresses) to the guest and allows the host to obtain guest +version information. + +.SH FILES +.ta +.nf +/var/opt/hyperv/.kvp_pool_* +.fi + +.SH AUTHORS +.nf +Written by K. Y. Srinivasan <ksrinivasan@novell.com> diff --git a/ubuntu/Kconfig b/ubuntu/Kconfig new file mode 100644 index 000000000000..faedd0bbc16b --- /dev/null +++ b/ubuntu/Kconfig @@ -0,0 +1,22 @@ +menu "Ubuntu Supplied Third-Party Device Drivers" + +# +# NOTE: to allow drivers to be added and removed without causing merge +# collisions you should add new entries in the middle of the six lines +# of ## at the bottom of the list. Always add three lines of ## above +# your new entry and maintain the six lines below. +# + +## +## +## +source "ubuntu/dm-raid4-5/Kconfig" +## +## +## +## +## +source "ubuntu/aufs/Kconfig" +## + +endmenu diff --git a/ubuntu/Makefile b/ubuntu/Makefile new file mode 100644 index 000000000000..997d9b990f1b --- /dev/null +++ b/ubuntu/Makefile @@ -0,0 +1,28 @@ +# +# Makefile for the Linux kernel ubuntu supplied third-party device drivers. +# + +# +# NOTE: to allow drivers to be added and removed without causing merge +# collisions you should add new entries in the middle of the six lines +# of ## at the bottom of the list. Always add three lines of ## above +# your new entry and maintain the six lines below. +# + +## +## +## +obj-$(CONFIG_DM_RAID45) += dm-raid4-5/ +## +## +## +## +## +## +#obj-$(CONFIG_AUFS_FS) += aufs/ +## +## +## + +# This is a stupid trick to get kbuild to create ubuntu/built-in.o +obj- += foo.o diff --git a/ubuntu/aufs-update b/ubuntu/aufs-update new file mode 100755 index 000000000000..a31cf944d7ff --- /dev/null +++ b/ubuntu/aufs-update @@ -0,0 +1,51 @@ +#!/bin/bash +# +# NOTE: See aufs/BOM.UPDATING for instructions on how to use this updater. +# + +if [ "$#" -ne 1 ]; then + echo "Usage: $0 <aufs2-standalone directory>" 1>&2 + exit 1 +fi +aufs="$1" + +# Get the current tip name +{ + read x url + read x o_log_sha1 + read x o_tip_sha1 +} <aufs/BOM + +# Identify the tip of the standalone tree for reporting +n_tip_sha1=`( cd "$aufs" && git log --format=%H HEAD^..HEAD )` + +# Update aufs to the latest. +git rm -rf aufs +cp -rp "$aufs/fs/aufs" aufs +#cp -rp "$aufs/include" aufs +cp -rp "$aufs/include/linux"/*.h include/linux +git checkout -f HEAD -- aufs/BOM aufs/BOM.UPDATING + +# Reinsert the include update. +#sed -i -e '1iEXTRA_CFLAGS += -I$(src)/include' aufs/Makefile + +# Fix the relative patch references ... +sed -i -e 's@/include/@/ubuntu/include/@g;' aufs/Makefile + +## # Find the latest commit in the ChangeLog. +## read x n_log_sha1 <"$aufs/ChangeLog" + +# Insert the new commit ID and commit the result. +sed -i -e "s/^COMMIT: .*/COMMIT: $n_tip_sha1/" aufs/BOM +sed -i -e "s/^CHANGELOG: .*/CHANGELOG: $n_log_sha1/" aufs/BOM + +git add aufs include/linux +{ + echo "UBUNTU: ubuntu: AUFS -- update to $n_tip_sha1" + echo "" + (cd "$aufs" && git log --no-merges "$o_tip_sha1..$n_tip_sha1" | git shortlog) +## awk <"$aufs/ChangeLog" ' +## /^commit '"$o_log_sha1"'/ { exit } +## { print " " $0 } +## ' +} | git commit -s -F - diff --git a/ubuntu/aufs/BOM b/ubuntu/aufs/BOM new file mode 100644 index 000000000000..f549f2e3ea1b --- /dev/null +++ b/ubuntu/aufs/BOM @@ -0,0 +1,3 @@ +URL: git://aufs.git.sourceforge.net/gitroot/aufs/aufs3-standalone.git +CHANGELOG: +COMMIT: d266b0c5d0693d6383976ee54b9e2c0fa9a3f5b0 diff --git a/ubuntu/aufs/BOM.UPDATING b/ubuntu/aufs/BOM.UPDATING new file mode 100644 index 000000000000..e2975b3ddf18 --- /dev/null +++ b/ubuntu/aufs/BOM.UPDATING @@ -0,0 +1,80 @@ += How to update AUFS2 = + +This document covers the process for updating aufs2 within the Ubuntu +drivers directory. + +== Background == + +Upstream aufs2 is maintained in a git tree as below (which is _not_ used +when updating Ubuntu). This represents the primary upstream source tree: + + http://git.c3sl.ufpr.br/pub/scm/aufs/aufs2-2.6.git + +However this is on an http: transport and incredibly slow. It is advisable +to also add the gitorius mirror to your tree, fetching that before origin +to reduce the objects you need from the main tree: + + git://gitorious.org/aufs2/aufs2.git + +Ubuntu updates are actually taken from the aufs2-standalone tree, somewhat +similar to the compat-wireless tree. The version in this tree is based on +the mainline tree above but is modularisable, a key requirement for Ubuntu. +This tree is found at the git tree below (check the BOM for the definative +location): + + http://git.c3sl.ufpr.br/pub/scm/aufs/aufs2-standalone.git + +This tree contains a set of branches, one per upstream release. The +aufs2.1 branch represents the mainline tracking branch, with aufs-2.1-38 +representing the delta to mainline 2.6.38. Each branch contains a set +of patches which affect the core enabling the application of aufs2, plus +an open tree for the fs/aufs tree. The core patches tend to be static +from early in the line of an upstream release, and thus generally do not +need updating as often. + +== Updating the core patches == + +Ubuntu uses two of the core enablement patches, which are applied in the +order below. The remaining changes required to enable aufs are Ubuntu +specific and static: + + aufs2-base.patch + aufs2-standalone.patch + +In order to update these patches it is simplest to simply revert the +existing pair and apply these as two commit. This allows us to more +easily drop aufs in the future should that be required. + +As these core enablement patches are very slow in changing we normally +do not need to update these more than once per upstream mainline release +though sometimes changes do affect these. + +== Updating aufs2 == + +Once the enablement patches are updated we can simply use the aufs-update +script in the ubuntu/ directory to update the existing source. There are +regular updates to the aufs2 upstream and it is likely we will see updates +there more than once a month. + +Firstly checkout the upstream standalone tree (see the BOM for the +location) and checkout an appropriate branch for the release you are +updating. Then simply run the aufs-update command from within the ubuntu/ +drivers directory, supplying the location of the local aufs2-standalone tree +on the command line: + + cd ubuntu + sh aufs-update ../../aufs2-standalone + +This will result in an update commit containing the updated code and +also updating the BOM. Note that any local modifications are now lost. +Where those exist they should be cherry-picked and then squashed into +the update commit to ensure we retain them. + +== Ubuntu modifications == + +We carry a very small delta to the upstream aufs2 source. Any such changes +need to be cherry-picked from the history and squashed into any update +commit in order to prevent regression. Any current patches are listed below: + +Lucid/Maverick/Natty/Oneiric: + UBUNTU: ubuntu: AUFS -- suppress benign plink warning messages diff --git a/ubuntu/aufs/Kconfig b/ubuntu/aufs/Kconfig new file mode 100644 index 000000000000..7a96cb5c26ba --- /dev/null +++ b/ubuntu/aufs/Kconfig @@ -0,0 +1,203 @@ +config AUFS_FS + tristate "Aufs (Advanced multi layered unification filesystem) support" + depends on EXPERIMENTAL + help + Aufs is a stackable unification filesystem such as Unionfs, + which unifies several directories and provides a merged single + directory. + In the early days, aufs was entirely re-designed and + re-implemented Unionfs Version 1.x series. Introducing many + original ideas, approaches and improvements, it becomes totally + different from Unionfs while keeping the basic features. + +if AUFS_FS +choice + prompt "Maximum number of branches" + default AUFS_BRANCH_MAX_127 + help + Specifies the maximum number of branches (or member directories) + in a single aufs. The larger value consumes more system + resources and has a minor impact to performance. +config AUFS_BRANCH_MAX_127 + bool "127" + help + Specifies the maximum number of branches (or member directories) + in a single aufs. The larger value consumes more system + resources and has a minor impact to performance. +config AUFS_BRANCH_MAX_511 + bool "511" + help + Specifies the maximum number of branches (or member directories) + in a single aufs. The larger value consumes more system + resources and has a minor impact to performance. +config AUFS_BRANCH_MAX_1023 + bool "1023" + help + Specifies the maximum number of branches (or member directories) + in a single aufs. The larger value consumes more system + resources and has a minor impact to performance. +config AUFS_BRANCH_MAX_32767 + bool "32767" + help + Specifies the maximum number of branches (or member directories) + in a single aufs. The larger value consumes more system + resources and has a minor impact to performance. +endchoice + +config AUFS_SBILIST + bool + depends on AUFS_MAGIC_SYSRQ || PROC_FS + default y + help + Automatic configuration for internal use. + When aufs supports Magic SysRq or /proc, enabled automatically. + +config AUFS_HNOTIFY + bool "Detect direct branch access (bypassing aufs)" + help + If you want to modify files on branches directly, eg. bypassing aufs, + and want aufs to detect the changes of them fully, then enable this + option and use 'udba=notify' mount option. + Currently there is only one available configuration, "fsnotify". + It will have a negative impact to the performance. + See detail in aufs.5. + +choice + prompt "method" if AUFS_HNOTIFY + default AUFS_HFSNOTIFY +config AUFS_HFSNOTIFY + bool "fsnotify" + select FSNOTIFY +endchoice + +config AUFS_EXPORT + bool "NFS-exportable aufs" + depends on EXPORTFS + help + If you want to export your mounted aufs via NFS, then enable this + option. There are several requirements for this configuration. + See detail in aufs.5. + +config AUFS_INO_T_64 + bool + depends on AUFS_EXPORT + depends on 64BIT && !(ALPHA || S390) + default y + help + Automatic configuration for internal use. + /* typedef unsigned long/int __kernel_ino_t */ + /* alpha and s390x are int */ + +config AUFS_RDU + bool "Readdir in userspace" + help + Aufs has two methods to provide a merged view for a directory, + by a user-space library and by kernel-space natively. The latter + is always enabled but sometimes large and slow. + If you enable this option, install the library in aufs2-util + package, and set some environment variables for your readdir(3), + then the work will be handled in user-space which generally + shows better performance in most cases. + See detail in aufs.5. + +config AUFS_PROC_MAP + bool "support for /proc/maps and lsof(1)" + depends on PROC_FS + help + When you issue mmap(2) in aufs, it is actually a direct mmap(2) + call to the file on the branch fs since the file in aufs is + purely virtual. And the file path printed in /proc/maps (and + others) will be the path on the branch fs. In most cases, it + does no harm. But some utilities like lsof(1) may confuse since + the utility or user may expect the file path in aufs to be + printed. + To address this issue, aufs provides a patch which introduces a + new member called vm_prfile into struct vm_are_struct. The patch + is meaningless without enabling this configuration since nobody + sets the new vm_prfile member. + If you don't apply the patch, then enabling this configuration + will cause a compile error. + This approach is fragile since if someone else make some changes + around vm_file, then vm_prfile may not work anymore. As a + workaround such case, aufs provides this configuration. If you + disable it, then lsof(1) may produce incorrect result but the + problem will be gone even if the aufs patch is applied (I hope). + +config AUFS_SP_IATTR + bool "Respect the attributes (mtime/ctime mainly) of special files" + help + When you write something to a special file, some attributes of it + (mtime/ctime mainly) may be updated. Generally such updates are + less important (actually some device drivers and NFS ignore + it). But some applications (such like test program) requires + such updates. If you need these updates, then enable this + configuration which introduces some overhead. + Currently this configuration handles FIFO only. + +config AUFS_SHWH + bool "Show whiteouts" + help + If you want to make the whiteouts in aufs visible, then enable + this option and specify 'shwh' mount option. Although it may + sounds like philosophy or something, but in technically it + simply shows the name of whiteout with keeping its behaviour. + +config AUFS_BR_RAMFS + bool "Ramfs (initramfs/rootfs) as an aufs branch" + help + If you want to use ramfs as an aufs branch fs, then enable this + option. Generally tmpfs is recommended. + Aufs prohibited them to be a branch fs by default, because + initramfs becomes unusable after switch_root or something + generally. If you sets initramfs as an aufs branch and boot your + system by switch_root, you will meet a problem easily since the + files in initramfs may be inaccessible. + Unless you are going to use ramfs as an aufs branch fs without + switch_root or something, leave it N. + +config AUFS_BR_FUSE + bool "Fuse fs as an aufs branch" + depends on FUSE_FS + select AUFS_POLL + help + If you want to use fuse-based userspace filesystem as an aufs + branch fs, then enable this option. + It implements the internal poll(2) operation which is + implemented by fuse only (curretnly). + +config AUFS_POLL + bool + help + Automatic configuration for internal use. + +config AUFS_BR_HFSPLUS + bool "Hfsplus as an aufs branch" + depends on HFSPLUS_FS + default y + help + If you want to use hfsplus fs as an aufs branch fs, then enable + this option. This option introduces a small overhead at + copying-up a file on hfsplus. + +config AUFS_BDEV_LOOP + bool + depends on BLK_DEV_LOOP + default y + help + Automatic configuration for internal use. + Convert =[ym] into =y. + +config AUFS_DEBUG + bool "Debug aufs" + help + Enable this to compile aufs internal debug code. + It will have a negative impact to the performance. + +config AUFS_MAGIC_SYSRQ + bool + depends on AUFS_DEBUG && MAGIC_SYSRQ + default y + help + Automatic configuration for internal use. + When aufs supports Magic SysRq, enabled automatically. +endif diff --git a/ubuntu/aufs/Makefile b/ubuntu/aufs/Makefile new file mode 100644 index 000000000000..7e60943ffd4b --- /dev/null +++ b/ubuntu/aufs/Makefile @@ -0,0 +1,42 @@ + +include ${src}/magic.mk +ifeq (${CONFIG_AUFS_FS},m) +include ${src}/conf.mk +endif +-include ${src}/priv_def.mk + +# cf. include/linux/kernel.h +# enable pr_debug +ccflags-y += -DDEBUG +# sparse requires the full pathname +ifdef M +ccflags-y += -include ${M}/../../ubuntu/include/linux/aufs_type.h +else +ccflags-y += -include ${srctree}/ubuntu/include/linux/aufs_type.h +endif + +obj-$(CONFIG_AUFS_FS) += aufs.o +aufs-y := module.o sbinfo.o super.o branch.o xino.o sysaufs.o opts.o \ + wkq.o vfsub.o dcsub.o \ + cpup.o whout.o wbr_policy.o \ + dinfo.o dentry.o \ + dynop.o \ + finfo.o file.o f_op.o \ + dir.o vdir.o \ + iinfo.o inode.o i_op.o i_op_add.o i_op_del.o i_op_ren.o \ + ioctl.o + +# all are boolean +aufs-$(CONFIG_PROC_FS) += procfs.o plink.o +aufs-$(CONFIG_SYSFS) += sysfs.o +aufs-$(CONFIG_DEBUG_FS) += dbgaufs.o +aufs-$(CONFIG_AUFS_BDEV_LOOP) += loop.o +aufs-$(CONFIG_AUFS_HNOTIFY) += hnotify.o +aufs-$(CONFIG_AUFS_HFSNOTIFY) += hfsnotify.o +aufs-$(CONFIG_AUFS_EXPORT) += export.o +aufs-$(CONFIG_AUFS_POLL) += poll.o +aufs-$(CONFIG_AUFS_RDU) += rdu.o +aufs-$(CONFIG_AUFS_SP_IATTR) += f_op_sp.o +aufs-$(CONFIG_AUFS_BR_HFSPLUS) += hfsplus.o +aufs-$(CONFIG_AUFS_DEBUG) += debug.o +aufs-$(CONFIG_AUFS_MAGIC_SYSRQ) += sysrq.o diff --git a/ubuntu/aufs/aufs.h b/ubuntu/aufs/aufs.h new file mode 100644 index 000000000000..33963a85a68c --- /dev/null +++ b/ubuntu/aufs/aufs.h @@ -0,0 +1,60 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * all header files + */ + +#ifndef __AUFS_H__ +#define __AUFS_H__ + +#ifdef __KERNEL__ + +#define AuStub(type, name, body, ...) \ + static inline type name(__VA_ARGS__) { body; } + +#define AuStubVoid(name, ...) \ + AuStub(void, name, , __VA_ARGS__) +#define AuStubInt0(name, ...) \ + AuStub(int, name, return 0, __VA_ARGS__) + +#include "debug.h" + +#include "branch.h" +#include "cpup.h" +#include "dcsub.h" +#include "dbgaufs.h" +#include "dentry.h" +#include "dir.h" +#include "dynop.h" +#include "file.h" +#include "fstype.h" +#include "inode.h" +#include "loop.h" +#include "module.h" +#include "opts.h" +#include "rwsem.h" +#include "spl.h" +#include "super.h" +#include "sysaufs.h" +#include "vfsub.h" +#include "whout.h" +#include "wkq.h" + +#endif /* __KERNEL__ */ +#endif /* __AUFS_H__ */ diff --git a/ubuntu/aufs/branch.c b/ubuntu/aufs/branch.c new file mode 100644 index 000000000000..4cfe9e28e2a7 --- /dev/null +++ b/ubuntu/aufs/branch.c @@ -0,0 +1,1169 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * branch management + */ + +#include <linux/compat.h> +#include <linux/statfs.h> +#include "aufs.h" + +/* + * free a single branch + */ +static void au_br_do_free(struct au_branch *br) +{ + int i; + struct au_wbr *wbr; + struct au_dykey **key; + + au_hnotify_fin_br(br); + + if (br->br_xino.xi_file) + fput(br->br_xino.xi_file); + mutex_destroy(&br->br_xino.xi_nondir_mtx); + + AuDebugOn(atomic_read(&br->br_count)); + + wbr = br->br_wbr; + if (wbr) { + for (i = 0; i < AuBrWh_Last; i++) + dput(wbr->wbr_wh[i]); + AuDebugOn(atomic_read(&wbr->wbr_wh_running)); + AuRwDestroy(&wbr->wbr_wh_rwsem); + } + + key = br->br_dykey; + for (i = 0; i < AuBrDynOp; i++, key++) + if (*key) + au_dy_put(*key); + else + break; + + mntput(br->br_mnt); + kfree(wbr); + kfree(br); +} + +/* + * frees all branches + */ +void au_br_free(struct au_sbinfo *sbinfo) +{ + aufs_bindex_t bmax; + struct au_branch **br; + + AuRwMustWriteLock(&sbinfo->si_rwsem); + + bmax = sbinfo->si_bend + 1; + br = sbinfo->si_branch; + while (bmax--) + au_br_do_free(*br++); +} + +/* + * find the index of a branch which is specified by @br_id. + */ +int au_br_index(struct super_block *sb, aufs_bindex_t br_id) +{ + aufs_bindex_t bindex, bend; + + bend = au_sbend(sb); + for (bindex = 0; bindex <= bend; bindex++) + if (au_sbr_id(sb, bindex) == br_id) + return bindex; + return -1; +} + +/* ---------------------------------------------------------------------- */ + +/* + * add a branch + */ + +static int test_overlap(struct super_block *sb, struct dentry *h_adding, + struct dentry *h_root) +{ + if (unlikely(h_adding == h_root + || au_test_loopback_overlap(sb, h_adding))) + return 1; + if (h_adding->d_sb != h_root->d_sb) + return 0; + return au_test_subdir(h_adding, h_root) + || au_test_subdir(h_root, h_adding); +} + +/* + * returns a newly allocated branch. @new_nbranch is a number of branches + * after adding a branch. + */ +static struct au_branch *au_br_alloc(struct super_block *sb, int new_nbranch, + int perm) +{ + struct au_branch *add_branch; + struct dentry *root; + int err; + + err = -ENOMEM; + root = sb->s_root; + add_branch = kmalloc(sizeof(*add_branch), GFP_NOFS); + if (unlikely(!add_branch)) + goto out; + + err = au_hnotify_init_br(add_branch, perm); + if (unlikely(err)) + goto out_br; + + add_branch->br_wbr = NULL; + if (au_br_writable(perm)) { + /* may be freed separately at changing the branch permission */ + add_branch->br_wbr = kmalloc(sizeof(*add_branch->br_wbr), + GFP_NOFS); + if (unlikely(!add_branch->br_wbr)) + goto out_hnotify; + } + + err = au_sbr_realloc(au_sbi(sb), new_nbranch); + if (!err) + err = au_di_realloc(au_di(root), new_nbranch); + if (!err) + err = au_ii_realloc(au_ii(root->d_inode), new_nbranch); + if (!err) + return add_branch; /* success */ + + kfree(add_branch->br_wbr); + +out_hnotify: + au_hnotify_fin_br(add_branch); +out_br: + kfree(add_branch); +out: + return ERR_PTR(err); +} + +/* + * test if the branch permission is legal or not. + */ +static int test_br(struct inode *inode, int brperm, char *path) +{ + int err; + + err = (au_br_writable(brperm) && IS_RDONLY(inode)); + if (!err) + goto out; + + err = -EINVAL; + pr_err("write permission for readonly mount or inode, %s\n", path); + +out: + return err; +} + +/* + * returns: + * 0: success, the caller will add it + * plus: success, it is already unified, the caller should ignore it + * minus: error + */ +static int test_add(struct super_block *sb, struct au_opt_add *add, int remount) +{ + int err; + aufs_bindex_t bend, bindex; + struct dentry *root; + struct inode *inode, *h_inode; + + root = sb->s_root; + bend = au_sbend(sb); + if (unlikely(bend >= 0 + && au_find_dbindex(root, add->path.dentry) >= 0)) { + err = 1; + if (!remount) { + err = -EINVAL; + pr_err("%s duplicated\n", add->pathname); + } + goto out; + } + + err = -ENOSPC; /* -E2BIG; */ + if (unlikely(AUFS_BRANCH_MAX <= add->bindex + || AUFS_BRANCH_MAX - 1 <= bend)) { + pr_err("number of branches exceeded %s\n", add->pathname); + goto out; + } + + err = -EDOM; + if (unlikely(add->bindex < 0 || bend + 1 < add->bindex)) { + pr_err("bad index %d\n", add->bindex); + goto out; + } + + inode = add->path.dentry->d_inode; + err = -ENOENT; + if (unlikely(!inode->i_nlink)) { + pr_err("no existence %s\n", add->pathname); + goto out; + } + + err = -EINVAL; + if (unlikely(inode->i_sb == sb)) { + pr_err("%s must be outside\n", add->pathname); + goto out; + } + + if (unlikely(au_test_fs_unsuppoted(inode->i_sb))) { + pr_err("unsupported filesystem, %s (%s)\n", + add->pathname, au_sbtype(inode->i_sb)); + goto out; + } + + err = test_br(add->path.dentry->d_inode, add->perm, add->pathname); + if (unlikely(err)) + goto out; + + if (bend < 0) + return 0; /* success */ + + err = -EINVAL; + for (bindex = 0; bindex <= bend; bindex++) + if (unlikely(test_overlap(sb, add->path.dentry, + au_h_dptr(root, bindex)))) { + pr_err("%s is overlapped\n", add->pathname); + goto out; + } + + err = 0; + if (au_opt_test(au_mntflags(sb), WARN_PERM)) { + h_inode = au_h_dptr(root, 0)->d_inode; + if ((h_inode->i_mode & S_IALLUGO) != (inode->i_mode & S_IALLUGO) + || h_inode->i_uid != inode->i_uid + || h_inode->i_gid != inode->i_gid) + pr_warning("uid/gid/perm %s %u/%u/0%o, %u/%u/0%o\n", + add->pathname, + inode->i_uid, inode->i_gid, + (inode->i_mode & S_IALLUGO), + h_inode->i_uid, h_inode->i_gid, + (h_inode->i_mode & S_IALLUGO)); + } + +out: + return err; +} + +/* + * initialize or clean the whiteouts for an adding branch + */ +static int au_br_init_wh(struct super_block *sb, struct au_branch *br, + int new_perm, struct dentry *h_root) +{ + int err, old_perm; + aufs_bindex_t bindex; + struct mutex *h_mtx; + struct au_wbr *wbr; + struct au_hinode *hdir; + + wbr = br->br_wbr; + old_perm = br->br_perm; + br->br_perm = new_perm; + hdir = NULL; + h_mtx = NULL; + bindex = au_br_index(sb, br->br_id); + if (0 <= bindex) { + hdir = au_hi(sb->s_root->d_inode, bindex); + au_hn_imtx_lock_nested(hdir, AuLsc_I_PARENT); + } else { + h_mtx = &h_root->d_inode->i_mutex; + mutex_lock_nested(h_mtx, AuLsc_I_PARENT); + } + if (!wbr) + err = au_wh_init(h_root, br, sb); + else { + wbr_wh_write_lock(wbr); + err = au_wh_init(h_root, br, sb); + wbr_wh_write_unlock(wbr); + } + if (hdir) + au_hn_imtx_unlock(hdir); + else + mutex_unlock(h_mtx); + br->br_perm = old_perm; + + if (!err && wbr && !au_br_writable(new_perm)) { + kfree(wbr); + br->br_wbr = NULL; + } + + return err; +} + +static int au_wbr_init(struct au_branch *br, struct super_block *sb, + int perm, struct path *path) +{ + int err; + struct kstatfs kst; + struct au_wbr *wbr; + struct dentry *h_dentry; + + wbr = br->br_wbr; + au_rw_init(&wbr->wbr_wh_rwsem); + memset(wbr->wbr_wh, 0, sizeof(wbr->wbr_wh)); + atomic_set(&wbr->wbr_wh_running, 0); + wbr->wbr_bytes = 0; + + /* + * a limit for rmdir/rename a dir + * cf. AUFS_MAX_NAMELEN in include/linux/aufs_type.h + */ + err = vfs_statfs(path, &kst); + if (unlikely(err)) + goto out; + err = -EINVAL; + h_dentry = path->dentry; + if (kst.f_namelen >= NAME_MAX) + err = au_br_init_wh(sb, br, perm, h_dentry); + else + pr_err("%.*s(%s), unsupported namelen %ld\n", + AuDLNPair(h_dentry), au_sbtype(h_dentry->d_sb), + kst.f_namelen); + +out: + return err; +} + +/* intialize a new branch */ +static int au_br_init(struct au_branch *br, struct super_block *sb, + struct au_opt_add *add) +{ + int err; + + err = 0; + memset(&br->br_xino, 0, sizeof(br->br_xino)); + mutex_init(&br->br_xino.xi_nondir_mtx); + br->br_perm = add->perm; + br->br_mnt = add->path.mnt; /* set first, mntget() later */ + spin_lock_init(&br->br_dykey_lock); + memset(br->br_dykey, 0, sizeof(br->br_dykey)); + atomic_set(&br->br_count, 0); + br->br_xino_upper = AUFS_XINO_TRUNC_INIT; + atomic_set(&br->br_xino_running, 0); + br->br_id = au_new_br_id(sb); + AuDebugOn(br->br_id < 0); + + if (au_br_writable(add->perm)) { + err = au_wbr_init(br, sb, add->perm, &add->path); + if (unlikely(err)) + goto out_err; + } + + if (au_opt_test(au_mntflags(sb), XINO)) { + err = au_xino_br(sb, br, add->path.dentry->d_inode->i_ino, + au_sbr(sb, 0)->br_xino.xi_file, /*do_test*/1); + if (unlikely(err)) { + AuDebugOn(br->br_xino.xi_file); + goto out_err; + } + } + + sysaufs_br_init(br); + mntget(add->path.mnt); + goto out; /* success */ + +out_err: + br->br_mnt = NULL; +out: + return err; +} + +static void au_br_do_add_brp(struct au_sbinfo *sbinfo, aufs_bindex_t bindex, + struct au_branch *br, aufs_bindex_t bend, + aufs_bindex_t amount) +{ + struct au_branch **brp; + + AuRwMustWriteLock(&sbinfo->si_rwsem); + + brp = sbinfo->si_branch + bindex; + memmove(brp + 1, brp, sizeof(*brp) * amount); + *brp = br; + sbinfo->si_bend++; + if (unlikely(bend < 0)) + sbinfo->si_bend = 0; +} + +static void au_br_do_add_hdp(struct au_dinfo *dinfo, aufs_bindex_t bindex, + aufs_bindex_t bend, aufs_bindex_t amount) +{ + struct au_hdentry *hdp; + + AuRwMustWriteLock(&dinfo->di_rwsem); + + hdp = dinfo->di_hdentry + bindex; + memmove(hdp + 1, hdp, sizeof(*hdp) * amount); + au_h_dentry_init(hdp); + dinfo->di_bend++; + if (unlikely(bend < 0)) + dinfo->di_bstart = 0; +} + +static void au_br_do_add_hip(struct au_iinfo *iinfo, aufs_bindex_t bindex, + aufs_bindex_t bend, aufs_bindex_t amount) +{ + struct au_hinode *hip; + + AuRwMustWriteLock(&iinfo->ii_rwsem); + + hip = iinfo->ii_hinode + bindex; + memmove(hip + 1, hip, sizeof(*hip) * amount); + hip->hi_inode = NULL; + au_hn_init(hip); + iinfo->ii_bend++; + if (unlikely(bend < 0)) + iinfo->ii_bstart = 0; +} + +static void au_br_do_add(struct super_block *sb, struct dentry *h_dentry, + struct au_branch *br, aufs_bindex_t bindex) +{ + struct dentry *root; + struct inode *root_inode; + aufs_bindex_t bend, amount; + + root = sb->s_root; + root_inode = root->d_inode; + bend = au_sbend(sb); + amount = bend + 1 - bindex; + au_sbilist_lock(); + au_br_do_add_brp(au_sbi(sb), bindex, br, bend, amount); + au_br_do_add_hdp(au_di(root), bindex, bend, amount); + au_br_do_add_hip(au_ii(root_inode), bindex, bend, amount); + au_set_h_dptr(root, bindex, dget(h_dentry)); + au_set_h_iptr(root_inode, bindex, au_igrab(h_dentry->d_inode), + /*flags*/0); + au_sbilist_unlock(); +} + +int au_br_add(struct super_block *sb, struct au_opt_add *add, int remount) +{ + int err; + aufs_bindex_t bend, add_bindex; + struct dentry *root, *h_dentry; + struct inode *root_inode; + struct au_branch *add_branch; + + root = sb->s_root; + root_inode = root->d_inode; + IMustLock(root_inode); + err = test_add(sb, add, remount); + if (unlikely(err < 0)) + goto out; + if (err) { + err = 0; + goto out; /* success */ + } + + bend = au_sbend(sb); + add_branch = au_br_alloc(sb, bend + 2, add->perm); + err = PTR_ERR(add_branch); + if (IS_ERR(add_branch)) + goto out; + + err = au_br_init(add_branch, sb, add); + if (unlikely(err)) { + au_br_do_free(add_branch); + goto out; + } + + add_bindex = add->bindex; + h_dentry = add->path.dentry; + if (!remount) + au_br_do_add(sb, h_dentry, add_branch, add_bindex); + else { + sysaufs_brs_del(sb, add_bindex); + au_br_do_add(sb, h_dentry, add_branch, add_bindex); + sysaufs_brs_add(sb, add_bindex); + } + + if (!add_bindex) { + au_cpup_attr_all(root_inode, /*force*/1); + sb->s_maxbytes = h_dentry->d_sb->s_maxbytes; + } else + au_add_nlink(root_inode, h_dentry->d_inode); + + /* + * this test/set prevents aufs from handling unnecesary notify events + * of xino files, in case of re-adding a writable branch which was + * once detached from aufs. + */ + if (au_xino_brid(sb) < 0 + && au_br_writable(add_branch->br_perm) + && !au_test_fs_bad_xino(h_dentry->d_sb) + && add_branch->br_xino.xi_file + && add_branch->br_xino.xi_file->f_dentry->d_parent == h_dentry) + au_xino_brid_set(sb, add_branch->br_id); + +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* + * delete a branch + */ + +/* to show the line number, do not make it inlined function */ +#define AuVerbose(do_info, fmt, ...) do { \ + if (do_info) \ + pr_info(fmt, ##__VA_ARGS__); \ +} while (0) + +static int au_test_ibusy(struct inode *inode, aufs_bindex_t bstart, + aufs_bindex_t bend) +{ + return (inode && !S_ISDIR(inode->i_mode)) || bstart == bend; +} + +static int au_test_dbusy(struct dentry *dentry, aufs_bindex_t bstart, + aufs_bindex_t bend) +{ + return au_test_ibusy(dentry->d_inode, bstart, bend); +} + +/* + * test if the branch is deletable or not. + */ +static int test_dentry_busy(struct dentry *root, aufs_bindex_t bindex, + unsigned int sigen, const unsigned int verbose) +{ + int err, i, j, ndentry; + aufs_bindex_t bstart, bend; + struct au_dcsub_pages dpages; + struct au_dpage *dpage; + struct dentry *d; + + err = au_dpages_init(&dpages, GFP_NOFS); + if (unlikely(err)) + goto out; + err = au_dcsub_pages(&dpages, root, NULL, NULL); + if (unlikely(err)) + goto out_dpages; + + for (i = 0; !err && i < dpages.ndpage; i++) { + dpage = dpages.dpages + i; + ndentry = dpage->ndentry; + for (j = 0; !err && j < ndentry; j++) { + d = dpage->dentries[j]; + AuDebugOn(!d->d_count); + if (!au_digen_test(d, sigen)) { + di_read_lock_child(d, AuLock_IR); + if (unlikely(au_dbrange_test(d))) { + di_read_unlock(d, AuLock_IR); + continue; + } + } else { + di_write_lock_child(d); + if (unlikely(au_dbrange_test(d))) { + di_write_unlock(d); + continue; + } + err = au_reval_dpath(d, sigen); + if (!err) + di_downgrade_lock(d, AuLock_IR); + else { + di_write_unlock(d); + break; + } + } + + /* AuDbgDentry(d); */ + bstart = au_dbstart(d); + bend = au_dbend(d); + if (bstart <= bindex + && bindex <= bend + && au_h_dptr(d, bindex) + && au_test_dbusy(d, bstart, bend)) { + err = -EBUSY; + AuVerbose(verbose, "busy %.*s\n", AuDLNPair(d)); + AuDbgDentry(d); + } + di_read_unlock(d, AuLock_IR); + } + } + +out_dpages: + au_dpages_free(&dpages); +out: + return err; +} + +static int test_inode_busy(struct super_block *sb, aufs_bindex_t bindex, + unsigned int sigen, const unsigned int verbose) +{ + int err; + unsigned long long max, ull; + struct inode *i, **array; + aufs_bindex_t bstart, bend; + + array = au_iarray_alloc(sb, &max); + err = PTR_ERR(array); + if (IS_ERR(array)) + goto out; + + err = 0; + AuDbg("b%d\n", bindex); + for (ull = 0; !err && ull < max; ull++) { + i = array[ull]; + if (i->i_ino == AUFS_ROOT_INO) + continue; + + /* AuDbgInode(i); */ + if (au_iigen(i) == sigen) + ii_read_lock_child(i); + else { + ii_write_lock_child(i); + err = au_refresh_hinode_self(i); + au_iigen_dec(i); + if (!err) + ii_downgrade_lock(i); + else { + ii_write_unlock(i); + break; + } + } + + bstart = au_ibstart(i); + bend = au_ibend(i); + if (bstart <= bindex + && bindex <= bend + && au_h_iptr(i, bindex) + && au_test_ibusy(i, bstart, bend)) { + err = -EBUSY; + AuVerbose(verbose, "busy i%lu\n", i->i_ino); + AuDbgInode(i); + } + ii_read_unlock(i); + } + au_iarray_free(array, max); + +out: + return err; +} + +static int test_children_busy(struct dentry *root, aufs_bindex_t bindex, + const unsigned int verbose) +{ + int err; + unsigned int sigen; + + sigen = au_sigen(root->d_sb); + DiMustNoWaiters(root); + IiMustNoWaiters(root->d_inode); + di_write_unlock(root); + err = test_dentry_busy(root, bindex, sigen, verbose); + if (!err) + err = test_inode_busy(root->d_sb, bindex, sigen, verbose); + di_write_lock_child(root); /* aufs_write_lock() calls ..._child() */ + + return err; +} + +static void au_br_do_del_brp(struct au_sbinfo *sbinfo, + const aufs_bindex_t bindex, + const aufs_bindex_t bend) +{ + struct au_branch **brp, **p; + + AuRwMustWriteLock(&sbinfo->si_rwsem); + + brp = sbinfo->si_branch + bindex; + if (bindex < bend) + memmove(brp, brp + 1, sizeof(*brp) * (bend - bindex)); + sbinfo->si_branch[0 + bend] = NULL; + sbinfo->si_bend--; + + p = krealloc(sbinfo->si_branch, sizeof(*p) * bend, AuGFP_SBILIST); + if (p) + sbinfo->si_branch = p; + /* harmless error */ +} + +static void au_br_do_del_hdp(struct au_dinfo *dinfo, const aufs_bindex_t bindex, + const aufs_bindex_t bend) +{ + struct au_hdentry *hdp, *p; + + AuRwMustWriteLock(&dinfo->di_rwsem); + + hdp = dinfo->di_hdentry; + if (bindex < bend) + memmove(hdp + bindex, hdp + bindex + 1, + sizeof(*hdp) * (bend - bindex)); + hdp[0 + bend].hd_dentry = NULL; + dinfo->di_bend--; + + p = krealloc(hdp, sizeof(*p) * bend, AuGFP_SBILIST); + if (p) + dinfo->di_hdentry = p; + /* harmless error */ +} + +static void au_br_do_del_hip(struct au_iinfo *iinfo, const aufs_bindex_t bindex, + const aufs_bindex_t bend) +{ + struct au_hinode *hip, *p; + + AuRwMustWriteLock(&iinfo->ii_rwsem); + + hip = iinfo->ii_hinode + bindex; + if (bindex < bend) + memmove(hip, hip + 1, sizeof(*hip) * (bend - bindex)); + iinfo->ii_hinode[0 + bend].hi_inode = NULL; + au_hn_init(iinfo->ii_hinode + bend); + iinfo->ii_bend--; + + p = krealloc(iinfo->ii_hinode, sizeof(*p) * bend, AuGFP_SBILIST); + if (p) + iinfo->ii_hinode = p; + /* harmless error */ +} + +static void au_br_do_del(struct super_block *sb, aufs_bindex_t bindex, + struct au_branch *br) +{ + aufs_bindex_t bend; + struct au_sbinfo *sbinfo; + struct dentry *root, *h_root; + struct inode *inode, *h_inode; + struct au_hinode *hinode; + + SiMustWriteLock(sb); + + root = sb->s_root; + inode = root->d_inode; + sbinfo = au_sbi(sb); + bend = sbinfo->si_bend; + + h_root = au_h_dptr(root, bindex); + hinode = au_hi(inode, bindex); + h_inode = au_igrab(hinode->hi_inode); + au_hiput(hinode); + + au_sbilist_lock(); + au_br_do_del_brp(sbinfo, bindex, bend); + au_br_do_del_hdp(au_di(root), bindex, bend); + au_br_do_del_hip(au_ii(inode), bindex, bend); + au_sbilist_unlock(); + + dput(h_root); + iput(h_inode); + au_br_do_free(br); +} + +int au_br_del(struct super_block *sb, struct au_opt_del *del, int remount) +{ + int err, rerr, i; + unsigned int mnt_flags; + aufs_bindex_t bindex, bend, br_id; + unsigned char do_wh, verbose; + struct au_branch *br; + struct au_wbr *wbr; + + err = 0; + bindex = au_find_dbindex(sb->s_root, del->h_path.dentry); + if (bindex < 0) { + if (remount) + goto out; /* success */ + err = -ENOENT; + pr_err("%s no such branch\n", del->pathname); + goto out; + } + AuDbg("bindex b%d\n", bindex); + + err = -EBUSY; + mnt_flags = au_mntflags(sb); + verbose = !!au_opt_test(mnt_flags, VERBOSE); + bend = au_sbend(sb); + if (unlikely(!bend)) { + AuVerbose(verbose, "no more branches left\n"); + goto out; + } + br = au_sbr(sb, bindex); + i = atomic_read(&br->br_count); + if (unlikely(i)) { + AuVerbose(verbose, "%d file(s) opened\n", i); + goto out; + } + + wbr = br->br_wbr; + do_wh = wbr && (wbr->wbr_whbase || wbr->wbr_plink || wbr->wbr_orph); + if (do_wh) { + /* instead of WbrWhMustWriteLock(wbr) */ + SiMustWriteLock(sb); + for (i = 0; i < AuBrWh_Last; i++) { + dput(wbr->wbr_wh[i]); + wbr->wbr_wh[i] = NULL; + } + } + + err = test_children_busy(sb->s_root, bindex, verbose); + if (unlikely(err)) { + if (do_wh) + goto out_wh; + goto out; + } + + err = 0; + br_id = br->br_id; + if (!remount) + au_br_do_del(sb, bindex, br); + else { + sysaufs_brs_del(sb, bindex); + au_br_do_del(sb, bindex, br); + sysaufs_brs_add(sb, bindex); + } + + if (!bindex) { + au_cpup_attr_all(sb->s_root->d_inode, /*force*/1); + sb->s_maxbytes = au_sbr_sb(sb, 0)->s_maxbytes; + } else + au_sub_nlink(sb->s_root->d_inode, del->h_path.dentry->d_inode); + if (au_opt_test(mnt_flags, PLINK)) + au_plink_half_refresh(sb, br_id); + + if (au_xino_brid(sb) == br_id) + au_xino_brid_set(sb, -1); + goto out; /* success */ + +out_wh: + /* revert */ + rerr = au_br_init_wh(sb, br, br->br_perm, del->h_path.dentry); + if (rerr) + pr_warning("failed re-creating base whiteout, %s. (%d)\n", + del->pathname, rerr); +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int au_ibusy(struct super_block *sb, struct aufs_ibusy __user *arg) +{ + int err; + aufs_bindex_t bstart, bend; + struct aufs_ibusy ibusy; + struct inode *inode, *h_inode; + + err = -EPERM; + if (unlikely(!capable(CAP_SYS_ADMIN))) + goto out; + + err = copy_from_user(&ibusy, arg, sizeof(ibusy)); + if (!err) + err = !access_ok(VERIFY_WRITE, &arg->h_ino, sizeof(arg->h_ino)); + if (unlikely(err)) { + err = -EFAULT; + AuTraceErr(err); + goto out; + } + + err = -EINVAL; + si_read_lock(sb, AuLock_FLUSH); + if (unlikely(ibusy.bindex < 0 || ibusy.bindex > au_sbend(sb))) + goto out_unlock; + + err = 0; + ibusy.h_ino = 0; /* invalid */ + inode = ilookup(sb, ibusy.ino); + if (!inode + || inode->i_ino == AUFS_ROOT_INO + || is_bad_inode(inode)) + goto out_unlock; + + ii_read_lock_child(inode); + bstart = au_ibstart(inode); + bend = au_ibend(inode); + if (bstart <= ibusy.bindex && ibusy.bindex <= bend) { + h_inode = au_h_iptr(inode, ibusy.bindex); + if (h_inode && au_test_ibusy(inode, bstart, bend)) + ibusy.h_ino = h_inode->i_ino; + } + ii_read_unlock(inode); + iput(inode); + +out_unlock: + si_read_unlock(sb); + if (!err) { + err = __put_user(ibusy.h_ino, &arg->h_ino); + if (unlikely(err)) { + err = -EFAULT; + AuTraceErr(err); + } + } +out: + return err; +} + +long au_ibusy_ioctl(struct file *file, unsigned long arg) +{ + return au_ibusy(file->f_dentry->d_sb, (void __user *)arg); +} + +#ifdef CONFIG_COMPAT +long au_ibusy_compat_ioctl(struct file *file, unsigned long arg) +{ + return au_ibusy(file->f_dentry->d_sb, compat_ptr(arg)); +} +#endif + +/* ---------------------------------------------------------------------- */ + +/* + * change a branch permission + */ + +static void au_warn_ima(void) +{ +#ifdef CONFIG_IMA + /* since it doesn't support mark_files_ro() */ + AuWarn1("RW -> RO makes IMA to produce wrong message\n"); +#endif +} + +static int do_need_sigen_inc(int a, int b) +{ + return au_br_whable(a) && !au_br_whable(b); +} + +static int need_sigen_inc(int old, int new) +{ + return do_need_sigen_inc(old, new) + || do_need_sigen_inc(new, old); +} + +static unsigned long long au_farray_cb(void *a, + unsigned long long max __maybe_unused, + void *arg) +{ + unsigned long long n; + struct file **p, *f; + struct super_block *sb = arg; + + n = 0; + p = a; + lg_global_lock(files_lglock); + do_file_list_for_each_entry(sb, f) { + if (au_fi(f) + && file_count(f) + && !special_file(f->f_dentry->d_inode->i_mode)) { + get_file(f); + *p++ = f; + n++; + AuDebugOn(n > max); + } + } while_file_list_for_each_entry; + lg_global_unlock(files_lglock); + + return n; +} + +static struct file **au_farray_alloc(struct super_block *sb, + unsigned long long *max) +{ + *max = atomic_long_read(&au_sbi(sb)->si_nfiles); + return au_array_alloc(max, au_farray_cb, sb); +} + +static void au_farray_free(struct file **a, unsigned long long max) +{ + unsigned long long ull; + + for (ull = 0; ull < max; ull++) + if (a[ull]) + fput(a[ull]); + au_array_free(a); +} + +static int au_br_mod_files_ro(struct super_block *sb, aufs_bindex_t bindex) +{ + int err, do_warn; + unsigned int mnt_flags; + unsigned long long ull, max; + aufs_bindex_t br_id; + unsigned char verbose; + struct file *file, *hf, **array; + struct inode *inode; + struct au_hfile *hfile; + + mnt_flags = au_mntflags(sb); + verbose = !!au_opt_test(mnt_flags, VERBOSE); + + array = au_farray_alloc(sb, &max); + err = PTR_ERR(array); + if (IS_ERR(array)) + goto out; + + do_warn = 0; + br_id = au_sbr_id(sb, bindex); + for (ull = 0; ull < max; ull++) { + file = array[ull]; + + /* AuDbg("%.*s\n", AuDLNPair(file->f_dentry)); */ + fi_read_lock(file); + if (unlikely(au_test_mmapped(file))) { + err = -EBUSY; + AuVerbose(verbose, "mmapped %.*s\n", + AuDLNPair(file->f_dentry)); + AuDbgFile(file); + FiMustNoWaiters(file); + fi_read_unlock(file); + goto out_array; + } + + inode = file->f_dentry->d_inode; + hfile = &au_fi(file)->fi_htop; + hf = hfile->hf_file; + if (!S_ISREG(inode->i_mode) + || !(file->f_mode & FMODE_WRITE) + || hfile->hf_br->br_id != br_id + || !(hf->f_mode & FMODE_WRITE)) + array[ull] = NULL; + else { + do_warn = 1; + get_file(file); + } + + FiMustNoWaiters(file); + fi_read_unlock(file); + fput(file); + } + + err = 0; + if (do_warn) + au_warn_ima(); + + for (ull = 0; ull < max; ull++) { + file = array[ull]; + if (!file) + continue; + + /* todo: already flushed? */ + /* cf. fs/super.c:mark_files_ro() */ + /* fi_read_lock(file); */ + hfile = &au_fi(file)->fi_htop; + hf = hfile->hf_file; + /* fi_read_unlock(file); */ + spin_lock(&hf->f_lock); + hf->f_mode &= ~FMODE_WRITE; + spin_unlock(&hf->f_lock); + if (!file_check_writeable(hf)) { + file_release_write(hf); + mnt_drop_write(hf->f_vfsmnt); + } + } + +out_array: + au_farray_free(array, max); +out: + AuTraceErr(err); + return err; +} + +int au_br_mod(struct super_block *sb, struct au_opt_mod *mod, int remount, + int *do_refresh) +{ + int err, rerr; + aufs_bindex_t bindex; + struct path path; + struct dentry *root; + struct au_branch *br; + + root = sb->s_root; + bindex = au_find_dbindex(root, mod->h_root); + if (bindex < 0) { + if (remount) + return 0; /* success */ + err = -ENOENT; + pr_err("%s no such branch\n", mod->path); + goto out; + } + AuDbg("bindex b%d\n", bindex); + + err = test_br(mod->h_root->d_inode, mod->perm, mod->path); + if (unlikely(err)) + goto out; + + br = au_sbr(sb, bindex); + if (br->br_perm == mod->perm) + return 0; /* success */ + + if (au_br_writable(br->br_perm)) { + /* remove whiteout base */ + err = au_br_init_wh(sb, br, mod->perm, mod->h_root); + if (unlikely(err)) + goto out; + + if (!au_br_writable(mod->perm)) { + /* rw --> ro, file might be mmapped */ + DiMustNoWaiters(root); + IiMustNoWaiters(root->d_inode); + di_write_unlock(root); + err = au_br_mod_files_ro(sb, bindex); + /* aufs_write_lock() calls ..._child() */ + di_write_lock_child(root); + + if (unlikely(err)) { + rerr = -ENOMEM; + br->br_wbr = kmalloc(sizeof(*br->br_wbr), + GFP_NOFS); + if (br->br_wbr) { + path.mnt = br->br_mnt; + path.dentry = mod->h_root; + rerr = au_wbr_init(br, sb, br->br_perm, + &path); + } + if (unlikely(rerr)) { + AuIOErr("nested error %d (%d)\n", + rerr, err); + br->br_perm = mod->perm; + } + } + } + } else if (au_br_writable(mod->perm)) { + /* ro --> rw */ + err = -ENOMEM; + br->br_wbr = kmalloc(sizeof(*br->br_wbr), GFP_NOFS); + if (br->br_wbr) { + path.mnt = br->br_mnt; + path.dentry = mod->h_root; + err = au_wbr_init(br, sb, mod->perm, &path); + if (unlikely(err)) { + kfree(br->br_wbr); + br->br_wbr = NULL; + } + } + } + + if (!err) { + *do_refresh |= need_sigen_inc(br->br_perm, mod->perm); + br->br_perm = mod->perm; + } + +out: + AuTraceErr(err); + return err; +} diff --git a/ubuntu/aufs/branch.h b/ubuntu/aufs/branch.h new file mode 100644 index 000000000000..3870bc3f4bd6 --- /dev/null +++ b/ubuntu/aufs/branch.h @@ -0,0 +1,230 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * branch filesystems and xino for them + */ + +#ifndef __AUFS_BRANCH_H__ +#define __AUFS_BRANCH_H__ + +#ifdef __KERNEL__ + +#include <linux/mount.h> +#include "dynop.h" +#include "rwsem.h" +#include "super.h" + +/* ---------------------------------------------------------------------- */ + +/* a xino file */ +struct au_xino_file { + struct file *xi_file; + struct mutex xi_nondir_mtx; + + /* todo: make xino files an array to support huge inode number */ + +#ifdef CONFIG_DEBUG_FS + struct dentry *xi_dbgaufs; +#endif +}; + +/* members for writable branch only */ +enum {AuBrWh_BASE, AuBrWh_PLINK, AuBrWh_ORPH, AuBrWh_Last}; +struct au_wbr { + struct au_rwsem wbr_wh_rwsem; + struct dentry *wbr_wh[AuBrWh_Last]; + atomic_t wbr_wh_running; +#define wbr_whbase wbr_wh[AuBrWh_BASE] /* whiteout base */ +#define wbr_plink wbr_wh[AuBrWh_PLINK] /* pseudo-link dir */ +#define wbr_orph wbr_wh[AuBrWh_ORPH] /* dir for orphans */ + + /* mfs mode */ + unsigned long long wbr_bytes; +}; + +/* ext2 has 3 types of operations at least, ext3 has 4 */ +#define AuBrDynOp (AuDyLast * 4) + +/* protected by superblock rwsem */ +struct au_branch { + struct au_xino_file br_xino; + + aufs_bindex_t br_id; + + int br_perm; + struct vfsmount *br_mnt; + spinlock_t br_dykey_lock; + struct au_dykey *br_dykey[AuBrDynOp]; + atomic_t br_count; + + struct au_wbr *br_wbr; + + /* xino truncation */ + blkcnt_t br_xino_upper; /* watermark in blocks */ + atomic_t br_xino_running; + +#ifdef CONFIG_AUFS_HFSNOTIFY + struct fsnotify_group *br_hfsn_group; + struct fsnotify_ops br_hfsn_ops; +#endif + +#ifdef CONFIG_SYSFS + /* an entry under sysfs per mount-point */ + char br_name[8]; + struct attribute br_attr; +#endif +}; + +/* ---------------------------------------------------------------------- */ + +/* branch permissions and attributes */ +#define AuBrPerm_RW 1 /* writable, hardlinkable wh */ +#define AuBrPerm_RO (1 << 1) /* readonly */ +#define AuBrPerm_RR (1 << 2) /* natively readonly */ +#define AuBrPerm_Mask (AuBrPerm_RW | AuBrPerm_RO | AuBrPerm_RR) + +#define AuBrRAttr_WH (1 << 3) /* whiteout-able */ + +#define AuBrWAttr_NoLinkWH (1 << 4) /* un-hardlinkable whiteouts */ + +static inline int au_br_writable(int brperm) +{ + return brperm & AuBrPerm_RW; +} + +static inline int au_br_whable(int brperm) +{ + return brperm & (AuBrPerm_RW | AuBrRAttr_WH); +} + +static inline int au_br_wh_linkable(int brperm) +{ + return !(brperm & AuBrWAttr_NoLinkWH); +} + +static inline int au_br_rdonly(struct au_branch *br) +{ + return ((br->br_mnt->mnt_sb->s_flags & MS_RDONLY) + || !au_br_writable(br->br_perm)) + ? -EROFS : 0; +} + +static inline int au_br_hnotifyable(int brperm __maybe_unused) +{ +#ifdef CONFIG_AUFS_HNOTIFY + return !(brperm & AuBrPerm_RR); +#else + return 0; +#endif +} + +/* ---------------------------------------------------------------------- */ + +/* branch.c */ +struct au_sbinfo; +void au_br_free(struct au_sbinfo *sinfo); +int au_br_index(struct super_block *sb, aufs_bindex_t br_id); +struct au_opt_add; +int au_br_add(struct super_block *sb, struct au_opt_add *add, int remount); +struct au_opt_del; +int au_br_del(struct super_block *sb, struct au_opt_del *del, int remount); +long au_ibusy_ioctl(struct file *file, unsigned long arg); +#ifdef CONFIG_COMPAT +long au_ibusy_compat_ioctl(struct file *file, unsigned long arg); +#endif +struct au_opt_mod; +int au_br_mod(struct super_block *sb, struct au_opt_mod *mod, int remount, + int *do_refresh); + +/* xino.c */ +static const loff_t au_loff_max = LLONG_MAX; + +int au_xib_trunc(struct super_block *sb); +ssize_t xino_fread(au_readf_t func, struct file *file, void *buf, size_t size, + loff_t *pos); +ssize_t xino_fwrite(au_writef_t func, struct file *file, void *buf, size_t size, + loff_t *pos); +struct file *au_xino_create2(struct file *base_file, struct file *copy_src); +struct file *au_xino_create(struct super_block *sb, char *fname, int silent); +ino_t au_xino_new_ino(struct super_block *sb); +void au_xino_delete_inode(struct inode *inode, const int unlinked); +int au_xino_write(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, + ino_t ino); +int au_xino_read(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, + ino_t *ino); +int au_xino_br(struct super_block *sb, struct au_branch *br, ino_t hino, + struct file *base_file, int do_test); +int au_xino_trunc(struct super_block *sb, aufs_bindex_t bindex); + +struct au_opt_xino; +int au_xino_set(struct super_block *sb, struct au_opt_xino *xino, int remount); +void au_xino_clr(struct super_block *sb); +struct file *au_xino_def(struct super_block *sb); +int au_xino_path(struct seq_file *seq, struct file *file); + +/* ---------------------------------------------------------------------- */ + +/* Superblock to branch */ +static inline +aufs_bindex_t au_sbr_id(struct super_block *sb, aufs_bindex_t bindex) +{ + return au_sbr(sb, bindex)->br_id; +} + +static inline +struct vfsmount *au_sbr_mnt(struct super_block *sb, aufs_bindex_t bindex) +{ + return au_sbr(sb, bindex)->br_mnt; +} + +static inline +struct super_block *au_sbr_sb(struct super_block *sb, aufs_bindex_t bindex) +{ + return au_sbr_mnt(sb, bindex)->mnt_sb; +} + +static inline void au_sbr_put(struct super_block *sb, aufs_bindex_t bindex) +{ + atomic_dec(&au_sbr(sb, bindex)->br_count); +} + +static inline int au_sbr_perm(struct super_block *sb, aufs_bindex_t bindex) +{ + return au_sbr(sb, bindex)->br_perm; +} + +static inline int au_sbr_whable(struct super_block *sb, aufs_bindex_t bindex) +{ + return au_br_whable(au_sbr_perm(sb, bindex)); +} + +/* ---------------------------------------------------------------------- */ + +/* + * wbr_wh_read_lock, wbr_wh_write_lock + * wbr_wh_read_unlock, wbr_wh_write_unlock, wbr_wh_downgrade_lock + */ +AuSimpleRwsemFuncs(wbr_wh, struct au_wbr *wbr, &wbr->wbr_wh_rwsem); + +#define WbrWhMustNoWaiters(wbr) AuRwMustNoWaiters(&wbr->wbr_wh_rwsem) +#define WbrWhMustAnyLock(wbr) AuRwMustAnyLock(&wbr->wbr_wh_rwsem) +#define WbrWhMustWriteLock(wbr) AuRwMustWriteLock(&wbr->wbr_wh_rwsem) + +#endif /* __KERNEL__ */ +#endif /* __AUFS_BRANCH_H__ */ diff --git a/ubuntu/aufs/conf.mk b/ubuntu/aufs/conf.mk new file mode 100644 index 000000000000..6c5108de1aaf --- /dev/null +++ b/ubuntu/aufs/conf.mk @@ -0,0 +1,38 @@ + +AuConfStr = CONFIG_AUFS_FS=${CONFIG_AUFS_FS} + +define AuConf +ifdef ${1} +AuConfStr += ${1}=${${1}} +endif +endef + +AuConfAll = BRANCH_MAX_127 BRANCH_MAX_511 BRANCH_MAX_1023 BRANCH_MAX_32767 \ + SBILIST \ + HNOTIFY HFSNOTIFY \ + EXPORT INO_T_64 \ + RDU \ + PROC_MAP \ + SP_IATTR \ + SHWH \ + BR_RAMFS \ + BR_FUSE POLL \ + BR_HFSPLUS \ + BDEV_LOOP \ + DEBUG MAGIC_SYSRQ +$(foreach i, ${AuConfAll}, \ + $(eval $(call AuConf,CONFIG_AUFS_${i}))) + +AuConfName = ${obj}/conf.str +${AuConfName}.tmp: FORCE + @echo ${AuConfStr} | tr ' ' '\n' | sed -e 's/^/"/' -e 's/$$/\\n"/' > $@ +${AuConfName}: ${AuConfName}.tmp + @diff -q $< $@ > /dev/null 2>&1 || { \ + echo ' GEN ' $@; \ + cp -p $< $@; \ + } +FORCE: +clean-files += ${AuConfName} ${AuConfName}.tmp +${obj}/sysfs.o: ${AuConfName} + +-include ${srctree}/${src}/conf_priv.mk diff --git a/ubuntu/aufs/cpup.c b/ubuntu/aufs/cpup.c new file mode 100644 index 000000000000..7bf2672a9cbc --- /dev/null +++ b/ubuntu/aufs/cpup.c @@ -0,0 +1,1079 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * copy-up functions, see wbr_policy.c for copy-down + */ + +#include <linux/fs_stack.h> +#include <linux/mm.h> +#include "aufs.h" + +void au_cpup_attr_flags(struct inode *dst, struct inode *src) +{ + const unsigned int mask = S_DEAD | S_SWAPFILE | S_PRIVATE + | S_NOATIME | S_NOCMTIME; + + dst->i_flags |= src->i_flags & ~mask; + if (au_test_fs_notime(dst->i_sb)) + dst->i_flags |= S_NOATIME | S_NOCMTIME; +} + +void au_cpup_attr_timesizes(struct inode *inode) +{ + struct inode *h_inode; + + h_inode = au_h_iptr(inode, au_ibstart(inode)); + fsstack_copy_attr_times(inode, h_inode); + fsstack_copy_inode_size(inode, h_inode); +} + +void au_cpup_attr_nlink(struct inode *inode, int force) +{ + struct inode *h_inode; + struct super_block *sb; + aufs_bindex_t bindex, bend; + + sb = inode->i_sb; + bindex = au_ibstart(inode); + h_inode = au_h_iptr(inode, bindex); + if (!force + && !S_ISDIR(h_inode->i_mode) + && au_opt_test(au_mntflags(sb), PLINK) + && au_plink_test(inode)) + return; + + set_nlink(inode, h_inode->i_nlink); + + /* + * fewer nlink makes find(1) noisy, but larger nlink doesn't. + * it may includes whplink directory. + */ + if (S_ISDIR(h_inode->i_mode)) { + bend = au_ibend(inode); + for (bindex++; bindex <= bend; bindex++) { + h_inode = au_h_iptr(inode, bindex); + if (h_inode) + au_add_nlink(inode, h_inode); + } + } +} + +void au_cpup_attr_changeable(struct inode *inode) +{ + struct inode *h_inode; + + h_inode = au_h_iptr(inode, au_ibstart(inode)); + inode->i_mode = h_inode->i_mode; + inode->i_uid = h_inode->i_uid; + inode->i_gid = h_inode->i_gid; + au_cpup_attr_timesizes(inode); + au_cpup_attr_flags(inode, h_inode); +} + +void au_cpup_igen(struct inode *inode, struct inode *h_inode) +{ + struct au_iinfo *iinfo = au_ii(inode); + + IiMustWriteLock(inode); + + iinfo->ii_higen = h_inode->i_generation; + iinfo->ii_hsb1 = h_inode->i_sb; +} + +void au_cpup_attr_all(struct inode *inode, int force) +{ + struct inode *h_inode; + + h_inode = au_h_iptr(inode, au_ibstart(inode)); + au_cpup_attr_changeable(inode); + if (inode->i_nlink > 0) + au_cpup_attr_nlink(inode, force); + inode->i_rdev = h_inode->i_rdev; + inode->i_blkbits = h_inode->i_blkbits; + au_cpup_igen(inode, h_inode); +} + +/* ---------------------------------------------------------------------- */ + +/* Note: dt_dentry and dt_h_dentry are not dget/dput-ed */ + +/* keep the timestamps of the parent dir when cpup */ +void au_dtime_store(struct au_dtime *dt, struct dentry *dentry, + struct path *h_path) +{ + struct inode *h_inode; + + dt->dt_dentry = dentry; + dt->dt_h_path = *h_path; + h_inode = h_path->dentry->d_inode; + dt->dt_atime = h_inode->i_atime; + dt->dt_mtime = h_inode->i_mtime; + /* smp_mb(); */ +} + +void au_dtime_revert(struct au_dtime *dt) +{ + struct iattr attr; + int err; + + attr.ia_atime = dt->dt_atime; + attr.ia_mtime = dt->dt_mtime; + attr.ia_valid = ATTR_FORCE | ATTR_MTIME | ATTR_MTIME_SET + | ATTR_ATIME | ATTR_ATIME_SET; + + err = vfsub_notify_change(&dt->dt_h_path, &attr); + if (unlikely(err)) + pr_warning("restoring timestamps failed(%d). ignored\n", err); +} + +/* ---------------------------------------------------------------------- */ + +static noinline_for_stack +int cpup_iattr(struct dentry *dst, aufs_bindex_t bindex, struct dentry *h_src) +{ + int err, sbits; + struct iattr ia; + struct path h_path; + struct inode *h_isrc, *h_idst; + + h_path.dentry = au_h_dptr(dst, bindex); + h_idst = h_path.dentry->d_inode; + h_path.mnt = au_sbr_mnt(dst->d_sb, bindex); + h_isrc = h_src->d_inode; + ia.ia_valid = ATTR_FORCE | ATTR_UID | ATTR_GID + | ATTR_ATIME | ATTR_MTIME + | ATTR_ATIME_SET | ATTR_MTIME_SET; + ia.ia_uid = h_isrc->i_uid; + ia.ia_gid = h_isrc->i_gid; + ia.ia_atime = h_isrc->i_atime; + ia.ia_mtime = h_isrc->i_mtime; + if (h_idst->i_mode != h_isrc->i_mode + && !S_ISLNK(h_idst->i_mode)) { + ia.ia_valid |= ATTR_MODE; + ia.ia_mode = h_isrc->i_mode; + } + sbits = !!(h_isrc->i_mode & (S_ISUID | S_ISGID)); + au_cpup_attr_flags(h_idst, h_isrc); + err = vfsub_notify_change(&h_path, &ia); + + /* is this nfs only? */ + if (!err && sbits && au_test_nfs(h_path.dentry->d_sb)) { + ia.ia_valid = ATTR_FORCE | ATTR_MODE; + ia.ia_mode = h_isrc->i_mode; + err = vfsub_notify_change(&h_path, &ia); + } + + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int au_do_copy_file(struct file *dst, struct file *src, loff_t len, + char *buf, unsigned long blksize) +{ + int err; + size_t sz, rbytes, wbytes; + unsigned char all_zero; + char *p, *zp; + struct mutex *h_mtx; + /* reduce stack usage */ + struct iattr *ia; + + zp = page_address(ZERO_PAGE(0)); + if (unlikely(!zp)) + return -ENOMEM; /* possible? */ + + err = 0; + all_zero = 0; + while (len) { + AuDbg("len %lld\n", len); + sz = blksize; + if (len < blksize) + sz = len; + + rbytes = 0; + /* todo: signal_pending? */ + while (!rbytes || err == -EAGAIN || err == -EINTR) { + rbytes = vfsub_read_k(src, buf, sz, &src->f_pos); + err = rbytes; + } + if (unlikely(err < 0)) + break; + + all_zero = 0; + if (len >= rbytes && rbytes == blksize) + all_zero = !memcmp(buf, zp, rbytes); + if (!all_zero) { + wbytes = rbytes; + p = buf; + while (wbytes) { + size_t b; + + b = vfsub_write_k(dst, p, wbytes, &dst->f_pos); + err = b; + /* todo: signal_pending? */ + if (unlikely(err == -EAGAIN || err == -EINTR)) + continue; + if (unlikely(err < 0)) + break; + wbytes -= b; + p += b; + } + } else { + loff_t res; + + AuLabel(hole); + res = vfsub_llseek(dst, rbytes, SEEK_CUR); + err = res; + if (unlikely(res < 0)) + break; + } + len -= rbytes; + err = 0; + } + + /* the last block may be a hole */ + if (!err && all_zero) { + AuLabel(last hole); + + err = 1; + if (au_test_nfs(dst->f_dentry->d_sb)) { + /* nfs requires this step to make last hole */ + /* is this only nfs? */ + do { + /* todo: signal_pending? */ + err = vfsub_write_k(dst, "\0", 1, &dst->f_pos); + } while (err == -EAGAIN || err == -EINTR); + if (err == 1) + dst->f_pos--; + } + + if (err == 1) { + ia = (void *)buf; + ia->ia_size = dst->f_pos; + ia->ia_valid = ATTR_SIZE | ATTR_FILE; + ia->ia_file = dst; + h_mtx = &dst->f_dentry->d_inode->i_mutex; + mutex_lock_nested(h_mtx, AuLsc_I_CHILD2); + err = vfsub_notify_change(&dst->f_path, ia); + mutex_unlock(h_mtx); + } + } + + return err; +} + +int au_copy_file(struct file *dst, struct file *src, loff_t len) +{ + int err; + unsigned long blksize; + unsigned char do_kfree; + char *buf; + + err = -ENOMEM; + blksize = dst->f_dentry->d_sb->s_blocksize; + if (!blksize || PAGE_SIZE < blksize) + blksize = PAGE_SIZE; + AuDbg("blksize %lu\n", blksize); + do_kfree = (blksize != PAGE_SIZE && blksize >= sizeof(struct iattr *)); + if (do_kfree) + buf = kmalloc(blksize, GFP_NOFS); + else + buf = (void *)__get_free_page(GFP_NOFS); + if (unlikely(!buf)) + goto out; + + if (len > (1 << 22)) + AuDbg("copying a large file %lld\n", (long long)len); + + src->f_pos = 0; + dst->f_pos = 0; + err = au_do_copy_file(dst, src, len, buf, blksize); + if (do_kfree) + kfree(buf); + else + free_page((unsigned long)buf); + +out: + return err; +} + +/* + * to support a sparse file which is opened with O_APPEND, + * we need to close the file. + */ +static int au_cp_regular(struct dentry *dentry, aufs_bindex_t bdst, + aufs_bindex_t bsrc, loff_t len) +{ + int err, i; + enum { SRC, DST }; + struct { + aufs_bindex_t bindex; + unsigned int flags; + struct dentry *dentry; + struct file *file; + void *label, *label_file; + } *f, file[] = { + { + .bindex = bsrc, + .flags = O_RDONLY | O_NOATIME | O_LARGEFILE, + .file = NULL, + .label = &&out, + .label_file = &&out_src + }, + { + .bindex = bdst, + .flags = O_WRONLY | O_NOATIME | O_LARGEFILE, + .file = NULL, + .label = &&out_src, + .label_file = &&out_dst + } + }; + struct super_block *sb; + + /* bsrc branch can be ro/rw. */ + sb = dentry->d_sb; + f = file; + for (i = 0; i < 2; i++, f++) { + f->dentry = au_h_dptr(dentry, f->bindex); + f->file = au_h_open(dentry, f->bindex, f->flags, /*file*/NULL); + err = PTR_ERR(f->file); + if (IS_ERR(f->file)) + goto *f->label; + err = -EINVAL; + if (unlikely(!f->file->f_op)) + goto *f->label_file; + } + + /* try stopping to update while we copyup */ + IMustLock(file[SRC].dentry->d_inode); + err = au_copy_file(file[DST].file, file[SRC].file, len); + +out_dst: + fput(file[DST].file); + au_sbr_put(sb, file[DST].bindex); +out_src: + fput(file[SRC].file); + au_sbr_put(sb, file[SRC].bindex); +out: + return err; +} + +static int au_do_cpup_regular(struct dentry *dentry, aufs_bindex_t bdst, + aufs_bindex_t bsrc, loff_t len, + struct inode *h_dir, struct path *h_path) +{ + int err, rerr; + loff_t l; + + err = 0; + l = i_size_read(au_h_iptr(dentry->d_inode, bsrc)); + if (len == -1 || l < len) + len = l; + if (len) + err = au_cp_regular(dentry, bdst, bsrc, len); + if (!err) + goto out; /* success */ + + rerr = vfsub_unlink(h_dir, h_path, /*force*/0); + if (rerr) { + AuIOErr("failed unlinking cpup-ed %.*s(%d, %d)\n", + AuDLNPair(h_path->dentry), err, rerr); + err = -EIO; + } + +out: + return err; +} + +static int au_do_cpup_symlink(struct path *h_path, struct dentry *h_src, + struct inode *h_dir) +{ + int err, symlen; + mm_segment_t old_fs; + union { + char *k; + char __user *u; + } sym; + + err = -ENOSYS; + if (unlikely(!h_src->d_inode->i_op->readlink)) + goto out; + + err = -ENOMEM; + sym.k = __getname_gfp(GFP_NOFS); + if (unlikely(!sym.k)) + goto out; + + /* unnecessary to support mmap_sem since symlink is not mmap-able */ + old_fs = get_fs(); + set_fs(KERNEL_DS); + symlen = h_src->d_inode->i_op->readlink(h_src, sym.u, PATH_MAX); + err = symlen; + set_fs(old_fs); + + if (symlen > 0) { + sym.k[symlen] = 0; + err = vfsub_symlink(h_dir, h_path, sym.k); + } + __putname(sym.k); + +out: + return err; +} + +/* return with the lower dst inode is locked */ +static noinline_for_stack +int cpup_entry(struct dentry *dentry, aufs_bindex_t bdst, + aufs_bindex_t bsrc, loff_t len, unsigned int flags, + struct dentry *dst_parent) +{ + int err; + umode_t mode; + unsigned int mnt_flags; + unsigned char isdir; + const unsigned char do_dt = !!au_ftest_cpup(flags, DTIME); + struct au_dtime dt; + struct path h_path; + struct dentry *h_src, *h_dst, *h_parent; + struct inode *h_inode, *h_dir; + struct super_block *sb; + + /* bsrc branch can be ro/rw. */ + h_src = au_h_dptr(dentry, bsrc); + h_inode = h_src->d_inode; + AuDebugOn(h_inode != au_h_iptr(dentry->d_inode, bsrc)); + + /* try stopping to be referenced while we are creating */ + h_dst = au_h_dptr(dentry, bdst); + h_parent = h_dst->d_parent; /* dir inode is locked */ + h_dir = h_parent->d_inode; + IMustLock(h_dir); + AuDebugOn(h_parent != h_dst->d_parent); + + sb = dentry->d_sb; + h_path.mnt = au_sbr_mnt(sb, bdst); + if (do_dt) { + h_path.dentry = h_parent; + au_dtime_store(&dt, dst_parent, &h_path); + } + h_path.dentry = h_dst; + + isdir = 0; + mode = h_inode->i_mode; + switch (mode & S_IFMT) { + case S_IFREG: + /* try stopping to update while we are referencing */ + IMustLock(h_inode); + err = vfsub_create(h_dir, &h_path, mode | S_IWUSR); + if (!err) + err = au_do_cpup_regular + (dentry, bdst, bsrc, len, + au_h_iptr(dst_parent->d_inode, bdst), &h_path); + break; + case S_IFDIR: + isdir = 1; + err = vfsub_mkdir(h_dir, &h_path, mode); + if (!err) { + /* + * strange behaviour from the users view, + * particularry setattr case + */ + if (au_ibstart(dst_parent->d_inode) == bdst) + au_cpup_attr_nlink(dst_parent->d_inode, + /*force*/1); + au_cpup_attr_nlink(dentry->d_inode, /*force*/1); + } + break; + case S_IFLNK: + err = au_do_cpup_symlink(&h_path, h_src, h_dir); + break; + case S_IFCHR: + case S_IFBLK: + AuDebugOn(!capable(CAP_MKNOD)); + /*FALLTHROUGH*/ + case S_IFIFO: + case S_IFSOCK: + err = vfsub_mknod(h_dir, &h_path, mode, h_inode->i_rdev); + break; + default: + AuIOErr("Unknown inode type 0%o\n", mode); + err = -EIO; + } + + mnt_flags = au_mntflags(sb); + if (!au_opt_test(mnt_flags, UDBA_NONE) + && !isdir + && au_opt_test(mnt_flags, XINO) + && h_inode->i_nlink == 1 + /* todo: unnecessary? */ + /* && dentry->d_inode->i_nlink == 1 */ + && bdst < bsrc + && !au_ftest_cpup(flags, KEEPLINO)) + au_xino_write(sb, bsrc, h_inode->i_ino, /*ino*/0); + /* ignore this error */ + + if (do_dt) + au_dtime_revert(&dt); + return err; +} + +/* + * copyup the @dentry from @bsrc to @bdst. + * the caller must set the both of lower dentries. + * @len is for truncating when it is -1 copyup the entire file. + * in link/rename cases, @dst_parent may be different from the real one. + */ +static int au_cpup_single(struct dentry *dentry, aufs_bindex_t bdst, + aufs_bindex_t bsrc, loff_t len, unsigned int flags, + struct dentry *dst_parent) +{ + int err, rerr; + aufs_bindex_t old_ibstart; + unsigned char isdir, plink; + struct au_dtime dt; + struct path h_path; + struct dentry *h_src, *h_dst, *h_parent; + struct inode *dst_inode, *h_dir, *inode; + struct super_block *sb; + + AuDebugOn(bsrc <= bdst); + + sb = dentry->d_sb; + h_path.mnt = au_sbr_mnt(sb, bdst); + h_dst = au_h_dptr(dentry, bdst); + h_parent = h_dst->d_parent; /* dir inode is locked */ + h_dir = h_parent->d_inode; + IMustLock(h_dir); + + h_src = au_h_dptr(dentry, bsrc); + inode = dentry->d_inode; + + if (!dst_parent) + dst_parent = dget_parent(dentry); + else + dget(dst_parent); + + plink = !!au_opt_test(au_mntflags(sb), PLINK); + dst_inode = au_h_iptr(inode, bdst); + if (dst_inode) { + if (unlikely(!plink)) { + err = -EIO; + AuIOErr("hi%lu(i%lu) exists on b%d " + "but plink is disabled\n", + dst_inode->i_ino, inode->i_ino, bdst); + goto out; + } + + if (dst_inode->i_nlink) { + const int do_dt = au_ftest_cpup(flags, DTIME); + + h_src = au_plink_lkup(inode, bdst); + err = PTR_ERR(h_src); + if (IS_ERR(h_src)) + goto out; + if (unlikely(!h_src->d_inode)) { + err = -EIO; + AuIOErr("i%lu exists on a upper branch " + "but not pseudo-linked\n", + inode->i_ino); + dput(h_src); + goto out; + } + + if (do_dt) { + h_path.dentry = h_parent; + au_dtime_store(&dt, dst_parent, &h_path); + } + h_path.dentry = h_dst; + err = vfsub_link(h_src, h_dir, &h_path); + if (do_dt) + au_dtime_revert(&dt); + dput(h_src); + goto out; + } else + /* todo: cpup_wh_file? */ + /* udba work */ + au_update_ibrange(inode, /*do_put_zero*/1); + } + + old_ibstart = au_ibstart(inode); + err = cpup_entry(dentry, bdst, bsrc, len, flags, dst_parent); + if (unlikely(err)) + goto out; + dst_inode = h_dst->d_inode; + mutex_lock_nested(&dst_inode->i_mutex, AuLsc_I_CHILD2); + + err = cpup_iattr(dentry, bdst, h_src); + isdir = S_ISDIR(dst_inode->i_mode); + if (!err) { + if (bdst < old_ibstart) { + if (S_ISREG(inode->i_mode)) { + err = au_dy_iaop(inode, bdst, dst_inode); + if (unlikely(err)) + goto out_rev; + } + au_set_ibstart(inode, bdst); + } + au_set_h_iptr(inode, bdst, au_igrab(dst_inode), + au_hi_flags(inode, isdir)); + mutex_unlock(&dst_inode->i_mutex); + if (!isdir + && h_src->d_inode->i_nlink > 1 + && plink) + au_plink_append(inode, bdst, h_dst); + goto out; /* success */ + } + + /* revert */ +out_rev: + h_path.dentry = h_parent; + mutex_unlock(&dst_inode->i_mutex); + au_dtime_store(&dt, dst_parent, &h_path); + h_path.dentry = h_dst; + if (!isdir) + rerr = vfsub_unlink(h_dir, &h_path, /*force*/0); + else + rerr = vfsub_rmdir(h_dir, &h_path); + au_dtime_revert(&dt); + if (rerr) { + AuIOErr("failed removing broken entry(%d, %d)\n", err, rerr); + err = -EIO; + } + +out: + dput(dst_parent); + return err; +} + +struct au_cpup_single_args { + int *errp; + struct dentry *dentry; + aufs_bindex_t bdst, bsrc; + loff_t len; + unsigned int flags; + struct dentry *dst_parent; +}; + +static void au_call_cpup_single(void *args) +{ + struct au_cpup_single_args *a = args; + *a->errp = au_cpup_single(a->dentry, a->bdst, a->bsrc, a->len, + a->flags, a->dst_parent); +} + +/* + * prevent SIGXFSZ in copy-up. + * testing CAP_MKNOD is for generic fs, + * but CAP_FSETID is for xfs only, currently. + */ +static int au_cpup_sio_test(struct super_block *sb, umode_t mode) +{ + int do_sio; + + do_sio = 0; + if (!au_wkq_test() + && (!au_sbi(sb)->si_plink_maint_pid + || au_plink_maint(sb, AuLock_NOPLM))) { + switch (mode & S_IFMT) { + case S_IFREG: + /* no condition about RLIMIT_FSIZE and the file size */ + do_sio = 1; + break; + case S_IFCHR: + case S_IFBLK: + do_sio = !capable(CAP_MKNOD); + break; + } + if (!do_sio) + do_sio = ((mode & (S_ISUID | S_ISGID)) + && !capable(CAP_FSETID)); + } + + return do_sio; +} + +int au_sio_cpup_single(struct dentry *dentry, aufs_bindex_t bdst, + aufs_bindex_t bsrc, loff_t len, unsigned int flags, + struct dentry *dst_parent) +{ + int err, wkq_err; + struct dentry *h_dentry; + + h_dentry = au_h_dptr(dentry, bsrc); + if (!au_cpup_sio_test(dentry->d_sb, h_dentry->d_inode->i_mode)) + err = au_cpup_single(dentry, bdst, bsrc, len, flags, + dst_parent); + else { + struct au_cpup_single_args args = { + .errp = &err, + .dentry = dentry, + .bdst = bdst, + .bsrc = bsrc, + .len = len, + .flags = flags, + .dst_parent = dst_parent + }; + wkq_err = au_wkq_wait(au_call_cpup_single, &args); + if (unlikely(wkq_err)) + err = wkq_err; + } + + return err; +} + +/* + * copyup the @dentry from the first active lower branch to @bdst, + * using au_cpup_single(). + */ +static int au_cpup_simple(struct dentry *dentry, aufs_bindex_t bdst, loff_t len, + unsigned int flags) +{ + int err; + aufs_bindex_t bsrc, bend; + + bend = au_dbend(dentry); + for (bsrc = bdst + 1; bsrc <= bend; bsrc++) + if (au_h_dptr(dentry, bsrc)) + break; + + err = au_lkup_neg(dentry, bdst); + if (!err) { + err = au_cpup_single(dentry, bdst, bsrc, len, flags, NULL); + if (!err) + return 0; /* success */ + + /* revert */ + au_set_h_dptr(dentry, bdst, NULL); + au_set_dbstart(dentry, bsrc); + } + + return err; +} + +struct au_cpup_simple_args { + int *errp; + struct dentry *dentry; + aufs_bindex_t bdst; + loff_t len; + unsigned int flags; +}; + +static void au_call_cpup_simple(void *args) +{ + struct au_cpup_simple_args *a = args; + *a->errp = au_cpup_simple(a->dentry, a->bdst, a->len, a->flags); +} + +int au_sio_cpup_simple(struct dentry *dentry, aufs_bindex_t bdst, loff_t len, + unsigned int flags) +{ + int err, wkq_err; + struct dentry *parent; + struct inode *h_dir; + + parent = dget_parent(dentry); + h_dir = au_h_iptr(parent->d_inode, bdst); + if (!au_test_h_perm_sio(h_dir, MAY_EXEC | MAY_WRITE) + && !au_cpup_sio_test(dentry->d_sb, dentry->d_inode->i_mode)) + err = au_cpup_simple(dentry, bdst, len, flags); + else { + struct au_cpup_simple_args args = { + .errp = &err, + .dentry = dentry, + .bdst = bdst, + .len = len, + .flags = flags + }; + wkq_err = au_wkq_wait(au_call_cpup_simple, &args); + if (unlikely(wkq_err)) + err = wkq_err; + } + + dput(parent); + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* + * copyup the deleted file for writing. + */ +static int au_do_cpup_wh(struct dentry *dentry, aufs_bindex_t bdst, + struct dentry *wh_dentry, struct file *file, + loff_t len) +{ + int err; + aufs_bindex_t bstart; + struct au_dinfo *dinfo; + struct dentry *h_d_dst, *h_d_start; + struct au_hdentry *hdp; + + dinfo = au_di(dentry); + AuRwMustWriteLock(&dinfo->di_rwsem); + + bstart = dinfo->di_bstart; + hdp = dinfo->di_hdentry; + h_d_dst = hdp[0 + bdst].hd_dentry; + dinfo->di_bstart = bdst; + hdp[0 + bdst].hd_dentry = wh_dentry; + if (file) { + h_d_start = hdp[0 + bstart].hd_dentry; + hdp[0 + bstart].hd_dentry = au_hf_top(file)->f_dentry; + } + err = au_cpup_single(dentry, bdst, bstart, len, !AuCpup_DTIME, + /*h_parent*/NULL); + if (file) { + if (!err) + err = au_reopen_nondir(file); + hdp[0 + bstart].hd_dentry = h_d_start; + } + hdp[0 + bdst].hd_dentry = h_d_dst; + dinfo->di_bstart = bstart; + + return err; +} + +static int au_cpup_wh(struct dentry *dentry, aufs_bindex_t bdst, loff_t len, + struct file *file) +{ + int err; + struct au_dtime dt; + struct dentry *parent, *h_parent, *wh_dentry; + struct au_branch *br; + struct path h_path; + + br = au_sbr(dentry->d_sb, bdst); + parent = dget_parent(dentry); + h_parent = au_h_dptr(parent, bdst); + wh_dentry = au_whtmp_lkup(h_parent, br, &dentry->d_name); + err = PTR_ERR(wh_dentry); + if (IS_ERR(wh_dentry)) + goto out; + + h_path.dentry = h_parent; + h_path.mnt = br->br_mnt; + au_dtime_store(&dt, parent, &h_path); + err = au_do_cpup_wh(dentry, bdst, wh_dentry, file, len); + if (unlikely(err)) + goto out_wh; + + dget(wh_dentry); + h_path.dentry = wh_dentry; + if (!S_ISDIR(wh_dentry->d_inode->i_mode)) + err = vfsub_unlink(h_parent->d_inode, &h_path, /*force*/0); + else + err = vfsub_rmdir(h_parent->d_inode, &h_path); + if (unlikely(err)) { + AuIOErr("failed remove copied-up tmp file %.*s(%d)\n", + AuDLNPair(wh_dentry), err); + err = -EIO; + } + au_dtime_revert(&dt); + au_set_hi_wh(dentry->d_inode, bdst, wh_dentry); + +out_wh: + dput(wh_dentry); +out: + dput(parent); + return err; +} + +struct au_cpup_wh_args { + int *errp; + struct dentry *dentry; + aufs_bindex_t bdst; + loff_t len; + struct file *file; +}; + +static void au_call_cpup_wh(void *args) +{ + struct au_cpup_wh_args *a = args; + *a->errp = au_cpup_wh(a->dentry, a->bdst, a->len, a->file); +} + +int au_sio_cpup_wh(struct dentry *dentry, aufs_bindex_t bdst, loff_t len, + struct file *file) +{ + int err, wkq_err; + struct dentry *parent, *h_orph, *h_parent, *h_dentry; + struct inode *dir, *h_dir, *h_tmpdir, *h_inode; + struct au_wbr *wbr; + + parent = dget_parent(dentry); + dir = parent->d_inode; + h_orph = NULL; + h_parent = NULL; + h_dir = au_igrab(au_h_iptr(dir, bdst)); + h_tmpdir = h_dir; + if (!h_dir->i_nlink) { + wbr = au_sbr(dentry->d_sb, bdst)->br_wbr; + h_orph = wbr->wbr_orph; + + h_parent = dget(au_h_dptr(parent, bdst)); + au_set_h_dptr(parent, bdst, dget(h_orph)); + h_tmpdir = h_orph->d_inode; + au_set_h_iptr(dir, bdst, au_igrab(h_tmpdir), /*flags*/0); + + /* this temporary unlock is safe */ + if (file) + h_dentry = au_hf_top(file)->f_dentry; + else + h_dentry = au_h_dptr(dentry, au_dbstart(dentry)); + h_inode = h_dentry->d_inode; + IMustLock(h_inode); + mutex_unlock(&h_inode->i_mutex); + mutex_lock_nested(&h_tmpdir->i_mutex, AuLsc_I_PARENT3); + mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD); + /* todo: au_h_open_pre()? */ + } + + if (!au_test_h_perm_sio(h_tmpdir, MAY_EXEC | MAY_WRITE) + && !au_cpup_sio_test(dentry->d_sb, dentry->d_inode->i_mode)) + err = au_cpup_wh(dentry, bdst, len, file); + else { + struct au_cpup_wh_args args = { + .errp = &err, + .dentry = dentry, + .bdst = bdst, + .len = len, + .file = file + }; + wkq_err = au_wkq_wait(au_call_cpup_wh, &args); + if (unlikely(wkq_err)) + err = wkq_err; + } + + if (h_orph) { + mutex_unlock(&h_tmpdir->i_mutex); + /* todo: au_h_open_post()? */ + au_set_h_iptr(dir, bdst, au_igrab(h_dir), /*flags*/0); + au_set_h_dptr(parent, bdst, h_parent); + } + iput(h_dir); + dput(parent); + + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* + * generic routine for both of copy-up and copy-down. + */ +/* cf. revalidate function in file.c */ +int au_cp_dirs(struct dentry *dentry, aufs_bindex_t bdst, + int (*cp)(struct dentry *dentry, aufs_bindex_t bdst, + struct dentry *h_parent, void *arg), + void *arg) +{ + int err; + struct au_pin pin; + struct dentry *d, *parent, *h_parent, *real_parent; + + err = 0; + parent = dget_parent(dentry); + if (IS_ROOT(parent)) + goto out; + + au_pin_init(&pin, dentry, bdst, AuLsc_DI_PARENT2, AuLsc_I_PARENT2, + au_opt_udba(dentry->d_sb), AuPin_MNT_WRITE); + + /* do not use au_dpage */ + real_parent = parent; + while (1) { + dput(parent); + parent = dget_parent(dentry); + h_parent = au_h_dptr(parent, bdst); + if (h_parent) + goto out; /* success */ + + /* find top dir which is necessary to cpup */ + do { + d = parent; + dput(parent); + parent = dget_parent(d); + di_read_lock_parent3(parent, !AuLock_IR); + h_parent = au_h_dptr(parent, bdst); + di_read_unlock(parent, !AuLock_IR); + } while (!h_parent); + + if (d != real_parent) + di_write_lock_child3(d); + + /* somebody else might create while we were sleeping */ + if (!au_h_dptr(d, bdst) || !au_h_dptr(d, bdst)->d_inode) { + if (au_h_dptr(d, bdst)) + au_update_dbstart(d); + + au_pin_set_dentry(&pin, d); + err = au_do_pin(&pin); + if (!err) { + err = cp(d, bdst, h_parent, arg); + au_unpin(&pin); + } + } + + if (d != real_parent) + di_write_unlock(d); + if (unlikely(err)) + break; + } + +out: + dput(parent); + return err; +} + +static int au_cpup_dir(struct dentry *dentry, aufs_bindex_t bdst, + struct dentry *h_parent __maybe_unused , + void *arg __maybe_unused) +{ + return au_sio_cpup_simple(dentry, bdst, -1, AuCpup_DTIME); +} + +int au_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst) +{ + return au_cp_dirs(dentry, bdst, au_cpup_dir, NULL); +} + +int au_test_and_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst) +{ + int err; + struct dentry *parent; + struct inode *dir; + + parent = dget_parent(dentry); + dir = parent->d_inode; + err = 0; + if (au_h_iptr(dir, bdst)) + goto out; + + di_read_unlock(parent, AuLock_IR); + di_write_lock_parent(parent); + /* someone else might change our inode while we were sleeping */ + if (!au_h_iptr(dir, bdst)) + err = au_cpup_dirs(dentry, bdst); + di_downgrade_lock(parent, AuLock_IR); + +out: + dput(parent); + return err; +} diff --git a/ubuntu/aufs/cpup.h b/ubuntu/aufs/cpup.h new file mode 100644 index 000000000000..2e4fbe079a25 --- /dev/null +++ b/ubuntu/aufs/cpup.h @@ -0,0 +1,81 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * copy-up/down functions + */ + +#ifndef __AUFS_CPUP_H__ +#define __AUFS_CPUP_H__ + +#ifdef __KERNEL__ + +#include <linux/path.h> + +struct inode; +struct file; + +void au_cpup_attr_flags(struct inode *dst, struct inode *src); +void au_cpup_attr_timesizes(struct inode *inode); +void au_cpup_attr_nlink(struct inode *inode, int force); +void au_cpup_attr_changeable(struct inode *inode); +void au_cpup_igen(struct inode *inode, struct inode *h_inode); +void au_cpup_attr_all(struct inode *inode, int force); + +/* ---------------------------------------------------------------------- */ + +/* cpup flags */ +#define AuCpup_DTIME 1 /* do dtime_store/revert */ +#define AuCpup_KEEPLINO (1 << 1) /* do not clear the lower xino, + for link(2) */ +#define au_ftest_cpup(flags, name) ((flags) & AuCpup_##name) +#define au_fset_cpup(flags, name) \ + do { (flags) |= AuCpup_##name; } while (0) +#define au_fclr_cpup(flags, name) \ + do { (flags) &= ~AuCpup_##name; } while (0) + +int au_copy_file(struct file *dst, struct file *src, loff_t len); +int au_sio_cpup_single(struct dentry *dentry, aufs_bindex_t bdst, + aufs_bindex_t bsrc, loff_t len, unsigned int flags, + struct dentry *dst_parent); +int au_sio_cpup_simple(struct dentry *dentry, aufs_bindex_t bdst, loff_t len, + unsigned int flags); +int au_sio_cpup_wh(struct dentry *dentry, aufs_bindex_t bdst, loff_t len, + struct file *file); + +int au_cp_dirs(struct dentry *dentry, aufs_bindex_t bdst, + int (*cp)(struct dentry *dentry, aufs_bindex_t bdst, + struct dentry *h_parent, void *arg), + void *arg); +int au_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst); +int au_test_and_cpup_dirs(struct dentry *dentry, aufs_bindex_t bdst); + +/* ---------------------------------------------------------------------- */ + +/* keep timestamps when copyup */ +struct au_dtime { + struct dentry *dt_dentry; + struct path dt_h_path; + struct timespec dt_atime, dt_mtime; +}; +void au_dtime_store(struct au_dtime *dt, struct dentry *dentry, + struct path *h_path); +void au_dtime_revert(struct au_dtime *dt); + +#endif /* __KERNEL__ */ +#endif /* __AUFS_CPUP_H__ */ diff --git a/ubuntu/aufs/dbgaufs.c b/ubuntu/aufs/dbgaufs.c new file mode 100644 index 000000000000..d1dbfd2655ec --- /dev/null +++ b/ubuntu/aufs/dbgaufs.c @@ -0,0 +1,334 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * debugfs interface + */ + +#include <linux/debugfs.h> +#include "aufs.h" + +#ifndef CONFIG_SYSFS +#error DEBUG_FS depends upon SYSFS +#endif + +static struct dentry *dbgaufs; +static const mode_t dbgaufs_mode = S_IRUSR | S_IRGRP | S_IROTH; + +/* 20 is max digits length of ulong 64 */ +struct dbgaufs_arg { + int n; + char a[20 * 4]; +}; + +/* + * common function for all XINO files + */ +static int dbgaufs_xi_release(struct inode *inode __maybe_unused, + struct file *file) +{ + kfree(file->private_data); + return 0; +} + +static int dbgaufs_xi_open(struct file *xf, struct file *file, int do_fcnt) +{ + int err; + struct kstat st; + struct dbgaufs_arg *p; + + err = -ENOMEM; + p = kmalloc(sizeof(*p), GFP_NOFS); + if (unlikely(!p)) + goto out; + + err = 0; + p->n = 0; + file->private_data = p; + if (!xf) + goto out; + + err = vfs_getattr(xf->f_vfsmnt, xf->f_dentry, &st); + if (!err) { + if (do_fcnt) + p->n = snprintf + (p->a, sizeof(p->a), "%ld, %llux%lu %lld\n", + (long)file_count(xf), st.blocks, st.blksize, + (long long)st.size); + else + p->n = snprintf(p->a, sizeof(p->a), "%llux%lu %lld\n", + st.blocks, st.blksize, + (long long)st.size); + AuDebugOn(p->n >= sizeof(p->a)); + } else { + p->n = snprintf(p->a, sizeof(p->a), "err %d\n", err); + err = 0; + } + +out: + return err; + +} + +static ssize_t dbgaufs_xi_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct dbgaufs_arg *p; + + p = file->private_data; + return simple_read_from_buffer(buf, count, ppos, p->a, p->n); +} + +/* ---------------------------------------------------------------------- */ + +static int dbgaufs_xib_open(struct inode *inode, struct file *file) +{ + int err; + struct au_sbinfo *sbinfo; + struct super_block *sb; + + sbinfo = inode->i_private; + sb = sbinfo->si_sb; + si_noflush_read_lock(sb); + err = dbgaufs_xi_open(sbinfo->si_xib, file, /*do_fcnt*/0); + si_read_unlock(sb); + return err; +} + +static const struct file_operations dbgaufs_xib_fop = { + .owner = THIS_MODULE, + .open = dbgaufs_xib_open, + .release = dbgaufs_xi_release, + .read = dbgaufs_xi_read +}; + +/* ---------------------------------------------------------------------- */ + +#define DbgaufsXi_PREFIX "xi" + +static int dbgaufs_xino_open(struct inode *inode, struct file *file) +{ + int err; + long l; + struct au_sbinfo *sbinfo; + struct super_block *sb; + struct file *xf; + struct qstr *name; + + err = -ENOENT; + xf = NULL; + name = &file->f_dentry->d_name; + if (unlikely(name->len < sizeof(DbgaufsXi_PREFIX) + || memcmp(name->name, DbgaufsXi_PREFIX, + sizeof(DbgaufsXi_PREFIX) - 1))) + goto out; + err = kstrtol(name->name + sizeof(DbgaufsXi_PREFIX) - 1, 10, &l); + if (unlikely(err)) + goto out; + + sbinfo = inode->i_private; + sb = sbinfo->si_sb; + si_noflush_read_lock(sb); + if (l <= au_sbend(sb)) { + xf = au_sbr(sb, (aufs_bindex_t)l)->br_xino.xi_file; + err = dbgaufs_xi_open(xf, file, /*do_fcnt*/1); + } else + err = -ENOENT; + si_read_unlock(sb); + +out: + return err; +} + +static const struct file_operations dbgaufs_xino_fop = { + .owner = THIS_MODULE, + .open = dbgaufs_xino_open, + .release = dbgaufs_xi_release, + .read = dbgaufs_xi_read +}; + +void dbgaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex) +{ + aufs_bindex_t bend; + struct au_branch *br; + struct au_xino_file *xi; + + if (!au_sbi(sb)->si_dbgaufs) + return; + + bend = au_sbend(sb); + for (; bindex <= bend; bindex++) { + br = au_sbr(sb, bindex); + xi = &br->br_xino; + if (xi->xi_dbgaufs) { + debugfs_remove(xi->xi_dbgaufs); + xi->xi_dbgaufs = NULL; + } + } +} + +void dbgaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex) +{ + struct au_sbinfo *sbinfo; + struct dentry *parent; + struct au_branch *br; + struct au_xino_file *xi; + aufs_bindex_t bend; + char name[sizeof(DbgaufsXi_PREFIX) + 5]; /* "xi" bindex NULL */ + + sbinfo = au_sbi(sb); + parent = sbinfo->si_dbgaufs; + if (!parent) + return; + + bend = au_sbend(sb); + for (; bindex <= bend; bindex++) { + snprintf(name, sizeof(name), DbgaufsXi_PREFIX "%d", bindex); + br = au_sbr(sb, bindex); + xi = &br->br_xino; + AuDebugOn(xi->xi_dbgaufs); + xi->xi_dbgaufs = debugfs_create_file(name, dbgaufs_mode, parent, + sbinfo, &dbgaufs_xino_fop); + /* ignore an error */ + if (unlikely(!xi->xi_dbgaufs)) + AuWarn1("failed %s under debugfs\n", name); + } +} + +/* ---------------------------------------------------------------------- */ + +#ifdef CONFIG_AUFS_EXPORT +static int dbgaufs_xigen_open(struct inode *inode, struct file *file) +{ + int err; + struct au_sbinfo *sbinfo; + struct super_block *sb; + + sbinfo = inode->i_private; + sb = sbinfo->si_sb; + si_noflush_read_lock(sb); + err = dbgaufs_xi_open(sbinfo->si_xigen, file, /*do_fcnt*/0); + si_read_unlock(sb); + return err; +} + +static const struct file_operations dbgaufs_xigen_fop = { + .owner = THIS_MODULE, + .open = dbgaufs_xigen_open, + .release = dbgaufs_xi_release, + .read = dbgaufs_xi_read +}; + +static int dbgaufs_xigen_init(struct au_sbinfo *sbinfo) +{ + int err; + + /* + * This function is a dynamic '__init' fucntion actually, + * so the tiny check for si_rwsem is unnecessary. + */ + /* AuRwMustWriteLock(&sbinfo->si_rwsem); */ + + err = -EIO; + sbinfo->si_dbgaufs_xigen = debugfs_create_file + ("xigen", dbgaufs_mode, sbinfo->si_dbgaufs, sbinfo, + &dbgaufs_xigen_fop); + if (sbinfo->si_dbgaufs_xigen) + err = 0; + + return err; +} +#else +static int dbgaufs_xigen_init(struct au_sbinfo *sbinfo) +{ + return 0; +} +#endif /* CONFIG_AUFS_EXPORT */ + +/* ---------------------------------------------------------------------- */ + +void dbgaufs_si_fin(struct au_sbinfo *sbinfo) +{ + /* + * This function is a dynamic '__init' fucntion actually, + * so the tiny check for si_rwsem is unnecessary. + */ + /* AuRwMustWriteLock(&sbinfo->si_rwsem); */ + + debugfs_remove_recursive(sbinfo->si_dbgaufs); + sbinfo->si_dbgaufs = NULL; + kobject_put(&sbinfo->si_kobj); +} + +int dbgaufs_si_init(struct au_sbinfo *sbinfo) +{ + int err; + char name[SysaufsSiNameLen]; + + /* + * This function is a dynamic '__init' fucntion actually, + * so the tiny check for si_rwsem is unnecessary. + */ + /* AuRwMustWriteLock(&sbinfo->si_rwsem); */ + + err = -ENOENT; + if (!dbgaufs) { + AuErr1("/debug/aufs is uninitialized\n"); + goto out; + } + + err = -EIO; + sysaufs_name(sbinfo, name); + sbinfo->si_dbgaufs = debugfs_create_dir(name, dbgaufs); + if (unlikely(!sbinfo->si_dbgaufs)) + goto out; + kobject_get(&sbinfo->si_kobj); + + sbinfo->si_dbgaufs_xib = debugfs_create_file + ("xib", dbgaufs_mode, sbinfo->si_dbgaufs, sbinfo, + &dbgaufs_xib_fop); + if (unlikely(!sbinfo->si_dbgaufs_xib)) + goto out_dir; + + err = dbgaufs_xigen_init(sbinfo); + if (!err) + goto out; /* success */ + +out_dir: + dbgaufs_si_fin(sbinfo); +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +void dbgaufs_fin(void) +{ + debugfs_remove(dbgaufs); +} + +int __init dbgaufs_init(void) +{ + int err; + + err = -EIO; + dbgaufs = debugfs_create_dir(AUFS_NAME, NULL); + if (dbgaufs) + err = 0; + return err; +} diff --git a/ubuntu/aufs/dbgaufs.h b/ubuntu/aufs/dbgaufs.h new file mode 100644 index 000000000000..8fe49742e558 --- /dev/null +++ b/ubuntu/aufs/dbgaufs.h @@ -0,0 +1,49 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * debugfs interface + */ + +#ifndef __DBGAUFS_H__ +#define __DBGAUFS_H__ + +#ifdef __KERNEL__ + +struct super_block; +struct au_sbinfo; + +#ifdef CONFIG_DEBUG_FS +/* dbgaufs.c */ +void dbgaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex); +void dbgaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex); +void dbgaufs_si_fin(struct au_sbinfo *sbinfo); +int dbgaufs_si_init(struct au_sbinfo *sbinfo); +void dbgaufs_fin(void); +int __init dbgaufs_init(void); +#else +AuStubVoid(dbgaufs_brs_del, struct super_block *sb, aufs_bindex_t bindex) +AuStubVoid(dbgaufs_brs_add, struct super_block *sb, aufs_bindex_t bindex) +AuStubVoid(dbgaufs_si_fin, struct au_sbinfo *sbinfo) +AuStubInt0(dbgaufs_si_init, struct au_sbinfo *sbinfo) +AuStubVoid(dbgaufs_fin, void) +AuStubInt0(__init dbgaufs_init, void) +#endif /* CONFIG_DEBUG_FS */ + +#endif /* __KERNEL__ */ +#endif /* __DBGAUFS_H__ */ diff --git a/ubuntu/aufs/dcsub.c b/ubuntu/aufs/dcsub.c new file mode 100644 index 000000000000..5e8321eca3d4 --- /dev/null +++ b/ubuntu/aufs/dcsub.c @@ -0,0 +1,243 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * sub-routines for dentry cache + */ + +#include "aufs.h" + +static void au_dpage_free(struct au_dpage *dpage) +{ + int i; + struct dentry **p; + + p = dpage->dentries; + for (i = 0; i < dpage->ndentry; i++) + dput(*p++); + free_page((unsigned long)dpage->dentries); +} + +int au_dpages_init(struct au_dcsub_pages *dpages, gfp_t gfp) +{ + int err; + void *p; + + err = -ENOMEM; + dpages->dpages = kmalloc(sizeof(*dpages->dpages), gfp); + if (unlikely(!dpages->dpages)) + goto out; + + p = (void *)__get_free_page(gfp); + if (unlikely(!p)) + goto out_dpages; + + dpages->dpages[0].ndentry = 0; + dpages->dpages[0].dentries = p; + dpages->ndpage = 1; + return 0; /* success */ + +out_dpages: + kfree(dpages->dpages); +out: + return err; +} + +void au_dpages_free(struct au_dcsub_pages *dpages) +{ + int i; + struct au_dpage *p; + + p = dpages->dpages; + for (i = 0; i < dpages->ndpage; i++) + au_dpage_free(p++); + kfree(dpages->dpages); +} + +static int au_dpages_append(struct au_dcsub_pages *dpages, + struct dentry *dentry, gfp_t gfp) +{ + int err, sz; + struct au_dpage *dpage; + void *p; + + dpage = dpages->dpages + dpages->ndpage - 1; + sz = PAGE_SIZE / sizeof(dentry); + if (unlikely(dpage->ndentry >= sz)) { + AuLabel(new dpage); + err = -ENOMEM; + sz = dpages->ndpage * sizeof(*dpages->dpages); + p = au_kzrealloc(dpages->dpages, sz, + sz + sizeof(*dpages->dpages), gfp); + if (unlikely(!p)) + goto out; + + dpages->dpages = p; + dpage = dpages->dpages + dpages->ndpage; + p = (void *)__get_free_page(gfp); + if (unlikely(!p)) + goto out; + + dpage->ndentry = 0; + dpage->dentries = p; + dpages->ndpage++; + } + + AuDebugOn(!dentry->d_count); + dpage->dentries[dpage->ndentry++] = dget_dlock(dentry); + return 0; /* success */ + +out: + return err; +} + +int au_dcsub_pages(struct au_dcsub_pages *dpages, struct dentry *root, + au_dpages_test test, void *arg) +{ + int err; + struct dentry *this_parent; + struct list_head *next; + struct super_block *sb = root->d_sb; + + err = 0; + write_seqlock(&rename_lock); + this_parent = root; + spin_lock(&this_parent->d_lock); +repeat: + next = this_parent->d_subdirs.next; +resume: + if (this_parent->d_sb == sb + && !IS_ROOT(this_parent) + && au_di(this_parent) + && this_parent->d_count + && (!test || test(this_parent, arg))) { + err = au_dpages_append(dpages, this_parent, GFP_ATOMIC); + if (unlikely(err)) + goto out; + } + + while (next != &this_parent->d_subdirs) { + struct list_head *tmp = next; + struct dentry *dentry = list_entry(tmp, struct dentry, + d_u.d_child); + + next = tmp->next; + spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); + if (dentry->d_count) { + if (!list_empty(&dentry->d_subdirs)) { + spin_unlock(&this_parent->d_lock); + spin_release(&dentry->d_lock.dep_map, 1, + _RET_IP_); + this_parent = dentry; + spin_acquire(&this_parent->d_lock.dep_map, 0, 1, + _RET_IP_); + goto repeat; + } + if (dentry->d_sb == sb + && au_di(dentry) + && (!test || test(dentry, arg))) + err = au_dpages_append(dpages, dentry, + GFP_ATOMIC); + } + spin_unlock(&dentry->d_lock); + if (unlikely(err)) + goto out; + } + + if (this_parent != root) { + struct dentry *tmp; + struct dentry *child; + + tmp = this_parent->d_parent; + rcu_read_lock(); + spin_unlock(&this_parent->d_lock); + child = this_parent; + this_parent = tmp; + spin_lock(&this_parent->d_lock); + rcu_read_unlock(); + next = child->d_u.d_child.next; + goto resume; + } + +out: + spin_unlock(&this_parent->d_lock); + write_sequnlock(&rename_lock); + return err; +} + +int au_dcsub_pages_rev(struct au_dcsub_pages *dpages, struct dentry *dentry, + int do_include, au_dpages_test test, void *arg) +{ + int err; + + err = 0; + write_seqlock(&rename_lock); + spin_lock(&dentry->d_lock); + if (do_include + && dentry->d_count + && (!test || test(dentry, arg))) + err = au_dpages_append(dpages, dentry, GFP_ATOMIC); + spin_unlock(&dentry->d_lock); + if (unlikely(err)) + goto out; + + /* + * vfsmount_lock is unnecessary since this is a traverse in a single + * mount + */ + while (!IS_ROOT(dentry)) { + dentry = dentry->d_parent; /* rename_lock is locked */ + spin_lock(&dentry->d_lock); + if (dentry->d_count + && (!test || test(dentry, arg))) + err = au_dpages_append(dpages, dentry, GFP_ATOMIC); + spin_unlock(&dentry->d_lock); + if (unlikely(err)) + break; + } + +out: + write_sequnlock(&rename_lock); + return err; +} + +static inline int au_dcsub_dpages_aufs(struct dentry *dentry, void *arg) +{ + return au_di(dentry) && dentry->d_sb == arg; +} + +int au_dcsub_pages_rev_aufs(struct au_dcsub_pages *dpages, + struct dentry *dentry, int do_include) +{ + return au_dcsub_pages_rev(dpages, dentry, do_include, + au_dcsub_dpages_aufs, dentry->d_sb); +} + +int au_test_subdir(struct dentry *d1, struct dentry *d2) +{ + struct path path[2] = { + { + .dentry = d1 + }, + { + .dentry = d2 + } + }; + + return path_is_under(path + 0, path + 1); +} diff --git a/ubuntu/aufs/dcsub.h b/ubuntu/aufs/dcsub.h new file mode 100644 index 000000000000..3d10731e2769 --- /dev/null +++ b/ubuntu/aufs/dcsub.h @@ -0,0 +1,94 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * sub-routines for dentry cache + */ + +#ifndef __AUFS_DCSUB_H__ +#define __AUFS_DCSUB_H__ + +#ifdef __KERNEL__ + +#include <linux/dcache.h> +#include <linux/fs.h> + +struct dentry; + +struct au_dpage { + int ndentry; + struct dentry **dentries; +}; + +struct au_dcsub_pages { + int ndpage; + struct au_dpage *dpages; +}; + +/* ---------------------------------------------------------------------- */ + +/* dcsub.c */ +int au_dpages_init(struct au_dcsub_pages *dpages, gfp_t gfp); +void au_dpages_free(struct au_dcsub_pages *dpages); +typedef int (*au_dpages_test)(struct dentry *dentry, void *arg); +int au_dcsub_pages(struct au_dcsub_pages *dpages, struct dentry *root, + au_dpages_test test, void *arg); +int au_dcsub_pages_rev(struct au_dcsub_pages *dpages, struct dentry *dentry, + int do_include, au_dpages_test test, void *arg); +int au_dcsub_pages_rev_aufs(struct au_dcsub_pages *dpages, + struct dentry *dentry, int do_include); +int au_test_subdir(struct dentry *d1, struct dentry *d2); + +/* ---------------------------------------------------------------------- */ + +static inline int au_d_hashed_positive(struct dentry *d) +{ + int err; + struct inode *inode = d->d_inode; + err = 0; + if (unlikely(d_unhashed(d) || !inode || !inode->i_nlink)) + err = -ENOENT; + return err; +} + +static inline int au_d_alive(struct dentry *d) +{ + int err; + struct inode *inode; + err = 0; + if (!IS_ROOT(d)) + err = au_d_hashed_positive(d); + else { + inode = d->d_inode; + if (unlikely(d_unlinked(d) || !inode || !inode->i_nlink)) + err = -ENOENT; + } + return err; +} + +static inline int au_alive_dir(struct dentry *d) +{ + int err; + err = au_d_alive(d); + if (unlikely(err || IS_DEADDIR(d->d_inode))) + err = -ENOENT; + return err; +} + +#endif /* __KERNEL__ */ +#endif /* __AUFS_DCSUB_H__ */ diff --git a/ubuntu/aufs/debug.c b/ubuntu/aufs/debug.c new file mode 100644 index 000000000000..9c9091d290a3 --- /dev/null +++ b/ubuntu/aufs/debug.c @@ -0,0 +1,489 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * debug print functions + */ + +#include <linux/vt_kern.h> +#include "aufs.h" + +int aufs_debug; +MODULE_PARM_DESC(debug, "debug print"); +module_param_named(debug, aufs_debug, int, S_IRUGO | S_IWUSR | S_IWGRP); + +char *au_plevel = KERN_DEBUG; +#define dpri(fmt, ...) do { \ + if ((au_plevel \ + && strcmp(au_plevel, KERN_DEBUG)) \ + || au_debug_test()) \ + printk("%s" fmt, au_plevel, ##__VA_ARGS__); \ +} while (0) + +/* ---------------------------------------------------------------------- */ + +void au_dpri_whlist(struct au_nhash *whlist) +{ + unsigned long ul, n; + struct hlist_head *head; + struct au_vdir_wh *tpos; + struct hlist_node *pos; + + n = whlist->nh_num; + head = whlist->nh_head; + for (ul = 0; ul < n; ul++) { + hlist_for_each_entry(tpos, pos, head, wh_hash) + dpri("b%d, %.*s, %d\n", + tpos->wh_bindex, + tpos->wh_str.len, tpos->wh_str.name, + tpos->wh_str.len); + head++; + } +} + +void au_dpri_vdir(struct au_vdir *vdir) +{ + unsigned long ul; + union au_vdir_deblk_p p; + unsigned char *o; + + if (!vdir || IS_ERR(vdir)) { + dpri("err %ld\n", PTR_ERR(vdir)); + return; + } + + dpri("deblk %u, nblk %lu, deblk %p, last{%lu, %p}, ver %lu\n", + vdir->vd_deblk_sz, vdir->vd_nblk, vdir->vd_deblk, + vdir->vd_last.ul, vdir->vd_last.p.deblk, vdir->vd_version); + for (ul = 0; ul < vdir->vd_nblk; ul++) { + p.deblk = vdir->vd_deblk[ul]; + o = p.deblk; + dpri("[%lu]: %p\n", ul, o); + } +} + +static int do_pri_inode(aufs_bindex_t bindex, struct inode *inode, int hn, + struct dentry *wh) +{ + char *n = NULL; + int l = 0; + + if (!inode || IS_ERR(inode)) { + dpri("i%d: err %ld\n", bindex, PTR_ERR(inode)); + return -1; + } + + /* the type of i_blocks depends upon CONFIG_LSF */ + BUILD_BUG_ON(sizeof(inode->i_blocks) != sizeof(unsigned long) + && sizeof(inode->i_blocks) != sizeof(u64)); + if (wh) { + n = (void *)wh->d_name.name; + l = wh->d_name.len; + } + + dpri("i%d: %p, i%lu, %s, cnt %d, nl %u, 0%o, sz %llu, blk %llu," + " hn %d, ct %lld, np %lu, st 0x%lx, f 0x%x, v %llu, g %x%s%.*s\n", + bindex, inode, + inode->i_ino, inode->i_sb ? au_sbtype(inode->i_sb) : "??", + atomic_read(&inode->i_count), inode->i_nlink, inode->i_mode, + i_size_read(inode), (unsigned long long)inode->i_blocks, + hn, (long long)timespec_to_ns(&inode->i_ctime) & 0x0ffff, + inode->i_mapping ? inode->i_mapping->nrpages : 0, + inode->i_state, inode->i_flags, inode->i_version, + inode->i_generation, + l ? ", wh " : "", l, n); + return 0; +} + +void au_dpri_inode(struct inode *inode) +{ + struct au_iinfo *iinfo; + aufs_bindex_t bindex; + int err, hn; + + err = do_pri_inode(-1, inode, -1, NULL); + if (err || !au_test_aufs(inode->i_sb)) + return; + + iinfo = au_ii(inode); + if (!iinfo) + return; + dpri("i-1: bstart %d, bend %d, gen %d\n", + iinfo->ii_bstart, iinfo->ii_bend, au_iigen(inode)); + if (iinfo->ii_bstart < 0) + return; + hn = 0; + for (bindex = iinfo->ii_bstart; bindex <= iinfo->ii_bend; bindex++) { + hn = !!au_hn(iinfo->ii_hinode + bindex); + do_pri_inode(bindex, iinfo->ii_hinode[0 + bindex].hi_inode, hn, + iinfo->ii_hinode[0 + bindex].hi_whdentry); + } +} + +void au_dpri_dalias(struct inode *inode) +{ + struct dentry *d; + + spin_lock(&inode->i_lock); + list_for_each_entry(d, &inode->i_dentry, d_alias) + au_dpri_dentry(d); + spin_unlock(&inode->i_lock); +} + +static int do_pri_dentry(aufs_bindex_t bindex, struct dentry *dentry) +{ + struct dentry *wh = NULL; + int hn; + + if (!dentry || IS_ERR(dentry)) { + dpri("d%d: err %ld\n", bindex, PTR_ERR(dentry)); + return -1; + } + /* do not call dget_parent() here */ + /* note: access d_xxx without d_lock */ + dpri("d%d: %.*s?/%.*s, %s, cnt %d, flags 0x%x\n", + bindex, + AuDLNPair(dentry->d_parent), AuDLNPair(dentry), + dentry->d_sb ? au_sbtype(dentry->d_sb) : "??", + dentry->d_count, dentry->d_flags); + hn = -1; + if (bindex >= 0 && dentry->d_inode && au_test_aufs(dentry->d_sb)) { + struct au_iinfo *iinfo = au_ii(dentry->d_inode); + if (iinfo) { + hn = !!au_hn(iinfo->ii_hinode + bindex); + wh = iinfo->ii_hinode[0 + bindex].hi_whdentry; + } + } + do_pri_inode(bindex, dentry->d_inode, hn, wh); + return 0; +} + +void au_dpri_dentry(struct dentry *dentry) +{ + struct au_dinfo *dinfo; + aufs_bindex_t bindex; + int err; + struct au_hdentry *hdp; + + err = do_pri_dentry(-1, dentry); + if (err || !au_test_aufs(dentry->d_sb)) + return; + + dinfo = au_di(dentry); + if (!dinfo) + return; + dpri("d-1: bstart %d, bend %d, bwh %d, bdiropq %d, gen %d\n", + dinfo->di_bstart, dinfo->di_bend, + dinfo->di_bwh, dinfo->di_bdiropq, au_digen(dentry)); + if (dinfo->di_bstart < 0) + return; + hdp = dinfo->di_hdentry; + for (bindex = dinfo->di_bstart; bindex <= dinfo->di_bend; bindex++) + do_pri_dentry(bindex, hdp[0 + bindex].hd_dentry); +} + +static int do_pri_file(aufs_bindex_t bindex, struct file *file) +{ + char a[32]; + + if (!file || IS_ERR(file)) { + dpri("f%d: err %ld\n", bindex, PTR_ERR(file)); + return -1; + } + a[0] = 0; + if (bindex < 0 + && file->f_dentry + && au_test_aufs(file->f_dentry->d_sb) + && au_fi(file)) + snprintf(a, sizeof(a), ", gen %d, mmapped %d", + au_figen(file), atomic_read(&au_fi(file)->fi_mmapped)); + dpri("f%d: mode 0x%x, flags 0%o, cnt %ld, v %llu, pos %llu%s\n", + bindex, file->f_mode, file->f_flags, (long)file_count(file), + file->f_version, file->f_pos, a); + if (file->f_dentry) + do_pri_dentry(bindex, file->f_dentry); + return 0; +} + +void au_dpri_file(struct file *file) +{ + struct au_finfo *finfo; + struct au_fidir *fidir; + struct au_hfile *hfile; + aufs_bindex_t bindex; + int err; + + err = do_pri_file(-1, file); + if (err || !file->f_dentry || !au_test_aufs(file->f_dentry->d_sb)) + return; + + finfo = au_fi(file); + if (!finfo) + return; + if (finfo->fi_btop < 0) + return; + fidir = finfo->fi_hdir; + if (!fidir) + do_pri_file(finfo->fi_btop, finfo->fi_htop.hf_file); + else + for (bindex = finfo->fi_btop; + bindex >= 0 && bindex <= fidir->fd_bbot; + bindex++) { + hfile = fidir->fd_hfile + bindex; + do_pri_file(bindex, hfile ? hfile->hf_file : NULL); + } +} + +static int do_pri_br(aufs_bindex_t bindex, struct au_branch *br) +{ + struct vfsmount *mnt; + struct super_block *sb; + + if (!br || IS_ERR(br)) + goto out; + mnt = br->br_mnt; + if (!mnt || IS_ERR(mnt)) + goto out; + sb = mnt->mnt_sb; + if (!sb || IS_ERR(sb)) + goto out; + + dpri("s%d: {perm 0x%x, id %d, cnt %d, wbr %p}, " + "%s, dev 0x%02x%02x, flags 0x%lx, cnt %d, active %d, " + "xino %d\n", + bindex, br->br_perm, br->br_id, atomic_read(&br->br_count), + br->br_wbr, au_sbtype(sb), MAJOR(sb->s_dev), MINOR(sb->s_dev), + sb->s_flags, sb->s_count, + atomic_read(&sb->s_active), !!br->br_xino.xi_file); + return 0; + +out: + dpri("s%d: err %ld\n", bindex, PTR_ERR(br)); + return -1; +} + +void au_dpri_sb(struct super_block *sb) +{ + struct au_sbinfo *sbinfo; + aufs_bindex_t bindex; + int err; + /* to reuduce stack size */ + struct { + struct vfsmount mnt; + struct au_branch fake; + } *a; + + /* this function can be called from magic sysrq */ + a = kzalloc(sizeof(*a), GFP_ATOMIC); + if (unlikely(!a)) { + dpri("no memory\n"); + return; + } + + a->mnt.mnt_sb = sb; + a->fake.br_perm = 0; + a->fake.br_mnt = &a->mnt; + a->fake.br_xino.xi_file = NULL; + atomic_set(&a->fake.br_count, 0); + smp_mb(); /* atomic_set */ + err = do_pri_br(-1, &a->fake); + kfree(a); + dpri("dev 0x%x\n", sb->s_dev); + if (err || !au_test_aufs(sb)) + return; + + sbinfo = au_sbi(sb); + if (!sbinfo) + return; + dpri("nw %d, gen %u, kobj %d\n", + atomic_read(&sbinfo->si_nowait.nw_len), sbinfo->si_generation, + atomic_read(&sbinfo->si_kobj.kref.refcount)); + for (bindex = 0; bindex <= sbinfo->si_bend; bindex++) + do_pri_br(bindex, sbinfo->si_branch[0 + bindex]); +} + +/* ---------------------------------------------------------------------- */ + +void au_dbg_sleep_jiffy(int jiffy) +{ + while (jiffy) + jiffy = schedule_timeout_uninterruptible(jiffy); +} + +void au_dbg_iattr(struct iattr *ia) +{ +#define AuBit(name) if (ia->ia_valid & ATTR_ ## name) \ + dpri(#name "\n") + AuBit(MODE); + AuBit(UID); + AuBit(GID); + AuBit(SIZE); + AuBit(ATIME); + AuBit(MTIME); + AuBit(CTIME); + AuBit(ATIME_SET); + AuBit(MTIME_SET); + AuBit(FORCE); + AuBit(ATTR_FLAG); + AuBit(KILL_SUID); + AuBit(KILL_SGID); + AuBit(FILE); + AuBit(KILL_PRIV); + AuBit(OPEN); + AuBit(TIMES_SET); +#undef AuBit + dpri("ia_file %p\n", ia->ia_file); +} + +/* ---------------------------------------------------------------------- */ + +void __au_dbg_verify_dinode(struct dentry *dentry, const char *func, int line) +{ + struct inode *h_inode, *inode = dentry->d_inode; + struct dentry *h_dentry; + aufs_bindex_t bindex, bend, bi; + + if (!inode /* || au_di(dentry)->di_lsc == AuLsc_DI_TMP */) + return; + + bend = au_dbend(dentry); + bi = au_ibend(inode); + if (bi < bend) + bend = bi; + bindex = au_dbstart(dentry); + bi = au_ibstart(inode); + if (bi > bindex) + bindex = bi; + + for (; bindex <= bend; bindex++) { + h_dentry = au_h_dptr(dentry, bindex); + if (!h_dentry) + continue; + h_inode = au_h_iptr(inode, bindex); + if (unlikely(h_inode != h_dentry->d_inode)) { + int old = au_debug_test(); + if (!old) + au_debug(1); + AuDbg("b%d, %s:%d\n", bindex, func, line); + AuDbgDentry(dentry); + AuDbgInode(inode); + if (!old) + au_debug(0); + BUG(); + } + } +} + +void au_dbg_verify_dir_parent(struct dentry *dentry, unsigned int sigen) +{ + struct dentry *parent; + + parent = dget_parent(dentry); + AuDebugOn(!S_ISDIR(dentry->d_inode->i_mode)); + AuDebugOn(IS_ROOT(dentry)); + AuDebugOn(au_digen_test(parent, sigen)); + dput(parent); +} + +void au_dbg_verify_nondir_parent(struct dentry *dentry, unsigned int sigen) +{ + struct dentry *parent; + struct inode *inode; + + parent = dget_parent(dentry); + inode = dentry->d_inode; + AuDebugOn(inode && S_ISDIR(dentry->d_inode->i_mode)); + AuDebugOn(au_digen_test(parent, sigen)); + dput(parent); +} + +void au_dbg_verify_gen(struct dentry *parent, unsigned int sigen) +{ + int err, i, j; + struct au_dcsub_pages dpages; + struct au_dpage *dpage; + struct dentry **dentries; + + err = au_dpages_init(&dpages, GFP_NOFS); + AuDebugOn(err); + err = au_dcsub_pages_rev_aufs(&dpages, parent, /*do_include*/1); + AuDebugOn(err); + for (i = dpages.ndpage - 1; !err && i >= 0; i--) { + dpage = dpages.dpages + i; + dentries = dpage->dentries; + for (j = dpage->ndentry - 1; !err && j >= 0; j--) + AuDebugOn(au_digen_test(dentries[j], sigen)); + } + au_dpages_free(&dpages); +} + +void au_dbg_verify_kthread(void) +{ + if (au_wkq_test()) { + au_dbg_blocked(); + /* + * It may be recursive, but udba=notify between two aufs mounts, + * where a single ro branch is shared, is not a problem. + */ + /* WARN_ON(1); */ + } +} + +/* ---------------------------------------------------------------------- */ + +void au_debug_sbinfo_init(struct au_sbinfo *sbinfo __maybe_unused) +{ +#ifdef AuForceNoPlink + au_opt_clr(sbinfo->si_mntflags, PLINK); +#endif +#ifdef AuForceNoXino + au_opt_clr(sbinfo->si_mntflags, XINO); +#endif +#ifdef AuForceNoRefrof + au_opt_clr(sbinfo->si_mntflags, REFROF); +#endif +#ifdef AuForceHnotify + au_opt_set_udba(sbinfo->si_mntflags, UDBA_HNOTIFY); +#endif +#ifdef AuForceRd0 + sbinfo->si_rdblk = 0; + sbinfo->si_rdhash = 0; +#endif +} + +int __init au_debug_init(void) +{ + aufs_bindex_t bindex; + struct au_vdir_destr destr; + + bindex = -1; + AuDebugOn(bindex >= 0); + + destr.len = -1; + AuDebugOn(destr.len < NAME_MAX); + +#ifdef CONFIG_4KSTACKS + pr_warning("CONFIG_4KSTACKS is defined.\n"); +#endif + +#ifdef AuForceNoBrs + sysaufs_brs = 0; +#endif + + return 0; +} diff --git a/ubuntu/aufs/debug.h b/ubuntu/aufs/debug.h new file mode 100644 index 000000000000..c4d5610a7f5c --- /dev/null +++ b/ubuntu/aufs/debug.h @@ -0,0 +1,243 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * debug print functions + */ + +#ifndef __AUFS_DEBUG_H__ +#define __AUFS_DEBUG_H__ + +#ifdef __KERNEL__ + +#include <asm/system.h> +#include <linux/module.h> +#include <linux/kallsyms.h> +#include <linux/sysrq.h> + +#ifdef CONFIG_AUFS_DEBUG +#define AuDebugOn(a) BUG_ON(a) + +/* module parameter */ +extern int aufs_debug; +static inline void au_debug(int n) +{ + aufs_debug = n; + smp_mb(); +} + +static inline int au_debug_test(void) +{ + return aufs_debug; +} +#else +#define AuDebugOn(a) do {} while (0) +AuStubVoid(au_debug, int n) +AuStubInt0(au_debug_test, void) +#endif /* CONFIG_AUFS_DEBUG */ + +/* ---------------------------------------------------------------------- */ + +/* debug print */ + +#define AuDbg(fmt, ...) do { \ + if (au_debug_test()) \ + pr_debug("DEBUG: " fmt, ##__VA_ARGS__); \ +} while (0) +#define AuLabel(l) AuDbg(#l "\n") +#define AuIOErr(fmt, ...) pr_err("I/O Error, " fmt, ##__VA_ARGS__) +#define AuWarn1(fmt, ...) do { \ + static unsigned char _c; \ + if (!_c++) \ + pr_warning(fmt, ##__VA_ARGS__); \ +} while (0) + +#define AuErr1(fmt, ...) do { \ + static unsigned char _c; \ + if (!_c++) \ + pr_err(fmt, ##__VA_ARGS__); \ +} while (0) + +#define AuIOErr1(fmt, ...) do { \ + static unsigned char _c; \ + if (!_c++) \ + AuIOErr(fmt, ##__VA_ARGS__); \ +} while (0) + +#define AuUnsupportMsg "This operation is not supported." \ + " Please report this application to aufs-users ML." +#define AuUnsupport(fmt, ...) do { \ + pr_err(AuUnsupportMsg "\n" fmt, ##__VA_ARGS__); \ + dump_stack(); \ +} while (0) + +#define AuTraceErr(e) do { \ + if (unlikely((e) < 0)) \ + AuDbg("err %d\n", (int)(e)); \ +} while (0) + +#define AuTraceErrPtr(p) do { \ + if (IS_ERR(p)) \ + AuDbg("err %ld\n", PTR_ERR(p)); \ +} while (0) + +/* dirty macros for debug print, use with "%.*s" and caution */ +#define AuLNPair(qstr) (qstr)->len, (qstr)->name +#define AuDLNPair(d) AuLNPair(&(d)->d_name) + +/* ---------------------------------------------------------------------- */ + +struct au_sbinfo; +struct au_finfo; +struct dentry; +#ifdef CONFIG_AUFS_DEBUG +extern char *au_plevel; +struct au_nhash; +void au_dpri_whlist(struct au_nhash *whlist); +struct au_vdir; +void au_dpri_vdir(struct au_vdir *vdir); +struct inode; +void au_dpri_inode(struct inode *inode); +void au_dpri_dalias(struct inode *inode); +void au_dpri_dentry(struct dentry *dentry); +struct file; +void au_dpri_file(struct file *filp); +struct super_block; +void au_dpri_sb(struct super_block *sb); + +void au_dbg_sleep_jiffy(int jiffy); +struct iattr; +void au_dbg_iattr(struct iattr *ia); + +#define au_dbg_verify_dinode(d) __au_dbg_verify_dinode(d, __func__, __LINE__) +void __au_dbg_verify_dinode(struct dentry *dentry, const char *func, int line); +void au_dbg_verify_dir_parent(struct dentry *dentry, unsigned int sigen); +void au_dbg_verify_nondir_parent(struct dentry *dentry, unsigned int sigen); +void au_dbg_verify_gen(struct dentry *parent, unsigned int sigen); +void au_dbg_verify_kthread(void); + +int __init au_debug_init(void); +void au_debug_sbinfo_init(struct au_sbinfo *sbinfo); +#define AuDbgWhlist(w) do { \ + AuDbg(#w "\n"); \ + au_dpri_whlist(w); \ +} while (0) + +#define AuDbgVdir(v) do { \ + AuDbg(#v "\n"); \ + au_dpri_vdir(v); \ +} while (0) + +#define AuDbgInode(i) do { \ + AuDbg(#i "\n"); \ + au_dpri_inode(i); \ +} while (0) + +#define AuDbgDAlias(i) do { \ + AuDbg(#i "\n"); \ + au_dpri_dalias(i); \ +} while (0) + +#define AuDbgDentry(d) do { \ + AuDbg(#d "\n"); \ + au_dpri_dentry(d); \ +} while (0) + +#define AuDbgFile(f) do { \ + AuDbg(#f "\n"); \ + au_dpri_file(f); \ +} while (0) + +#define AuDbgSb(sb) do { \ + AuDbg(#sb "\n"); \ + au_dpri_sb(sb); \ +} while (0) + +#define AuDbgSleep(sec) do { \ + AuDbg("sleep %d sec\n", sec); \ + ssleep(sec); \ +} while (0) + +#define AuDbgSleepJiffy(jiffy) do { \ + AuDbg("sleep %d jiffies\n", jiffy); \ + au_dbg_sleep_jiffy(jiffy); \ +} while (0) + +#define AuDbgIAttr(ia) do { \ + AuDbg("ia_valid 0x%x\n", (ia)->ia_valid); \ + au_dbg_iattr(ia); \ +} while (0) + +#define AuDbgSym(addr) do { \ + char sym[KSYM_SYMBOL_LEN]; \ + sprint_symbol(sym, (unsigned long)addr); \ + AuDbg("%s\n", sym); \ +} while (0) + +#define AuInfoSym(addr) do { \ + char sym[KSYM_SYMBOL_LEN]; \ + sprint_symbol(sym, (unsigned long)addr); \ + AuInfo("%s\n", sym); \ +} while (0) +#else +AuStubVoid(au_dbg_verify_dinode, struct dentry *dentry) +AuStubVoid(au_dbg_verify_dir_parent, struct dentry *dentry, unsigned int sigen) +AuStubVoid(au_dbg_verify_nondir_parent, struct dentry *dentry, + unsigned int sigen) +AuStubVoid(au_dbg_verify_gen, struct dentry *parent, unsigned int sigen) +AuStubVoid(au_dbg_verify_kthread, void) +AuStubInt0(__init au_debug_init, void) +AuStubVoid(au_debug_sbinfo_init, struct au_sbinfo *sbinfo) + +#define AuDbgWhlist(w) do {} while (0) +#define AuDbgVdir(v) do {} while (0) +#define AuDbgInode(i) do {} while (0) +#define AuDbgDAlias(i) do {} while (0) +#define AuDbgDentry(d) do {} while (0) +#define AuDbgFile(f) do {} while (0) +#define AuDbgSb(sb) do {} while (0) +#define AuDbgSleep(sec) do {} while (0) +#define AuDbgSleepJiffy(jiffy) do {} while (0) +#define AuDbgIAttr(ia) do {} while (0) +#define AuDbgSym(addr) do {} while (0) +#define AuInfoSym(addr) do {} while (0) +#endif /* CONFIG_AUFS_DEBUG */ + +/* ---------------------------------------------------------------------- */ + +#ifdef CONFIG_AUFS_MAGIC_SYSRQ +int __init au_sysrq_init(void); +void au_sysrq_fin(void); + +#ifdef CONFIG_HW_CONSOLE +#define au_dbg_blocked() do { \ + WARN_ON(1); \ + handle_sysrq('w'); \ +} while (0) +#else +AuStubVoid(au_dbg_blocked, void) +#endif + +#else +AuStubInt0(__init au_sysrq_init, void) +AuStubVoid(au_sysrq_fin, void) +AuStubVoid(au_dbg_blocked, void) +#endif /* CONFIG_AUFS_MAGIC_SYSRQ */ + +#endif /* __KERNEL__ */ +#endif /* __AUFS_DEBUG_H__ */ diff --git a/ubuntu/aufs/dentry.c b/ubuntu/aufs/dentry.c new file mode 100644 index 000000000000..11ed8c25faf1 --- /dev/null +++ b/ubuntu/aufs/dentry.c @@ -0,0 +1,1140 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * lookup and dentry operations + */ + +#include <linux/namei.h> +#include "aufs.h" + +static void au_h_nd(struct nameidata *h_nd, struct nameidata *nd) +{ + if (nd) { + *h_nd = *nd; + + /* + * gave up supporting LOOKUP_CREATE/OPEN for lower fs, + * due to whiteout and branch permission. + */ + h_nd->flags &= ~(/*LOOKUP_PARENT |*/ LOOKUP_OPEN | LOOKUP_CREATE + | LOOKUP_FOLLOW | LOOKUP_EXCL); + /* unnecessary? */ + h_nd->intent.open.file = NULL; + } else + memset(h_nd, 0, sizeof(*h_nd)); +} + +struct au_lkup_one_args { + struct dentry **errp; + struct qstr *name; + struct dentry *h_parent; + struct au_branch *br; + struct nameidata *nd; +}; + +struct dentry *au_lkup_one(struct qstr *name, struct dentry *h_parent, + struct au_branch *br, struct nameidata *nd) +{ + struct dentry *h_dentry; + int err; + struct nameidata h_nd; + + if (au_test_fs_null_nd(h_parent->d_sb)) + return vfsub_lookup_one_len(name->name, h_parent, name->len); + + au_h_nd(&h_nd, nd); + h_nd.path.dentry = h_parent; + h_nd.path.mnt = br->br_mnt; + + err = vfsub_name_hash(name->name, &h_nd.last, name->len); + h_dentry = ERR_PTR(err); + if (!err) { + path_get(&h_nd.path); + h_dentry = vfsub_lookup_hash(&h_nd); + path_put(&h_nd.path); + } + + AuTraceErrPtr(h_dentry); + return h_dentry; +} + +static void au_call_lkup_one(void *args) +{ + struct au_lkup_one_args *a = args; + *a->errp = au_lkup_one(a->name, a->h_parent, a->br, a->nd); +} + +#define AuLkup_ALLOW_NEG 1 +#define au_ftest_lkup(flags, name) ((flags) & AuLkup_##name) +#define au_fset_lkup(flags, name) \ + do { (flags) |= AuLkup_##name; } while (0) +#define au_fclr_lkup(flags, name) \ + do { (flags) &= ~AuLkup_##name; } while (0) + +struct au_do_lookup_args { + unsigned int flags; + mode_t type; + struct nameidata *nd; +}; + +/* + * returns positive/negative dentry, NULL or an error. + * NULL means whiteout-ed or not-found. + */ +static struct dentry* +au_do_lookup(struct dentry *h_parent, struct dentry *dentry, + aufs_bindex_t bindex, struct qstr *wh_name, + struct au_do_lookup_args *args) +{ + struct dentry *h_dentry; + struct inode *h_inode, *inode; + struct au_branch *br; + int wh_found, opq; + unsigned char wh_able; + const unsigned char allow_neg = !!au_ftest_lkup(args->flags, ALLOW_NEG); + + wh_found = 0; + br = au_sbr(dentry->d_sb, bindex); + wh_able = !!au_br_whable(br->br_perm); + if (wh_able) + wh_found = au_wh_test(h_parent, wh_name, br, /*try_sio*/0); + h_dentry = ERR_PTR(wh_found); + if (!wh_found) + goto real_lookup; + if (unlikely(wh_found < 0)) + goto out; + + /* We found a whiteout */ + /* au_set_dbend(dentry, bindex); */ + au_set_dbwh(dentry, bindex); + if (!allow_neg) + return NULL; /* success */ + +real_lookup: + h_dentry = au_lkup_one(&dentry->d_name, h_parent, br, args->nd); + if (IS_ERR(h_dentry)) + goto out; + + h_inode = h_dentry->d_inode; + if (!h_inode) { + if (!allow_neg) + goto out_neg; + } else if (wh_found + || (args->type && args->type != (h_inode->i_mode & S_IFMT))) + goto out_neg; + + if (au_dbend(dentry) <= bindex) + au_set_dbend(dentry, bindex); + if (au_dbstart(dentry) < 0 || bindex < au_dbstart(dentry)) + au_set_dbstart(dentry, bindex); + au_set_h_dptr(dentry, bindex, h_dentry); + + inode = dentry->d_inode; + if (!h_inode || !S_ISDIR(h_inode->i_mode) || !wh_able + || (inode && !S_ISDIR(inode->i_mode))) + goto out; /* success */ + + mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD); + opq = au_diropq_test(h_dentry, br); + mutex_unlock(&h_inode->i_mutex); + if (opq > 0) + au_set_dbdiropq(dentry, bindex); + else if (unlikely(opq < 0)) { + au_set_h_dptr(dentry, bindex, NULL); + h_dentry = ERR_PTR(opq); + } + goto out; + +out_neg: + dput(h_dentry); + h_dentry = NULL; +out: + return h_dentry; +} + +static int au_test_shwh(struct super_block *sb, const struct qstr *name) +{ + if (unlikely(!au_opt_test(au_mntflags(sb), SHWH) + && !strncmp(name->name, AUFS_WH_PFX, AUFS_WH_PFX_LEN))) + return -EPERM; + return 0; +} + +/* + * returns the number of lower positive dentries, + * otherwise an error. + * can be called at unlinking with @type is zero. + */ +int au_lkup_dentry(struct dentry *dentry, aufs_bindex_t bstart, mode_t type, + struct nameidata *nd) +{ + int npositive, err; + aufs_bindex_t bindex, btail, bdiropq; + unsigned char isdir; + struct qstr whname; + struct au_do_lookup_args args = { + .flags = 0, + .type = type, + .nd = nd + }; + const struct qstr *name = &dentry->d_name; + struct dentry *parent; + struct inode *inode; + + err = au_test_shwh(dentry->d_sb, name); + if (unlikely(err)) + goto out; + + err = au_wh_name_alloc(&whname, name); + if (unlikely(err)) + goto out; + + inode = dentry->d_inode; + isdir = !!(inode && S_ISDIR(inode->i_mode)); + if (!type) + au_fset_lkup(args.flags, ALLOW_NEG); + + npositive = 0; + parent = dget_parent(dentry); + btail = au_dbtaildir(parent); + for (bindex = bstart; bindex <= btail; bindex++) { + struct dentry *h_parent, *h_dentry; + struct inode *h_inode, *h_dir; + + h_dentry = au_h_dptr(dentry, bindex); + if (h_dentry) { + if (h_dentry->d_inode) + npositive++; + if (type != S_IFDIR) + break; + continue; + } + h_parent = au_h_dptr(parent, bindex); + if (!h_parent) + continue; + h_dir = h_parent->d_inode; + if (!h_dir || !S_ISDIR(h_dir->i_mode)) + continue; + + mutex_lock_nested(&h_dir->i_mutex, AuLsc_I_PARENT); + h_dentry = au_do_lookup(h_parent, dentry, bindex, &whname, + &args); + mutex_unlock(&h_dir->i_mutex); + err = PTR_ERR(h_dentry); + if (IS_ERR(h_dentry)) + goto out_parent; + au_fclr_lkup(args.flags, ALLOW_NEG); + + if (au_dbwh(dentry) >= 0) + break; + if (!h_dentry) + continue; + h_inode = h_dentry->d_inode; + if (!h_inode) + continue; + npositive++; + if (!args.type) + args.type = h_inode->i_mode & S_IFMT; + if (args.type != S_IFDIR) + break; + else if (isdir) { + /* the type of lower may be different */ + bdiropq = au_dbdiropq(dentry); + if (bdiropq >= 0 && bdiropq <= bindex) + break; + } + } + + if (npositive) { + AuLabel(positive); + au_update_dbstart(dentry); + } + err = npositive; + if (unlikely(!au_opt_test(au_mntflags(dentry->d_sb), UDBA_NONE) + && au_dbstart(dentry) < 0)) { + err = -EIO; + AuIOErr("both of real entry and whiteout found, %.*s, err %d\n", + AuDLNPair(dentry), err); + } + +out_parent: + dput(parent); + kfree(whname.name); +out: + return err; +} + +struct dentry *au_sio_lkup_one(struct qstr *name, struct dentry *parent, + struct au_branch *br) +{ + struct dentry *dentry; + int wkq_err; + + if (!au_test_h_perm_sio(parent->d_inode, MAY_EXEC)) + dentry = au_lkup_one(name, parent, br, /*nd*/NULL); + else { + struct au_lkup_one_args args = { + .errp = &dentry, + .name = name, + .h_parent = parent, + .br = br, + .nd = NULL + }; + + wkq_err = au_wkq_wait(au_call_lkup_one, &args); + if (unlikely(wkq_err)) + dentry = ERR_PTR(wkq_err); + } + + return dentry; +} + +/* + * lookup @dentry on @bindex which should be negative. + */ +int au_lkup_neg(struct dentry *dentry, aufs_bindex_t bindex) +{ + int err; + struct dentry *parent, *h_parent, *h_dentry; + + parent = dget_parent(dentry); + h_parent = au_h_dptr(parent, bindex); + h_dentry = au_sio_lkup_one(&dentry->d_name, h_parent, + au_sbr(dentry->d_sb, bindex)); + err = PTR_ERR(h_dentry); + if (IS_ERR(h_dentry)) + goto out; + if (unlikely(h_dentry->d_inode)) { + err = -EIO; + AuIOErr("%.*s should be negative on b%d.\n", + AuDLNPair(h_dentry), bindex); + dput(h_dentry); + goto out; + } + + err = 0; + if (bindex < au_dbstart(dentry)) + au_set_dbstart(dentry, bindex); + if (au_dbend(dentry) < bindex) + au_set_dbend(dentry, bindex); + au_set_h_dptr(dentry, bindex, h_dentry); + +out: + dput(parent); + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* subset of struct inode */ +struct au_iattr { + unsigned long i_ino; + /* unsigned int i_nlink; */ + uid_t i_uid; + gid_t i_gid; + u64 i_version; +/* + loff_t i_size; + blkcnt_t i_blocks; +*/ + umode_t i_mode; +}; + +static void au_iattr_save(struct au_iattr *ia, struct inode *h_inode) +{ + ia->i_ino = h_inode->i_ino; + /* ia->i_nlink = h_inode->i_nlink; */ + ia->i_uid = h_inode->i_uid; + ia->i_gid = h_inode->i_gid; + ia->i_version = h_inode->i_version; +/* + ia->i_size = h_inode->i_size; + ia->i_blocks = h_inode->i_blocks; +*/ + ia->i_mode = (h_inode->i_mode & S_IFMT); +} + +static int au_iattr_test(struct au_iattr *ia, struct inode *h_inode) +{ + return ia->i_ino != h_inode->i_ino + /* || ia->i_nlink != h_inode->i_nlink */ + || ia->i_uid != h_inode->i_uid + || ia->i_gid != h_inode->i_gid + || ia->i_version != h_inode->i_version +/* + || ia->i_size != h_inode->i_size + || ia->i_blocks != h_inode->i_blocks +*/ + || ia->i_mode != (h_inode->i_mode & S_IFMT); +} + +static int au_h_verify_dentry(struct dentry *h_dentry, struct dentry *h_parent, + struct au_branch *br) +{ + int err; + struct au_iattr ia; + struct inode *h_inode; + struct dentry *h_d; + struct super_block *h_sb; + + err = 0; + memset(&ia, -1, sizeof(ia)); + h_sb = h_dentry->d_sb; + h_inode = h_dentry->d_inode; + if (h_inode) + au_iattr_save(&ia, h_inode); + else if (au_test_nfs(h_sb) || au_test_fuse(h_sb)) + /* nfs d_revalidate may return 0 for negative dentry */ + /* fuse d_revalidate always return 0 for negative dentry */ + goto out; + + /* main purpose is namei.c:cached_lookup() and d_revalidate */ + h_d = au_lkup_one(&h_dentry->d_name, h_parent, br, /*nd*/NULL); + err = PTR_ERR(h_d); + if (IS_ERR(h_d)) + goto out; + + err = 0; + if (unlikely(h_d != h_dentry + || h_d->d_inode != h_inode + || (h_inode && au_iattr_test(&ia, h_inode)))) + err = au_busy_or_stale(); + dput(h_d); + +out: + AuTraceErr(err); + return err; +} + +int au_h_verify(struct dentry *h_dentry, unsigned int udba, struct inode *h_dir, + struct dentry *h_parent, struct au_branch *br) +{ + int err; + + err = 0; + if (udba == AuOpt_UDBA_REVAL + && !au_test_fs_remote(h_dentry->d_sb)) { + IMustLock(h_dir); + err = (h_dentry->d_parent->d_inode != h_dir); + } else if (udba != AuOpt_UDBA_NONE) + err = au_h_verify_dentry(h_dentry, h_parent, br); + + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int au_do_refresh_hdentry(struct dentry *dentry, struct dentry *parent) +{ + int err; + aufs_bindex_t new_bindex, bindex, bend, bwh, bdiropq; + struct au_hdentry tmp, *p, *q; + struct au_dinfo *dinfo; + struct super_block *sb; + + DiMustWriteLock(dentry); + + sb = dentry->d_sb; + dinfo = au_di(dentry); + bend = dinfo->di_bend; + bwh = dinfo->di_bwh; + bdiropq = dinfo->di_bdiropq; + p = dinfo->di_hdentry + dinfo->di_bstart; + for (bindex = dinfo->di_bstart; bindex <= bend; bindex++, p++) { + if (!p->hd_dentry) + continue; + + new_bindex = au_br_index(sb, p->hd_id); + if (new_bindex == bindex) + continue; + + if (dinfo->di_bwh == bindex) + bwh = new_bindex; + if (dinfo->di_bdiropq == bindex) + bdiropq = new_bindex; + if (new_bindex < 0) { + au_hdput(p); + p->hd_dentry = NULL; + continue; + } + + /* swap two lower dentries, and loop again */ + q = dinfo->di_hdentry + new_bindex; + tmp = *q; + *q = *p; + *p = tmp; + if (tmp.hd_dentry) { + bindex--; + p--; + } + } + + dinfo->di_bwh = -1; + if (bwh >= 0 && bwh <= au_sbend(sb) && au_sbr_whable(sb, bwh)) + dinfo->di_bwh = bwh; + + dinfo->di_bdiropq = -1; + if (bdiropq >= 0 + && bdiropq <= au_sbend(sb) + && au_sbr_whable(sb, bdiropq)) + dinfo->di_bdiropq = bdiropq; + + err = -EIO; + dinfo->di_bstart = -1; + dinfo->di_bend = -1; + bend = au_dbend(parent); + p = dinfo->di_hdentry; + for (bindex = 0; bindex <= bend; bindex++, p++) + if (p->hd_dentry) { + dinfo->di_bstart = bindex; + break; + } + + if (dinfo->di_bstart >= 0) { + p = dinfo->di_hdentry + bend; + for (bindex = bend; bindex >= 0; bindex--, p--) + if (p->hd_dentry) { + dinfo->di_bend = bindex; + err = 0; + break; + } + } + + return err; +} + +static void au_do_hide(struct dentry *dentry) +{ + struct inode *inode; + + inode = dentry->d_inode; + if (inode) { + if (!S_ISDIR(inode->i_mode)) { + if (inode->i_nlink && !d_unhashed(dentry)) + drop_nlink(inode); + } else { + clear_nlink(inode); + /* stop next lookup */ + inode->i_flags |= S_DEAD; + } + smp_mb(); /* necessary? */ + } + d_drop(dentry); +} + +static int au_hide_children(struct dentry *parent) +{ + int err, i, j, ndentry; + struct au_dcsub_pages dpages; + struct au_dpage *dpage; + struct dentry *dentry; + + err = au_dpages_init(&dpages, GFP_NOFS); + if (unlikely(err)) + goto out; + err = au_dcsub_pages(&dpages, parent, NULL, NULL); + if (unlikely(err)) + goto out_dpages; + + /* in reverse order */ + for (i = dpages.ndpage - 1; i >= 0; i--) { + dpage = dpages.dpages + i; + ndentry = dpage->ndentry; + for (j = ndentry - 1; j >= 0; j--) { + dentry = dpage->dentries[j]; + if (dentry != parent) + au_do_hide(dentry); + } + } + +out_dpages: + au_dpages_free(&dpages); +out: + return err; +} + +static void au_hide(struct dentry *dentry) +{ + int err; + struct inode *inode; + + AuDbgDentry(dentry); + inode = dentry->d_inode; + if (inode && S_ISDIR(inode->i_mode)) { + /* shrink_dcache_parent(dentry); */ + err = au_hide_children(dentry); + if (unlikely(err)) + AuIOErr("%.*s, failed hiding children, ignored %d\n", + AuDLNPair(dentry), err); + } + au_do_hide(dentry); +} + +/* + * By adding a dirty branch, a cached dentry may be affected in various ways. + * + * a dirty branch is added + * - on the top of layers + * - in the middle of layers + * - to the bottom of layers + * + * on the added branch there exists + * - a whiteout + * - a diropq + * - a same named entry + * + exist + * * negative --> positive + * * positive --> positive + * - type is unchanged + * - type is changed + * + doesn't exist + * * negative --> negative + * * positive --> negative (rejected by au_br_del() for non-dir case) + * - none + */ +static int au_refresh_by_dinfo(struct dentry *dentry, struct au_dinfo *dinfo, + struct au_dinfo *tmp) +{ + int err; + aufs_bindex_t bindex, bend; + struct { + struct dentry *dentry; + struct inode *inode; + mode_t mode; + } orig_h, tmp_h; + struct au_hdentry *hd; + struct inode *inode, *h_inode; + struct dentry *h_dentry; + + err = 0; + AuDebugOn(dinfo->di_bstart < 0); + orig_h.dentry = dinfo->di_hdentry[dinfo->di_bstart].hd_dentry; + orig_h.inode = orig_h.dentry->d_inode; + orig_h.mode = 0; + if (orig_h.inode) + orig_h.mode = orig_h.inode->i_mode & S_IFMT; + memset(&tmp_h, 0, sizeof(tmp_h)); + if (tmp->di_bstart >= 0) { + tmp_h.dentry = tmp->di_hdentry[tmp->di_bstart].hd_dentry; + tmp_h.inode = tmp_h.dentry->d_inode; + if (tmp_h.inode) + tmp_h.mode = tmp_h.inode->i_mode & S_IFMT; + } + + inode = dentry->d_inode; + if (!orig_h.inode) { + AuDbg("nagative originally\n"); + if (inode) { + au_hide(dentry); + goto out; + } + AuDebugOn(inode); + AuDebugOn(dinfo->di_bstart != dinfo->di_bend); + AuDebugOn(dinfo->di_bdiropq != -1); + + if (!tmp_h.inode) { + AuDbg("negative --> negative\n"); + /* should have only one negative lower */ + if (tmp->di_bstart >= 0 + && tmp->di_bstart < dinfo->di_bstart) { + AuDebugOn(tmp->di_bstart != tmp->di_bend); + AuDebugOn(dinfo->di_bstart != dinfo->di_bend); + au_set_h_dptr(dentry, dinfo->di_bstart, NULL); + au_di_cp(dinfo, tmp); + hd = tmp->di_hdentry + tmp->di_bstart; + au_set_h_dptr(dentry, tmp->di_bstart, + dget(hd->hd_dentry)); + } + au_dbg_verify_dinode(dentry); + } else { + AuDbg("negative --> positive\n"); + /* + * similar to the behaviour of creating with bypassing + * aufs. + * unhash it in order to force an error in the + * succeeding create operation. + * we should not set S_DEAD here. + */ + d_drop(dentry); + /* au_di_swap(tmp, dinfo); */ + au_dbg_verify_dinode(dentry); + } + } else { + AuDbg("positive originally\n"); + /* inode may be NULL */ + AuDebugOn(inode && (inode->i_mode & S_IFMT) != orig_h.mode); + if (!tmp_h.inode) { + AuDbg("positive --> negative\n"); + /* or bypassing aufs */ + au_hide(dentry); + if (tmp->di_bwh >= 0 && tmp->di_bwh <= dinfo->di_bstart) + dinfo->di_bwh = tmp->di_bwh; + if (inode) + err = au_refresh_hinode_self(inode); + au_dbg_verify_dinode(dentry); + } else if (orig_h.mode == tmp_h.mode) { + AuDbg("positive --> positive, same type\n"); + if (!S_ISDIR(orig_h.mode) + && dinfo->di_bstart > tmp->di_bstart) { + /* + * similar to the behaviour of removing and + * creating. + */ + au_hide(dentry); + if (inode) + err = au_refresh_hinode_self(inode); + au_dbg_verify_dinode(dentry); + } else { + /* fill empty slots */ + if (dinfo->di_bstart > tmp->di_bstart) + dinfo->di_bstart = tmp->di_bstart; + if (dinfo->di_bend < tmp->di_bend) + dinfo->di_bend = tmp->di_bend; + dinfo->di_bwh = tmp->di_bwh; + dinfo->di_bdiropq = tmp->di_bdiropq; + hd = tmp->di_hdentry; + bend = dinfo->di_bend; + for (bindex = tmp->di_bstart; bindex <= bend; + bindex++) { + if (au_h_dptr(dentry, bindex)) + continue; + h_dentry = hd[bindex].hd_dentry; + if (!h_dentry) + continue; + h_inode = h_dentry->d_inode; + AuDebugOn(!h_inode); + AuDebugOn(orig_h.mode + != (h_inode->i_mode + & S_IFMT)); + au_set_h_dptr(dentry, bindex, + dget(h_dentry)); + } + err = au_refresh_hinode(inode, dentry); + au_dbg_verify_dinode(dentry); + } + } else { + AuDbg("positive --> positive, different type\n"); + /* similar to the behaviour of removing and creating */ + au_hide(dentry); + if (inode) + err = au_refresh_hinode_self(inode); + au_dbg_verify_dinode(dentry); + } + } + +out: + return err; +} + +int au_refresh_dentry(struct dentry *dentry, struct dentry *parent) +{ + int err, ebrange; + unsigned int sigen; + struct au_dinfo *dinfo, *tmp; + struct super_block *sb; + struct inode *inode; + + DiMustWriteLock(dentry); + AuDebugOn(IS_ROOT(dentry)); + AuDebugOn(!parent->d_inode); + + sb = dentry->d_sb; + inode = dentry->d_inode; + sigen = au_sigen(sb); + err = au_digen_test(parent, sigen); + if (unlikely(err)) + goto out; + + dinfo = au_di(dentry); + err = au_di_realloc(dinfo, au_sbend(sb) + 1); + if (unlikely(err)) + goto out; + ebrange = au_dbrange_test(dentry); + if (!ebrange) + ebrange = au_do_refresh_hdentry(dentry, parent); + + if (d_unhashed(dentry) || ebrange) { + AuDebugOn(au_dbstart(dentry) < 0 && au_dbend(dentry) >= 0); + if (inode) + err = au_refresh_hinode_self(inode); + au_dbg_verify_dinode(dentry); + if (!err) + goto out_dgen; /* success */ + goto out; + } + + /* temporary dinfo */ + AuDbgDentry(dentry); + err = -ENOMEM; + tmp = au_di_alloc(sb, AuLsc_DI_TMP); + if (unlikely(!tmp)) + goto out; + au_di_swap(tmp, dinfo); + /* returns the number of positive dentries */ + /* + * if current working dir is removed, it returns an error. + * but the dentry is legal. + */ + err = au_lkup_dentry(dentry, /*bstart*/0, /*type*/0, /*nd*/NULL); + AuDbgDentry(dentry); + au_di_swap(tmp, dinfo); + if (err == -ENOENT) + err = 0; + if (err >= 0) { + /* compare/refresh by dinfo */ + AuDbgDentry(dentry); + err = au_refresh_by_dinfo(dentry, dinfo, tmp); + au_dbg_verify_dinode(dentry); + AuTraceErr(err); + } + au_rw_write_unlock(&tmp->di_rwsem); + au_di_free(tmp); + if (unlikely(err)) + goto out; + +out_dgen: + au_update_digen(dentry); +out: + if (unlikely(err && !(dentry->d_flags & DCACHE_NFSFS_RENAMED))) { + AuIOErr("failed refreshing %.*s, %d\n", + AuDLNPair(dentry), err); + AuDbgDentry(dentry); + } + AuTraceErr(err); + return err; +} + +static noinline_for_stack +int au_do_h_d_reval(struct dentry *h_dentry, struct nameidata *nd, + struct dentry *dentry, aufs_bindex_t bindex) +{ + int err, valid; + int (*reval)(struct dentry *, struct nameidata *); + + err = 0; + if (!(h_dentry->d_flags & DCACHE_OP_REVALIDATE)) + goto out; + reval = h_dentry->d_op->d_revalidate; + + AuDbg("b%d\n", bindex); + if (au_test_fs_null_nd(h_dentry->d_sb)) + /* it may return tri-state */ + valid = reval(h_dentry, NULL); + else { + struct nameidata h_nd; + int locked; + struct dentry *parent; + + au_h_nd(&h_nd, nd); + parent = nd->path.dentry; + locked = (nd && nd->path.dentry != dentry); + if (locked) + di_read_lock_parent(parent, AuLock_IR); + BUG_ON(bindex > au_dbend(parent)); + h_nd.path.dentry = au_h_dptr(parent, bindex); + BUG_ON(!h_nd.path.dentry); + h_nd.path.mnt = au_sbr(parent->d_sb, bindex)->br_mnt; + path_get(&h_nd.path); + valid = reval(h_dentry, &h_nd); + path_put(&h_nd.path); + if (locked) + di_read_unlock(parent, AuLock_IR); + } + + if (unlikely(valid < 0)) + err = valid; + else if (!valid) + err = -EINVAL; + +out: + AuTraceErr(err); + return err; +} + +/* todo: remove this */ +static int h_d_revalidate(struct dentry *dentry, struct inode *inode, + struct nameidata *nd, int do_udba) +{ + int err; + umode_t mode, h_mode; + aufs_bindex_t bindex, btail, bstart, ibs, ibe; + unsigned char plus, unhashed, is_root, h_plus; + struct inode *h_inode, *h_cached_inode; + struct dentry *h_dentry; + struct qstr *name, *h_name; + + err = 0; + plus = 0; + mode = 0; + ibs = -1; + ibe = -1; + unhashed = !!d_unhashed(dentry); + is_root = !!IS_ROOT(dentry); + name = &dentry->d_name; + + /* + * Theoretically, REVAL test should be unnecessary in case of + * {FS,I}NOTIFY. + * But {fs,i}notify doesn't fire some necessary events, + * IN_ATTRIB for atime/nlink/pageio + * IN_DELETE for NFS dentry + * Let's do REVAL test too. + */ + if (do_udba && inode) { + mode = (inode->i_mode & S_IFMT); + plus = (inode->i_nlink > 0); + ibs = au_ibstart(inode); + ibe = au_ibend(inode); + } + + bstart = au_dbstart(dentry); + btail = bstart; + if (inode && S_ISDIR(inode->i_mode)) + btail = au_dbtaildir(dentry); + for (bindex = bstart; bindex <= btail; bindex++) { + h_dentry = au_h_dptr(dentry, bindex); + if (!h_dentry) + continue; + + AuDbg("b%d, %.*s\n", bindex, AuDLNPair(h_dentry)); + spin_lock(&h_dentry->d_lock); + h_name = &h_dentry->d_name; + if (unlikely(do_udba + && !is_root + && (unhashed != !!d_unhashed(h_dentry) + || name->len != h_name->len + || memcmp(name->name, h_name->name, name->len)) + )) { + AuDbg("unhash 0x%x 0x%x, %.*s %.*s\n", + unhashed, d_unhashed(h_dentry), + AuDLNPair(dentry), AuDLNPair(h_dentry)); + spin_unlock(&h_dentry->d_lock); + goto err; + } + spin_unlock(&h_dentry->d_lock); + + err = au_do_h_d_reval(h_dentry, nd, dentry, bindex); + if (unlikely(err)) + /* do not goto err, to keep the errno */ + break; + + /* todo: plink too? */ + if (!do_udba) + continue; + + /* UDBA tests */ + h_inode = h_dentry->d_inode; + if (unlikely(!!inode != !!h_inode)) + goto err; + + h_plus = plus; + h_mode = mode; + h_cached_inode = h_inode; + if (h_inode) { + h_mode = (h_inode->i_mode & S_IFMT); + h_plus = (h_inode->i_nlink > 0); + } + if (inode && ibs <= bindex && bindex <= ibe) + h_cached_inode = au_h_iptr(inode, bindex); + + if (unlikely(plus != h_plus + || mode != h_mode + || h_cached_inode != h_inode)) + goto err; + continue; + + err: + err = -EINVAL; + break; + } + + return err; +} + +/* todo: consolidate with do_refresh() and au_reval_for_attr() */ +static int simple_reval_dpath(struct dentry *dentry, unsigned int sigen) +{ + int err; + struct dentry *parent; + + if (!au_digen_test(dentry, sigen)) + return 0; + + parent = dget_parent(dentry); + di_read_lock_parent(parent, AuLock_IR); + AuDebugOn(au_digen_test(parent, sigen)); + au_dbg_verify_gen(parent, sigen); + err = au_refresh_dentry(dentry, parent); + di_read_unlock(parent, AuLock_IR); + dput(parent); + AuTraceErr(err); + return err; +} + +int au_reval_dpath(struct dentry *dentry, unsigned int sigen) +{ + int err; + struct dentry *d, *parent; + struct inode *inode; + + if (!au_ftest_si(au_sbi(dentry->d_sb), FAILED_REFRESH_DIR)) + return simple_reval_dpath(dentry, sigen); + + /* slow loop, keep it simple and stupid */ + /* cf: au_cpup_dirs() */ + err = 0; + parent = NULL; + while (au_digen_test(dentry, sigen)) { + d = dentry; + while (1) { + dput(parent); + parent = dget_parent(d); + if (!au_digen_test(parent, sigen)) + break; + d = parent; + } + + inode = d->d_inode; + if (d != dentry) + di_write_lock_child2(d); + + /* someone might update our dentry while we were sleeping */ + if (au_digen_test(d, sigen)) { + /* + * todo: consolidate with simple_reval_dpath(), + * do_refresh() and au_reval_for_attr(). + */ + di_read_lock_parent(parent, AuLock_IR); + err = au_refresh_dentry(d, parent); + di_read_unlock(parent, AuLock_IR); + } + + if (d != dentry) + di_write_unlock(d); + dput(parent); + if (unlikely(err)) + break; + } + + return err; +} + +/* + * if valid returns 1, otherwise 0. + */ +static int aufs_d_revalidate(struct dentry *dentry, struct nameidata *nd) +{ + int valid, err; + unsigned int sigen; + unsigned char do_udba; + struct super_block *sb; + struct inode *inode; + + /* todo: support rcu-walk? */ + if (nd && (nd->flags & LOOKUP_RCU)) + return -ECHILD; + + valid = 0; + if (unlikely(!au_di(dentry))) + goto out; + + inode = dentry->d_inode; + if (inode && is_bad_inode(inode)) + goto out; + + valid = 1; + sb = dentry->d_sb; + /* + * todo: very ugly + * i_mutex of parent dir may be held, + * but we should not return 'invalid' due to busy. + */ + err = aufs_read_lock(dentry, AuLock_FLUSH | AuLock_DW | AuLock_NOPLM); + if (unlikely(err)) { + valid = err; + AuTraceErr(err); + goto out; + } + if (unlikely(au_dbrange_test(dentry))) { + err = -EINVAL; + AuTraceErr(err); + goto out_dgrade; + } + + sigen = au_sigen(sb); + if (au_digen_test(dentry, sigen)) { + AuDebugOn(IS_ROOT(dentry)); + err = au_reval_dpath(dentry, sigen); + if (unlikely(err)) { + AuTraceErr(err); + goto out_dgrade; + } + } + di_downgrade_lock(dentry, AuLock_IR); + + err = -EINVAL; + if (inode && (IS_DEADDIR(inode) || !inode->i_nlink)) + goto out_inval; + + do_udba = !au_opt_test(au_mntflags(sb), UDBA_NONE); + if (do_udba && inode) { + aufs_bindex_t bstart = au_ibstart(inode); + struct inode *h_inode; + + if (bstart >= 0) { + h_inode = au_h_iptr(inode, bstart); + if (h_inode && au_test_higen(inode, h_inode)) + goto out_inval; + } + } + + err = h_d_revalidate(dentry, inode, nd, do_udba); + if (unlikely(!err && do_udba && au_dbstart(dentry) < 0)) { + err = -EIO; + AuDbg("both of real entry and whiteout found, %.*s, err %d\n", + AuDLNPair(dentry), err); + } + goto out_inval; + +out_dgrade: + di_downgrade_lock(dentry, AuLock_IR); +out_inval: + aufs_read_unlock(dentry, AuLock_IR); + AuTraceErr(err); + valid = !err; +out: + if (!valid) { + AuDbg("%.*s invalid, %d\n", AuDLNPair(dentry), valid); + d_drop(dentry); + } + return valid; +} + +static void aufs_d_release(struct dentry *dentry) +{ + if (au_di(dentry)) { + au_di_fin(dentry); + au_hn_di_reinit(dentry); + } +} + +const struct dentry_operations aufs_dop = { + .d_revalidate = aufs_d_revalidate, + .d_release = aufs_d_release +}; diff --git a/ubuntu/aufs/dentry.h b/ubuntu/aufs/dentry.h new file mode 100644 index 000000000000..bbd9dc643efd --- /dev/null +++ b/ubuntu/aufs/dentry.h @@ -0,0 +1,237 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * lookup and dentry operations + */ + +#ifndef __AUFS_DENTRY_H__ +#define __AUFS_DENTRY_H__ + +#ifdef __KERNEL__ + +#include <linux/dcache.h> +#include "rwsem.h" + +struct au_hdentry { + struct dentry *hd_dentry; + aufs_bindex_t hd_id; +}; + +struct au_dinfo { + atomic_t di_generation; + + struct au_rwsem di_rwsem; + aufs_bindex_t di_bstart, di_bend, di_bwh, di_bdiropq; + struct au_hdentry *di_hdentry; +} ____cacheline_aligned_in_smp; + +/* ---------------------------------------------------------------------- */ + +/* dentry.c */ +extern const struct dentry_operations aufs_dop; +struct au_branch; +struct dentry *au_lkup_one(struct qstr *name, struct dentry *h_parent, + struct au_branch *br, struct nameidata *nd); +struct dentry *au_sio_lkup_one(struct qstr *name, struct dentry *parent, + struct au_branch *br); +int au_h_verify(struct dentry *h_dentry, unsigned int udba, struct inode *h_dir, + struct dentry *h_parent, struct au_branch *br); + +int au_lkup_dentry(struct dentry *dentry, aufs_bindex_t bstart, mode_t type, + struct nameidata *nd); +int au_lkup_neg(struct dentry *dentry, aufs_bindex_t bindex); +int au_refresh_dentry(struct dentry *dentry, struct dentry *parent); +int au_reval_dpath(struct dentry *dentry, unsigned int sigen); + +/* dinfo.c */ +void au_di_init_once(void *_di); +struct au_dinfo *au_di_alloc(struct super_block *sb, unsigned int lsc); +void au_di_free(struct au_dinfo *dinfo); +void au_di_swap(struct au_dinfo *a, struct au_dinfo *b); +void au_di_cp(struct au_dinfo *dst, struct au_dinfo *src); +int au_di_init(struct dentry *dentry); +void au_di_fin(struct dentry *dentry); +int au_di_realloc(struct au_dinfo *dinfo, int nbr); + +void di_read_lock(struct dentry *d, int flags, unsigned int lsc); +void di_read_unlock(struct dentry *d, int flags); +void di_downgrade_lock(struct dentry *d, int flags); +void di_write_lock(struct dentry *d, unsigned int lsc); +void di_write_unlock(struct dentry *d); +void di_write_lock2_child(struct dentry *d1, struct dentry *d2, int isdir); +void di_write_lock2_parent(struct dentry *d1, struct dentry *d2, int isdir); +void di_write_unlock2(struct dentry *d1, struct dentry *d2); + +struct dentry *au_h_dptr(struct dentry *dentry, aufs_bindex_t bindex); +struct dentry *au_h_d_alias(struct dentry *dentry, aufs_bindex_t bindex); +aufs_bindex_t au_dbtail(struct dentry *dentry); +aufs_bindex_t au_dbtaildir(struct dentry *dentry); + +void au_set_h_dptr(struct dentry *dentry, aufs_bindex_t bindex, + struct dentry *h_dentry); +int au_digen_test(struct dentry *dentry, unsigned int sigen); +int au_dbrange_test(struct dentry *dentry); +void au_update_digen(struct dentry *dentry); +void au_update_dbrange(struct dentry *dentry, int do_put_zero); +void au_update_dbstart(struct dentry *dentry); +void au_update_dbend(struct dentry *dentry); +int au_find_dbindex(struct dentry *dentry, struct dentry *h_dentry); + +/* ---------------------------------------------------------------------- */ + +static inline struct au_dinfo *au_di(struct dentry *dentry) +{ + return dentry->d_fsdata; +} + +/* ---------------------------------------------------------------------- */ + +/* lock subclass for dinfo */ +enum { + AuLsc_DI_CHILD, /* child first */ + AuLsc_DI_CHILD2, /* rename(2), link(2), and cpup at hnotify */ + AuLsc_DI_CHILD3, /* copyup dirs */ + AuLsc_DI_PARENT, + AuLsc_DI_PARENT2, + AuLsc_DI_PARENT3, + AuLsc_DI_TMP /* temp for replacing dinfo */ +}; + +/* + * di_read_lock_child, di_write_lock_child, + * di_read_lock_child2, di_write_lock_child2, + * di_read_lock_child3, di_write_lock_child3, + * di_read_lock_parent, di_write_lock_parent, + * di_read_lock_parent2, di_write_lock_parent2, + * di_read_lock_parent3, di_write_lock_parent3, + */ +#define AuReadLockFunc(name, lsc) \ +static inline void di_read_lock_##name(struct dentry *d, int flags) \ +{ di_read_lock(d, flags, AuLsc_DI_##lsc); } + +#define AuWriteLockFunc(name, lsc) \ +static inline void di_write_lock_##name(struct dentry *d) \ +{ di_write_lock(d, AuLsc_DI_##lsc); } + +#define AuRWLockFuncs(name, lsc) \ + AuReadLockFunc(name, lsc) \ + AuWriteLockFunc(name, lsc) + +AuRWLockFuncs(child, CHILD); +AuRWLockFuncs(child2, CHILD2); +AuRWLockFuncs(child3, CHILD3); +AuRWLockFuncs(parent, PARENT); +AuRWLockFuncs(parent2, PARENT2); +AuRWLockFuncs(parent3, PARENT3); + +#undef AuReadLockFunc +#undef AuWriteLockFunc +#undef AuRWLockFuncs + +#define DiMustNoWaiters(d) AuRwMustNoWaiters(&au_di(d)->di_rwsem) +#define DiMustAnyLock(d) AuRwMustAnyLock(&au_di(d)->di_rwsem) +#define DiMustWriteLock(d) AuRwMustWriteLock(&au_di(d)->di_rwsem) + +/* ---------------------------------------------------------------------- */ + +/* todo: memory barrier? */ +static inline unsigned int au_digen(struct dentry *d) +{ + return atomic_read(&au_di(d)->di_generation); +} + +static inline void au_h_dentry_init(struct au_hdentry *hdentry) +{ + hdentry->hd_dentry = NULL; +} + +static inline void au_hdput(struct au_hdentry *hd) +{ + if (hd) + dput(hd->hd_dentry); +} + +static inline aufs_bindex_t au_dbstart(struct dentry *dentry) +{ + DiMustAnyLock(dentry); + return au_di(dentry)->di_bstart; +} + +static inline aufs_bindex_t au_dbend(struct dentry *dentry) +{ + DiMustAnyLock(dentry); + return au_di(dentry)->di_bend; +} + +static inline aufs_bindex_t au_dbwh(struct dentry *dentry) +{ + DiMustAnyLock(dentry); + return au_di(dentry)->di_bwh; +} + +static inline aufs_bindex_t au_dbdiropq(struct dentry *dentry) +{ + DiMustAnyLock(dentry); + return au_di(dentry)->di_bdiropq; +} + +/* todo: hard/soft set? */ +static inline void au_set_dbstart(struct dentry *dentry, aufs_bindex_t bindex) +{ + DiMustWriteLock(dentry); + au_di(dentry)->di_bstart = bindex; +} + +static inline void au_set_dbend(struct dentry *dentry, aufs_bindex_t bindex) +{ + DiMustWriteLock(dentry); + au_di(dentry)->di_bend = bindex; +} + +static inline void au_set_dbwh(struct dentry *dentry, aufs_bindex_t bindex) +{ + DiMustWriteLock(dentry); + /* dbwh can be outside of bstart - bend range */ + au_di(dentry)->di_bwh = bindex; +} + +static inline void au_set_dbdiropq(struct dentry *dentry, aufs_bindex_t bindex) +{ + DiMustWriteLock(dentry); + au_di(dentry)->di_bdiropq = bindex; +} + +/* ---------------------------------------------------------------------- */ + +#ifdef CONFIG_AUFS_HNOTIFY +static inline void au_digen_dec(struct dentry *d) +{ + atomic_dec(&au_di(d)->di_generation); +} + +static inline void au_hn_di_reinit(struct dentry *dentry) +{ + dentry->d_fsdata = NULL; +} +#else +AuStubVoid(au_hn_di_reinit, struct dentry *dentry __maybe_unused) +#endif /* CONFIG_AUFS_HNOTIFY */ + +#endif /* __KERNEL__ */ +#endif /* __AUFS_DENTRY_H__ */ diff --git a/ubuntu/aufs/dinfo.c b/ubuntu/aufs/dinfo.c new file mode 100644 index 000000000000..24f22a91d21e --- /dev/null +++ b/ubuntu/aufs/dinfo.c @@ -0,0 +1,543 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * dentry private data + */ + +#include "aufs.h" + +void au_di_init_once(void *_dinfo) +{ + struct au_dinfo *dinfo = _dinfo; + static struct lock_class_key aufs_di; + + au_rw_init(&dinfo->di_rwsem); + au_rw_class(&dinfo->di_rwsem, &aufs_di); +} + +struct au_dinfo *au_di_alloc(struct super_block *sb, unsigned int lsc) +{ + struct au_dinfo *dinfo; + int nbr, i; + + dinfo = au_cache_alloc_dinfo(); + if (unlikely(!dinfo)) + goto out; + + nbr = au_sbend(sb) + 1; + if (nbr <= 0) + nbr = 1; + dinfo->di_hdentry = kcalloc(nbr, sizeof(*dinfo->di_hdentry), GFP_NOFS); + if (dinfo->di_hdentry) { + au_rw_write_lock_nested(&dinfo->di_rwsem, lsc); + dinfo->di_bstart = -1; + dinfo->di_bend = -1; + dinfo->di_bwh = -1; + dinfo->di_bdiropq = -1; + for (i = 0; i < nbr; i++) + dinfo->di_hdentry[i].hd_id = -1; + goto out; + } + + au_cache_free_dinfo(dinfo); + dinfo = NULL; + +out: + return dinfo; +} + +void au_di_free(struct au_dinfo *dinfo) +{ + struct au_hdentry *p; + aufs_bindex_t bend, bindex; + + /* dentry may not be revalidated */ + bindex = dinfo->di_bstart; + if (bindex >= 0) { + bend = dinfo->di_bend; + p = dinfo->di_hdentry + bindex; + while (bindex++ <= bend) + au_hdput(p++); + } + kfree(dinfo->di_hdentry); + au_cache_free_dinfo(dinfo); +} + +void au_di_swap(struct au_dinfo *a, struct au_dinfo *b) +{ + struct au_hdentry *p; + aufs_bindex_t bi; + + AuRwMustWriteLock(&a->di_rwsem); + AuRwMustWriteLock(&b->di_rwsem); + +#define DiSwap(v, name) \ + do { \ + v = a->di_##name; \ + a->di_##name = b->di_##name; \ + b->di_##name = v; \ + } while (0) + + DiSwap(p, hdentry); + DiSwap(bi, bstart); + DiSwap(bi, bend); + DiSwap(bi, bwh); + DiSwap(bi, bdiropq); + /* smp_mb(); */ + +#undef DiSwap +} + +void au_di_cp(struct au_dinfo *dst, struct au_dinfo *src) +{ + AuRwMustWriteLock(&dst->di_rwsem); + AuRwMustWriteLock(&src->di_rwsem); + + dst->di_bstart = src->di_bstart; + dst->di_bend = src->di_bend; + dst->di_bwh = src->di_bwh; + dst->di_bdiropq = src->di_bdiropq; + /* smp_mb(); */ +} + +int au_di_init(struct dentry *dentry) +{ + int err; + struct super_block *sb; + struct au_dinfo *dinfo; + + err = 0; + sb = dentry->d_sb; + dinfo = au_di_alloc(sb, AuLsc_DI_CHILD); + if (dinfo) { + atomic_set(&dinfo->di_generation, au_sigen(sb)); + /* smp_mb(); */ /* atomic_set */ + dentry->d_fsdata = dinfo; + } else + err = -ENOMEM; + + return err; +} + +void au_di_fin(struct dentry *dentry) +{ + struct au_dinfo *dinfo; + + dinfo = au_di(dentry); + AuRwDestroy(&dinfo->di_rwsem); + au_di_free(dinfo); +} + +int au_di_realloc(struct au_dinfo *dinfo, int nbr) +{ + int err, sz; + struct au_hdentry *hdp; + + AuRwMustWriteLock(&dinfo->di_rwsem); + + err = -ENOMEM; + sz = sizeof(*hdp) * (dinfo->di_bend + 1); + if (!sz) + sz = sizeof(*hdp); + hdp = au_kzrealloc(dinfo->di_hdentry, sz, sizeof(*hdp) * nbr, GFP_NOFS); + if (hdp) { + dinfo->di_hdentry = hdp; + err = 0; + } + + return err; +} + +/* ---------------------------------------------------------------------- */ + +static void do_ii_write_lock(struct inode *inode, unsigned int lsc) +{ + switch (lsc) { + case AuLsc_DI_CHILD: + ii_write_lock_child(inode); + break; + case AuLsc_DI_CHILD2: + ii_write_lock_child2(inode); + break; + case AuLsc_DI_CHILD3: + ii_write_lock_child3(inode); + break; + case AuLsc_DI_PARENT: + ii_write_lock_parent(inode); + break; + case AuLsc_DI_PARENT2: + ii_write_lock_parent2(inode); + break; + case AuLsc_DI_PARENT3: + ii_write_lock_parent3(inode); + break; + default: + BUG(); + } +} + +static void do_ii_read_lock(struct inode *inode, unsigned int lsc) +{ + switch (lsc) { + case AuLsc_DI_CHILD: + ii_read_lock_child(inode); + break; + case AuLsc_DI_CHILD2: + ii_read_lock_child2(inode); + break; + case AuLsc_DI_CHILD3: + ii_read_lock_child3(inode); + break; + case AuLsc_DI_PARENT: + ii_read_lock_parent(inode); + break; + case AuLsc_DI_PARENT2: + ii_read_lock_parent2(inode); + break; + case AuLsc_DI_PARENT3: + ii_read_lock_parent3(inode); + break; + default: + BUG(); + } +} + +void di_read_lock(struct dentry *d, int flags, unsigned int lsc) +{ + au_rw_read_lock_nested(&au_di(d)->di_rwsem, lsc); + if (d->d_inode) { + if (au_ftest_lock(flags, IW)) + do_ii_write_lock(d->d_inode, lsc); + else if (au_ftest_lock(flags, IR)) + do_ii_read_lock(d->d_inode, lsc); + } +} + +void di_read_unlock(struct dentry *d, int flags) +{ + if (d->d_inode) { + if (au_ftest_lock(flags, IW)) { + au_dbg_verify_dinode(d); + ii_write_unlock(d->d_inode); + } else if (au_ftest_lock(flags, IR)) { + au_dbg_verify_dinode(d); + ii_read_unlock(d->d_inode); + } + } + au_rw_read_unlock(&au_di(d)->di_rwsem); +} + +void di_downgrade_lock(struct dentry *d, int flags) +{ + if (d->d_inode && au_ftest_lock(flags, IR)) + ii_downgrade_lock(d->d_inode); + au_rw_dgrade_lock(&au_di(d)->di_rwsem); +} + +void di_write_lock(struct dentry *d, unsigned int lsc) +{ + au_rw_write_lock_nested(&au_di(d)->di_rwsem, lsc); + if (d->d_inode) + do_ii_write_lock(d->d_inode, lsc); +} + +void di_write_unlock(struct dentry *d) +{ + au_dbg_verify_dinode(d); + if (d->d_inode) + ii_write_unlock(d->d_inode); + au_rw_write_unlock(&au_di(d)->di_rwsem); +} + +void di_write_lock2_child(struct dentry *d1, struct dentry *d2, int isdir) +{ + AuDebugOn(d1 == d2 + || d1->d_inode == d2->d_inode + || d1->d_sb != d2->d_sb); + + if (isdir && au_test_subdir(d1, d2)) { + di_write_lock_child(d1); + di_write_lock_child2(d2); + } else { + /* there should be no races */ + di_write_lock_child(d2); + di_write_lock_child2(d1); + } +} + +void di_write_lock2_parent(struct dentry *d1, struct dentry *d2, int isdir) +{ + AuDebugOn(d1 == d2 + || d1->d_inode == d2->d_inode + || d1->d_sb != d2->d_sb); + + if (isdir && au_test_subdir(d1, d2)) { + di_write_lock_parent(d1); + di_write_lock_parent2(d2); + } else { + /* there should be no races */ + di_write_lock_parent(d2); + di_write_lock_parent2(d1); + } +} + +void di_write_unlock2(struct dentry *d1, struct dentry *d2) +{ + di_write_unlock(d1); + if (d1->d_inode == d2->d_inode) + au_rw_write_unlock(&au_di(d2)->di_rwsem); + else + di_write_unlock(d2); +} + +/* ---------------------------------------------------------------------- */ + +struct dentry *au_h_dptr(struct dentry *dentry, aufs_bindex_t bindex) +{ + struct dentry *d; + + DiMustAnyLock(dentry); + + if (au_dbstart(dentry) < 0 || bindex < au_dbstart(dentry)) + return NULL; + AuDebugOn(bindex < 0); + d = au_di(dentry)->di_hdentry[0 + bindex].hd_dentry; + AuDebugOn(d && d->d_count <= 0); + return d; +} + +/* + * extended version of au_h_dptr(). + * returns a hashed and positive h_dentry in bindex, NULL, or error. + */ +struct dentry *au_h_d_alias(struct dentry *dentry, aufs_bindex_t bindex) +{ + struct dentry *h_dentry; + struct inode *inode, *h_inode; + + inode = dentry->d_inode; + AuDebugOn(!inode); + + h_dentry = NULL; + if (au_dbstart(dentry) <= bindex + && bindex <= au_dbend(dentry)) + h_dentry = au_h_dptr(dentry, bindex); + if (h_dentry && !au_d_hashed_positive(h_dentry)) { + dget(h_dentry); + goto out; /* success */ + } + + AuDebugOn(bindex < au_ibstart(inode)); + AuDebugOn(au_ibend(inode) < bindex); + h_inode = au_h_iptr(inode, bindex); + h_dentry = d_find_alias(h_inode); + if (h_dentry) { + if (!IS_ERR(h_dentry)) { + if (!au_d_hashed_positive(h_dentry)) + goto out; /* success */ + dput(h_dentry); + } else + goto out; + } + + if (au_opt_test(au_mntflags(dentry->d_sb), PLINK)) { + h_dentry = au_plink_lkup(inode, bindex); + AuDebugOn(!h_dentry); + if (!IS_ERR(h_dentry)) { + if (!au_d_hashed_positive(h_dentry)) + goto out; /* success */ + dput(h_dentry); + h_dentry = NULL; + } + } + +out: + AuDbgDentry(h_dentry); + return h_dentry; +} + +aufs_bindex_t au_dbtail(struct dentry *dentry) +{ + aufs_bindex_t bend, bwh; + + bend = au_dbend(dentry); + if (0 <= bend) { + bwh = au_dbwh(dentry); + if (!bwh) + return bwh; + if (0 < bwh && bwh < bend) + return bwh - 1; + } + return bend; +} + +aufs_bindex_t au_dbtaildir(struct dentry *dentry) +{ + aufs_bindex_t bend, bopq; + + bend = au_dbtail(dentry); + if (0 <= bend) { + bopq = au_dbdiropq(dentry); + if (0 <= bopq && bopq < bend) + bend = bopq; + } + return bend; +} + +/* ---------------------------------------------------------------------- */ + +void au_set_h_dptr(struct dentry *dentry, aufs_bindex_t bindex, + struct dentry *h_dentry) +{ + struct au_hdentry *hd = au_di(dentry)->di_hdentry + bindex; + struct au_branch *br; + + DiMustWriteLock(dentry); + + au_hdput(hd); + hd->hd_dentry = h_dentry; + if (h_dentry) { + br = au_sbr(dentry->d_sb, bindex); + hd->hd_id = br->br_id; + } +} + +int au_dbrange_test(struct dentry *dentry) +{ + int err; + aufs_bindex_t bstart, bend; + + err = 0; + bstart = au_dbstart(dentry); + bend = au_dbend(dentry); + if (bstart >= 0) + AuDebugOn(bend < 0 && bstart > bend); + else { + err = -EIO; + AuDebugOn(bend >= 0); + } + + return err; +} + +int au_digen_test(struct dentry *dentry, unsigned int sigen) +{ + int err; + + err = 0; + if (unlikely(au_digen(dentry) != sigen + || au_iigen_test(dentry->d_inode, sigen))) + err = -EIO; + + return err; +} + +void au_update_digen(struct dentry *dentry) +{ + atomic_set(&au_di(dentry)->di_generation, au_sigen(dentry->d_sb)); + /* smp_mb(); */ /* atomic_set */ +} + +void au_update_dbrange(struct dentry *dentry, int do_put_zero) +{ + struct au_dinfo *dinfo; + struct dentry *h_d; + struct au_hdentry *hdp; + + DiMustWriteLock(dentry); + + dinfo = au_di(dentry); + if (!dinfo || dinfo->di_bstart < 0) + return; + + hdp = dinfo->di_hdentry; + if (do_put_zero) { + aufs_bindex_t bindex, bend; + + bend = dinfo->di_bend; + for (bindex = dinfo->di_bstart; bindex <= bend; bindex++) { + h_d = hdp[0 + bindex].hd_dentry; + if (h_d && !h_d->d_inode) + au_set_h_dptr(dentry, bindex, NULL); + } + } + + dinfo->di_bstart = -1; + while (++dinfo->di_bstart <= dinfo->di_bend) + if (hdp[0 + dinfo->di_bstart].hd_dentry) + break; + if (dinfo->di_bstart > dinfo->di_bend) { + dinfo->di_bstart = -1; + dinfo->di_bend = -1; + return; + } + + dinfo->di_bend++; + while (0 <= --dinfo->di_bend) + if (hdp[0 + dinfo->di_bend].hd_dentry) + break; + AuDebugOn(dinfo->di_bstart > dinfo->di_bend || dinfo->di_bend < 0); +} + +void au_update_dbstart(struct dentry *dentry) +{ + aufs_bindex_t bindex, bend; + struct dentry *h_dentry; + + bend = au_dbend(dentry); + for (bindex = au_dbstart(dentry); bindex <= bend; bindex++) { + h_dentry = au_h_dptr(dentry, bindex); + if (!h_dentry) + continue; + if (h_dentry->d_inode) { + au_set_dbstart(dentry, bindex); + return; + } + au_set_h_dptr(dentry, bindex, NULL); + } +} + +void au_update_dbend(struct dentry *dentry) +{ + aufs_bindex_t bindex, bstart; + struct dentry *h_dentry; + + bstart = au_dbstart(dentry); + for (bindex = au_dbend(dentry); bindex >= bstart; bindex--) { + h_dentry = au_h_dptr(dentry, bindex); + if (!h_dentry) + continue; + if (h_dentry->d_inode) { + au_set_dbend(dentry, bindex); + return; + } + au_set_h_dptr(dentry, bindex, NULL); + } +} + +int au_find_dbindex(struct dentry *dentry, struct dentry *h_dentry) +{ + aufs_bindex_t bindex, bend; + + bend = au_dbend(dentry); + for (bindex = au_dbstart(dentry); bindex <= bend; bindex++) + if (au_h_dptr(dentry, bindex) == h_dentry) + return bindex; + return -1; +} diff --git a/ubuntu/aufs/dir.c b/ubuntu/aufs/dir.c new file mode 100644 index 000000000000..ec5a236b46d2 --- /dev/null +++ b/ubuntu/aufs/dir.c @@ -0,0 +1,634 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * directory operations + */ + +#include <linux/fs_stack.h> +#include "aufs.h" + +void au_add_nlink(struct inode *dir, struct inode *h_dir) +{ + unsigned int nlink; + + AuDebugOn(!S_ISDIR(dir->i_mode) || !S_ISDIR(h_dir->i_mode)); + + nlink = dir->i_nlink; + nlink += h_dir->i_nlink - 2; + if (h_dir->i_nlink < 2) + nlink += 2; + set_nlink(dir, nlink); +} + +void au_sub_nlink(struct inode *dir, struct inode *h_dir) +{ + unsigned int nlink; + + AuDebugOn(!S_ISDIR(dir->i_mode) || !S_ISDIR(h_dir->i_mode)); + + nlink = dir->i_nlink; + nlink -= h_dir->i_nlink - 2; + if (h_dir->i_nlink < 2) + nlink -= 2; + set_nlink(dir, nlink); +} + +loff_t au_dir_size(struct file *file, struct dentry *dentry) +{ + loff_t sz; + aufs_bindex_t bindex, bend; + struct file *h_file; + struct dentry *h_dentry; + + sz = 0; + if (file) { + AuDebugOn(!file->f_dentry); + AuDebugOn(!file->f_dentry->d_inode); + AuDebugOn(!S_ISDIR(file->f_dentry->d_inode->i_mode)); + + bend = au_fbend_dir(file); + for (bindex = au_fbstart(file); + bindex <= bend && sz < KMALLOC_MAX_SIZE; + bindex++) { + h_file = au_hf_dir(file, bindex); + if (h_file + && h_file->f_dentry + && h_file->f_dentry->d_inode) + sz += i_size_read(h_file->f_dentry->d_inode); + } + } else { + AuDebugOn(!dentry); + AuDebugOn(!dentry->d_inode); + AuDebugOn(!S_ISDIR(dentry->d_inode->i_mode)); + + bend = au_dbtaildir(dentry); + for (bindex = au_dbstart(dentry); + bindex <= bend && sz < KMALLOC_MAX_SIZE; + bindex++) { + h_dentry = au_h_dptr(dentry, bindex); + if (h_dentry && h_dentry->d_inode) + sz += i_size_read(h_dentry->d_inode); + } + } + if (sz < KMALLOC_MAX_SIZE) + sz = roundup_pow_of_two(sz); + if (sz > KMALLOC_MAX_SIZE) + sz = KMALLOC_MAX_SIZE; + else if (sz < NAME_MAX) { + BUILD_BUG_ON(AUFS_RDBLK_DEF < NAME_MAX); + sz = AUFS_RDBLK_DEF; + } + return sz; +} + +/* ---------------------------------------------------------------------- */ + +static int reopen_dir(struct file *file) +{ + int err; + unsigned int flags; + aufs_bindex_t bindex, btail, bstart; + struct dentry *dentry, *h_dentry; + struct file *h_file; + + /* open all lower dirs */ + dentry = file->f_dentry; + bstart = au_dbstart(dentry); + for (bindex = au_fbstart(file); bindex < bstart; bindex++) + au_set_h_fptr(file, bindex, NULL); + au_set_fbstart(file, bstart); + + btail = au_dbtaildir(dentry); + for (bindex = au_fbend_dir(file); btail < bindex; bindex--) + au_set_h_fptr(file, bindex, NULL); + au_set_fbend_dir(file, btail); + + flags = vfsub_file_flags(file); + for (bindex = bstart; bindex <= btail; bindex++) { + h_dentry = au_h_dptr(dentry, bindex); + if (!h_dentry) + continue; + h_file = au_hf_dir(file, bindex); + if (h_file) + continue; + + h_file = au_h_open(dentry, bindex, flags, file); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; /* close all? */ + au_set_h_fptr(file, bindex, h_file); + } + au_update_figen(file); + /* todo: necessary? */ + /* file->f_ra = h_file->f_ra; */ + err = 0; + +out: + return err; +} + +static int do_open_dir(struct file *file, int flags) +{ + int err; + aufs_bindex_t bindex, btail; + struct dentry *dentry, *h_dentry; + struct file *h_file; + + FiMustWriteLock(file); + + dentry = file->f_dentry; + err = au_alive_dir(dentry); + if (unlikely(err)) + goto out; + + file->f_version = dentry->d_inode->i_version; + bindex = au_dbstart(dentry); + au_set_fbstart(file, bindex); + btail = au_dbtaildir(dentry); + au_set_fbend_dir(file, btail); + for (; !err && bindex <= btail; bindex++) { + h_dentry = au_h_dptr(dentry, bindex); + if (!h_dentry) + continue; + + h_file = au_h_open(dentry, bindex, flags, file); + if (IS_ERR(h_file)) { + err = PTR_ERR(h_file); + break; + } + au_set_h_fptr(file, bindex, h_file); + } + au_update_figen(file); + /* todo: necessary? */ + /* file->f_ra = h_file->f_ra; */ + if (!err) + return 0; /* success */ + + /* close all */ + for (bindex = au_fbstart(file); bindex <= btail; bindex++) + au_set_h_fptr(file, bindex, NULL); + au_set_fbstart(file, -1); + au_set_fbend_dir(file, -1); + +out: + return err; +} + +static int aufs_open_dir(struct inode *inode __maybe_unused, + struct file *file) +{ + int err; + struct super_block *sb; + struct au_fidir *fidir; + + err = -ENOMEM; + sb = file->f_dentry->d_sb; + si_read_lock(sb, AuLock_FLUSH); + fidir = au_fidir_alloc(sb); + if (fidir) { + err = au_do_open(file, do_open_dir, fidir); + if (unlikely(err)) + kfree(fidir); + } + si_read_unlock(sb); + return err; +} + +static int aufs_release_dir(struct inode *inode __maybe_unused, + struct file *file) +{ + struct au_vdir *vdir_cache; + struct au_finfo *finfo; + struct au_fidir *fidir; + aufs_bindex_t bindex, bend; + + finfo = au_fi(file); + fidir = finfo->fi_hdir; + if (fidir) { + /* remove me from sb->s_files */ + file_sb_list_del(file); + + vdir_cache = fidir->fd_vdir_cache; /* lock-free */ + if (vdir_cache) + au_vdir_free(vdir_cache); + + bindex = finfo->fi_btop; + if (bindex >= 0) { + /* + * calls fput() instead of filp_close(), + * since no dnotify or lock for the lower file. + */ + bend = fidir->fd_bbot; + for (; bindex <= bend; bindex++) + au_set_h_fptr(file, bindex, NULL); + } + kfree(fidir); + finfo->fi_hdir = NULL; + } + au_finfo_fin(file); + return 0; +} + +/* ---------------------------------------------------------------------- */ + +static int au_do_flush_dir(struct file *file, fl_owner_t id) +{ + int err; + aufs_bindex_t bindex, bend; + struct file *h_file; + + err = 0; + bend = au_fbend_dir(file); + for (bindex = au_fbstart(file); !err && bindex <= bend; bindex++) { + h_file = au_hf_dir(file, bindex); + if (h_file) + err = vfsub_flush(h_file, id); + } + return err; +} + +static int aufs_flush_dir(struct file *file, fl_owner_t id) +{ + return au_do_flush(file, id, au_do_flush_dir); +} + +/* ---------------------------------------------------------------------- */ + +static int au_do_fsync_dir_no_file(struct dentry *dentry, int datasync) +{ + int err; + aufs_bindex_t bend, bindex; + struct inode *inode; + struct super_block *sb; + + err = 0; + sb = dentry->d_sb; + inode = dentry->d_inode; + IMustLock(inode); + bend = au_dbend(dentry); + for (bindex = au_dbstart(dentry); !err && bindex <= bend; bindex++) { + struct path h_path; + + if (au_test_ro(sb, bindex, inode)) + continue; + h_path.dentry = au_h_dptr(dentry, bindex); + if (!h_path.dentry) + continue; + + h_path.mnt = au_sbr_mnt(sb, bindex); + err = vfsub_fsync(NULL, &h_path, datasync); + } + + return err; +} + +static int au_do_fsync_dir(struct file *file, int datasync) +{ + int err; + aufs_bindex_t bend, bindex; + struct file *h_file; + struct super_block *sb; + struct inode *inode; + + err = au_reval_and_lock_fdi(file, reopen_dir, /*wlock*/1); + if (unlikely(err)) + goto out; + + sb = file->f_dentry->d_sb; + inode = file->f_dentry->d_inode; + bend = au_fbend_dir(file); + for (bindex = au_fbstart(file); !err && bindex <= bend; bindex++) { + h_file = au_hf_dir(file, bindex); + if (!h_file || au_test_ro(sb, bindex, inode)) + continue; + + err = vfsub_fsync(h_file, &h_file->f_path, datasync); + } + +out: + return err; +} + +/* + * @file may be NULL + */ +static int aufs_fsync_dir(struct file *file, loff_t start, loff_t end, + int datasync) +{ + int err; + struct dentry *dentry; + struct super_block *sb; + struct mutex *mtx; + + err = 0; + dentry = file->f_dentry; + mtx = &dentry->d_inode->i_mutex; + mutex_lock(mtx); + sb = dentry->d_sb; + si_noflush_read_lock(sb); + if (file) + err = au_do_fsync_dir(file, datasync); + else { + di_write_lock_child(dentry); + err = au_do_fsync_dir_no_file(dentry, datasync); + } + au_cpup_attr_timesizes(dentry->d_inode); + di_write_unlock(dentry); + if (file) + fi_write_unlock(file); + + si_read_unlock(sb); + mutex_unlock(mtx); + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int aufs_readdir(struct file *file, void *dirent, filldir_t filldir) +{ + int err; + struct dentry *dentry; + struct inode *inode, *h_inode; + struct super_block *sb; + + dentry = file->f_dentry; + inode = dentry->d_inode; + IMustLock(inode); + + sb = dentry->d_sb; + si_read_lock(sb, AuLock_FLUSH); + err = au_reval_and_lock_fdi(file, reopen_dir, /*wlock*/1); + if (unlikely(err)) + goto out; + err = au_alive_dir(dentry); + if (!err) + err = au_vdir_init(file); + di_downgrade_lock(dentry, AuLock_IR); + if (unlikely(err)) + goto out_unlock; + + h_inode = au_h_iptr(inode, au_ibstart(inode)); + if (!au_test_nfsd()) { + err = au_vdir_fill_de(file, dirent, filldir); + fsstack_copy_attr_atime(inode, h_inode); + } else { + /* + * nfsd filldir may call lookup_one_len(), vfs_getattr(), + * encode_fh() and others. + */ + atomic_inc(&h_inode->i_count); + di_read_unlock(dentry, AuLock_IR); + si_read_unlock(sb); + err = au_vdir_fill_de(file, dirent, filldir); + fsstack_copy_attr_atime(inode, h_inode); + fi_write_unlock(file); + iput(h_inode); + + AuTraceErr(err); + return err; + } + +out_unlock: + di_read_unlock(dentry, AuLock_IR); + fi_write_unlock(file); +out: + si_read_unlock(sb); + return err; +} + +/* ---------------------------------------------------------------------- */ + +#define AuTestEmpty_WHONLY 1 +#define AuTestEmpty_CALLED (1 << 1) +#define AuTestEmpty_SHWH (1 << 2) +#define au_ftest_testempty(flags, name) ((flags) & AuTestEmpty_##name) +#define au_fset_testempty(flags, name) \ + do { (flags) |= AuTestEmpty_##name; } while (0) +#define au_fclr_testempty(flags, name) \ + do { (flags) &= ~AuTestEmpty_##name; } while (0) + +#ifndef CONFIG_AUFS_SHWH +#undef AuTestEmpty_SHWH +#define AuTestEmpty_SHWH 0 +#endif + +struct test_empty_arg { + struct au_nhash *whlist; + unsigned int flags; + int err; + aufs_bindex_t bindex; +}; + +static int test_empty_cb(void *__arg, const char *__name, int namelen, + loff_t offset __maybe_unused, u64 ino, + unsigned int d_type) +{ + struct test_empty_arg *arg = __arg; + char *name = (void *)__name; + + arg->err = 0; + au_fset_testempty(arg->flags, CALLED); + /* smp_mb(); */ + if (name[0] == '.' + && (namelen == 1 || (name[1] == '.' && namelen == 2))) + goto out; /* success */ + + if (namelen <= AUFS_WH_PFX_LEN + || memcmp(name, AUFS_WH_PFX, AUFS_WH_PFX_LEN)) { + if (au_ftest_testempty(arg->flags, WHONLY) + && !au_nhash_test_known_wh(arg->whlist, name, namelen)) + arg->err = -ENOTEMPTY; + goto out; + } + + name += AUFS_WH_PFX_LEN; + namelen -= AUFS_WH_PFX_LEN; + if (!au_nhash_test_known_wh(arg->whlist, name, namelen)) + arg->err = au_nhash_append_wh + (arg->whlist, name, namelen, ino, d_type, arg->bindex, + au_ftest_testempty(arg->flags, SHWH)); + +out: + /* smp_mb(); */ + AuTraceErr(arg->err); + return arg->err; +} + +static int do_test_empty(struct dentry *dentry, struct test_empty_arg *arg) +{ + int err; + struct file *h_file; + + h_file = au_h_open(dentry, arg->bindex, + O_RDONLY | O_NONBLOCK | O_DIRECTORY | O_LARGEFILE, + /*file*/NULL); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; + + err = 0; + if (!au_opt_test(au_mntflags(dentry->d_sb), UDBA_NONE) + && !h_file->f_dentry->d_inode->i_nlink) + goto out_put; + + do { + arg->err = 0; + au_fclr_testempty(arg->flags, CALLED); + /* smp_mb(); */ + err = vfsub_readdir(h_file, test_empty_cb, arg); + if (err >= 0) + err = arg->err; + } while (!err && au_ftest_testempty(arg->flags, CALLED)); + +out_put: + fput(h_file); + au_sbr_put(dentry->d_sb, arg->bindex); +out: + return err; +} + +struct do_test_empty_args { + int *errp; + struct dentry *dentry; + struct test_empty_arg *arg; +}; + +static void call_do_test_empty(void *args) +{ + struct do_test_empty_args *a = args; + *a->errp = do_test_empty(a->dentry, a->arg); +} + +static int sio_test_empty(struct dentry *dentry, struct test_empty_arg *arg) +{ + int err, wkq_err; + struct dentry *h_dentry; + struct inode *h_inode; + + h_dentry = au_h_dptr(dentry, arg->bindex); + h_inode = h_dentry->d_inode; + /* todo: i_mode changes anytime? */ + mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD); + err = au_test_h_perm_sio(h_inode, MAY_EXEC | MAY_READ); + mutex_unlock(&h_inode->i_mutex); + if (!err) + err = do_test_empty(dentry, arg); + else { + struct do_test_empty_args args = { + .errp = &err, + .dentry = dentry, + .arg = arg + }; + unsigned int flags = arg->flags; + + wkq_err = au_wkq_wait(call_do_test_empty, &args); + if (unlikely(wkq_err)) + err = wkq_err; + arg->flags = flags; + } + + return err; +} + +int au_test_empty_lower(struct dentry *dentry) +{ + int err; + unsigned int rdhash; + aufs_bindex_t bindex, bstart, btail; + struct au_nhash whlist; + struct test_empty_arg arg; + + SiMustAnyLock(dentry->d_sb); + + rdhash = au_sbi(dentry->d_sb)->si_rdhash; + if (!rdhash) + rdhash = au_rdhash_est(au_dir_size(/*file*/NULL, dentry)); + err = au_nhash_alloc(&whlist, rdhash, GFP_NOFS); + if (unlikely(err)) + goto out; + + arg.flags = 0; + arg.whlist = &whlist; + bstart = au_dbstart(dentry); + if (au_opt_test(au_mntflags(dentry->d_sb), SHWH)) + au_fset_testempty(arg.flags, SHWH); + arg.bindex = bstart; + err = do_test_empty(dentry, &arg); + if (unlikely(err)) + goto out_whlist; + + au_fset_testempty(arg.flags, WHONLY); + btail = au_dbtaildir(dentry); + for (bindex = bstart + 1; !err && bindex <= btail; bindex++) { + struct dentry *h_dentry; + + h_dentry = au_h_dptr(dentry, bindex); + if (h_dentry && h_dentry->d_inode) { + arg.bindex = bindex; + err = do_test_empty(dentry, &arg); + } + } + +out_whlist: + au_nhash_wh_free(&whlist); +out: + return err; +} + +int au_test_empty(struct dentry *dentry, struct au_nhash *whlist) +{ + int err; + struct test_empty_arg arg; + aufs_bindex_t bindex, btail; + + err = 0; + arg.whlist = whlist; + arg.flags = AuTestEmpty_WHONLY; + if (au_opt_test(au_mntflags(dentry->d_sb), SHWH)) + au_fset_testempty(arg.flags, SHWH); + btail = au_dbtaildir(dentry); + for (bindex = au_dbstart(dentry); !err && bindex <= btail; bindex++) { + struct dentry *h_dentry; + + h_dentry = au_h_dptr(dentry, bindex); + if (h_dentry && h_dentry->d_inode) { + arg.bindex = bindex; + err = sio_test_empty(dentry, &arg); + } + } + + return err; +} + +/* ---------------------------------------------------------------------- */ + +const struct file_operations aufs_dir_fop = { + .owner = THIS_MODULE, + .llseek = default_llseek, + .read = generic_read_dir, + .readdir = aufs_readdir, + .unlocked_ioctl = aufs_ioctl_dir, +#ifdef CONFIG_COMPAT + .compat_ioctl = aufs_compat_ioctl_dir, +#endif + .open = aufs_open_dir, + .release = aufs_release_dir, + .flush = aufs_flush_dir, + .fsync = aufs_fsync_dir +}; diff --git a/ubuntu/aufs/dir.h b/ubuntu/aufs/dir.h new file mode 100644 index 000000000000..dc52a6325c33 --- /dev/null +++ b/ubuntu/aufs/dir.h @@ -0,0 +1,137 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * directory operations + */ + +#ifndef __AUFS_DIR_H__ +#define __AUFS_DIR_H__ + +#ifdef __KERNEL__ + +#include <linux/fs.h> + +/* ---------------------------------------------------------------------- */ + +/* need to be faster and smaller */ + +struct au_nhash { + unsigned int nh_num; + struct hlist_head *nh_head; +}; + +struct au_vdir_destr { + unsigned char len; + unsigned char name[0]; +} __packed; + +struct au_vdir_dehstr { + struct hlist_node hash; + struct au_vdir_destr *str; +} ____cacheline_aligned_in_smp; + +struct au_vdir_de { + ino_t de_ino; + unsigned char de_type; + /* caution: packed */ + struct au_vdir_destr de_str; +} __packed; + +struct au_vdir_wh { + struct hlist_node wh_hash; +#ifdef CONFIG_AUFS_SHWH + ino_t wh_ino; + aufs_bindex_t wh_bindex; + unsigned char wh_type; +#else + aufs_bindex_t wh_bindex; +#endif + /* caution: packed */ + struct au_vdir_destr wh_str; +} __packed; + +union au_vdir_deblk_p { + unsigned char *deblk; + struct au_vdir_de *de; +}; + +struct au_vdir { + unsigned char **vd_deblk; + unsigned long vd_nblk; + struct { + unsigned long ul; + union au_vdir_deblk_p p; + } vd_last; + + unsigned long vd_version; + unsigned int vd_deblk_sz; + unsigned long vd_jiffy; +} ____cacheline_aligned_in_smp; + +/* ---------------------------------------------------------------------- */ + +/* dir.c */ +extern const struct file_operations aufs_dir_fop; +void au_add_nlink(struct inode *dir, struct inode *h_dir); +void au_sub_nlink(struct inode *dir, struct inode *h_dir); +loff_t au_dir_size(struct file *file, struct dentry *dentry); +int au_test_empty_lower(struct dentry *dentry); +int au_test_empty(struct dentry *dentry, struct au_nhash *whlist); + +/* vdir.c */ +unsigned int au_rdhash_est(loff_t sz); +int au_nhash_alloc(struct au_nhash *nhash, unsigned int num_hash, gfp_t gfp); +void au_nhash_wh_free(struct au_nhash *whlist); +int au_nhash_test_longer_wh(struct au_nhash *whlist, aufs_bindex_t btgt, + int limit); +int au_nhash_test_known_wh(struct au_nhash *whlist, char *name, int nlen); +int au_nhash_append_wh(struct au_nhash *whlist, char *name, int nlen, ino_t ino, + unsigned int d_type, aufs_bindex_t bindex, + unsigned char shwh); +void au_vdir_free(struct au_vdir *vdir); +int au_vdir_init(struct file *file); +int au_vdir_fill_de(struct file *file, void *dirent, filldir_t filldir); + +/* ioctl.c */ +long aufs_ioctl_dir(struct file *file, unsigned int cmd, unsigned long arg); + +#ifdef CONFIG_AUFS_RDU +/* rdu.c */ +long au_rdu_ioctl(struct file *file, unsigned int cmd, unsigned long arg); +#ifdef CONFIG_COMPAT +long au_rdu_compat_ioctl(struct file *file, unsigned int cmd, + unsigned long arg); +#endif +#else +static inline long au_rdu_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + return -EINVAL; +} +#ifdef CONFIG_COMPAT +static inline long au_rdu_compat_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + return -EINVAL; +} +#endif +#endif + +#endif /* __KERNEL__ */ +#endif /* __AUFS_DIR_H__ */ diff --git a/ubuntu/aufs/dynop.c b/ubuntu/aufs/dynop.c new file mode 100644 index 000000000000..2aedc11fa079 --- /dev/null +++ b/ubuntu/aufs/dynop.c @@ -0,0 +1,377 @@ +/* + * Copyright (C) 2010-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * dynamically customizable operations for regular files + */ + +#include "aufs.h" + +#define DyPrSym(key) AuDbgSym(key->dk_op.dy_hop) + +/* + * How large will these lists be? + * Usually just a few elements, 20-30 at most for each, I guess. + */ +static struct au_splhead dynop[AuDyLast]; + +static struct au_dykey *dy_gfind_get(struct au_splhead *spl, const void *h_op) +{ + struct au_dykey *key, *tmp; + struct list_head *head; + + key = NULL; + head = &spl->head; + rcu_read_lock(); + list_for_each_entry_rcu(tmp, head, dk_list) + if (tmp->dk_op.dy_hop == h_op) { + key = tmp; + kref_get(&key->dk_kref); + break; + } + rcu_read_unlock(); + + return key; +} + +static struct au_dykey *dy_bradd(struct au_branch *br, struct au_dykey *key) +{ + struct au_dykey **k, *found; + const void *h_op = key->dk_op.dy_hop; + int i; + + found = NULL; + k = br->br_dykey; + for (i = 0; i < AuBrDynOp; i++) + if (k[i]) { + if (k[i]->dk_op.dy_hop == h_op) { + found = k[i]; + break; + } + } else + break; + if (!found) { + spin_lock(&br->br_dykey_lock); + for (; i < AuBrDynOp; i++) + if (k[i]) { + if (k[i]->dk_op.dy_hop == h_op) { + found = k[i]; + break; + } + } else { + k[i] = key; + break; + } + spin_unlock(&br->br_dykey_lock); + BUG_ON(i == AuBrDynOp); /* expand the array */ + } + + return found; +} + +/* kref_get() if @key is already added */ +static struct au_dykey *dy_gadd(struct au_splhead *spl, struct au_dykey *key) +{ + struct au_dykey *tmp, *found; + struct list_head *head; + const void *h_op = key->dk_op.dy_hop; + + found = NULL; + head = &spl->head; + spin_lock(&spl->spin); + list_for_each_entry(tmp, head, dk_list) + if (tmp->dk_op.dy_hop == h_op) { + kref_get(&tmp->dk_kref); + found = tmp; + break; + } + if (!found) + list_add_rcu(&key->dk_list, head); + spin_unlock(&spl->spin); + + if (!found) + DyPrSym(key); + return found; +} + +static void dy_free_rcu(struct rcu_head *rcu) +{ + struct au_dykey *key; + + key = container_of(rcu, struct au_dykey, dk_rcu); + DyPrSym(key); + kfree(key); +} + +static void dy_free(struct kref *kref) +{ + struct au_dykey *key; + struct au_splhead *spl; + + key = container_of(kref, struct au_dykey, dk_kref); + spl = dynop + key->dk_op.dy_type; + au_spl_del_rcu(&key->dk_list, spl); + call_rcu(&key->dk_rcu, dy_free_rcu); +} + +void au_dy_put(struct au_dykey *key) +{ + kref_put(&key->dk_kref, dy_free); +} + +/* ---------------------------------------------------------------------- */ + +#define DyDbgSize(cnt, op) AuDebugOn(cnt != sizeof(op)/sizeof(void *)) + +#ifdef CONFIG_AUFS_DEBUG +#define DyDbgDeclare(cnt) unsigned int cnt = 0 +#define DyDbgInc(cnt) do { cnt++; } while (0) +#else +#define DyDbgDeclare(cnt) do {} while (0) +#define DyDbgInc(cnt) do {} while (0) +#endif + +#define DySet(func, dst, src, h_op, h_sb) do { \ + DyDbgInc(cnt); \ + if (h_op->func) { \ + if (src.func) \ + dst.func = src.func; \ + else \ + AuDbg("%s %s\n", au_sbtype(h_sb), #func); \ + } \ +} while (0) + +#define DySetForce(func, dst, src) do { \ + AuDebugOn(!src.func); \ + DyDbgInc(cnt); \ + dst.func = src.func; \ +} while (0) + +#define DySetAop(func) \ + DySet(func, dyaop->da_op, aufs_aop, h_aop, h_sb) +#define DySetAopForce(func) \ + DySetForce(func, dyaop->da_op, aufs_aop) + +static void dy_aop(struct au_dykey *key, const void *h_op, + struct super_block *h_sb __maybe_unused) +{ + struct au_dyaop *dyaop = (void *)key; + const struct address_space_operations *h_aop = h_op; + DyDbgDeclare(cnt); + + AuDbg("%s\n", au_sbtype(h_sb)); + + DySetAop(writepage); + DySetAopForce(readpage); /* force */ + DySetAop(writepages); + DySetAop(set_page_dirty); + DySetAop(readpages); + DySetAop(write_begin); + DySetAop(write_end); + DySetAop(bmap); + DySetAop(invalidatepage); + DySetAop(releasepage); + DySetAop(freepage); + /* these two will be changed according to an aufs mount option */ + DySetAop(direct_IO); + DySetAop(get_xip_mem); + DySetAop(migratepage); + DySetAop(launder_page); + DySetAop(is_partially_uptodate); + DySetAop(error_remove_page); + + DyDbgSize(cnt, *h_aop); + dyaop->da_get_xip_mem = h_aop->get_xip_mem; +} + +/* ---------------------------------------------------------------------- */ + +static void dy_bug(struct kref *kref) +{ + BUG(); +} + +static struct au_dykey *dy_get(struct au_dynop *op, struct au_branch *br) +{ + struct au_dykey *key, *old; + struct au_splhead *spl; + struct op { + unsigned int sz; + void (*set)(struct au_dykey *key, const void *h_op, + struct super_block *h_sb __maybe_unused); + }; + static const struct op a[] = { + [AuDy_AOP] = { + .sz = sizeof(struct au_dyaop), + .set = dy_aop + } + }; + const struct op *p; + + spl = dynop + op->dy_type; + key = dy_gfind_get(spl, op->dy_hop); + if (key) + goto out_add; /* success */ + + p = a + op->dy_type; + key = kzalloc(p->sz, GFP_NOFS); + if (unlikely(!key)) { + key = ERR_PTR(-ENOMEM); + goto out; + } + + key->dk_op.dy_hop = op->dy_hop; + kref_init(&key->dk_kref); + p->set(key, op->dy_hop, br->br_mnt->mnt_sb); + old = dy_gadd(spl, key); + if (old) { + kfree(key); + key = old; + } + +out_add: + old = dy_bradd(br, key); + if (old) + /* its ref-count should never be zero here */ + kref_put(&key->dk_kref, dy_bug); +out: + return key; +} + +/* ---------------------------------------------------------------------- */ +/* + * Aufs prohibits O_DIRECT by defaut even if the branch supports it. + * This behaviour is neccessary to return an error from open(O_DIRECT) instead + * of the succeeding I/O. The dio mount option enables O_DIRECT and makes + * open(O_DIRECT) always succeed, but the succeeding I/O may return an error. + * See the aufs manual in detail. + * + * To keep this behaviour, aufs has to set NULL to ->get_xip_mem too, and the + * performance of fadvise() and madvise() may be affected. + */ +static void dy_adx(struct au_dyaop *dyaop, int do_dx) +{ + if (!do_dx) { + dyaop->da_op.direct_IO = NULL; + dyaop->da_op.get_xip_mem = NULL; + } else { + dyaop->da_op.direct_IO = aufs_aop.direct_IO; + dyaop->da_op.get_xip_mem = aufs_aop.get_xip_mem; + if (!dyaop->da_get_xip_mem) + dyaop->da_op.get_xip_mem = NULL; + } +} + +static struct au_dyaop *dy_aget(struct au_branch *br, + const struct address_space_operations *h_aop, + int do_dx) +{ + struct au_dyaop *dyaop; + struct au_dynop op; + + op.dy_type = AuDy_AOP; + op.dy_haop = h_aop; + dyaop = (void *)dy_get(&op, br); + if (IS_ERR(dyaop)) + goto out; + dy_adx(dyaop, do_dx); + +out: + return dyaop; +} + +int au_dy_iaop(struct inode *inode, aufs_bindex_t bindex, + struct inode *h_inode) +{ + int err, do_dx; + struct super_block *sb; + struct au_branch *br; + struct au_dyaop *dyaop; + + AuDebugOn(!S_ISREG(h_inode->i_mode)); + IiMustWriteLock(inode); + + sb = inode->i_sb; + br = au_sbr(sb, bindex); + do_dx = !!au_opt_test(au_mntflags(sb), DIO); + dyaop = dy_aget(br, h_inode->i_mapping->a_ops, do_dx); + err = PTR_ERR(dyaop); + if (IS_ERR(dyaop)) + /* unnecessary to call dy_fput() */ + goto out; + + err = 0; + inode->i_mapping->a_ops = &dyaop->da_op; + +out: + return err; +} + +/* + * Is it safe to replace a_ops during the inode/file is in operation? + * Yes, I hope so. + */ +int au_dy_irefresh(struct inode *inode) +{ + int err; + aufs_bindex_t bstart; + struct inode *h_inode; + + err = 0; + if (S_ISREG(inode->i_mode)) { + bstart = au_ibstart(inode); + h_inode = au_h_iptr(inode, bstart); + err = au_dy_iaop(inode, bstart, h_inode); + } + return err; +} + +void au_dy_arefresh(int do_dx) +{ + struct au_splhead *spl; + struct list_head *head; + struct au_dykey *key; + + spl = dynop + AuDy_AOP; + head = &spl->head; + spin_lock(&spl->spin); + list_for_each_entry(key, head, dk_list) + dy_adx((void *)key, do_dx); + spin_unlock(&spl->spin); +} + +/* ---------------------------------------------------------------------- */ + +void __init au_dy_init(void) +{ + int i; + + /* make sure that 'struct au_dykey *' can be any type */ + BUILD_BUG_ON(offsetof(struct au_dyaop, da_key)); + + for (i = 0; i < AuDyLast; i++) + au_spl_init(dynop + i); +} + +void au_dy_fin(void) +{ + int i; + + for (i = 0; i < AuDyLast; i++) + WARN_ON(!list_empty(&dynop[i].head)); +} diff --git a/ubuntu/aufs/dynop.h b/ubuntu/aufs/dynop.h new file mode 100644 index 000000000000..029b08cff025 --- /dev/null +++ b/ubuntu/aufs/dynop.h @@ -0,0 +1,76 @@ +/* + * Copyright (C) 2010-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * dynamically customizable operations (for regular files only) + */ + +#ifndef __AUFS_DYNOP_H__ +#define __AUFS_DYNOP_H__ + +#ifdef __KERNEL__ + +#include "inode.h" + +enum {AuDy_AOP, AuDyLast}; + +struct au_dynop { + int dy_type; + union { + const void *dy_hop; + const struct address_space_operations *dy_haop; + }; +}; + +struct au_dykey { + union { + struct list_head dk_list; + struct rcu_head dk_rcu; + }; + struct au_dynop dk_op; + + /* + * during I am in the branch local array, kref is gotten. when the + * branch is removed, kref is put. + */ + struct kref dk_kref; +}; + +/* stop unioning since their sizes are very different from each other */ +struct au_dyaop { + struct au_dykey da_key; + struct address_space_operations da_op; /* not const */ + int (*da_get_xip_mem)(struct address_space *, pgoff_t, int, + void **, unsigned long *); +}; + +/* ---------------------------------------------------------------------- */ + +/* dynop.c */ +struct au_branch; +void au_dy_put(struct au_dykey *key); +int au_dy_iaop(struct inode *inode, aufs_bindex_t bindex, + struct inode *h_inode); +int au_dy_irefresh(struct inode *inode); +void au_dy_arefresh(int do_dio); + +void __init au_dy_init(void); +void au_dy_fin(void); + +#endif /* __KERNEL__ */ +#endif /* __AUFS_DYNOP_H__ */ diff --git a/ubuntu/aufs/export.c b/ubuntu/aufs/export.c new file mode 100644 index 000000000000..962d8e04f9e0 --- /dev/null +++ b/ubuntu/aufs/export.c @@ -0,0 +1,804 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * export via nfs + */ + +#include <linux/exportfs.h> +#include <linux/mnt_namespace.h> +#include <linux/namei.h> +#include <linux/nsproxy.h> +#include <linux/random.h> +#include <linux/writeback.h> +#include "aufs.h" + +union conv { +#ifdef CONFIG_AUFS_INO_T_64 + __u32 a[2]; +#else + __u32 a[1]; +#endif + ino_t ino; +}; + +static ino_t decode_ino(__u32 *a) +{ + union conv u; + + BUILD_BUG_ON(sizeof(u.ino) != sizeof(u.a)); + u.a[0] = a[0]; +#ifdef CONFIG_AUFS_INO_T_64 + u.a[1] = a[1]; +#endif + return u.ino; +} + +static void encode_ino(__u32 *a, ino_t ino) +{ + union conv u; + + u.ino = ino; + a[0] = u.a[0]; +#ifdef CONFIG_AUFS_INO_T_64 + a[1] = u.a[1]; +#endif +} + +/* NFS file handle */ +enum { + Fh_br_id, + Fh_sigen, +#ifdef CONFIG_AUFS_INO_T_64 + /* support 64bit inode number */ + Fh_ino1, + Fh_ino2, + Fh_dir_ino1, + Fh_dir_ino2, +#else + Fh_ino1, + Fh_dir_ino1, +#endif + Fh_igen, + Fh_h_type, + Fh_tail, + + Fh_ino = Fh_ino1, + Fh_dir_ino = Fh_dir_ino1 +}; + +static int au_test_anon(struct dentry *dentry) +{ + /* note: read d_flags without d_lock */ + return !!(dentry->d_flags & DCACHE_DISCONNECTED); +} + +/* ---------------------------------------------------------------------- */ +/* inode generation external table */ + +void au_xigen_inc(struct inode *inode) +{ + loff_t pos; + ssize_t sz; + __u32 igen; + struct super_block *sb; + struct au_sbinfo *sbinfo; + + sb = inode->i_sb; + AuDebugOn(!au_opt_test(au_mntflags(sb), XINO)); + + sbinfo = au_sbi(sb); + pos = inode->i_ino; + pos *= sizeof(igen); + igen = inode->i_generation + 1; + sz = xino_fwrite(sbinfo->si_xwrite, sbinfo->si_xigen, &igen, + sizeof(igen), &pos); + if (sz == sizeof(igen)) + return; /* success */ + + if (unlikely(sz >= 0)) + AuIOErr("xigen error (%zd)\n", sz); +} + +int au_xigen_new(struct inode *inode) +{ + int err; + loff_t pos; + ssize_t sz; + struct super_block *sb; + struct au_sbinfo *sbinfo; + struct file *file; + + err = 0; + /* todo: dirty, at mount time */ + if (inode->i_ino == AUFS_ROOT_INO) + goto out; + sb = inode->i_sb; + SiMustAnyLock(sb); + if (unlikely(!au_opt_test(au_mntflags(sb), XINO))) + goto out; + + err = -EFBIG; + pos = inode->i_ino; + if (unlikely(au_loff_max / sizeof(inode->i_generation) - 1 < pos)) { + AuIOErr1("too large i%lld\n", pos); + goto out; + } + pos *= sizeof(inode->i_generation); + + err = 0; + sbinfo = au_sbi(sb); + file = sbinfo->si_xigen; + BUG_ON(!file); + + if (i_size_read(file->f_dentry->d_inode) + < pos + sizeof(inode->i_generation)) { + inode->i_generation = atomic_inc_return(&sbinfo->si_xigen_next); + sz = xino_fwrite(sbinfo->si_xwrite, file, &inode->i_generation, + sizeof(inode->i_generation), &pos); + } else + sz = xino_fread(sbinfo->si_xread, file, &inode->i_generation, + sizeof(inode->i_generation), &pos); + if (sz == sizeof(inode->i_generation)) + goto out; /* success */ + + err = sz; + if (unlikely(sz >= 0)) { + err = -EIO; + AuIOErr("xigen error (%zd)\n", sz); + } + +out: + return err; +} + +int au_xigen_set(struct super_block *sb, struct file *base) +{ + int err; + struct au_sbinfo *sbinfo; + struct file *file; + + SiMustWriteLock(sb); + + sbinfo = au_sbi(sb); + file = au_xino_create2(base, sbinfo->si_xigen); + err = PTR_ERR(file); + if (IS_ERR(file)) + goto out; + err = 0; + if (sbinfo->si_xigen) + fput(sbinfo->si_xigen); + sbinfo->si_xigen = file; + +out: + return err; +} + +void au_xigen_clr(struct super_block *sb) +{ + struct au_sbinfo *sbinfo; + + SiMustWriteLock(sb); + + sbinfo = au_sbi(sb); + if (sbinfo->si_xigen) { + fput(sbinfo->si_xigen); + sbinfo->si_xigen = NULL; + } +} + +/* ---------------------------------------------------------------------- */ + +static struct dentry *decode_by_ino(struct super_block *sb, ino_t ino, + ino_t dir_ino) +{ + struct dentry *dentry, *d; + struct inode *inode; + unsigned int sigen; + + dentry = NULL; + inode = ilookup(sb, ino); + if (!inode) + goto out; + + dentry = ERR_PTR(-ESTALE); + sigen = au_sigen(sb); + if (unlikely(is_bad_inode(inode) + || IS_DEADDIR(inode) + || sigen != au_iigen(inode))) + goto out_iput; + + dentry = NULL; + if (!dir_ino || S_ISDIR(inode->i_mode)) + dentry = d_find_alias(inode); + else { + spin_lock(&inode->i_lock); + list_for_each_entry(d, &inode->i_dentry, d_alias) { + spin_lock(&d->d_lock); + if (!au_test_anon(d) + && d->d_parent->d_inode->i_ino == dir_ino) { + dentry = dget_dlock(d); + spin_unlock(&d->d_lock); + break; + } + spin_unlock(&d->d_lock); + } + spin_unlock(&inode->i_lock); + } + if (unlikely(dentry && au_digen_test(dentry, sigen))) { + /* need to refresh */ + dput(dentry); + dentry = NULL; + } + +out_iput: + iput(inode); +out: + AuTraceErrPtr(dentry); + return dentry; +} + +/* ---------------------------------------------------------------------- */ + +/* todo: dirty? */ +/* if exportfs_decode_fh() passed vfsmount*, we could be happy */ + +struct au_compare_mnt_args { + /* input */ + struct super_block *sb; + + /* output */ + struct vfsmount *mnt; +}; + +static int au_compare_mnt(struct vfsmount *mnt, void *arg) +{ + struct au_compare_mnt_args *a = arg; + + if (mnt->mnt_sb != a->sb) + return 0; + a->mnt = mntget(mnt); + return 1; +} + +static struct vfsmount *au_mnt_get(struct super_block *sb) +{ + int err; + struct au_compare_mnt_args args = { + .sb = sb + }; + struct mnt_namespace *ns; + + br_read_lock(vfsmount_lock); + /* no get/put ?? */ + AuDebugOn(!current->nsproxy); + ns = current->nsproxy->mnt_ns; + AuDebugOn(!ns); + err = iterate_mounts(au_compare_mnt, &args, ns->root); + br_read_unlock(vfsmount_lock); + AuDebugOn(!err); + AuDebugOn(!args.mnt); + return args.mnt; +} + +struct au_nfsd_si_lock { + unsigned int sigen; + aufs_bindex_t bindex, br_id; + unsigned char force_lock; +}; + +static int si_nfsd_read_lock(struct super_block *sb, + struct au_nfsd_si_lock *nsi_lock) +{ + int err; + aufs_bindex_t bindex; + + si_read_lock(sb, AuLock_FLUSH); + + /* branch id may be wrapped around */ + err = 0; + bindex = au_br_index(sb, nsi_lock->br_id); + if (bindex >= 0 && nsi_lock->sigen + AUFS_BRANCH_MAX > au_sigen(sb)) + goto out; /* success */ + + err = -ESTALE; + bindex = -1; + if (!nsi_lock->force_lock) + si_read_unlock(sb); + +out: + nsi_lock->bindex = bindex; + return err; +} + +struct find_name_by_ino { + int called, found; + ino_t ino; + char *name; + int namelen; +}; + +static int +find_name_by_ino(void *arg, const char *name, int namelen, loff_t offset, + u64 ino, unsigned int d_type) +{ + struct find_name_by_ino *a = arg; + + a->called++; + if (a->ino != ino) + return 0; + + memcpy(a->name, name, namelen); + a->namelen = namelen; + a->found = 1; + return 1; +} + +static struct dentry *au_lkup_by_ino(struct path *path, ino_t ino, + struct au_nfsd_si_lock *nsi_lock) +{ + struct dentry *dentry, *parent; + struct file *file; + struct inode *dir; + struct find_name_by_ino arg; + int err; + + parent = path->dentry; + if (nsi_lock) + si_read_unlock(parent->d_sb); + file = vfsub_dentry_open(path, au_dir_roflags); + dentry = (void *)file; + if (IS_ERR(file)) + goto out; + + dentry = ERR_PTR(-ENOMEM); + arg.name = __getname_gfp(GFP_NOFS); + if (unlikely(!arg.name)) + goto out_file; + arg.ino = ino; + arg.found = 0; + do { + arg.called = 0; + /* smp_mb(); */ + err = vfsub_readdir(file, find_name_by_ino, &arg); + } while (!err && !arg.found && arg.called); + dentry = ERR_PTR(err); + if (unlikely(err)) + goto out_name; + dentry = ERR_PTR(-ENOENT); + if (!arg.found) + goto out_name; + + /* do not call au_lkup_one() */ + dir = parent->d_inode; + mutex_lock(&dir->i_mutex); + dentry = vfsub_lookup_one_len(arg.name, parent, arg.namelen); + mutex_unlock(&dir->i_mutex); + AuTraceErrPtr(dentry); + if (IS_ERR(dentry)) + goto out_name; + AuDebugOn(au_test_anon(dentry)); + if (unlikely(!dentry->d_inode)) { + dput(dentry); + dentry = ERR_PTR(-ENOENT); + } + +out_name: + __putname(arg.name); +out_file: + fput(file); +out: + if (unlikely(nsi_lock + && si_nfsd_read_lock(parent->d_sb, nsi_lock) < 0)) + if (!IS_ERR(dentry)) { + dput(dentry); + dentry = ERR_PTR(-ESTALE); + } + AuTraceErrPtr(dentry); + return dentry; +} + +static struct dentry *decode_by_dir_ino(struct super_block *sb, ino_t ino, + ino_t dir_ino, + struct au_nfsd_si_lock *nsi_lock) +{ + struct dentry *dentry; + struct path path; + + if (dir_ino != AUFS_ROOT_INO) { + path.dentry = decode_by_ino(sb, dir_ino, 0); + dentry = path.dentry; + if (!path.dentry || IS_ERR(path.dentry)) + goto out; + AuDebugOn(au_test_anon(path.dentry)); + } else + path.dentry = dget(sb->s_root); + + path.mnt = au_mnt_get(sb); + dentry = au_lkup_by_ino(&path, ino, nsi_lock); + path_put(&path); + +out: + AuTraceErrPtr(dentry); + return dentry; +} + +/* ---------------------------------------------------------------------- */ + +static int h_acceptable(void *expv, struct dentry *dentry) +{ + return 1; +} + +static char *au_build_path(struct dentry *h_parent, struct path *h_rootpath, + char *buf, int len, struct super_block *sb) +{ + char *p; + int n; + struct path path; + + p = d_path(h_rootpath, buf, len); + if (IS_ERR(p)) + goto out; + n = strlen(p); + + path.mnt = h_rootpath->mnt; + path.dentry = h_parent; + p = d_path(&path, buf, len); + if (IS_ERR(p)) + goto out; + if (n != 1) + p += n; + + path.mnt = au_mnt_get(sb); + path.dentry = sb->s_root; + p = d_path(&path, buf, len - strlen(p)); + mntput(path.mnt); + if (IS_ERR(p)) + goto out; + if (n != 1) + p[strlen(p)] = '/'; + +out: + AuTraceErrPtr(p); + return p; +} + +static +struct dentry *decode_by_path(struct super_block *sb, ino_t ino, __u32 *fh, + int fh_len, struct au_nfsd_si_lock *nsi_lock) +{ + struct dentry *dentry, *h_parent, *root; + struct super_block *h_sb; + char *pathname, *p; + struct vfsmount *h_mnt; + struct au_branch *br; + int err; + struct path path; + + br = au_sbr(sb, nsi_lock->bindex); + h_mnt = br->br_mnt; + h_sb = h_mnt->mnt_sb; + /* todo: call lower fh_to_dentry()? fh_to_parent()? */ + h_parent = exportfs_decode_fh(h_mnt, (void *)(fh + Fh_tail), + fh_len - Fh_tail, fh[Fh_h_type], + h_acceptable, /*context*/NULL); + dentry = h_parent; + if (unlikely(!h_parent || IS_ERR(h_parent))) { + AuWarn1("%s decode_fh failed, %ld\n", + au_sbtype(h_sb), PTR_ERR(h_parent)); + goto out; + } + dentry = NULL; + if (unlikely(au_test_anon(h_parent))) { + AuWarn1("%s decode_fh returned a disconnected dentry\n", + au_sbtype(h_sb)); + goto out_h_parent; + } + + dentry = ERR_PTR(-ENOMEM); + pathname = (void *)__get_free_page(GFP_NOFS); + if (unlikely(!pathname)) + goto out_h_parent; + + root = sb->s_root; + path.mnt = h_mnt; + di_read_lock_parent(root, !AuLock_IR); + path.dentry = au_h_dptr(root, nsi_lock->bindex); + di_read_unlock(root, !AuLock_IR); + p = au_build_path(h_parent, &path, pathname, PAGE_SIZE, sb); + dentry = (void *)p; + if (IS_ERR(p)) + goto out_pathname; + + si_read_unlock(sb); + err = vfsub_kern_path(p, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path); + dentry = ERR_PTR(err); + if (unlikely(err)) + goto out_relock; + + dentry = ERR_PTR(-ENOENT); + AuDebugOn(au_test_anon(path.dentry)); + if (unlikely(!path.dentry->d_inode)) + goto out_path; + + if (ino != path.dentry->d_inode->i_ino) + dentry = au_lkup_by_ino(&path, ino, /*nsi_lock*/NULL); + else + dentry = dget(path.dentry); + +out_path: + path_put(&path); +out_relock: + if (unlikely(si_nfsd_read_lock(sb, nsi_lock) < 0)) + if (!IS_ERR(dentry)) { + dput(dentry); + dentry = ERR_PTR(-ESTALE); + } +out_pathname: + free_page((unsigned long)pathname); +out_h_parent: + dput(h_parent); +out: + AuTraceErrPtr(dentry); + return dentry; +} + +/* ---------------------------------------------------------------------- */ + +static struct dentry * +aufs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, + int fh_type) +{ + struct dentry *dentry; + __u32 *fh = fid->raw; + struct au_branch *br; + ino_t ino, dir_ino; + struct au_nfsd_si_lock nsi_lock = { + .force_lock = 0 + }; + + dentry = ERR_PTR(-ESTALE); + /* it should never happen, but the file handle is unreliable */ + if (unlikely(fh_len < Fh_tail)) + goto out; + nsi_lock.sigen = fh[Fh_sigen]; + nsi_lock.br_id = fh[Fh_br_id]; + + /* branch id may be wrapped around */ + br = NULL; + if (unlikely(si_nfsd_read_lock(sb, &nsi_lock))) + goto out; + nsi_lock.force_lock = 1; + + /* is this inode still cached? */ + ino = decode_ino(fh + Fh_ino); + /* it should never happen */ + if (unlikely(ino == AUFS_ROOT_INO)) + goto out; + + dir_ino = decode_ino(fh + Fh_dir_ino); + dentry = decode_by_ino(sb, ino, dir_ino); + if (IS_ERR(dentry)) + goto out_unlock; + if (dentry) + goto accept; + + /* is the parent dir cached? */ + br = au_sbr(sb, nsi_lock.bindex); + atomic_inc(&br->br_count); + dentry = decode_by_dir_ino(sb, ino, dir_ino, &nsi_lock); + if (IS_ERR(dentry)) + goto out_unlock; + if (dentry) + goto accept; + + /* lookup path */ + dentry = decode_by_path(sb, ino, fh, fh_len, &nsi_lock); + if (IS_ERR(dentry)) + goto out_unlock; + if (unlikely(!dentry)) + /* todo?: make it ESTALE */ + goto out_unlock; + +accept: + if (!au_digen_test(dentry, au_sigen(sb)) + && dentry->d_inode->i_generation == fh[Fh_igen]) + goto out_unlock; /* success */ + + dput(dentry); + dentry = ERR_PTR(-ESTALE); +out_unlock: + if (br) + atomic_dec(&br->br_count); + si_read_unlock(sb); +out: + AuTraceErrPtr(dentry); + return dentry; +} + +#if 0 /* reserved for future use */ +/* support subtreecheck option */ +static struct dentry *aufs_fh_to_parent(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type) +{ + struct dentry *parent; + __u32 *fh = fid->raw; + ino_t dir_ino; + + dir_ino = decode_ino(fh + Fh_dir_ino); + parent = decode_by_ino(sb, dir_ino, 0); + if (IS_ERR(parent)) + goto out; + if (!parent) + parent = decode_by_path(sb, au_br_index(sb, fh[Fh_br_id]), + dir_ino, fh, fh_len); + +out: + AuTraceErrPtr(parent); + return parent; +} +#endif + +/* ---------------------------------------------------------------------- */ + +static int aufs_encode_fh(struct dentry *dentry, __u32 *fh, int *max_len, + int connectable) +{ + int err; + aufs_bindex_t bindex, bend; + struct super_block *sb, *h_sb; + struct inode *inode; + struct dentry *parent, *h_parent; + struct au_branch *br; + + AuDebugOn(au_test_anon(dentry)); + + parent = NULL; + err = -ENOSPC; + if (unlikely(*max_len <= Fh_tail)) { + AuWarn1("NFSv2 client (max_len %d)?\n", *max_len); + goto out; + } + + err = FILEID_ROOT; + if (IS_ROOT(dentry)) { + AuDebugOn(dentry->d_inode->i_ino != AUFS_ROOT_INO); + goto out; + } + + h_parent = NULL; + err = aufs_read_lock(dentry, AuLock_FLUSH | AuLock_IR | AuLock_GEN); + if (unlikely(err)) + goto out; + + inode = dentry->d_inode; + AuDebugOn(!inode); + sb = dentry->d_sb; +#ifdef CONFIG_AUFS_DEBUG + if (unlikely(!au_opt_test(au_mntflags(sb), XINO))) + AuWarn1("NFS-exporting requires xino\n"); +#endif + err = -EIO; + parent = dget_parent(dentry); + di_read_lock_parent(parent, !AuLock_IR); + bend = au_dbtaildir(parent); + for (bindex = au_dbstart(parent); bindex <= bend; bindex++) { + h_parent = au_h_dptr(parent, bindex); + if (h_parent) { + dget(h_parent); + break; + } + } + if (unlikely(!h_parent)) + goto out_unlock; + + err = -EPERM; + br = au_sbr(sb, bindex); + h_sb = br->br_mnt->mnt_sb; + if (unlikely(!h_sb->s_export_op)) { + AuErr1("%s branch is not exportable\n", au_sbtype(h_sb)); + goto out_dput; + } + + fh[Fh_br_id] = br->br_id; + fh[Fh_sigen] = au_sigen(sb); + encode_ino(fh + Fh_ino, inode->i_ino); + encode_ino(fh + Fh_dir_ino, parent->d_inode->i_ino); + fh[Fh_igen] = inode->i_generation; + + *max_len -= Fh_tail; + fh[Fh_h_type] = exportfs_encode_fh(h_parent, (void *)(fh + Fh_tail), + max_len, + /*connectable or subtreecheck*/0); + err = fh[Fh_h_type]; + *max_len += Fh_tail; + /* todo: macros? */ + if (err != 255) + err = 99; + else + AuWarn1("%s encode_fh failed\n", au_sbtype(h_sb)); + +out_dput: + dput(h_parent); +out_unlock: + di_read_unlock(parent, !AuLock_IR); + dput(parent); + aufs_read_unlock(dentry, AuLock_IR); +out: + if (unlikely(err < 0)) + err = 255; + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int aufs_commit_metadata(struct inode *inode) +{ + int err; + aufs_bindex_t bindex; + struct super_block *sb; + struct inode *h_inode; + int (*f)(struct inode *inode); + + sb = inode->i_sb; + si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); + ii_write_lock_child(inode); + bindex = au_ibstart(inode); + AuDebugOn(bindex < 0); + h_inode = au_h_iptr(inode, bindex); + + f = h_inode->i_sb->s_export_op->commit_metadata; + if (f) + err = f(h_inode); + else { + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = 0 /* metadata only */ + }; + + err = sync_inode(h_inode, &wbc); + } + + au_cpup_attr_timesizes(inode); + ii_write_unlock(inode); + si_read_unlock(sb); + return err; +} + +/* ---------------------------------------------------------------------- */ + +static struct export_operations aufs_export_op = { + .fh_to_dentry = aufs_fh_to_dentry, + /* .fh_to_parent = aufs_fh_to_parent, */ + .encode_fh = aufs_encode_fh, + .commit_metadata = aufs_commit_metadata +}; + +void au_export_init(struct super_block *sb) +{ + struct au_sbinfo *sbinfo; + __u32 u; + + sb->s_export_op = &aufs_export_op; + sbinfo = au_sbi(sb); + sbinfo->si_xigen = NULL; + get_random_bytes(&u, sizeof(u)); + BUILD_BUG_ON(sizeof(u) != sizeof(int)); + atomic_set(&sbinfo->si_xigen_next, u); +} diff --git a/ubuntu/aufs/f_op.c b/ubuntu/aufs/f_op.c new file mode 100644 index 000000000000..942e71a7781c --- /dev/null +++ b/ubuntu/aufs/f_op.c @@ -0,0 +1,729 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * file and vm operations + */ + +#include <linux/fs_stack.h> +#include <linux/mman.h> +#include <linux/security.h> +#include "aufs.h" + +int au_do_open_nondir(struct file *file, int flags) +{ + int err; + aufs_bindex_t bindex; + struct file *h_file; + struct dentry *dentry; + struct au_finfo *finfo; + + FiMustWriteLock(file); + + dentry = file->f_dentry; + err = au_d_alive(dentry); + if (unlikely(err)) + goto out; + + finfo = au_fi(file); + memset(&finfo->fi_htop, 0, sizeof(finfo->fi_htop)); + atomic_set(&finfo->fi_mmapped, 0); + bindex = au_dbstart(dentry); + h_file = au_h_open(dentry, bindex, flags, file); + if (IS_ERR(h_file)) + err = PTR_ERR(h_file); + else { + au_set_fbstart(file, bindex); + au_set_h_fptr(file, bindex, h_file); + au_update_figen(file); + /* todo: necessary? */ + /* file->f_ra = h_file->f_ra; */ + } + +out: + return err; +} + +static int aufs_open_nondir(struct inode *inode __maybe_unused, + struct file *file) +{ + int err; + struct super_block *sb; + + AuDbg("%.*s, f_flags 0x%x, f_mode 0x%x\n", + AuDLNPair(file->f_dentry), vfsub_file_flags(file), + file->f_mode); + + sb = file->f_dentry->d_sb; + si_read_lock(sb, AuLock_FLUSH); + err = au_do_open(file, au_do_open_nondir, /*fidir*/NULL); + si_read_unlock(sb); + return err; +} + +int aufs_release_nondir(struct inode *inode __maybe_unused, struct file *file) +{ + struct au_finfo *finfo; + aufs_bindex_t bindex; + + finfo = au_fi(file); + bindex = finfo->fi_btop; + if (bindex >= 0) { + /* remove me from sb->s_files */ + file_sb_list_del(file); + au_set_h_fptr(file, bindex, NULL); + } + + au_finfo_fin(file); + return 0; +} + +/* ---------------------------------------------------------------------- */ + +static int au_do_flush_nondir(struct file *file, fl_owner_t id) +{ + int err; + struct file *h_file; + + err = 0; + h_file = au_hf_top(file); + if (h_file) + err = vfsub_flush(h_file, id); + return err; +} + +static int aufs_flush_nondir(struct file *file, fl_owner_t id) +{ + return au_do_flush(file, id, au_do_flush_nondir); +} + +/* ---------------------------------------------------------------------- */ +/* + * read and write functions acquire [fdi]_rwsem once, but release before + * mmap_sem. This is because to stop a race condition between mmap(2). + * Releasing these aufs-rwsem should be safe, no branch-mamagement (by keeping + * si_rwsem), no harmful copy-up should happen. Actually copy-up may happen in + * read functions after [fdi]_rwsem are released, but it should be harmless. + */ + +static ssize_t aufs_read(struct file *file, char __user *buf, size_t count, + loff_t *ppos) +{ + ssize_t err; + struct dentry *dentry; + struct file *h_file; + struct super_block *sb; + + dentry = file->f_dentry; + sb = dentry->d_sb; + si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); + err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/0); + if (unlikely(err)) + goto out; + + h_file = au_hf_top(file); + get_file(h_file); + di_read_unlock(dentry, AuLock_IR); + fi_read_unlock(file); + + /* filedata may be obsoleted by concurrent copyup, but no problem */ + err = vfsub_read_u(h_file, buf, count, ppos); + /* todo: necessary? */ + /* file->f_ra = h_file->f_ra; */ + /* update without lock, I don't think it a problem */ + fsstack_copy_attr_atime(dentry->d_inode, h_file->f_dentry->d_inode); + fput(h_file); + +out: + si_read_unlock(sb); + return err; +} + +/* + * todo: very ugly + * it locks both of i_mutex and si_rwsem for read in safe. + * if the plink maintenance mode continues forever (that is the problem), + * may loop forever. + */ +static void au_mtx_and_read_lock(struct inode *inode) +{ + int err; + struct super_block *sb = inode->i_sb; + + while (1) { + mutex_lock(&inode->i_mutex); + err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); + if (!err) + break; + mutex_unlock(&inode->i_mutex); + si_read_lock(sb, AuLock_NOPLMW); + si_read_unlock(sb); + } +} + +static ssize_t aufs_write(struct file *file, const char __user *ubuf, + size_t count, loff_t *ppos) +{ + ssize_t err; + struct au_pin pin; + struct dentry *dentry; + struct super_block *sb; + struct inode *inode; + struct file *h_file; + char __user *buf = (char __user *)ubuf; + + dentry = file->f_dentry; + sb = dentry->d_sb; + inode = dentry->d_inode; + au_mtx_and_read_lock(inode); + + err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1); + if (unlikely(err)) + goto out; + + err = au_ready_to_write(file, -1, &pin); + di_downgrade_lock(dentry, AuLock_IR); + if (unlikely(err)) { + di_read_unlock(dentry, AuLock_IR); + fi_write_unlock(file); + goto out; + } + + h_file = au_hf_top(file); + get_file(h_file); + au_unpin(&pin); + di_read_unlock(dentry, AuLock_IR); + fi_write_unlock(file); + + err = vfsub_write_u(h_file, buf, count, ppos); + ii_write_lock_child(inode); + au_cpup_attr_timesizes(inode); + inode->i_mode = h_file->f_dentry->d_inode->i_mode; + ii_write_unlock(inode); + fput(h_file); + +out: + si_read_unlock(sb); + mutex_unlock(&inode->i_mutex); + return err; +} + +static ssize_t au_do_aio(struct file *h_file, int rw, struct kiocb *kio, + const struct iovec *iov, unsigned long nv, loff_t pos) +{ + ssize_t err; + struct file *file; + ssize_t (*func)(struct kiocb *, const struct iovec *, unsigned long, + loff_t); + + err = security_file_permission(h_file, rw); + if (unlikely(err)) + goto out; + + err = -ENOSYS; + func = NULL; + if (rw == MAY_READ) + func = h_file->f_op->aio_read; + else if (rw == MAY_WRITE) + func = h_file->f_op->aio_write; + if (func) { + file = kio->ki_filp; + kio->ki_filp = h_file; + lockdep_off(); + err = func(kio, iov, nv, pos); + lockdep_on(); + kio->ki_filp = file; + } else + /* currently there is no such fs */ + WARN_ON_ONCE(1); + +out: + return err; +} + +static ssize_t aufs_aio_read(struct kiocb *kio, const struct iovec *iov, + unsigned long nv, loff_t pos) +{ + ssize_t err; + struct file *file, *h_file; + struct dentry *dentry; + struct super_block *sb; + + file = kio->ki_filp; + dentry = file->f_dentry; + sb = dentry->d_sb; + si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); + err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/0); + if (unlikely(err)) + goto out; + + h_file = au_hf_top(file); + get_file(h_file); + di_read_unlock(dentry, AuLock_IR); + fi_read_unlock(file); + + err = au_do_aio(h_file, MAY_READ, kio, iov, nv, pos); + /* todo: necessary? */ + /* file->f_ra = h_file->f_ra; */ + /* update without lock, I don't think it a problem */ + fsstack_copy_attr_atime(dentry->d_inode, h_file->f_dentry->d_inode); + fput(h_file); + +out: + si_read_unlock(sb); + return err; +} + +static ssize_t aufs_aio_write(struct kiocb *kio, const struct iovec *iov, + unsigned long nv, loff_t pos) +{ + ssize_t err; + struct au_pin pin; + struct dentry *dentry; + struct inode *inode; + struct file *file, *h_file; + struct super_block *sb; + + file = kio->ki_filp; + dentry = file->f_dentry; + sb = dentry->d_sb; + inode = dentry->d_inode; + au_mtx_and_read_lock(inode); + + err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1); + if (unlikely(err)) + goto out; + + err = au_ready_to_write(file, -1, &pin); + di_downgrade_lock(dentry, AuLock_IR); + if (unlikely(err)) { + di_read_unlock(dentry, AuLock_IR); + fi_write_unlock(file); + goto out; + } + + h_file = au_hf_top(file); + get_file(h_file); + au_unpin(&pin); + di_read_unlock(dentry, AuLock_IR); + fi_write_unlock(file); + + err = au_do_aio(h_file, MAY_WRITE, kio, iov, nv, pos); + ii_write_lock_child(inode); + au_cpup_attr_timesizes(inode); + inode->i_mode = h_file->f_dentry->d_inode->i_mode; + ii_write_unlock(inode); + fput(h_file); + +out: + si_read_unlock(sb); + mutex_unlock(&inode->i_mutex); + return err; +} + +static ssize_t aufs_splice_read(struct file *file, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) +{ + ssize_t err; + struct file *h_file; + struct dentry *dentry; + struct super_block *sb; + + dentry = file->f_dentry; + sb = dentry->d_sb; + si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); + err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/0); + if (unlikely(err)) + goto out; + + err = -EINVAL; + h_file = au_hf_top(file); + get_file(h_file); + if (au_test_loopback_kthread()) { + au_warn_loopback(h_file->f_dentry->d_sb); + if (file->f_mapping != h_file->f_mapping) { + file->f_mapping = h_file->f_mapping; + smp_mb(); /* unnecessary? */ + } + } + di_read_unlock(dentry, AuLock_IR); + fi_read_unlock(file); + + err = vfsub_splice_to(h_file, ppos, pipe, len, flags); + /* todo: necessasry? */ + /* file->f_ra = h_file->f_ra; */ + /* update without lock, I don't think it a problem */ + fsstack_copy_attr_atime(dentry->d_inode, h_file->f_dentry->d_inode); + fput(h_file); + +out: + si_read_unlock(sb); + return err; +} + +static ssize_t +aufs_splice_write(struct pipe_inode_info *pipe, struct file *file, loff_t *ppos, + size_t len, unsigned int flags) +{ + ssize_t err; + struct au_pin pin; + struct dentry *dentry; + struct inode *inode; + struct file *h_file; + struct super_block *sb; + + dentry = file->f_dentry; + sb = dentry->d_sb; + inode = dentry->d_inode; + au_mtx_and_read_lock(inode); + + err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1); + if (unlikely(err)) + goto out; + + err = au_ready_to_write(file, -1, &pin); + di_downgrade_lock(dentry, AuLock_IR); + if (unlikely(err)) { + di_read_unlock(dentry, AuLock_IR); + fi_write_unlock(file); + goto out; + } + + h_file = au_hf_top(file); + get_file(h_file); + au_unpin(&pin); + di_read_unlock(dentry, AuLock_IR); + fi_write_unlock(file); + + err = vfsub_splice_from(pipe, h_file, ppos, len, flags); + ii_write_lock_child(inode); + au_cpup_attr_timesizes(inode); + inode->i_mode = h_file->f_dentry->d_inode->i_mode; + ii_write_unlock(inode); + fput(h_file); + +out: + si_read_unlock(sb); + mutex_unlock(&inode->i_mutex); + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* + * The locking order around current->mmap_sem. + * - in most and regular cases + * file I/O syscall -- aufs_read() or something + * -- si_rwsem for read -- mmap_sem + * (Note that [fdi]i_rwsem are released before mmap_sem). + * - in mmap case + * mmap(2) -- mmap_sem -- aufs_mmap() -- si_rwsem for read -- [fdi]i_rwsem + * This AB-BA order is definitly bad, but is not a problem since "si_rwsem for + * read" allows muliple processes to acquire it and [fdi]i_rwsem are not held in + * file I/O. Aufs needs to stop lockdep in aufs_mmap() though. + * It means that when aufs acquires si_rwsem for write, the process should never + * acquire mmap_sem. + * + * Actually aufs_readdir() holds [fdi]i_rwsem before mmap_sem, but this is not a + * problem either since any directory is not able to be mmap-ed. + * The similar scenario is applied to aufs_readlink() too. + */ + +/* cf. linux/include/linux/mman.h: calc_vm_prot_bits() */ +#define AuConv_VM_PROT(f, b) _calc_vm_trans(f, VM_##b, PROT_##b) + +static unsigned long au_arch_prot_conv(unsigned long flags) +{ + /* currently ppc64 only */ +#ifdef CONFIG_PPC64 + /* cf. linux/arch/powerpc/include/asm/mman.h */ + AuDebugOn(arch_calc_vm_prot_bits(-1) != VM_SAO); + return AuConv_VM_PROT(flags, SAO); +#else + AuDebugOn(arch_calc_vm_prot_bits(-1)); + return 0; +#endif +} + +static unsigned long au_prot_conv(unsigned long flags) +{ + return AuConv_VM_PROT(flags, READ) + | AuConv_VM_PROT(flags, WRITE) + | AuConv_VM_PROT(flags, EXEC) + | au_arch_prot_conv(flags); +} + +/* cf. linux/include/linux/mman.h: calc_vm_flag_bits() */ +#define AuConv_VM_MAP(f, b) _calc_vm_trans(f, VM_##b, MAP_##b) + +static unsigned long au_flag_conv(unsigned long flags) +{ + return AuConv_VM_MAP(flags, GROWSDOWN) + | AuConv_VM_MAP(flags, DENYWRITE) + | AuConv_VM_MAP(flags, EXECUTABLE) + | AuConv_VM_MAP(flags, LOCKED); +} + +static int aufs_mmap(struct file *file, struct vm_area_struct *vma) +{ + int err; + unsigned long prot; + aufs_bindex_t bstart; + const unsigned char wlock + = (file->f_mode & FMODE_WRITE) && (vma->vm_flags & VM_SHARED); + struct dentry *dentry; + struct super_block *sb; + struct file *h_file; + struct au_branch *br; + struct au_pin pin; + + AuDbgVmRegion(file, vma); + + dentry = file->f_dentry; + sb = dentry->d_sb; + lockdep_off(); + si_read_lock(sb, AuLock_NOPLMW); + err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1); + if (unlikely(err)) + goto out; + + if (wlock) { + err = au_ready_to_write(file, -1, &pin); + di_write_unlock(dentry); + if (unlikely(err)) { + fi_write_unlock(file); + goto out; + } + au_unpin(&pin); + } else + di_write_unlock(dentry); + + bstart = au_fbstart(file); + br = au_sbr(sb, bstart); + h_file = au_hf_top(file); + get_file(h_file); + au_set_mmapped(file); + fi_write_unlock(file); + lockdep_on(); + + au_vm_file_reset(vma, h_file); + prot = au_prot_conv(vma->vm_flags); + err = security_file_mmap(h_file, /*reqprot*/prot, prot, + au_flag_conv(vma->vm_flags), vma->vm_start, 0); + if (!err) + err = h_file->f_op->mmap(h_file, vma); + if (unlikely(err)) + goto out_reset; + + au_vm_prfile_set(vma, file); + /* update without lock, I don't think it a problem */ + fsstack_copy_attr_atime(file->f_dentry->d_inode, + h_file->f_dentry->d_inode); + goto out_fput; /* success */ + +out_reset: + au_unset_mmapped(file); + au_vm_file_reset(vma, file); +out_fput: + fput(h_file); + lockdep_off(); +out: + si_read_unlock(sb); + lockdep_on(); + AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int aufs_fsync_nondir(struct file *file, loff_t start, loff_t end, + int datasync) +{ + int err; + struct au_pin pin; + struct dentry *dentry; + struct inode *inode; + struct file *h_file; + struct super_block *sb; + + dentry = file->f_dentry; + inode = dentry->d_inode; + sb = dentry->d_sb; + mutex_lock(&inode->i_mutex); + err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); + if (unlikely(err)) + goto out; + + err = 0; /* -EBADF; */ /* posix? */ + if (unlikely(!(file->f_mode & FMODE_WRITE))) + goto out_si; + err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1); + if (unlikely(err)) + goto out_si; + + err = au_ready_to_write(file, -1, &pin); + di_downgrade_lock(dentry, AuLock_IR); + if (unlikely(err)) + goto out_unlock; + au_unpin(&pin); + + err = -EINVAL; + h_file = au_hf_top(file); + err = vfsub_fsync(h_file, &h_file->f_path, datasync); + au_cpup_attr_timesizes(inode); + +out_unlock: + di_read_unlock(dentry, AuLock_IR); + fi_write_unlock(file); +out_si: + si_read_unlock(sb); +out: + mutex_unlock(&inode->i_mutex); + return err; +} + +/* no one supports this operation, currently */ +#if 0 +static int aufs_aio_fsync_nondir(struct kiocb *kio, int datasync) +{ + int err; + struct au_pin pin; + struct dentry *dentry; + struct inode *inode; + struct file *file, *h_file; + + file = kio->ki_filp; + dentry = file->f_dentry; + inode = dentry->d_inode; + au_mtx_and_read_lock(inode); + + err = 0; /* -EBADF; */ /* posix? */ + if (unlikely(!(file->f_mode & FMODE_WRITE))) + goto out; + err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1); + if (unlikely(err)) + goto out; + + err = au_ready_to_write(file, -1, &pin); + di_downgrade_lock(dentry, AuLock_IR); + if (unlikely(err)) + goto out_unlock; + au_unpin(&pin); + + err = -ENOSYS; + h_file = au_hf_top(file); + if (h_file->f_op && h_file->f_op->aio_fsync) { + struct dentry *h_d; + struct mutex *h_mtx; + + h_d = h_file->f_dentry; + h_mtx = &h_d->d_inode->i_mutex; + if (!is_sync_kiocb(kio)) { + get_file(h_file); + fput(file); + } + kio->ki_filp = h_file; + err = h_file->f_op->aio_fsync(kio, datasync); + mutex_lock_nested(h_mtx, AuLsc_I_CHILD); + if (!err) + vfsub_update_h_iattr(&h_file->f_path, /*did*/NULL); + /*ignore*/ + au_cpup_attr_timesizes(inode); + mutex_unlock(h_mtx); + } + +out_unlock: + di_read_unlock(dentry, AuLock_IR); + fi_write_unlock(file); +out: + si_read_unlock(inode->sb); + mutex_unlock(&inode->i_mutex); + return err; +} +#endif + +static int aufs_fasync(int fd, struct file *file, int flag) +{ + int err; + struct file *h_file; + struct dentry *dentry; + struct super_block *sb; + + dentry = file->f_dentry; + sb = dentry->d_sb; + si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); + err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/0); + if (unlikely(err)) + goto out; + + h_file = au_hf_top(file); + if (h_file->f_op && h_file->f_op->fasync) + err = h_file->f_op->fasync(fd, h_file, flag); + + di_read_unlock(dentry, AuLock_IR); + fi_read_unlock(file); + +out: + si_read_unlock(sb); + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* no one supports this operation, currently */ +#if 0 +static ssize_t aufs_sendpage(struct file *file, struct page *page, int offset, + size_t len, loff_t *pos , int more) +{ +} +#endif + +/* ---------------------------------------------------------------------- */ + +const struct file_operations aufs_file_fop = { + .owner = THIS_MODULE, + + .llseek = default_llseek, + + .read = aufs_read, + .write = aufs_write, + .aio_read = aufs_aio_read, + .aio_write = aufs_aio_write, +#ifdef CONFIG_AUFS_POLL + .poll = aufs_poll, +#endif + .unlocked_ioctl = aufs_ioctl_nondir, +#ifdef CONFIG_COMPAT + .compat_ioctl = aufs_ioctl_nondir, /* same */ +#endif + .mmap = aufs_mmap, + .open = aufs_open_nondir, + .flush = aufs_flush_nondir, + .release = aufs_release_nondir, + .fsync = aufs_fsync_nondir, + /* .aio_fsync = aufs_aio_fsync_nondir, */ + .fasync = aufs_fasync, + /* .sendpage = aufs_sendpage, */ + .splice_write = aufs_splice_write, + .splice_read = aufs_splice_read, +#if 0 + .aio_splice_write = aufs_aio_splice_write, + .aio_splice_read = aufs_aio_splice_read +#endif +}; diff --git a/ubuntu/aufs/f_op_sp.c b/ubuntu/aufs/f_op_sp.c new file mode 100644 index 000000000000..48b8aa18af27 --- /dev/null +++ b/ubuntu/aufs/f_op_sp.c @@ -0,0 +1,298 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * file operations for special files. + * while they exist in aufs virtually, + * their file I/O is handled out of aufs. + */ + +#include "aufs.h" + +static ssize_t aufs_aio_read_sp(struct kiocb *kio, const struct iovec *iov, + unsigned long nv, loff_t pos) +{ + ssize_t err; + aufs_bindex_t bstart; + unsigned char wbr; + struct file *file, *h_file; + struct super_block *sb; + + file = kio->ki_filp; + sb = file->f_dentry->d_sb; + si_read_lock(sb, AuLock_FLUSH); + fi_read_lock(file); + bstart = au_fbstart(file); + h_file = au_hf_top(file); + fi_read_unlock(file); + wbr = !!au_br_writable(au_sbr(sb, bstart)->br_perm); + si_read_unlock(sb); + + /* do not change the file in kio */ + AuDebugOn(!h_file->f_op || !h_file->f_op->aio_read); + err = h_file->f_op->aio_read(kio, iov, nv, pos); + if (err > 0 && wbr) + file_accessed(h_file); + + return err; +} + +static ssize_t aufs_aio_write_sp(struct kiocb *kio, const struct iovec *iov, + unsigned long nv, loff_t pos) +{ + ssize_t err; + aufs_bindex_t bstart; + unsigned char wbr; + struct super_block *sb; + struct file *file, *h_file; + + file = kio->ki_filp; + sb = file->f_dentry->d_sb; + si_read_lock(sb, AuLock_FLUSH); + fi_read_lock(file); + bstart = au_fbstart(file); + h_file = au_hf_top(file); + fi_read_unlock(file); + wbr = !!au_br_writable(au_sbr(sb, bstart)->br_perm); + si_read_unlock(sb); + + /* do not change the file in kio */ + AuDebugOn(!h_file->f_op || !h_file->f_op->aio_write); + err = h_file->f_op->aio_write(kio, iov, nv, pos); + if (err > 0 && wbr) + file_update_time(h_file); + + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int aufs_release_sp(struct inode *inode, struct file *file) +{ + int err; + struct file *h_file; + + fi_read_lock(file); + h_file = au_hf_top(file); + fi_read_unlock(file); + /* close this fifo in aufs */ + err = h_file->f_op->release(inode, file); /* ignore */ + aufs_release_nondir(inode, file); /* ignore */ + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* currently, support only FIFO */ +enum { + AuSp_FIFO, AuSp_FIFO_R, AuSp_FIFO_W, AuSp_FIFO_RW, + /* AuSp_SOCK, AuSp_CHR, AuSp_BLK, */ + AuSp_Last +}; +static int aufs_open_sp(struct inode *inode, struct file *file); +static struct au_sp_fop { + int done; + struct file_operations fop; /* not 'const' */ + spinlock_t spin; +} au_sp_fop[AuSp_Last] = { + [AuSp_FIFO] = { + .fop = { + .owner = THIS_MODULE, + .open = aufs_open_sp + } + } +}; + +static void au_init_fop_sp(struct file *file) +{ + struct au_sp_fop *p; + int i; + struct file *h_file; + + p = au_sp_fop; + if (unlikely(!p->done)) { + /* initialize first time only */ + static DEFINE_SPINLOCK(spin); + + spin_lock(&spin); + if (!p->done) { + BUILD_BUG_ON(sizeof(au_sp_fop)/sizeof(*au_sp_fop) + != AuSp_Last); + for (i = 0; i < AuSp_Last; i++) + spin_lock_init(&p[i].spin); + p->done = 1; + } + spin_unlock(&spin); + } + + switch (file->f_mode & (FMODE_READ | FMODE_WRITE)) { + case FMODE_READ: + i = AuSp_FIFO_R; + break; + case FMODE_WRITE: + i = AuSp_FIFO_W; + break; + case FMODE_READ | FMODE_WRITE: + i = AuSp_FIFO_RW; + break; + default: + BUG(); + } + + p += i; + if (unlikely(!p->done)) { + /* initialize first time only */ + h_file = au_hf_top(file); + spin_lock(&p->spin); + if (!p->done) { + p->fop = *h_file->f_op; + p->fop.owner = THIS_MODULE; + if (p->fop.aio_read) + p->fop.aio_read = aufs_aio_read_sp; + if (p->fop.aio_write) + p->fop.aio_write = aufs_aio_write_sp; + p->fop.release = aufs_release_sp; + p->done = 1; + } + spin_unlock(&p->spin); + } + file->f_op = &p->fop; +} + +static int au_cpup_sp(struct dentry *dentry) +{ + int err; + aufs_bindex_t bcpup; + struct au_pin pin; + struct au_wr_dir_args wr_dir_args = { + .force_btgt = -1, + .flags = 0 + }; + + AuDbg("%.*s\n", AuDLNPair(dentry)); + + di_read_unlock(dentry, AuLock_IR); + di_write_lock_child(dentry); + err = au_wr_dir(dentry, /*src_dentry*/NULL, &wr_dir_args); + if (unlikely(err < 0)) + goto out; + bcpup = err; + err = 0; + if (bcpup == au_dbstart(dentry)) + goto out; /* success */ + + err = au_pin(&pin, dentry, bcpup, au_opt_udba(dentry->d_sb), + AuPin_MNT_WRITE); + if (!err) { + err = au_sio_cpup_simple(dentry, bcpup, -1, AuCpup_DTIME); + au_unpin(&pin); + } + +out: + di_downgrade_lock(dentry, AuLock_IR); + return err; +} + +static int au_do_open_sp(struct file *file, int flags) +{ + int err; + struct dentry *dentry; + struct super_block *sb; + struct file *h_file; + struct inode *h_inode; + + dentry = file->f_dentry; + AuDbg("%.*s\n", AuDLNPair(dentry)); + + /* + * try copying-up. + * operate on the ro branch is not an error. + */ + au_cpup_sp(dentry); /* ignore */ + + /* prepare h_file */ + err = au_do_open_nondir(file, vfsub_file_flags(file)); + if (unlikely(err)) + goto out; + + sb = dentry->d_sb; + h_file = au_hf_top(file); + h_inode = h_file->f_dentry->d_inode; + di_read_unlock(dentry, AuLock_IR); + fi_write_unlock(file); + si_read_unlock(sb); + /* open this fifo in aufs */ + err = h_inode->i_fop->open(file->f_dentry->d_inode, file); + si_noflush_read_lock(sb); + fi_write_lock(file); + di_read_lock_child(dentry, AuLock_IR); + if (!err) + au_init_fop_sp(file); + +out: + return err; +} + +static int aufs_open_sp(struct inode *inode, struct file *file) +{ + int err; + struct super_block *sb; + + sb = file->f_dentry->d_sb; + si_read_lock(sb, AuLock_FLUSH); + err = au_do_open(file, au_do_open_sp, /*fidir*/NULL); + si_read_unlock(sb); + return err; +} + +/* ---------------------------------------------------------------------- */ + +void au_init_special_fop(struct inode *inode, umode_t mode, dev_t rdev) +{ + init_special_inode(inode, mode, rdev); + + switch (mode & S_IFMT) { + case S_IFIFO: + inode->i_fop = &au_sp_fop[AuSp_FIFO].fop; + /*FALLTHROUGH*/ + case S_IFCHR: + case S_IFBLK: + case S_IFSOCK: + break; + default: + AuDebugOn(1); + } +} + +int au_special_file(umode_t mode) +{ + int ret; + + ret = 0; + switch (mode & S_IFMT) { + case S_IFIFO: +#if 0 + case S_IFCHR: + case S_IFBLK: + case S_IFSOCK: +#endif + ret = 1; + } + + return ret; +} diff --git a/ubuntu/aufs/file.c b/ubuntu/aufs/file.c new file mode 100644 index 000000000000..0b9aa487f012 --- /dev/null +++ b/ubuntu/aufs/file.c @@ -0,0 +1,673 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * handling file/dir, and address_space operation + */ + +#include <linux/pagemap.h> +#include "aufs.h" + +/* drop flags for writing */ +unsigned int au_file_roflags(unsigned int flags) +{ + flags &= ~(O_WRONLY | O_RDWR | O_APPEND | O_CREAT | O_TRUNC); + flags |= O_RDONLY | O_NOATIME; + return flags; +} + +/* common functions to regular file and dir */ +struct file *au_h_open(struct dentry *dentry, aufs_bindex_t bindex, int flags, + struct file *file) +{ + struct file *h_file; + struct dentry *h_dentry; + struct inode *h_inode; + struct super_block *sb; + struct au_branch *br; + struct path h_path; + int err, exec_flag; + + /* a race condition can happen between open and unlink/rmdir */ + h_file = ERR_PTR(-ENOENT); + h_dentry = au_h_dptr(dentry, bindex); + if (au_test_nfsd() && !h_dentry) + goto out; + h_inode = h_dentry->d_inode; + if (au_test_nfsd() && !h_inode) + goto out; + spin_lock(&h_dentry->d_lock); + err = (!d_unhashed(dentry) && d_unlinked(h_dentry)) + || !h_inode + /* || !dentry->d_inode->i_nlink */ + ; + spin_unlock(&h_dentry->d_lock); + if (unlikely(err)) + goto out; + + sb = dentry->d_sb; + br = au_sbr(sb, bindex); + h_file = ERR_PTR(-EACCES); + exec_flag = flags & __FMODE_EXEC; + if (exec_flag && (br->br_mnt->mnt_flags & MNT_NOEXEC)) + goto out; + + /* drop flags for writing */ + if (au_test_ro(sb, bindex, dentry->d_inode)) + flags = au_file_roflags(flags); + flags &= ~O_CREAT; + atomic_inc(&br->br_count); + h_path.dentry = h_dentry; + h_path.mnt = br->br_mnt; + if (!au_special_file(h_inode->i_mode)) + h_file = vfsub_dentry_open(&h_path, flags); + else { + /* this block depends upon the configuration */ + di_read_unlock(dentry, AuLock_IR); + fi_write_unlock(file); + si_read_unlock(sb); + h_file = vfsub_dentry_open(&h_path, flags); + si_noflush_read_lock(sb); + fi_write_lock(file); + di_read_lock_child(dentry, AuLock_IR); + } + if (IS_ERR(h_file)) + goto out_br; + + if (exec_flag) { + err = deny_write_access(h_file); + if (unlikely(err)) { + fput(h_file); + h_file = ERR_PTR(err); + goto out_br; + } + } + fsnotify_open(h_file); + goto out; /* success */ + +out_br: + atomic_dec(&br->br_count); +out: + return h_file; +} + +int au_do_open(struct file *file, int (*open)(struct file *file, int flags), + struct au_fidir *fidir) +{ + int err; + struct dentry *dentry; + + err = au_finfo_init(file, fidir); + if (unlikely(err)) + goto out; + + dentry = file->f_dentry; + di_read_lock_child(dentry, AuLock_IR); + err = open(file, vfsub_file_flags(file)); + di_read_unlock(dentry, AuLock_IR); + + fi_write_unlock(file); + if (unlikely(err)) { + au_fi(file)->fi_hdir = NULL; + au_finfo_fin(file); + } + +out: + return err; +} + +int au_reopen_nondir(struct file *file) +{ + int err; + aufs_bindex_t bstart; + struct dentry *dentry; + struct file *h_file, *h_file_tmp; + + dentry = file->f_dentry; + AuDebugOn(au_special_file(dentry->d_inode->i_mode)); + bstart = au_dbstart(dentry); + h_file_tmp = NULL; + if (au_fbstart(file) == bstart) { + h_file = au_hf_top(file); + if (file->f_mode == h_file->f_mode) + return 0; /* success */ + h_file_tmp = h_file; + get_file(h_file_tmp); + au_set_h_fptr(file, bstart, NULL); + } + AuDebugOn(au_fi(file)->fi_hdir); + AuDebugOn(au_fbstart(file) < bstart); + + h_file = au_h_open(dentry, bstart, vfsub_file_flags(file) & ~O_TRUNC, + file); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out; /* todo: close all? */ + + err = 0; + au_set_fbstart(file, bstart); + au_set_h_fptr(file, bstart, h_file); + au_update_figen(file); + /* todo: necessary? */ + /* file->f_ra = h_file->f_ra; */ + +out: + if (h_file_tmp) + fput(h_file_tmp); + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int au_reopen_wh(struct file *file, aufs_bindex_t btgt, + struct dentry *hi_wh) +{ + int err; + aufs_bindex_t bstart; + struct au_dinfo *dinfo; + struct dentry *h_dentry; + struct au_hdentry *hdp; + + dinfo = au_di(file->f_dentry); + AuRwMustWriteLock(&dinfo->di_rwsem); + + bstart = dinfo->di_bstart; + dinfo->di_bstart = btgt; + hdp = dinfo->di_hdentry; + h_dentry = hdp[0 + btgt].hd_dentry; + hdp[0 + btgt].hd_dentry = hi_wh; + err = au_reopen_nondir(file); + hdp[0 + btgt].hd_dentry = h_dentry; + dinfo->di_bstart = bstart; + + return err; +} + +static int au_ready_to_write_wh(struct file *file, loff_t len, + aufs_bindex_t bcpup) +{ + int err; + struct inode *inode, *h_inode; + struct dentry *dentry, *h_dentry, *hi_wh; + + dentry = file->f_dentry; + au_update_dbstart(dentry); + inode = dentry->d_inode; + h_inode = NULL; + if (au_dbstart(dentry) <= bcpup && au_dbend(dentry) >= bcpup) { + h_dentry = au_h_dptr(dentry, bcpup); + if (h_dentry) + h_inode = h_dentry->d_inode; + } + hi_wh = au_hi_wh(inode, bcpup); + if (!hi_wh && !h_inode) + err = au_sio_cpup_wh(dentry, bcpup, len, file); + else + /* already copied-up after unlink */ + err = au_reopen_wh(file, bcpup, hi_wh); + + if (!err + && inode->i_nlink > 1 + && au_opt_test(au_mntflags(dentry->d_sb), PLINK)) + au_plink_append(inode, bcpup, au_h_dptr(dentry, bcpup)); + + return err; +} + +/* + * prepare the @file for writing. + */ +int au_ready_to_write(struct file *file, loff_t len, struct au_pin *pin) +{ + int err; + aufs_bindex_t bstart, bcpup, dbstart; + struct dentry *dentry, *parent, *h_dentry; + struct inode *h_inode, *inode; + struct super_block *sb; + struct file *h_file; + + dentry = file->f_dentry; + sb = dentry->d_sb; + inode = dentry->d_inode; + AuDebugOn(au_special_file(inode->i_mode)); + bstart = au_fbstart(file); + err = au_test_ro(sb, bstart, inode); + if (!err && (au_hf_top(file)->f_mode & FMODE_WRITE)) { + err = au_pin(pin, dentry, bstart, AuOpt_UDBA_NONE, /*flags*/0); + goto out; + } + + /* need to cpup or reopen */ + parent = dget_parent(dentry); + di_write_lock_parent(parent); + err = AuWbrCopyup(au_sbi(sb), dentry); + bcpup = err; + if (unlikely(err < 0)) + goto out_dgrade; + err = 0; + + if (!d_unhashed(dentry) && !au_h_dptr(parent, bcpup)) { + err = au_cpup_dirs(dentry, bcpup); + if (unlikely(err)) + goto out_dgrade; + } + + err = au_pin(pin, dentry, bcpup, AuOpt_UDBA_NONE, + AuPin_DI_LOCKED | AuPin_MNT_WRITE); + if (unlikely(err)) + goto out_dgrade; + + h_dentry = au_hf_top(file)->f_dentry; + h_inode = h_dentry->d_inode; + dbstart = au_dbstart(dentry); + if (dbstart <= bcpup) { + h_dentry = au_h_dptr(dentry, bcpup); + AuDebugOn(!h_dentry); + h_inode = h_dentry->d_inode; + AuDebugOn(!h_inode); + bstart = bcpup; + } + + if (dbstart <= bcpup /* just reopen */ + || !d_unhashed(dentry) /* copyup and reopen */ + ) { + mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD); + h_file = au_h_open_pre(dentry, bstart); + if (IS_ERR(h_file)) { + err = PTR_ERR(h_file); + h_file = NULL; + } else { + di_downgrade_lock(parent, AuLock_IR); + if (dbstart > bcpup) + err = au_sio_cpup_simple(dentry, bcpup, len, + AuCpup_DTIME); + if (!err) + err = au_reopen_nondir(file); + } + mutex_unlock(&h_inode->i_mutex); + au_h_open_post(dentry, bstart, h_file); + } else { /* copyup as wh and reopen */ + /* + * since writable hfsplus branch is not supported, + * h_open_pre/post() are unnecessary. + */ + mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD); + err = au_ready_to_write_wh(file, len, bcpup); + di_downgrade_lock(parent, AuLock_IR); + mutex_unlock(&h_inode->i_mutex); + } + + if (!err) { + au_pin_set_parent_lflag(pin, /*lflag*/0); + goto out_dput; /* success */ + } + au_unpin(pin); + goto out_unlock; + +out_dgrade: + di_downgrade_lock(parent, AuLock_IR); +out_unlock: + di_read_unlock(parent, AuLock_IR); +out_dput: + dput(parent); +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +int au_do_flush(struct file *file, fl_owner_t id, + int (*flush)(struct file *file, fl_owner_t id)) +{ + int err; + struct dentry *dentry; + struct super_block *sb; + struct inode *inode; + + dentry = file->f_dentry; + sb = dentry->d_sb; + inode = dentry->d_inode; + si_noflush_read_lock(sb); + fi_read_lock(file); + ii_read_lock_child(inode); + + err = flush(file, id); + au_cpup_attr_timesizes(inode); + + ii_read_unlock(inode); + fi_read_unlock(file); + si_read_unlock(sb); + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int au_file_refresh_by_inode(struct file *file, int *need_reopen) +{ + int err; + aufs_bindex_t bstart; + struct au_pin pin; + struct au_finfo *finfo; + struct dentry *dentry, *parent, *hi_wh; + struct inode *inode; + struct super_block *sb; + + FiMustWriteLock(file); + + err = 0; + finfo = au_fi(file); + dentry = file->f_dentry; + sb = dentry->d_sb; + inode = dentry->d_inode; + bstart = au_ibstart(inode); + if (bstart == finfo->fi_btop || IS_ROOT(dentry)) + goto out; + + parent = dget_parent(dentry); + if (au_test_ro(sb, bstart, inode)) { + di_read_lock_parent(parent, !AuLock_IR); + err = AuWbrCopyup(au_sbi(sb), dentry); + bstart = err; + di_read_unlock(parent, !AuLock_IR); + if (unlikely(err < 0)) + goto out_parent; + err = 0; + } + + di_read_lock_parent(parent, AuLock_IR); + hi_wh = au_hi_wh(inode, bstart); + if (!S_ISDIR(inode->i_mode) + && au_opt_test(au_mntflags(sb), PLINK) + && au_plink_test(inode) + && !d_unhashed(dentry)) { + err = au_test_and_cpup_dirs(dentry, bstart); + if (unlikely(err)) + goto out_unlock; + + /* always superio. */ + err = au_pin(&pin, dentry, bstart, AuOpt_UDBA_NONE, + AuPin_DI_LOCKED | AuPin_MNT_WRITE); + if (!err) + err = au_sio_cpup_simple(dentry, bstart, -1, + AuCpup_DTIME); + au_unpin(&pin); + } else if (hi_wh) { + /* already copied-up after unlink */ + err = au_reopen_wh(file, bstart, hi_wh); + *need_reopen = 0; + } + +out_unlock: + di_read_unlock(parent, AuLock_IR); +out_parent: + dput(parent); +out: + return err; +} + +static void au_do_refresh_dir(struct file *file) +{ + aufs_bindex_t bindex, bend, new_bindex, brid; + struct au_hfile *p, tmp, *q; + struct au_finfo *finfo; + struct super_block *sb; + struct au_fidir *fidir; + + FiMustWriteLock(file); + + sb = file->f_dentry->d_sb; + finfo = au_fi(file); + fidir = finfo->fi_hdir; + AuDebugOn(!fidir); + p = fidir->fd_hfile + finfo->fi_btop; + brid = p->hf_br->br_id; + bend = fidir->fd_bbot; + for (bindex = finfo->fi_btop; bindex <= bend; bindex++, p++) { + if (!p->hf_file) + continue; + + new_bindex = au_br_index(sb, p->hf_br->br_id); + if (new_bindex == bindex) + continue; + if (new_bindex < 0) { + au_set_h_fptr(file, bindex, NULL); + continue; + } + + /* swap two lower inode, and loop again */ + q = fidir->fd_hfile + new_bindex; + tmp = *q; + *q = *p; + *p = tmp; + if (tmp.hf_file) { + bindex--; + p--; + } + } + + p = fidir->fd_hfile; + if (!au_test_mmapped(file) && !d_unlinked(file->f_dentry)) { + bend = au_sbend(sb); + for (finfo->fi_btop = 0; finfo->fi_btop <= bend; + finfo->fi_btop++, p++) + if (p->hf_file) { + if (p->hf_file->f_dentry + && p->hf_file->f_dentry->d_inode) + break; + else + au_hfput(p, file); + } + } else { + bend = au_br_index(sb, brid); + for (finfo->fi_btop = 0; finfo->fi_btop < bend; + finfo->fi_btop++, p++) + if (p->hf_file) + au_hfput(p, file); + bend = au_sbend(sb); + } + + p = fidir->fd_hfile + bend; + for (fidir->fd_bbot = bend; fidir->fd_bbot >= finfo->fi_btop; + fidir->fd_bbot--, p--) + if (p->hf_file) { + if (p->hf_file->f_dentry + && p->hf_file->f_dentry->d_inode) + break; + else + au_hfput(p, file); + } + AuDebugOn(fidir->fd_bbot < finfo->fi_btop); +} + +/* + * after branch manipulating, refresh the file. + */ +static int refresh_file(struct file *file, int (*reopen)(struct file *file)) +{ + int err, need_reopen; + aufs_bindex_t bend, bindex; + struct dentry *dentry; + struct au_finfo *finfo; + struct au_hfile *hfile; + + dentry = file->f_dentry; + finfo = au_fi(file); + if (!finfo->fi_hdir) { + hfile = &finfo->fi_htop; + AuDebugOn(!hfile->hf_file); + bindex = au_br_index(dentry->d_sb, hfile->hf_br->br_id); + AuDebugOn(bindex < 0); + if (bindex != finfo->fi_btop) + au_set_fbstart(file, bindex); + } else { + err = au_fidir_realloc(finfo, au_sbend(dentry->d_sb) + 1); + if (unlikely(err)) + goto out; + au_do_refresh_dir(file); + } + + err = 0; + need_reopen = 1; + if (!au_test_mmapped(file)) + err = au_file_refresh_by_inode(file, &need_reopen); + if (!err && need_reopen && !d_unlinked(dentry)) + err = reopen(file); + if (!err) { + au_update_figen(file); + goto out; /* success */ + } + + /* error, close all lower files */ + if (finfo->fi_hdir) { + bend = au_fbend_dir(file); + for (bindex = au_fbstart(file); bindex <= bend; bindex++) + au_set_h_fptr(file, bindex, NULL); + } + +out: + return err; +} + +/* common function to regular file and dir */ +int au_reval_and_lock_fdi(struct file *file, int (*reopen)(struct file *file), + int wlock) +{ + int err; + unsigned int sigen, figen; + aufs_bindex_t bstart; + unsigned char pseudo_link; + struct dentry *dentry; + struct inode *inode; + + err = 0; + dentry = file->f_dentry; + inode = dentry->d_inode; + AuDebugOn(au_special_file(inode->i_mode)); + sigen = au_sigen(dentry->d_sb); + fi_write_lock(file); + figen = au_figen(file); + di_write_lock_child(dentry); + bstart = au_dbstart(dentry); + pseudo_link = (bstart != au_ibstart(inode)); + if (sigen == figen && !pseudo_link && au_fbstart(file) == bstart) { + if (!wlock) { + di_downgrade_lock(dentry, AuLock_IR); + fi_downgrade_lock(file); + } + goto out; /* success */ + } + + AuDbg("sigen %d, figen %d\n", sigen, figen); + if (au_digen_test(dentry, sigen)) { + err = au_reval_dpath(dentry, sigen); + AuDebugOn(!err && au_digen_test(dentry, sigen)); + } + + if (!err) + err = refresh_file(file, reopen); + if (!err) { + if (!wlock) { + di_downgrade_lock(dentry, AuLock_IR); + fi_downgrade_lock(file); + } + } else { + di_write_unlock(dentry); + fi_write_unlock(file); + } + +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* cf. aufs_nopage() */ +/* for madvise(2) */ +static int aufs_readpage(struct file *file __maybe_unused, struct page *page) +{ + unlock_page(page); + return 0; +} + +/* it will never be called, but necessary to support O_DIRECT */ +static ssize_t aufs_direct_IO(int rw, struct kiocb *iocb, + const struct iovec *iov, loff_t offset, + unsigned long nr_segs) +{ BUG(); return 0; } + +/* + * it will never be called, but madvise and fadvise behaves differently + * when get_xip_mem is defined + */ +static int aufs_get_xip_mem(struct address_space *mapping, pgoff_t pgoff, + int create, void **kmem, unsigned long *pfn) +{ BUG(); return 0; } + +/* they will never be called. */ +#ifdef CONFIG_AUFS_DEBUG +static int aufs_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata) +{ AuUnsupport(); return 0; } +static int aufs_write_end(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) +{ AuUnsupport(); return 0; } +static int aufs_writepage(struct page *page, struct writeback_control *wbc) +{ AuUnsupport(); return 0; } + +static int aufs_set_page_dirty(struct page *page) +{ AuUnsupport(); return 0; } +static void aufs_invalidatepage(struct page *page, unsigned long offset) +{ AuUnsupport(); } +static int aufs_releasepage(struct page *page, gfp_t gfp) +{ AuUnsupport(); return 0; } +static int aufs_migratepage(struct address_space *mapping, struct page *newpage, + struct page *page) +{ AuUnsupport(); return 0; } +static int aufs_launder_page(struct page *page) +{ AuUnsupport(); return 0; } +static int aufs_is_partially_uptodate(struct page *page, + read_descriptor_t *desc, + unsigned long from) +{ AuUnsupport(); return 0; } +static int aufs_error_remove_page(struct address_space *mapping, + struct page *page) +{ AuUnsupport(); return 0; } +#endif /* CONFIG_AUFS_DEBUG */ + +const struct address_space_operations aufs_aop = { + .readpage = aufs_readpage, + .direct_IO = aufs_direct_IO, + .get_xip_mem = aufs_get_xip_mem, +#ifdef CONFIG_AUFS_DEBUG + .writepage = aufs_writepage, + /* no writepages, because of writepage */ + .set_page_dirty = aufs_set_page_dirty, + /* no readpages, because of readpage */ + .write_begin = aufs_write_begin, + .write_end = aufs_write_end, + /* no bmap, no block device */ + .invalidatepage = aufs_invalidatepage, + .releasepage = aufs_releasepage, + .migratepage = aufs_migratepage, + .launder_page = aufs_launder_page, + .is_partially_uptodate = aufs_is_partially_uptodate, + .error_remove_page = aufs_error_remove_page +#endif /* CONFIG_AUFS_DEBUG */ +}; diff --git a/ubuntu/aufs/file.h b/ubuntu/aufs/file.h new file mode 100644 index 000000000000..8bd6e3bab1a0 --- /dev/null +++ b/ubuntu/aufs/file.h @@ -0,0 +1,298 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * file operations + */ + +#ifndef __AUFS_FILE_H__ +#define __AUFS_FILE_H__ + +#ifdef __KERNEL__ + +#include <linux/file.h> +#include <linux/fs.h> +#include <linux/poll.h> +#include "rwsem.h" + +struct au_branch; +struct au_hfile { + struct file *hf_file; + struct au_branch *hf_br; +}; + +struct au_vdir; +struct au_fidir { + aufs_bindex_t fd_bbot; + aufs_bindex_t fd_nent; + struct au_vdir *fd_vdir_cache; + struct au_hfile fd_hfile[]; +}; + +static inline int au_fidir_sz(int nent) +{ + AuDebugOn(nent < 0); + return sizeof(struct au_fidir) + sizeof(struct au_hfile) * nent; +} + +struct au_finfo { + atomic_t fi_generation; + + struct au_rwsem fi_rwsem; + aufs_bindex_t fi_btop; + + /* do not union them */ + struct { /* for non-dir */ + struct au_hfile fi_htop; + atomic_t fi_mmapped; + }; + struct au_fidir *fi_hdir; /* for dir only */ +} ____cacheline_aligned_in_smp; + +/* ---------------------------------------------------------------------- */ + +/* file.c */ +extern const struct address_space_operations aufs_aop; +unsigned int au_file_roflags(unsigned int flags); +struct file *au_h_open(struct dentry *dentry, aufs_bindex_t bindex, int flags, + struct file *file); +int au_do_open(struct file *file, int (*open)(struct file *file, int flags), + struct au_fidir *fidir); +int au_reopen_nondir(struct file *file); +struct au_pin; +int au_ready_to_write(struct file *file, loff_t len, struct au_pin *pin); +int au_reval_and_lock_fdi(struct file *file, int (*reopen)(struct file *file), + int wlock); +int au_do_flush(struct file *file, fl_owner_t id, + int (*flush)(struct file *file, fl_owner_t id)); + +/* poll.c */ +#ifdef CONFIG_AUFS_POLL +unsigned int aufs_poll(struct file *file, poll_table *wait); +#endif + +#ifdef CONFIG_AUFS_BR_HFSPLUS +/* hfsplus.c */ +struct file *au_h_open_pre(struct dentry *dentry, aufs_bindex_t bindex); +void au_h_open_post(struct dentry *dentry, aufs_bindex_t bindex, + struct file *h_file); +#else +static inline +struct file *au_h_open_pre(struct dentry *dentry, aufs_bindex_t bindex) +{ + return NULL; +} + +AuStubVoid(au_h_open_post, struct dentry *dentry, aufs_bindex_t bindex, + struct file *h_file); +#endif + +/* f_op.c */ +extern const struct file_operations aufs_file_fop; +int au_do_open_nondir(struct file *file, int flags); +int aufs_release_nondir(struct inode *inode __maybe_unused, struct file *file); + +#ifdef CONFIG_AUFS_SP_IATTR +/* f_op_sp.c */ +int au_special_file(umode_t mode); +void au_init_special_fop(struct inode *inode, umode_t mode, dev_t rdev); +#else +AuStubInt0(au_special_file, umode_t mode) +static inline void au_init_special_fop(struct inode *inode, umode_t mode, + dev_t rdev) +{ + init_special_inode(inode, mode, rdev); +} +#endif + +/* finfo.c */ +void au_hfput(struct au_hfile *hf, struct file *file); +void au_set_h_fptr(struct file *file, aufs_bindex_t bindex, + struct file *h_file); + +void au_update_figen(struct file *file); +struct au_fidir *au_fidir_alloc(struct super_block *sb); +int au_fidir_realloc(struct au_finfo *finfo, int nbr); + +void au_fi_init_once(void *_fi); +void au_finfo_fin(struct file *file); +int au_finfo_init(struct file *file, struct au_fidir *fidir); + +/* ioctl.c */ +long aufs_ioctl_nondir(struct file *file, unsigned int cmd, unsigned long arg); +#ifdef CONFIG_COMPAT +long aufs_compat_ioctl_dir(struct file *file, unsigned int cmd, + unsigned long arg); +#endif + +/* ---------------------------------------------------------------------- */ + +static inline struct au_finfo *au_fi(struct file *file) +{ + return file->private_data; +} + +/* ---------------------------------------------------------------------- */ + +/* + * fi_read_lock, fi_write_lock, + * fi_read_unlock, fi_write_unlock, fi_downgrade_lock + */ +AuSimpleRwsemFuncs(fi, struct file *f, &au_fi(f)->fi_rwsem); + +#define FiMustNoWaiters(f) AuRwMustNoWaiters(&au_fi(f)->fi_rwsem) +#define FiMustAnyLock(f) AuRwMustAnyLock(&au_fi(f)->fi_rwsem) +#define FiMustWriteLock(f) AuRwMustWriteLock(&au_fi(f)->fi_rwsem) + +/* ---------------------------------------------------------------------- */ + +/* todo: hard/soft set? */ +static inline aufs_bindex_t au_fbstart(struct file *file) +{ + FiMustAnyLock(file); + return au_fi(file)->fi_btop; +} + +static inline aufs_bindex_t au_fbend_dir(struct file *file) +{ + FiMustAnyLock(file); + AuDebugOn(!au_fi(file)->fi_hdir); + return au_fi(file)->fi_hdir->fd_bbot; +} + +static inline struct au_vdir *au_fvdir_cache(struct file *file) +{ + FiMustAnyLock(file); + AuDebugOn(!au_fi(file)->fi_hdir); + return au_fi(file)->fi_hdir->fd_vdir_cache; +} + +static inline void au_set_fbstart(struct file *file, aufs_bindex_t bindex) +{ + FiMustWriteLock(file); + au_fi(file)->fi_btop = bindex; +} + +static inline void au_set_fbend_dir(struct file *file, aufs_bindex_t bindex) +{ + FiMustWriteLock(file); + AuDebugOn(!au_fi(file)->fi_hdir); + au_fi(file)->fi_hdir->fd_bbot = bindex; +} + +static inline void au_set_fvdir_cache(struct file *file, + struct au_vdir *vdir_cache) +{ + FiMustWriteLock(file); + AuDebugOn(!au_fi(file)->fi_hdir); + au_fi(file)->fi_hdir->fd_vdir_cache = vdir_cache; +} + +static inline struct file *au_hf_top(struct file *file) +{ + FiMustAnyLock(file); + AuDebugOn(au_fi(file)->fi_hdir); + return au_fi(file)->fi_htop.hf_file; +} + +static inline struct file *au_hf_dir(struct file *file, aufs_bindex_t bindex) +{ + FiMustAnyLock(file); + AuDebugOn(!au_fi(file)->fi_hdir); + return au_fi(file)->fi_hdir->fd_hfile[0 + bindex].hf_file; +} + +/* todo: memory barrier? */ +static inline unsigned int au_figen(struct file *f) +{ + return atomic_read(&au_fi(f)->fi_generation); +} + +static inline void au_set_mmapped(struct file *f) +{ + if (atomic_inc_return(&au_fi(f)->fi_mmapped)) + return; + pr_warning("fi_mmapped wrapped around\n"); + while (!atomic_inc_return(&au_fi(f)->fi_mmapped)) + ; +} + +static inline void au_unset_mmapped(struct file *f) +{ + atomic_dec(&au_fi(f)->fi_mmapped); +} + +static inline int au_test_mmapped(struct file *f) +{ + return atomic_read(&au_fi(f)->fi_mmapped); +} + +/* customize vma->vm_file */ + +static inline void au_do_vm_file_reset(struct vm_area_struct *vma, + struct file *file) +{ + struct file *f; + + f = vma->vm_file; + get_file(file); + vma->vm_file = file; + fput(f); +} + +#ifdef CONFIG_MMU +#define AuDbgVmRegion(file, vma) do {} while (0) + +static inline void au_vm_file_reset(struct vm_area_struct *vma, + struct file *file) +{ + au_do_vm_file_reset(vma, file); +} +#else +#define AuDbgVmRegion(file, vma) \ + AuDebugOn((vma)->vm_region && (vma)->vm_region->vm_file != (file)) + +static inline void au_vm_file_reset(struct vm_area_struct *vma, + struct file *file) +{ + struct file *f; + + au_do_vm_file_reset(vma, file); + f = vma->vm_region->vm_file; + get_file(file); + vma->vm_region->vm_file = file; + fput(f); +} +#endif /* CONFIG_MMU */ + +/* handle vma->vm_prfile */ +static inline void au_vm_prfile_set(struct vm_area_struct *vma, + struct file *file) +{ +#ifdef CONFIG_AUFS_PROC_MAP + get_file(file); + vma->vm_prfile = file; +#ifndef CONFIG_MMU + get_file(file); + vma->vm_region->vm_prfile = file; +#endif +#endif +} + +#endif /* __KERNEL__ */ +#endif /* __AUFS_FILE_H__ */ diff --git a/ubuntu/aufs/finfo.c b/ubuntu/aufs/finfo.c new file mode 100644 index 000000000000..3208510c5ee9 --- /dev/null +++ b/ubuntu/aufs/finfo.c @@ -0,0 +1,156 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * file private data + */ + +#include "aufs.h" + +void au_hfput(struct au_hfile *hf, struct file *file) +{ + /* todo: direct access f_flags */ + if (vfsub_file_flags(file) & __FMODE_EXEC) + allow_write_access(hf->hf_file); + fput(hf->hf_file); + hf->hf_file = NULL; + atomic_dec(&hf->hf_br->br_count); + hf->hf_br = NULL; +} + +void au_set_h_fptr(struct file *file, aufs_bindex_t bindex, struct file *val) +{ + struct au_finfo *finfo = au_fi(file); + struct au_hfile *hf; + struct au_fidir *fidir; + + fidir = finfo->fi_hdir; + if (!fidir) { + AuDebugOn(finfo->fi_btop != bindex); + hf = &finfo->fi_htop; + } else + hf = fidir->fd_hfile + bindex; + + if (hf && hf->hf_file) + au_hfput(hf, file); + if (val) { + FiMustWriteLock(file); + hf->hf_file = val; + hf->hf_br = au_sbr(file->f_dentry->d_sb, bindex); + } +} + +void au_update_figen(struct file *file) +{ + atomic_set(&au_fi(file)->fi_generation, au_digen(file->f_dentry)); + /* smp_mb(); */ /* atomic_set */ +} + +/* ---------------------------------------------------------------------- */ + +struct au_fidir *au_fidir_alloc(struct super_block *sb) +{ + struct au_fidir *fidir; + int nbr; + + nbr = au_sbend(sb) + 1; + if (nbr < 2) + nbr = 2; /* initial allocate for 2 branches */ + fidir = kzalloc(au_fidir_sz(nbr), GFP_NOFS); + if (fidir) { + fidir->fd_bbot = -1; + fidir->fd_nent = nbr; + fidir->fd_vdir_cache = NULL; + } + + return fidir; +} + +int au_fidir_realloc(struct au_finfo *finfo, int nbr) +{ + int err; + struct au_fidir *fidir, *p; + + AuRwMustWriteLock(&finfo->fi_rwsem); + fidir = finfo->fi_hdir; + AuDebugOn(!fidir); + + err = -ENOMEM; + p = au_kzrealloc(fidir, au_fidir_sz(fidir->fd_nent), au_fidir_sz(nbr), + GFP_NOFS); + if (p) { + p->fd_nent = nbr; + finfo->fi_hdir = p; + err = 0; + } + + return err; +} + +/* ---------------------------------------------------------------------- */ + +void au_finfo_fin(struct file *file) +{ + struct au_finfo *finfo; + + au_nfiles_dec(file->f_dentry->d_sb); + + finfo = au_fi(file); + AuDebugOn(finfo->fi_hdir); + AuRwDestroy(&finfo->fi_rwsem); + au_cache_free_finfo(finfo); +} + +void au_fi_init_once(void *_finfo) +{ + struct au_finfo *finfo = _finfo; + static struct lock_class_key aufs_fi; + + au_rw_init(&finfo->fi_rwsem); + au_rw_class(&finfo->fi_rwsem, &aufs_fi); +} + +int au_finfo_init(struct file *file, struct au_fidir *fidir) +{ + int err, lc_idx; + struct au_finfo *finfo; + struct dentry *dentry; + + err = -ENOMEM; + dentry = file->f_dentry; + finfo = au_cache_alloc_finfo(); + if (unlikely(!finfo)) + goto out; + + err = 0; + au_nfiles_inc(dentry->d_sb); + lc_idx = AuLcNonDir_FIINFO; + if (fidir) + lc_idx = AuLcDir_FIINFO; + au_rw_class(&finfo->fi_rwsem, au_lc_key + lc_idx); + au_rw_write_lock(&finfo->fi_rwsem); + finfo->fi_btop = -1; + finfo->fi_hdir = fidir; + atomic_set(&finfo->fi_generation, au_digen(dentry)); + /* smp_mb(); */ /* atomic_set */ + + file->private_data = finfo; + +out: + return err; +} diff --git a/ubuntu/aufs/fstype.h b/ubuntu/aufs/fstype.h new file mode 100644 index 000000000000..a6b1037eeeeb --- /dev/null +++ b/ubuntu/aufs/fstype.h @@ -0,0 +1,496 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * judging filesystem type + */ + +#ifndef __AUFS_FSTYPE_H__ +#define __AUFS_FSTYPE_H__ + +#ifdef __KERNEL__ + +#include <linux/fs.h> +#include <linux/magic.h> +#include <linux/romfs_fs.h> + +static inline int au_test_aufs(struct super_block *sb) +{ + return sb->s_magic == AUFS_SUPER_MAGIC; +} + +static inline const char *au_sbtype(struct super_block *sb) +{ + return sb->s_type->name; +} + +static inline int au_test_iso9660(struct super_block *sb __maybe_unused) +{ +#if defined(CONFIG_ROMFS_FS) || defined(CONFIG_ROMFS_FS_MODULE) + return sb->s_magic == ROMFS_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_romfs(struct super_block *sb __maybe_unused) +{ +#if defined(CONFIG_ISO9660_FS) || defined(CONFIG_ISO9660_FS_MODULE) + return sb->s_magic == ISOFS_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_cramfs(struct super_block *sb __maybe_unused) +{ +#if defined(CONFIG_CRAMFS) || defined(CONFIG_CRAMFS_MODULE) + return sb->s_magic == CRAMFS_MAGIC; +#endif + return 0; +} + +static inline int au_test_nfs(struct super_block *sb __maybe_unused) +{ +#if defined(CONFIG_NFS_FS) || defined(CONFIG_NFS_FS_MODULE) + return sb->s_magic == NFS_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_fuse(struct super_block *sb __maybe_unused) +{ +#if defined(CONFIG_FUSE_FS) || defined(CONFIG_FUSE_FS_MODULE) + return sb->s_magic == FUSE_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_xfs(struct super_block *sb __maybe_unused) +{ +#if defined(CONFIG_XFS_FS) || defined(CONFIG_XFS_FS_MODULE) + return sb->s_magic == XFS_SB_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_tmpfs(struct super_block *sb __maybe_unused) +{ +#ifdef CONFIG_TMPFS + return sb->s_magic == TMPFS_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_ecryptfs(struct super_block *sb __maybe_unused) +{ +#if defined(CONFIG_ECRYPT_FS) || defined(CONFIG_ECRYPT_FS_MODULE) + return !strcmp(au_sbtype(sb), "ecryptfs"); +#else + return 0; +#endif +} + +static inline int au_test_smbfs(struct super_block *sb __maybe_unused) +{ +#if defined(CONFIG_SMB_FS) || defined(CONFIG_SMB_FS_MODULE) + return sb->s_magic == SMB_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_ocfs2(struct super_block *sb __maybe_unused) +{ +#if defined(CONFIG_OCFS2_FS) || defined(CONFIG_OCFS2_FS_MODULE) + return sb->s_magic == OCFS2_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_ocfs2_dlmfs(struct super_block *sb __maybe_unused) +{ +#if defined(CONFIG_OCFS2_FS_O2CB) || defined(CONFIG_OCFS2_FS_O2CB_MODULE) + return sb->s_magic == DLMFS_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_coda(struct super_block *sb __maybe_unused) +{ +#if defined(CONFIG_CODA_FS) || defined(CONFIG_CODA_FS_MODULE) + return sb->s_magic == CODA_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_v9fs(struct super_block *sb __maybe_unused) +{ +#if defined(CONFIG_9P_FS) || defined(CONFIG_9P_FS_MODULE) + return sb->s_magic == V9FS_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_ext4(struct super_block *sb __maybe_unused) +{ +#if defined(CONFIG_EXT4DEV_FS) || defined(CONFIG_EXT4DEV_FS_MODULE) + return sb->s_magic == EXT4_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_sysv(struct super_block *sb __maybe_unused) +{ +#if defined(CONFIG_SYSV_FS) || defined(CONFIG_SYSV_FS_MODULE) + return !strcmp(au_sbtype(sb), "sysv"); +#else + return 0; +#endif +} + +static inline int au_test_ramfs(struct super_block *sb) +{ + return sb->s_magic == RAMFS_MAGIC; +} + +static inline int au_test_ubifs(struct super_block *sb __maybe_unused) +{ +#if defined(CONFIG_UBIFS_FS) || defined(CONFIG_UBIFS_FS_MODULE) + return sb->s_magic == UBIFS_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_procfs(struct super_block *sb __maybe_unused) +{ +#ifdef CONFIG_PROC_FS + return sb->s_magic == PROC_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_sysfs(struct super_block *sb __maybe_unused) +{ +#ifdef CONFIG_SYSFS + return sb->s_magic == SYSFS_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_configfs(struct super_block *sb __maybe_unused) +{ +#if defined(CONFIG_CONFIGFS_FS) || defined(CONFIG_CONFIGFS_FS_MODULE) + return sb->s_magic == CONFIGFS_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_minix(struct super_block *sb __maybe_unused) +{ +#if defined(CONFIG_MINIX_FS) || defined(CONFIG_MINIX_FS_MODULE) + return sb->s_magic == MINIX3_SUPER_MAGIC + || sb->s_magic == MINIX2_SUPER_MAGIC + || sb->s_magic == MINIX2_SUPER_MAGIC2 + || sb->s_magic == MINIX_SUPER_MAGIC + || sb->s_magic == MINIX_SUPER_MAGIC2; +#else + return 0; +#endif +} + +static inline int au_test_cifs(struct super_block *sb __maybe_unused) +{ +#if defined(CONFIG_CIFS_FS) || defined(CONFIGCIFS_FS_MODULE) + return sb->s_magic == CIFS_MAGIC_NUMBER; +#else + return 0; +#endif +} + +static inline int au_test_fat(struct super_block *sb __maybe_unused) +{ +#if defined(CONFIG_FAT_FS) || defined(CONFIG_FAT_FS_MODULE) + return sb->s_magic == MSDOS_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_msdos(struct super_block *sb) +{ + return au_test_fat(sb); +} + +static inline int au_test_vfat(struct super_block *sb) +{ + return au_test_fat(sb); +} + +static inline int au_test_securityfs(struct super_block *sb __maybe_unused) +{ +#ifdef CONFIG_SECURITYFS + return sb->s_magic == SECURITYFS_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_squashfs(struct super_block *sb __maybe_unused) +{ +#if defined(CONFIG_SQUASHFS) || defined(CONFIG_SQUASHFS_MODULE) + return sb->s_magic == SQUASHFS_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_btrfs(struct super_block *sb __maybe_unused) +{ +#if defined(CONFIG_BTRFS_FS) || defined(CONFIG_BTRFS_FS_MODULE) + return sb->s_magic == BTRFS_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_xenfs(struct super_block *sb __maybe_unused) +{ +#if defined(CONFIG_XENFS) || defined(CONFIG_XENFS_MODULE) + return sb->s_magic == XENFS_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_debugfs(struct super_block *sb __maybe_unused) +{ +#ifdef CONFIG_DEBUG_FS + return sb->s_magic == DEBUGFS_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_nilfs(struct super_block *sb __maybe_unused) +{ +#if defined(CONFIG_NILFS) || defined(CONFIG_NILFS_MODULE) + return sb->s_magic == NILFS_SUPER_MAGIC; +#else + return 0; +#endif +} + +static inline int au_test_hfsplus(struct super_block *sb __maybe_unused) +{ +#if defined(CONFIG_HFSPLUS_FS) || defined(CONFIG_HFSPLUS_FS_MODULE) + return sb->s_magic == HFSPLUS_SUPER_MAGIC; +#else + return 0; +#endif +} + +/* ---------------------------------------------------------------------- */ +/* + * they can't be an aufs branch. + */ +static inline int au_test_fs_unsuppoted(struct super_block *sb) +{ + return +#ifndef CONFIG_AUFS_BR_RAMFS + au_test_ramfs(sb) || +#endif + au_test_procfs(sb) + || au_test_sysfs(sb) + || au_test_configfs(sb) + || au_test_debugfs(sb) + || au_test_securityfs(sb) + || au_test_xenfs(sb) + || au_test_ecryptfs(sb) + /* || !strcmp(au_sbtype(sb), "unionfs") */ + || au_test_aufs(sb); /* will be supported in next version */ +} + +/* + * If the filesystem supports NFS-export, then it has to support NULL as + * a nameidata parameter for ->create(), ->lookup() and ->d_revalidate(). + * We can apply this principle when we handle a lower filesystem. + */ +static inline int au_test_fs_null_nd(struct super_block *sb) +{ + return !!sb->s_export_op; +} + +static inline int au_test_fs_remote(struct super_block *sb) +{ + return !au_test_tmpfs(sb) +#ifdef CONFIG_AUFS_BR_RAMFS + && !au_test_ramfs(sb) +#endif + && !(sb->s_type->fs_flags & FS_REQUIRES_DEV); +} + +/* ---------------------------------------------------------------------- */ + +/* + * Note: these functions (below) are created after reading ->getattr() in all + * filesystems under linux/fs. it means we have to do so in every update... + */ + +/* + * some filesystems require getattr to refresh the inode attributes before + * referencing. + * in most cases, we can rely on the inode attribute in NFS (or every remote fs) + * and leave the work for d_revalidate() + */ +static inline int au_test_fs_refresh_iattr(struct super_block *sb) +{ + return au_test_nfs(sb) + || au_test_fuse(sb) + /* || au_test_smbfs(sb) */ /* untested */ + /* || au_test_ocfs2(sb) */ /* untested */ + /* || au_test_btrfs(sb) */ /* untested */ + /* || au_test_coda(sb) */ /* untested */ + /* || au_test_v9fs(sb) */ /* untested */ + ; +} + +/* + * filesystems which don't maintain i_size or i_blocks. + */ +static inline int au_test_fs_bad_iattr_size(struct super_block *sb) +{ + return au_test_xfs(sb) + || au_test_btrfs(sb) + || au_test_ubifs(sb) + || au_test_hfsplus(sb) /* maintained, but incorrect */ + /* || au_test_ext4(sb) */ /* untested */ + /* || au_test_ocfs2(sb) */ /* untested */ + /* || au_test_ocfs2_dlmfs(sb) */ /* untested */ + /* || au_test_sysv(sb) */ /* untested */ + /* || au_test_minix(sb) */ /* untested */ + ; +} + +/* + * filesystems which don't store the correct value in some of their inode + * attributes. + */ +static inline int au_test_fs_bad_iattr(struct super_block *sb) +{ + return au_test_fs_bad_iattr_size(sb) + /* || au_test_cifs(sb) */ /* untested */ + || au_test_fat(sb) + || au_test_msdos(sb) + || au_test_vfat(sb); +} + +/* they don't check i_nlink in link(2) */ +static inline int au_test_fs_no_limit_nlink(struct super_block *sb) +{ + return au_test_tmpfs(sb) +#ifdef CONFIG_AUFS_BR_RAMFS + || au_test_ramfs(sb) +#endif + || au_test_ubifs(sb) + || au_test_btrfs(sb) + || au_test_hfsplus(sb); +} + +/* + * filesystems which sets S_NOATIME and S_NOCMTIME. + */ +static inline int au_test_fs_notime(struct super_block *sb) +{ + return au_test_nfs(sb) + || au_test_fuse(sb) + || au_test_ubifs(sb) + /* || au_test_cifs(sb) */ /* untested */ + ; +} + +/* + * filesystems which requires replacing i_mapping. + */ +static inline int au_test_fs_bad_mapping(struct super_block *sb) +{ + return au_test_fuse(sb) + || au_test_ubifs(sb); +} + +/* temporary support for i#1 in cramfs */ +static inline int au_test_fs_unique_ino(struct inode *inode) +{ + if (au_test_cramfs(inode->i_sb)) + return inode->i_ino != 1; + return 1; +} + +/* ---------------------------------------------------------------------- */ + +/* + * the filesystem where the xino files placed must support i/o after unlink and + * maintain i_size and i_blocks. + */ +static inline int au_test_fs_bad_xino(struct super_block *sb) +{ + return au_test_fs_remote(sb) + || au_test_fs_bad_iattr_size(sb) +#ifdef CONFIG_AUFS_BR_RAMFS + || !(au_test_ramfs(sb) || au_test_fs_null_nd(sb)) +#else + || !au_test_fs_null_nd(sb) /* to keep xino code simple */ +#endif + /* don't want unnecessary work for xino */ + || au_test_aufs(sb) + || au_test_ecryptfs(sb) + || au_test_nilfs(sb); +} + +static inline int au_test_fs_trunc_xino(struct super_block *sb) +{ + return au_test_tmpfs(sb) + || au_test_ramfs(sb); +} + +/* + * test if the @sb is real-readonly. + */ +static inline int au_test_fs_rr(struct super_block *sb) +{ + return au_test_squashfs(sb) + || au_test_iso9660(sb) + || au_test_cramfs(sb) + || au_test_romfs(sb); +} + +#endif /* __KERNEL__ */ +#endif /* __AUFS_FSTYPE_H__ */ diff --git a/ubuntu/aufs/hfsnotify.c b/ubuntu/aufs/hfsnotify.c new file mode 100644 index 000000000000..c48c315ac3e2 --- /dev/null +++ b/ubuntu/aufs/hfsnotify.c @@ -0,0 +1,247 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * fsnotify for the lower directories + */ + +#include "aufs.h" + +/* FS_IN_IGNORED is unnecessary */ +static const __u32 AuHfsnMask = (FS_MOVED_TO | FS_MOVED_FROM | FS_DELETE + | FS_CREATE | FS_EVENT_ON_CHILD); +static DECLARE_WAIT_QUEUE_HEAD(au_hfsn_wq); + +static void au_hfsn_free_mark(struct fsnotify_mark *mark) +{ + struct au_hnotify *hn = container_of(mark, struct au_hnotify, + hn_mark); + AuDbg("here\n"); + hn->hn_mark_dead = 1; + smp_mb(); + wake_up_all(&au_hfsn_wq); +} + +static int au_hfsn_alloc(struct au_hinode *hinode) +{ + struct au_hnotify *hn; + struct super_block *sb; + struct au_branch *br; + struct fsnotify_mark *mark; + aufs_bindex_t bindex; + + hn = hinode->hi_notify; + sb = hn->hn_aufs_inode->i_sb; + bindex = au_br_index(sb, hinode->hi_id); + br = au_sbr(sb, bindex); + hn->hn_mark_dead = 0; + mark = &hn->hn_mark; + fsnotify_init_mark(mark, au_hfsn_free_mark); + mark->mask = AuHfsnMask; + /* + * by udba rename or rmdir, aufs assign a new inode to the known + * h_inode, so specify 1 to allow dups. + */ + return fsnotify_add_mark(mark, br->br_hfsn_group, hinode->hi_inode, + /*mnt*/NULL, /*allow_dups*/1); +} + +static void au_hfsn_free(struct au_hinode *hinode) +{ + struct au_hnotify *hn; + struct fsnotify_mark *mark; + + hn = hinode->hi_notify; + mark = &hn->hn_mark; + fsnotify_destroy_mark(mark); + fsnotify_put_mark(mark); + + /* TODO: bad approach */ + wait_event(au_hfsn_wq, hn->hn_mark_dead); +} + +/* ---------------------------------------------------------------------- */ + +static void au_hfsn_ctl(struct au_hinode *hinode, int do_set) +{ + struct fsnotify_mark *mark; + + mark = &hinode->hi_notify->hn_mark; + spin_lock(&mark->lock); + if (do_set) { + AuDebugOn(mark->mask & AuHfsnMask); + mark->mask |= AuHfsnMask; + } else { + AuDebugOn(!(mark->mask & AuHfsnMask)); + mark->mask &= ~AuHfsnMask; + } + spin_unlock(&mark->lock); + /* fsnotify_recalc_inode_mask(hinode->hi_inode); */ +} + +/* ---------------------------------------------------------------------- */ + +/* #define AuDbgHnotify */ +#ifdef AuDbgHnotify +static char *au_hfsn_name(u32 mask) +{ +#ifdef CONFIG_AUFS_DEBUG +#define test_ret(flag) if (mask & flag) \ + return #flag; + test_ret(FS_ACCESS); + test_ret(FS_MODIFY); + test_ret(FS_ATTRIB); + test_ret(FS_CLOSE_WRITE); + test_ret(FS_CLOSE_NOWRITE); + test_ret(FS_OPEN); + test_ret(FS_MOVED_FROM); + test_ret(FS_MOVED_TO); + test_ret(FS_CREATE); + test_ret(FS_DELETE); + test_ret(FS_DELETE_SELF); + test_ret(FS_MOVE_SELF); + test_ret(FS_UNMOUNT); + test_ret(FS_Q_OVERFLOW); + test_ret(FS_IN_IGNORED); + test_ret(FS_IN_ISDIR); + test_ret(FS_IN_ONESHOT); + test_ret(FS_EVENT_ON_CHILD); + return ""; +#undef test_ret +#else + return "??"; +#endif +} +#endif + +/* ---------------------------------------------------------------------- */ + +static int au_hfsn_handle_event(struct fsnotify_group *group, + struct fsnotify_mark *inode_mark, + struct fsnotify_mark *vfsmount_mark, + struct fsnotify_event *event) +{ + int err; + struct au_hnotify *hnotify; + struct inode *h_dir, *h_inode; + __u32 mask; + struct qstr h_child_qstr = { + .name = event->file_name, + .len = event->name_len + }; + + AuDebugOn(event->data_type != FSNOTIFY_EVENT_INODE); + + err = 0; + /* if FS_UNMOUNT happens, there must be another bug */ + mask = event->mask; + AuDebugOn(mask & FS_UNMOUNT); + if (mask & (FS_IN_IGNORED | FS_UNMOUNT)) + goto out; + + h_dir = event->to_tell; + h_inode = event->inode; +#ifdef AuDbgHnotify + au_debug(1); + if (1 || h_child_qstr.len != sizeof(AUFS_XINO_FNAME) - 1 + || strncmp(h_child_qstr.name, AUFS_XINO_FNAME, h_child_qstr.len)) { + AuDbg("i%lu, mask 0x%x %s, hcname %.*s, hi%lu\n", + h_dir->i_ino, mask, au_hfsn_name(mask), + AuLNPair(&h_child_qstr), h_inode ? h_inode->i_ino : 0); + /* WARN_ON(1); */ + } + au_debug(0); +#endif + + AuDebugOn(!inode_mark); + hnotify = container_of(inode_mark, struct au_hnotify, hn_mark); + err = au_hnotify(h_dir, hnotify, mask, &h_child_qstr, h_inode); + +out: + return err; +} + +/* isn't it waste to ask every registered 'group'? */ +/* copied from linux/fs/notify/inotify/inotify_fsnotiry.c */ +/* it should be exported to modules */ +static bool au_hfsn_should_send_event(struct fsnotify_group *group, + struct inode *h_inode, + struct fsnotify_mark *inode_mark, + struct fsnotify_mark *vfsmount_mark, + __u32 mask, void *data, int data_type) +{ + mask = (mask & ~FS_EVENT_ON_CHILD); + return inode_mark->mask & mask; +} + +static struct fsnotify_ops au_hfsn_ops = { + .should_send_event = au_hfsn_should_send_event, + .handle_event = au_hfsn_handle_event +}; + +/* ---------------------------------------------------------------------- */ + +static void au_hfsn_fin_br(struct au_branch *br) +{ + if (br->br_hfsn_group) + fsnotify_put_group(br->br_hfsn_group); +} + +static int au_hfsn_init_br(struct au_branch *br, int perm) +{ + br->br_hfsn_group = NULL; + br->br_hfsn_ops = au_hfsn_ops; + return 0; +} + +static int au_hfsn_reset_br(unsigned int udba, struct au_branch *br, int perm) +{ + int err; + + err = 0; + if (udba != AuOpt_UDBA_HNOTIFY + || !au_br_hnotifyable(perm)) { + au_hfsn_fin_br(br); + br->br_hfsn_group = NULL; + goto out; + } + + if (br->br_hfsn_group) + goto out; + + br->br_hfsn_group = fsnotify_alloc_group(&br->br_hfsn_ops); + if (IS_ERR(br->br_hfsn_group)) { + err = PTR_ERR(br->br_hfsn_group); + pr_err("fsnotify_alloc_group() failed, %d\n", err); + br->br_hfsn_group = NULL; + } + +out: + AuTraceErr(err); + return err; +} + +const struct au_hnotify_op au_hnotify_op = { + .ctl = au_hfsn_ctl, + .alloc = au_hfsn_alloc, + .free = au_hfsn_free, + + .reset_br = au_hfsn_reset_br, + .fin_br = au_hfsn_fin_br, + .init_br = au_hfsn_init_br +}; diff --git a/ubuntu/aufs/hfsplus.c b/ubuntu/aufs/hfsplus.c new file mode 100644 index 000000000000..9941f76083c5 --- /dev/null +++ b/ubuntu/aufs/hfsplus.c @@ -0,0 +1,57 @@ +/* + * Copyright (C) 2010-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * special support for filesystems which aqucires an inode mutex + * at final closing a file, eg, hfsplus. + * + * This trick is very simple and stupid, just to open the file before really + * neceeary open to tell hfsplus that this is not the final closing. + * The caller should call au_h_open_pre() after acquiring the inode mutex, + * and au_h_open_post() after releasing it. + */ + +#include "aufs.h" + +struct file *au_h_open_pre(struct dentry *dentry, aufs_bindex_t bindex) +{ + struct file *h_file; + struct dentry *h_dentry; + + h_dentry = au_h_dptr(dentry, bindex); + AuDebugOn(!h_dentry); + AuDebugOn(!h_dentry->d_inode); + IMustLock(h_dentry->d_inode); + + h_file = NULL; + if (au_test_hfsplus(h_dentry->d_sb) + && S_ISREG(h_dentry->d_inode->i_mode)) + h_file = au_h_open(dentry, bindex, + O_RDONLY | O_NOATIME | O_LARGEFILE, + /*file*/NULL); + return h_file; +} + +void au_h_open_post(struct dentry *dentry, aufs_bindex_t bindex, + struct file *h_file) +{ + if (h_file) { + fput(h_file); + au_sbr_put(dentry->d_sb, bindex); + } +} diff --git a/ubuntu/aufs/hnotify.c b/ubuntu/aufs/hnotify.c new file mode 100644 index 000000000000..251588c4c8e5 --- /dev/null +++ b/ubuntu/aufs/hnotify.c @@ -0,0 +1,712 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * abstraction to notify the direct changes on lower directories + */ + +#include "aufs.h" + +int au_hn_alloc(struct au_hinode *hinode, struct inode *inode) +{ + int err; + struct au_hnotify *hn; + + err = -ENOMEM; + hn = au_cache_alloc_hnotify(); + if (hn) { + hn->hn_aufs_inode = inode; + hinode->hi_notify = hn; + err = au_hnotify_op.alloc(hinode); + AuTraceErr(err); + if (unlikely(err)) { + hinode->hi_notify = NULL; + au_cache_free_hnotify(hn); + /* + * The upper dir was removed by udba, but the same named + * dir left. In this case, aufs assignes a new inode + * number and set the monitor again. + * For the lower dir, the old monitnor is still left. + */ + if (err == -EEXIST) + err = 0; + } + } + + AuTraceErr(err); + return err; +} + +void au_hn_free(struct au_hinode *hinode) +{ + struct au_hnotify *hn; + + hn = hinode->hi_notify; + if (hn) { + au_hnotify_op.free(hinode); + au_cache_free_hnotify(hn); + hinode->hi_notify = NULL; + } +} + +/* ---------------------------------------------------------------------- */ + +void au_hn_ctl(struct au_hinode *hinode, int do_set) +{ + if (hinode->hi_notify) + au_hnotify_op.ctl(hinode, do_set); +} + +void au_hn_reset(struct inode *inode, unsigned int flags) +{ + aufs_bindex_t bindex, bend; + struct inode *hi; + struct dentry *iwhdentry; + + bend = au_ibend(inode); + for (bindex = au_ibstart(inode); bindex <= bend; bindex++) { + hi = au_h_iptr(inode, bindex); + if (!hi) + continue; + + /* mutex_lock_nested(&hi->i_mutex, AuLsc_I_CHILD); */ + iwhdentry = au_hi_wh(inode, bindex); + if (iwhdentry) + dget(iwhdentry); + au_igrab(hi); + au_set_h_iptr(inode, bindex, NULL, 0); + au_set_h_iptr(inode, bindex, au_igrab(hi), + flags & ~AuHi_XINO); + iput(hi); + dput(iwhdentry); + /* mutex_unlock(&hi->i_mutex); */ + } +} + +/* ---------------------------------------------------------------------- */ + +static int hn_xino(struct inode *inode, struct inode *h_inode) +{ + int err; + aufs_bindex_t bindex, bend, bfound, bstart; + struct inode *h_i; + + err = 0; + if (unlikely(inode->i_ino == AUFS_ROOT_INO)) { + pr_warning("branch root dir was changed\n"); + goto out; + } + + bfound = -1; + bend = au_ibend(inode); + bstart = au_ibstart(inode); +#if 0 /* reserved for future use */ + if (bindex == bend) { + /* keep this ino in rename case */ + goto out; + } +#endif + for (bindex = bstart; bindex <= bend; bindex++) + if (au_h_iptr(inode, bindex) == h_inode) { + bfound = bindex; + break; + } + if (bfound < 0) + goto out; + + for (bindex = bstart; bindex <= bend; bindex++) { + h_i = au_h_iptr(inode, bindex); + if (!h_i) + continue; + + err = au_xino_write(inode->i_sb, bindex, h_i->i_ino, /*ino*/0); + /* ignore this error */ + /* bad action? */ + } + + /* children inode number will be broken */ + +out: + AuTraceErr(err); + return err; +} + +static int hn_gen_tree(struct dentry *dentry) +{ + int err, i, j, ndentry; + struct au_dcsub_pages dpages; + struct au_dpage *dpage; + struct dentry **dentries; + + err = au_dpages_init(&dpages, GFP_NOFS); + if (unlikely(err)) + goto out; + err = au_dcsub_pages(&dpages, dentry, NULL, NULL); + if (unlikely(err)) + goto out_dpages; + + for (i = 0; i < dpages.ndpage; i++) { + dpage = dpages.dpages + i; + dentries = dpage->dentries; + ndentry = dpage->ndentry; + for (j = 0; j < ndentry; j++) { + struct dentry *d; + + d = dentries[j]; + if (IS_ROOT(d)) + continue; + + au_digen_dec(d); + if (d->d_inode) + /* todo: reset children xino? + cached children only? */ + au_iigen_dec(d->d_inode); + } + } + +out_dpages: + au_dpages_free(&dpages); + +#if 0 + /* discard children */ + dentry_unhash(dentry); + dput(dentry); +#endif +out: + return err; +} + +/* + * return 0 if processed. + */ +static int hn_gen_by_inode(char *name, unsigned int nlen, struct inode *inode, + const unsigned int isdir) +{ + int err; + struct dentry *d; + struct qstr *dname; + + err = 1; + if (unlikely(inode->i_ino == AUFS_ROOT_INO)) { + pr_warning("branch root dir was changed\n"); + err = 0; + goto out; + } + + if (!isdir) { + AuDebugOn(!name); + au_iigen_dec(inode); + spin_lock(&inode->i_lock); + list_for_each_entry(d, &inode->i_dentry, d_alias) { + spin_lock(&d->d_lock); + dname = &d->d_name; + if (dname->len != nlen + && memcmp(dname->name, name, nlen)) { + spin_unlock(&d->d_lock); + continue; + } + err = 0; + au_digen_dec(d); + spin_unlock(&d->d_lock); + break; + } + spin_unlock(&inode->i_lock); + } else { + au_fset_si(au_sbi(inode->i_sb), FAILED_REFRESH_DIR); + d = d_find_alias(inode); + if (!d) { + au_iigen_dec(inode); + goto out; + } + + spin_lock(&d->d_lock); + dname = &d->d_name; + if (dname->len == nlen && !memcmp(dname->name, name, nlen)) { + spin_unlock(&d->d_lock); + err = hn_gen_tree(d); + spin_lock(&d->d_lock); + } + spin_unlock(&d->d_lock); + dput(d); + } + +out: + AuTraceErr(err); + return err; +} + +static int hn_gen_by_name(struct dentry *dentry, const unsigned int isdir) +{ + int err; + struct inode *inode; + + inode = dentry->d_inode; + if (IS_ROOT(dentry) + /* || (inode && inode->i_ino == AUFS_ROOT_INO) */ + ) { + pr_warning("branch root dir was changed\n"); + return 0; + } + + err = 0; + if (!isdir) { + au_digen_dec(dentry); + if (inode) + au_iigen_dec(inode); + } else { + au_fset_si(au_sbi(dentry->d_sb), FAILED_REFRESH_DIR); + if (inode) + err = hn_gen_tree(dentry); + } + + AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* hnotify job flags */ +#define AuHnJob_XINO0 1 +#define AuHnJob_GEN (1 << 1) +#define AuHnJob_DIRENT (1 << 2) +#define AuHnJob_ISDIR (1 << 3) +#define AuHnJob_TRYXINO0 (1 << 4) +#define AuHnJob_MNTPNT (1 << 5) +#define au_ftest_hnjob(flags, name) ((flags) & AuHnJob_##name) +#define au_fset_hnjob(flags, name) \ + do { (flags) |= AuHnJob_##name; } while (0) +#define au_fclr_hnjob(flags, name) \ + do { (flags) &= ~AuHnJob_##name; } while (0) + +enum { + AuHn_CHILD, + AuHn_PARENT, + AuHnLast +}; + +struct au_hnotify_args { + struct inode *h_dir, *dir, *h_child_inode; + u32 mask; + unsigned int flags[AuHnLast]; + unsigned int h_child_nlen; + char h_child_name[]; +}; + +struct hn_job_args { + unsigned int flags; + struct inode *inode, *h_inode, *dir, *h_dir; + struct dentry *dentry; + char *h_name; + int h_nlen; +}; + +static int hn_job(struct hn_job_args *a) +{ + const unsigned int isdir = au_ftest_hnjob(a->flags, ISDIR); + + /* reset xino */ + if (au_ftest_hnjob(a->flags, XINO0) && a->inode) + hn_xino(a->inode, a->h_inode); /* ignore this error */ + + if (au_ftest_hnjob(a->flags, TRYXINO0) + && a->inode + && a->h_inode) { + mutex_lock_nested(&a->h_inode->i_mutex, AuLsc_I_CHILD); + if (!a->h_inode->i_nlink) + hn_xino(a->inode, a->h_inode); /* ignore this error */ + mutex_unlock(&a->h_inode->i_mutex); + } + + /* make the generation obsolete */ + if (au_ftest_hnjob(a->flags, GEN)) { + int err = -1; + if (a->inode) + err = hn_gen_by_inode(a->h_name, a->h_nlen, a->inode, + isdir); + if (err && a->dentry) + hn_gen_by_name(a->dentry, isdir); + /* ignore this error */ + } + + /* make dir entries obsolete */ + if (au_ftest_hnjob(a->flags, DIRENT) && a->inode) { + struct au_vdir *vdir; + + vdir = au_ivdir(a->inode); + if (vdir) + vdir->vd_jiffy = 0; + /* IMustLock(a->inode); */ + /* a->inode->i_version++; */ + } + + /* can do nothing but warn */ + if (au_ftest_hnjob(a->flags, MNTPNT) + && a->dentry + && d_mountpoint(a->dentry)) + pr_warning("mount-point %.*s is removed or renamed\n", + AuDLNPair(a->dentry)); + + return 0; +} + +/* ---------------------------------------------------------------------- */ + +static struct dentry *lookup_wlock_by_name(char *name, unsigned int nlen, + struct inode *dir) +{ + struct dentry *dentry, *d, *parent; + struct qstr *dname; + + parent = d_find_alias(dir); + if (!parent) + return NULL; + + dentry = NULL; + spin_lock(&parent->d_lock); + list_for_each_entry(d, &parent->d_subdirs, d_u.d_child) { + /* AuDbg("%.*s\n", AuDLNPair(d)); */ + spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); + dname = &d->d_name; + if (dname->len != nlen || memcmp(dname->name, name, nlen)) + goto cont_unlock; + if (au_di(d)) + au_digen_dec(d); + else + goto cont_unlock; + if (d->d_count) { + dentry = dget_dlock(d); + spin_unlock(&d->d_lock); + break; + } + + cont_unlock: + spin_unlock(&d->d_lock); + } + spin_unlock(&parent->d_lock); + dput(parent); + + if (dentry) + di_write_lock_child(dentry); + + return dentry; +} + +static struct inode *lookup_wlock_by_ino(struct super_block *sb, + aufs_bindex_t bindex, ino_t h_ino) +{ + struct inode *inode; + ino_t ino; + int err; + + inode = NULL; + err = au_xino_read(sb, bindex, h_ino, &ino); + if (!err && ino) + inode = ilookup(sb, ino); + if (!inode) + goto out; + + if (unlikely(inode->i_ino == AUFS_ROOT_INO)) { + pr_warning("wrong root branch\n"); + iput(inode); + inode = NULL; + goto out; + } + + ii_write_lock_child(inode); + +out: + return inode; +} + +static void au_hn_bh(void *_args) +{ + struct au_hnotify_args *a = _args; + struct super_block *sb; + aufs_bindex_t bindex, bend, bfound; + unsigned char xino, try_iput; + int err; + struct inode *inode; + ino_t h_ino; + struct hn_job_args args; + struct dentry *dentry; + struct au_sbinfo *sbinfo; + + AuDebugOn(!_args); + AuDebugOn(!a->h_dir); + AuDebugOn(!a->dir); + AuDebugOn(!a->mask); + AuDbg("mask 0x%x, i%lu, hi%lu, hci%lu\n", + a->mask, a->dir->i_ino, a->h_dir->i_ino, + a->h_child_inode ? a->h_child_inode->i_ino : 0); + + inode = NULL; + dentry = NULL; + /* + * do not lock a->dir->i_mutex here + * because of d_revalidate() may cause a deadlock. + */ + sb = a->dir->i_sb; + AuDebugOn(!sb); + sbinfo = au_sbi(sb); + AuDebugOn(!sbinfo); + si_write_lock(sb, AuLock_NOPLMW); + + ii_read_lock_parent(a->dir); + bfound = -1; + bend = au_ibend(a->dir); + for (bindex = au_ibstart(a->dir); bindex <= bend; bindex++) + if (au_h_iptr(a->dir, bindex) == a->h_dir) { + bfound = bindex; + break; + } + ii_read_unlock(a->dir); + if (unlikely(bfound < 0)) + goto out; + + xino = !!au_opt_test(au_mntflags(sb), XINO); + h_ino = 0; + if (a->h_child_inode) + h_ino = a->h_child_inode->i_ino; + + if (a->h_child_nlen + && (au_ftest_hnjob(a->flags[AuHn_CHILD], GEN) + || au_ftest_hnjob(a->flags[AuHn_CHILD], MNTPNT))) + dentry = lookup_wlock_by_name(a->h_child_name, a->h_child_nlen, + a->dir); + try_iput = 0; + if (dentry) + inode = dentry->d_inode; + if (xino && !inode && h_ino + && (au_ftest_hnjob(a->flags[AuHn_CHILD], XINO0) + || au_ftest_hnjob(a->flags[AuHn_CHILD], TRYXINO0) + || au_ftest_hnjob(a->flags[AuHn_CHILD], GEN))) { + inode = lookup_wlock_by_ino(sb, bfound, h_ino); + try_iput = 1; + } + + args.flags = a->flags[AuHn_CHILD]; + args.dentry = dentry; + args.inode = inode; + args.h_inode = a->h_child_inode; + args.dir = a->dir; + args.h_dir = a->h_dir; + args.h_name = a->h_child_name; + args.h_nlen = a->h_child_nlen; + err = hn_job(&args); + if (dentry) { + if (au_di(dentry)) + di_write_unlock(dentry); + dput(dentry); + } + if (inode && try_iput) { + ii_write_unlock(inode); + iput(inode); + } + + ii_write_lock_parent(a->dir); + args.flags = a->flags[AuHn_PARENT]; + args.dentry = NULL; + args.inode = a->dir; + args.h_inode = a->h_dir; + args.dir = NULL; + args.h_dir = NULL; + args.h_name = NULL; + args.h_nlen = 0; + err = hn_job(&args); + ii_write_unlock(a->dir); + +out: + iput(a->h_child_inode); + iput(a->h_dir); + iput(a->dir); + si_write_unlock(sb); + au_nwt_done(&sbinfo->si_nowait); + kfree(a); +} + +/* ---------------------------------------------------------------------- */ + +int au_hnotify(struct inode *h_dir, struct au_hnotify *hnotify, u32 mask, + struct qstr *h_child_qstr, struct inode *h_child_inode) +{ + int err, len; + unsigned int flags[AuHnLast], f; + unsigned char isdir, isroot, wh; + struct inode *dir; + struct au_hnotify_args *args; + char *p, *h_child_name; + + err = 0; + AuDebugOn(!hnotify || !hnotify->hn_aufs_inode); + dir = igrab(hnotify->hn_aufs_inode); + if (!dir) + goto out; + + isroot = (dir->i_ino == AUFS_ROOT_INO); + wh = 0; + h_child_name = (void *)h_child_qstr->name; + len = h_child_qstr->len; + if (h_child_name) { + if (len > AUFS_WH_PFX_LEN + && !memcmp(h_child_name, AUFS_WH_PFX, AUFS_WH_PFX_LEN)) { + h_child_name += AUFS_WH_PFX_LEN; + len -= AUFS_WH_PFX_LEN; + wh = 1; + } + } + + isdir = 0; + if (h_child_inode) + isdir = !!S_ISDIR(h_child_inode->i_mode); + flags[AuHn_PARENT] = AuHnJob_ISDIR; + flags[AuHn_CHILD] = 0; + if (isdir) + flags[AuHn_CHILD] = AuHnJob_ISDIR; + au_fset_hnjob(flags[AuHn_PARENT], DIRENT); + au_fset_hnjob(flags[AuHn_CHILD], GEN); + switch (mask & FS_EVENTS_POSS_ON_CHILD) { + case FS_MOVED_FROM: + case FS_MOVED_TO: + au_fset_hnjob(flags[AuHn_CHILD], XINO0); + au_fset_hnjob(flags[AuHn_CHILD], MNTPNT); + /*FALLTHROUGH*/ + case FS_CREATE: + AuDebugOn(!h_child_name || !h_child_inode); + break; + + case FS_DELETE: + /* + * aufs never be able to get this child inode. + * revalidation should be in d_revalidate() + * by checking i_nlink, i_generation or d_unhashed(). + */ + AuDebugOn(!h_child_name); + au_fset_hnjob(flags[AuHn_CHILD], TRYXINO0); + au_fset_hnjob(flags[AuHn_CHILD], MNTPNT); + break; + + default: + AuDebugOn(1); + } + + if (wh) + h_child_inode = NULL; + + err = -ENOMEM; + /* iput() and kfree() will be called in au_hnotify() */ + args = kmalloc(sizeof(*args) + len + 1, GFP_NOFS); + if (unlikely(!args)) { + AuErr1("no memory\n"); + iput(dir); + goto out; + } + args->flags[AuHn_PARENT] = flags[AuHn_PARENT]; + args->flags[AuHn_CHILD] = flags[AuHn_CHILD]; + args->mask = mask; + args->dir = dir; + args->h_dir = igrab(h_dir); + if (h_child_inode) + h_child_inode = igrab(h_child_inode); /* can be NULL */ + args->h_child_inode = h_child_inode; + args->h_child_nlen = len; + if (len) { + p = (void *)args; + p += sizeof(*args); + memcpy(p, h_child_name, len); + p[len] = 0; + } + + f = 0; + if (!dir->i_nlink) + f = AuWkq_NEST; + err = au_wkq_nowait(au_hn_bh, args, dir->i_sb, f); + if (unlikely(err)) { + pr_err("wkq %d\n", err); + iput(args->h_child_inode); + iput(args->h_dir); + iput(args->dir); + kfree(args); + } + +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +int au_hnotify_reset_br(unsigned int udba, struct au_branch *br, int perm) +{ + int err; + + AuDebugOn(!(udba & AuOptMask_UDBA)); + + err = 0; + if (au_hnotify_op.reset_br) + err = au_hnotify_op.reset_br(udba, br, perm); + + return err; +} + +int au_hnotify_init_br(struct au_branch *br, int perm) +{ + int err; + + err = 0; + if (au_hnotify_op.init_br) + err = au_hnotify_op.init_br(br, perm); + + return err; +} + +void au_hnotify_fin_br(struct au_branch *br) +{ + if (au_hnotify_op.fin_br) + au_hnotify_op.fin_br(br); +} + +static void au_hn_destroy_cache(void) +{ + kmem_cache_destroy(au_cachep[AuCache_HNOTIFY]); + au_cachep[AuCache_HNOTIFY] = NULL; +} + +int __init au_hnotify_init(void) +{ + int err; + + err = -ENOMEM; + au_cachep[AuCache_HNOTIFY] = AuCache(au_hnotify); + if (au_cachep[AuCache_HNOTIFY]) { + err = 0; + if (au_hnotify_op.init) + err = au_hnotify_op.init(); + if (unlikely(err)) + au_hn_destroy_cache(); + } + AuTraceErr(err); + return err; +} + +void au_hnotify_fin(void) +{ + if (au_hnotify_op.fin) + au_hnotify_op.fin(); + /* cf. au_cache_fin() */ + if (au_cachep[AuCache_HNOTIFY]) + au_hn_destroy_cache(); +} diff --git a/ubuntu/aufs/i_op.c b/ubuntu/aufs/i_op.c new file mode 100644 index 000000000000..ec50afd99ef7 --- /dev/null +++ b/ubuntu/aufs/i_op.c @@ -0,0 +1,991 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * inode operations (except add/del/rename) + */ + +#include <linux/device_cgroup.h> +#include <linux/fs_stack.h> +#include <linux/namei.h> +#include <linux/security.h> +#include "aufs.h" + +static int h_permission(struct inode *h_inode, int mask, + struct vfsmount *h_mnt, int brperm) +{ + int err; + const unsigned char write_mask = !!(mask & (MAY_WRITE | MAY_APPEND)); + + err = -EACCES; + if ((write_mask && IS_IMMUTABLE(h_inode)) + || ((mask & MAY_EXEC) + && S_ISREG(h_inode->i_mode) + && ((h_mnt->mnt_flags & MNT_NOEXEC) + || !(h_inode->i_mode & S_IXUGO)))) + goto out; + + /* + * - skip the lower fs test in the case of write to ro branch. + * - nfs dir permission write check is optimized, but a policy for + * link/rename requires a real check. + */ + if ((write_mask && !au_br_writable(brperm)) + || (au_test_nfs(h_inode->i_sb) && S_ISDIR(h_inode->i_mode) + && write_mask && !(mask & MAY_READ)) + || !h_inode->i_op->permission) { + /* AuLabel(generic_permission); */ + err = generic_permission(h_inode, mask); + } else { + /* AuLabel(h_inode->permission); */ + err = h_inode->i_op->permission(h_inode, mask); + AuTraceErr(err); + } + + if (!err) + err = devcgroup_inode_permission(h_inode, mask); + if (!err) + err = security_inode_permission(h_inode, mask); + +#if 0 + if (!err) { + /* todo: do we need to call ima_path_check()? */ + struct path h_path = { + .dentry = + .mnt = h_mnt + }; + err = ima_path_check(&h_path, + mask & (MAY_READ | MAY_WRITE | MAY_EXEC), + IMA_COUNT_LEAVE); + } +#endif + +out: + return err; +} + +static int aufs_permission(struct inode *inode, int mask) +{ + int err; + aufs_bindex_t bindex, bend; + const unsigned char isdir = !!S_ISDIR(inode->i_mode), + write_mask = !!(mask & (MAY_WRITE | MAY_APPEND)); + struct inode *h_inode; + struct super_block *sb; + struct au_branch *br; + + /* todo: support rcu-walk? */ + if (mask & MAY_NOT_BLOCK) + return -ECHILD; + + sb = inode->i_sb; + si_read_lock(sb, AuLock_FLUSH); + ii_read_lock_child(inode); +#if 0 + err = au_iigen_test(inode, au_sigen(sb)); + if (unlikely(err)) + goto out; +#endif + + if (!isdir || write_mask) { + err = au_busy_or_stale(); + h_inode = au_h_iptr(inode, au_ibstart(inode)); + if (unlikely(!h_inode + || (h_inode->i_mode & S_IFMT) + != (inode->i_mode & S_IFMT))) + goto out; + + err = 0; + bindex = au_ibstart(inode); + br = au_sbr(sb, bindex); + err = h_permission(h_inode, mask, br->br_mnt, br->br_perm); + if (write_mask + && !err + && !special_file(h_inode->i_mode)) { + /* test whether the upper writable branch exists */ + err = -EROFS; + for (; bindex >= 0; bindex--) + if (!au_br_rdonly(au_sbr(sb, bindex))) { + err = 0; + break; + } + } + goto out; + } + + /* non-write to dir */ + err = 0; + bend = au_ibend(inode); + for (bindex = au_ibstart(inode); !err && bindex <= bend; bindex++) { + h_inode = au_h_iptr(inode, bindex); + if (h_inode) { + err = au_busy_or_stale(); + if (unlikely(!S_ISDIR(h_inode->i_mode))) + break; + + br = au_sbr(sb, bindex); + err = h_permission(h_inode, mask, br->br_mnt, + br->br_perm); + } + } + +out: + ii_read_unlock(inode); + si_read_unlock(sb); + return err; +} + +/* ---------------------------------------------------------------------- */ + +static struct dentry *aufs_lookup(struct inode *dir, struct dentry *dentry, + struct nameidata *nd) +{ + struct dentry *ret, *parent; + struct inode *inode; + struct super_block *sb; + int err, npositive, lc_idx; + + IMustLock(dir); + + sb = dir->i_sb; + err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); + ret = ERR_PTR(err); + if (unlikely(err)) + goto out; + + ret = ERR_PTR(-ENAMETOOLONG); + if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN)) + goto out_si; + err = au_di_init(dentry); + ret = ERR_PTR(err); + if (unlikely(err)) + goto out_si; + + inode = NULL; + npositive = 0; /* suppress a warning */ + parent = dentry->d_parent; /* dir inode is locked */ + di_read_lock_parent(parent, AuLock_IR); + err = au_alive_dir(parent); + if (!err) + err = au_digen_test(parent, au_sigen(sb)); + if (!err) { + npositive = au_lkup_dentry(dentry, au_dbstart(parent), + /*type*/0, nd); + err = npositive; + } + di_read_unlock(parent, AuLock_IR); + ret = ERR_PTR(err); + if (unlikely(err < 0)) + goto out_unlock; + + if (npositive) { + inode = au_new_inode(dentry, /*must_new*/0); + ret = (void *)inode; + } + if (IS_ERR(inode)) { + inode = NULL; + goto out_unlock; + } + + ret = d_splice_alias(inode, dentry); + if (unlikely(IS_ERR(ret) && inode)) { + ii_write_unlock(inode); + lc_idx = AuLcNonDir_IIINFO; + if (S_ISLNK(inode->i_mode)) + lc_idx = AuLcSymlink_IIINFO; + else if (S_ISDIR(inode->i_mode)) + lc_idx = AuLcDir_IIINFO; + au_rw_class(&au_ii(inode)->ii_rwsem, au_lc_key + lc_idx); + iput(inode); + } + +out_unlock: + di_write_unlock(dentry); + if (unlikely(IS_ERR(ret) && inode)) { + lc_idx = AuLcNonDir_DIINFO; + if (S_ISLNK(inode->i_mode)) + lc_idx = AuLcSymlink_DIINFO; + else if (S_ISDIR(inode->i_mode)) + lc_idx = AuLcDir_DIINFO; + au_rw_class(&au_di(dentry)->di_rwsem, au_lc_key + lc_idx); + } +out_si: + si_read_unlock(sb); +out: + return ret; +} + +/* ---------------------------------------------------------------------- */ + +static int au_wr_dir_cpup(struct dentry *dentry, struct dentry *parent, + const unsigned char add_entry, aufs_bindex_t bcpup, + aufs_bindex_t bstart) +{ + int err; + struct dentry *h_parent; + struct inode *h_dir; + + if (add_entry) + IMustLock(parent->d_inode); + else + di_write_lock_parent(parent); + + err = 0; + if (!au_h_dptr(parent, bcpup)) { + if (bstart < bcpup) + err = au_cpdown_dirs(dentry, bcpup); + else + err = au_cpup_dirs(dentry, bcpup); + } + if (!err && add_entry) { + h_parent = au_h_dptr(parent, bcpup); + h_dir = h_parent->d_inode; + mutex_lock_nested(&h_dir->i_mutex, AuLsc_I_PARENT); + err = au_lkup_neg(dentry, bcpup); + /* todo: no unlock here */ + mutex_unlock(&h_dir->i_mutex); + + AuDbg("bcpup %d\n", bcpup); + if (!err) { + if (!dentry->d_inode) + au_set_h_dptr(dentry, bstart, NULL); + au_update_dbrange(dentry, /*do_put_zero*/0); + } + } + + if (!add_entry) + di_write_unlock(parent); + if (!err) + err = bcpup; /* success */ + + AuTraceErr(err); + return err; +} + +/* + * decide the branch and the parent dir where we will create a new entry. + * returns new bindex or an error. + * copyup the parent dir if needed. + */ +int au_wr_dir(struct dentry *dentry, struct dentry *src_dentry, + struct au_wr_dir_args *args) +{ + int err; + aufs_bindex_t bcpup, bstart, src_bstart; + const unsigned char add_entry = !!au_ftest_wrdir(args->flags, + ADD_ENTRY); + struct super_block *sb; + struct dentry *parent; + struct au_sbinfo *sbinfo; + + sb = dentry->d_sb; + sbinfo = au_sbi(sb); + parent = dget_parent(dentry); + bstart = au_dbstart(dentry); + bcpup = bstart; + if (args->force_btgt < 0) { + if (src_dentry) { + src_bstart = au_dbstart(src_dentry); + if (src_bstart < bstart) + bcpup = src_bstart; + } else if (add_entry) { + err = AuWbrCreate(sbinfo, dentry, + au_ftest_wrdir(args->flags, ISDIR)); + bcpup = err; + } + + if (bcpup < 0 || au_test_ro(sb, bcpup, dentry->d_inode)) { + if (add_entry) + err = AuWbrCopyup(sbinfo, dentry); + else { + if (!IS_ROOT(dentry)) { + di_read_lock_parent(parent, !AuLock_IR); + err = AuWbrCopyup(sbinfo, dentry); + di_read_unlock(parent, !AuLock_IR); + } else + err = AuWbrCopyup(sbinfo, dentry); + } + bcpup = err; + if (unlikely(err < 0)) + goto out; + } + } else { + bcpup = args->force_btgt; + AuDebugOn(au_test_ro(sb, bcpup, dentry->d_inode)); + } + + AuDbg("bstart %d, bcpup %d\n", bstart, bcpup); + err = bcpup; + if (bcpup == bstart) + goto out; /* success */ + + /* copyup the new parent into the branch we process */ + err = au_wr_dir_cpup(dentry, parent, add_entry, bcpup, bstart); + if (err >= 0) { + if (!dentry->d_inode) { + au_set_h_dptr(dentry, bstart, NULL); + au_set_dbstart(dentry, bcpup); + au_set_dbend(dentry, bcpup); + } + AuDebugOn(add_entry && !au_h_dptr(dentry, bcpup)); + } + +out: + dput(parent); + return err; +} + +/* ---------------------------------------------------------------------- */ + +struct dentry *au_pinned_h_parent(struct au_pin *pin) +{ + if (pin && pin->parent) + return au_h_dptr(pin->parent, pin->bindex); + return NULL; +} + +void au_unpin(struct au_pin *p) +{ + if (p->h_mnt && au_ftest_pin(p->flags, MNT_WRITE)) + mnt_drop_write(p->h_mnt); + if (!p->hdir) + return; + + au_hn_imtx_unlock(p->hdir); + if (!au_ftest_pin(p->flags, DI_LOCKED)) + di_read_unlock(p->parent, AuLock_IR); + iput(p->hdir->hi_inode); + dput(p->parent); + p->parent = NULL; + p->hdir = NULL; + p->h_mnt = NULL; +} + +int au_do_pin(struct au_pin *p) +{ + int err; + struct super_block *sb; + struct dentry *h_dentry, *h_parent; + struct au_branch *br; + struct inode *h_dir; + + err = 0; + sb = p->dentry->d_sb; + br = au_sbr(sb, p->bindex); + if (IS_ROOT(p->dentry)) { + if (au_ftest_pin(p->flags, MNT_WRITE)) { + p->h_mnt = br->br_mnt; + err = mnt_want_write(p->h_mnt); + if (unlikely(err)) { + au_fclr_pin(p->flags, MNT_WRITE); + goto out_err; + } + } + goto out; + } + + h_dentry = NULL; + if (p->bindex <= au_dbend(p->dentry)) + h_dentry = au_h_dptr(p->dentry, p->bindex); + + p->parent = dget_parent(p->dentry); + if (!au_ftest_pin(p->flags, DI_LOCKED)) + di_read_lock(p->parent, AuLock_IR, p->lsc_di); + + h_dir = NULL; + h_parent = au_h_dptr(p->parent, p->bindex); + p->hdir = au_hi(p->parent->d_inode, p->bindex); + if (p->hdir) + h_dir = p->hdir->hi_inode; + + /* + * udba case, or + * if DI_LOCKED is not set, then p->parent may be different + * and h_parent can be NULL. + */ + if (unlikely(!p->hdir || !h_dir || !h_parent)) { + err = -EBUSY; + if (!au_ftest_pin(p->flags, DI_LOCKED)) + di_read_unlock(p->parent, AuLock_IR); + dput(p->parent); + p->parent = NULL; + goto out_err; + } + + au_igrab(h_dir); + au_hn_imtx_lock_nested(p->hdir, p->lsc_hi); + + if (unlikely(p->hdir->hi_inode != h_parent->d_inode)) { + err = -EBUSY; + goto out_unpin; + } + if (h_dentry) { + err = au_h_verify(h_dentry, p->udba, h_dir, h_parent, br); + if (unlikely(err)) { + au_fclr_pin(p->flags, MNT_WRITE); + goto out_unpin; + } + } + + if (au_ftest_pin(p->flags, MNT_WRITE)) { + p->h_mnt = br->br_mnt; + err = mnt_want_write(p->h_mnt); + if (unlikely(err)) { + au_fclr_pin(p->flags, MNT_WRITE); + goto out_unpin; + } + } + goto out; /* success */ + +out_unpin: + au_unpin(p); +out_err: + pr_err("err %d\n", err); + err = au_busy_or_stale(); +out: + return err; +} + +void au_pin_init(struct au_pin *p, struct dentry *dentry, + aufs_bindex_t bindex, int lsc_di, int lsc_hi, + unsigned int udba, unsigned char flags) +{ + p->dentry = dentry; + p->udba = udba; + p->lsc_di = lsc_di; + p->lsc_hi = lsc_hi; + p->flags = flags; + p->bindex = bindex; + + p->parent = NULL; + p->hdir = NULL; + p->h_mnt = NULL; +} + +int au_pin(struct au_pin *pin, struct dentry *dentry, aufs_bindex_t bindex, + unsigned int udba, unsigned char flags) +{ + au_pin_init(pin, dentry, bindex, AuLsc_DI_PARENT, AuLsc_I_PARENT2, + udba, flags); + return au_do_pin(pin); +} + +/* ---------------------------------------------------------------------- */ + +/* + * ->setattr() and ->getattr() are called in various cases. + * chmod, stat: dentry is revalidated. + * fchmod, fstat: file and dentry are not revalidated, additionally they may be + * unhashed. + * for ->setattr(), ia->ia_file is passed from ftruncate only. + */ +/* todo: consolidate with do_refresh() and simple_reval_dpath() */ +static int au_reval_for_attr(struct dentry *dentry, unsigned int sigen) +{ + int err; + struct inode *inode; + struct dentry *parent; + + err = 0; + inode = dentry->d_inode; + if (au_digen_test(dentry, sigen)) { + parent = dget_parent(dentry); + di_read_lock_parent(parent, AuLock_IR); + err = au_refresh_dentry(dentry, parent); + di_read_unlock(parent, AuLock_IR); + dput(parent); + } + + AuTraceErr(err); + return err; +} + +#define AuIcpup_DID_CPUP 1 +#define au_ftest_icpup(flags, name) ((flags) & AuIcpup_##name) +#define au_fset_icpup(flags, name) \ + do { (flags) |= AuIcpup_##name; } while (0) +#define au_fclr_icpup(flags, name) \ + do { (flags) &= ~AuIcpup_##name; } while (0) + +struct au_icpup_args { + unsigned char flags; + unsigned char pin_flags; + aufs_bindex_t btgt; + unsigned int udba; + struct au_pin pin; + struct path h_path; + struct inode *h_inode; +}; + +static int au_pin_and_icpup(struct dentry *dentry, struct iattr *ia, + struct au_icpup_args *a) +{ + int err; + loff_t sz; + aufs_bindex_t bstart, ibstart; + struct dentry *hi_wh, *parent; + struct inode *inode; + struct file *h_file; + struct au_wr_dir_args wr_dir_args = { + .force_btgt = -1, + .flags = 0 + }; + + bstart = au_dbstart(dentry); + inode = dentry->d_inode; + if (S_ISDIR(inode->i_mode)) + au_fset_wrdir(wr_dir_args.flags, ISDIR); + /* plink or hi_wh() case */ + ibstart = au_ibstart(inode); + if (bstart != ibstart && !au_test_ro(inode->i_sb, ibstart, inode)) + wr_dir_args.force_btgt = ibstart; + err = au_wr_dir(dentry, /*src_dentry*/NULL, &wr_dir_args); + if (unlikely(err < 0)) + goto out; + a->btgt = err; + if (err != bstart) + au_fset_icpup(a->flags, DID_CPUP); + + err = 0; + a->pin_flags = AuPin_MNT_WRITE; + parent = NULL; + if (!IS_ROOT(dentry)) { + au_fset_pin(a->pin_flags, DI_LOCKED); + parent = dget_parent(dentry); + di_write_lock_parent(parent); + } + + err = au_pin(&a->pin, dentry, a->btgt, a->udba, a->pin_flags); + if (unlikely(err)) + goto out_parent; + + a->h_path.dentry = au_h_dptr(dentry, bstart); + a->h_inode = a->h_path.dentry->d_inode; + mutex_lock_nested(&a->h_inode->i_mutex, AuLsc_I_CHILD); + sz = -1; + if ((ia->ia_valid & ATTR_SIZE) && ia->ia_size < i_size_read(a->h_inode)) + sz = ia->ia_size; + + h_file = NULL; + hi_wh = NULL; + if (au_ftest_icpup(a->flags, DID_CPUP) && d_unlinked(dentry)) { + hi_wh = au_hi_wh(inode, a->btgt); + if (!hi_wh) { + err = au_sio_cpup_wh(dentry, a->btgt, sz, /*file*/NULL); + if (unlikely(err)) + goto out_unlock; + hi_wh = au_hi_wh(inode, a->btgt); + /* todo: revalidate hi_wh? */ + } + } + + if (parent) { + au_pin_set_parent_lflag(&a->pin, /*lflag*/0); + di_downgrade_lock(parent, AuLock_IR); + dput(parent); + parent = NULL; + } + if (!au_ftest_icpup(a->flags, DID_CPUP)) + goto out; /* success */ + + if (!d_unhashed(dentry)) { + h_file = au_h_open_pre(dentry, bstart); + if (IS_ERR(h_file)) { + err = PTR_ERR(h_file); + h_file = NULL; + } else + err = au_sio_cpup_simple(dentry, a->btgt, sz, + AuCpup_DTIME); + if (!err) + a->h_path.dentry = au_h_dptr(dentry, a->btgt); + } else if (!hi_wh) + a->h_path.dentry = au_h_dptr(dentry, a->btgt); + else + a->h_path.dentry = hi_wh; /* do not dget here */ + +out_unlock: + mutex_unlock(&a->h_inode->i_mutex); + au_h_open_post(dentry, bstart, h_file); + a->h_inode = a->h_path.dentry->d_inode; + if (!err) { + mutex_lock_nested(&a->h_inode->i_mutex, AuLsc_I_CHILD); + goto out; /* success */ + } + + au_unpin(&a->pin); +out_parent: + if (parent) { + di_write_unlock(parent); + dput(parent); + } +out: + return err; +} + +static int aufs_setattr(struct dentry *dentry, struct iattr *ia) +{ + int err; + struct inode *inode; + struct super_block *sb; + struct file *file; + struct au_icpup_args *a; + + inode = dentry->d_inode; + IMustLock(inode); + + err = -ENOMEM; + a = kzalloc(sizeof(*a), GFP_NOFS); + if (unlikely(!a)) + goto out; + + if (ia->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) + ia->ia_valid &= ~ATTR_MODE; + + file = NULL; + sb = dentry->d_sb; + err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); + if (unlikely(err)) + goto out_kfree; + + if (ia->ia_valid & ATTR_FILE) { + /* currently ftruncate(2) only */ + AuDebugOn(!S_ISREG(inode->i_mode)); + file = ia->ia_file; + err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1); + if (unlikely(err)) + goto out_si; + ia->ia_file = au_hf_top(file); + a->udba = AuOpt_UDBA_NONE; + } else { + /* fchmod() doesn't pass ia_file */ + a->udba = au_opt_udba(sb); + di_write_lock_child(dentry); + /* no d_unlinked(), to set UDBA_NONE for root */ + if (d_unhashed(dentry)) + a->udba = AuOpt_UDBA_NONE; + if (a->udba != AuOpt_UDBA_NONE) { + AuDebugOn(IS_ROOT(dentry)); + err = au_reval_for_attr(dentry, au_sigen(sb)); + if (unlikely(err)) + goto out_dentry; + } + } + + err = au_pin_and_icpup(dentry, ia, a); + if (unlikely(err < 0)) + goto out_dentry; + if (au_ftest_icpup(a->flags, DID_CPUP)) { + ia->ia_file = NULL; + ia->ia_valid &= ~ATTR_FILE; + } + + a->h_path.mnt = au_sbr_mnt(sb, a->btgt); + if ((ia->ia_valid & (ATTR_MODE | ATTR_CTIME)) + == (ATTR_MODE | ATTR_CTIME)) { + err = security_path_chmod(&a->h_path, ia->ia_mode); + if (unlikely(err)) + goto out_unlock; + } else if ((ia->ia_valid & (ATTR_UID | ATTR_GID)) + && (ia->ia_valid & ATTR_CTIME)) { + err = security_path_chown(&a->h_path, ia->ia_uid, ia->ia_gid); + if (unlikely(err)) + goto out_unlock; + } + + if (ia->ia_valid & ATTR_SIZE) { + struct file *f; + + if (ia->ia_size < i_size_read(inode)) + /* unmap only */ + truncate_setsize(inode, ia->ia_size); + + f = NULL; + if (ia->ia_valid & ATTR_FILE) + f = ia->ia_file; + mutex_unlock(&a->h_inode->i_mutex); + err = vfsub_trunc(&a->h_path, ia->ia_size, ia->ia_valid, f); + mutex_lock_nested(&a->h_inode->i_mutex, AuLsc_I_CHILD); + } else + err = vfsub_notify_change(&a->h_path, ia); + if (!err) + au_cpup_attr_changeable(inode); + +out_unlock: + mutex_unlock(&a->h_inode->i_mutex); + au_unpin(&a->pin); + if (unlikely(err)) + au_update_dbstart(dentry); +out_dentry: + di_write_unlock(dentry); + if (file) { + fi_write_unlock(file); + ia->ia_file = file; + ia->ia_valid |= ATTR_FILE; + } +out_si: + si_read_unlock(sb); +out_kfree: + kfree(a); +out: + AuTraceErr(err); + return err; +} + +static void au_refresh_iattr(struct inode *inode, struct kstat *st, + unsigned int nlink) +{ + unsigned int n; + + inode->i_mode = st->mode; + inode->i_uid = st->uid; + inode->i_gid = st->gid; + inode->i_atime = st->atime; + inode->i_mtime = st->mtime; + inode->i_ctime = st->ctime; + + au_cpup_attr_nlink(inode, /*force*/0); + if (S_ISDIR(inode->i_mode)) { + n = inode->i_nlink; + n -= nlink; + n += st->nlink; + set_nlink(inode, n); + } + + spin_lock(&inode->i_lock); + inode->i_blocks = st->blocks; + i_size_write(inode, st->size); + spin_unlock(&inode->i_lock); +} + +static int aufs_getattr(struct vfsmount *mnt __maybe_unused, + struct dentry *dentry, struct kstat *st) +{ + int err; + unsigned int mnt_flags; + aufs_bindex_t bindex; + unsigned char udba_none, positive; + struct super_block *sb, *h_sb; + struct inode *inode; + struct vfsmount *h_mnt; + struct dentry *h_dentry; + + sb = dentry->d_sb; + inode = dentry->d_inode; + err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM); + if (unlikely(err)) + goto out; + mnt_flags = au_mntflags(sb); + udba_none = !!au_opt_test(mnt_flags, UDBA_NONE); + + /* support fstat(2) */ + if (!d_unlinked(dentry) && !udba_none) { + unsigned int sigen = au_sigen(sb); + err = au_digen_test(dentry, sigen); + if (!err) { + di_read_lock_child(dentry, AuLock_IR); + err = au_dbrange_test(dentry); + if (unlikely(err)) + goto out_unlock; + } else { + AuDebugOn(IS_ROOT(dentry)); + di_write_lock_child(dentry); + err = au_dbrange_test(dentry); + if (!err) + err = au_reval_for_attr(dentry, sigen); + di_downgrade_lock(dentry, AuLock_IR); + if (unlikely(err)) + goto out_unlock; + } + } else + di_read_lock_child(dentry, AuLock_IR); + + bindex = au_ibstart(inode); + h_mnt = au_sbr_mnt(sb, bindex); + h_sb = h_mnt->mnt_sb; + if (!au_test_fs_bad_iattr(h_sb) && udba_none) + goto out_fill; /* success */ + + h_dentry = NULL; + if (au_dbstart(dentry) == bindex) + h_dentry = dget(au_h_dptr(dentry, bindex)); + else if (au_opt_test(mnt_flags, PLINK) && au_plink_test(inode)) { + h_dentry = au_plink_lkup(inode, bindex); + if (IS_ERR(h_dentry)) + goto out_fill; /* pretending success */ + } + /* illegally overlapped or something */ + if (unlikely(!h_dentry)) + goto out_fill; /* pretending success */ + + positive = !!h_dentry->d_inode; + if (positive) + err = vfs_getattr(h_mnt, h_dentry, st); + dput(h_dentry); + if (!err) { + if (positive) + au_refresh_iattr(inode, st, h_dentry->d_inode->i_nlink); + goto out_fill; /* success */ + } + AuTraceErr(err); + goto out_unlock; + +out_fill: + generic_fillattr(inode, st); +out_unlock: + di_read_unlock(dentry, AuLock_IR); + si_read_unlock(sb); +out: + AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int h_readlink(struct dentry *dentry, int bindex, char __user *buf, + int bufsiz) +{ + int err; + struct super_block *sb; + struct dentry *h_dentry; + + err = -EINVAL; + h_dentry = au_h_dptr(dentry, bindex); + if (unlikely(!h_dentry->d_inode->i_op->readlink)) + goto out; + + err = security_inode_readlink(h_dentry); + if (unlikely(err)) + goto out; + + sb = dentry->d_sb; + if (!au_test_ro(sb, bindex, dentry->d_inode)) { + vfsub_touch_atime(au_sbr_mnt(sb, bindex), h_dentry); + fsstack_copy_attr_atime(dentry->d_inode, h_dentry->d_inode); + } + err = h_dentry->d_inode->i_op->readlink(h_dentry, buf, bufsiz); + +out: + return err; +} + +static int aufs_readlink(struct dentry *dentry, char __user *buf, int bufsiz) +{ + int err; + + err = aufs_read_lock(dentry, AuLock_IR | AuLock_GEN); + if (unlikely(err)) + goto out; + err = au_d_hashed_positive(dentry); + if (!err) + err = h_readlink(dentry, au_dbstart(dentry), buf, bufsiz); + aufs_read_unlock(dentry, AuLock_IR); + +out: + return err; +} + +static void *aufs_follow_link(struct dentry *dentry, struct nameidata *nd) +{ + int err; + mm_segment_t old_fs; + union { + char *k; + char __user *u; + } buf; + + err = -ENOMEM; + buf.k = __getname_gfp(GFP_NOFS); + if (unlikely(!buf.k)) + goto out; + + err = aufs_read_lock(dentry, AuLock_IR | AuLock_GEN); + if (unlikely(err)) + goto out_name; + + err = au_d_hashed_positive(dentry); + if (!err) { + old_fs = get_fs(); + set_fs(KERNEL_DS); + err = h_readlink(dentry, au_dbstart(dentry), buf.u, PATH_MAX); + set_fs(old_fs); + } + aufs_read_unlock(dentry, AuLock_IR); + + if (err >= 0) { + buf.k[err] = 0; + /* will be freed by put_link */ + nd_set_link(nd, buf.k); + return NULL; /* success */ + } + +out_name: + __putname(buf.k); +out: + path_put(&nd->path); + AuTraceErr(err); + return ERR_PTR(err); +} + +static void aufs_put_link(struct dentry *dentry __maybe_unused, + struct nameidata *nd, void *cookie __maybe_unused) +{ + __putname(nd_get_link(nd)); +} + +/* ---------------------------------------------------------------------- */ + +static void aufs_truncate_range(struct inode *inode __maybe_unused, + loff_t start __maybe_unused, + loff_t end __maybe_unused) +{ + AuUnsupport(); +} + +/* ---------------------------------------------------------------------- */ + +struct inode_operations aufs_symlink_iop = { + .permission = aufs_permission, + .setattr = aufs_setattr, + .getattr = aufs_getattr, + .readlink = aufs_readlink, + .follow_link = aufs_follow_link, + .put_link = aufs_put_link +}; + +struct inode_operations aufs_dir_iop = { + .create = aufs_create, + .lookup = aufs_lookup, + .link = aufs_link, + .unlink = aufs_unlink, + .symlink = aufs_symlink, + .mkdir = aufs_mkdir, + .rmdir = aufs_rmdir, + .mknod = aufs_mknod, + .rename = aufs_rename, + + .permission = aufs_permission, + .setattr = aufs_setattr, + .getattr = aufs_getattr +}; + +struct inode_operations aufs_iop = { + .permission = aufs_permission, + .setattr = aufs_setattr, + .getattr = aufs_getattr, + .truncate_range = aufs_truncate_range +}; diff --git a/ubuntu/aufs/i_op_add.c b/ubuntu/aufs/i_op_add.c new file mode 100644 index 000000000000..c5255c6a7b9d --- /dev/null +++ b/ubuntu/aufs/i_op_add.c @@ -0,0 +1,711 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * inode operations (add entry) + */ + +#include "aufs.h" + +/* + * final procedure of adding a new entry, except link(2). + * remove whiteout, instantiate, copyup the parent dir's times and size + * and update version. + * if it failed, re-create the removed whiteout. + */ +static int epilog(struct inode *dir, aufs_bindex_t bindex, + struct dentry *wh_dentry, struct dentry *dentry) +{ + int err, rerr; + aufs_bindex_t bwh; + struct path h_path; + struct inode *inode, *h_dir; + struct dentry *wh; + + bwh = -1; + if (wh_dentry) { + h_dir = wh_dentry->d_parent->d_inode; /* dir inode is locked */ + IMustLock(h_dir); + AuDebugOn(au_h_iptr(dir, bindex) != h_dir); + bwh = au_dbwh(dentry); + h_path.dentry = wh_dentry; + h_path.mnt = au_sbr_mnt(dir->i_sb, bindex); + err = au_wh_unlink_dentry(au_h_iptr(dir, bindex), &h_path, + dentry); + if (unlikely(err)) + goto out; + } + + inode = au_new_inode(dentry, /*must_new*/1); + if (!IS_ERR(inode)) { + d_instantiate(dentry, inode); + dir = dentry->d_parent->d_inode; /* dir inode is locked */ + IMustLock(dir); + if (au_ibstart(dir) == au_dbstart(dentry)) + au_cpup_attr_timesizes(dir); + dir->i_version++; + return 0; /* success */ + } + + err = PTR_ERR(inode); + if (!wh_dentry) + goto out; + + /* revert */ + /* dir inode is locked */ + wh = au_wh_create(dentry, bwh, wh_dentry->d_parent); + rerr = PTR_ERR(wh); + if (IS_ERR(wh)) { + AuIOErr("%.*s reverting whiteout failed(%d, %d)\n", + AuDLNPair(dentry), err, rerr); + err = -EIO; + } else + dput(wh); + +out: + return err; +} + +static int au_d_may_add(struct dentry *dentry) +{ + int err; + + err = 0; + if (unlikely(d_unhashed(dentry))) + err = -ENOENT; + if (unlikely(dentry->d_inode)) + err = -EEXIST; + return err; +} + +/* + * simple tests for the adding inode operations. + * following the checks in vfs, plus the parent-child relationship. + */ +int au_may_add(struct dentry *dentry, aufs_bindex_t bindex, + struct dentry *h_parent, int isdir) +{ + int err; + umode_t h_mode; + struct dentry *h_dentry; + struct inode *h_inode; + + err = -ENAMETOOLONG; + if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN)) + goto out; + + h_dentry = au_h_dptr(dentry, bindex); + h_inode = h_dentry->d_inode; + if (!dentry->d_inode) { + err = -EEXIST; + if (unlikely(h_inode)) + goto out; + } else { + /* rename(2) case */ + err = -EIO; + if (unlikely(!h_inode || !h_inode->i_nlink)) + goto out; + + h_mode = h_inode->i_mode; + if (!isdir) { + err = -EISDIR; + if (unlikely(S_ISDIR(h_mode))) + goto out; + } else if (unlikely(!S_ISDIR(h_mode))) { + err = -ENOTDIR; + goto out; + } + } + + err = 0; + /* expected parent dir is locked */ + if (unlikely(h_parent != h_dentry->d_parent)) + err = -EIO; + +out: + AuTraceErr(err); + return err; +} + +/* + * initial procedure of adding a new entry. + * prepare writable branch and the parent dir, lock it, + * and lookup whiteout for the new entry. + */ +static struct dentry* +lock_hdir_lkup_wh(struct dentry *dentry, struct au_dtime *dt, + struct dentry *src_dentry, struct au_pin *pin, + struct au_wr_dir_args *wr_dir_args) +{ + struct dentry *wh_dentry, *h_parent; + struct super_block *sb; + struct au_branch *br; + int err; + unsigned int udba; + aufs_bindex_t bcpup; + + AuDbg("%.*s\n", AuDLNPair(dentry)); + + err = au_wr_dir(dentry, src_dentry, wr_dir_args); + bcpup = err; + wh_dentry = ERR_PTR(err); + if (unlikely(err < 0)) + goto out; + + sb = dentry->d_sb; + udba = au_opt_udba(sb); + err = au_pin(pin, dentry, bcpup, udba, + AuPin_DI_LOCKED | AuPin_MNT_WRITE); + wh_dentry = ERR_PTR(err); + if (unlikely(err)) + goto out; + + h_parent = au_pinned_h_parent(pin); + if (udba != AuOpt_UDBA_NONE + && au_dbstart(dentry) == bcpup) + err = au_may_add(dentry, bcpup, h_parent, + au_ftest_wrdir(wr_dir_args->flags, ISDIR)); + else if (unlikely(dentry->d_name.len > AUFS_MAX_NAMELEN)) + err = -ENAMETOOLONG; + wh_dentry = ERR_PTR(err); + if (unlikely(err)) + goto out_unpin; + + br = au_sbr(sb, bcpup); + if (dt) { + struct path tmp = { + .dentry = h_parent, + .mnt = br->br_mnt + }; + au_dtime_store(dt, au_pinned_parent(pin), &tmp); + } + + wh_dentry = NULL; + if (bcpup != au_dbwh(dentry)) + goto out; /* success */ + + wh_dentry = au_wh_lkup(h_parent, &dentry->d_name, br); + +out_unpin: + if (IS_ERR(wh_dentry)) + au_unpin(pin); +out: + return wh_dentry; +} + +/* ---------------------------------------------------------------------- */ + +enum { Mknod, Symlink, Creat }; +struct simple_arg { + int type; + union { + struct { + int mode; + struct nameidata *nd; + } c; + struct { + const char *symname; + } s; + struct { + int mode; + dev_t dev; + } m; + } u; +}; + +static int add_simple(struct inode *dir, struct dentry *dentry, + struct simple_arg *arg) +{ + int err; + aufs_bindex_t bstart; + unsigned char created; + struct au_dtime dt; + struct au_pin pin; + struct path h_path; + struct dentry *wh_dentry, *parent; + struct inode *h_dir; + struct au_wr_dir_args wr_dir_args = { + .force_btgt = -1, + .flags = AuWrDir_ADD_ENTRY + }; + + AuDbg("%.*s\n", AuDLNPair(dentry)); + IMustLock(dir); + + parent = dentry->d_parent; /* dir inode is locked */ + err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN); + if (unlikely(err)) + goto out; + err = au_d_may_add(dentry); + if (unlikely(err)) + goto out_unlock; + di_write_lock_parent(parent); + wh_dentry = lock_hdir_lkup_wh(dentry, &dt, /*src_dentry*/NULL, &pin, + &wr_dir_args); + err = PTR_ERR(wh_dentry); + if (IS_ERR(wh_dentry)) + goto out_parent; + + bstart = au_dbstart(dentry); + h_path.dentry = au_h_dptr(dentry, bstart); + h_path.mnt = au_sbr_mnt(dentry->d_sb, bstart); + h_dir = au_pinned_h_dir(&pin); + switch (arg->type) { + case Creat: + err = vfsub_create(h_dir, &h_path, arg->u.c.mode); + break; + case Symlink: + err = vfsub_symlink(h_dir, &h_path, arg->u.s.symname); + break; + case Mknod: + err = vfsub_mknod(h_dir, &h_path, arg->u.m.mode, arg->u.m.dev); + break; + default: + BUG(); + } + created = !err; + if (!err) + err = epilog(dir, bstart, wh_dentry, dentry); + + /* revert */ + if (unlikely(created && err && h_path.dentry->d_inode)) { + int rerr; + rerr = vfsub_unlink(h_dir, &h_path, /*force*/0); + if (rerr) { + AuIOErr("%.*s revert failure(%d, %d)\n", + AuDLNPair(dentry), err, rerr); + err = -EIO; + } + au_dtime_revert(&dt); + } + + au_unpin(&pin); + dput(wh_dentry); + +out_parent: + di_write_unlock(parent); +out_unlock: + if (unlikely(err)) { + au_update_dbstart(dentry); + d_drop(dentry); + } + aufs_read_unlock(dentry, AuLock_DW); +out: + return err; +} + +int aufs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev) +{ + struct simple_arg arg = { + .type = Mknod, + .u.m = { + .mode = mode, + .dev = dev + } + }; + return add_simple(dir, dentry, &arg); +} + +int aufs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) +{ + struct simple_arg arg = { + .type = Symlink, + .u.s.symname = symname + }; + return add_simple(dir, dentry, &arg); +} + +int aufs_create(struct inode *dir, struct dentry *dentry, int mode, + struct nameidata *nd) +{ + struct simple_arg arg = { + .type = Creat, + .u.c = { + .mode = mode, + .nd = nd + } + }; + return add_simple(dir, dentry, &arg); +} + +/* ---------------------------------------------------------------------- */ + +struct au_link_args { + aufs_bindex_t bdst, bsrc; + struct au_pin pin; + struct path h_path; + struct dentry *src_parent, *parent; +}; + +static int au_cpup_before_link(struct dentry *src_dentry, + struct au_link_args *a) +{ + int err; + struct dentry *h_src_dentry; + struct mutex *h_mtx; + struct file *h_file; + + di_read_lock_parent(a->src_parent, AuLock_IR); + err = au_test_and_cpup_dirs(src_dentry, a->bdst); + if (unlikely(err)) + goto out; + + h_src_dentry = au_h_dptr(src_dentry, a->bsrc); + h_mtx = &h_src_dentry->d_inode->i_mutex; + err = au_pin(&a->pin, src_dentry, a->bdst, + au_opt_udba(src_dentry->d_sb), + AuPin_DI_LOCKED | AuPin_MNT_WRITE); + if (unlikely(err)) + goto out; + mutex_lock_nested(h_mtx, AuLsc_I_CHILD); + h_file = au_h_open_pre(src_dentry, a->bsrc); + if (IS_ERR(h_file)) { + err = PTR_ERR(h_file); + h_file = NULL; + } else + err = au_sio_cpup_simple(src_dentry, a->bdst, -1, + AuCpup_DTIME /* | AuCpup_KEEPLINO */); + mutex_unlock(h_mtx); + au_h_open_post(src_dentry, a->bsrc, h_file); + au_unpin(&a->pin); + +out: + di_read_unlock(a->src_parent, AuLock_IR); + return err; +} + +static int au_cpup_or_link(struct dentry *src_dentry, struct au_link_args *a) +{ + int err; + unsigned char plink; + struct inode *h_inode, *inode; + struct dentry *h_src_dentry; + struct super_block *sb; + struct file *h_file; + + plink = 0; + h_inode = NULL; + sb = src_dentry->d_sb; + inode = src_dentry->d_inode; + if (au_ibstart(inode) <= a->bdst) + h_inode = au_h_iptr(inode, a->bdst); + if (!h_inode || !h_inode->i_nlink) { + /* copyup src_dentry as the name of dentry. */ + au_set_dbstart(src_dentry, a->bdst); + au_set_h_dptr(src_dentry, a->bdst, dget(a->h_path.dentry)); + h_inode = au_h_dptr(src_dentry, a->bsrc)->d_inode; + mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD); + h_file = au_h_open_pre(src_dentry, a->bsrc); + if (IS_ERR(h_file)) { + err = PTR_ERR(h_file); + h_file = NULL; + } else + err = au_sio_cpup_single(src_dentry, a->bdst, a->bsrc, + -1, AuCpup_KEEPLINO, + a->parent); + mutex_unlock(&h_inode->i_mutex); + au_h_open_post(src_dentry, a->bsrc, h_file); + au_set_h_dptr(src_dentry, a->bdst, NULL); + au_set_dbstart(src_dentry, a->bsrc); + } else { + /* the inode of src_dentry already exists on a.bdst branch */ + h_src_dentry = d_find_alias(h_inode); + if (!h_src_dentry && au_plink_test(inode)) { + plink = 1; + h_src_dentry = au_plink_lkup(inode, a->bdst); + err = PTR_ERR(h_src_dentry); + if (IS_ERR(h_src_dentry)) + goto out; + + if (unlikely(!h_src_dentry->d_inode)) { + dput(h_src_dentry); + h_src_dentry = NULL; + } + + } + if (h_src_dentry) { + err = vfsub_link(h_src_dentry, au_pinned_h_dir(&a->pin), + &a->h_path); + dput(h_src_dentry); + } else { + AuIOErr("no dentry found for hi%lu on b%d\n", + h_inode->i_ino, a->bdst); + err = -EIO; + } + } + + if (!err && !plink) + au_plink_append(inode, a->bdst, a->h_path.dentry); + +out: + AuTraceErr(err); + return err; +} + +int aufs_link(struct dentry *src_dentry, struct inode *dir, + struct dentry *dentry) +{ + int err, rerr; + struct au_dtime dt; + struct au_link_args *a; + struct dentry *wh_dentry, *h_src_dentry; + struct inode *inode; + struct super_block *sb; + struct au_wr_dir_args wr_dir_args = { + /* .force_btgt = -1, */ + .flags = AuWrDir_ADD_ENTRY + }; + + IMustLock(dir); + inode = src_dentry->d_inode; + IMustLock(inode); + + err = -ENOMEM; + a = kzalloc(sizeof(*a), GFP_NOFS); + if (unlikely(!a)) + goto out; + + a->parent = dentry->d_parent; /* dir inode is locked */ + err = aufs_read_and_write_lock2(dentry, src_dentry, + AuLock_NOPLM | AuLock_GEN); + if (unlikely(err)) + goto out_kfree; + err = au_d_hashed_positive(src_dentry); + if (unlikely(err)) + goto out_unlock; + err = au_d_may_add(dentry); + if (unlikely(err)) + goto out_unlock; + + a->src_parent = dget_parent(src_dentry); + wr_dir_args.force_btgt = au_ibstart(inode); + + di_write_lock_parent(a->parent); + wr_dir_args.force_btgt = au_wbr(dentry, wr_dir_args.force_btgt); + wh_dentry = lock_hdir_lkup_wh(dentry, &dt, src_dentry, &a->pin, + &wr_dir_args); + err = PTR_ERR(wh_dentry); + if (IS_ERR(wh_dentry)) + goto out_parent; + + err = 0; + sb = dentry->d_sb; + a->bdst = au_dbstart(dentry); + a->h_path.dentry = au_h_dptr(dentry, a->bdst); + a->h_path.mnt = au_sbr_mnt(sb, a->bdst); + a->bsrc = au_ibstart(inode); + h_src_dentry = au_h_d_alias(src_dentry, a->bsrc); + if (!h_src_dentry) { + a->bsrc = au_dbstart(src_dentry); + h_src_dentry = au_h_d_alias(src_dentry, a->bsrc); + AuDebugOn(!h_src_dentry); + } else if (IS_ERR(h_src_dentry)) + goto out_parent; + + if (au_opt_test(au_mntflags(sb), PLINK)) { + if (a->bdst < a->bsrc + /* && h_src_dentry->d_sb != a->h_path.dentry->d_sb */) + err = au_cpup_or_link(src_dentry, a); + else + err = vfsub_link(h_src_dentry, au_pinned_h_dir(&a->pin), + &a->h_path); + dput(h_src_dentry); + } else { + /* + * copyup src_dentry to the branch we process, + * and then link(2) to it. + */ + dput(h_src_dentry); + if (a->bdst < a->bsrc + /* && h_src_dentry->d_sb != a->h_path.dentry->d_sb */) { + au_unpin(&a->pin); + di_write_unlock(a->parent); + err = au_cpup_before_link(src_dentry, a); + di_write_lock_parent(a->parent); + if (!err) + err = au_pin(&a->pin, dentry, a->bdst, + au_opt_udba(sb), + AuPin_DI_LOCKED | AuPin_MNT_WRITE); + if (unlikely(err)) + goto out_wh; + } + if (!err) { + h_src_dentry = au_h_dptr(src_dentry, a->bdst); + err = -ENOENT; + if (h_src_dentry && h_src_dentry->d_inode) + err = vfsub_link(h_src_dentry, + au_pinned_h_dir(&a->pin), + &a->h_path); + } + } + if (unlikely(err)) + goto out_unpin; + + if (wh_dentry) { + a->h_path.dentry = wh_dentry; + err = au_wh_unlink_dentry(au_pinned_h_dir(&a->pin), &a->h_path, + dentry); + if (unlikely(err)) + goto out_revert; + } + + dir->i_version++; + if (au_ibstart(dir) == au_dbstart(dentry)) + au_cpup_attr_timesizes(dir); + inc_nlink(inode); + inode->i_ctime = dir->i_ctime; + d_instantiate(dentry, au_igrab(inode)); + if (d_unhashed(a->h_path.dentry)) + /* some filesystem calls d_drop() */ + d_drop(dentry); + goto out_unpin; /* success */ + +out_revert: + rerr = vfsub_unlink(au_pinned_h_dir(&a->pin), &a->h_path, /*force*/0); + if (unlikely(rerr)) { + AuIOErr("%.*s reverting failed(%d, %d)\n", + AuDLNPair(dentry), err, rerr); + err = -EIO; + } + au_dtime_revert(&dt); +out_unpin: + au_unpin(&a->pin); +out_wh: + dput(wh_dentry); +out_parent: + di_write_unlock(a->parent); + dput(a->src_parent); +out_unlock: + if (unlikely(err)) { + au_update_dbstart(dentry); + d_drop(dentry); + } + aufs_read_and_write_unlock2(dentry, src_dentry); +out_kfree: + kfree(a); +out: + return err; +} + +int aufs_mkdir(struct inode *dir, struct dentry *dentry, int mode) +{ + int err, rerr; + aufs_bindex_t bindex; + unsigned char diropq; + struct path h_path; + struct dentry *wh_dentry, *parent, *opq_dentry; + struct mutex *h_mtx; + struct super_block *sb; + struct { + struct au_pin pin; + struct au_dtime dt; + } *a; /* reduce the stack usage */ + struct au_wr_dir_args wr_dir_args = { + .force_btgt = -1, + .flags = AuWrDir_ADD_ENTRY | AuWrDir_ISDIR + }; + + IMustLock(dir); + + err = -ENOMEM; + a = kmalloc(sizeof(*a), GFP_NOFS); + if (unlikely(!a)) + goto out; + + err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN); + if (unlikely(err)) + goto out_free; + err = au_d_may_add(dentry); + if (unlikely(err)) + goto out_unlock; + + parent = dentry->d_parent; /* dir inode is locked */ + di_write_lock_parent(parent); + wh_dentry = lock_hdir_lkup_wh(dentry, &a->dt, /*src_dentry*/NULL, + &a->pin, &wr_dir_args); + err = PTR_ERR(wh_dentry); + if (IS_ERR(wh_dentry)) + goto out_parent; + + sb = dentry->d_sb; + bindex = au_dbstart(dentry); + h_path.dentry = au_h_dptr(dentry, bindex); + h_path.mnt = au_sbr_mnt(sb, bindex); + err = vfsub_mkdir(au_pinned_h_dir(&a->pin), &h_path, mode); + if (unlikely(err)) + goto out_unpin; + + /* make the dir opaque */ + diropq = 0; + h_mtx = &h_path.dentry->d_inode->i_mutex; + if (wh_dentry + || au_opt_test(au_mntflags(sb), ALWAYS_DIROPQ)) { + mutex_lock_nested(h_mtx, AuLsc_I_CHILD); + opq_dentry = au_diropq_create(dentry, bindex); + mutex_unlock(h_mtx); + err = PTR_ERR(opq_dentry); + if (IS_ERR(opq_dentry)) + goto out_dir; + dput(opq_dentry); + diropq = 1; + } + + err = epilog(dir, bindex, wh_dentry, dentry); + if (!err) { + inc_nlink(dir); + goto out_unpin; /* success */ + } + + /* revert */ + if (diropq) { + AuLabel(revert opq); + mutex_lock_nested(h_mtx, AuLsc_I_CHILD); + rerr = au_diropq_remove(dentry, bindex); + mutex_unlock(h_mtx); + if (rerr) { + AuIOErr("%.*s reverting diropq failed(%d, %d)\n", + AuDLNPair(dentry), err, rerr); + err = -EIO; + } + } + +out_dir: + AuLabel(revert dir); + rerr = vfsub_rmdir(au_pinned_h_dir(&a->pin), &h_path); + if (rerr) { + AuIOErr("%.*s reverting dir failed(%d, %d)\n", + AuDLNPair(dentry), err, rerr); + err = -EIO; + } + au_dtime_revert(&a->dt); +out_unpin: + au_unpin(&a->pin); + dput(wh_dentry); +out_parent: + di_write_unlock(parent); +out_unlock: + if (unlikely(err)) { + au_update_dbstart(dentry); + d_drop(dentry); + } + aufs_read_unlock(dentry, AuLock_DW); +out_free: + kfree(a); +out: + return err; +} diff --git a/ubuntu/aufs/i_op_del.c b/ubuntu/aufs/i_op_del.c new file mode 100644 index 000000000000..e69c151ce75e --- /dev/null +++ b/ubuntu/aufs/i_op_del.c @@ -0,0 +1,478 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * inode operations (del entry) + */ + +#include "aufs.h" + +/* + * decide if a new whiteout for @dentry is necessary or not. + * when it is necessary, prepare the parent dir for the upper branch whose + * branch index is @bcpup for creation. the actual creation of the whiteout will + * be done by caller. + * return value: + * 0: wh is unnecessary + * plus: wh is necessary + * minus: error + */ +int au_wr_dir_need_wh(struct dentry *dentry, int isdir, aufs_bindex_t *bcpup) +{ + int need_wh, err; + aufs_bindex_t bstart; + struct super_block *sb; + + sb = dentry->d_sb; + bstart = au_dbstart(dentry); + if (*bcpup < 0) { + *bcpup = bstart; + if (au_test_ro(sb, bstart, dentry->d_inode)) { + err = AuWbrCopyup(au_sbi(sb), dentry); + *bcpup = err; + if (unlikely(err < 0)) + goto out; + } + } else + AuDebugOn(bstart < *bcpup + || au_test_ro(sb, *bcpup, dentry->d_inode)); + AuDbg("bcpup %d, bstart %d\n", *bcpup, bstart); + + if (*bcpup != bstart) { + err = au_cpup_dirs(dentry, *bcpup); + if (unlikely(err)) + goto out; + need_wh = 1; + } else { + struct au_dinfo *dinfo, *tmp; + + need_wh = -ENOMEM; + dinfo = au_di(dentry); + tmp = au_di_alloc(sb, AuLsc_DI_TMP); + if (tmp) { + au_di_cp(tmp, dinfo); + au_di_swap(tmp, dinfo); + /* returns the number of positive dentries */ + need_wh = au_lkup_dentry(dentry, bstart + 1, /*type*/0, + /*nd*/NULL); + au_di_swap(tmp, dinfo); + au_rw_write_unlock(&tmp->di_rwsem); + au_di_free(tmp); + } + } + AuDbg("need_wh %d\n", need_wh); + err = need_wh; + +out: + return err; +} + +/* + * simple tests for the del-entry operations. + * following the checks in vfs, plus the parent-child relationship. + */ +int au_may_del(struct dentry *dentry, aufs_bindex_t bindex, + struct dentry *h_parent, int isdir) +{ + int err; + umode_t h_mode; + struct dentry *h_dentry, *h_latest; + struct inode *h_inode; + + h_dentry = au_h_dptr(dentry, bindex); + h_inode = h_dentry->d_inode; + if (dentry->d_inode) { + err = -ENOENT; + if (unlikely(!h_inode || !h_inode->i_nlink)) + goto out; + + h_mode = h_inode->i_mode; + if (!isdir) { + err = -EISDIR; + if (unlikely(S_ISDIR(h_mode))) + goto out; + } else if (unlikely(!S_ISDIR(h_mode))) { + err = -ENOTDIR; + goto out; + } + } else { + /* rename(2) case */ + err = -EIO; + if (unlikely(h_inode)) + goto out; + } + + err = -ENOENT; + /* expected parent dir is locked */ + if (unlikely(h_parent != h_dentry->d_parent)) + goto out; + err = 0; + + /* + * rmdir a dir may break the consistency on some filesystem. + * let's try heavy test. + */ + err = -EACCES; + if (unlikely(au_test_h_perm(h_parent->d_inode, MAY_EXEC | MAY_WRITE))) + goto out; + + h_latest = au_sio_lkup_one(&dentry->d_name, h_parent, + au_sbr(dentry->d_sb, bindex)); + err = -EIO; + if (IS_ERR(h_latest)) + goto out; + if (h_latest == h_dentry) + err = 0; + dput(h_latest); + +out: + return err; +} + +/* + * decide the branch where we operate for @dentry. the branch index will be set + * @rbcpup. after diciding it, 'pin' it and store the timestamps of the parent + * dir for reverting. + * when a new whiteout is necessary, create it. + */ +static struct dentry* +lock_hdir_create_wh(struct dentry *dentry, int isdir, aufs_bindex_t *rbcpup, + struct au_dtime *dt, struct au_pin *pin) +{ + struct dentry *wh_dentry; + struct super_block *sb; + struct path h_path; + int err, need_wh; + unsigned int udba; + aufs_bindex_t bcpup; + + need_wh = au_wr_dir_need_wh(dentry, isdir, rbcpup); + wh_dentry = ERR_PTR(need_wh); + if (unlikely(need_wh < 0)) + goto out; + + sb = dentry->d_sb; + udba = au_opt_udba(sb); + bcpup = *rbcpup; + err = au_pin(pin, dentry, bcpup, udba, + AuPin_DI_LOCKED | AuPin_MNT_WRITE); + wh_dentry = ERR_PTR(err); + if (unlikely(err)) + goto out; + + h_path.dentry = au_pinned_h_parent(pin); + if (udba != AuOpt_UDBA_NONE + && au_dbstart(dentry) == bcpup) { + err = au_may_del(dentry, bcpup, h_path.dentry, isdir); + wh_dentry = ERR_PTR(err); + if (unlikely(err)) + goto out_unpin; + } + + h_path.mnt = au_sbr_mnt(sb, bcpup); + au_dtime_store(dt, au_pinned_parent(pin), &h_path); + wh_dentry = NULL; + if (!need_wh) + goto out; /* success, no need to create whiteout */ + + wh_dentry = au_wh_create(dentry, bcpup, h_path.dentry); + if (IS_ERR(wh_dentry)) + goto out_unpin; + + /* returns with the parent is locked and wh_dentry is dget-ed */ + goto out; /* success */ + +out_unpin: + au_unpin(pin); +out: + return wh_dentry; +} + +/* + * when removing a dir, rename it to a unique temporary whiteout-ed name first + * in order to be revertible and save time for removing many child whiteouts + * under the dir. + * returns 1 when there are too many child whiteout and caller should remove + * them asynchronously. returns 0 when the number of children is enough small to + * remove now or the branch fs is a remote fs. + * otherwise return an error. + */ +static int renwh_and_rmdir(struct dentry *dentry, aufs_bindex_t bindex, + struct au_nhash *whlist, struct inode *dir) +{ + int rmdir_later, err, dirwh; + struct dentry *h_dentry; + struct super_block *sb; + + sb = dentry->d_sb; + SiMustAnyLock(sb); + h_dentry = au_h_dptr(dentry, bindex); + err = au_whtmp_ren(h_dentry, au_sbr(sb, bindex)); + if (unlikely(err)) + goto out; + + /* stop monitoring */ + au_hn_free(au_hi(dentry->d_inode, bindex)); + + if (!au_test_fs_remote(h_dentry->d_sb)) { + dirwh = au_sbi(sb)->si_dirwh; + rmdir_later = (dirwh <= 1); + if (!rmdir_later) + rmdir_later = au_nhash_test_longer_wh(whlist, bindex, + dirwh); + if (rmdir_later) + return rmdir_later; + } + + err = au_whtmp_rmdir(dir, bindex, h_dentry, whlist); + if (unlikely(err)) { + AuIOErr("rmdir %.*s, b%d failed, %d. ignored\n", + AuDLNPair(h_dentry), bindex, err); + err = 0; + } + +out: + AuTraceErr(err); + return err; +} + +/* + * final procedure for deleting a entry. + * maintain dentry and iattr. + */ +static void epilog(struct inode *dir, struct dentry *dentry, + aufs_bindex_t bindex) +{ + struct inode *inode; + + inode = dentry->d_inode; + d_drop(dentry); + inode->i_ctime = dir->i_ctime; + + if (au_ibstart(dir) == bindex) + au_cpup_attr_timesizes(dir); + dir->i_version++; +} + +/* + * when an error happened, remove the created whiteout and revert everything. + */ +static int do_revert(int err, struct inode *dir, aufs_bindex_t bindex, + aufs_bindex_t bwh, struct dentry *wh_dentry, + struct dentry *dentry, struct au_dtime *dt) +{ + int rerr; + struct path h_path = { + .dentry = wh_dentry, + .mnt = au_sbr_mnt(dir->i_sb, bindex) + }; + + rerr = au_wh_unlink_dentry(au_h_iptr(dir, bindex), &h_path, dentry); + if (!rerr) { + au_set_dbwh(dentry, bwh); + au_dtime_revert(dt); + return 0; + } + + AuIOErr("%.*s reverting whiteout failed(%d, %d)\n", + AuDLNPair(dentry), err, rerr); + return -EIO; +} + +/* ---------------------------------------------------------------------- */ + +int aufs_unlink(struct inode *dir, struct dentry *dentry) +{ + int err; + aufs_bindex_t bwh, bindex, bstart; + struct au_dtime dt; + struct au_pin pin; + struct path h_path; + struct inode *inode, *h_dir; + struct dentry *parent, *wh_dentry; + + IMustLock(dir); + + err = aufs_read_lock(dentry, AuLock_DW | AuLock_GEN); + if (unlikely(err)) + goto out; + err = au_d_hashed_positive(dentry); + if (unlikely(err)) + goto out_unlock; + inode = dentry->d_inode; + IMustLock(inode); + err = -EISDIR; + if (unlikely(S_ISDIR(inode->i_mode))) + goto out_unlock; /* possible? */ + + bstart = au_dbstart(dentry); + bwh = au_dbwh(dentry); + bindex = -1; + parent = dentry->d_parent; /* dir inode is locked */ + di_write_lock_parent(parent); + wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/0, &bindex, &dt, &pin); + err = PTR_ERR(wh_dentry); + if (IS_ERR(wh_dentry)) + goto out_parent; + + h_path.mnt = au_sbr_mnt(dentry->d_sb, bstart); + h_path.dentry = au_h_dptr(dentry, bstart); + dget(h_path.dentry); + if (bindex == bstart) { + h_dir = au_pinned_h_dir(&pin); + err = vfsub_unlink(h_dir, &h_path, /*force*/0); + } else { + /* dir inode is locked */ + h_dir = wh_dentry->d_parent->d_inode; + IMustLock(h_dir); + err = 0; + } + + if (!err) { + vfsub_drop_nlink(inode); + epilog(dir, dentry, bindex); + + /* update target timestamps */ + if (bindex == bstart) { + vfsub_update_h_iattr(&h_path, /*did*/NULL); /*ignore*/ + inode->i_ctime = h_path.dentry->d_inode->i_ctime; + } else + /* todo: this timestamp may be reverted later */ + inode->i_ctime = h_dir->i_ctime; + goto out_unpin; /* success */ + } + + /* revert */ + if (wh_dentry) { + int rerr; + + rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry, &dt); + if (rerr) + err = rerr; + } + +out_unpin: + au_unpin(&pin); + dput(wh_dentry); + dput(h_path.dentry); +out_parent: + di_write_unlock(parent); +out_unlock: + aufs_read_unlock(dentry, AuLock_DW); +out: + return err; +} + +int aufs_rmdir(struct inode *dir, struct dentry *dentry) +{ + int err, rmdir_later; + aufs_bindex_t bwh, bindex, bstart; + struct au_dtime dt; + struct au_pin pin; + struct inode *inode; + struct dentry *parent, *wh_dentry, *h_dentry; + struct au_whtmp_rmdir *args; + + IMustLock(dir); + + err = aufs_read_lock(dentry, AuLock_DW | AuLock_FLUSH | AuLock_GEN); + if (unlikely(err)) + goto out; + err = au_alive_dir(dentry); + if (unlikely(err)) + goto out_unlock; + inode = dentry->d_inode; + IMustLock(inode); + err = -ENOTDIR; + if (unlikely(!S_ISDIR(inode->i_mode))) + goto out_unlock; /* possible? */ + + err = -ENOMEM; + args = au_whtmp_rmdir_alloc(dir->i_sb, GFP_NOFS); + if (unlikely(!args)) + goto out_unlock; + + parent = dentry->d_parent; /* dir inode is locked */ + di_write_lock_parent(parent); + err = au_test_empty(dentry, &args->whlist); + if (unlikely(err)) + goto out_parent; + + bstart = au_dbstart(dentry); + bwh = au_dbwh(dentry); + bindex = -1; + wh_dentry = lock_hdir_create_wh(dentry, /*isdir*/1, &bindex, &dt, &pin); + err = PTR_ERR(wh_dentry); + if (IS_ERR(wh_dentry)) + goto out_parent; + + h_dentry = au_h_dptr(dentry, bstart); + dget(h_dentry); + rmdir_later = 0; + if (bindex == bstart) { + err = renwh_and_rmdir(dentry, bstart, &args->whlist, dir); + if (err > 0) { + rmdir_later = err; + err = 0; + } + } else { + /* stop monitoring */ + au_hn_free(au_hi(inode, bstart)); + + /* dir inode is locked */ + IMustLock(wh_dentry->d_parent->d_inode); + err = 0; + } + + if (!err) { + vfsub_dead_dir(inode); + au_set_dbdiropq(dentry, -1); + epilog(dir, dentry, bindex); + + if (rmdir_later) { + au_whtmp_kick_rmdir(dir, bstart, h_dentry, args); + args = NULL; + } + + goto out_unpin; /* success */ + } + + /* revert */ + AuLabel(revert); + if (wh_dentry) { + int rerr; + + rerr = do_revert(err, dir, bindex, bwh, wh_dentry, dentry, &dt); + if (rerr) + err = rerr; + } + +out_unpin: + au_unpin(&pin); + dput(wh_dentry); + dput(h_dentry); +out_parent: + di_write_unlock(parent); + if (args) + au_whtmp_rmdir_free(args); +out_unlock: + aufs_read_unlock(dentry, AuLock_DW); +out: + AuTraceErr(err); + return err; +} diff --git a/ubuntu/aufs/i_op_ren.c b/ubuntu/aufs/i_op_ren.c new file mode 100644 index 000000000000..f253bec7efa9 --- /dev/null +++ b/ubuntu/aufs/i_op_ren.c @@ -0,0 +1,1017 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * inode operation (rename entry) + * todo: this is crazy monster + */ + +#include "aufs.h" + +enum { AuSRC, AuDST, AuSrcDst }; +enum { AuPARENT, AuCHILD, AuParentChild }; + +#define AuRen_ISDIR 1 +#define AuRen_ISSAMEDIR (1 << 1) +#define AuRen_WHSRC (1 << 2) +#define AuRen_WHDST (1 << 3) +#define AuRen_MNT_WRITE (1 << 4) +#define AuRen_DT_DSTDIR (1 << 5) +#define AuRen_DIROPQ (1 << 6) +#define AuRen_CPUP (1 << 7) +#define au_ftest_ren(flags, name) ((flags) & AuRen_##name) +#define au_fset_ren(flags, name) \ + do { (flags) |= AuRen_##name; } while (0) +#define au_fclr_ren(flags, name) \ + do { (flags) &= ~AuRen_##name; } while (0) + +struct au_ren_args { + struct { + struct dentry *dentry, *h_dentry, *parent, *h_parent, + *wh_dentry; + struct inode *dir, *inode; + struct au_hinode *hdir; + struct au_dtime dt[AuParentChild]; + aufs_bindex_t bstart; + } sd[AuSrcDst]; + +#define src_dentry sd[AuSRC].dentry +#define src_dir sd[AuSRC].dir +#define src_inode sd[AuSRC].inode +#define src_h_dentry sd[AuSRC].h_dentry +#define src_parent sd[AuSRC].parent +#define src_h_parent sd[AuSRC].h_parent +#define src_wh_dentry sd[AuSRC].wh_dentry +#define src_hdir sd[AuSRC].hdir +#define src_h_dir sd[AuSRC].hdir->hi_inode +#define src_dt sd[AuSRC].dt +#define src_bstart sd[AuSRC].bstart + +#define dst_dentry sd[AuDST].dentry +#define dst_dir sd[AuDST].dir +#define dst_inode sd[AuDST].inode +#define dst_h_dentry sd[AuDST].h_dentry +#define dst_parent sd[AuDST].parent +#define dst_h_parent sd[AuDST].h_parent +#define dst_wh_dentry sd[AuDST].wh_dentry +#define dst_hdir sd[AuDST].hdir +#define dst_h_dir sd[AuDST].hdir->hi_inode +#define dst_dt sd[AuDST].dt +#define dst_bstart sd[AuDST].bstart + + struct dentry *h_trap; + struct au_branch *br; + struct au_hinode *src_hinode; + struct path h_path; + struct au_nhash whlist; + aufs_bindex_t btgt, src_bwh, src_bdiropq; + + unsigned int flags; + + struct au_whtmp_rmdir *thargs; + struct dentry *h_dst; +}; + +/* ---------------------------------------------------------------------- */ + +/* + * functions for reverting. + * when an error happened in a single rename systemcall, we should revert + * everything as if nothing happend. + * we don't need to revert the copied-up/down the parent dir since they are + * harmless. + */ + +#define RevertFailure(fmt, ...) do { \ + AuIOErr("revert failure: " fmt " (%d, %d)\n", \ + ##__VA_ARGS__, err, rerr); \ + err = -EIO; \ +} while (0) + +static void au_ren_rev_diropq(int err, struct au_ren_args *a) +{ + int rerr; + + au_hn_imtx_lock_nested(a->src_hinode, AuLsc_I_CHILD); + rerr = au_diropq_remove(a->src_dentry, a->btgt); + au_hn_imtx_unlock(a->src_hinode); + au_set_dbdiropq(a->src_dentry, a->src_bdiropq); + if (rerr) + RevertFailure("remove diropq %.*s", AuDLNPair(a->src_dentry)); +} + +static void au_ren_rev_rename(int err, struct au_ren_args *a) +{ + int rerr; + + a->h_path.dentry = au_lkup_one(&a->src_dentry->d_name, a->src_h_parent, + a->br, /*nd*/NULL); + rerr = PTR_ERR(a->h_path.dentry); + if (IS_ERR(a->h_path.dentry)) { + RevertFailure("au_lkup_one %.*s", AuDLNPair(a->src_dentry)); + return; + } + + rerr = vfsub_rename(a->dst_h_dir, + au_h_dptr(a->src_dentry, a->btgt), + a->src_h_dir, &a->h_path); + d_drop(a->h_path.dentry); + dput(a->h_path.dentry); + /* au_set_h_dptr(a->src_dentry, a->btgt, NULL); */ + if (rerr) + RevertFailure("rename %.*s", AuDLNPair(a->src_dentry)); +} + +static void au_ren_rev_cpup(int err, struct au_ren_args *a) +{ + int rerr; + + a->h_path.dentry = a->dst_h_dentry; + rerr = vfsub_unlink(a->dst_h_dir, &a->h_path, /*force*/0); + au_set_h_dptr(a->src_dentry, a->btgt, NULL); + au_set_dbstart(a->src_dentry, a->src_bstart); + if (rerr) + RevertFailure("unlink %.*s", AuDLNPair(a->dst_h_dentry)); +} + +static void au_ren_rev_whtmp(int err, struct au_ren_args *a) +{ + int rerr; + + a->h_path.dentry = au_lkup_one(&a->dst_dentry->d_name, a->dst_h_parent, + a->br, /*nd*/NULL); + rerr = PTR_ERR(a->h_path.dentry); + if (IS_ERR(a->h_path.dentry)) { + RevertFailure("lookup %.*s", AuDLNPair(a->dst_dentry)); + return; + } + if (a->h_path.dentry->d_inode) { + d_drop(a->h_path.dentry); + dput(a->h_path.dentry); + return; + } + + rerr = vfsub_rename(a->dst_h_dir, a->h_dst, a->dst_h_dir, &a->h_path); + d_drop(a->h_path.dentry); + dput(a->h_path.dentry); + if (!rerr) + au_set_h_dptr(a->dst_dentry, a->btgt, dget(a->h_dst)); + else + RevertFailure("rename %.*s", AuDLNPair(a->h_dst)); +} + +static void au_ren_rev_whsrc(int err, struct au_ren_args *a) +{ + int rerr; + + a->h_path.dentry = a->src_wh_dentry; + rerr = au_wh_unlink_dentry(a->src_h_dir, &a->h_path, a->src_dentry); + au_set_dbwh(a->src_dentry, a->src_bwh); + if (rerr) + RevertFailure("unlink %.*s", AuDLNPair(a->src_wh_dentry)); +} +#undef RevertFailure + +/* ---------------------------------------------------------------------- */ + +/* + * when we have to copyup the renaming entry, do it with the rename-target name + * in order to minimize the cost (the later actual rename is unnecessary). + * otherwise rename it on the target branch. + */ +static int au_ren_or_cpup(struct au_ren_args *a) +{ + int err; + struct dentry *d; + + d = a->src_dentry; + if (au_dbstart(d) == a->btgt) { + a->h_path.dentry = a->dst_h_dentry; + if (au_ftest_ren(a->flags, DIROPQ) + && au_dbdiropq(d) == a->btgt) + au_fclr_ren(a->flags, DIROPQ); + AuDebugOn(au_dbstart(d) != a->btgt); + err = vfsub_rename(a->src_h_dir, au_h_dptr(d, a->btgt), + a->dst_h_dir, &a->h_path); + } else { + struct mutex *h_mtx = &a->src_h_dentry->d_inode->i_mutex; + struct file *h_file; + + au_fset_ren(a->flags, CPUP); + mutex_lock_nested(h_mtx, AuLsc_I_CHILD); + au_set_dbstart(d, a->btgt); + au_set_h_dptr(d, a->btgt, dget(a->dst_h_dentry)); + h_file = au_h_open_pre(d, a->src_bstart); + if (IS_ERR(h_file)) { + err = PTR_ERR(h_file); + h_file = NULL; + } else + err = au_sio_cpup_single(d, a->btgt, a->src_bstart, -1, + !AuCpup_DTIME, a->dst_parent); + mutex_unlock(h_mtx); + au_h_open_post(d, a->src_bstart, h_file); + if (!err) { + d = a->dst_dentry; + au_set_h_dptr(d, a->btgt, NULL); + au_update_dbstart(d); + } else { + au_set_h_dptr(d, a->btgt, NULL); + au_set_dbstart(d, a->src_bstart); + } + } + if (!err && a->h_dst) + /* it will be set to dinfo later */ + dget(a->h_dst); + + return err; +} + +/* cf. aufs_rmdir() */ +static int au_ren_del_whtmp(struct au_ren_args *a) +{ + int err; + struct inode *dir; + + dir = a->dst_dir; + SiMustAnyLock(dir->i_sb); + if (!au_nhash_test_longer_wh(&a->whlist, a->btgt, + au_sbi(dir->i_sb)->si_dirwh) + || au_test_fs_remote(a->h_dst->d_sb)) { + err = au_whtmp_rmdir(dir, a->btgt, a->h_dst, &a->whlist); + if (unlikely(err)) + pr_warning("failed removing whtmp dir %.*s (%d), " + "ignored.\n", AuDLNPair(a->h_dst), err); + } else { + au_nhash_wh_free(&a->thargs->whlist); + a->thargs->whlist = a->whlist; + a->whlist.nh_num = 0; + au_whtmp_kick_rmdir(dir, a->btgt, a->h_dst, a->thargs); + dput(a->h_dst); + a->thargs = NULL; + } + + return 0; +} + +/* make it 'opaque' dir. */ +static int au_ren_diropq(struct au_ren_args *a) +{ + int err; + struct dentry *diropq; + + err = 0; + a->src_bdiropq = au_dbdiropq(a->src_dentry); + a->src_hinode = au_hi(a->src_inode, a->btgt); + au_hn_imtx_lock_nested(a->src_hinode, AuLsc_I_CHILD); + diropq = au_diropq_create(a->src_dentry, a->btgt); + au_hn_imtx_unlock(a->src_hinode); + if (IS_ERR(diropq)) + err = PTR_ERR(diropq); + dput(diropq); + + return err; +} + +static int do_rename(struct au_ren_args *a) +{ + int err; + struct dentry *d, *h_d; + + /* prepare workqueue args for asynchronous rmdir */ + h_d = a->dst_h_dentry; + if (au_ftest_ren(a->flags, ISDIR) && h_d->d_inode) { + err = -ENOMEM; + a->thargs = au_whtmp_rmdir_alloc(a->src_dentry->d_sb, GFP_NOFS); + if (unlikely(!a->thargs)) + goto out; + a->h_dst = dget(h_d); + } + + /* create whiteout for src_dentry */ + if (au_ftest_ren(a->flags, WHSRC)) { + a->src_bwh = au_dbwh(a->src_dentry); + AuDebugOn(a->src_bwh >= 0); + a->src_wh_dentry + = au_wh_create(a->src_dentry, a->btgt, a->src_h_parent); + err = PTR_ERR(a->src_wh_dentry); + if (IS_ERR(a->src_wh_dentry)) + goto out_thargs; + } + + /* lookup whiteout for dentry */ + if (au_ftest_ren(a->flags, WHDST)) { + h_d = au_wh_lkup(a->dst_h_parent, &a->dst_dentry->d_name, + a->br); + err = PTR_ERR(h_d); + if (IS_ERR(h_d)) + goto out_whsrc; + if (!h_d->d_inode) + dput(h_d); + else + a->dst_wh_dentry = h_d; + } + + /* rename dentry to tmpwh */ + if (a->thargs) { + err = au_whtmp_ren(a->dst_h_dentry, a->br); + if (unlikely(err)) + goto out_whdst; + + d = a->dst_dentry; + au_set_h_dptr(d, a->btgt, NULL); + err = au_lkup_neg(d, a->btgt); + if (unlikely(err)) + goto out_whtmp; + a->dst_h_dentry = au_h_dptr(d, a->btgt); + } + + /* cpup src */ + if (a->dst_h_dentry->d_inode && a->src_bstart != a->btgt) { + struct mutex *h_mtx = &a->src_h_dentry->d_inode->i_mutex; + struct file *h_file; + + mutex_lock_nested(h_mtx, AuLsc_I_CHILD); + AuDebugOn(au_dbstart(a->src_dentry) != a->src_bstart); + h_file = au_h_open_pre(a->src_dentry, a->src_bstart); + if (IS_ERR(h_file)) { + err = PTR_ERR(h_file); + h_file = NULL; + } else + err = au_sio_cpup_simple(a->src_dentry, a->btgt, -1, + !AuCpup_DTIME); + mutex_unlock(h_mtx); + au_h_open_post(a->src_dentry, a->src_bstart, h_file); + if (unlikely(err)) + goto out_whtmp; + } + + /* rename by vfs_rename or cpup */ + d = a->dst_dentry; + if (au_ftest_ren(a->flags, ISDIR) + && (a->dst_wh_dentry + || au_dbdiropq(d) == a->btgt + /* hide the lower to keep xino */ + || a->btgt < au_dbend(d) + || au_opt_test(au_mntflags(d->d_sb), ALWAYS_DIROPQ))) + au_fset_ren(a->flags, DIROPQ); + err = au_ren_or_cpup(a); + if (unlikely(err)) + /* leave the copied-up one */ + goto out_whtmp; + + /* make dir opaque */ + if (au_ftest_ren(a->flags, DIROPQ)) { + err = au_ren_diropq(a); + if (unlikely(err)) + goto out_rename; + } + + /* update target timestamps */ + AuDebugOn(au_dbstart(a->src_dentry) != a->btgt); + a->h_path.dentry = au_h_dptr(a->src_dentry, a->btgt); + vfsub_update_h_iattr(&a->h_path, /*did*/NULL); /*ignore*/ + a->src_inode->i_ctime = a->h_path.dentry->d_inode->i_ctime; + + /* remove whiteout for dentry */ + if (a->dst_wh_dentry) { + a->h_path.dentry = a->dst_wh_dentry; + err = au_wh_unlink_dentry(a->dst_h_dir, &a->h_path, + a->dst_dentry); + if (unlikely(err)) + goto out_diropq; + } + + /* remove whtmp */ + if (a->thargs) + au_ren_del_whtmp(a); /* ignore this error */ + + err = 0; + goto out_success; + +out_diropq: + if (au_ftest_ren(a->flags, DIROPQ)) + au_ren_rev_diropq(err, a); +out_rename: + if (!au_ftest_ren(a->flags, CPUP)) + au_ren_rev_rename(err, a); + else + au_ren_rev_cpup(err, a); + dput(a->h_dst); +out_whtmp: + if (a->thargs) + au_ren_rev_whtmp(err, a); +out_whdst: + dput(a->dst_wh_dentry); + a->dst_wh_dentry = NULL; +out_whsrc: + if (a->src_wh_dentry) + au_ren_rev_whsrc(err, a); +out_success: + dput(a->src_wh_dentry); + dput(a->dst_wh_dentry); +out_thargs: + if (a->thargs) { + dput(a->h_dst); + au_whtmp_rmdir_free(a->thargs); + a->thargs = NULL; + } +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* + * test if @dentry dir can be rename destination or not. + * success means, it is a logically empty dir. + */ +static int may_rename_dstdir(struct dentry *dentry, struct au_nhash *whlist) +{ + return au_test_empty(dentry, whlist); +} + +/* + * test if @dentry dir can be rename source or not. + * if it can, return 0 and @children is filled. + * success means, + * - it is a logically empty dir. + * - or, it exists on writable branch and has no children including whiteouts + * on the lower branch. + */ +static int may_rename_srcdir(struct dentry *dentry, aufs_bindex_t btgt) +{ + int err; + unsigned int rdhash; + aufs_bindex_t bstart; + + bstart = au_dbstart(dentry); + if (bstart != btgt) { + struct au_nhash whlist; + + SiMustAnyLock(dentry->d_sb); + rdhash = au_sbi(dentry->d_sb)->si_rdhash; + if (!rdhash) + rdhash = au_rdhash_est(au_dir_size(/*file*/NULL, + dentry)); + err = au_nhash_alloc(&whlist, rdhash, GFP_NOFS); + if (unlikely(err)) + goto out; + err = au_test_empty(dentry, &whlist); + au_nhash_wh_free(&whlist); + goto out; + } + + if (bstart == au_dbtaildir(dentry)) + return 0; /* success */ + + err = au_test_empty_lower(dentry); + +out: + if (err == -ENOTEMPTY) { + AuWarn1("renaming dir who has child(ren) on multiple branches," + " is not supported\n"); + err = -EXDEV; + } + return err; +} + +/* side effect: sets whlist and h_dentry */ +static int au_ren_may_dir(struct au_ren_args *a) +{ + int err; + unsigned int rdhash; + struct dentry *d; + + d = a->dst_dentry; + SiMustAnyLock(d->d_sb); + + err = 0; + if (au_ftest_ren(a->flags, ISDIR) && a->dst_inode) { + rdhash = au_sbi(d->d_sb)->si_rdhash; + if (!rdhash) + rdhash = au_rdhash_est(au_dir_size(/*file*/NULL, d)); + err = au_nhash_alloc(&a->whlist, rdhash, GFP_NOFS); + if (unlikely(err)) + goto out; + + au_set_dbstart(d, a->dst_bstart); + err = may_rename_dstdir(d, &a->whlist); + au_set_dbstart(d, a->btgt); + } + a->dst_h_dentry = au_h_dptr(d, au_dbstart(d)); + if (unlikely(err)) + goto out; + + d = a->src_dentry; + a->src_h_dentry = au_h_dptr(d, au_dbstart(d)); + if (au_ftest_ren(a->flags, ISDIR)) { + err = may_rename_srcdir(d, a->btgt); + if (unlikely(err)) { + au_nhash_wh_free(&a->whlist); + a->whlist.nh_num = 0; + } + } +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* + * simple tests for rename. + * following the checks in vfs, plus the parent-child relationship. + */ +static int au_may_ren(struct au_ren_args *a) +{ + int err, isdir; + struct inode *h_inode; + + if (a->src_bstart == a->btgt) { + err = au_may_del(a->src_dentry, a->btgt, a->src_h_parent, + au_ftest_ren(a->flags, ISDIR)); + if (unlikely(err)) + goto out; + err = -EINVAL; + if (unlikely(a->src_h_dentry == a->h_trap)) + goto out; + } + + err = 0; + if (a->dst_bstart != a->btgt) + goto out; + + err = -ENOTEMPTY; + if (unlikely(a->dst_h_dentry == a->h_trap)) + goto out; + + err = -EIO; + h_inode = a->dst_h_dentry->d_inode; + isdir = !!au_ftest_ren(a->flags, ISDIR); + if (!a->dst_dentry->d_inode) { + if (unlikely(h_inode)) + goto out; + err = au_may_add(a->dst_dentry, a->btgt, a->dst_h_parent, + isdir); + } else { + if (unlikely(!h_inode || !h_inode->i_nlink)) + goto out; + err = au_may_del(a->dst_dentry, a->btgt, a->dst_h_parent, + isdir); + if (unlikely(err)) + goto out; + } + +out: + if (unlikely(err == -ENOENT || err == -EEXIST)) + err = -EIO; + AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* + * locking order + * (VFS) + * - src_dir and dir by lock_rename() + * - inode if exitsts + * (aufs) + * - lock all + * + src_dentry and dentry by aufs_read_and_write_lock2() which calls, + * + si_read_lock + * + di_write_lock2_child() + * + di_write_lock_child() + * + ii_write_lock_child() + * + di_write_lock_child2() + * + ii_write_lock_child2() + * + src_parent and parent + * + di_write_lock_parent() + * + ii_write_lock_parent() + * + di_write_lock_parent2() + * + ii_write_lock_parent2() + * + lower src_dir and dir by vfsub_lock_rename() + * + verify the every relationships between child and parent. if any + * of them failed, unlock all and return -EBUSY. + */ +static void au_ren_unlock(struct au_ren_args *a) +{ + struct super_block *sb; + + sb = a->dst_dentry->d_sb; + if (au_ftest_ren(a->flags, MNT_WRITE)) + mnt_drop_write(a->br->br_mnt); + vfsub_unlock_rename(a->src_h_parent, a->src_hdir, + a->dst_h_parent, a->dst_hdir); +} + +static int au_ren_lock(struct au_ren_args *a) +{ + int err; + unsigned int udba; + + err = 0; + a->src_h_parent = au_h_dptr(a->src_parent, a->btgt); + a->src_hdir = au_hi(a->src_dir, a->btgt); + a->dst_h_parent = au_h_dptr(a->dst_parent, a->btgt); + a->dst_hdir = au_hi(a->dst_dir, a->btgt); + a->h_trap = vfsub_lock_rename(a->src_h_parent, a->src_hdir, + a->dst_h_parent, a->dst_hdir); + udba = au_opt_udba(a->src_dentry->d_sb); + if (unlikely(a->src_hdir->hi_inode != a->src_h_parent->d_inode + || a->dst_hdir->hi_inode != a->dst_h_parent->d_inode)) + err = au_busy_or_stale(); + if (!err && au_dbstart(a->src_dentry) == a->btgt) + err = au_h_verify(a->src_h_dentry, udba, + a->src_h_parent->d_inode, a->src_h_parent, + a->br); + if (!err && au_dbstart(a->dst_dentry) == a->btgt) + err = au_h_verify(a->dst_h_dentry, udba, + a->dst_h_parent->d_inode, a->dst_h_parent, + a->br); + if (!err) { + err = mnt_want_write(a->br->br_mnt); + if (unlikely(err)) + goto out_unlock; + au_fset_ren(a->flags, MNT_WRITE); + goto out; /* success */ + } + + err = au_busy_or_stale(); + +out_unlock: + au_ren_unlock(a); +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +static void au_ren_refresh_dir(struct au_ren_args *a) +{ + struct inode *dir; + + dir = a->dst_dir; + dir->i_version++; + if (au_ftest_ren(a->flags, ISDIR)) { + /* is this updating defined in POSIX? */ + au_cpup_attr_timesizes(a->src_inode); + au_cpup_attr_nlink(dir, /*force*/1); + } + + if (au_ibstart(dir) == a->btgt) + au_cpup_attr_timesizes(dir); + + if (au_ftest_ren(a->flags, ISSAMEDIR)) + return; + + dir = a->src_dir; + dir->i_version++; + if (au_ftest_ren(a->flags, ISDIR)) + au_cpup_attr_nlink(dir, /*force*/1); + if (au_ibstart(dir) == a->btgt) + au_cpup_attr_timesizes(dir); +} + +static void au_ren_refresh(struct au_ren_args *a) +{ + aufs_bindex_t bend, bindex; + struct dentry *d, *h_d; + struct inode *i, *h_i; + struct super_block *sb; + + d = a->dst_dentry; + d_drop(d); + if (a->h_dst) + /* already dget-ed by au_ren_or_cpup() */ + au_set_h_dptr(d, a->btgt, a->h_dst); + + i = a->dst_inode; + if (i) { + if (!au_ftest_ren(a->flags, ISDIR)) + vfsub_drop_nlink(i); + else { + vfsub_dead_dir(i); + au_cpup_attr_timesizes(i); + } + au_update_dbrange(d, /*do_put_zero*/1); + } else { + bend = a->btgt; + for (bindex = au_dbstart(d); bindex < bend; bindex++) + au_set_h_dptr(d, bindex, NULL); + bend = au_dbend(d); + for (bindex = a->btgt + 1; bindex <= bend; bindex++) + au_set_h_dptr(d, bindex, NULL); + au_update_dbrange(d, /*do_put_zero*/0); + } + + d = a->src_dentry; + au_set_dbwh(d, -1); + bend = au_dbend(d); + for (bindex = a->btgt + 1; bindex <= bend; bindex++) { + h_d = au_h_dptr(d, bindex); + if (h_d) + au_set_h_dptr(d, bindex, NULL); + } + au_set_dbend(d, a->btgt); + + sb = d->d_sb; + i = a->src_inode; + if (au_opt_test(au_mntflags(sb), PLINK) && au_plink_test(i)) + return; /* success */ + + bend = au_ibend(i); + for (bindex = a->btgt + 1; bindex <= bend; bindex++) { + h_i = au_h_iptr(i, bindex); + if (h_i) { + au_xino_write(sb, bindex, h_i->i_ino, /*ino*/0); + /* ignore this error */ + au_set_h_iptr(i, bindex, NULL, 0); + } + } + au_set_ibend(i, a->btgt); +} + +/* ---------------------------------------------------------------------- */ + +/* mainly for link(2) and rename(2) */ +int au_wbr(struct dentry *dentry, aufs_bindex_t btgt) +{ + aufs_bindex_t bdiropq, bwh; + struct dentry *parent; + struct au_branch *br; + + parent = dentry->d_parent; + IMustLock(parent->d_inode); /* dir is locked */ + + bdiropq = au_dbdiropq(parent); + bwh = au_dbwh(dentry); + br = au_sbr(dentry->d_sb, btgt); + if (au_br_rdonly(br) + || (0 <= bdiropq && bdiropq < btgt) + || (0 <= bwh && bwh < btgt)) + btgt = -1; + + AuDbg("btgt %d\n", btgt); + return btgt; +} + +/* sets src_bstart, dst_bstart and btgt */ +static int au_ren_wbr(struct au_ren_args *a) +{ + int err; + struct au_wr_dir_args wr_dir_args = { + /* .force_btgt = -1, */ + .flags = AuWrDir_ADD_ENTRY + }; + + a->src_bstart = au_dbstart(a->src_dentry); + a->dst_bstart = au_dbstart(a->dst_dentry); + if (au_ftest_ren(a->flags, ISDIR)) + au_fset_wrdir(wr_dir_args.flags, ISDIR); + wr_dir_args.force_btgt = a->src_bstart; + if (a->dst_inode && a->dst_bstart < a->src_bstart) + wr_dir_args.force_btgt = a->dst_bstart; + wr_dir_args.force_btgt = au_wbr(a->dst_dentry, wr_dir_args.force_btgt); + err = au_wr_dir(a->dst_dentry, a->src_dentry, &wr_dir_args); + a->btgt = err; + + return err; +} + +static void au_ren_dt(struct au_ren_args *a) +{ + a->h_path.dentry = a->src_h_parent; + au_dtime_store(a->src_dt + AuPARENT, a->src_parent, &a->h_path); + if (!au_ftest_ren(a->flags, ISSAMEDIR)) { + a->h_path.dentry = a->dst_h_parent; + au_dtime_store(a->dst_dt + AuPARENT, a->dst_parent, &a->h_path); + } + + au_fclr_ren(a->flags, DT_DSTDIR); + if (!au_ftest_ren(a->flags, ISDIR)) + return; + + a->h_path.dentry = a->src_h_dentry; + au_dtime_store(a->src_dt + AuCHILD, a->src_dentry, &a->h_path); + if (a->dst_h_dentry->d_inode) { + au_fset_ren(a->flags, DT_DSTDIR); + a->h_path.dentry = a->dst_h_dentry; + au_dtime_store(a->dst_dt + AuCHILD, a->dst_dentry, &a->h_path); + } +} + +static void au_ren_rev_dt(int err, struct au_ren_args *a) +{ + struct dentry *h_d; + struct mutex *h_mtx; + + au_dtime_revert(a->src_dt + AuPARENT); + if (!au_ftest_ren(a->flags, ISSAMEDIR)) + au_dtime_revert(a->dst_dt + AuPARENT); + + if (au_ftest_ren(a->flags, ISDIR) && err != -EIO) { + h_d = a->src_dt[AuCHILD].dt_h_path.dentry; + h_mtx = &h_d->d_inode->i_mutex; + mutex_lock_nested(h_mtx, AuLsc_I_CHILD); + au_dtime_revert(a->src_dt + AuCHILD); + mutex_unlock(h_mtx); + + if (au_ftest_ren(a->flags, DT_DSTDIR)) { + h_d = a->dst_dt[AuCHILD].dt_h_path.dentry; + h_mtx = &h_d->d_inode->i_mutex; + mutex_lock_nested(h_mtx, AuLsc_I_CHILD); + au_dtime_revert(a->dst_dt + AuCHILD); + mutex_unlock(h_mtx); + } + } +} + +/* ---------------------------------------------------------------------- */ + +int aufs_rename(struct inode *_src_dir, struct dentry *_src_dentry, + struct inode *_dst_dir, struct dentry *_dst_dentry) +{ + int err, flags; + /* reduce stack space */ + struct au_ren_args *a; + + AuDbg("%.*s, %.*s\n", AuDLNPair(_src_dentry), AuDLNPair(_dst_dentry)); + IMustLock(_src_dir); + IMustLock(_dst_dir); + + err = -ENOMEM; + BUILD_BUG_ON(sizeof(*a) > PAGE_SIZE); + a = kzalloc(sizeof(*a), GFP_NOFS); + if (unlikely(!a)) + goto out; + + a->src_dir = _src_dir; + a->src_dentry = _src_dentry; + a->src_inode = a->src_dentry->d_inode; + a->src_parent = a->src_dentry->d_parent; /* dir inode is locked */ + a->dst_dir = _dst_dir; + a->dst_dentry = _dst_dentry; + a->dst_inode = a->dst_dentry->d_inode; + a->dst_parent = a->dst_dentry->d_parent; /* dir inode is locked */ + if (a->dst_inode) { + IMustLock(a->dst_inode); + au_igrab(a->dst_inode); + } + + err = -ENOTDIR; + flags = AuLock_FLUSH | AuLock_NOPLM | AuLock_GEN; + if (S_ISDIR(a->src_inode->i_mode)) { + au_fset_ren(a->flags, ISDIR); + if (unlikely(a->dst_inode && !S_ISDIR(a->dst_inode->i_mode))) + goto out_free; + err = aufs_read_and_write_lock2(a->dst_dentry, a->src_dentry, + AuLock_DIR | flags); + } else + err = aufs_read_and_write_lock2(a->dst_dentry, a->src_dentry, + flags); + if (unlikely(err)) + goto out_free; + + err = au_d_hashed_positive(a->src_dentry); + if (unlikely(err)) + goto out_unlock; + err = -ENOENT; + if (a->dst_inode) { + /* + * If it is a dir, VFS unhash dst_dentry before this + * function. It means we cannot rely upon d_unhashed(). + */ + if (unlikely(!a->dst_inode->i_nlink)) + goto out_unlock; + if (!S_ISDIR(a->dst_inode->i_mode)) { + err = au_d_hashed_positive(a->dst_dentry); + if (unlikely(err)) + goto out_unlock; + } else if (unlikely(IS_DEADDIR(a->dst_inode))) + goto out_unlock; + } else if (unlikely(d_unhashed(a->dst_dentry))) + goto out_unlock; + + au_fset_ren(a->flags, ISSAMEDIR); /* temporary */ + di_write_lock_parent(a->dst_parent); + + /* which branch we process */ + err = au_ren_wbr(a); + if (unlikely(err < 0)) + goto out_parent; + a->br = au_sbr(a->dst_dentry->d_sb, a->btgt); + a->h_path.mnt = a->br->br_mnt; + + /* are they available to be renamed */ + err = au_ren_may_dir(a); + if (unlikely(err)) + goto out_children; + + /* prepare the writable parent dir on the same branch */ + if (a->dst_bstart == a->btgt) { + au_fset_ren(a->flags, WHDST); + } else { + err = au_cpup_dirs(a->dst_dentry, a->btgt); + if (unlikely(err)) + goto out_children; + } + + if (a->src_dir != a->dst_dir) { + /* + * this temporary unlock is safe, + * because both dir->i_mutex are locked. + */ + di_write_unlock(a->dst_parent); + di_write_lock_parent(a->src_parent); + err = au_wr_dir_need_wh(a->src_dentry, + au_ftest_ren(a->flags, ISDIR), + &a->btgt); + di_write_unlock(a->src_parent); + di_write_lock2_parent(a->src_parent, a->dst_parent, /*isdir*/1); + au_fclr_ren(a->flags, ISSAMEDIR); + } else + err = au_wr_dir_need_wh(a->src_dentry, + au_ftest_ren(a->flags, ISDIR), + &a->btgt); + if (unlikely(err < 0)) + goto out_children; + if (err) + au_fset_ren(a->flags, WHSRC); + + /* lock them all */ + err = au_ren_lock(a); + if (unlikely(err)) + goto out_children; + + if (!au_opt_test(au_mntflags(a->dst_dir->i_sb), UDBA_NONE)) + err = au_may_ren(a); + else if (unlikely(a->dst_dentry->d_name.len > AUFS_MAX_NAMELEN)) + err = -ENAMETOOLONG; + if (unlikely(err)) + goto out_hdir; + + /* store timestamps to be revertible */ + au_ren_dt(a); + + /* here we go */ + err = do_rename(a); + if (unlikely(err)) + goto out_dt; + + /* update dir attributes */ + au_ren_refresh_dir(a); + + /* dput/iput all lower dentries */ + au_ren_refresh(a); + + goto out_hdir; /* success */ + +out_dt: + au_ren_rev_dt(err, a); +out_hdir: + au_ren_unlock(a); +out_children: + au_nhash_wh_free(&a->whlist); + if (err && a->dst_inode && a->dst_bstart != a->btgt) { + AuDbg("bstart %d, btgt %d\n", a->dst_bstart, a->btgt); + au_set_h_dptr(a->dst_dentry, a->btgt, NULL); + au_set_dbstart(a->dst_dentry, a->dst_bstart); + } +out_parent: + if (!err) + d_move(a->src_dentry, a->dst_dentry); + else { + au_update_dbstart(a->dst_dentry); + if (!a->dst_inode) + d_drop(a->dst_dentry); + } + if (au_ftest_ren(a->flags, ISSAMEDIR)) + di_write_unlock(a->dst_parent); + else + di_write_unlock2(a->src_parent, a->dst_parent); +out_unlock: + aufs_read_and_write_unlock2(a->dst_dentry, a->src_dentry); +out_free: + iput(a->dst_inode); + if (a->thargs) + au_whtmp_rmdir_free(a->thargs); + kfree(a); +out: + AuTraceErr(err); + return err; +} diff --git a/ubuntu/aufs/iinfo.c b/ubuntu/aufs/iinfo.c new file mode 100644 index 000000000000..d9571c47609f --- /dev/null +++ b/ubuntu/aufs/iinfo.c @@ -0,0 +1,264 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * inode private data + */ + +#include "aufs.h" + +struct inode *au_h_iptr(struct inode *inode, aufs_bindex_t bindex) +{ + struct inode *h_inode; + + IiMustAnyLock(inode); + + h_inode = au_ii(inode)->ii_hinode[0 + bindex].hi_inode; + AuDebugOn(h_inode && atomic_read(&h_inode->i_count) <= 0); + return h_inode; +} + +/* todo: hard/soft set? */ +void au_hiput(struct au_hinode *hinode) +{ + au_hn_free(hinode); + dput(hinode->hi_whdentry); + iput(hinode->hi_inode); +} + +unsigned int au_hi_flags(struct inode *inode, int isdir) +{ + unsigned int flags; + const unsigned int mnt_flags = au_mntflags(inode->i_sb); + + flags = 0; + if (au_opt_test(mnt_flags, XINO)) + au_fset_hi(flags, XINO); + if (isdir && au_opt_test(mnt_flags, UDBA_HNOTIFY)) + au_fset_hi(flags, HNOTIFY); + return flags; +} + +void au_set_h_iptr(struct inode *inode, aufs_bindex_t bindex, + struct inode *h_inode, unsigned int flags) +{ + struct au_hinode *hinode; + struct inode *hi; + struct au_iinfo *iinfo = au_ii(inode); + + IiMustWriteLock(inode); + + hinode = iinfo->ii_hinode + bindex; + hi = hinode->hi_inode; + AuDebugOn(h_inode && atomic_read(&h_inode->i_count) <= 0); + + if (hi) + au_hiput(hinode); + hinode->hi_inode = h_inode; + if (h_inode) { + int err; + struct super_block *sb = inode->i_sb; + struct au_branch *br; + + AuDebugOn(inode->i_mode + && (h_inode->i_mode & S_IFMT) + != (inode->i_mode & S_IFMT)); + if (bindex == iinfo->ii_bstart) + au_cpup_igen(inode, h_inode); + br = au_sbr(sb, bindex); + hinode->hi_id = br->br_id; + if (au_ftest_hi(flags, XINO)) { + err = au_xino_write(sb, bindex, h_inode->i_ino, + inode->i_ino); + if (unlikely(err)) + AuIOErr1("failed au_xino_write() %d\n", err); + } + + if (au_ftest_hi(flags, HNOTIFY) + && au_br_hnotifyable(br->br_perm)) { + err = au_hn_alloc(hinode, inode); + if (unlikely(err)) + AuIOErr1("au_hn_alloc() %d\n", err); + } + } +} + +void au_set_hi_wh(struct inode *inode, aufs_bindex_t bindex, + struct dentry *h_wh) +{ + struct au_hinode *hinode; + + IiMustWriteLock(inode); + + hinode = au_ii(inode)->ii_hinode + bindex; + AuDebugOn(hinode->hi_whdentry); + hinode->hi_whdentry = h_wh; +} + +void au_update_iigen(struct inode *inode) +{ + atomic_set(&au_ii(inode)->ii_generation, au_sigen(inode->i_sb)); + /* smp_mb(); */ /* atomic_set */ +} + +/* it may be called at remount time, too */ +void au_update_ibrange(struct inode *inode, int do_put_zero) +{ + struct au_iinfo *iinfo; + aufs_bindex_t bindex, bend; + + iinfo = au_ii(inode); + if (!iinfo) + return; + + IiMustWriteLock(inode); + + if (do_put_zero && iinfo->ii_bstart >= 0) { + for (bindex = iinfo->ii_bstart; bindex <= iinfo->ii_bend; + bindex++) { + struct inode *h_i; + + h_i = iinfo->ii_hinode[0 + bindex].hi_inode; + if (h_i && !h_i->i_nlink) + au_set_h_iptr(inode, bindex, NULL, 0); + } + } + + iinfo->ii_bstart = -1; + iinfo->ii_bend = -1; + bend = au_sbend(inode->i_sb); + for (bindex = 0; bindex <= bend; bindex++) + if (iinfo->ii_hinode[0 + bindex].hi_inode) { + iinfo->ii_bstart = bindex; + break; + } + if (iinfo->ii_bstart >= 0) + for (bindex = bend; bindex >= iinfo->ii_bstart; bindex--) + if (iinfo->ii_hinode[0 + bindex].hi_inode) { + iinfo->ii_bend = bindex; + break; + } + AuDebugOn(iinfo->ii_bstart > iinfo->ii_bend); +} + +/* ---------------------------------------------------------------------- */ + +void au_icntnr_init_once(void *_c) +{ + struct au_icntnr *c = _c; + struct au_iinfo *iinfo = &c->iinfo; + static struct lock_class_key aufs_ii; + + au_rw_init(&iinfo->ii_rwsem); + au_rw_class(&iinfo->ii_rwsem, &aufs_ii); + inode_init_once(&c->vfs_inode); +} + +int au_iinfo_init(struct inode *inode) +{ + struct au_iinfo *iinfo; + struct super_block *sb; + int nbr, i; + + sb = inode->i_sb; + iinfo = &(container_of(inode, struct au_icntnr, vfs_inode)->iinfo); + nbr = au_sbend(sb) + 1; + if (unlikely(nbr <= 0)) + nbr = 1; + iinfo->ii_hinode = kcalloc(nbr, sizeof(*iinfo->ii_hinode), GFP_NOFS); + if (iinfo->ii_hinode) { + au_ninodes_inc(sb); + for (i = 0; i < nbr; i++) + iinfo->ii_hinode[i].hi_id = -1; + + atomic_set(&iinfo->ii_generation, au_sigen(sb)); + /* smp_mb(); */ /* atomic_set */ + iinfo->ii_bstart = -1; + iinfo->ii_bend = -1; + iinfo->ii_vdir = NULL; + return 0; + } + return -ENOMEM; +} + +int au_ii_realloc(struct au_iinfo *iinfo, int nbr) +{ + int err, sz; + struct au_hinode *hip; + + AuRwMustWriteLock(&iinfo->ii_rwsem); + + err = -ENOMEM; + sz = sizeof(*hip) * (iinfo->ii_bend + 1); + if (!sz) + sz = sizeof(*hip); + hip = au_kzrealloc(iinfo->ii_hinode, sz, sizeof(*hip) * nbr, GFP_NOFS); + if (hip) { + iinfo->ii_hinode = hip; + err = 0; + } + + return err; +} + +void au_iinfo_fin(struct inode *inode) +{ + struct au_iinfo *iinfo; + struct au_hinode *hi; + struct super_block *sb; + aufs_bindex_t bindex, bend; + const unsigned char unlinked = !inode->i_nlink; + + iinfo = au_ii(inode); + /* bad_inode case */ + if (!iinfo) + return; + + sb = inode->i_sb; + au_ninodes_dec(sb); + if (si_pid_test(sb)) + au_xino_delete_inode(inode, unlinked); + else { + /* + * it is safe to hide the dependency between sbinfo and + * sb->s_umount. + */ + lockdep_off(); + si_noflush_read_lock(sb); + au_xino_delete_inode(inode, unlinked); + si_read_unlock(sb); + lockdep_on(); + } + + if (iinfo->ii_vdir) + au_vdir_free(iinfo->ii_vdir); + + bindex = iinfo->ii_bstart; + if (bindex >= 0) { + hi = iinfo->ii_hinode + bindex; + bend = iinfo->ii_bend; + while (bindex++ <= bend) { + if (hi->hi_inode) + au_hiput(hi); + hi++; + } + } + kfree(iinfo->ii_hinode); + iinfo->ii_hinode = NULL; + AuRwDestroy(&iinfo->ii_rwsem); +} diff --git a/ubuntu/aufs/inode.c b/ubuntu/aufs/inode.c new file mode 100644 index 000000000000..df70edee95c3 --- /dev/null +++ b/ubuntu/aufs/inode.c @@ -0,0 +1,471 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * inode functions + */ + +#include "aufs.h" + +struct inode *au_igrab(struct inode *inode) +{ + if (inode) { + AuDebugOn(!atomic_read(&inode->i_count)); + ihold(inode); + } + return inode; +} + +static void au_refresh_hinode_attr(struct inode *inode, int do_version) +{ + au_cpup_attr_all(inode, /*force*/0); + au_update_iigen(inode); + if (do_version) + inode->i_version++; +} + +static int au_ii_refresh(struct inode *inode, int *update) +{ + int err, e; + umode_t type; + aufs_bindex_t bindex, new_bindex; + struct super_block *sb; + struct au_iinfo *iinfo; + struct au_hinode *p, *q, tmp; + + IiMustWriteLock(inode); + + *update = 0; + sb = inode->i_sb; + type = inode->i_mode & S_IFMT; + iinfo = au_ii(inode); + err = au_ii_realloc(iinfo, au_sbend(sb) + 1); + if (unlikely(err)) + goto out; + + AuDebugOn(iinfo->ii_bstart < 0); + p = iinfo->ii_hinode + iinfo->ii_bstart; + for (bindex = iinfo->ii_bstart; bindex <= iinfo->ii_bend; + bindex++, p++) { + if (!p->hi_inode) + continue; + + AuDebugOn(type != (p->hi_inode->i_mode & S_IFMT)); + new_bindex = au_br_index(sb, p->hi_id); + if (new_bindex == bindex) + continue; + + if (new_bindex < 0) { + *update = 1; + au_hiput(p); + p->hi_inode = NULL; + continue; + } + + if (new_bindex < iinfo->ii_bstart) + iinfo->ii_bstart = new_bindex; + if (iinfo->ii_bend < new_bindex) + iinfo->ii_bend = new_bindex; + /* swap two lower inode, and loop again */ + q = iinfo->ii_hinode + new_bindex; + tmp = *q; + *q = *p; + *p = tmp; + if (tmp.hi_inode) { + bindex--; + p--; + } + } + au_update_ibrange(inode, /*do_put_zero*/0); + e = au_dy_irefresh(inode); + if (unlikely(e && !err)) + err = e; + +out: + AuTraceErr(err); + return err; +} + +int au_refresh_hinode_self(struct inode *inode) +{ + int err, update; + + err = au_ii_refresh(inode, &update); + if (!err) + au_refresh_hinode_attr(inode, update && S_ISDIR(inode->i_mode)); + + AuTraceErr(err); + return err; +} + +int au_refresh_hinode(struct inode *inode, struct dentry *dentry) +{ + int err, e, update; + unsigned int flags; + umode_t mode; + aufs_bindex_t bindex, bend; + unsigned char isdir; + struct au_hinode *p; + struct au_iinfo *iinfo; + + err = au_ii_refresh(inode, &update); + if (unlikely(err)) + goto out; + + update = 0; + iinfo = au_ii(inode); + p = iinfo->ii_hinode + iinfo->ii_bstart; + mode = (inode->i_mode & S_IFMT); + isdir = S_ISDIR(mode); + flags = au_hi_flags(inode, isdir); + bend = au_dbend(dentry); + for (bindex = au_dbstart(dentry); bindex <= bend; bindex++) { + struct inode *h_i; + struct dentry *h_d; + + h_d = au_h_dptr(dentry, bindex); + if (!h_d || !h_d->d_inode) + continue; + + AuDebugOn(mode != (h_d->d_inode->i_mode & S_IFMT)); + if (iinfo->ii_bstart <= bindex && bindex <= iinfo->ii_bend) { + h_i = au_h_iptr(inode, bindex); + if (h_i) { + if (h_i == h_d->d_inode) + continue; + err = -EIO; + break; + } + } + if (bindex < iinfo->ii_bstart) + iinfo->ii_bstart = bindex; + if (iinfo->ii_bend < bindex) + iinfo->ii_bend = bindex; + au_set_h_iptr(inode, bindex, au_igrab(h_d->d_inode), flags); + update = 1; + } + au_update_ibrange(inode, /*do_put_zero*/0); + e = au_dy_irefresh(inode); + if (unlikely(e && !err)) + err = e; + if (!err) + au_refresh_hinode_attr(inode, update && isdir); + +out: + AuTraceErr(err); + return err; +} + +static int set_inode(struct inode *inode, struct dentry *dentry) +{ + int err; + unsigned int flags; + umode_t mode; + aufs_bindex_t bindex, bstart, btail; + unsigned char isdir; + struct dentry *h_dentry; + struct inode *h_inode; + struct au_iinfo *iinfo; + + IiMustWriteLock(inode); + + err = 0; + isdir = 0; + bstart = au_dbstart(dentry); + h_inode = au_h_dptr(dentry, bstart)->d_inode; + mode = h_inode->i_mode; + switch (mode & S_IFMT) { + case S_IFREG: + btail = au_dbtail(dentry); + inode->i_op = &aufs_iop; + inode->i_fop = &aufs_file_fop; + err = au_dy_iaop(inode, bstart, h_inode); + if (unlikely(err)) + goto out; + break; + case S_IFDIR: + isdir = 1; + btail = au_dbtaildir(dentry); + inode->i_op = &aufs_dir_iop; + inode->i_fop = &aufs_dir_fop; + break; + case S_IFLNK: + btail = au_dbtail(dentry); + inode->i_op = &aufs_symlink_iop; + break; + case S_IFBLK: + case S_IFCHR: + case S_IFIFO: + case S_IFSOCK: + btail = au_dbtail(dentry); + inode->i_op = &aufs_iop; + au_init_special_fop(inode, mode, h_inode->i_rdev); + break; + default: + AuIOErr("Unknown file type 0%o\n", mode); + err = -EIO; + goto out; + } + + /* do not set hnotify for whiteouted dirs (SHWH mode) */ + flags = au_hi_flags(inode, isdir); + if (au_opt_test(au_mntflags(dentry->d_sb), SHWH) + && au_ftest_hi(flags, HNOTIFY) + && dentry->d_name.len > AUFS_WH_PFX_LEN + && !memcmp(dentry->d_name.name, AUFS_WH_PFX, AUFS_WH_PFX_LEN)) + au_fclr_hi(flags, HNOTIFY); + iinfo = au_ii(inode); + iinfo->ii_bstart = bstart; + iinfo->ii_bend = btail; + for (bindex = bstart; bindex <= btail; bindex++) { + h_dentry = au_h_dptr(dentry, bindex); + if (h_dentry) + au_set_h_iptr(inode, bindex, + au_igrab(h_dentry->d_inode), flags); + } + au_cpup_attr_all(inode, /*force*/1); + +out: + return err; +} + +/* + * successful returns with iinfo write_locked + * minus: errno + * zero: success, matched + * plus: no error, but unmatched + */ +static int reval_inode(struct inode *inode, struct dentry *dentry) +{ + int err; + aufs_bindex_t bindex, bend; + struct inode *h_inode, *h_dinode; + + /* + * before this function, if aufs got any iinfo lock, it must be only + * one, the parent dir. + * it can happen by UDBA and the obsoleted inode number. + */ + err = -EIO; + if (unlikely(inode->i_ino == parent_ino(dentry))) + goto out; + + err = 1; + ii_write_lock_new_child(inode); + h_dinode = au_h_dptr(dentry, au_dbstart(dentry))->d_inode; + bend = au_ibend(inode); + for (bindex = au_ibstart(inode); bindex <= bend; bindex++) { + h_inode = au_h_iptr(inode, bindex); + if (h_inode && h_inode == h_dinode) { + err = 0; + if (au_iigen_test(inode, au_digen(dentry))) + err = au_refresh_hinode(inode, dentry); + break; + } + } + + if (unlikely(err)) + ii_write_unlock(inode); +out: + return err; +} + +int au_ino(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, + unsigned int d_type, ino_t *ino) +{ + int err; + struct mutex *mtx; + + /* prevent hardlinked inode number from race condition */ + mtx = NULL; + if (d_type != DT_DIR) { + mtx = &au_sbr(sb, bindex)->br_xino.xi_nondir_mtx; + mutex_lock(mtx); + } + err = au_xino_read(sb, bindex, h_ino, ino); + if (unlikely(err)) + goto out; + + if (!*ino) { + err = -EIO; + *ino = au_xino_new_ino(sb); + if (unlikely(!*ino)) + goto out; + err = au_xino_write(sb, bindex, h_ino, *ino); + if (unlikely(err)) + goto out; + } + +out: + if (mtx) + mutex_unlock(mtx); + return err; +} + +/* successful returns with iinfo write_locked */ +/* todo: return with unlocked? */ +struct inode *au_new_inode(struct dentry *dentry, int must_new) +{ + struct inode *inode, *h_inode; + struct dentry *h_dentry; + struct super_block *sb; + struct mutex *mtx; + ino_t h_ino, ino; + int err; + aufs_bindex_t bstart; + + sb = dentry->d_sb; + bstart = au_dbstart(dentry); + h_dentry = au_h_dptr(dentry, bstart); + h_inode = h_dentry->d_inode; + h_ino = h_inode->i_ino; + + /* + * stop 'race'-ing between hardlinks under different + * parents. + */ + mtx = NULL; + if (!S_ISDIR(h_inode->i_mode)) + mtx = &au_sbr(sb, bstart)->br_xino.xi_nondir_mtx; + +new_ino: + if (mtx) + mutex_lock(mtx); + err = au_xino_read(sb, bstart, h_ino, &ino); + inode = ERR_PTR(err); + if (unlikely(err)) + goto out; + + if (!ino) { + ino = au_xino_new_ino(sb); + if (unlikely(!ino)) { + inode = ERR_PTR(-EIO); + goto out; + } + } + + AuDbg("i%lu\n", (unsigned long)ino); + inode = au_iget_locked(sb, ino); + err = PTR_ERR(inode); + if (IS_ERR(inode)) + goto out; + + AuDbg("%lx, new %d\n", inode->i_state, !!(inode->i_state & I_NEW)); + if (inode->i_state & I_NEW) { + ii_write_lock_new_child(inode); + err = set_inode(inode, dentry); + if (!err) { + unlock_new_inode(inode); + goto out; /* success */ + } + + /* + * iget_failed() calls iput(), but we need to call + * ii_write_unlock() after iget_failed(). so dirty hack for + * i_count. + */ + atomic_inc(&inode->i_count); + iget_failed(inode); + ii_write_unlock(inode); + au_xino_write(sb, bstart, h_ino, /*ino*/0); + /* ignore this error */ + goto out_iput; + } else if (!must_new && !IS_DEADDIR(inode) && inode->i_nlink) { + /* + * horrible race condition between lookup, readdir and copyup + * (or something). + */ + if (mtx) + mutex_unlock(mtx); + err = reval_inode(inode, dentry); + if (unlikely(err < 0)) { + mtx = NULL; + goto out_iput; + } + + if (!err) { + mtx = NULL; + goto out; /* success */ + } else if (mtx) + mutex_lock(mtx); + } + + if (unlikely(au_test_fs_unique_ino(h_dentry->d_inode))) + AuWarn1("Warning: Un-notified UDBA or repeatedly renamed dir," + " b%d, %s, %.*s, hi%lu, i%lu.\n", + bstart, au_sbtype(h_dentry->d_sb), AuDLNPair(dentry), + (unsigned long)h_ino, (unsigned long)ino); + ino = 0; + err = au_xino_write(sb, bstart, h_ino, /*ino*/0); + if (!err) { + iput(inode); + if (mtx) + mutex_unlock(mtx); + goto new_ino; + } + +out_iput: + iput(inode); + inode = ERR_PTR(err); +out: + if (mtx) + mutex_unlock(mtx); + return inode; +} + +/* ---------------------------------------------------------------------- */ + +int au_test_ro(struct super_block *sb, aufs_bindex_t bindex, + struct inode *inode) +{ + int err; + + err = au_br_rdonly(au_sbr(sb, bindex)); + + /* pseudo-link after flushed may happen out of bounds */ + if (!err + && inode + && au_ibstart(inode) <= bindex + && bindex <= au_ibend(inode)) { + /* + * permission check is unnecessary since vfsub routine + * will be called later + */ + struct inode *hi = au_h_iptr(inode, bindex); + if (hi) + err = IS_IMMUTABLE(hi) ? -EROFS : 0; + } + + return err; +} + +int au_test_h_perm(struct inode *h_inode, int mask) +{ + if (!current_fsuid()) + return 0; + return inode_permission(h_inode, mask); +} + +int au_test_h_perm_sio(struct inode *h_inode, int mask) +{ + if (au_test_nfs(h_inode->i_sb) + && (mask & MAY_WRITE) + && S_ISDIR(h_inode->i_mode)) + mask |= MAY_READ; /* force permission check */ + return au_test_h_perm(h_inode, mask); +} diff --git a/ubuntu/aufs/inode.h b/ubuntu/aufs/inode.h new file mode 100644 index 000000000000..1fe58f632534 --- /dev/null +++ b/ubuntu/aufs/inode.h @@ -0,0 +1,554 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * inode operations + */ + +#ifndef __AUFS_INODE_H__ +#define __AUFS_INODE_H__ + +#ifdef __KERNEL__ + +#include <linux/fsnotify.h> +#include "rwsem.h" + +struct vfsmount; + +struct au_hnotify { +#ifdef CONFIG_AUFS_HNOTIFY +#ifdef CONFIG_AUFS_HFSNOTIFY + /* never use fsnotify_add_vfsmount_mark() */ + struct fsnotify_mark hn_mark; + int hn_mark_dead; +#endif + struct inode *hn_aufs_inode; /* no get/put */ +#endif +} ____cacheline_aligned_in_smp; + +struct au_hinode { + struct inode *hi_inode; + aufs_bindex_t hi_id; +#ifdef CONFIG_AUFS_HNOTIFY + struct au_hnotify *hi_notify; +#endif + + /* reference to the copied-up whiteout with get/put */ + struct dentry *hi_whdentry; +}; + +struct au_vdir; +struct au_iinfo { + atomic_t ii_generation; + struct super_block *ii_hsb1; /* no get/put */ + + struct au_rwsem ii_rwsem; + aufs_bindex_t ii_bstart, ii_bend; + __u32 ii_higen; + struct au_hinode *ii_hinode; + struct au_vdir *ii_vdir; +}; + +struct au_icntnr { + struct au_iinfo iinfo; + struct inode vfs_inode; +} ____cacheline_aligned_in_smp; + +/* au_pin flags */ +#define AuPin_DI_LOCKED 1 +#define AuPin_MNT_WRITE (1 << 1) +#define au_ftest_pin(flags, name) ((flags) & AuPin_##name) +#define au_fset_pin(flags, name) \ + do { (flags) |= AuPin_##name; } while (0) +#define au_fclr_pin(flags, name) \ + do { (flags) &= ~AuPin_##name; } while (0) + +struct au_pin { + /* input */ + struct dentry *dentry; + unsigned int udba; + unsigned char lsc_di, lsc_hi, flags; + aufs_bindex_t bindex; + + /* output */ + struct dentry *parent; + struct au_hinode *hdir; + struct vfsmount *h_mnt; +}; + +/* ---------------------------------------------------------------------- */ + +static inline struct au_iinfo *au_ii(struct inode *inode) +{ + struct au_iinfo *iinfo; + + iinfo = &(container_of(inode, struct au_icntnr, vfs_inode)->iinfo); + if (iinfo->ii_hinode) + return iinfo; + return NULL; /* debugging bad_inode case */ +} + +/* ---------------------------------------------------------------------- */ + +/* inode.c */ +struct inode *au_igrab(struct inode *inode); +int au_refresh_hinode_self(struct inode *inode); +int au_refresh_hinode(struct inode *inode, struct dentry *dentry); +int au_ino(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, + unsigned int d_type, ino_t *ino); +struct inode *au_new_inode(struct dentry *dentry, int must_new); +int au_test_ro(struct super_block *sb, aufs_bindex_t bindex, + struct inode *inode); +int au_test_h_perm(struct inode *h_inode, int mask); +int au_test_h_perm_sio(struct inode *h_inode, int mask); + +static inline int au_wh_ino(struct super_block *sb, aufs_bindex_t bindex, + ino_t h_ino, unsigned int d_type, ino_t *ino) +{ +#ifdef CONFIG_AUFS_SHWH + return au_ino(sb, bindex, h_ino, d_type, ino); +#else + return 0; +#endif +} + +/* i_op.c */ +extern struct inode_operations aufs_iop, aufs_symlink_iop, aufs_dir_iop; + +/* au_wr_dir flags */ +#define AuWrDir_ADD_ENTRY 1 +#define AuWrDir_ISDIR (1 << 1) +#define au_ftest_wrdir(flags, name) ((flags) & AuWrDir_##name) +#define au_fset_wrdir(flags, name) \ + do { (flags) |= AuWrDir_##name; } while (0) +#define au_fclr_wrdir(flags, name) \ + do { (flags) &= ~AuWrDir_##name; } while (0) + +struct au_wr_dir_args { + aufs_bindex_t force_btgt; + unsigned char flags; +}; +int au_wr_dir(struct dentry *dentry, struct dentry *src_dentry, + struct au_wr_dir_args *args); + +struct dentry *au_pinned_h_parent(struct au_pin *pin); +void au_pin_init(struct au_pin *pin, struct dentry *dentry, + aufs_bindex_t bindex, int lsc_di, int lsc_hi, + unsigned int udba, unsigned char flags); +int au_pin(struct au_pin *pin, struct dentry *dentry, aufs_bindex_t bindex, + unsigned int udba, unsigned char flags) __must_check; +int au_do_pin(struct au_pin *pin) __must_check; +void au_unpin(struct au_pin *pin); + +/* i_op_add.c */ +int au_may_add(struct dentry *dentry, aufs_bindex_t bindex, + struct dentry *h_parent, int isdir); +int aufs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev); +int aufs_symlink(struct inode *dir, struct dentry *dentry, const char *symname); +int aufs_create(struct inode *dir, struct dentry *dentry, int mode, + struct nameidata *nd); +int aufs_link(struct dentry *src_dentry, struct inode *dir, + struct dentry *dentry); +int aufs_mkdir(struct inode *dir, struct dentry *dentry, int mode); + +/* i_op_del.c */ +int au_wr_dir_need_wh(struct dentry *dentry, int isdir, aufs_bindex_t *bcpup); +int au_may_del(struct dentry *dentry, aufs_bindex_t bindex, + struct dentry *h_parent, int isdir); +int aufs_unlink(struct inode *dir, struct dentry *dentry); +int aufs_rmdir(struct inode *dir, struct dentry *dentry); + +/* i_op_ren.c */ +int au_wbr(struct dentry *dentry, aufs_bindex_t btgt); +int aufs_rename(struct inode *src_dir, struct dentry *src_dentry, + struct inode *dir, struct dentry *dentry); + +/* iinfo.c */ +struct inode *au_h_iptr(struct inode *inode, aufs_bindex_t bindex); +void au_hiput(struct au_hinode *hinode); +void au_set_hi_wh(struct inode *inode, aufs_bindex_t bindex, + struct dentry *h_wh); +unsigned int au_hi_flags(struct inode *inode, int isdir); + +/* hinode flags */ +#define AuHi_XINO 1 +#define AuHi_HNOTIFY (1 << 1) +#define au_ftest_hi(flags, name) ((flags) & AuHi_##name) +#define au_fset_hi(flags, name) \ + do { (flags) |= AuHi_##name; } while (0) +#define au_fclr_hi(flags, name) \ + do { (flags) &= ~AuHi_##name; } while (0) + +#ifndef CONFIG_AUFS_HNOTIFY +#undef AuHi_HNOTIFY +#define AuHi_HNOTIFY 0 +#endif + +void au_set_h_iptr(struct inode *inode, aufs_bindex_t bindex, + struct inode *h_inode, unsigned int flags); + +void au_update_iigen(struct inode *inode); +void au_update_ibrange(struct inode *inode, int do_put_zero); + +void au_icntnr_init_once(void *_c); +int au_iinfo_init(struct inode *inode); +void au_iinfo_fin(struct inode *inode); +int au_ii_realloc(struct au_iinfo *iinfo, int nbr); + +#ifdef CONFIG_PROC_FS +/* plink.c */ +int au_plink_maint(struct super_block *sb, int flags); +void au_plink_maint_leave(struct au_sbinfo *sbinfo); +int au_plink_maint_enter(struct super_block *sb); +#ifdef CONFIG_AUFS_DEBUG +void au_plink_list(struct super_block *sb); +#else +AuStubVoid(au_plink_list, struct super_block *sb) +#endif +int au_plink_test(struct inode *inode); +struct dentry *au_plink_lkup(struct inode *inode, aufs_bindex_t bindex); +void au_plink_append(struct inode *inode, aufs_bindex_t bindex, + struct dentry *h_dentry); +void au_plink_put(struct super_block *sb, int verbose); +void au_plink_clean(struct super_block *sb, int verbose); +void au_plink_half_refresh(struct super_block *sb, aufs_bindex_t br_id); +#else +AuStubInt0(au_plink_maint, struct super_block *sb, int flags); +AuStubVoid(au_plink_maint_leave, struct au_sbinfo *sbinfo); +AuStubInt0(au_plink_maint_enter, struct super_block *sb); +AuStubVoid(au_plink_list, struct super_block *sb); +AuStubInt0(au_plink_test, struct inode *inode); +AuStub(struct dentry *, au_plink_lkup, return NULL, + struct inode *inode, aufs_bindex_t bindex); +AuStubVoid(au_plink_append, struct inode *inode, aufs_bindex_t bindex, + struct dentry *h_dentry); +AuStubVoid(au_plink_put, struct super_block *sb, int verbose); +AuStubVoid(au_plink_clean, struct super_block *sb, int verbose); +AuStubVoid(au_plink_half_refresh, struct super_block *sb, aufs_bindex_t br_id); +#endif /* CONFIG_PROC_FS */ + +/* ---------------------------------------------------------------------- */ + +/* lock subclass for iinfo */ +enum { + AuLsc_II_CHILD, /* child first */ + AuLsc_II_CHILD2, /* rename(2), link(2), and cpup at hnotify */ + AuLsc_II_CHILD3, /* copyup dirs */ + AuLsc_II_PARENT, /* see AuLsc_I_PARENT in vfsub.h */ + AuLsc_II_PARENT2, + AuLsc_II_PARENT3, /* copyup dirs */ + AuLsc_II_NEW_CHILD +}; + +/* + * ii_read_lock_child, ii_write_lock_child, + * ii_read_lock_child2, ii_write_lock_child2, + * ii_read_lock_child3, ii_write_lock_child3, + * ii_read_lock_parent, ii_write_lock_parent, + * ii_read_lock_parent2, ii_write_lock_parent2, + * ii_read_lock_parent3, ii_write_lock_parent3, + * ii_read_lock_new_child, ii_write_lock_new_child, + */ +#define AuReadLockFunc(name, lsc) \ +static inline void ii_read_lock_##name(struct inode *i) \ +{ \ + au_rw_read_lock_nested(&au_ii(i)->ii_rwsem, AuLsc_II_##lsc); \ +} + +#define AuWriteLockFunc(name, lsc) \ +static inline void ii_write_lock_##name(struct inode *i) \ +{ \ + au_rw_write_lock_nested(&au_ii(i)->ii_rwsem, AuLsc_II_##lsc); \ +} + +#define AuRWLockFuncs(name, lsc) \ + AuReadLockFunc(name, lsc) \ + AuWriteLockFunc(name, lsc) + +AuRWLockFuncs(child, CHILD); +AuRWLockFuncs(child2, CHILD2); +AuRWLockFuncs(child3, CHILD3); +AuRWLockFuncs(parent, PARENT); +AuRWLockFuncs(parent2, PARENT2); +AuRWLockFuncs(parent3, PARENT3); +AuRWLockFuncs(new_child, NEW_CHILD); + +#undef AuReadLockFunc +#undef AuWriteLockFunc +#undef AuRWLockFuncs + +/* + * ii_read_unlock, ii_write_unlock, ii_downgrade_lock + */ +AuSimpleUnlockRwsemFuncs(ii, struct inode *i, &au_ii(i)->ii_rwsem); + +#define IiMustNoWaiters(i) AuRwMustNoWaiters(&au_ii(i)->ii_rwsem) +#define IiMustAnyLock(i) AuRwMustAnyLock(&au_ii(i)->ii_rwsem) +#define IiMustWriteLock(i) AuRwMustWriteLock(&au_ii(i)->ii_rwsem) + +/* ---------------------------------------------------------------------- */ + +static inline void au_icntnr_init(struct au_icntnr *c) +{ +#ifdef CONFIG_AUFS_DEBUG + c->vfs_inode.i_mode = 0; +#endif +} + +static inline unsigned int au_iigen(struct inode *inode) +{ + return atomic_read(&au_ii(inode)->ii_generation); +} + +/* tiny test for inode number */ +/* tmpfs generation is too rough */ +static inline int au_test_higen(struct inode *inode, struct inode *h_inode) +{ + struct au_iinfo *iinfo; + + iinfo = au_ii(inode); + AuRwMustAnyLock(&iinfo->ii_rwsem); + return !(iinfo->ii_hsb1 == h_inode->i_sb + && iinfo->ii_higen == h_inode->i_generation); +} + +static inline void au_iigen_dec(struct inode *inode) +{ + atomic_dec(&au_ii(inode)->ii_generation); +} + +static inline int au_iigen_test(struct inode *inode, unsigned int sigen) +{ + int err; + + err = 0; + if (unlikely(inode && au_iigen(inode) != sigen)) + err = -EIO; + + return err; +} + +/* ---------------------------------------------------------------------- */ + +static inline aufs_bindex_t au_ii_br_id(struct inode *inode, + aufs_bindex_t bindex) +{ + IiMustAnyLock(inode); + return au_ii(inode)->ii_hinode[0 + bindex].hi_id; +} + +static inline aufs_bindex_t au_ibstart(struct inode *inode) +{ + IiMustAnyLock(inode); + return au_ii(inode)->ii_bstart; +} + +static inline aufs_bindex_t au_ibend(struct inode *inode) +{ + IiMustAnyLock(inode); + return au_ii(inode)->ii_bend; +} + +static inline struct au_vdir *au_ivdir(struct inode *inode) +{ + IiMustAnyLock(inode); + return au_ii(inode)->ii_vdir; +} + +static inline struct dentry *au_hi_wh(struct inode *inode, aufs_bindex_t bindex) +{ + IiMustAnyLock(inode); + return au_ii(inode)->ii_hinode[0 + bindex].hi_whdentry; +} + +static inline void au_set_ibstart(struct inode *inode, aufs_bindex_t bindex) +{ + IiMustWriteLock(inode); + au_ii(inode)->ii_bstart = bindex; +} + +static inline void au_set_ibend(struct inode *inode, aufs_bindex_t bindex) +{ + IiMustWriteLock(inode); + au_ii(inode)->ii_bend = bindex; +} + +static inline void au_set_ivdir(struct inode *inode, struct au_vdir *vdir) +{ + IiMustWriteLock(inode); + au_ii(inode)->ii_vdir = vdir; +} + +static inline struct au_hinode *au_hi(struct inode *inode, aufs_bindex_t bindex) +{ + IiMustAnyLock(inode); + return au_ii(inode)->ii_hinode + bindex; +} + +/* ---------------------------------------------------------------------- */ + +static inline struct dentry *au_pinned_parent(struct au_pin *pin) +{ + if (pin) + return pin->parent; + return NULL; +} + +static inline struct inode *au_pinned_h_dir(struct au_pin *pin) +{ + if (pin && pin->hdir) + return pin->hdir->hi_inode; + return NULL; +} + +static inline struct au_hinode *au_pinned_hdir(struct au_pin *pin) +{ + if (pin) + return pin->hdir; + return NULL; +} + +static inline void au_pin_set_dentry(struct au_pin *pin, struct dentry *dentry) +{ + if (pin) + pin->dentry = dentry; +} + +static inline void au_pin_set_parent_lflag(struct au_pin *pin, + unsigned char lflag) +{ + if (pin) { + if (lflag) + au_fset_pin(pin->flags, DI_LOCKED); + else + au_fclr_pin(pin->flags, DI_LOCKED); + } +} + +static inline void au_pin_set_parent(struct au_pin *pin, struct dentry *parent) +{ + if (pin) { + dput(pin->parent); + pin->parent = dget(parent); + } +} + +/* ---------------------------------------------------------------------- */ + +struct au_branch; +#ifdef CONFIG_AUFS_HNOTIFY +struct au_hnotify_op { + void (*ctl)(struct au_hinode *hinode, int do_set); + int (*alloc)(struct au_hinode *hinode); + void (*free)(struct au_hinode *hinode); + + void (*fin)(void); + int (*init)(void); + + int (*reset_br)(unsigned int udba, struct au_branch *br, int perm); + void (*fin_br)(struct au_branch *br); + int (*init_br)(struct au_branch *br, int perm); +}; + +/* hnotify.c */ +int au_hn_alloc(struct au_hinode *hinode, struct inode *inode); +void au_hn_free(struct au_hinode *hinode); +void au_hn_ctl(struct au_hinode *hinode, int do_set); +void au_hn_reset(struct inode *inode, unsigned int flags); +int au_hnotify(struct inode *h_dir, struct au_hnotify *hnotify, u32 mask, + struct qstr *h_child_qstr, struct inode *h_child_inode); +int au_hnotify_reset_br(unsigned int udba, struct au_branch *br, int perm); +int au_hnotify_init_br(struct au_branch *br, int perm); +void au_hnotify_fin_br(struct au_branch *br); +int __init au_hnotify_init(void); +void au_hnotify_fin(void); + +/* hfsnotify.c */ +extern const struct au_hnotify_op au_hnotify_op; + +static inline +void au_hn_init(struct au_hinode *hinode) +{ + hinode->hi_notify = NULL; +} + +static inline struct au_hnotify *au_hn(struct au_hinode *hinode) +{ + return hinode->hi_notify; +} + +#else +static inline +int au_hn_alloc(struct au_hinode *hinode __maybe_unused, + struct inode *inode __maybe_unused) +{ + return -EOPNOTSUPP; +} + +static inline struct au_hnotify *au_hn(struct au_hinode *hinode) +{ + return NULL; +} + +AuStubVoid(au_hn_free, struct au_hinode *hinode __maybe_unused) +AuStubVoid(au_hn_ctl, struct au_hinode *hinode __maybe_unused, + int do_set __maybe_unused) +AuStubVoid(au_hn_reset, struct inode *inode __maybe_unused, + unsigned int flags __maybe_unused) +AuStubInt0(au_hnotify_reset_br, unsigned int udba __maybe_unused, + struct au_branch *br __maybe_unused, + int perm __maybe_unused) +AuStubInt0(au_hnotify_init_br, struct au_branch *br __maybe_unused, + int perm __maybe_unused) +AuStubVoid(au_hnotify_fin_br, struct au_branch *br __maybe_unused) +AuStubInt0(__init au_hnotify_init, void) +AuStubVoid(au_hnotify_fin, void) +AuStubVoid(au_hn_init, struct au_hinode *hinode __maybe_unused) +#endif /* CONFIG_AUFS_HNOTIFY */ + +static inline void au_hn_suspend(struct au_hinode *hdir) +{ + au_hn_ctl(hdir, /*do_set*/0); +} + +static inline void au_hn_resume(struct au_hinode *hdir) +{ + au_hn_ctl(hdir, /*do_set*/1); +} + +static inline void au_hn_imtx_lock(struct au_hinode *hdir) +{ + mutex_lock(&hdir->hi_inode->i_mutex); + au_hn_suspend(hdir); +} + +static inline void au_hn_imtx_lock_nested(struct au_hinode *hdir, + unsigned int sc __maybe_unused) +{ + mutex_lock_nested(&hdir->hi_inode->i_mutex, sc); + au_hn_suspend(hdir); +} + +static inline void au_hn_imtx_unlock(struct au_hinode *hdir) +{ + au_hn_resume(hdir); + mutex_unlock(&hdir->hi_inode->i_mutex); +} + +#endif /* __KERNEL__ */ +#endif /* __AUFS_INODE_H__ */ diff --git a/ubuntu/aufs/ioctl.c b/ubuntu/aufs/ioctl.c new file mode 100644 index 000000000000..30a49dff8214 --- /dev/null +++ b/ubuntu/aufs/ioctl.c @@ -0,0 +1,196 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * ioctl + * plink-management and readdir in userspace. + * assist the pathconf(3) wrapper library. + */ + +#include "aufs.h" + +static int au_wbr_fd(struct path *path, struct aufs_wbr_fd __user *arg) +{ + int err, fd; + aufs_bindex_t wbi, bindex, bend; + struct file *h_file; + struct super_block *sb; + struct dentry *root; + struct au_branch *br; + struct aufs_wbr_fd wbrfd = { + .oflags = au_dir_roflags, + .brid = -1 + }; + const int valid = O_RDONLY | O_NONBLOCK | O_LARGEFILE | O_DIRECTORY + | O_NOATIME | O_CLOEXEC; + + AuDebugOn(wbrfd.oflags & ~valid); + + if (arg) { + err = copy_from_user(&wbrfd, arg, sizeof(wbrfd)); + if (unlikely(err)) { + err = -EFAULT; + goto out; + } + + err = -EINVAL; + AuDbg("wbrfd{0%o, %d}\n", wbrfd.oflags, wbrfd.brid); + wbrfd.oflags |= au_dir_roflags; + AuDbg("0%o\n", wbrfd.oflags); + if (unlikely(wbrfd.oflags & ~valid)) + goto out; + } + + fd = get_unused_fd(); + err = fd; + if (unlikely(fd < 0)) + goto out; + + h_file = ERR_PTR(-EINVAL); + wbi = 0; + br = NULL; + sb = path->dentry->d_sb; + root = sb->s_root; + aufs_read_lock(root, AuLock_IR); + bend = au_sbend(sb); + if (wbrfd.brid >= 0) { + wbi = au_br_index(sb, wbrfd.brid); + if (unlikely(wbi < 0 || wbi > bend)) + goto out_unlock; + } + + h_file = ERR_PTR(-ENOENT); + br = au_sbr(sb, wbi); + if (!au_br_writable(br->br_perm)) { + if (arg) + goto out_unlock; + + bindex = wbi + 1; + wbi = -1; + for (; bindex <= bend; bindex++) { + br = au_sbr(sb, bindex); + if (au_br_writable(br->br_perm)) { + wbi = bindex; + br = au_sbr(sb, wbi); + break; + } + } + } + AuDbg("wbi %d\n", wbi); + if (wbi >= 0) + h_file = au_h_open(root, wbi, wbrfd.oflags, NULL); + +out_unlock: + aufs_read_unlock(root, AuLock_IR); + err = PTR_ERR(h_file); + if (IS_ERR(h_file)) + goto out_fd; + + atomic_dec(&br->br_count); /* cf. au_h_open() */ + fd_install(fd, h_file); + err = fd; + goto out; /* success */ + +out_fd: + put_unused_fd(fd); +out: + AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +long aufs_ioctl_dir(struct file *file, unsigned int cmd, unsigned long arg) +{ + long err; + + switch (cmd) { + case AUFS_CTL_RDU: + case AUFS_CTL_RDU_INO: + err = au_rdu_ioctl(file, cmd, arg); + break; + + case AUFS_CTL_WBR_FD: + err = au_wbr_fd(&file->f_path, (void __user *)arg); + break; + + case AUFS_CTL_IBUSY: + err = au_ibusy_ioctl(file, arg); + break; + + default: + /* do not call the lower */ + AuDbg("0x%x\n", cmd); + err = -ENOTTY; + } + + AuTraceErr(err); + return err; +} + +long aufs_ioctl_nondir(struct file *file, unsigned int cmd, unsigned long arg) +{ + long err; + + switch (cmd) { + case AUFS_CTL_WBR_FD: + err = au_wbr_fd(&file->f_path, (void __user *)arg); + break; + + default: + /* do not call the lower */ + AuDbg("0x%x\n", cmd); + err = -ENOTTY; + } + + AuTraceErr(err); + return err; +} + +#ifdef CONFIG_COMPAT +long aufs_compat_ioctl_dir(struct file *file, unsigned int cmd, + unsigned long arg) +{ + long err; + + switch (cmd) { + case AUFS_CTL_RDU: + case AUFS_CTL_RDU_INO: + err = au_rdu_compat_ioctl(file, cmd, arg); + break; + + case AUFS_CTL_IBUSY: + err = au_ibusy_compat_ioctl(file, arg); + break; + + default: + err = aufs_ioctl_dir(file, cmd, arg); + } + + AuTraceErr(err); + return err; +} + +#if 0 /* unused yet */ +long aufs_compat_ioctl_nondir(struct file *file, unsigned int cmd, + unsigned long arg) +{ + return aufs_ioctl_nondir(file, cmd, (unsigned long)compat_ptr(arg)); +} +#endif +#endif diff --git a/ubuntu/aufs/loop.c b/ubuntu/aufs/loop.c new file mode 100644 index 000000000000..317f0e46de33 --- /dev/null +++ b/ubuntu/aufs/loop.c @@ -0,0 +1,133 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * support for loopback block device as a branch + */ + +#include <linux/loop.h> +#include "aufs.h" + +/* + * test if two lower dentries have overlapping branches. + */ +int au_test_loopback_overlap(struct super_block *sb, struct dentry *h_adding) +{ + struct super_block *h_sb; + struct loop_device *l; + + h_sb = h_adding->d_sb; + if (MAJOR(h_sb->s_dev) != LOOP_MAJOR) + return 0; + + l = h_sb->s_bdev->bd_disk->private_data; + h_adding = l->lo_backing_file->f_dentry; + /* + * h_adding can be local NFS. + * in this case aufs cannot detect the loop. + */ + if (unlikely(h_adding->d_sb == sb)) + return 1; + return !!au_test_subdir(h_adding, sb->s_root); +} + +/* true if a kernel thread named 'loop[0-9].*' accesses a file */ +int au_test_loopback_kthread(void) +{ + int ret; + struct task_struct *tsk = current; + + ret = 0; + if (tsk->flags & PF_KTHREAD) { + const char c = tsk->comm[4]; + ret = ('0' <= c && c <= '9' + && !strncmp(tsk->comm, "loop", 4)); + } + + return ret; +} + +/* ---------------------------------------------------------------------- */ + +#define au_warn_loopback_step 16 +static int au_warn_loopback_nelem = au_warn_loopback_step; +static unsigned long *au_warn_loopback_array; + +void au_warn_loopback(struct super_block *h_sb) +{ + int i, new_nelem; + unsigned long *a, magic; + static DEFINE_SPINLOCK(spin); + + magic = h_sb->s_magic; + spin_lock(&spin); + a = au_warn_loopback_array; + for (i = 0; i < au_warn_loopback_nelem && *a; i++) + if (a[i] == magic) { + spin_unlock(&spin); + return; + } + + /* h_sb is new to us, print it */ + if (i < au_warn_loopback_nelem) { + a[i] = magic; + goto pr; + } + + /* expand the array */ + new_nelem = au_warn_loopback_nelem + au_warn_loopback_step; + a = au_kzrealloc(au_warn_loopback_array, + au_warn_loopback_nelem * sizeof(unsigned long), + new_nelem * sizeof(unsigned long), GFP_ATOMIC); + if (a) { + au_warn_loopback_nelem = new_nelem; + au_warn_loopback_array = a; + a[i] = magic; + goto pr; + } + + spin_unlock(&spin); + AuWarn1("realloc failed, ignored\n"); + return; + +pr: + spin_unlock(&spin); + pr_warning("you may want to try another patch for loopback file " + "on %s(0x%lx) branch\n", au_sbtype(h_sb), magic); +} + +int au_loopback_init(void) +{ + int err; + struct super_block *sb __maybe_unused; + + AuDebugOn(sizeof(sb->s_magic) != sizeof(unsigned long)); + + err = 0; + au_warn_loopback_array = kcalloc(au_warn_loopback_step, + sizeof(unsigned long), GFP_NOFS); + if (unlikely(!au_warn_loopback_array)) + err = -ENOMEM; + + return err; +} + +void au_loopback_fin(void) +{ + kfree(au_warn_loopback_array); +} diff --git a/ubuntu/aufs/loop.h b/ubuntu/aufs/loop.h new file mode 100644 index 000000000000..b7af6a73cad8 --- /dev/null +++ b/ubuntu/aufs/loop.h @@ -0,0 +1,50 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * support for loopback mount as a branch + */ + +#ifndef __AUFS_LOOP_H__ +#define __AUFS_LOOP_H__ + +#ifdef __KERNEL__ + +struct dentry; +struct super_block; + +#ifdef CONFIG_AUFS_BDEV_LOOP +/* loop.c */ +int au_test_loopback_overlap(struct super_block *sb, struct dentry *h_adding); +int au_test_loopback_kthread(void); +void au_warn_loopback(struct super_block *h_sb); + +int au_loopback_init(void); +void au_loopback_fin(void); +#else +AuStubInt0(au_test_loopback_overlap, struct super_block *sb, + struct dentry *h_adding) +AuStubInt0(au_test_loopback_kthread, void) +AuStubVoid(au_warn_loopback, struct super_block *h_sb) + +AuStubInt0(au_loopback_init, void) +AuStubVoid(au_loopback_fin, void) +#endif /* BLK_DEV_LOOP */ + +#endif /* __KERNEL__ */ +#endif /* __AUFS_LOOP_H__ */ diff --git a/ubuntu/aufs/magic.mk b/ubuntu/aufs/magic.mk new file mode 100644 index 000000000000..3e6387b01b49 --- /dev/null +++ b/ubuntu/aufs/magic.mk @@ -0,0 +1,54 @@ + +# defined in ${srctree}/fs/fuse/inode.c +# tristate +ifdef CONFIG_FUSE_FS +ccflags-y += -DFUSE_SUPER_MAGIC=0x65735546 +endif + +# defined in ${srctree}/fs/ocfs2/ocfs2_fs.h +# tristate +ifdef CONFIG_OCFS2_FS +ccflags-y += -DOCFS2_SUPER_MAGIC=0x7461636f +endif + +# defined in ${srctree}/fs/ocfs2/dlm/userdlm.h +# tristate +ifdef CONFIG_OCFS2_FS_O2CB +ccflags-y += -DDLMFS_MAGIC=0x76a9f425 +endif + +# defined in ${srctree}/fs/cifs/cifsfs.c +# tristate +ifdef CONFIG_CIFS_FS +ccflags-y += -DCIFS_MAGIC_NUMBER=0xFF534D42 +endif + +# defined in ${srctree}/fs/xfs/xfs_sb.h +# tristate +ifdef CONFIG_XFS_FS +ccflags-y += -DXFS_SB_MAGIC=0x58465342 +endif + +# defined in ${srctree}/fs/configfs/mount.c +# tristate +ifdef CONFIG_CONFIGFS_FS +ccflags-y += -DCONFIGFS_MAGIC=0x62656570 +endif + +# defined in ${srctree}/fs/9p/v9fs.h +# tristate +ifdef CONFIG_9P_FS +ccflags-y += -DV9FS_MAGIC=0x01021997 +endif + +# defined in ${srctree}/fs/ubifs/ubifs.h +# tristate +ifdef CONFIG_UBIFS_FS +ccflags-y += -DUBIFS_SUPER_MAGIC=0x24051905 +endif + +# defined in ${srctree}/fs/hfsplus/hfsplus_raw.h +# tristate +ifdef CONFIG_HFSPLUS_FS +ccflags-y += -DHFSPLUS_SUPER_MAGIC=0x482b +endif diff --git a/ubuntu/aufs/module.c b/ubuntu/aufs/module.c new file mode 100644 index 000000000000..ef288b867244 --- /dev/null +++ b/ubuntu/aufs/module.c @@ -0,0 +1,195 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * module global variables and operations + */ + +#include <linux/module.h> +#include <linux/seq_file.h> +#include "aufs.h" + +void *au_kzrealloc(void *p, unsigned int nused, unsigned int new_sz, gfp_t gfp) +{ + if (new_sz <= nused) + return p; + + p = krealloc(p, new_sz, gfp); + if (p) + memset(p + nused, 0, new_sz - nused); + return p; +} + +/* ---------------------------------------------------------------------- */ + +/* + * aufs caches + */ +struct kmem_cache *au_cachep[AuCache_Last]; +static int __init au_cache_init(void) +{ + au_cachep[AuCache_DINFO] = AuCacheCtor(au_dinfo, au_di_init_once); + if (au_cachep[AuCache_DINFO]) + /* SLAB_DESTROY_BY_RCU */ + au_cachep[AuCache_ICNTNR] = AuCacheCtor(au_icntnr, + au_icntnr_init_once); + if (au_cachep[AuCache_ICNTNR]) + au_cachep[AuCache_FINFO] = AuCacheCtor(au_finfo, + au_fi_init_once); + if (au_cachep[AuCache_FINFO]) + au_cachep[AuCache_VDIR] = AuCache(au_vdir); + if (au_cachep[AuCache_VDIR]) + au_cachep[AuCache_DEHSTR] = AuCache(au_vdir_dehstr); + if (au_cachep[AuCache_DEHSTR]) + return 0; + + return -ENOMEM; +} + +static void au_cache_fin(void) +{ + int i; + + /* including AuCache_HNOTIFY */ + for (i = 0; i < AuCache_Last; i++) + if (au_cachep[i]) { + kmem_cache_destroy(au_cachep[i]); + au_cachep[i] = NULL; + } +} + +/* ---------------------------------------------------------------------- */ + +int au_dir_roflags; + +#ifdef CONFIG_AUFS_SBILIST +/* + * iterate_supers_type() doesn't protect us from + * remounting (branch management) + */ +struct au_splhead au_sbilist; +#endif + +struct lock_class_key au_lc_key[AuLcKey_Last]; + +/* + * functions for module interface. + */ +MODULE_LICENSE("GPL"); +/* MODULE_LICENSE("GPL v2"); */ +MODULE_AUTHOR("Junjiro R. Okajima <aufs-users@lists.sourceforge.net>"); +MODULE_DESCRIPTION(AUFS_NAME + " -- Advanced multi layered unification filesystem"); +MODULE_VERSION(AUFS_VERSION); + +/* this module parameter has no meaning when SYSFS is disabled */ +int sysaufs_brs = 1; +MODULE_PARM_DESC(brs, "use <sysfs>/fs/aufs/si_*/brN"); +module_param_named(brs, sysaufs_brs, int, S_IRUGO); + +/* ---------------------------------------------------------------------- */ + +static char au_esc_chars[0x20 + 3]; /* 0x01-0x20, backslash, del, and NULL */ + +int au_seq_path(struct seq_file *seq, struct path *path) +{ + return seq_path(seq, path, au_esc_chars); +} + +/* ---------------------------------------------------------------------- */ + +static int __init aufs_init(void) +{ + int err, i; + char *p; + + p = au_esc_chars; + for (i = 1; i <= ' '; i++) + *p++ = i; + *p++ = '\\'; + *p++ = '\x7f'; + *p = 0; + + au_dir_roflags = au_file_roflags(O_DIRECTORY | O_LARGEFILE); + + au_sbilist_init(); + sysaufs_brs_init(); + au_debug_init(); + au_dy_init(); + err = sysaufs_init(); + if (unlikely(err)) + goto out; + err = au_procfs_init(); + if (unlikely(err)) + goto out_sysaufs; + err = au_wkq_init(); + if (unlikely(err)) + goto out_procfs; + err = au_loopback_init(); + if (unlikely(err)) + goto out_wkq; + err = au_hnotify_init(); + if (unlikely(err)) + goto out_loopback; + err = au_sysrq_init(); + if (unlikely(err)) + goto out_hin; + err = au_cache_init(); + if (unlikely(err)) + goto out_sysrq; + err = register_filesystem(&aufs_fs_type); + if (unlikely(err)) + goto out_cache; + /* since we define pr_fmt, call printk directly */ + printk(KERN_INFO AUFS_NAME " " AUFS_VERSION "\n"); + goto out; /* success */ + +out_cache: + au_cache_fin(); +out_sysrq: + au_sysrq_fin(); +out_hin: + au_hnotify_fin(); +out_loopback: + au_loopback_fin(); +out_wkq: + au_wkq_fin(); +out_procfs: + au_procfs_fin(); +out_sysaufs: + sysaufs_fin(); + au_dy_fin(); +out: + return err; +} + +static void __exit aufs_exit(void) +{ + unregister_filesystem(&aufs_fs_type); + au_cache_fin(); + au_sysrq_fin(); + au_hnotify_fin(); + au_loopback_fin(); + au_wkq_fin(); + au_procfs_fin(); + sysaufs_fin(); + au_dy_fin(); +} + +module_init(aufs_init); +module_exit(aufs_exit); diff --git a/ubuntu/aufs/module.h b/ubuntu/aufs/module.h new file mode 100644 index 000000000000..242f4ea3e99c --- /dev/null +++ b/ubuntu/aufs/module.h @@ -0,0 +1,107 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * module initialization and module-global + */ + +#ifndef __AUFS_MODULE_H__ +#define __AUFS_MODULE_H__ + +#ifdef __KERNEL__ + +#include <linux/slab.h> + +struct path; +struct seq_file; + +/* module parameters */ +extern int sysaufs_brs; + +/* ---------------------------------------------------------------------- */ + +extern int au_dir_roflags; + +enum { + AuLcNonDir_FIINFO, + AuLcNonDir_DIINFO, + AuLcNonDir_IIINFO, + + AuLcDir_FIINFO, + AuLcDir_DIINFO, + AuLcDir_IIINFO, + + AuLcSymlink_DIINFO, + AuLcSymlink_IIINFO, + + AuLcKey_Last +}; +extern struct lock_class_key au_lc_key[AuLcKey_Last]; + +void *au_kzrealloc(void *p, unsigned int nused, unsigned int new_sz, gfp_t gfp); +int au_seq_path(struct seq_file *seq, struct path *path); + +#ifdef CONFIG_PROC_FS +/* procfs.c */ +int __init au_procfs_init(void); +void au_procfs_fin(void); +#else +AuStubInt0(au_procfs_init, void); +AuStubVoid(au_procfs_fin, void); +#endif + +/* ---------------------------------------------------------------------- */ + +/* kmem cache */ +enum { + AuCache_DINFO, + AuCache_ICNTNR, + AuCache_FINFO, + AuCache_VDIR, + AuCache_DEHSTR, +#ifdef CONFIG_AUFS_HNOTIFY + AuCache_HNOTIFY, +#endif + AuCache_Last +}; + +#define AuCacheFlags (SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD) +#define AuCache(type) KMEM_CACHE(type, AuCacheFlags) +#define AuCacheCtor(type, ctor) \ + kmem_cache_create(#type, sizeof(struct type), \ + __alignof__(struct type), AuCacheFlags, ctor) + +extern struct kmem_cache *au_cachep[]; + +#define AuCacheFuncs(name, index) \ +static inline struct au_##name *au_cache_alloc_##name(void) \ +{ return kmem_cache_alloc(au_cachep[AuCache_##index], GFP_NOFS); } \ +static inline void au_cache_free_##name(struct au_##name *p) \ +{ kmem_cache_free(au_cachep[AuCache_##index], p); } + +AuCacheFuncs(dinfo, DINFO); +AuCacheFuncs(icntnr, ICNTNR); +AuCacheFuncs(finfo, FINFO); +AuCacheFuncs(vdir, VDIR); +AuCacheFuncs(vdir_dehstr, DEHSTR); +#ifdef CONFIG_AUFS_HNOTIFY +AuCacheFuncs(hnotify, HNOTIFY); +#endif + +#endif /* __KERNEL__ */ +#endif /* __AUFS_MODULE_H__ */ diff --git a/ubuntu/aufs/opts.c b/ubuntu/aufs/opts.c new file mode 100644 index 000000000000..35c18ef307e9 --- /dev/null +++ b/ubuntu/aufs/opts.c @@ -0,0 +1,1677 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * mount options/flags + */ + +#include <linux/namei.h> +#include <linux/types.h> /* a distribution requires */ +#include <linux/parser.h> +#include "aufs.h" + +/* ---------------------------------------------------------------------- */ + +enum { + Opt_br, + Opt_add, Opt_del, Opt_mod, Opt_reorder, Opt_append, Opt_prepend, + Opt_idel, Opt_imod, Opt_ireorder, + Opt_dirwh, Opt_rdcache, Opt_rdblk, Opt_rdhash, Opt_rendir, + Opt_rdblk_def, Opt_rdhash_def, + Opt_xino, Opt_zxino, Opt_noxino, + Opt_trunc_xino, Opt_trunc_xino_v, Opt_notrunc_xino, + Opt_trunc_xino_path, Opt_itrunc_xino, + Opt_trunc_xib, Opt_notrunc_xib, + Opt_shwh, Opt_noshwh, + Opt_plink, Opt_noplink, Opt_list_plink, + Opt_udba, + Opt_dio, Opt_nodio, + /* Opt_lock, Opt_unlock, */ + Opt_cmd, Opt_cmd_args, + Opt_diropq_a, Opt_diropq_w, + Opt_warn_perm, Opt_nowarn_perm, + Opt_wbr_copyup, Opt_wbr_create, + Opt_refrof, Opt_norefrof, + Opt_verbose, Opt_noverbose, + Opt_sum, Opt_nosum, Opt_wsum, + Opt_tail, Opt_ignore, Opt_ignore_silent, Opt_err +}; + +static match_table_t options = { + {Opt_br, "br=%s"}, + {Opt_br, "br:%s"}, + + {Opt_add, "add=%d:%s"}, + {Opt_add, "add:%d:%s"}, + {Opt_add, "ins=%d:%s"}, + {Opt_add, "ins:%d:%s"}, + {Opt_append, "append=%s"}, + {Opt_append, "append:%s"}, + {Opt_prepend, "prepend=%s"}, + {Opt_prepend, "prepend:%s"}, + + {Opt_del, "del=%s"}, + {Opt_del, "del:%s"}, + /* {Opt_idel, "idel:%d"}, */ + {Opt_mod, "mod=%s"}, + {Opt_mod, "mod:%s"}, + /* {Opt_imod, "imod:%d:%s"}, */ + + {Opt_dirwh, "dirwh=%d"}, + + {Opt_xino, "xino=%s"}, + {Opt_noxino, "noxino"}, + {Opt_trunc_xino, "trunc_xino"}, + {Opt_trunc_xino_v, "trunc_xino_v=%d:%d"}, + {Opt_notrunc_xino, "notrunc_xino"}, + {Opt_trunc_xino_path, "trunc_xino=%s"}, + {Opt_itrunc_xino, "itrunc_xino=%d"}, + /* {Opt_zxino, "zxino=%s"}, */ + {Opt_trunc_xib, "trunc_xib"}, + {Opt_notrunc_xib, "notrunc_xib"}, + +#ifdef CONFIG_PROC_FS + {Opt_plink, "plink"}, +#else + {Opt_ignore_silent, "plink"}, +#endif + + {Opt_noplink, "noplink"}, + +#ifdef CONFIG_AUFS_DEBUG + {Opt_list_plink, "list_plink"}, +#endif + + {Opt_udba, "udba=%s"}, + + {Opt_dio, "dio"}, + {Opt_nodio, "nodio"}, + + {Opt_diropq_a, "diropq=always"}, + {Opt_diropq_a, "diropq=a"}, + {Opt_diropq_w, "diropq=whiteouted"}, + {Opt_diropq_w, "diropq=w"}, + + {Opt_warn_perm, "warn_perm"}, + {Opt_nowarn_perm, "nowarn_perm"}, + + /* keep them temporary */ + {Opt_ignore_silent, "coo=%s"}, + {Opt_ignore_silent, "nodlgt"}, + {Opt_ignore_silent, "nodirperm1"}, + {Opt_ignore_silent, "clean_plink"}, + +#ifdef CONFIG_AUFS_SHWH + {Opt_shwh, "shwh"}, +#endif + {Opt_noshwh, "noshwh"}, + + {Opt_rendir, "rendir=%d"}, + + {Opt_refrof, "refrof"}, + {Opt_norefrof, "norefrof"}, + + {Opt_verbose, "verbose"}, + {Opt_verbose, "v"}, + {Opt_noverbose, "noverbose"}, + {Opt_noverbose, "quiet"}, + {Opt_noverbose, "q"}, + {Opt_noverbose, "silent"}, + + {Opt_sum, "sum"}, + {Opt_nosum, "nosum"}, + {Opt_wsum, "wsum"}, + + {Opt_rdcache, "rdcache=%d"}, + {Opt_rdblk, "rdblk=%d"}, + {Opt_rdblk_def, "rdblk=def"}, + {Opt_rdhash, "rdhash=%d"}, + {Opt_rdhash_def, "rdhash=def"}, + + {Opt_wbr_create, "create=%s"}, + {Opt_wbr_create, "create_policy=%s"}, + {Opt_wbr_copyup, "cpup=%s"}, + {Opt_wbr_copyup, "copyup=%s"}, + {Opt_wbr_copyup, "copyup_policy=%s"}, + + /* internal use for the scripts */ + {Opt_ignore_silent, "si=%s"}, + + {Opt_br, "dirs=%s"}, + {Opt_ignore, "debug=%d"}, + {Opt_ignore, "delete=whiteout"}, + {Opt_ignore, "delete=all"}, + {Opt_ignore, "imap=%s"}, + + /* temporary workaround, due to old mount(8)? */ + {Opt_ignore_silent, "relatime"}, + + {Opt_err, NULL} +}; + +/* ---------------------------------------------------------------------- */ + +static const char *au_parser_pattern(int val, struct match_token *token) +{ + while (token->pattern) { + if (token->token == val) + return token->pattern; + token++; + } + BUG(); + return "??"; +} + +/* ---------------------------------------------------------------------- */ + +static match_table_t brperm = { + {AuBrPerm_RO, AUFS_BRPERM_RO}, + {AuBrPerm_RR, AUFS_BRPERM_RR}, + {AuBrPerm_RW, AUFS_BRPERM_RW}, + {0, NULL} +}; + +static match_table_t brrattr = { + {AuBrRAttr_WH, AUFS_BRRATTR_WH}, + {0, NULL} +}; + +static match_table_t brwattr = { + {AuBrWAttr_NoLinkWH, AUFS_BRWATTR_NLWH}, + {0, NULL} +}; + +#define AuBrStr_LONGEST AUFS_BRPERM_RW "+" AUFS_BRWATTR_NLWH + +static int br_attr_val(char *str, match_table_t table, substring_t args[]) +{ + int attr, v; + char *p; + + attr = 0; + do { + p = strchr(str, '+'); + if (p) + *p = 0; + v = match_token(str, table, args); + if (v) + attr |= v; + else { + if (p) + *p = '+'; + pr_warning("ignored branch attribute %s\n", str); + break; + } + if (p) + str = p + 1; + } while (p); + + return attr; +} + +static int noinline_for_stack br_perm_val(char *perm) +{ + int val; + char *p; + substring_t args[MAX_OPT_ARGS]; + + p = strchr(perm, '+'); + if (p) + *p = 0; + val = match_token(perm, brperm, args); + if (!val) { + if (p) + *p = '+'; + pr_warning("ignored branch permission %s\n", perm); + val = AuBrPerm_RO; + goto out; + } + if (!p) + goto out; + + switch (val) { + case AuBrPerm_RO: + case AuBrPerm_RR: + val |= br_attr_val(p + 1, brrattr, args); + break; + case AuBrPerm_RW: + val |= br_attr_val(p + 1, brwattr, args); + break; + } + +out: + return val; +} + +/* Caller should free the return value */ +char *au_optstr_br_perm(int brperm) +{ + char *p, a[sizeof(AuBrStr_LONGEST)]; + int sz; + +#define SetPerm(str) do { \ + sz = sizeof(str); \ + memcpy(a, str, sz); \ + p = a + sz - 1; \ + } while (0) + +#define AppendAttr(flag, str) do { \ + if (brperm & flag) { \ + sz = sizeof(str); \ + *p++ = '+'; \ + memcpy(p, str, sz); \ + p += sz - 1; \ + } \ + } while (0) + + switch (brperm & AuBrPerm_Mask) { + case AuBrPerm_RO: + SetPerm(AUFS_BRPERM_RO); + break; + case AuBrPerm_RR: + SetPerm(AUFS_BRPERM_RR); + break; + case AuBrPerm_RW: + SetPerm(AUFS_BRPERM_RW); + break; + default: + AuDebugOn(1); + } + + AppendAttr(AuBrRAttr_WH, AUFS_BRRATTR_WH); + AppendAttr(AuBrWAttr_NoLinkWH, AUFS_BRWATTR_NLWH); + + AuDebugOn(strlen(a) >= sizeof(a)); + return kstrdup(a, GFP_NOFS); +#undef SetPerm +#undef AppendAttr +} + +/* ---------------------------------------------------------------------- */ + +static match_table_t udbalevel = { + {AuOpt_UDBA_REVAL, "reval"}, + {AuOpt_UDBA_NONE, "none"}, +#ifdef CONFIG_AUFS_HNOTIFY + {AuOpt_UDBA_HNOTIFY, "notify"}, /* abstraction */ +#ifdef CONFIG_AUFS_HFSNOTIFY + {AuOpt_UDBA_HNOTIFY, "fsnotify"}, +#endif +#endif + {-1, NULL} +}; + +static int noinline_for_stack udba_val(char *str) +{ + substring_t args[MAX_OPT_ARGS]; + + return match_token(str, udbalevel, args); +} + +const char *au_optstr_udba(int udba) +{ + return au_parser_pattern(udba, (void *)udbalevel); +} + +/* ---------------------------------------------------------------------- */ + +static match_table_t au_wbr_create_policy = { + {AuWbrCreate_TDP, "tdp"}, + {AuWbrCreate_TDP, "top-down-parent"}, + {AuWbrCreate_RR, "rr"}, + {AuWbrCreate_RR, "round-robin"}, + {AuWbrCreate_MFS, "mfs"}, + {AuWbrCreate_MFS, "most-free-space"}, + {AuWbrCreate_MFSV, "mfs:%d"}, + {AuWbrCreate_MFSV, "most-free-space:%d"}, + + {AuWbrCreate_MFSRR, "mfsrr:%d"}, + {AuWbrCreate_MFSRRV, "mfsrr:%d:%d"}, + {AuWbrCreate_PMFS, "pmfs"}, + {AuWbrCreate_PMFSV, "pmfs:%d"}, + + {-1, NULL} +}; + +/* + * cf. linux/lib/parser.c and cmdline.c + * gave up calling memparse() since it uses simple_strtoull() instead of + * kstrto...(). + */ +static int noinline_for_stack +au_match_ull(substring_t *s, unsigned long long *result) +{ + int err; + unsigned int len; + char a[32]; + + err = -ERANGE; + len = s->to - s->from; + if (len + 1 <= sizeof(a)) { + memcpy(a, s->from, len); + a[len] = '\0'; + err = kstrtoull(a, 0, result); + } + return err; +} + +static int au_wbr_mfs_wmark(substring_t *arg, char *str, + struct au_opt_wbr_create *create) +{ + int err; + unsigned long long ull; + + err = 0; + if (!au_match_ull(arg, &ull)) + create->mfsrr_watermark = ull; + else { + pr_err("bad integer in %s\n", str); + err = -EINVAL; + } + + return err; +} + +static int au_wbr_mfs_sec(substring_t *arg, char *str, + struct au_opt_wbr_create *create) +{ + int n, err; + + err = 0; + if (!match_int(arg, &n) && 0 <= n && n <= AUFS_MFS_MAX_SEC) + create->mfs_second = n; + else { + pr_err("bad integer in %s\n", str); + err = -EINVAL; + } + + return err; +} + +static int noinline_for_stack +au_wbr_create_val(char *str, struct au_opt_wbr_create *create) +{ + int err, e; + substring_t args[MAX_OPT_ARGS]; + + err = match_token(str, au_wbr_create_policy, args); + create->wbr_create = err; + switch (err) { + case AuWbrCreate_MFSRRV: + e = au_wbr_mfs_wmark(&args[0], str, create); + if (!e) + e = au_wbr_mfs_sec(&args[1], str, create); + if (unlikely(e)) + err = e; + break; + case AuWbrCreate_MFSRR: + e = au_wbr_mfs_wmark(&args[0], str, create); + if (unlikely(e)) { + err = e; + break; + } + /*FALLTHROUGH*/ + case AuWbrCreate_MFS: + case AuWbrCreate_PMFS: + create->mfs_second = AUFS_MFS_DEF_SEC; + break; + case AuWbrCreate_MFSV: + case AuWbrCreate_PMFSV: + e = au_wbr_mfs_sec(&args[0], str, create); + if (unlikely(e)) + err = e; + break; + } + + return err; +} + +const char *au_optstr_wbr_create(int wbr_create) +{ + return au_parser_pattern(wbr_create, (void *)au_wbr_create_policy); +} + +static match_table_t au_wbr_copyup_policy = { + {AuWbrCopyup_TDP, "tdp"}, + {AuWbrCopyup_TDP, "top-down-parent"}, + {AuWbrCopyup_BUP, "bup"}, + {AuWbrCopyup_BUP, "bottom-up-parent"}, + {AuWbrCopyup_BU, "bu"}, + {AuWbrCopyup_BU, "bottom-up"}, + {-1, NULL} +}; + +static int noinline_for_stack au_wbr_copyup_val(char *str) +{ + substring_t args[MAX_OPT_ARGS]; + + return match_token(str, au_wbr_copyup_policy, args); +} + +const char *au_optstr_wbr_copyup(int wbr_copyup) +{ + return au_parser_pattern(wbr_copyup, (void *)au_wbr_copyup_policy); +} + +/* ---------------------------------------------------------------------- */ + +static const int lkup_dirflags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY; + +static void dump_opts(struct au_opts *opts) +{ +#ifdef CONFIG_AUFS_DEBUG + /* reduce stack space */ + union { + struct au_opt_add *add; + struct au_opt_del *del; + struct au_opt_mod *mod; + struct au_opt_xino *xino; + struct au_opt_xino_itrunc *xino_itrunc; + struct au_opt_wbr_create *create; + } u; + struct au_opt *opt; + + opt = opts->opt; + while (opt->type != Opt_tail) { + switch (opt->type) { + case Opt_add: + u.add = &opt->add; + AuDbg("add {b%d, %s, 0x%x, %p}\n", + u.add->bindex, u.add->pathname, u.add->perm, + u.add->path.dentry); + break; + case Opt_del: + case Opt_idel: + u.del = &opt->del; + AuDbg("del {%s, %p}\n", + u.del->pathname, u.del->h_path.dentry); + break; + case Opt_mod: + case Opt_imod: + u.mod = &opt->mod; + AuDbg("mod {%s, 0x%x, %p}\n", + u.mod->path, u.mod->perm, u.mod->h_root); + break; + case Opt_append: + u.add = &opt->add; + AuDbg("append {b%d, %s, 0x%x, %p}\n", + u.add->bindex, u.add->pathname, u.add->perm, + u.add->path.dentry); + break; + case Opt_prepend: + u.add = &opt->add; + AuDbg("prepend {b%d, %s, 0x%x, %p}\n", + u.add->bindex, u.add->pathname, u.add->perm, + u.add->path.dentry); + break; + case Opt_dirwh: + AuDbg("dirwh %d\n", opt->dirwh); + break; + case Opt_rdcache: + AuDbg("rdcache %d\n", opt->rdcache); + break; + case Opt_rdblk: + AuDbg("rdblk %u\n", opt->rdblk); + break; + case Opt_rdblk_def: + AuDbg("rdblk_def\n"); + break; + case Opt_rdhash: + AuDbg("rdhash %u\n", opt->rdhash); + break; + case Opt_rdhash_def: + AuDbg("rdhash_def\n"); + break; + case Opt_xino: + u.xino = &opt->xino; + AuDbg("xino {%s %.*s}\n", + u.xino->path, + AuDLNPair(u.xino->file->f_dentry)); + break; + case Opt_trunc_xino: + AuLabel(trunc_xino); + break; + case Opt_notrunc_xino: + AuLabel(notrunc_xino); + break; + case Opt_trunc_xino_path: + case Opt_itrunc_xino: + u.xino_itrunc = &opt->xino_itrunc; + AuDbg("trunc_xino %d\n", u.xino_itrunc->bindex); + break; + + case Opt_noxino: + AuLabel(noxino); + break; + case Opt_trunc_xib: + AuLabel(trunc_xib); + break; + case Opt_notrunc_xib: + AuLabel(notrunc_xib); + break; + case Opt_shwh: + AuLabel(shwh); + break; + case Opt_noshwh: + AuLabel(noshwh); + break; + case Opt_plink: + AuLabel(plink); + break; + case Opt_noplink: + AuLabel(noplink); + break; + case Opt_list_plink: + AuLabel(list_plink); + break; + case Opt_udba: + AuDbg("udba %d, %s\n", + opt->udba, au_optstr_udba(opt->udba)); + break; + case Opt_dio: + AuLabel(dio); + break; + case Opt_nodio: + AuLabel(nodio); + break; + case Opt_diropq_a: + AuLabel(diropq_a); + break; + case Opt_diropq_w: + AuLabel(diropq_w); + break; + case Opt_warn_perm: + AuLabel(warn_perm); + break; + case Opt_nowarn_perm: + AuLabel(nowarn_perm); + break; + case Opt_refrof: + AuLabel(refrof); + break; + case Opt_norefrof: + AuLabel(norefrof); + break; + case Opt_verbose: + AuLabel(verbose); + break; + case Opt_noverbose: + AuLabel(noverbose); + break; + case Opt_sum: + AuLabel(sum); + break; + case Opt_nosum: + AuLabel(nosum); + break; + case Opt_wsum: + AuLabel(wsum); + break; + case Opt_wbr_create: + u.create = &opt->wbr_create; + AuDbg("create %d, %s\n", u.create->wbr_create, + au_optstr_wbr_create(u.create->wbr_create)); + switch (u.create->wbr_create) { + case AuWbrCreate_MFSV: + case AuWbrCreate_PMFSV: + AuDbg("%d sec\n", u.create->mfs_second); + break; + case AuWbrCreate_MFSRR: + AuDbg("%llu watermark\n", + u.create->mfsrr_watermark); + break; + case AuWbrCreate_MFSRRV: + AuDbg("%llu watermark, %d sec\n", + u.create->mfsrr_watermark, + u.create->mfs_second); + break; + } + break; + case Opt_wbr_copyup: + AuDbg("copyup %d, %s\n", opt->wbr_copyup, + au_optstr_wbr_copyup(opt->wbr_copyup)); + break; + default: + BUG(); + } + opt++; + } +#endif +} + +void au_opts_free(struct au_opts *opts) +{ + struct au_opt *opt; + + opt = opts->opt; + while (opt->type != Opt_tail) { + switch (opt->type) { + case Opt_add: + case Opt_append: + case Opt_prepend: + path_put(&opt->add.path); + break; + case Opt_del: + case Opt_idel: + path_put(&opt->del.h_path); + break; + case Opt_mod: + case Opt_imod: + dput(opt->mod.h_root); + break; + case Opt_xino: + fput(opt->xino.file); + break; + } + opt++; + } +} + +static int opt_add(struct au_opt *opt, char *opt_str, unsigned long sb_flags, + aufs_bindex_t bindex) +{ + int err; + struct au_opt_add *add = &opt->add; + char *p; + + add->bindex = bindex; + add->perm = AuBrPerm_RO; + add->pathname = opt_str; + p = strchr(opt_str, '='); + if (p) { + *p++ = 0; + if (*p) + add->perm = br_perm_val(p); + } + + err = vfsub_kern_path(add->pathname, lkup_dirflags, &add->path); + if (!err) { + if (!p) { + add->perm = AuBrPerm_RO; + if (au_test_fs_rr(add->path.dentry->d_sb)) + add->perm = AuBrPerm_RR; + else if (!bindex && !(sb_flags & MS_RDONLY)) + add->perm = AuBrPerm_RW; + } + opt->type = Opt_add; + goto out; + } + pr_err("lookup failed %s (%d)\n", add->pathname, err); + err = -EINVAL; + +out: + return err; +} + +static int au_opts_parse_del(struct au_opt_del *del, substring_t args[]) +{ + int err; + + del->pathname = args[0].from; + AuDbg("del path %s\n", del->pathname); + + err = vfsub_kern_path(del->pathname, lkup_dirflags, &del->h_path); + if (unlikely(err)) + pr_err("lookup failed %s (%d)\n", del->pathname, err); + + return err; +} + +#if 0 /* reserved for future use */ +static int au_opts_parse_idel(struct super_block *sb, aufs_bindex_t bindex, + struct au_opt_del *del, substring_t args[]) +{ + int err; + struct dentry *root; + + err = -EINVAL; + root = sb->s_root; + aufs_read_lock(root, AuLock_FLUSH); + if (bindex < 0 || au_sbend(sb) < bindex) { + pr_err("out of bounds, %d\n", bindex); + goto out; + } + + err = 0; + del->h_path.dentry = dget(au_h_dptr(root, bindex)); + del->h_path.mnt = mntget(au_sbr_mnt(sb, bindex)); + +out: + aufs_read_unlock(root, !AuLock_IR); + return err; +} +#endif + +static int noinline_for_stack +au_opts_parse_mod(struct au_opt_mod *mod, substring_t args[]) +{ + int err; + struct path path; + char *p; + + err = -EINVAL; + mod->path = args[0].from; + p = strchr(mod->path, '='); + if (unlikely(!p)) { + pr_err("no permssion %s\n", args[0].from); + goto out; + } + + *p++ = 0; + err = vfsub_kern_path(mod->path, lkup_dirflags, &path); + if (unlikely(err)) { + pr_err("lookup failed %s (%d)\n", mod->path, err); + goto out; + } + + mod->perm = br_perm_val(p); + AuDbg("mod path %s, perm 0x%x, %s\n", mod->path, mod->perm, p); + mod->h_root = dget(path.dentry); + path_put(&path); + +out: + return err; +} + +#if 0 /* reserved for future use */ +static int au_opts_parse_imod(struct super_block *sb, aufs_bindex_t bindex, + struct au_opt_mod *mod, substring_t args[]) +{ + int err; + struct dentry *root; + + err = -EINVAL; + root = sb->s_root; + aufs_read_lock(root, AuLock_FLUSH); + if (bindex < 0 || au_sbend(sb) < bindex) { + pr_err("out of bounds, %d\n", bindex); + goto out; + } + + err = 0; + mod->perm = br_perm_val(args[1].from); + AuDbg("mod path %s, perm 0x%x, %s\n", + mod->path, mod->perm, args[1].from); + mod->h_root = dget(au_h_dptr(root, bindex)); + +out: + aufs_read_unlock(root, !AuLock_IR); + return err; +} +#endif + +static int au_opts_parse_xino(struct super_block *sb, struct au_opt_xino *xino, + substring_t args[]) +{ + int err; + struct file *file; + + file = au_xino_create(sb, args[0].from, /*silent*/0); + err = PTR_ERR(file); + if (IS_ERR(file)) + goto out; + + err = -EINVAL; + if (unlikely(file->f_dentry->d_sb == sb)) { + fput(file); + pr_err("%s must be outside\n", args[0].from); + goto out; + } + + err = 0; + xino->file = file; + xino->path = args[0].from; + +out: + return err; +} + +static int noinline_for_stack +au_opts_parse_xino_itrunc_path(struct super_block *sb, + struct au_opt_xino_itrunc *xino_itrunc, + substring_t args[]) +{ + int err; + aufs_bindex_t bend, bindex; + struct path path; + struct dentry *root; + + err = vfsub_kern_path(args[0].from, lkup_dirflags, &path); + if (unlikely(err)) { + pr_err("lookup failed %s (%d)\n", args[0].from, err); + goto out; + } + + xino_itrunc->bindex = -1; + root = sb->s_root; + aufs_read_lock(root, AuLock_FLUSH); + bend = au_sbend(sb); + for (bindex = 0; bindex <= bend; bindex++) { + if (au_h_dptr(root, bindex) == path.dentry) { + xino_itrunc->bindex = bindex; + break; + } + } + aufs_read_unlock(root, !AuLock_IR); + path_put(&path); + + if (unlikely(xino_itrunc->bindex < 0)) { + pr_err("no such branch %s\n", args[0].from); + err = -EINVAL; + } + +out: + return err; +} + +/* called without aufs lock */ +int au_opts_parse(struct super_block *sb, char *str, struct au_opts *opts) +{ + int err, n, token; + aufs_bindex_t bindex; + unsigned char skipped; + struct dentry *root; + struct au_opt *opt, *opt_tail; + char *opt_str; + /* reduce the stack space */ + union { + struct au_opt_xino_itrunc *xino_itrunc; + struct au_opt_wbr_create *create; + } u; + struct { + substring_t args[MAX_OPT_ARGS]; + } *a; + + err = -ENOMEM; + a = kmalloc(sizeof(*a), GFP_NOFS); + if (unlikely(!a)) + goto out; + + root = sb->s_root; + err = 0; + bindex = 0; + opt = opts->opt; + opt_tail = opt + opts->max_opt - 1; + opt->type = Opt_tail; + while (!err && (opt_str = strsep(&str, ",")) && *opt_str) { + err = -EINVAL; + skipped = 0; + token = match_token(opt_str, options, a->args); + switch (token) { + case Opt_br: + err = 0; + while (!err && (opt_str = strsep(&a->args[0].from, ":")) + && *opt_str) { + err = opt_add(opt, opt_str, opts->sb_flags, + bindex++); + if (unlikely(!err && ++opt > opt_tail)) { + err = -E2BIG; + break; + } + opt->type = Opt_tail; + skipped = 1; + } + break; + case Opt_add: + if (unlikely(match_int(&a->args[0], &n))) { + pr_err("bad integer in %s\n", opt_str); + break; + } + bindex = n; + err = opt_add(opt, a->args[1].from, opts->sb_flags, + bindex); + if (!err) + opt->type = token; + break; + case Opt_append: + err = opt_add(opt, a->args[0].from, opts->sb_flags, + /*dummy bindex*/1); + if (!err) + opt->type = token; + break; + case Opt_prepend: + err = opt_add(opt, a->args[0].from, opts->sb_flags, + /*bindex*/0); + if (!err) + opt->type = token; + break; + case Opt_del: + err = au_opts_parse_del(&opt->del, a->args); + if (!err) + opt->type = token; + break; +#if 0 /* reserved for future use */ + case Opt_idel: + del->pathname = "(indexed)"; + if (unlikely(match_int(&args[0], &n))) { + pr_err("bad integer in %s\n", opt_str); + break; + } + err = au_opts_parse_idel(sb, n, &opt->del, a->args); + if (!err) + opt->type = token; + break; +#endif + case Opt_mod: + err = au_opts_parse_mod(&opt->mod, a->args); + if (!err) + opt->type = token; + break; +#ifdef IMOD /* reserved for future use */ + case Opt_imod: + u.mod->path = "(indexed)"; + if (unlikely(match_int(&a->args[0], &n))) { + pr_err("bad integer in %s\n", opt_str); + break; + } + err = au_opts_parse_imod(sb, n, &opt->mod, a->args); + if (!err) + opt->type = token; + break; +#endif + case Opt_xino: + err = au_opts_parse_xino(sb, &opt->xino, a->args); + if (!err) + opt->type = token; + break; + + case Opt_trunc_xino_path: + err = au_opts_parse_xino_itrunc_path + (sb, &opt->xino_itrunc, a->args); + if (!err) + opt->type = token; + break; + + case Opt_itrunc_xino: + u.xino_itrunc = &opt->xino_itrunc; + if (unlikely(match_int(&a->args[0], &n))) { + pr_err("bad integer in %s\n", opt_str); + break; + } + u.xino_itrunc->bindex = n; + aufs_read_lock(root, AuLock_FLUSH); + if (n < 0 || au_sbend(sb) < n) { + pr_err("out of bounds, %d\n", n); + aufs_read_unlock(root, !AuLock_IR); + break; + } + aufs_read_unlock(root, !AuLock_IR); + err = 0; + opt->type = token; + break; + + case Opt_dirwh: + if (unlikely(match_int(&a->args[0], &opt->dirwh))) + break; + err = 0; + opt->type = token; + break; + + case Opt_rdcache: + if (unlikely(match_int(&a->args[0], &n))) { + pr_err("bad integer in %s\n", opt_str); + break; + } + if (unlikely(n > AUFS_RDCACHE_MAX)) { + pr_err("rdcache must be smaller than %d\n", + AUFS_RDCACHE_MAX); + break; + } + opt->rdcache = n; + err = 0; + opt->type = token; + break; + case Opt_rdblk: + if (unlikely(match_int(&a->args[0], &n) + || n < 0 + || n > KMALLOC_MAX_SIZE)) { + pr_err("bad integer in %s\n", opt_str); + break; + } + if (unlikely(n && n < NAME_MAX)) { + pr_err("rdblk must be larger than %d\n", + NAME_MAX); + break; + } + opt->rdblk = n; + err = 0; + opt->type = token; + break; + case Opt_rdhash: + if (unlikely(match_int(&a->args[0], &n) + || n < 0 + || n * sizeof(struct hlist_head) + > KMALLOC_MAX_SIZE)) { + pr_err("bad integer in %s\n", opt_str); + break; + } + opt->rdhash = n; + err = 0; + opt->type = token; + break; + + case Opt_trunc_xino: + case Opt_notrunc_xino: + case Opt_noxino: + case Opt_trunc_xib: + case Opt_notrunc_xib: + case Opt_shwh: + case Opt_noshwh: + case Opt_plink: + case Opt_noplink: + case Opt_list_plink: + case Opt_dio: + case Opt_nodio: + case Opt_diropq_a: + case Opt_diropq_w: + case Opt_warn_perm: + case Opt_nowarn_perm: + case Opt_refrof: + case Opt_norefrof: + case Opt_verbose: + case Opt_noverbose: + case Opt_sum: + case Opt_nosum: + case Opt_wsum: + case Opt_rdblk_def: + case Opt_rdhash_def: + err = 0; + opt->type = token; + break; + + case Opt_udba: + opt->udba = udba_val(a->args[0].from); + if (opt->udba >= 0) { + err = 0; + opt->type = token; + } else + pr_err("wrong value, %s\n", opt_str); + break; + + case Opt_wbr_create: + u.create = &opt->wbr_create; + u.create->wbr_create + = au_wbr_create_val(a->args[0].from, u.create); + if (u.create->wbr_create >= 0) { + err = 0; + opt->type = token; + } else + pr_err("wrong value, %s\n", opt_str); + break; + case Opt_wbr_copyup: + opt->wbr_copyup = au_wbr_copyup_val(a->args[0].from); + if (opt->wbr_copyup >= 0) { + err = 0; + opt->type = token; + } else + pr_err("wrong value, %s\n", opt_str); + break; + + case Opt_ignore: + pr_warning("ignored %s\n", opt_str); + /*FALLTHROUGH*/ + case Opt_ignore_silent: + skipped = 1; + err = 0; + break; + case Opt_err: + pr_err("unknown option %s\n", opt_str); + break; + } + + if (!err && !skipped) { + if (unlikely(++opt > opt_tail)) { + err = -E2BIG; + opt--; + opt->type = Opt_tail; + break; + } + opt->type = Opt_tail; + } + } + + kfree(a); + dump_opts(opts); + if (unlikely(err)) + au_opts_free(opts); + +out: + return err; +} + +static int au_opt_wbr_create(struct super_block *sb, + struct au_opt_wbr_create *create) +{ + int err; + struct au_sbinfo *sbinfo; + + SiMustWriteLock(sb); + + err = 1; /* handled */ + sbinfo = au_sbi(sb); + if (sbinfo->si_wbr_create_ops->fin) { + err = sbinfo->si_wbr_create_ops->fin(sb); + if (!err) + err = 1; + } + + sbinfo->si_wbr_create = create->wbr_create; + sbinfo->si_wbr_create_ops = au_wbr_create_ops + create->wbr_create; + switch (create->wbr_create) { + case AuWbrCreate_MFSRRV: + case AuWbrCreate_MFSRR: + sbinfo->si_wbr_mfs.mfsrr_watermark = create->mfsrr_watermark; + /*FALLTHROUGH*/ + case AuWbrCreate_MFS: + case AuWbrCreate_MFSV: + case AuWbrCreate_PMFS: + case AuWbrCreate_PMFSV: + sbinfo->si_wbr_mfs.mfs_expire + = msecs_to_jiffies(create->mfs_second * MSEC_PER_SEC); + break; + } + + if (sbinfo->si_wbr_create_ops->init) + sbinfo->si_wbr_create_ops->init(sb); /* ignore */ + + return err; +} + +/* + * returns, + * plus: processed without an error + * zero: unprocessed + */ +static int au_opt_simple(struct super_block *sb, struct au_opt *opt, + struct au_opts *opts) +{ + int err; + struct au_sbinfo *sbinfo; + + SiMustWriteLock(sb); + + err = 1; /* handled */ + sbinfo = au_sbi(sb); + switch (opt->type) { + case Opt_udba: + sbinfo->si_mntflags &= ~AuOptMask_UDBA; + sbinfo->si_mntflags |= opt->udba; + opts->given_udba |= opt->udba; + break; + + case Opt_plink: + au_opt_set(sbinfo->si_mntflags, PLINK); + break; + case Opt_noplink: + if (au_opt_test(sbinfo->si_mntflags, PLINK)) + au_plink_put(sb, /*verbose*/1); + au_opt_clr(sbinfo->si_mntflags, PLINK); + break; + case Opt_list_plink: + if (au_opt_test(sbinfo->si_mntflags, PLINK)) + au_plink_list(sb); + break; + + case Opt_dio: + au_opt_set(sbinfo->si_mntflags, DIO); + au_fset_opts(opts->flags, REFRESH_DYAOP); + break; + case Opt_nodio: + au_opt_clr(sbinfo->si_mntflags, DIO); + au_fset_opts(opts->flags, REFRESH_DYAOP); + break; + + case Opt_diropq_a: + au_opt_set(sbinfo->si_mntflags, ALWAYS_DIROPQ); + break; + case Opt_diropq_w: + au_opt_clr(sbinfo->si_mntflags, ALWAYS_DIROPQ); + break; + + case Opt_warn_perm: + au_opt_set(sbinfo->si_mntflags, WARN_PERM); + break; + case Opt_nowarn_perm: + au_opt_clr(sbinfo->si_mntflags, WARN_PERM); + break; + + case Opt_refrof: + au_opt_set(sbinfo->si_mntflags, REFROF); + break; + case Opt_norefrof: + au_opt_clr(sbinfo->si_mntflags, REFROF); + break; + + case Opt_verbose: + au_opt_set(sbinfo->si_mntflags, VERBOSE); + break; + case Opt_noverbose: + au_opt_clr(sbinfo->si_mntflags, VERBOSE); + break; + + case Opt_sum: + au_opt_set(sbinfo->si_mntflags, SUM); + break; + case Opt_wsum: + au_opt_clr(sbinfo->si_mntflags, SUM); + au_opt_set(sbinfo->si_mntflags, SUM_W); + case Opt_nosum: + au_opt_clr(sbinfo->si_mntflags, SUM); + au_opt_clr(sbinfo->si_mntflags, SUM_W); + break; + + case Opt_wbr_create: + err = au_opt_wbr_create(sb, &opt->wbr_create); + break; + case Opt_wbr_copyup: + sbinfo->si_wbr_copyup = opt->wbr_copyup; + sbinfo->si_wbr_copyup_ops = au_wbr_copyup_ops + opt->wbr_copyup; + break; + + case Opt_dirwh: + sbinfo->si_dirwh = opt->dirwh; + break; + + case Opt_rdcache: + sbinfo->si_rdcache + = msecs_to_jiffies(opt->rdcache * MSEC_PER_SEC); + break; + case Opt_rdblk: + sbinfo->si_rdblk = opt->rdblk; + break; + case Opt_rdblk_def: + sbinfo->si_rdblk = AUFS_RDBLK_DEF; + break; + case Opt_rdhash: + sbinfo->si_rdhash = opt->rdhash; + break; + case Opt_rdhash_def: + sbinfo->si_rdhash = AUFS_RDHASH_DEF; + break; + + case Opt_shwh: + au_opt_set(sbinfo->si_mntflags, SHWH); + break; + case Opt_noshwh: + au_opt_clr(sbinfo->si_mntflags, SHWH); + break; + + case Opt_trunc_xino: + au_opt_set(sbinfo->si_mntflags, TRUNC_XINO); + break; + case Opt_notrunc_xino: + au_opt_clr(sbinfo->si_mntflags, TRUNC_XINO); + break; + + case Opt_trunc_xino_path: + case Opt_itrunc_xino: + err = au_xino_trunc(sb, opt->xino_itrunc.bindex); + if (!err) + err = 1; + break; + + case Opt_trunc_xib: + au_fset_opts(opts->flags, TRUNC_XIB); + break; + case Opt_notrunc_xib: + au_fclr_opts(opts->flags, TRUNC_XIB); + break; + + default: + err = 0; + break; + } + + return err; +} + +/* + * returns tri-state. + * plus: processed without an error + * zero: unprocessed + * minus: error + */ +static int au_opt_br(struct super_block *sb, struct au_opt *opt, + struct au_opts *opts) +{ + int err, do_refresh; + + err = 0; + switch (opt->type) { + case Opt_append: + opt->add.bindex = au_sbend(sb) + 1; + if (opt->add.bindex < 0) + opt->add.bindex = 0; + goto add; + case Opt_prepend: + opt->add.bindex = 0; + add: + case Opt_add: + err = au_br_add(sb, &opt->add, + au_ftest_opts(opts->flags, REMOUNT)); + if (!err) { + err = 1; + au_fset_opts(opts->flags, REFRESH); + } + break; + + case Opt_del: + case Opt_idel: + err = au_br_del(sb, &opt->del, + au_ftest_opts(opts->flags, REMOUNT)); + if (!err) { + err = 1; + au_fset_opts(opts->flags, TRUNC_XIB); + au_fset_opts(opts->flags, REFRESH); + } + break; + + case Opt_mod: + case Opt_imod: + err = au_br_mod(sb, &opt->mod, + au_ftest_opts(opts->flags, REMOUNT), + &do_refresh); + if (!err) { + err = 1; + if (do_refresh) + au_fset_opts(opts->flags, REFRESH); + } + break; + } + + return err; +} + +static int au_opt_xino(struct super_block *sb, struct au_opt *opt, + struct au_opt_xino **opt_xino, + struct au_opts *opts) +{ + int err; + aufs_bindex_t bend, bindex; + struct dentry *root, *parent, *h_root; + + err = 0; + switch (opt->type) { + case Opt_xino: + err = au_xino_set(sb, &opt->xino, + !!au_ftest_opts(opts->flags, REMOUNT)); + if (unlikely(err)) + break; + + *opt_xino = &opt->xino; + au_xino_brid_set(sb, -1); + + /* safe d_parent access */ + parent = opt->xino.file->f_dentry->d_parent; + root = sb->s_root; + bend = au_sbend(sb); + for (bindex = 0; bindex <= bend; bindex++) { + h_root = au_h_dptr(root, bindex); + if (h_root == parent) { + au_xino_brid_set(sb, au_sbr_id(sb, bindex)); + break; + } + } + break; + + case Opt_noxino: + au_xino_clr(sb); + au_xino_brid_set(sb, -1); + *opt_xino = (void *)-1; + break; + } + + return err; +} + +int au_opts_verify(struct super_block *sb, unsigned long sb_flags, + unsigned int pending) +{ + int err; + aufs_bindex_t bindex, bend; + unsigned char do_plink, skip, do_free; + struct au_branch *br; + struct au_wbr *wbr; + struct dentry *root; + struct inode *dir, *h_dir; + struct au_sbinfo *sbinfo; + struct au_hinode *hdir; + + SiMustAnyLock(sb); + + sbinfo = au_sbi(sb); + AuDebugOn(!(sbinfo->si_mntflags & AuOptMask_UDBA)); + + if (!(sb_flags & MS_RDONLY)) { + if (unlikely(!au_br_writable(au_sbr_perm(sb, 0)))) + pr_warning("first branch should be rw\n"); + if (unlikely(au_opt_test(sbinfo->si_mntflags, SHWH))) + pr_warning("shwh should be used with ro\n"); + } + + if (au_opt_test((sbinfo->si_mntflags | pending), UDBA_HNOTIFY) + && !au_opt_test(sbinfo->si_mntflags, XINO)) + pr_warning("udba=*notify requires xino\n"); + + err = 0; + root = sb->s_root; + dir = root->d_inode; + do_plink = !!au_opt_test(sbinfo->si_mntflags, PLINK); + bend = au_sbend(sb); + for (bindex = 0; !err && bindex <= bend; bindex++) { + skip = 0; + h_dir = au_h_iptr(dir, bindex); + br = au_sbr(sb, bindex); + do_free = 0; + + wbr = br->br_wbr; + if (wbr) + wbr_wh_read_lock(wbr); + + if (!au_br_writable(br->br_perm)) { + do_free = !!wbr; + skip = (!wbr + || (!wbr->wbr_whbase + && !wbr->wbr_plink + && !wbr->wbr_orph)); + } else if (!au_br_wh_linkable(br->br_perm)) { + /* skip = (!br->br_whbase && !br->br_orph); */ + skip = (!wbr || !wbr->wbr_whbase); + if (skip && wbr) { + if (do_plink) + skip = !!wbr->wbr_plink; + else + skip = !wbr->wbr_plink; + } + } else { + /* skip = (br->br_whbase && br->br_ohph); */ + skip = (wbr && wbr->wbr_whbase); + if (skip) { + if (do_plink) + skip = !!wbr->wbr_plink; + else + skip = !wbr->wbr_plink; + } + } + if (wbr) + wbr_wh_read_unlock(wbr); + + if (skip) + continue; + + hdir = au_hi(dir, bindex); + au_hn_imtx_lock_nested(hdir, AuLsc_I_PARENT); + if (wbr) + wbr_wh_write_lock(wbr); + err = au_wh_init(au_h_dptr(root, bindex), br, sb); + if (wbr) + wbr_wh_write_unlock(wbr); + au_hn_imtx_unlock(hdir); + + if (!err && do_free) { + kfree(wbr); + br->br_wbr = NULL; + } + } + + return err; +} + +int au_opts_mount(struct super_block *sb, struct au_opts *opts) +{ + int err; + unsigned int tmp; + aufs_bindex_t bindex, bend; + struct au_opt *opt; + struct au_opt_xino *opt_xino, xino; + struct au_sbinfo *sbinfo; + struct au_branch *br; + + SiMustWriteLock(sb); + + err = 0; + opt_xino = NULL; + opt = opts->opt; + while (err >= 0 && opt->type != Opt_tail) + err = au_opt_simple(sb, opt++, opts); + if (err > 0) + err = 0; + else if (unlikely(err < 0)) + goto out; + + /* disable xino and udba temporary */ + sbinfo = au_sbi(sb); + tmp = sbinfo->si_mntflags; + au_opt_clr(sbinfo->si_mntflags, XINO); + au_opt_set_udba(sbinfo->si_mntflags, UDBA_REVAL); + + opt = opts->opt; + while (err >= 0 && opt->type != Opt_tail) + err = au_opt_br(sb, opt++, opts); + if (err > 0) + err = 0; + else if (unlikely(err < 0)) + goto out; + + bend = au_sbend(sb); + if (unlikely(bend < 0)) { + err = -EINVAL; + pr_err("no branches\n"); + goto out; + } + + if (au_opt_test(tmp, XINO)) + au_opt_set(sbinfo->si_mntflags, XINO); + opt = opts->opt; + while (!err && opt->type != Opt_tail) + err = au_opt_xino(sb, opt++, &opt_xino, opts); + if (unlikely(err)) + goto out; + + err = au_opts_verify(sb, sb->s_flags, tmp); + if (unlikely(err)) + goto out; + + /* restore xino */ + if (au_opt_test(tmp, XINO) && !opt_xino) { + xino.file = au_xino_def(sb); + err = PTR_ERR(xino.file); + if (IS_ERR(xino.file)) + goto out; + + err = au_xino_set(sb, &xino, /*remount*/0); + fput(xino.file); + if (unlikely(err)) + goto out; + } + + /* restore udba */ + tmp &= AuOptMask_UDBA; + sbinfo->si_mntflags &= ~AuOptMask_UDBA; + sbinfo->si_mntflags |= tmp; + bend = au_sbend(sb); + for (bindex = 0; bindex <= bend; bindex++) { + br = au_sbr(sb, bindex); + err = au_hnotify_reset_br(tmp, br, br->br_perm); + if (unlikely(err)) + AuIOErr("hnotify failed on br %d, %d, ignored\n", + bindex, err); + /* go on even if err */ + } + if (au_opt_test(tmp, UDBA_HNOTIFY)) { + struct inode *dir = sb->s_root->d_inode; + au_hn_reset(dir, au_hi_flags(dir, /*isdir*/1) & ~AuHi_XINO); + } + +out: + return err; +} + +int au_opts_remount(struct super_block *sb, struct au_opts *opts) +{ + int err, rerr; + struct inode *dir; + struct au_opt_xino *opt_xino; + struct au_opt *opt; + struct au_sbinfo *sbinfo; + + SiMustWriteLock(sb); + + dir = sb->s_root->d_inode; + sbinfo = au_sbi(sb); + err = 0; + opt_xino = NULL; + opt = opts->opt; + while (err >= 0 && opt->type != Opt_tail) { + err = au_opt_simple(sb, opt, opts); + if (!err) + err = au_opt_br(sb, opt, opts); + if (!err) + err = au_opt_xino(sb, opt, &opt_xino, opts); + opt++; + } + if (err > 0) + err = 0; + AuTraceErr(err); + /* go on even err */ + + rerr = au_opts_verify(sb, opts->sb_flags, /*pending*/0); + if (unlikely(rerr && !err)) + err = rerr; + + if (au_ftest_opts(opts->flags, TRUNC_XIB)) { + rerr = au_xib_trunc(sb); + if (unlikely(rerr && !err)) + err = rerr; + } + + /* will be handled by the caller */ + if (!au_ftest_opts(opts->flags, REFRESH) + && (opts->given_udba || au_opt_test(sbinfo->si_mntflags, XINO))) + au_fset_opts(opts->flags, REFRESH); + + AuDbg("status 0x%x\n", opts->flags); + return err; +} + +/* ---------------------------------------------------------------------- */ + +unsigned int au_opt_udba(struct super_block *sb) +{ + return au_mntflags(sb) & AuOptMask_UDBA; +} diff --git a/ubuntu/aufs/opts.h b/ubuntu/aufs/opts.h new file mode 100644 index 000000000000..958f5119b01e --- /dev/null +++ b/ubuntu/aufs/opts.h @@ -0,0 +1,209 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * mount options/flags + */ + +#ifndef __AUFS_OPTS_H__ +#define __AUFS_OPTS_H__ + +#ifdef __KERNEL__ + +#include <linux/path.h> + +struct file; +struct super_block; + +/* ---------------------------------------------------------------------- */ + +/* mount flags */ +#define AuOpt_XINO 1 /* external inode number bitmap + and translation table */ +#define AuOpt_TRUNC_XINO (1 << 1) /* truncate xino files */ +#define AuOpt_UDBA_NONE (1 << 2) /* users direct branch access */ +#define AuOpt_UDBA_REVAL (1 << 3) +#define AuOpt_UDBA_HNOTIFY (1 << 4) +#define AuOpt_SHWH (1 << 5) /* show whiteout */ +#define AuOpt_PLINK (1 << 6) /* pseudo-link */ +#define AuOpt_DIRPERM1 (1 << 7) /* unimplemented */ +#define AuOpt_REFROF (1 << 8) /* unimplemented */ +#define AuOpt_ALWAYS_DIROPQ (1 << 9) /* policy to creating diropq */ +#define AuOpt_SUM (1 << 10) /* summation for statfs(2) */ +#define AuOpt_SUM_W (1 << 11) /* unimplemented */ +#define AuOpt_WARN_PERM (1 << 12) /* warn when add-branch */ +#define AuOpt_VERBOSE (1 << 13) /* busy inode when del-branch */ +#define AuOpt_DIO (1 << 14) /* direct io */ + +#ifndef CONFIG_AUFS_HNOTIFY +#undef AuOpt_UDBA_HNOTIFY +#define AuOpt_UDBA_HNOTIFY 0 +#endif +#ifndef CONFIG_AUFS_SHWH +#undef AuOpt_SHWH +#define AuOpt_SHWH 0 +#endif + +#define AuOpt_Def (AuOpt_XINO \ + | AuOpt_UDBA_REVAL \ + | AuOpt_PLINK \ + /* | AuOpt_DIRPERM1 */ \ + | AuOpt_WARN_PERM) +#define AuOptMask_UDBA (AuOpt_UDBA_NONE \ + | AuOpt_UDBA_REVAL \ + | AuOpt_UDBA_HNOTIFY) + +#define au_opt_test(flags, name) (flags & AuOpt_##name) +#define au_opt_set(flags, name) do { \ + BUILD_BUG_ON(AuOpt_##name & AuOptMask_UDBA); \ + ((flags) |= AuOpt_##name); \ +} while (0) +#define au_opt_set_udba(flags, name) do { \ + (flags) &= ~AuOptMask_UDBA; \ + ((flags) |= AuOpt_##name); \ +} while (0) +#define au_opt_clr(flags, name) do { \ + ((flags) &= ~AuOpt_##name); \ +} while (0) + +static inline unsigned int au_opts_plink(unsigned int mntflags) +{ +#ifdef CONFIG_PROC_FS + return mntflags; +#else + return mntflags & ~AuOpt_PLINK; +#endif +} + +/* ---------------------------------------------------------------------- */ + +/* policies to select one among multiple writable branches */ +enum { + AuWbrCreate_TDP, /* top down parent */ + AuWbrCreate_RR, /* round robin */ + AuWbrCreate_MFS, /* most free space */ + AuWbrCreate_MFSV, /* mfs with seconds */ + AuWbrCreate_MFSRR, /* mfs then rr */ + AuWbrCreate_MFSRRV, /* mfs then rr with seconds */ + AuWbrCreate_PMFS, /* parent and mfs */ + AuWbrCreate_PMFSV, /* parent and mfs with seconds */ + + AuWbrCreate_Def = AuWbrCreate_TDP +}; + +enum { + AuWbrCopyup_TDP, /* top down parent */ + AuWbrCopyup_BUP, /* bottom up parent */ + AuWbrCopyup_BU, /* bottom up */ + + AuWbrCopyup_Def = AuWbrCopyup_TDP +}; + +/* ---------------------------------------------------------------------- */ + +struct au_opt_add { + aufs_bindex_t bindex; + char *pathname; + int perm; + struct path path; +}; + +struct au_opt_del { + char *pathname; + struct path h_path; +}; + +struct au_opt_mod { + char *path; + int perm; + struct dentry *h_root; +}; + +struct au_opt_xino { + char *path; + struct file *file; +}; + +struct au_opt_xino_itrunc { + aufs_bindex_t bindex; +}; + +struct au_opt_wbr_create { + int wbr_create; + int mfs_second; + unsigned long long mfsrr_watermark; +}; + +struct au_opt { + int type; + union { + struct au_opt_xino xino; + struct au_opt_xino_itrunc xino_itrunc; + struct au_opt_add add; + struct au_opt_del del; + struct au_opt_mod mod; + int dirwh; + int rdcache; + unsigned int rdblk; + unsigned int rdhash; + int udba; + struct au_opt_wbr_create wbr_create; + int wbr_copyup; + }; +}; + +/* opts flags */ +#define AuOpts_REMOUNT 1 +#define AuOpts_REFRESH (1 << 1) +#define AuOpts_TRUNC_XIB (1 << 2) +#define AuOpts_REFRESH_DYAOP (1 << 3) +#define au_ftest_opts(flags, name) ((flags) & AuOpts_##name) +#define au_fset_opts(flags, name) \ + do { (flags) |= AuOpts_##name; } while (0) +#define au_fclr_opts(flags, name) \ + do { (flags) &= ~AuOpts_##name; } while (0) + +struct au_opts { + struct au_opt *opt; + int max_opt; + + unsigned int given_udba; + unsigned int flags; + unsigned long sb_flags; +}; + +/* ---------------------------------------------------------------------- */ + +char *au_optstr_br_perm(int brperm); +const char *au_optstr_udba(int udba); +const char *au_optstr_wbr_copyup(int wbr_copyup); +const char *au_optstr_wbr_create(int wbr_create); + +void au_opts_free(struct au_opts *opts); +int au_opts_parse(struct super_block *sb, char *str, struct au_opts *opts); +int au_opts_verify(struct super_block *sb, unsigned long sb_flags, + unsigned int pending); +int au_opts_mount(struct super_block *sb, struct au_opts *opts); +int au_opts_remount(struct super_block *sb, struct au_opts *opts); + +unsigned int au_opt_udba(struct super_block *sb); + +/* ---------------------------------------------------------------------- */ + +#endif /* __KERNEL__ */ +#endif /* __AUFS_OPTS_H__ */ diff --git a/ubuntu/aufs/plink.c b/ubuntu/aufs/plink.c new file mode 100644 index 000000000000..6338461902b6 --- /dev/null +++ b/ubuntu/aufs/plink.c @@ -0,0 +1,515 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * pseudo-link + */ + +#include "aufs.h" + +/* + * the pseudo-link maintenance mode. + * during a user process maintains the pseudo-links, + * prohibit adding a new plink and branch manipulation. + * + * Flags + * NOPLM: + * For entry functions which will handle plink, and i_mutex is already held + * in VFS. + * They cannot wait and should return an error at once. + * Callers has to check the error. + * NOPLMW: + * For entry functions which will handle plink, but i_mutex is not held + * in VFS. + * They can wait the plink maintenance mode to finish. + * + * They behave like F_SETLK and F_SETLKW. + * If the caller never handle plink, then both flags are unnecessary. + */ + +int au_plink_maint(struct super_block *sb, int flags) +{ + int err; + pid_t pid, ppid; + struct au_sbinfo *sbi; + + SiMustAnyLock(sb); + + err = 0; + if (!au_opt_test(au_mntflags(sb), PLINK)) + goto out; + + sbi = au_sbi(sb); + pid = sbi->si_plink_maint_pid; + if (!pid || pid == current->pid) + goto out; + + /* todo: it highly depends upon /sbin/mount.aufs */ + rcu_read_lock(); + ppid = task_pid_vnr(rcu_dereference(current->real_parent)); + rcu_read_unlock(); + if (pid == ppid) + goto out; + + if (au_ftest_lock(flags, NOPLMW)) { + /* if there is no i_mutex lock in VFS, we don't need to wait */ + /* AuDebugOn(!lockdep_depth(current)); */ + while (sbi->si_plink_maint_pid) { + si_read_unlock(sb); + /* gave up wake_up_bit() */ + wait_event(sbi->si_plink_wq, !sbi->si_plink_maint_pid); + + if (au_ftest_lock(flags, FLUSH)) + au_nwt_flush(&sbi->si_nowait); + si_noflush_read_lock(sb); + } + } else if (au_ftest_lock(flags, NOPLM)) { + AuDbg("ppid %d, pid %d\n", ppid, pid); + err = -EAGAIN; + } + +out: + return err; +} + +void au_plink_maint_leave(struct au_sbinfo *sbinfo) +{ + spin_lock(&sbinfo->si_plink_maint_lock); + sbinfo->si_plink_maint_pid = 0; + spin_unlock(&sbinfo->si_plink_maint_lock); + wake_up_all(&sbinfo->si_plink_wq); +} + +int au_plink_maint_enter(struct super_block *sb) +{ + int err; + struct au_sbinfo *sbinfo; + + err = 0; + sbinfo = au_sbi(sb); + /* make sure i am the only one in this fs */ + si_write_lock(sb, AuLock_FLUSH); + if (au_opt_test(au_mntflags(sb), PLINK)) { + spin_lock(&sbinfo->si_plink_maint_lock); + if (!sbinfo->si_plink_maint_pid) + sbinfo->si_plink_maint_pid = current->pid; + else + err = -EBUSY; + spin_unlock(&sbinfo->si_plink_maint_lock); + } + si_write_unlock(sb); + + return err; +} + +/* ---------------------------------------------------------------------- */ + +struct pseudo_link { + union { + struct list_head list; + struct rcu_head rcu; + }; + struct inode *inode; +}; + +#ifdef CONFIG_AUFS_DEBUG +void au_plink_list(struct super_block *sb) +{ + struct au_sbinfo *sbinfo; + struct list_head *plink_list; + struct pseudo_link *plink; + + SiMustAnyLock(sb); + + sbinfo = au_sbi(sb); + AuDebugOn(!au_opt_test(au_mntflags(sb), PLINK)); + AuDebugOn(au_plink_maint(sb, AuLock_NOPLM)); + + plink_list = &sbinfo->si_plink.head; + rcu_read_lock(); + list_for_each_entry_rcu(plink, plink_list, list) + AuDbg("%lu\n", plink->inode->i_ino); + rcu_read_unlock(); +} +#endif + +/* is the inode pseudo-linked? */ +int au_plink_test(struct inode *inode) +{ + int found; + struct au_sbinfo *sbinfo; + struct list_head *plink_list; + struct pseudo_link *plink; + + sbinfo = au_sbi(inode->i_sb); + AuRwMustAnyLock(&sbinfo->si_rwsem); + AuDebugOn(!au_opt_test(au_mntflags(inode->i_sb), PLINK)); + AuDebugOn(au_plink_maint(inode->i_sb, AuLock_NOPLM)); + + found = 0; + plink_list = &sbinfo->si_plink.head; + rcu_read_lock(); + list_for_each_entry_rcu(plink, plink_list, list) + if (plink->inode == inode) { + found = 1; + break; + } + rcu_read_unlock(); + return found; +} + +/* ---------------------------------------------------------------------- */ + +/* + * generate a name for plink. + * the file will be stored under AUFS_WH_PLINKDIR. + */ +/* 20 is max digits length of ulong 64 */ +#define PLINK_NAME_LEN ((20 + 1) * 2) + +static int plink_name(char *name, int len, struct inode *inode, + aufs_bindex_t bindex) +{ + int rlen; + struct inode *h_inode; + + h_inode = au_h_iptr(inode, bindex); + rlen = snprintf(name, len, "%lu.%lu", inode->i_ino, h_inode->i_ino); + return rlen; +} + +struct au_do_plink_lkup_args { + struct dentry **errp; + struct qstr *tgtname; + struct dentry *h_parent; + struct au_branch *br; +}; + +static struct dentry *au_do_plink_lkup(struct qstr *tgtname, + struct dentry *h_parent, + struct au_branch *br) +{ + struct dentry *h_dentry; + struct mutex *h_mtx; + + h_mtx = &h_parent->d_inode->i_mutex; + mutex_lock_nested(h_mtx, AuLsc_I_CHILD2); + h_dentry = au_lkup_one(tgtname, h_parent, br, /*nd*/NULL); + mutex_unlock(h_mtx); + return h_dentry; +} + +static void au_call_do_plink_lkup(void *args) +{ + struct au_do_plink_lkup_args *a = args; + *a->errp = au_do_plink_lkup(a->tgtname, a->h_parent, a->br); +} + +/* lookup the plink-ed @inode under the branch at @bindex */ +struct dentry *au_plink_lkup(struct inode *inode, aufs_bindex_t bindex) +{ + struct dentry *h_dentry, *h_parent; + struct au_branch *br; + struct inode *h_dir; + int wkq_err; + char a[PLINK_NAME_LEN]; + struct qstr tgtname = { + .name = a + }; + + AuDebugOn(au_plink_maint(inode->i_sb, AuLock_NOPLM)); + + br = au_sbr(inode->i_sb, bindex); + h_parent = br->br_wbr->wbr_plink; + h_dir = h_parent->d_inode; + tgtname.len = plink_name(a, sizeof(a), inode, bindex); + + if (current_fsuid()) { + struct au_do_plink_lkup_args args = { + .errp = &h_dentry, + .tgtname = &tgtname, + .h_parent = h_parent, + .br = br + }; + + wkq_err = au_wkq_wait(au_call_do_plink_lkup, &args); + if (unlikely(wkq_err)) + h_dentry = ERR_PTR(wkq_err); + } else + h_dentry = au_do_plink_lkup(&tgtname, h_parent, br); + + return h_dentry; +} + +/* create a pseudo-link */ +static int do_whplink(struct qstr *tgt, struct dentry *h_parent, + struct dentry *h_dentry, struct au_branch *br) +{ + int err; + struct path h_path = { + .mnt = br->br_mnt + }; + struct inode *h_dir; + + h_dir = h_parent->d_inode; + mutex_lock_nested(&h_dir->i_mutex, AuLsc_I_CHILD2); +again: + h_path.dentry = au_lkup_one(tgt, h_parent, br, /*nd*/NULL); + err = PTR_ERR(h_path.dentry); + if (IS_ERR(h_path.dentry)) + goto out; + + err = 0; + /* wh.plink dir is not monitored */ + /* todo: is it really safe? */ + if (h_path.dentry->d_inode + && h_path.dentry->d_inode != h_dentry->d_inode) { + err = vfsub_unlink(h_dir, &h_path, /*force*/0); + dput(h_path.dentry); + h_path.dentry = NULL; + if (!err) + goto again; + } + if (!err && !h_path.dentry->d_inode) + err = vfsub_link(h_dentry, h_dir, &h_path); + dput(h_path.dentry); + +out: + mutex_unlock(&h_dir->i_mutex); + return err; +} + +struct do_whplink_args { + int *errp; + struct qstr *tgt; + struct dentry *h_parent; + struct dentry *h_dentry; + struct au_branch *br; +}; + +static void call_do_whplink(void *args) +{ + struct do_whplink_args *a = args; + *a->errp = do_whplink(a->tgt, a->h_parent, a->h_dentry, a->br); +} + +static int whplink(struct dentry *h_dentry, struct inode *inode, + aufs_bindex_t bindex, struct au_branch *br) +{ + int err, wkq_err; + struct au_wbr *wbr; + struct dentry *h_parent; + struct inode *h_dir; + char a[PLINK_NAME_LEN]; + struct qstr tgtname = { + .name = a + }; + + wbr = au_sbr(inode->i_sb, bindex)->br_wbr; + h_parent = wbr->wbr_plink; + h_dir = h_parent->d_inode; + tgtname.len = plink_name(a, sizeof(a), inode, bindex); + + /* always superio. */ + if (current_fsuid()) { + struct do_whplink_args args = { + .errp = &err, + .tgt = &tgtname, + .h_parent = h_parent, + .h_dentry = h_dentry, + .br = br + }; + wkq_err = au_wkq_wait(call_do_whplink, &args); + if (unlikely(wkq_err)) + err = wkq_err; + } else + err = do_whplink(&tgtname, h_parent, h_dentry, br); + + return err; +} + +/* free a single plink */ +static void do_put_plink(struct pseudo_link *plink, int do_del) +{ + if (do_del) + list_del(&plink->list); + iput(plink->inode); + kfree(plink); +} + +static void do_put_plink_rcu(struct rcu_head *rcu) +{ + struct pseudo_link *plink; + + plink = container_of(rcu, struct pseudo_link, rcu); + iput(plink->inode); + kfree(plink); +} + +/* + * create a new pseudo-link for @h_dentry on @bindex. + * the linked inode is held in aufs @inode. + */ +void au_plink_append(struct inode *inode, aufs_bindex_t bindex, + struct dentry *h_dentry) +{ + struct super_block *sb; + struct au_sbinfo *sbinfo; + struct list_head *plink_list; + struct pseudo_link *plink, *tmp; + int found, err, cnt; + + sb = inode->i_sb; + sbinfo = au_sbi(sb); + AuDebugOn(!au_opt_test(au_mntflags(sb), PLINK)); + AuDebugOn(au_plink_maint(sb, AuLock_NOPLM)); + + cnt = 0; + found = 0; + plink_list = &sbinfo->si_plink.head; + rcu_read_lock(); + list_for_each_entry_rcu(plink, plink_list, list) { + cnt++; + if (plink->inode == inode) { + found = 1; + break; + } + } + rcu_read_unlock(); + if (found) + return; + + tmp = kmalloc(sizeof(*plink), GFP_NOFS); + if (tmp) + tmp->inode = au_igrab(inode); + else { + err = -ENOMEM; + goto out; + } + + spin_lock(&sbinfo->si_plink.spin); + list_for_each_entry(plink, plink_list, list) { + if (plink->inode == inode) { + found = 1; + break; + } + } + if (!found) + list_add_rcu(&tmp->list, plink_list); + spin_unlock(&sbinfo->si_plink.spin); + if (!found) { + cnt++; +// WARN_ONCE(cnt > AUFS_PLINK_WARN, +// "unexpectedly many pseudo links, %d\n", cnt); + err = whplink(h_dentry, inode, bindex, au_sbr(sb, bindex)); + } else { + do_put_plink(tmp, 0); + return; + } + +out: + if (unlikely(err)) { + pr_warning("err %d, damaged pseudo link.\n", err); + if (tmp) { + au_spl_del_rcu(&tmp->list, &sbinfo->si_plink); + call_rcu(&tmp->rcu, do_put_plink_rcu); + } + } +} + +/* free all plinks */ +void au_plink_put(struct super_block *sb, int verbose) +{ + struct au_sbinfo *sbinfo; + struct list_head *plink_list; + struct pseudo_link *plink, *tmp; + + SiMustWriteLock(sb); + + sbinfo = au_sbi(sb); + AuDebugOn(!au_opt_test(au_mntflags(sb), PLINK)); + AuDebugOn(au_plink_maint(sb, AuLock_NOPLM)); + + plink_list = &sbinfo->si_plink.head; + /* no spin_lock since sbinfo is write-locked */ + WARN(verbose && !list_empty(plink_list), "pseudo-link is not flushed"); + list_for_each_entry_safe(plink, tmp, plink_list, list) + do_put_plink(plink, 0); + INIT_LIST_HEAD(plink_list); +} + +void au_plink_clean(struct super_block *sb, int verbose) +{ + struct dentry *root; + + root = sb->s_root; + aufs_write_lock(root); + if (au_opt_test(au_mntflags(sb), PLINK)) + au_plink_put(sb, verbose); + aufs_write_unlock(root); +} + +/* free the plinks on a branch specified by @br_id */ +void au_plink_half_refresh(struct super_block *sb, aufs_bindex_t br_id) +{ + struct au_sbinfo *sbinfo; + struct list_head *plink_list; + struct pseudo_link *plink, *tmp; + struct inode *inode; + aufs_bindex_t bstart, bend, bindex; + unsigned char do_put; + + SiMustWriteLock(sb); + + sbinfo = au_sbi(sb); + AuDebugOn(!au_opt_test(au_mntflags(sb), PLINK)); + AuDebugOn(au_plink_maint(sb, AuLock_NOPLM)); + + plink_list = &sbinfo->si_plink.head; + /* no spin_lock since sbinfo is write-locked */ + list_for_each_entry_safe(plink, tmp, plink_list, list) { + do_put = 0; + inode = au_igrab(plink->inode); + ii_write_lock_child(inode); + bstart = au_ibstart(inode); + bend = au_ibend(inode); + if (bstart >= 0) { + for (bindex = bstart; bindex <= bend; bindex++) { + if (!au_h_iptr(inode, bindex) + || au_ii_br_id(inode, bindex) != br_id) + continue; + au_set_h_iptr(inode, bindex, NULL, 0); + do_put = 1; + break; + } + } else + do_put_plink(plink, 1); + + if (do_put) { + for (bindex = bstart; bindex <= bend; bindex++) + if (au_h_iptr(inode, bindex)) { + do_put = 0; + break; + } + if (do_put) + do_put_plink(plink, 1); + } + ii_write_unlock(inode); + iput(inode); + } +} diff --git a/ubuntu/aufs/poll.c b/ubuntu/aufs/poll.c new file mode 100644 index 000000000000..59d1a4b285ea --- /dev/null +++ b/ubuntu/aufs/poll.c @@ -0,0 +1,56 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * poll operation + * There is only one filesystem which implements ->poll operation, currently. + */ + +#include "aufs.h" + +unsigned int aufs_poll(struct file *file, poll_table *wait) +{ + unsigned int mask; + int err; + struct file *h_file; + struct dentry *dentry; + struct super_block *sb; + + /* We should pretend an error happened. */ + mask = POLLERR /* | POLLIN | POLLOUT */; + dentry = file->f_dentry; + sb = dentry->d_sb; + si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW); + err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/0); + if (unlikely(err)) + goto out; + + /* it is not an error if h_file has no operation */ + mask = DEFAULT_POLLMASK; + h_file = au_hf_top(file); + if (h_file->f_op && h_file->f_op->poll) + mask = h_file->f_op->poll(h_file, wait); + + di_read_unlock(dentry, AuLock_IR); + fi_read_unlock(file); + +out: + si_read_unlock(sb); + AuTraceErr((int)mask); + return mask; +} diff --git a/ubuntu/aufs/procfs.c b/ubuntu/aufs/procfs.c new file mode 100644 index 000000000000..8169782d5e3a --- /dev/null +++ b/ubuntu/aufs/procfs.c @@ -0,0 +1,170 @@ +/* + * Copyright (C) 2010-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * procfs interfaces + */ + +#include <linux/proc_fs.h> +#include "aufs.h" + +static int au_procfs_plm_release(struct inode *inode, struct file *file) +{ + struct au_sbinfo *sbinfo; + + sbinfo = file->private_data; + if (sbinfo) { + au_plink_maint_leave(sbinfo); + kobject_put(&sbinfo->si_kobj); + } + + return 0; +} + +static void au_procfs_plm_write_clean(struct file *file) +{ + struct au_sbinfo *sbinfo; + + sbinfo = file->private_data; + if (sbinfo) + au_plink_clean(sbinfo->si_sb, /*verbose*/0); +} + +static int au_procfs_plm_write_si(struct file *file, unsigned long id) +{ + int err; + struct super_block *sb; + struct au_sbinfo *sbinfo; + + err = -EBUSY; + if (unlikely(file->private_data)) + goto out; + + sb = NULL; + /* don't use au_sbilist_lock() here */ + spin_lock(&au_sbilist.spin); + list_for_each_entry(sbinfo, &au_sbilist.head, si_list) + if (id == sysaufs_si_id(sbinfo)) { + kobject_get(&sbinfo->si_kobj); + sb = sbinfo->si_sb; + break; + } + spin_unlock(&au_sbilist.spin); + + err = -EINVAL; + if (unlikely(!sb)) + goto out; + + err = au_plink_maint_enter(sb); + if (!err) + /* keep kobject_get() */ + file->private_data = sbinfo; + else + kobject_put(&sbinfo->si_kobj); +out: + return err; +} + +/* + * Accept a valid "si=xxxx" only. + * Once it is accepted successfully, accept "clean" too. + */ +static ssize_t au_procfs_plm_write(struct file *file, const char __user *ubuf, + size_t count, loff_t *ppos) +{ + ssize_t err; + unsigned long id; + /* last newline is allowed */ + char buf[3 + sizeof(unsigned long) * 2 + 1]; + + err = -EACCES; + if (unlikely(!capable(CAP_SYS_ADMIN))) + goto out; + + err = -EINVAL; + if (unlikely(count > sizeof(buf))) + goto out; + + err = copy_from_user(buf, ubuf, count); + if (unlikely(err)) { + err = -EFAULT; + goto out; + } + buf[count] = 0; + + err = -EINVAL; + if (!strcmp("clean", buf)) { + au_procfs_plm_write_clean(file); + goto out_success; + } else if (unlikely(strncmp("si=", buf, 3))) + goto out; + + err = kstrtoul(buf + 3, 16, &id); + if (unlikely(err)) + goto out; + + err = au_procfs_plm_write_si(file, id); + if (unlikely(err)) + goto out; + +out_success: + err = count; /* success */ +out: + return err; +} + +static const struct file_operations au_procfs_plm_fop = { + .write = au_procfs_plm_write, + .release = au_procfs_plm_release, + .owner = THIS_MODULE +}; + +/* ---------------------------------------------------------------------- */ + +static struct proc_dir_entry *au_procfs_dir; + +void au_procfs_fin(void) +{ + remove_proc_entry(AUFS_PLINK_MAINT_NAME, au_procfs_dir); + remove_proc_entry(AUFS_PLINK_MAINT_DIR, NULL); +} + +int __init au_procfs_init(void) +{ + int err; + struct proc_dir_entry *entry; + + err = -ENOMEM; + au_procfs_dir = proc_mkdir(AUFS_PLINK_MAINT_DIR, NULL); + if (unlikely(!au_procfs_dir)) + goto out; + + entry = proc_create(AUFS_PLINK_MAINT_NAME, S_IFREG | S_IWUSR, + au_procfs_dir, &au_procfs_plm_fop); + if (unlikely(!entry)) + goto out_dir; + + err = 0; + goto out; /* success */ + + +out_dir: + remove_proc_entry(AUFS_PLINK_MAINT_DIR, NULL); +out: + return err; +} diff --git a/ubuntu/aufs/rdu.c b/ubuntu/aufs/rdu.c new file mode 100644 index 000000000000..765650379404 --- /dev/null +++ b/ubuntu/aufs/rdu.c @@ -0,0 +1,383 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * readdir in userspace. + */ + +#include <linux/compat.h> +#include <linux/fs_stack.h> +#include <linux/security.h> +#include "aufs.h" + +/* bits for struct aufs_rdu.flags */ +#define AuRdu_CALLED 1 +#define AuRdu_CONT (1 << 1) +#define AuRdu_FULL (1 << 2) +#define au_ftest_rdu(flags, name) ((flags) & AuRdu_##name) +#define au_fset_rdu(flags, name) \ + do { (flags) |= AuRdu_##name; } while (0) +#define au_fclr_rdu(flags, name) \ + do { (flags) &= ~AuRdu_##name; } while (0) + +struct au_rdu_arg { + struct aufs_rdu *rdu; + union au_rdu_ent_ul ent; + unsigned long end; + + struct super_block *sb; + int err; +}; + +static int au_rdu_fill(void *__arg, const char *name, int nlen, + loff_t offset, u64 h_ino, unsigned int d_type) +{ + int err, len; + struct au_rdu_arg *arg = __arg; + struct aufs_rdu *rdu = arg->rdu; + struct au_rdu_ent ent; + + err = 0; + arg->err = 0; + au_fset_rdu(rdu->cookie.flags, CALLED); + len = au_rdu_len(nlen); + if (arg->ent.ul + len < arg->end) { + ent.ino = h_ino; + ent.bindex = rdu->cookie.bindex; + ent.type = d_type; + ent.nlen = nlen; + if (unlikely(nlen > AUFS_MAX_NAMELEN)) + ent.type = DT_UNKNOWN; + + /* unnecessary to support mmap_sem since this is a dir */ + err = -EFAULT; + if (copy_to_user(arg->ent.e, &ent, sizeof(ent))) + goto out; + if (copy_to_user(arg->ent.e->name, name, nlen)) + goto out; + /* the terminating NULL */ + if (__put_user(0, arg->ent.e->name + nlen)) + goto out; + err = 0; + /* AuDbg("%p, %.*s\n", arg->ent.p, nlen, name); */ + arg->ent.ul += len; + rdu->rent++; + } else { + err = -EFAULT; + au_fset_rdu(rdu->cookie.flags, FULL); + rdu->full = 1; + rdu->tail = arg->ent; + } + +out: + /* AuTraceErr(err); */ + return err; +} + +static int au_rdu_do(struct file *h_file, struct au_rdu_arg *arg) +{ + int err; + loff_t offset; + struct au_rdu_cookie *cookie = &arg->rdu->cookie; + + offset = vfsub_llseek(h_file, cookie->h_pos, SEEK_SET); + err = offset; + if (unlikely(offset != cookie->h_pos)) + goto out; + + err = 0; + do { + arg->err = 0; + au_fclr_rdu(cookie->flags, CALLED); + /* smp_mb(); */ + err = vfsub_readdir(h_file, au_rdu_fill, arg); + if (err >= 0) + err = arg->err; + } while (!err + && au_ftest_rdu(cookie->flags, CALLED) + && !au_ftest_rdu(cookie->flags, FULL)); + cookie->h_pos = h_file->f_pos; + +out: + AuTraceErr(err); + return err; +} + +static int au_rdu(struct file *file, struct aufs_rdu *rdu) +{ + int err; + aufs_bindex_t bend; + struct au_rdu_arg arg; + struct dentry *dentry; + struct inode *inode; + struct file *h_file; + struct au_rdu_cookie *cookie = &rdu->cookie; + + err = !access_ok(VERIFY_WRITE, rdu->ent.e, rdu->sz); + if (unlikely(err)) { + err = -EFAULT; + AuTraceErr(err); + goto out; + } + rdu->rent = 0; + rdu->tail = rdu->ent; + rdu->full = 0; + arg.rdu = rdu; + arg.ent = rdu->ent; + arg.end = arg.ent.ul; + arg.end += rdu->sz; + + err = -ENOTDIR; + if (unlikely(!file->f_op || !file->f_op->readdir)) + goto out; + + err = security_file_permission(file, MAY_READ); + AuTraceErr(err); + if (unlikely(err)) + goto out; + + dentry = file->f_dentry; + inode = dentry->d_inode; +#if 1 + mutex_lock(&inode->i_mutex); +#else + err = mutex_lock_killable(&inode->i_mutex); + AuTraceErr(err); + if (unlikely(err)) + goto out; +#endif + + arg.sb = inode->i_sb; + err = si_read_lock(arg.sb, AuLock_FLUSH | AuLock_NOPLM); + if (unlikely(err)) + goto out_mtx; + err = au_alive_dir(dentry); + if (unlikely(err)) + goto out_si; + /* todo: reval? */ + fi_read_lock(file); + + err = -EAGAIN; + if (unlikely(au_ftest_rdu(cookie->flags, CONT) + && cookie->generation != au_figen(file))) + goto out_unlock; + + err = 0; + if (!rdu->blk) { + rdu->blk = au_sbi(arg.sb)->si_rdblk; + if (!rdu->blk) + rdu->blk = au_dir_size(file, /*dentry*/NULL); + } + bend = au_fbstart(file); + if (cookie->bindex < bend) + cookie->bindex = bend; + bend = au_fbend_dir(file); + /* AuDbg("b%d, b%d\n", cookie->bindex, bend); */ + for (; !err && cookie->bindex <= bend; + cookie->bindex++, cookie->h_pos = 0) { + h_file = au_hf_dir(file, cookie->bindex); + if (!h_file) + continue; + + au_fclr_rdu(cookie->flags, FULL); + err = au_rdu_do(h_file, &arg); + AuTraceErr(err); + if (unlikely(au_ftest_rdu(cookie->flags, FULL) || err)) + break; + } + AuDbg("rent %llu\n", rdu->rent); + + if (!err && !au_ftest_rdu(cookie->flags, CONT)) { + rdu->shwh = !!au_opt_test(au_sbi(arg.sb)->si_mntflags, SHWH); + au_fset_rdu(cookie->flags, CONT); + cookie->generation = au_figen(file); + } + + ii_read_lock_child(inode); + fsstack_copy_attr_atime(inode, au_h_iptr(inode, au_ibstart(inode))); + ii_read_unlock(inode); + +out_unlock: + fi_read_unlock(file); +out_si: + si_read_unlock(arg.sb); +out_mtx: + mutex_unlock(&inode->i_mutex); +out: + AuTraceErr(err); + return err; +} + +static int au_rdu_ino(struct file *file, struct aufs_rdu *rdu) +{ + int err; + ino_t ino; + unsigned long long nent; + union au_rdu_ent_ul *u; + struct au_rdu_ent ent; + struct super_block *sb; + + err = 0; + nent = rdu->nent; + u = &rdu->ent; + sb = file->f_dentry->d_sb; + si_read_lock(sb, AuLock_FLUSH); + while (nent-- > 0) { + /* unnecessary to support mmap_sem since this is a dir */ + err = copy_from_user(&ent, u->e, sizeof(ent)); + if (!err) + err = !access_ok(VERIFY_WRITE, &u->e->ino, sizeof(ino)); + if (unlikely(err)) { + err = -EFAULT; + AuTraceErr(err); + break; + } + + /* AuDbg("b%d, i%llu\n", ent.bindex, ent.ino); */ + if (!ent.wh) + err = au_ino(sb, ent.bindex, ent.ino, ent.type, &ino); + else + err = au_wh_ino(sb, ent.bindex, ent.ino, ent.type, + &ino); + if (unlikely(err)) { + AuTraceErr(err); + break; + } + + err = __put_user(ino, &u->e->ino); + if (unlikely(err)) { + err = -EFAULT; + AuTraceErr(err); + break; + } + u->ul += au_rdu_len(ent.nlen); + } + si_read_unlock(sb); + + return err; +} + +/* ---------------------------------------------------------------------- */ + +static int au_rdu_verify(struct aufs_rdu *rdu) +{ + AuDbg("rdu{%llu, %p, %u | %u | %llu, %u, %u | " + "%llu, b%d, 0x%x, g%u}\n", + rdu->sz, rdu->ent.e, rdu->verify[AufsCtlRduV_SZ], + rdu->blk, + rdu->rent, rdu->shwh, rdu->full, + rdu->cookie.h_pos, rdu->cookie.bindex, rdu->cookie.flags, + rdu->cookie.generation); + + if (rdu->verify[AufsCtlRduV_SZ] == sizeof(*rdu)) + return 0; + + AuDbg("%u:%u\n", + rdu->verify[AufsCtlRduV_SZ], (unsigned int)sizeof(*rdu)); + return -EINVAL; +} + +long au_rdu_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + long err, e; + struct aufs_rdu rdu; + void __user *p = (void __user *)arg; + + err = copy_from_user(&rdu, p, sizeof(rdu)); + if (unlikely(err)) { + err = -EFAULT; + AuTraceErr(err); + goto out; + } + err = au_rdu_verify(&rdu); + if (unlikely(err)) + goto out; + + switch (cmd) { + case AUFS_CTL_RDU: + err = au_rdu(file, &rdu); + if (unlikely(err)) + break; + + e = copy_to_user(p, &rdu, sizeof(rdu)); + if (unlikely(e)) { + err = -EFAULT; + AuTraceErr(err); + } + break; + case AUFS_CTL_RDU_INO: + err = au_rdu_ino(file, &rdu); + break; + + default: + /* err = -ENOTTY; */ + err = -EINVAL; + } + +out: + AuTraceErr(err); + return err; +} + +#ifdef CONFIG_COMPAT +long au_rdu_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + long err, e; + struct aufs_rdu rdu; + void __user *p = compat_ptr(arg); + + /* todo: get_user()? */ + err = copy_from_user(&rdu, p, sizeof(rdu)); + if (unlikely(err)) { + err = -EFAULT; + AuTraceErr(err); + goto out; + } + rdu.ent.e = compat_ptr(rdu.ent.ul); + err = au_rdu_verify(&rdu); + if (unlikely(err)) + goto out; + + switch (cmd) { + case AUFS_CTL_RDU: + err = au_rdu(file, &rdu); + if (unlikely(err)) + break; + + rdu.ent.ul = ptr_to_compat(rdu.ent.e); + rdu.tail.ul = ptr_to_compat(rdu.tail.e); + e = copy_to_user(p, &rdu, sizeof(rdu)); + if (unlikely(e)) { + err = -EFAULT; + AuTraceErr(err); + } + break; + case AUFS_CTL_RDU_INO: + err = au_rdu_ino(file, &rdu); + break; + + default: + /* err = -ENOTTY; */ + err = -EINVAL; + } + +out: + AuTraceErr(err); + return err; +} +#endif diff --git a/ubuntu/aufs/rwsem.h b/ubuntu/aufs/rwsem.h new file mode 100644 index 000000000000..d6c1b3767308 --- /dev/null +++ b/ubuntu/aufs/rwsem.h @@ -0,0 +1,188 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * simple read-write semaphore wrappers + */ + +#ifndef __AUFS_RWSEM_H__ +#define __AUFS_RWSEM_H__ + +#ifdef __KERNEL__ + +#include "debug.h" + +struct au_rwsem { + struct rw_semaphore rwsem; +#ifdef CONFIG_AUFS_DEBUG + /* just for debugging, not almighty counter */ + atomic_t rcnt, wcnt; +#endif +}; + +#ifdef CONFIG_AUFS_DEBUG +#define AuDbgCntInit(rw) do { \ + atomic_set(&(rw)->rcnt, 0); \ + atomic_set(&(rw)->wcnt, 0); \ + smp_mb(); /* atomic set */ \ +} while (0) + +#define AuDbgRcntInc(rw) atomic_inc(&(rw)->rcnt) +#define AuDbgRcntDec(rw) WARN_ON(atomic_dec_return(&(rw)->rcnt) < 0) +#define AuDbgWcntInc(rw) atomic_inc(&(rw)->wcnt) +#define AuDbgWcntDec(rw) WARN_ON(atomic_dec_return(&(rw)->wcnt) < 0) +#else +#define AuDbgCntInit(rw) do {} while (0) +#define AuDbgRcntInc(rw) do {} while (0) +#define AuDbgRcntDec(rw) do {} while (0) +#define AuDbgWcntInc(rw) do {} while (0) +#define AuDbgWcntDec(rw) do {} while (0) +#endif /* CONFIG_AUFS_DEBUG */ + +/* to debug easier, do not make them inlined functions */ +#define AuRwMustNoWaiters(rw) AuDebugOn(!list_empty(&(rw)->rwsem.wait_list)) +/* rwsem_is_locked() is unusable */ +#define AuRwMustReadLock(rw) AuDebugOn(atomic_read(&(rw)->rcnt) <= 0) +#define AuRwMustWriteLock(rw) AuDebugOn(atomic_read(&(rw)->wcnt) <= 0) +#define AuRwMustAnyLock(rw) AuDebugOn(atomic_read(&(rw)->rcnt) <= 0 \ + && atomic_read(&(rw)->wcnt) <= 0) +#define AuRwDestroy(rw) AuDebugOn(atomic_read(&(rw)->rcnt) \ + || atomic_read(&(rw)->wcnt)) + +#define au_rw_class(rw, key) lockdep_set_class(&(rw)->rwsem, key) + +static inline void au_rw_init(struct au_rwsem *rw) +{ + AuDbgCntInit(rw); + init_rwsem(&rw->rwsem); +} + +static inline void au_rw_init_wlock(struct au_rwsem *rw) +{ + au_rw_init(rw); + down_write(&rw->rwsem); + AuDbgWcntInc(rw); +} + +static inline void au_rw_init_wlock_nested(struct au_rwsem *rw, + unsigned int lsc) +{ + au_rw_init(rw); + down_write_nested(&rw->rwsem, lsc); + AuDbgWcntInc(rw); +} + +static inline void au_rw_read_lock(struct au_rwsem *rw) +{ + down_read(&rw->rwsem); + AuDbgRcntInc(rw); +} + +static inline void au_rw_read_lock_nested(struct au_rwsem *rw, unsigned int lsc) +{ + down_read_nested(&rw->rwsem, lsc); + AuDbgRcntInc(rw); +} + +static inline void au_rw_read_unlock(struct au_rwsem *rw) +{ + AuRwMustReadLock(rw); + AuDbgRcntDec(rw); + up_read(&rw->rwsem); +} + +static inline void au_rw_dgrade_lock(struct au_rwsem *rw) +{ + AuRwMustWriteLock(rw); + AuDbgRcntInc(rw); + AuDbgWcntDec(rw); + downgrade_write(&rw->rwsem); +} + +static inline void au_rw_write_lock(struct au_rwsem *rw) +{ + down_write(&rw->rwsem); + AuDbgWcntInc(rw); +} + +static inline void au_rw_write_lock_nested(struct au_rwsem *rw, + unsigned int lsc) +{ + down_write_nested(&rw->rwsem, lsc); + AuDbgWcntInc(rw); +} + +static inline void au_rw_write_unlock(struct au_rwsem *rw) +{ + AuRwMustWriteLock(rw); + AuDbgWcntDec(rw); + up_write(&rw->rwsem); +} + +/* why is not _nested version defined */ +static inline int au_rw_read_trylock(struct au_rwsem *rw) +{ + int ret = down_read_trylock(&rw->rwsem); + if (ret) + AuDbgRcntInc(rw); + return ret; +} + +static inline int au_rw_write_trylock(struct au_rwsem *rw) +{ + int ret = down_write_trylock(&rw->rwsem); + if (ret) + AuDbgWcntInc(rw); + return ret; +} + +#undef AuDbgCntInit +#undef AuDbgRcntInc +#undef AuDbgRcntDec +#undef AuDbgWcntInc +#undef AuDbgWcntDec + +#define AuSimpleLockRwsemFuncs(prefix, param, rwsem) \ +static inline void prefix##_read_lock(param) \ +{ au_rw_read_lock(rwsem); } \ +static inline void prefix##_write_lock(param) \ +{ au_rw_write_lock(rwsem); } \ +static inline int prefix##_read_trylock(param) \ +{ return au_rw_read_trylock(rwsem); } \ +static inline int prefix##_write_trylock(param) \ +{ return au_rw_write_trylock(rwsem); } +/* why is not _nested version defined */ +/* static inline void prefix##_read_trylock_nested(param, lsc) +{ au_rw_read_trylock_nested(rwsem, lsc)); } +static inline void prefix##_write_trylock_nestd(param, lsc) +{ au_rw_write_trylock_nested(rwsem, lsc); } */ + +#define AuSimpleUnlockRwsemFuncs(prefix, param, rwsem) \ +static inline void prefix##_read_unlock(param) \ +{ au_rw_read_unlock(rwsem); } \ +static inline void prefix##_write_unlock(param) \ +{ au_rw_write_unlock(rwsem); } \ +static inline void prefix##_downgrade_lock(param) \ +{ au_rw_dgrade_lock(rwsem); } + +#define AuSimpleRwsemFuncs(prefix, param, rwsem) \ + AuSimpleLockRwsemFuncs(prefix, param, rwsem) \ + AuSimpleUnlockRwsemFuncs(prefix, param, rwsem) + +#endif /* __KERNEL__ */ +#endif /* __AUFS_RWSEM_H__ */ diff --git a/ubuntu/aufs/sbinfo.c b/ubuntu/aufs/sbinfo.c new file mode 100644 index 000000000000..2448efe08014 --- /dev/null +++ b/ubuntu/aufs/sbinfo.c @@ -0,0 +1,343 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * superblock private data + */ + +#include "aufs.h" + +/* + * they are necessary regardless sysfs is disabled. + */ +void au_si_free(struct kobject *kobj) +{ + struct au_sbinfo *sbinfo; + char *locked __maybe_unused; /* debug only */ + + sbinfo = container_of(kobj, struct au_sbinfo, si_kobj); + AuDebugOn(!list_empty(&sbinfo->si_plink.head)); + AuDebugOn(atomic_read(&sbinfo->si_nowait.nw_len)); + + au_rw_write_lock(&sbinfo->si_rwsem); + au_br_free(sbinfo); + au_rw_write_unlock(&sbinfo->si_rwsem); + + AuDebugOn(radix_tree_gang_lookup + (&sbinfo->au_si_pid.tree, (void **)&locked, + /*first_index*/PID_MAX_DEFAULT - 1, + /*max_items*/sizeof(locked)/sizeof(*locked))); + + kfree(sbinfo->si_branch); + kfree(sbinfo->au_si_pid.bitmap); + mutex_destroy(&sbinfo->si_xib_mtx); + AuRwDestroy(&sbinfo->si_rwsem); + + kfree(sbinfo); +} + +int au_si_alloc(struct super_block *sb) +{ + int err; + struct au_sbinfo *sbinfo; + static struct lock_class_key aufs_si; + + err = -ENOMEM; + sbinfo = kzalloc(sizeof(*sbinfo), GFP_NOFS); + if (unlikely(!sbinfo)) + goto out; + + BUILD_BUG_ON(sizeof(unsigned long) != + sizeof(*sbinfo->au_si_pid.bitmap)); + sbinfo->au_si_pid.bitmap = kcalloc(BITS_TO_LONGS(PID_MAX_DEFAULT), + sizeof(*sbinfo->au_si_pid.bitmap), + GFP_NOFS); + if (unlikely(!sbinfo->au_si_pid.bitmap)) + goto out_sbinfo; + + /* will be reallocated separately */ + sbinfo->si_branch = kzalloc(sizeof(*sbinfo->si_branch), GFP_NOFS); + if (unlikely(!sbinfo->si_branch)) + goto out_pidmap; + + err = sysaufs_si_init(sbinfo); + if (unlikely(err)) + goto out_br; + + au_nwt_init(&sbinfo->si_nowait); + au_rw_init_wlock(&sbinfo->si_rwsem); + au_rw_class(&sbinfo->si_rwsem, &aufs_si); + spin_lock_init(&sbinfo->au_si_pid.tree_lock); + INIT_RADIX_TREE(&sbinfo->au_si_pid.tree, GFP_ATOMIC | __GFP_NOFAIL); + + atomic_long_set(&sbinfo->si_ninodes, 0); + atomic_long_set(&sbinfo->si_nfiles, 0); + + sbinfo->si_bend = -1; + + sbinfo->si_wbr_copyup = AuWbrCopyup_Def; + sbinfo->si_wbr_create = AuWbrCreate_Def; + sbinfo->si_wbr_copyup_ops = au_wbr_copyup_ops + sbinfo->si_wbr_copyup; + sbinfo->si_wbr_create_ops = au_wbr_create_ops + sbinfo->si_wbr_create; + + sbinfo->si_mntflags = au_opts_plink(AuOpt_Def); + + mutex_init(&sbinfo->si_xib_mtx); + sbinfo->si_xino_brid = -1; + /* leave si_xib_last_pindex and si_xib_next_bit */ + + sbinfo->si_rdcache = msecs_to_jiffies(AUFS_RDCACHE_DEF * MSEC_PER_SEC); + sbinfo->si_rdblk = AUFS_RDBLK_DEF; + sbinfo->si_rdhash = AUFS_RDHASH_DEF; + sbinfo->si_dirwh = AUFS_DIRWH_DEF; + + au_spl_init(&sbinfo->si_plink); + init_waitqueue_head(&sbinfo->si_plink_wq); + spin_lock_init(&sbinfo->si_plink_maint_lock); + + /* leave other members for sysaufs and si_mnt. */ + sbinfo->si_sb = sb; + sb->s_fs_info = sbinfo; + si_pid_set(sb); + au_debug_sbinfo_init(sbinfo); + return 0; /* success */ + +out_br: + kfree(sbinfo->si_branch); +out_pidmap: + kfree(sbinfo->au_si_pid.bitmap); +out_sbinfo: + kfree(sbinfo); +out: + return err; +} + +int au_sbr_realloc(struct au_sbinfo *sbinfo, int nbr) +{ + int err, sz; + struct au_branch **brp; + + AuRwMustWriteLock(&sbinfo->si_rwsem); + + err = -ENOMEM; + sz = sizeof(*brp) * (sbinfo->si_bend + 1); + if (unlikely(!sz)) + sz = sizeof(*brp); + brp = au_kzrealloc(sbinfo->si_branch, sz, sizeof(*brp) * nbr, GFP_NOFS); + if (brp) { + sbinfo->si_branch = brp; + err = 0; + } + + return err; +} + +/* ---------------------------------------------------------------------- */ + +unsigned int au_sigen_inc(struct super_block *sb) +{ + unsigned int gen; + + SiMustWriteLock(sb); + + gen = ++au_sbi(sb)->si_generation; + au_update_digen(sb->s_root); + au_update_iigen(sb->s_root->d_inode); + sb->s_root->d_inode->i_version++; + return gen; +} + +aufs_bindex_t au_new_br_id(struct super_block *sb) +{ + aufs_bindex_t br_id; + int i; + struct au_sbinfo *sbinfo; + + SiMustWriteLock(sb); + + sbinfo = au_sbi(sb); + for (i = 0; i <= AUFS_BRANCH_MAX; i++) { + br_id = ++sbinfo->si_last_br_id; + AuDebugOn(br_id < 0); + if (br_id && au_br_index(sb, br_id) < 0) + return br_id; + } + + return -1; +} + +/* ---------------------------------------------------------------------- */ + +/* it is ok that new 'nwt' tasks are appended while we are sleeping */ +int si_read_lock(struct super_block *sb, int flags) +{ + int err; + + err = 0; + if (au_ftest_lock(flags, FLUSH)) + au_nwt_flush(&au_sbi(sb)->si_nowait); + + si_noflush_read_lock(sb); + err = au_plink_maint(sb, flags); + if (unlikely(err)) + si_read_unlock(sb); + + return err; +} + +int si_write_lock(struct super_block *sb, int flags) +{ + int err; + + if (au_ftest_lock(flags, FLUSH)) + au_nwt_flush(&au_sbi(sb)->si_nowait); + + si_noflush_write_lock(sb); + err = au_plink_maint(sb, flags); + if (unlikely(err)) + si_write_unlock(sb); + + return err; +} + +/* dentry and super_block lock. call at entry point */ +int aufs_read_lock(struct dentry *dentry, int flags) +{ + int err; + struct super_block *sb; + + sb = dentry->d_sb; + err = si_read_lock(sb, flags); + if (unlikely(err)) + goto out; + + if (au_ftest_lock(flags, DW)) + di_write_lock_child(dentry); + else + di_read_lock_child(dentry, flags); + + if (au_ftest_lock(flags, GEN)) { + err = au_digen_test(dentry, au_sigen(sb)); + AuDebugOn(!err && au_dbrange_test(dentry)); + if (unlikely(err)) + aufs_read_unlock(dentry, flags); + } + +out: + return err; +} + +void aufs_read_unlock(struct dentry *dentry, int flags) +{ + if (au_ftest_lock(flags, DW)) + di_write_unlock(dentry); + else + di_read_unlock(dentry, flags); + si_read_unlock(dentry->d_sb); +} + +void aufs_write_lock(struct dentry *dentry) +{ + si_write_lock(dentry->d_sb, AuLock_FLUSH | AuLock_NOPLMW); + di_write_lock_child(dentry); +} + +void aufs_write_unlock(struct dentry *dentry) +{ + di_write_unlock(dentry); + si_write_unlock(dentry->d_sb); +} + +int aufs_read_and_write_lock2(struct dentry *d1, struct dentry *d2, int flags) +{ + int err; + unsigned int sigen; + struct super_block *sb; + + sb = d1->d_sb; + err = si_read_lock(sb, flags); + if (unlikely(err)) + goto out; + + di_write_lock2_child(d1, d2, au_ftest_lock(flags, DIR)); + + if (au_ftest_lock(flags, GEN)) { + sigen = au_sigen(sb); + err = au_digen_test(d1, sigen); + AuDebugOn(!err && au_dbrange_test(d1)); + if (!err) { + err = au_digen_test(d2, sigen); + AuDebugOn(!err && au_dbrange_test(d2)); + } + if (unlikely(err)) + aufs_read_and_write_unlock2(d1, d2); + } + +out: + return err; +} + +void aufs_read_and_write_unlock2(struct dentry *d1, struct dentry *d2) +{ + di_write_unlock2(d1, d2); + si_read_unlock(d1->d_sb); +} + +/* ---------------------------------------------------------------------- */ + +int si_pid_test_slow(struct super_block *sb) +{ + void *p; + + rcu_read_lock(); + p = radix_tree_lookup(&au_sbi(sb)->au_si_pid.tree, current->pid); + rcu_read_unlock(); + + return (long)!!p; +} + +void si_pid_set_slow(struct super_block *sb) +{ + int err; + struct au_sbinfo *sbinfo; + + AuDebugOn(si_pid_test_slow(sb)); + + sbinfo = au_sbi(sb); + err = radix_tree_preload(GFP_NOFS | __GFP_NOFAIL); + AuDebugOn(err); + spin_lock(&sbinfo->au_si_pid.tree_lock); + err = radix_tree_insert(&sbinfo->au_si_pid.tree, current->pid, + /*any valid ptr*/sb); + spin_unlock(&sbinfo->au_si_pid.tree_lock); + AuDebugOn(err); + radix_tree_preload_end(); +} + +void si_pid_clr_slow(struct super_block *sb) +{ + void *p; + struct au_sbinfo *sbinfo; + + AuDebugOn(!si_pid_test_slow(sb)); + + sbinfo = au_sbi(sb); + spin_lock(&sbinfo->au_si_pid.tree_lock); + p = radix_tree_delete(&sbinfo->au_si_pid.tree, current->pid); + spin_unlock(&sbinfo->au_si_pid.tree_lock); +} diff --git a/ubuntu/aufs/spl.h b/ubuntu/aufs/spl.h new file mode 100644 index 000000000000..743a3076207c --- /dev/null +++ b/ubuntu/aufs/spl.h @@ -0,0 +1,62 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * simple list protected by a spinlock + */ + +#ifndef __AUFS_SPL_H__ +#define __AUFS_SPL_H__ + +#ifdef __KERNEL__ + +struct au_splhead { + spinlock_t spin; + struct list_head head; +}; + +static inline void au_spl_init(struct au_splhead *spl) +{ + spin_lock_init(&spl->spin); + INIT_LIST_HEAD(&spl->head); +} + +static inline void au_spl_add(struct list_head *list, struct au_splhead *spl) +{ + spin_lock(&spl->spin); + list_add(list, &spl->head); + spin_unlock(&spl->spin); +} + +static inline void au_spl_del(struct list_head *list, struct au_splhead *spl) +{ + spin_lock(&spl->spin); + list_del(list); + spin_unlock(&spl->spin); +} + +static inline void au_spl_del_rcu(struct list_head *list, + struct au_splhead *spl) +{ + spin_lock(&spl->spin); + list_del_rcu(list); + spin_unlock(&spl->spin); +} + +#endif /* __KERNEL__ */ +#endif /* __AUFS_SPL_H__ */ diff --git a/ubuntu/aufs/super.c b/ubuntu/aufs/super.c new file mode 100644 index 000000000000..c798792b74e9 --- /dev/null +++ b/ubuntu/aufs/super.c @@ -0,0 +1,938 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * mount and super_block operations + */ + +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/seq_file.h> +#include <linux/statfs.h> +#include <linux/vmalloc.h> +#include <linux/writeback.h> +#include "aufs.h" + +/* + * super_operations + */ +static struct inode *aufs_alloc_inode(struct super_block *sb __maybe_unused) +{ + struct au_icntnr *c; + + c = au_cache_alloc_icntnr(); + if (c) { + au_icntnr_init(c); + c->vfs_inode.i_version = 1; /* sigen(sb); */ + c->iinfo.ii_hinode = NULL; + return &c->vfs_inode; + } + return NULL; +} + +static void aufs_destroy_inode_cb(struct rcu_head *head) +{ + struct inode *inode = container_of(head, struct inode, i_rcu); + + INIT_LIST_HEAD(&inode->i_dentry); + au_cache_free_icntnr(container_of(inode, struct au_icntnr, vfs_inode)); +} + +static void aufs_destroy_inode(struct inode *inode) +{ + au_iinfo_fin(inode); + call_rcu(&inode->i_rcu, aufs_destroy_inode_cb); +} + +struct inode *au_iget_locked(struct super_block *sb, ino_t ino) +{ + struct inode *inode; + int err; + + inode = iget_locked(sb, ino); + if (unlikely(!inode)) { + inode = ERR_PTR(-ENOMEM); + goto out; + } + if (!(inode->i_state & I_NEW)) + goto out; + + err = au_xigen_new(inode); + if (!err) + err = au_iinfo_init(inode); + if (!err) + inode->i_version++; + else { + iget_failed(inode); + inode = ERR_PTR(err); + } + +out: + /* never return NULL */ + AuDebugOn(!inode); + AuTraceErrPtr(inode); + return inode; +} + +/* lock free root dinfo */ +static int au_show_brs(struct seq_file *seq, struct super_block *sb) +{ + int err; + aufs_bindex_t bindex, bend; + struct path path; + struct au_hdentry *hdp; + struct au_branch *br; + char *perm; + + err = 0; + bend = au_sbend(sb); + hdp = au_di(sb->s_root)->di_hdentry; + for (bindex = 0; !err && bindex <= bend; bindex++) { + br = au_sbr(sb, bindex); + path.mnt = br->br_mnt; + path.dentry = hdp[bindex].hd_dentry; + err = au_seq_path(seq, &path); + if (err > 0) { + perm = au_optstr_br_perm(br->br_perm); + if (perm) { + err = seq_printf(seq, "=%s", perm); + kfree(perm); + if (err == -1) + err = -E2BIG; + } else + err = -ENOMEM; + } + if (!err && bindex != bend) + err = seq_putc(seq, ':'); + } + + return err; +} + +static void au_show_wbr_create(struct seq_file *m, int v, + struct au_sbinfo *sbinfo) +{ + const char *pat; + + AuRwMustAnyLock(&sbinfo->si_rwsem); + + seq_printf(m, ",create="); + pat = au_optstr_wbr_create(v); + switch (v) { + case AuWbrCreate_TDP: + case AuWbrCreate_RR: + case AuWbrCreate_MFS: + case AuWbrCreate_PMFS: + seq_printf(m, pat); + break; + case AuWbrCreate_MFSV: + seq_printf(m, /*pat*/"mfs:%lu", + jiffies_to_msecs(sbinfo->si_wbr_mfs.mfs_expire) + / MSEC_PER_SEC); + break; + case AuWbrCreate_PMFSV: + seq_printf(m, /*pat*/"pmfs:%lu", + jiffies_to_msecs(sbinfo->si_wbr_mfs.mfs_expire) + / MSEC_PER_SEC); + break; + case AuWbrCreate_MFSRR: + seq_printf(m, /*pat*/"mfsrr:%llu", + sbinfo->si_wbr_mfs.mfsrr_watermark); + break; + case AuWbrCreate_MFSRRV: + seq_printf(m, /*pat*/"mfsrr:%llu:%lu", + sbinfo->si_wbr_mfs.mfsrr_watermark, + jiffies_to_msecs(sbinfo->si_wbr_mfs.mfs_expire) + / MSEC_PER_SEC); + break; + } +} + +static int au_show_xino(struct seq_file *seq, struct vfsmount *mnt) +{ +#ifdef CONFIG_SYSFS + return 0; +#else + int err; + const int len = sizeof(AUFS_XINO_FNAME) - 1; + aufs_bindex_t bindex, brid; + struct super_block *sb; + struct qstr *name; + struct file *f; + struct dentry *d, *h_root; + struct au_hdentry *hdp; + + AuRwMustAnyLock(&sbinfo->si_rwsem); + + err = 0; + sb = mnt->mnt_sb; + f = au_sbi(sb)->si_xib; + if (!f) + goto out; + + /* stop printing the default xino path on the first writable branch */ + h_root = NULL; + brid = au_xino_brid(sb); + if (brid >= 0) { + bindex = au_br_index(sb, brid); + hdp = au_di(sb->s_root)->di_hdentry; + h_root = hdp[0 + bindex].hd_dentry; + } + d = f->f_dentry; + name = &d->d_name; + /* safe ->d_parent because the file is unlinked */ + if (d->d_parent == h_root + && name->len == len + && !memcmp(name->name, AUFS_XINO_FNAME, len)) + goto out; + + seq_puts(seq, ",xino="); + err = au_xino_path(seq, f); + +out: + return err; +#endif +} + +/* seq_file will re-call me in case of too long string */ +static int aufs_show_options(struct seq_file *m, struct vfsmount *mnt) +{ + int err; + unsigned int mnt_flags, v; + struct super_block *sb; + struct au_sbinfo *sbinfo; + +#define AuBool(name, str) do { \ + v = au_opt_test(mnt_flags, name); \ + if (v != au_opt_test(AuOpt_Def, name)) \ + seq_printf(m, ",%s" #str, v ? "" : "no"); \ +} while (0) + +#define AuStr(name, str) do { \ + v = mnt_flags & AuOptMask_##name; \ + if (v != (AuOpt_Def & AuOptMask_##name)) \ + seq_printf(m, "," #str "=%s", au_optstr_##str(v)); \ +} while (0) + +#define AuUInt(name, str, val) do { \ + if (val != AUFS_##name##_DEF) \ + seq_printf(m, "," #str "=%u", val); \ +} while (0) + + /* lock free root dinfo */ + sb = mnt->mnt_sb; + si_noflush_read_lock(sb); + sbinfo = au_sbi(sb); + seq_printf(m, ",si=%lx", sysaufs_si_id(sbinfo)); + + mnt_flags = au_mntflags(sb); + if (au_opt_test(mnt_flags, XINO)) { + err = au_show_xino(m, mnt); + if (unlikely(err)) + goto out; + } else + seq_puts(m, ",noxino"); + + AuBool(TRUNC_XINO, trunc_xino); + AuStr(UDBA, udba); + AuBool(SHWH, shwh); + AuBool(PLINK, plink); + AuBool(DIO, dio); + /* AuBool(DIRPERM1, dirperm1); */ + /* AuBool(REFROF, refrof); */ + + v = sbinfo->si_wbr_create; + if (v != AuWbrCreate_Def) + au_show_wbr_create(m, v, sbinfo); + + v = sbinfo->si_wbr_copyup; + if (v != AuWbrCopyup_Def) + seq_printf(m, ",cpup=%s", au_optstr_wbr_copyup(v)); + + v = au_opt_test(mnt_flags, ALWAYS_DIROPQ); + if (v != au_opt_test(AuOpt_Def, ALWAYS_DIROPQ)) + seq_printf(m, ",diropq=%c", v ? 'a' : 'w'); + + AuUInt(DIRWH, dirwh, sbinfo->si_dirwh); + + v = jiffies_to_msecs(sbinfo->si_rdcache) / MSEC_PER_SEC; + AuUInt(RDCACHE, rdcache, v); + + AuUInt(RDBLK, rdblk, sbinfo->si_rdblk); + AuUInt(RDHASH, rdhash, sbinfo->si_rdhash); + + AuBool(SUM, sum); + /* AuBool(SUM_W, wsum); */ + AuBool(WARN_PERM, warn_perm); + AuBool(VERBOSE, verbose); + +out: + /* be sure to print "br:" last */ + if (!sysaufs_brs) { + seq_puts(m, ",br:"); + au_show_brs(m, sb); + } + si_read_unlock(sb); + return 0; + +#undef AuBool +#undef AuStr +#undef AuUInt +} + +/* ---------------------------------------------------------------------- */ + +/* sum mode which returns the summation for statfs(2) */ + +static u64 au_add_till_max(u64 a, u64 b) +{ + u64 old; + + old = a; + a += b; + if (old < a) + return a; + return ULLONG_MAX; +} + +static int au_statfs_sum(struct super_block *sb, struct kstatfs *buf) +{ + int err; + u64 blocks, bfree, bavail, files, ffree; + aufs_bindex_t bend, bindex, i; + unsigned char shared; + struct path h_path; + struct super_block *h_sb; + + blocks = 0; + bfree = 0; + bavail = 0; + files = 0; + ffree = 0; + + err = 0; + bend = au_sbend(sb); + for (bindex = bend; bindex >= 0; bindex--) { + h_path.mnt = au_sbr_mnt(sb, bindex); + h_sb = h_path.mnt->mnt_sb; + shared = 0; + for (i = bindex + 1; !shared && i <= bend; i++) + shared = (au_sbr_sb(sb, i) == h_sb); + if (shared) + continue; + + /* sb->s_root for NFS is unreliable */ + h_path.dentry = h_path.mnt->mnt_root; + err = vfs_statfs(&h_path, buf); + if (unlikely(err)) + goto out; + + blocks = au_add_till_max(blocks, buf->f_blocks); + bfree = au_add_till_max(bfree, buf->f_bfree); + bavail = au_add_till_max(bavail, buf->f_bavail); + files = au_add_till_max(files, buf->f_files); + ffree = au_add_till_max(ffree, buf->f_ffree); + } + + buf->f_blocks = blocks; + buf->f_bfree = bfree; + buf->f_bavail = bavail; + buf->f_files = files; + buf->f_ffree = ffree; + +out: + return err; +} + +static int aufs_statfs(struct dentry *dentry, struct kstatfs *buf) +{ + int err; + struct path h_path; + struct super_block *sb; + + /* lock free root dinfo */ + sb = dentry->d_sb; + si_noflush_read_lock(sb); + if (!au_opt_test(au_mntflags(sb), SUM)) { + /* sb->s_root for NFS is unreliable */ + h_path.mnt = au_sbr_mnt(sb, 0); + h_path.dentry = h_path.mnt->mnt_root; + err = vfs_statfs(&h_path, buf); + } else + err = au_statfs_sum(sb, buf); + si_read_unlock(sb); + + if (!err) { + buf->f_type = AUFS_SUPER_MAGIC; + buf->f_namelen = AUFS_MAX_NAMELEN; + memset(&buf->f_fsid, 0, sizeof(buf->f_fsid)); + } + /* buf->f_bsize = buf->f_blocks = buf->f_bfree = buf->f_bavail = -1; */ + + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* final actions when unmounting a file system */ +static void aufs_put_super(struct super_block *sb) +{ + struct au_sbinfo *sbinfo; + + sbinfo = au_sbi(sb); + if (!sbinfo) + return; + + dbgaufs_si_fin(sbinfo); + kobject_put(&sbinfo->si_kobj); +} + +/* ---------------------------------------------------------------------- */ + +void au_array_free(void *array) +{ + if (array) { + if (!is_vmalloc_addr(array)) + kfree(array); + else + vfree(array); + } +} + +void *au_array_alloc(unsigned long long *hint, au_arraycb_t cb, void *arg) +{ + void *array; + unsigned long long n; + + array = NULL; + n = 0; + if (!*hint) + goto out; + + if (*hint > ULLONG_MAX / sizeof(array)) { + array = ERR_PTR(-EMFILE); + pr_err("hint %llu\n", *hint); + goto out; + } + + array = kmalloc(sizeof(array) * *hint, GFP_NOFS); + if (unlikely(!array)) + array = vmalloc(sizeof(array) * *hint); + if (unlikely(!array)) { + array = ERR_PTR(-ENOMEM); + goto out; + } + + n = cb(array, *hint, arg); + AuDebugOn(n > *hint); + +out: + *hint = n; + return array; +} + +static unsigned long long au_iarray_cb(void *a, + unsigned long long max __maybe_unused, + void *arg) +{ + unsigned long long n; + struct inode **p, *inode; + struct list_head *head; + + n = 0; + p = a; + head = arg; + spin_lock(&inode_sb_list_lock); + list_for_each_entry(inode, head, i_sb_list) { + if (!is_bad_inode(inode) + && au_ii(inode)->ii_bstart >= 0) { + spin_lock(&inode->i_lock); + if (atomic_read(&inode->i_count)) { + au_igrab(inode); + *p++ = inode; + n++; + AuDebugOn(n > max); + } + spin_unlock(&inode->i_lock); + } + } + spin_unlock(&inode_sb_list_lock); + + return n; +} + +struct inode **au_iarray_alloc(struct super_block *sb, unsigned long long *max) +{ + *max = atomic_long_read(&au_sbi(sb)->si_ninodes); + return au_array_alloc(max, au_iarray_cb, &sb->s_inodes); +} + +void au_iarray_free(struct inode **a, unsigned long long max) +{ + unsigned long long ull; + + for (ull = 0; ull < max; ull++) + iput(a[ull]); + au_array_free(a); +} + +/* ---------------------------------------------------------------------- */ + +/* + * refresh dentry and inode at remount time. + */ +/* todo: consolidate with simple_reval_dpath() and au_reval_for_attr() */ +static int au_do_refresh(struct dentry *dentry, unsigned int dir_flags, + struct dentry *parent) +{ + int err; + + di_write_lock_child(dentry); + di_read_lock_parent(parent, AuLock_IR); + err = au_refresh_dentry(dentry, parent); + if (!err && dir_flags) + au_hn_reset(dentry->d_inode, dir_flags); + di_read_unlock(parent, AuLock_IR); + di_write_unlock(dentry); + + return err; +} + +static int au_do_refresh_d(struct dentry *dentry, unsigned int sigen, + struct au_sbinfo *sbinfo, + const unsigned int dir_flags) +{ + int err; + struct dentry *parent; + struct inode *inode; + + err = 0; + parent = dget_parent(dentry); + if (!au_digen_test(parent, sigen) && au_digen_test(dentry, sigen)) { + inode = dentry->d_inode; + if (inode) { + if (!S_ISDIR(inode->i_mode)) + err = au_do_refresh(dentry, /*dir_flags*/0, + parent); + else { + err = au_do_refresh(dentry, dir_flags, parent); + if (unlikely(err)) + au_fset_si(sbinfo, FAILED_REFRESH_DIR); + } + } else + err = au_do_refresh(dentry, /*dir_flags*/0, parent); + AuDbgDentry(dentry); + } + dput(parent); + + AuTraceErr(err); + return err; +} + +static int au_refresh_d(struct super_block *sb) +{ + int err, i, j, ndentry, e; + unsigned int sigen; + struct au_dcsub_pages dpages; + struct au_dpage *dpage; + struct dentry **dentries, *d; + struct au_sbinfo *sbinfo; + struct dentry *root = sb->s_root; + const unsigned int dir_flags = au_hi_flags(root->d_inode, /*isdir*/1); + + err = au_dpages_init(&dpages, GFP_NOFS); + if (unlikely(err)) + goto out; + err = au_dcsub_pages(&dpages, root, NULL, NULL); + if (unlikely(err)) + goto out_dpages; + + sigen = au_sigen(sb); + sbinfo = au_sbi(sb); + for (i = 0; i < dpages.ndpage; i++) { + dpage = dpages.dpages + i; + dentries = dpage->dentries; + ndentry = dpage->ndentry; + for (j = 0; j < ndentry; j++) { + d = dentries[j]; + e = au_do_refresh_d(d, sigen, sbinfo, dir_flags); + if (unlikely(e && !err)) + err = e; + /* go on even err */ + } + } + +out_dpages: + au_dpages_free(&dpages); +out: + return err; +} + +static int au_refresh_i(struct super_block *sb) +{ + int err, e; + unsigned int sigen; + unsigned long long max, ull; + struct inode *inode, **array; + + array = au_iarray_alloc(sb, &max); + err = PTR_ERR(array); + if (IS_ERR(array)) + goto out; + + err = 0; + sigen = au_sigen(sb); + for (ull = 0; ull < max; ull++) { + inode = array[ull]; + if (au_iigen(inode) != sigen) { + ii_write_lock_child(inode); + e = au_refresh_hinode_self(inode); + ii_write_unlock(inode); + if (unlikely(e)) { + pr_err("error %d, i%lu\n", e, inode->i_ino); + if (!err) + err = e; + /* go on even if err */ + } + } + } + + au_iarray_free(array, max); + +out: + return err; +} + +static void au_remount_refresh(struct super_block *sb) +{ + int err, e; + unsigned int udba; + aufs_bindex_t bindex, bend; + struct dentry *root; + struct inode *inode; + struct au_branch *br; + + au_sigen_inc(sb); + au_fclr_si(au_sbi(sb), FAILED_REFRESH_DIR); + + root = sb->s_root; + DiMustNoWaiters(root); + inode = root->d_inode; + IiMustNoWaiters(inode); + + udba = au_opt_udba(sb); + bend = au_sbend(sb); + for (bindex = 0; bindex <= bend; bindex++) { + br = au_sbr(sb, bindex); + err = au_hnotify_reset_br(udba, br, br->br_perm); + if (unlikely(err)) + AuIOErr("hnotify failed on br %d, %d, ignored\n", + bindex, err); + /* go on even if err */ + } + au_hn_reset(inode, au_hi_flags(inode, /*isdir*/1)); + + di_write_unlock(root); + err = au_refresh_d(sb); + e = au_refresh_i(sb); + if (unlikely(e && !err)) + err = e; + /* aufs_write_lock() calls ..._child() */ + di_write_lock_child(root); + + au_cpup_attr_all(inode, /*force*/1); + + if (unlikely(err)) + AuIOErr("refresh failed, ignored, %d\n", err); +} + +/* stop extra interpretation of errno in mount(8), and strange error messages */ +static int cvt_err(int err) +{ + AuTraceErr(err); + + switch (err) { + case -ENOENT: + case -ENOTDIR: + case -EEXIST: + case -EIO: + err = -EINVAL; + } + return err; +} + +static int aufs_remount_fs(struct super_block *sb, int *flags, char *data) +{ + int err, do_dx; + unsigned int mntflags; + struct au_opts opts; + struct dentry *root; + struct inode *inode; + struct au_sbinfo *sbinfo; + + err = 0; + root = sb->s_root; + if (!data || !*data) { + err = si_write_lock(sb, AuLock_FLUSH | AuLock_NOPLM); + if (!err) { + di_write_lock_child(root); + err = au_opts_verify(sb, *flags, /*pending*/0); + aufs_write_unlock(root); + } + goto out; + } + + err = -ENOMEM; + memset(&opts, 0, sizeof(opts)); + opts.opt = (void *)__get_free_page(GFP_NOFS); + if (unlikely(!opts.opt)) + goto out; + opts.max_opt = PAGE_SIZE / sizeof(*opts.opt); + opts.flags = AuOpts_REMOUNT; + opts.sb_flags = *flags; + + /* parse it before aufs lock */ + err = au_opts_parse(sb, data, &opts); + if (unlikely(err)) + goto out_opts; + + sbinfo = au_sbi(sb); + inode = root->d_inode; + mutex_lock(&inode->i_mutex); + err = si_write_lock(sb, AuLock_FLUSH | AuLock_NOPLM); + if (unlikely(err)) + goto out_mtx; + di_write_lock_child(root); + + /* au_opts_remount() may return an error */ + err = au_opts_remount(sb, &opts); + au_opts_free(&opts); + + if (au_ftest_opts(opts.flags, REFRESH)) + au_remount_refresh(sb); + + if (au_ftest_opts(opts.flags, REFRESH_DYAOP)) { + mntflags = au_mntflags(sb); + do_dx = !!au_opt_test(mntflags, DIO); + au_dy_arefresh(do_dx); + } + + aufs_write_unlock(root); + +out_mtx: + mutex_unlock(&inode->i_mutex); +out_opts: + free_page((unsigned long)opts.opt); +out: + err = cvt_err(err); + AuTraceErr(err); + return err; +} + +static const struct super_operations aufs_sop = { + .alloc_inode = aufs_alloc_inode, + .destroy_inode = aufs_destroy_inode, + /* always deleting, no clearing */ + .drop_inode = generic_delete_inode, + .show_options = aufs_show_options, + .statfs = aufs_statfs, + .put_super = aufs_put_super, + .remount_fs = aufs_remount_fs +}; + +/* ---------------------------------------------------------------------- */ + +static int alloc_root(struct super_block *sb) +{ + int err; + struct inode *inode; + struct dentry *root; + + err = -ENOMEM; + inode = au_iget_locked(sb, AUFS_ROOT_INO); + err = PTR_ERR(inode); + if (IS_ERR(inode)) + goto out; + + inode->i_op = &aufs_dir_iop; + inode->i_fop = &aufs_dir_fop; + inode->i_mode = S_IFDIR; + set_nlink(inode, 2); + unlock_new_inode(inode); + + root = d_alloc_root(inode); + if (unlikely(!root)) + goto out_iput; + err = PTR_ERR(root); + if (IS_ERR(root)) + goto out_iput; + + err = au_di_init(root); + if (!err) { + sb->s_root = root; + return 0; /* success */ + } + dput(root); + goto out; /* do not iput */ + +out_iput: + iget_failed(inode); +out: + return err; + +} + +static int aufs_fill_super(struct super_block *sb, void *raw_data, + int silent __maybe_unused) +{ + int err; + struct au_opts opts; + struct dentry *root; + struct inode *inode; + char *arg = raw_data; + + if (unlikely(!arg || !*arg)) { + err = -EINVAL; + pr_err("no arg\n"); + goto out; + } + + err = -ENOMEM; + memset(&opts, 0, sizeof(opts)); + opts.opt = (void *)__get_free_page(GFP_NOFS); + if (unlikely(!opts.opt)) + goto out; + opts.max_opt = PAGE_SIZE / sizeof(*opts.opt); + opts.sb_flags = sb->s_flags; + + err = au_si_alloc(sb); + if (unlikely(err)) + goto out_opts; + + /* all timestamps always follow the ones on the branch */ + sb->s_flags |= MS_NOATIME | MS_NODIRATIME; + sb->s_op = &aufs_sop; + sb->s_d_op = &aufs_dop; + sb->s_magic = AUFS_SUPER_MAGIC; + sb->s_maxbytes = 0; + au_export_init(sb); + + err = alloc_root(sb); + if (unlikely(err)) { + si_write_unlock(sb); + goto out_info; + } + root = sb->s_root; + inode = root->d_inode; + + /* + * actually we can parse options regardless aufs lock here. + * but at remount time, parsing must be done before aufs lock. + * so we follow the same rule. + */ + ii_write_lock_parent(inode); + aufs_write_unlock(root); + err = au_opts_parse(sb, arg, &opts); + if (unlikely(err)) + goto out_root; + + /* lock vfs_inode first, then aufs. */ + mutex_lock(&inode->i_mutex); + aufs_write_lock(root); + err = au_opts_mount(sb, &opts); + au_opts_free(&opts); + aufs_write_unlock(root); + mutex_unlock(&inode->i_mutex); + if (!err) + goto out_opts; /* success */ + +out_root: + dput(root); + sb->s_root = NULL; +out_info: + dbgaufs_si_fin(au_sbi(sb)); + kobject_put(&au_sbi(sb)->si_kobj); + sb->s_fs_info = NULL; +out_opts: + free_page((unsigned long)opts.opt); +out: + AuTraceErr(err); + err = cvt_err(err); + AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +static struct dentry *aufs_mount(struct file_system_type *fs_type, int flags, + const char *dev_name __maybe_unused, + void *raw_data) +{ + struct dentry *root; + struct super_block *sb; + + /* all timestamps always follow the ones on the branch */ + /* mnt->mnt_flags |= MNT_NOATIME | MNT_NODIRATIME; */ + root = mount_nodev(fs_type, flags, raw_data, aufs_fill_super); + if (IS_ERR(root)) + goto out; + + sb = root->d_sb; + si_write_lock(sb, !AuLock_FLUSH); + sysaufs_brs_add(sb, 0); + si_write_unlock(sb); + au_sbilist_add(sb); + +out: + return root; +} + +static void aufs_kill_sb(struct super_block *sb) +{ + struct au_sbinfo *sbinfo; + + sbinfo = au_sbi(sb); + if (sbinfo) { + au_sbilist_del(sb); + aufs_write_lock(sb->s_root); + if (sbinfo->si_wbr_create_ops->fin) + sbinfo->si_wbr_create_ops->fin(sb); + if (au_opt_test(sbinfo->si_mntflags, UDBA_HNOTIFY)) { + au_opt_set_udba(sbinfo->si_mntflags, UDBA_NONE); + au_remount_refresh(sb); + } + if (au_opt_test(sbinfo->si_mntflags, PLINK)) + au_plink_put(sb, /*verbose*/1); + au_xino_clr(sb); + sbinfo->si_sb = NULL; + aufs_write_unlock(sb->s_root); + au_nwt_flush(&sbinfo->si_nowait); + } + generic_shutdown_super(sb); +} + +struct file_system_type aufs_fs_type = { + .name = AUFS_FSTYPE, + .fs_flags = + FS_RENAME_DOES_D_MOVE /* a race between rename and others */ + | FS_REVAL_DOT, /* for NFS branch and udba */ + .mount = aufs_mount, + .kill_sb = aufs_kill_sb, + /* no need to __module_get() and module_put(). */ + .owner = THIS_MODULE, +}; diff --git a/ubuntu/aufs/super.h b/ubuntu/aufs/super.h new file mode 100644 index 000000000000..9967dee0a50e --- /dev/null +++ b/ubuntu/aufs/super.h @@ -0,0 +1,546 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * super_block operations + */ + +#ifndef __AUFS_SUPER_H__ +#define __AUFS_SUPER_H__ + +#ifdef __KERNEL__ + +#include <linux/fs.h> +#include "rwsem.h" +#include "spl.h" +#include "wkq.h" + +typedef ssize_t (*au_readf_t)(struct file *, char __user *, size_t, loff_t *); +typedef ssize_t (*au_writef_t)(struct file *, const char __user *, size_t, + loff_t *); + +/* policies to select one among multiple writable branches */ +struct au_wbr_copyup_operations { + int (*copyup)(struct dentry *dentry); +}; + +struct au_wbr_create_operations { + int (*create)(struct dentry *dentry, int isdir); + int (*init)(struct super_block *sb); + int (*fin)(struct super_block *sb); +}; + +struct au_wbr_mfs { + struct mutex mfs_lock; /* protect this structure */ + unsigned long mfs_jiffy; + unsigned long mfs_expire; + aufs_bindex_t mfs_bindex; + + unsigned long long mfsrr_bytes; + unsigned long long mfsrr_watermark; +}; + +struct au_branch; +struct au_sbinfo { + /* nowait tasks in the system-wide workqueue */ + struct au_nowait_tasks si_nowait; + + /* + * tried sb->s_umount, but failed due to the dependecy between i_mutex. + * rwsem for au_sbinfo is necessary. + */ + struct au_rwsem si_rwsem; + + /* prevent recursive locking in deleting inode */ + struct { + unsigned long *bitmap; + spinlock_t tree_lock; + struct radix_tree_root tree; + } au_si_pid; + + /* + * dirty approach to protect sb->sb_inodes and ->s_files from remount. + */ + atomic_long_t si_ninodes, si_nfiles; + + /* branch management */ + unsigned int si_generation; + + /* see above flags */ + unsigned char au_si_status; + + aufs_bindex_t si_bend; + + /* dirty trick to keep br_id plus */ + unsigned int si_last_br_id : + sizeof(aufs_bindex_t) * BITS_PER_BYTE - 1; + struct au_branch **si_branch; + + /* policy to select a writable branch */ + unsigned char si_wbr_copyup; + unsigned char si_wbr_create; + struct au_wbr_copyup_operations *si_wbr_copyup_ops; + struct au_wbr_create_operations *si_wbr_create_ops; + + /* round robin */ + atomic_t si_wbr_rr_next; + + /* most free space */ + struct au_wbr_mfs si_wbr_mfs; + + /* mount flags */ + /* include/asm-ia64/siginfo.h defines a macro named si_flags */ + unsigned int si_mntflags; + + /* external inode number (bitmap and translation table) */ + au_readf_t si_xread; + au_writef_t si_xwrite; + struct file *si_xib; + struct mutex si_xib_mtx; /* protect xib members */ + unsigned long *si_xib_buf; + unsigned long si_xib_last_pindex; + int si_xib_next_bit; + aufs_bindex_t si_xino_brid; + /* reserved for future use */ + /* unsigned long long si_xib_limit; */ /* Max xib file size */ + +#ifdef CONFIG_AUFS_EXPORT + /* i_generation */ + struct file *si_xigen; + atomic_t si_xigen_next; +#endif + + /* vdir parameters */ + unsigned long si_rdcache; /* max cache time in jiffies */ + unsigned int si_rdblk; /* deblk size */ + unsigned int si_rdhash; /* hash size */ + + /* + * If the number of whiteouts are larger than si_dirwh, leave all of + * them after au_whtmp_ren to reduce the cost of rmdir(2). + * future fsck.aufs or kernel thread will remove them later. + * Otherwise, remove all whiteouts and the dir in rmdir(2). + */ + unsigned int si_dirwh; + + /* + * rename(2) a directory with all children. + */ + /* reserved for future use */ + /* int si_rendir; */ + + /* pseudo_link list */ + struct au_splhead si_plink; + wait_queue_head_t si_plink_wq; + spinlock_t si_plink_maint_lock; + pid_t si_plink_maint_pid; + + /* + * sysfs and lifetime management. + * this is not a small structure and it may be a waste of memory in case + * of sysfs is disabled, particulary when many aufs-es are mounted. + * but using sysfs is majority. + */ + struct kobject si_kobj; +#ifdef CONFIG_DEBUG_FS + struct dentry *si_dbgaufs, *si_dbgaufs_xib; +#ifdef CONFIG_AUFS_EXPORT + struct dentry *si_dbgaufs_xigen; +#endif +#endif + +#ifdef CONFIG_AUFS_SBILIST + struct list_head si_list; +#endif + + /* dirty, necessary for unmounting, sysfs and sysrq */ + struct super_block *si_sb; +}; + +/* sbinfo status flags */ +/* + * set true when refresh_dirs() failed at remount time. + * then try refreshing dirs at access time again. + * if it is false, refreshing dirs at access time is unnecesary + */ +#define AuSi_FAILED_REFRESH_DIR 1 +static inline unsigned char au_do_ftest_si(struct au_sbinfo *sbi, + unsigned int flag) +{ + AuRwMustAnyLock(&sbi->si_rwsem); + return sbi->au_si_status & flag; +} +#define au_ftest_si(sbinfo, name) au_do_ftest_si(sbinfo, AuSi_##name) +#define au_fset_si(sbinfo, name) do { \ + AuRwMustWriteLock(&(sbinfo)->si_rwsem); \ + (sbinfo)->au_si_status |= AuSi_##name; \ +} while (0) +#define au_fclr_si(sbinfo, name) do { \ + AuRwMustWriteLock(&(sbinfo)->si_rwsem); \ + (sbinfo)->au_si_status &= ~AuSi_##name; \ +} while (0) + +/* ---------------------------------------------------------------------- */ + +/* policy to select one among writable branches */ +#define AuWbrCopyup(sbinfo, ...) \ + ((sbinfo)->si_wbr_copyup_ops->copyup(__VA_ARGS__)) +#define AuWbrCreate(sbinfo, ...) \ + ((sbinfo)->si_wbr_create_ops->create(__VA_ARGS__)) + +/* flags for si_read_lock()/aufs_read_lock()/di_read_lock() */ +#define AuLock_DW 1 /* write-lock dentry */ +#define AuLock_IR (1 << 1) /* read-lock inode */ +#define AuLock_IW (1 << 2) /* write-lock inode */ +#define AuLock_FLUSH (1 << 3) /* wait for 'nowait' tasks */ +#define AuLock_DIR (1 << 4) /* target is a dir */ +#define AuLock_NOPLM (1 << 5) /* return err in plm mode */ +#define AuLock_NOPLMW (1 << 6) /* wait for plm mode ends */ +#define AuLock_GEN (1 << 7) /* test digen/iigen */ +#define au_ftest_lock(flags, name) ((flags) & AuLock_##name) +#define au_fset_lock(flags, name) \ + do { (flags) |= AuLock_##name; } while (0) +#define au_fclr_lock(flags, name) \ + do { (flags) &= ~AuLock_##name; } while (0) + +/* ---------------------------------------------------------------------- */ + +/* super.c */ +extern struct file_system_type aufs_fs_type; +struct inode *au_iget_locked(struct super_block *sb, ino_t ino); +typedef unsigned long long (*au_arraycb_t)(void *array, unsigned long long max, + void *arg); +void au_array_free(void *array); +void *au_array_alloc(unsigned long long *hint, au_arraycb_t cb, void *arg); +struct inode **au_iarray_alloc(struct super_block *sb, unsigned long long *max); +void au_iarray_free(struct inode **a, unsigned long long max); + +/* sbinfo.c */ +void au_si_free(struct kobject *kobj); +int au_si_alloc(struct super_block *sb); +int au_sbr_realloc(struct au_sbinfo *sbinfo, int nbr); + +unsigned int au_sigen_inc(struct super_block *sb); +aufs_bindex_t au_new_br_id(struct super_block *sb); + +int si_read_lock(struct super_block *sb, int flags); +int si_write_lock(struct super_block *sb, int flags); +int aufs_read_lock(struct dentry *dentry, int flags); +void aufs_read_unlock(struct dentry *dentry, int flags); +void aufs_write_lock(struct dentry *dentry); +void aufs_write_unlock(struct dentry *dentry); +int aufs_read_and_write_lock2(struct dentry *d1, struct dentry *d2, int flags); +void aufs_read_and_write_unlock2(struct dentry *d1, struct dentry *d2); + +int si_pid_test_slow(struct super_block *sb); +void si_pid_set_slow(struct super_block *sb); +void si_pid_clr_slow(struct super_block *sb); + +/* wbr_policy.c */ +extern struct au_wbr_copyup_operations au_wbr_copyup_ops[]; +extern struct au_wbr_create_operations au_wbr_create_ops[]; +int au_cpdown_dirs(struct dentry *dentry, aufs_bindex_t bdst); + +/* ---------------------------------------------------------------------- */ + +static inline struct au_sbinfo *au_sbi(struct super_block *sb) +{ + return sb->s_fs_info; +} + +/* ---------------------------------------------------------------------- */ + +#ifdef CONFIG_AUFS_EXPORT +void au_export_init(struct super_block *sb); + +static inline int au_test_nfsd(void) +{ + struct task_struct *tsk = current; + + return (tsk->flags & PF_KTHREAD) + && !strcmp(tsk->comm, "nfsd"); +} + +void au_xigen_inc(struct inode *inode); +int au_xigen_new(struct inode *inode); +int au_xigen_set(struct super_block *sb, struct file *base); +void au_xigen_clr(struct super_block *sb); + +static inline int au_busy_or_stale(void) +{ + if (!au_test_nfsd()) + return -EBUSY; + return -ESTALE; +} +#else +AuStubVoid(au_export_init, struct super_block *sb) +AuStubInt0(au_test_nfsd, void) +AuStubVoid(au_xigen_inc, struct inode *inode) +AuStubInt0(au_xigen_new, struct inode *inode) +AuStubInt0(au_xigen_set, struct super_block *sb, struct file *base) +AuStubVoid(au_xigen_clr, struct super_block *sb) +static inline int au_busy_or_stale(void) +{ + return -EBUSY; +} +#endif /* CONFIG_AUFS_EXPORT */ + +/* ---------------------------------------------------------------------- */ + +#ifdef CONFIG_AUFS_SBILIST +/* module.c */ +extern struct au_splhead au_sbilist; + +static inline void au_sbilist_init(void) +{ + au_spl_init(&au_sbilist); +} + +static inline void au_sbilist_add(struct super_block *sb) +{ + au_spl_add(&au_sbi(sb)->si_list, &au_sbilist); +} + +static inline void au_sbilist_del(struct super_block *sb) +{ + au_spl_del(&au_sbi(sb)->si_list, &au_sbilist); +} + +#ifdef CONFIG_AUFS_MAGIC_SYSRQ +static inline void au_sbilist_lock(void) +{ + spin_lock(&au_sbilist.spin); +} + +static inline void au_sbilist_unlock(void) +{ + spin_unlock(&au_sbilist.spin); +} +#define AuGFP_SBILIST GFP_ATOMIC +#else +AuStubVoid(au_sbilist_lock, void) +AuStubVoid(au_sbilist_unlock, void) +#define AuGFP_SBILIST GFP_NOFS +#endif /* CONFIG_AUFS_MAGIC_SYSRQ */ +#else +AuStubVoid(au_sbilist_init, void) +AuStubVoid(au_sbilist_add, struct super_block*) +AuStubVoid(au_sbilist_del, struct super_block*) +AuStubVoid(au_sbilist_lock, void) +AuStubVoid(au_sbilist_unlock, void) +#define AuGFP_SBILIST GFP_NOFS +#endif + +/* ---------------------------------------------------------------------- */ + +static inline void dbgaufs_si_null(struct au_sbinfo *sbinfo) +{ + /* + * This function is a dynamic '__init' fucntion actually, + * so the tiny check for si_rwsem is unnecessary. + */ + /* AuRwMustWriteLock(&sbinfo->si_rwsem); */ +#ifdef CONFIG_DEBUG_FS + sbinfo->si_dbgaufs = NULL; + sbinfo->si_dbgaufs_xib = NULL; +#ifdef CONFIG_AUFS_EXPORT + sbinfo->si_dbgaufs_xigen = NULL; +#endif +#endif +} + +/* ---------------------------------------------------------------------- */ + +static inline pid_t si_pid_bit(void) +{ + /* the origin of pid is 1, but the bitmap's is 0 */ + return current->pid - 1; +} + +static inline int si_pid_test(struct super_block *sb) +{ + pid_t bit = si_pid_bit(); + if (bit < PID_MAX_DEFAULT) + return test_bit(bit, au_sbi(sb)->au_si_pid.bitmap); + else + return si_pid_test_slow(sb); +} + +static inline void si_pid_set(struct super_block *sb) +{ + pid_t bit = si_pid_bit(); + if (bit < PID_MAX_DEFAULT) { + AuDebugOn(test_bit(bit, au_sbi(sb)->au_si_pid.bitmap)); + set_bit(bit, au_sbi(sb)->au_si_pid.bitmap); + /* smp_mb(); */ + } else + si_pid_set_slow(sb); +} + +static inline void si_pid_clr(struct super_block *sb) +{ + pid_t bit = si_pid_bit(); + if (bit < PID_MAX_DEFAULT) { + AuDebugOn(!test_bit(bit, au_sbi(sb)->au_si_pid.bitmap)); + clear_bit(bit, au_sbi(sb)->au_si_pid.bitmap); + /* smp_mb(); */ + } else + si_pid_clr_slow(sb); +} + +/* ---------------------------------------------------------------------- */ + +/* lock superblock. mainly for entry point functions */ +/* + * __si_read_lock, __si_write_lock, + * __si_read_unlock, __si_write_unlock, __si_downgrade_lock + */ +AuSimpleRwsemFuncs(__si, struct super_block *sb, &au_sbi(sb)->si_rwsem); + +#define SiMustNoWaiters(sb) AuRwMustNoWaiters(&au_sbi(sb)->si_rwsem) +#define SiMustAnyLock(sb) AuRwMustAnyLock(&au_sbi(sb)->si_rwsem) +#define SiMustWriteLock(sb) AuRwMustWriteLock(&au_sbi(sb)->si_rwsem) + +static inline void si_noflush_read_lock(struct super_block *sb) +{ + __si_read_lock(sb); + si_pid_set(sb); +} + +static inline int si_noflush_read_trylock(struct super_block *sb) +{ + int locked = __si_read_trylock(sb); + if (locked) + si_pid_set(sb); + return locked; +} + +static inline void si_noflush_write_lock(struct super_block *sb) +{ + __si_write_lock(sb); + si_pid_set(sb); +} + +static inline int si_noflush_write_trylock(struct super_block *sb) +{ + int locked = __si_write_trylock(sb); + if (locked) + si_pid_set(sb); + return locked; +} + +#if 0 /* unused */ +static inline int si_read_trylock(struct super_block *sb, int flags) +{ + if (au_ftest_lock(flags, FLUSH)) + au_nwt_flush(&au_sbi(sb)->si_nowait); + return si_noflush_read_trylock(sb); +} +#endif + +static inline void si_read_unlock(struct super_block *sb) +{ + si_pid_clr(sb); + __si_read_unlock(sb); +} + +#if 0 /* unused */ +static inline int si_write_trylock(struct super_block *sb, int flags) +{ + if (au_ftest_lock(flags, FLUSH)) + au_nwt_flush(&au_sbi(sb)->si_nowait); + return si_noflush_write_trylock(sb); +} +#endif + +static inline void si_write_unlock(struct super_block *sb) +{ + si_pid_clr(sb); + __si_write_unlock(sb); +} + +#if 0 /* unused */ +static inline void si_downgrade_lock(struct super_block *sb) +{ + __si_downgrade_lock(sb); +} +#endif + +/* ---------------------------------------------------------------------- */ + +static inline aufs_bindex_t au_sbend(struct super_block *sb) +{ + SiMustAnyLock(sb); + return au_sbi(sb)->si_bend; +} + +static inline unsigned int au_mntflags(struct super_block *sb) +{ + SiMustAnyLock(sb); + return au_sbi(sb)->si_mntflags; +} + +static inline unsigned int au_sigen(struct super_block *sb) +{ + SiMustAnyLock(sb); + return au_sbi(sb)->si_generation; +} + +static inline void au_ninodes_inc(struct super_block *sb) +{ + atomic_long_inc(&au_sbi(sb)->si_ninodes); +} + +static inline void au_ninodes_dec(struct super_block *sb) +{ + AuDebugOn(!atomic_long_read(&au_sbi(sb)->si_ninodes)); + atomic_long_dec(&au_sbi(sb)->si_ninodes); +} + +static inline void au_nfiles_inc(struct super_block *sb) +{ + atomic_long_inc(&au_sbi(sb)->si_nfiles); +} + +static inline void au_nfiles_dec(struct super_block *sb) +{ + AuDebugOn(!atomic_long_read(&au_sbi(sb)->si_nfiles)); + atomic_long_dec(&au_sbi(sb)->si_nfiles); +} + +static inline struct au_branch *au_sbr(struct super_block *sb, + aufs_bindex_t bindex) +{ + SiMustAnyLock(sb); + return au_sbi(sb)->si_branch[0 + bindex]; +} + +static inline void au_xino_brid_set(struct super_block *sb, aufs_bindex_t brid) +{ + SiMustWriteLock(sb); + au_sbi(sb)->si_xino_brid = brid; +} + +static inline aufs_bindex_t au_xino_brid(struct super_block *sb) +{ + SiMustAnyLock(sb); + return au_sbi(sb)->si_xino_brid; +} + +#endif /* __KERNEL__ */ +#endif /* __AUFS_SUPER_H__ */ diff --git a/ubuntu/aufs/sysaufs.c b/ubuntu/aufs/sysaufs.c new file mode 100644 index 000000000000..a675324ca6f2 --- /dev/null +++ b/ubuntu/aufs/sysaufs.c @@ -0,0 +1,105 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * sysfs interface and lifetime management + * they are necessary regardless sysfs is disabled. + */ + +#include <linux/random.h> +#include "aufs.h" + +unsigned long sysaufs_si_mask; +struct kset *sysaufs_kset; + +#define AuSiAttr(_name) { \ + .attr = { .name = __stringify(_name), .mode = 0444 }, \ + .show = sysaufs_si_##_name, \ +} + +static struct sysaufs_si_attr sysaufs_si_attr_xi_path = AuSiAttr(xi_path); +struct attribute *sysaufs_si_attrs[] = { + &sysaufs_si_attr_xi_path.attr, + NULL, +}; + +static const struct sysfs_ops au_sbi_ops = { + .show = sysaufs_si_show +}; + +static struct kobj_type au_sbi_ktype = { + .release = au_si_free, + .sysfs_ops = &au_sbi_ops, + .default_attrs = sysaufs_si_attrs +}; + +/* ---------------------------------------------------------------------- */ + +int sysaufs_si_init(struct au_sbinfo *sbinfo) +{ + int err; + + sbinfo->si_kobj.kset = sysaufs_kset; + /* cf. sysaufs_name() */ + err = kobject_init_and_add + (&sbinfo->si_kobj, &au_sbi_ktype, /*&sysaufs_kset->kobj*/NULL, + SysaufsSiNamePrefix "%lx", sysaufs_si_id(sbinfo)); + + dbgaufs_si_null(sbinfo); + if (!err) { + err = dbgaufs_si_init(sbinfo); + if (unlikely(err)) + kobject_put(&sbinfo->si_kobj); + } + return err; +} + +void sysaufs_fin(void) +{ + dbgaufs_fin(); + sysfs_remove_group(&sysaufs_kset->kobj, sysaufs_attr_group); + kset_unregister(sysaufs_kset); +} + +int __init sysaufs_init(void) +{ + int err; + + do { + get_random_bytes(&sysaufs_si_mask, sizeof(sysaufs_si_mask)); + } while (!sysaufs_si_mask); + + err = -EINVAL; + sysaufs_kset = kset_create_and_add(AUFS_NAME, NULL, fs_kobj); + if (unlikely(!sysaufs_kset)) + goto out; + err = PTR_ERR(sysaufs_kset); + if (IS_ERR(sysaufs_kset)) + goto out; + err = sysfs_create_group(&sysaufs_kset->kobj, sysaufs_attr_group); + if (unlikely(err)) { + kset_unregister(sysaufs_kset); + goto out; + } + + err = dbgaufs_init(); + if (unlikely(err)) + sysaufs_fin(); +out: + return err; +} diff --git a/ubuntu/aufs/sysaufs.h b/ubuntu/aufs/sysaufs.h new file mode 100644 index 000000000000..5aaff3bb608b --- /dev/null +++ b/ubuntu/aufs/sysaufs.h @@ -0,0 +1,104 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * sysfs interface and mount lifetime management + */ + +#ifndef __SYSAUFS_H__ +#define __SYSAUFS_H__ + +#ifdef __KERNEL__ + +#include <linux/sysfs.h> +#include "module.h" + +struct super_block; +struct au_sbinfo; + +struct sysaufs_si_attr { + struct attribute attr; + int (*show)(struct seq_file *seq, struct super_block *sb); +}; + +/* ---------------------------------------------------------------------- */ + +/* sysaufs.c */ +extern unsigned long sysaufs_si_mask; +extern struct kset *sysaufs_kset; +extern struct attribute *sysaufs_si_attrs[]; +int sysaufs_si_init(struct au_sbinfo *sbinfo); +int __init sysaufs_init(void); +void sysaufs_fin(void); + +/* ---------------------------------------------------------------------- */ + +/* some people doesn't like to show a pointer in kernel */ +static inline unsigned long sysaufs_si_id(struct au_sbinfo *sbinfo) +{ + return sysaufs_si_mask ^ (unsigned long)sbinfo; +} + +#define SysaufsSiNamePrefix "si_" +#define SysaufsSiNameLen (sizeof(SysaufsSiNamePrefix) + 16) +static inline void sysaufs_name(struct au_sbinfo *sbinfo, char *name) +{ + snprintf(name, SysaufsSiNameLen, SysaufsSiNamePrefix "%lx", + sysaufs_si_id(sbinfo)); +} + +struct au_branch; +#ifdef CONFIG_SYSFS +/* sysfs.c */ +extern struct attribute_group *sysaufs_attr_group; + +int sysaufs_si_xi_path(struct seq_file *seq, struct super_block *sb); +ssize_t sysaufs_si_show(struct kobject *kobj, struct attribute *attr, + char *buf); + +void sysaufs_br_init(struct au_branch *br); +void sysaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex); +void sysaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex); + +#define sysaufs_brs_init() do {} while (0) + +#else +#define sysaufs_attr_group NULL + +AuStubInt0(sysaufs_si_xi_path, struct seq_file *seq, struct super_block *sb) + +static inline +ssize_t sysaufs_si_show(struct kobject *kobj, struct attribute *attr, + char *buf) +{ + return 0; +} + +AuStubVoid(sysaufs_br_init, struct au_branch *br) +AuStubVoid(sysaufs_brs_add, struct super_block *sb, aufs_bindex_t bindex) +AuStubVoid(sysaufs_brs_del, struct super_block *sb, aufs_bindex_t bindex) + +static inline void sysaufs_brs_init(void) +{ + sysaufs_brs = 0; +} + +#endif /* CONFIG_SYSFS */ + +#endif /* __KERNEL__ */ +#endif /* __SYSAUFS_H__ */ diff --git a/ubuntu/aufs/sysfs.c b/ubuntu/aufs/sysfs.c new file mode 100644 index 000000000000..f72519dac361 --- /dev/null +++ b/ubuntu/aufs/sysfs.c @@ -0,0 +1,257 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * sysfs interface + */ + +#include <linux/seq_file.h> +#include "aufs.h" + +#ifdef CONFIG_AUFS_FS_MODULE +/* this entry violates the "one line per file" policy of sysfs */ +static ssize_t config_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + ssize_t err; + static char *conf = +/* this file is generated at compiling */ +#include "conf.str" + ; + + err = snprintf(buf, PAGE_SIZE, conf); + if (unlikely(err >= PAGE_SIZE)) + err = -EFBIG; + return err; +} + +static struct kobj_attribute au_config_attr = __ATTR_RO(config); +#endif + +static struct attribute *au_attr[] = { +#ifdef CONFIG_AUFS_FS_MODULE + &au_config_attr.attr, +#endif + NULL, /* need to NULL terminate the list of attributes */ +}; + +static struct attribute_group sysaufs_attr_group_body = { + .attrs = au_attr +}; + +struct attribute_group *sysaufs_attr_group = &sysaufs_attr_group_body; + +/* ---------------------------------------------------------------------- */ + +int sysaufs_si_xi_path(struct seq_file *seq, struct super_block *sb) +{ + int err; + + SiMustAnyLock(sb); + + err = 0; + if (au_opt_test(au_mntflags(sb), XINO)) { + err = au_xino_path(seq, au_sbi(sb)->si_xib); + seq_putc(seq, '\n'); + } + return err; +} + +/* + * the lifetime of branch is independent from the entry under sysfs. + * sysfs handles the lifetime of the entry, and never call ->show() after it is + * unlinked. + */ +static int sysaufs_si_br(struct seq_file *seq, struct super_block *sb, + aufs_bindex_t bindex) +{ + int err; + struct path path; + struct dentry *root; + struct au_branch *br; + char *perm; + + AuDbg("b%d\n", bindex); + + err = 0; + root = sb->s_root; + di_read_lock_parent(root, !AuLock_IR); + br = au_sbr(sb, bindex); + path.mnt = br->br_mnt; + path.dentry = au_h_dptr(root, bindex); + au_seq_path(seq, &path); + di_read_unlock(root, !AuLock_IR); + perm = au_optstr_br_perm(br->br_perm); + if (perm) { + err = seq_printf(seq, "=%s\n", perm); + kfree(perm); + if (err == -1) + err = -E2BIG; + } else + err = -ENOMEM; + return err; +} + +/* ---------------------------------------------------------------------- */ + +static struct seq_file *au_seq(char *p, ssize_t len) +{ + struct seq_file *seq; + + seq = kzalloc(sizeof(*seq), GFP_NOFS); + if (seq) { + /* mutex_init(&seq.lock); */ + seq->buf = p; + seq->size = len; + return seq; /* success */ + } + + seq = ERR_PTR(-ENOMEM); + return seq; +} + +#define SysaufsBr_PREFIX "br" + +/* todo: file size may exceed PAGE_SIZE */ +ssize_t sysaufs_si_show(struct kobject *kobj, struct attribute *attr, + char *buf) +{ + ssize_t err; + long l; + aufs_bindex_t bend; + struct au_sbinfo *sbinfo; + struct super_block *sb; + struct seq_file *seq; + char *name; + struct attribute **cattr; + + sbinfo = container_of(kobj, struct au_sbinfo, si_kobj); + sb = sbinfo->si_sb; + + /* + * prevent a race condition between sysfs and aufs. + * for instance, sysfs_file_read() calls sysfs_get_active_two() which + * prohibits maintaining the sysfs entries. + * hew we acquire read lock after sysfs_get_active_two(). + * on the other hand, the remount process may maintain the sysfs/aufs + * entries after acquiring write lock. + * it can cause a deadlock. + * simply we gave up processing read here. + */ + err = -EBUSY; + if (unlikely(!si_noflush_read_trylock(sb))) + goto out; + + seq = au_seq(buf, PAGE_SIZE); + err = PTR_ERR(seq); + if (IS_ERR(seq)) + goto out_unlock; + + name = (void *)attr->name; + cattr = sysaufs_si_attrs; + while (*cattr) { + if (!strcmp(name, (*cattr)->name)) { + err = container_of(*cattr, struct sysaufs_si_attr, attr) + ->show(seq, sb); + goto out_seq; + } + cattr++; + } + + bend = au_sbend(sb); + if (!strncmp(name, SysaufsBr_PREFIX, sizeof(SysaufsBr_PREFIX) - 1)) { + name += sizeof(SysaufsBr_PREFIX) - 1; + err = kstrtol(name, 10, &l); + if (!err) { + if (l <= bend) + err = sysaufs_si_br(seq, sb, (aufs_bindex_t)l); + else + err = -ENOENT; + } + goto out_seq; + } + BUG(); + +out_seq: + if (!err) { + err = seq->count; + /* sysfs limit */ + if (unlikely(err == PAGE_SIZE)) + err = -EFBIG; + } + kfree(seq); +out_unlock: + si_read_unlock(sb); +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +void sysaufs_br_init(struct au_branch *br) +{ + struct attribute *attr = &br->br_attr; + + sysfs_attr_init(attr); + attr->name = br->br_name; + attr->mode = S_IRUGO; +} + +void sysaufs_brs_del(struct super_block *sb, aufs_bindex_t bindex) +{ + struct au_branch *br; + struct kobject *kobj; + aufs_bindex_t bend; + + dbgaufs_brs_del(sb, bindex); + + if (!sysaufs_brs) + return; + + kobj = &au_sbi(sb)->si_kobj; + bend = au_sbend(sb); + for (; bindex <= bend; bindex++) { + br = au_sbr(sb, bindex); + sysfs_remove_file(kobj, &br->br_attr); + } +} + +void sysaufs_brs_add(struct super_block *sb, aufs_bindex_t bindex) +{ + int err; + aufs_bindex_t bend; + struct kobject *kobj; + struct au_branch *br; + + dbgaufs_brs_add(sb, bindex); + + if (!sysaufs_brs) + return; + + kobj = &au_sbi(sb)->si_kobj; + bend = au_sbend(sb); + for (; bindex <= bend; bindex++) { + br = au_sbr(sb, bindex); + snprintf(br->br_name, sizeof(br->br_name), SysaufsBr_PREFIX + "%d", bindex); + err = sysfs_create_file(kobj, &br->br_attr); + if (unlikely(err)) + pr_warning("failed %s under sysfs(%d)\n", + br->br_name, err); + } +} diff --git a/ubuntu/aufs/sysrq.c b/ubuntu/aufs/sysrq.c new file mode 100644 index 000000000000..c481d2b6dd58 --- /dev/null +++ b/ubuntu/aufs/sysrq.c @@ -0,0 +1,148 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * magic sysrq hanlder + */ + +/* #include <linux/sysrq.h> */ +#include <linux/writeback.h> +#include "aufs.h" + +/* ---------------------------------------------------------------------- */ + +static void sysrq_sb(struct super_block *sb) +{ + char *plevel; + struct au_sbinfo *sbinfo; + struct file *file; + + plevel = au_plevel; + au_plevel = KERN_WARNING; + + sbinfo = au_sbi(sb); + /* since we define pr_fmt, call printk directly */ + printk(KERN_WARNING "si=%lx\n", sysaufs_si_id(sbinfo)); + printk(KERN_WARNING AUFS_NAME ": superblock\n"); + au_dpri_sb(sb); + +#if 0 + printk(KERN_WARNING AUFS_NAME ": root dentry\n"); + au_dpri_dentry(sb->s_root); + printk(KERN_WARNING AUFS_NAME ": root inode\n"); + au_dpri_inode(sb->s_root->d_inode); +#endif + +#if 0 + do { + int err, i, j, ndentry; + struct au_dcsub_pages dpages; + struct au_dpage *dpage; + + err = au_dpages_init(&dpages, GFP_ATOMIC); + if (unlikely(err)) + break; + err = au_dcsub_pages(&dpages, sb->s_root, NULL, NULL); + if (!err) + for (i = 0; i < dpages.ndpage; i++) { + dpage = dpages.dpages + i; + ndentry = dpage->ndentry; + for (j = 0; j < ndentry; j++) + au_dpri_dentry(dpage->dentries[j]); + } + au_dpages_free(&dpages); + } while (0); +#endif + +#if 1 + { + struct inode *i; + printk(KERN_WARNING AUFS_NAME ": isolated inode\n"); + spin_lock(&inode_sb_list_lock); + list_for_each_entry(i, &sb->s_inodes, i_sb_list) { + spin_lock(&i->i_lock); + if (1 || list_empty(&i->i_dentry)) + au_dpri_inode(i); + spin_unlock(&i->i_lock); + } + spin_unlock(&inode_sb_list_lock); + } +#endif + printk(KERN_WARNING AUFS_NAME ": files\n"); + lg_global_lock(files_lglock); + do_file_list_for_each_entry(sb, file) { + umode_t mode; + mode = file->f_dentry->d_inode->i_mode; + if (!special_file(mode) || au_special_file(mode)) + au_dpri_file(file); + } while_file_list_for_each_entry; + lg_global_unlock(files_lglock); + printk(KERN_WARNING AUFS_NAME ": done\n"); + + au_plevel = plevel; +} + +/* ---------------------------------------------------------------------- */ + +/* module parameter */ +static char *aufs_sysrq_key = "a"; +module_param_named(sysrq, aufs_sysrq_key, charp, S_IRUGO); +MODULE_PARM_DESC(sysrq, "MagicSysRq key for " AUFS_NAME); + +static void au_sysrq(int key __maybe_unused) +{ + struct au_sbinfo *sbinfo; + + lockdep_off(); + au_sbilist_lock(); + list_for_each_entry(sbinfo, &au_sbilist.head, si_list) + sysrq_sb(sbinfo->si_sb); + au_sbilist_unlock(); + lockdep_on(); +} + +static struct sysrq_key_op au_sysrq_op = { + .handler = au_sysrq, + .help_msg = "Aufs", + .action_msg = "Aufs", + .enable_mask = SYSRQ_ENABLE_DUMP +}; + +/* ---------------------------------------------------------------------- */ + +int __init au_sysrq_init(void) +{ + int err; + char key; + + err = -1; + key = *aufs_sysrq_key; + if ('a' <= key && key <= 'z') + err = register_sysrq_key(key, &au_sysrq_op); + if (unlikely(err)) + pr_err("err %d, sysrq=%c\n", err, key); + return err; +} + +void au_sysrq_fin(void) +{ + int err; + err = unregister_sysrq_key(*aufs_sysrq_key, &au_sysrq_op); + if (unlikely(err)) + pr_err("err %d (ignored)\n", err); +} diff --git a/ubuntu/aufs/vdir.c b/ubuntu/aufs/vdir.c new file mode 100644 index 000000000000..3f16d5153774 --- /dev/null +++ b/ubuntu/aufs/vdir.c @@ -0,0 +1,885 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * virtual or vertical directory + */ + +#include "aufs.h" + +static unsigned int calc_size(int nlen) +{ + return ALIGN(sizeof(struct au_vdir_de) + nlen, sizeof(ino_t)); +} + +static int set_deblk_end(union au_vdir_deblk_p *p, + union au_vdir_deblk_p *deblk_end) +{ + if (calc_size(0) <= deblk_end->deblk - p->deblk) { + p->de->de_str.len = 0; + /* smp_mb(); */ + return 0; + } + return -1; /* error */ +} + +/* returns true or false */ +static int is_deblk_end(union au_vdir_deblk_p *p, + union au_vdir_deblk_p *deblk_end) +{ + if (calc_size(0) <= deblk_end->deblk - p->deblk) + return !p->de->de_str.len; + return 1; +} + +static unsigned char *last_deblk(struct au_vdir *vdir) +{ + return vdir->vd_deblk[vdir->vd_nblk - 1]; +} + +/* ---------------------------------------------------------------------- */ + +/* estimate the apropriate size for name hash table */ +unsigned int au_rdhash_est(loff_t sz) +{ + unsigned int n; + + n = UINT_MAX; + sz >>= 10; + if (sz < n) + n = sz; + if (sz < AUFS_RDHASH_DEF) + n = AUFS_RDHASH_DEF; + /* pr_info("n %u\n", n); */ + return n; +} + +/* + * the allocated memory has to be freed by + * au_nhash_wh_free() or au_nhash_de_free(). + */ +int au_nhash_alloc(struct au_nhash *nhash, unsigned int num_hash, gfp_t gfp) +{ + struct hlist_head *head; + unsigned int u; + + head = kmalloc(sizeof(*nhash->nh_head) * num_hash, gfp); + if (head) { + nhash->nh_num = num_hash; + nhash->nh_head = head; + for (u = 0; u < num_hash; u++) + INIT_HLIST_HEAD(head++); + return 0; /* success */ + } + + return -ENOMEM; +} + +static void nhash_count(struct hlist_head *head) +{ +#if 0 + unsigned long n; + struct hlist_node *pos; + + n = 0; + hlist_for_each(pos, head) + n++; + pr_info("%lu\n", n); +#endif +} + +static void au_nhash_wh_do_free(struct hlist_head *head) +{ + struct au_vdir_wh *tpos; + struct hlist_node *pos, *node; + + hlist_for_each_entry_safe(tpos, pos, node, head, wh_hash) { + /* hlist_del(pos); */ + kfree(tpos); + } +} + +static void au_nhash_de_do_free(struct hlist_head *head) +{ + struct au_vdir_dehstr *tpos; + struct hlist_node *pos, *node; + + hlist_for_each_entry_safe(tpos, pos, node, head, hash) { + /* hlist_del(pos); */ + au_cache_free_vdir_dehstr(tpos); + } +} + +static void au_nhash_do_free(struct au_nhash *nhash, + void (*free)(struct hlist_head *head)) +{ + unsigned int n; + struct hlist_head *head; + + n = nhash->nh_num; + if (!n) + return; + + head = nhash->nh_head; + while (n-- > 0) { + nhash_count(head); + free(head++); + } + kfree(nhash->nh_head); +} + +void au_nhash_wh_free(struct au_nhash *whlist) +{ + au_nhash_do_free(whlist, au_nhash_wh_do_free); +} + +static void au_nhash_de_free(struct au_nhash *delist) +{ + au_nhash_do_free(delist, au_nhash_de_do_free); +} + +/* ---------------------------------------------------------------------- */ + +int au_nhash_test_longer_wh(struct au_nhash *whlist, aufs_bindex_t btgt, + int limit) +{ + int num; + unsigned int u, n; + struct hlist_head *head; + struct au_vdir_wh *tpos; + struct hlist_node *pos; + + num = 0; + n = whlist->nh_num; + head = whlist->nh_head; + for (u = 0; u < n; u++, head++) + hlist_for_each_entry(tpos, pos, head, wh_hash) + if (tpos->wh_bindex == btgt && ++num > limit) + return 1; + return 0; +} + +static struct hlist_head *au_name_hash(struct au_nhash *nhash, + unsigned char *name, + unsigned int len) +{ + unsigned int v; + /* const unsigned int magic_bit = 12; */ + + AuDebugOn(!nhash->nh_num || !nhash->nh_head); + + v = 0; + while (len--) + v += *name++; + /* v = hash_long(v, magic_bit); */ + v %= nhash->nh_num; + return nhash->nh_head + v; +} + +static int au_nhash_test_name(struct au_vdir_destr *str, const char *name, + int nlen) +{ + return str->len == nlen && !memcmp(str->name, name, nlen); +} + +/* returns found or not */ +int au_nhash_test_known_wh(struct au_nhash *whlist, char *name, int nlen) +{ + struct hlist_head *head; + struct au_vdir_wh *tpos; + struct hlist_node *pos; + struct au_vdir_destr *str; + + head = au_name_hash(whlist, name, nlen); + hlist_for_each_entry(tpos, pos, head, wh_hash) { + str = &tpos->wh_str; + AuDbg("%.*s\n", str->len, str->name); + if (au_nhash_test_name(str, name, nlen)) + return 1; + } + return 0; +} + +/* returns found(true) or not */ +static int test_known(struct au_nhash *delist, char *name, int nlen) +{ + struct hlist_head *head; + struct au_vdir_dehstr *tpos; + struct hlist_node *pos; + struct au_vdir_destr *str; + + head = au_name_hash(delist, name, nlen); + hlist_for_each_entry(tpos, pos, head, hash) { + str = tpos->str; + AuDbg("%.*s\n", str->len, str->name); + if (au_nhash_test_name(str, name, nlen)) + return 1; + } + return 0; +} + +static void au_shwh_init_wh(struct au_vdir_wh *wh, ino_t ino, + unsigned char d_type) +{ +#ifdef CONFIG_AUFS_SHWH + wh->wh_ino = ino; + wh->wh_type = d_type; +#endif +} + +/* ---------------------------------------------------------------------- */ + +int au_nhash_append_wh(struct au_nhash *whlist, char *name, int nlen, ino_t ino, + unsigned int d_type, aufs_bindex_t bindex, + unsigned char shwh) +{ + int err; + struct au_vdir_destr *str; + struct au_vdir_wh *wh; + + AuDbg("%.*s\n", nlen, name); + AuDebugOn(!whlist->nh_num || !whlist->nh_head); + + err = -ENOMEM; + wh = kmalloc(sizeof(*wh) + nlen, GFP_NOFS); + if (unlikely(!wh)) + goto out; + + err = 0; + wh->wh_bindex = bindex; + if (shwh) + au_shwh_init_wh(wh, ino, d_type); + str = &wh->wh_str; + str->len = nlen; + memcpy(str->name, name, nlen); + hlist_add_head(&wh->wh_hash, au_name_hash(whlist, name, nlen)); + /* smp_mb(); */ + +out: + return err; +} + +static int append_deblk(struct au_vdir *vdir) +{ + int err; + unsigned long ul; + const unsigned int deblk_sz = vdir->vd_deblk_sz; + union au_vdir_deblk_p p, deblk_end; + unsigned char **o; + + err = -ENOMEM; + o = krealloc(vdir->vd_deblk, sizeof(*o) * (vdir->vd_nblk + 1), + GFP_NOFS); + if (unlikely(!o)) + goto out; + + vdir->vd_deblk = o; + p.deblk = kmalloc(deblk_sz, GFP_NOFS); + if (p.deblk) { + ul = vdir->vd_nblk++; + vdir->vd_deblk[ul] = p.deblk; + vdir->vd_last.ul = ul; + vdir->vd_last.p.deblk = p.deblk; + deblk_end.deblk = p.deblk + deblk_sz; + err = set_deblk_end(&p, &deblk_end); + } + +out: + return err; +} + +static int append_de(struct au_vdir *vdir, char *name, int nlen, ino_t ino, + unsigned int d_type, struct au_nhash *delist) +{ + int err; + unsigned int sz; + const unsigned int deblk_sz = vdir->vd_deblk_sz; + union au_vdir_deblk_p p, *room, deblk_end; + struct au_vdir_dehstr *dehstr; + + p.deblk = last_deblk(vdir); + deblk_end.deblk = p.deblk + deblk_sz; + room = &vdir->vd_last.p; + AuDebugOn(room->deblk < p.deblk || deblk_end.deblk <= room->deblk + || !is_deblk_end(room, &deblk_end)); + + sz = calc_size(nlen); + if (unlikely(sz > deblk_end.deblk - room->deblk)) { + err = append_deblk(vdir); + if (unlikely(err)) + goto out; + + p.deblk = last_deblk(vdir); + deblk_end.deblk = p.deblk + deblk_sz; + /* smp_mb(); */ + AuDebugOn(room->deblk != p.deblk); + } + + err = -ENOMEM; + dehstr = au_cache_alloc_vdir_dehstr(); + if (unlikely(!dehstr)) + goto out; + + dehstr->str = &room->de->de_str; + hlist_add_head(&dehstr->hash, au_name_hash(delist, name, nlen)); + room->de->de_ino = ino; + room->de->de_type = d_type; + room->de->de_str.len = nlen; + memcpy(room->de->de_str.name, name, nlen); + + err = 0; + room->deblk += sz; + if (unlikely(set_deblk_end(room, &deblk_end))) + err = append_deblk(vdir); + /* smp_mb(); */ + +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +void au_vdir_free(struct au_vdir *vdir) +{ + unsigned char **deblk; + + deblk = vdir->vd_deblk; + while (vdir->vd_nblk--) + kfree(*deblk++); + kfree(vdir->vd_deblk); + au_cache_free_vdir(vdir); +} + +static struct au_vdir *alloc_vdir(struct file *file) +{ + struct au_vdir *vdir; + struct super_block *sb; + int err; + + sb = file->f_dentry->d_sb; + SiMustAnyLock(sb); + + err = -ENOMEM; + vdir = au_cache_alloc_vdir(); + if (unlikely(!vdir)) + goto out; + + vdir->vd_deblk = kzalloc(sizeof(*vdir->vd_deblk), GFP_NOFS); + if (unlikely(!vdir->vd_deblk)) + goto out_free; + + vdir->vd_deblk_sz = au_sbi(sb)->si_rdblk; + if (!vdir->vd_deblk_sz) { + /* estimate the apropriate size for deblk */ + vdir->vd_deblk_sz = au_dir_size(file, /*dentry*/NULL); + /* pr_info("vd_deblk_sz %u\n", vdir->vd_deblk_sz); */ + } + vdir->vd_nblk = 0; + vdir->vd_version = 0; + vdir->vd_jiffy = 0; + err = append_deblk(vdir); + if (!err) + return vdir; /* success */ + + kfree(vdir->vd_deblk); + +out_free: + au_cache_free_vdir(vdir); +out: + vdir = ERR_PTR(err); + return vdir; +} + +static int reinit_vdir(struct au_vdir *vdir) +{ + int err; + union au_vdir_deblk_p p, deblk_end; + + while (vdir->vd_nblk > 1) { + kfree(vdir->vd_deblk[vdir->vd_nblk - 1]); + /* vdir->vd_deblk[vdir->vd_nblk - 1] = NULL; */ + vdir->vd_nblk--; + } + p.deblk = vdir->vd_deblk[0]; + deblk_end.deblk = p.deblk + vdir->vd_deblk_sz; + err = set_deblk_end(&p, &deblk_end); + /* keep vd_dblk_sz */ + vdir->vd_last.ul = 0; + vdir->vd_last.p.deblk = vdir->vd_deblk[0]; + vdir->vd_version = 0; + vdir->vd_jiffy = 0; + /* smp_mb(); */ + return err; +} + +/* ---------------------------------------------------------------------- */ + +#define AuFillVdir_CALLED 1 +#define AuFillVdir_WHABLE (1 << 1) +#define AuFillVdir_SHWH (1 << 2) +#define au_ftest_fillvdir(flags, name) ((flags) & AuFillVdir_##name) +#define au_fset_fillvdir(flags, name) \ + do { (flags) |= AuFillVdir_##name; } while (0) +#define au_fclr_fillvdir(flags, name) \ + do { (flags) &= ~AuFillVdir_##name; } while (0) + +#ifndef CONFIG_AUFS_SHWH +#undef AuFillVdir_SHWH +#define AuFillVdir_SHWH 0 +#endif + +struct fillvdir_arg { + struct file *file; + struct au_vdir *vdir; + struct au_nhash delist; + struct au_nhash whlist; + aufs_bindex_t bindex; + unsigned int flags; + int err; +}; + +static int fillvdir(void *__arg, const char *__name, int nlen, + loff_t offset __maybe_unused, u64 h_ino, + unsigned int d_type) +{ + struct fillvdir_arg *arg = __arg; + char *name = (void *)__name; + struct super_block *sb; + ino_t ino; + const unsigned char shwh = !!au_ftest_fillvdir(arg->flags, SHWH); + + arg->err = 0; + sb = arg->file->f_dentry->d_sb; + au_fset_fillvdir(arg->flags, CALLED); + /* smp_mb(); */ + if (nlen <= AUFS_WH_PFX_LEN + || memcmp(name, AUFS_WH_PFX, AUFS_WH_PFX_LEN)) { + if (test_known(&arg->delist, name, nlen) + || au_nhash_test_known_wh(&arg->whlist, name, nlen)) + goto out; /* already exists or whiteouted */ + + sb = arg->file->f_dentry->d_sb; + arg->err = au_ino(sb, arg->bindex, h_ino, d_type, &ino); + if (!arg->err) { + if (unlikely(nlen > AUFS_MAX_NAMELEN)) + d_type = DT_UNKNOWN; + arg->err = append_de(arg->vdir, name, nlen, ino, + d_type, &arg->delist); + } + } else if (au_ftest_fillvdir(arg->flags, WHABLE)) { + name += AUFS_WH_PFX_LEN; + nlen -= AUFS_WH_PFX_LEN; + if (au_nhash_test_known_wh(&arg->whlist, name, nlen)) + goto out; /* already whiteouted */ + + if (shwh) + arg->err = au_wh_ino(sb, arg->bindex, h_ino, d_type, + &ino); + if (!arg->err) { + if (nlen <= AUFS_MAX_NAMELEN + AUFS_WH_PFX_LEN) + d_type = DT_UNKNOWN; + arg->err = au_nhash_append_wh + (&arg->whlist, name, nlen, ino, d_type, + arg->bindex, shwh); + } + } + +out: + if (!arg->err) + arg->vdir->vd_jiffy = jiffies; + /* smp_mb(); */ + AuTraceErr(arg->err); + return arg->err; +} + +static int au_handle_shwh(struct super_block *sb, struct au_vdir *vdir, + struct au_nhash *whlist, struct au_nhash *delist) +{ +#ifdef CONFIG_AUFS_SHWH + int err; + unsigned int nh, u; + struct hlist_head *head; + struct au_vdir_wh *tpos; + struct hlist_node *pos, *n; + char *p, *o; + struct au_vdir_destr *destr; + + AuDebugOn(!au_opt_test(au_mntflags(sb), SHWH)); + + err = -ENOMEM; + o = p = __getname_gfp(GFP_NOFS); + if (unlikely(!p)) + goto out; + + err = 0; + nh = whlist->nh_num; + memcpy(p, AUFS_WH_PFX, AUFS_WH_PFX_LEN); + p += AUFS_WH_PFX_LEN; + for (u = 0; u < nh; u++) { + head = whlist->nh_head + u; + hlist_for_each_entry_safe(tpos, pos, n, head, wh_hash) { + destr = &tpos->wh_str; + memcpy(p, destr->name, destr->len); + err = append_de(vdir, o, destr->len + AUFS_WH_PFX_LEN, + tpos->wh_ino, tpos->wh_type, delist); + if (unlikely(err)) + break; + } + } + + __putname(o); + +out: + AuTraceErr(err); + return err; +#else + return 0; +#endif +} + +static int au_do_read_vdir(struct fillvdir_arg *arg) +{ + int err; + unsigned int rdhash; + loff_t offset; + aufs_bindex_t bend, bindex, bstart; + unsigned char shwh; + struct file *hf, *file; + struct super_block *sb; + + file = arg->file; + sb = file->f_dentry->d_sb; + SiMustAnyLock(sb); + + rdhash = au_sbi(sb)->si_rdhash; + if (!rdhash) + rdhash = au_rdhash_est(au_dir_size(file, /*dentry*/NULL)); + err = au_nhash_alloc(&arg->delist, rdhash, GFP_NOFS); + if (unlikely(err)) + goto out; + err = au_nhash_alloc(&arg->whlist, rdhash, GFP_NOFS); + if (unlikely(err)) + goto out_delist; + + err = 0; + arg->flags = 0; + shwh = 0; + if (au_opt_test(au_mntflags(sb), SHWH)) { + shwh = 1; + au_fset_fillvdir(arg->flags, SHWH); + } + bstart = au_fbstart(file); + bend = au_fbend_dir(file); + for (bindex = bstart; !err && bindex <= bend; bindex++) { + hf = au_hf_dir(file, bindex); + if (!hf) + continue; + + offset = vfsub_llseek(hf, 0, SEEK_SET); + err = offset; + if (unlikely(offset)) + break; + + arg->bindex = bindex; + au_fclr_fillvdir(arg->flags, WHABLE); + if (shwh + || (bindex != bend + && au_br_whable(au_sbr_perm(sb, bindex)))) + au_fset_fillvdir(arg->flags, WHABLE); + do { + arg->err = 0; + au_fclr_fillvdir(arg->flags, CALLED); + /* smp_mb(); */ + err = vfsub_readdir(hf, fillvdir, arg); + if (err >= 0) + err = arg->err; + } while (!err && au_ftest_fillvdir(arg->flags, CALLED)); + } + + if (!err && shwh) + err = au_handle_shwh(sb, arg->vdir, &arg->whlist, &arg->delist); + + au_nhash_wh_free(&arg->whlist); + +out_delist: + au_nhash_de_free(&arg->delist); +out: + return err; +} + +static int read_vdir(struct file *file, int may_read) +{ + int err; + unsigned long expire; + unsigned char do_read; + struct fillvdir_arg arg; + struct inode *inode; + struct au_vdir *vdir, *allocated; + + err = 0; + inode = file->f_dentry->d_inode; + IMustLock(inode); + SiMustAnyLock(inode->i_sb); + + allocated = NULL; + do_read = 0; + expire = au_sbi(inode->i_sb)->si_rdcache; + vdir = au_ivdir(inode); + if (!vdir) { + do_read = 1; + vdir = alloc_vdir(file); + err = PTR_ERR(vdir); + if (IS_ERR(vdir)) + goto out; + err = 0; + allocated = vdir; + } else if (may_read + && (inode->i_version != vdir->vd_version + || time_after(jiffies, vdir->vd_jiffy + expire))) { + do_read = 1; + err = reinit_vdir(vdir); + if (unlikely(err)) + goto out; + } + + if (!do_read) + return 0; /* success */ + + arg.file = file; + arg.vdir = vdir; + err = au_do_read_vdir(&arg); + if (!err) { + /* file->f_pos = 0; */ + vdir->vd_version = inode->i_version; + vdir->vd_last.ul = 0; + vdir->vd_last.p.deblk = vdir->vd_deblk[0]; + if (allocated) + au_set_ivdir(inode, allocated); + } else if (allocated) + au_vdir_free(allocated); + +out: + return err; +} + +static int copy_vdir(struct au_vdir *tgt, struct au_vdir *src) +{ + int err, rerr; + unsigned long ul, n; + const unsigned int deblk_sz = src->vd_deblk_sz; + + AuDebugOn(tgt->vd_nblk != 1); + + err = -ENOMEM; + if (tgt->vd_nblk < src->vd_nblk) { + unsigned char **p; + + p = krealloc(tgt->vd_deblk, sizeof(*p) * src->vd_nblk, + GFP_NOFS); + if (unlikely(!p)) + goto out; + tgt->vd_deblk = p; + } + + if (tgt->vd_deblk_sz != deblk_sz) { + unsigned char *p; + + tgt->vd_deblk_sz = deblk_sz; + p = krealloc(tgt->vd_deblk[0], deblk_sz, GFP_NOFS); + if (unlikely(!p)) + goto out; + tgt->vd_deblk[0] = p; + } + memcpy(tgt->vd_deblk[0], src->vd_deblk[0], deblk_sz); + tgt->vd_version = src->vd_version; + tgt->vd_jiffy = src->vd_jiffy; + + n = src->vd_nblk; + for (ul = 1; ul < n; ul++) { + tgt->vd_deblk[ul] = kmemdup(src->vd_deblk[ul], deblk_sz, + GFP_NOFS); + if (unlikely(!tgt->vd_deblk[ul])) + goto out; + tgt->vd_nblk++; + } + tgt->vd_nblk = n; + tgt->vd_last.ul = tgt->vd_last.ul; + tgt->vd_last.p.deblk = tgt->vd_deblk[tgt->vd_last.ul]; + tgt->vd_last.p.deblk += src->vd_last.p.deblk + - src->vd_deblk[src->vd_last.ul]; + /* smp_mb(); */ + return 0; /* success */ + +out: + rerr = reinit_vdir(tgt); + BUG_ON(rerr); + return err; +} + +int au_vdir_init(struct file *file) +{ + int err; + struct inode *inode; + struct au_vdir *vdir_cache, *allocated; + + err = read_vdir(file, !file->f_pos); + if (unlikely(err)) + goto out; + + allocated = NULL; + vdir_cache = au_fvdir_cache(file); + if (!vdir_cache) { + vdir_cache = alloc_vdir(file); + err = PTR_ERR(vdir_cache); + if (IS_ERR(vdir_cache)) + goto out; + allocated = vdir_cache; + } else if (!file->f_pos && vdir_cache->vd_version != file->f_version) { + err = reinit_vdir(vdir_cache); + if (unlikely(err)) + goto out; + } else + return 0; /* success */ + + inode = file->f_dentry->d_inode; + err = copy_vdir(vdir_cache, au_ivdir(inode)); + if (!err) { + file->f_version = inode->i_version; + if (allocated) + au_set_fvdir_cache(file, allocated); + } else if (allocated) + au_vdir_free(allocated); + +out: + return err; +} + +static loff_t calc_offset(struct au_vdir *vdir) +{ + loff_t offset; + union au_vdir_deblk_p p; + + p.deblk = vdir->vd_deblk[vdir->vd_last.ul]; + offset = vdir->vd_last.p.deblk - p.deblk; + offset += vdir->vd_deblk_sz * vdir->vd_last.ul; + return offset; +} + +/* returns true or false */ +static int seek_vdir(struct file *file) +{ + int valid; + unsigned int deblk_sz; + unsigned long ul, n; + loff_t offset; + union au_vdir_deblk_p p, deblk_end; + struct au_vdir *vdir_cache; + + valid = 1; + vdir_cache = au_fvdir_cache(file); + offset = calc_offset(vdir_cache); + AuDbg("offset %lld\n", offset); + if (file->f_pos == offset) + goto out; + + vdir_cache->vd_last.ul = 0; + vdir_cache->vd_last.p.deblk = vdir_cache->vd_deblk[0]; + if (!file->f_pos) + goto out; + + valid = 0; + deblk_sz = vdir_cache->vd_deblk_sz; + ul = div64_u64(file->f_pos, deblk_sz); + AuDbg("ul %lu\n", ul); + if (ul >= vdir_cache->vd_nblk) + goto out; + + n = vdir_cache->vd_nblk; + for (; ul < n; ul++) { + p.deblk = vdir_cache->vd_deblk[ul]; + deblk_end.deblk = p.deblk + deblk_sz; + offset = ul; + offset *= deblk_sz; + while (!is_deblk_end(&p, &deblk_end) && offset < file->f_pos) { + unsigned int l; + + l = calc_size(p.de->de_str.len); + offset += l; + p.deblk += l; + } + if (!is_deblk_end(&p, &deblk_end)) { + valid = 1; + vdir_cache->vd_last.ul = ul; + vdir_cache->vd_last.p = p; + break; + } + } + +out: + /* smp_mb(); */ + AuTraceErr(!valid); + return valid; +} + +int au_vdir_fill_de(struct file *file, void *dirent, filldir_t filldir) +{ + int err; + unsigned int l, deblk_sz; + union au_vdir_deblk_p deblk_end; + struct au_vdir *vdir_cache; + struct au_vdir_de *de; + + vdir_cache = au_fvdir_cache(file); + if (!seek_vdir(file)) + return 0; + + deblk_sz = vdir_cache->vd_deblk_sz; + while (1) { + deblk_end.deblk = vdir_cache->vd_deblk[vdir_cache->vd_last.ul]; + deblk_end.deblk += deblk_sz; + while (!is_deblk_end(&vdir_cache->vd_last.p, &deblk_end)) { + de = vdir_cache->vd_last.p.de; + AuDbg("%.*s, off%lld, i%lu, dt%d\n", + de->de_str.len, de->de_str.name, file->f_pos, + (unsigned long)de->de_ino, de->de_type); + err = filldir(dirent, de->de_str.name, de->de_str.len, + file->f_pos, de->de_ino, de->de_type); + if (unlikely(err)) { + AuTraceErr(err); + /* todo: ignore the error caused by udba? */ + /* return err; */ + return 0; + } + + l = calc_size(de->de_str.len); + vdir_cache->vd_last.p.deblk += l; + file->f_pos += l; + } + if (vdir_cache->vd_last.ul < vdir_cache->vd_nblk - 1) { + vdir_cache->vd_last.ul++; + vdir_cache->vd_last.p.deblk + = vdir_cache->vd_deblk[vdir_cache->vd_last.ul]; + file->f_pos = deblk_sz * vdir_cache->vd_last.ul; + continue; + } + break; + } + + /* smp_mb(); */ + return 0; +} diff --git a/ubuntu/aufs/vfsub.c b/ubuntu/aufs/vfsub.c new file mode 100644 index 000000000000..331ab17fb5c1 --- /dev/null +++ b/ubuntu/aufs/vfsub.c @@ -0,0 +1,835 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * sub-routines for VFS + */ + +#include <linux/ima.h> +#include <linux/namei.h> +#include <linux/security.h> +#include <linux/splice.h> +#include "aufs.h" + +int vfsub_update_h_iattr(struct path *h_path, int *did) +{ + int err; + struct kstat st; + struct super_block *h_sb; + + /* for remote fs, leave work for its getattr or d_revalidate */ + /* for bad i_attr fs, handle them in aufs_getattr() */ + /* still some fs may acquire i_mutex. we need to skip them */ + err = 0; + if (!did) + did = &err; + h_sb = h_path->dentry->d_sb; + *did = (!au_test_fs_remote(h_sb) && au_test_fs_refresh_iattr(h_sb)); + if (*did) + err = vfs_getattr(h_path->mnt, h_path->dentry, &st); + + return err; +} + +/* ---------------------------------------------------------------------- */ + +struct file *vfsub_dentry_open(struct path *path, int flags) +{ + struct file *file; + + path_get(path); + file = dentry_open(path->dentry, path->mnt, + flags /* | __FMODE_NONOTIFY */, + current_cred()); + if (!IS_ERR_OR_NULL(file) + && (file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) + i_readcount_inc(path->dentry->d_inode); + + return file; +} + +struct file *vfsub_filp_open(const char *path, int oflags, int mode) +{ + struct file *file; + + lockdep_off(); + file = filp_open(path, + oflags /* | __FMODE_NONOTIFY */, + mode); + lockdep_on(); + if (IS_ERR(file)) + goto out; + vfsub_update_h_iattr(&file->f_path, /*did*/NULL); /*ignore*/ + +out: + return file; +} + +int vfsub_kern_path(const char *name, unsigned int flags, struct path *path) +{ + int err; + + err = kern_path(name, flags, path); + if (!err && path->dentry->d_inode) + vfsub_update_h_iattr(path, /*did*/NULL); /*ignore*/ + return err; +} + +struct dentry *vfsub_lookup_one_len(const char *name, struct dentry *parent, + int len) +{ + struct path path = { + .mnt = NULL + }; + + /* VFS checks it too, but by WARN_ON_ONCE() */ + IMustLock(parent->d_inode); + + path.dentry = lookup_one_len(name, parent, len); + if (IS_ERR(path.dentry)) + goto out; + if (path.dentry->d_inode) + vfsub_update_h_iattr(&path, /*did*/NULL); /*ignore*/ + +out: + AuTraceErrPtr(path.dentry); + return path.dentry; +} + +struct dentry *vfsub_lookup_hash(struct nameidata *nd) +{ + struct path path = { + .mnt = nd->path.mnt + }; + + IMustLock(nd->path.dentry->d_inode); + + path.dentry = lookup_hash(nd); + if (IS_ERR(path.dentry)) + goto out; + if (path.dentry->d_inode) + vfsub_update_h_iattr(&path, /*did*/NULL); /*ignore*/ + +out: + AuTraceErrPtr(path.dentry); + return path.dentry; +} + +/* + * this is "VFS:__lookup_one_len()" which was removed and merged into + * VFS:lookup_one_len() by the commit. + * 6a96ba5 2011-03-14 kill __lookup_one_len() + * this function should always be equivalent to the corresponding part in + * VFS:lookup_one_len(). + */ +int vfsub_name_hash(const char *name, struct qstr *this, int len) +{ + unsigned long hash; + unsigned int c; + + this->name = name; + this->len = len; + if (!len) + return -EACCES; + + hash = init_name_hash(); + while (len--) { + c = *(const unsigned char *)name++; + if (c == '/' || c == '\0') + return -EACCES; + hash = partial_name_hash(c, hash); + } + this->hash = end_name_hash(hash); + return 0; +} + +/* ---------------------------------------------------------------------- */ + +struct dentry *vfsub_lock_rename(struct dentry *d1, struct au_hinode *hdir1, + struct dentry *d2, struct au_hinode *hdir2) +{ + struct dentry *d; + + lockdep_off(); + d = lock_rename(d1, d2); + lockdep_on(); + au_hn_suspend(hdir1); + if (hdir1 != hdir2) + au_hn_suspend(hdir2); + + return d; +} + +void vfsub_unlock_rename(struct dentry *d1, struct au_hinode *hdir1, + struct dentry *d2, struct au_hinode *hdir2) +{ + au_hn_resume(hdir1); + if (hdir1 != hdir2) + au_hn_resume(hdir2); + lockdep_off(); + unlock_rename(d1, d2); + lockdep_on(); +} + +/* ---------------------------------------------------------------------- */ + +int vfsub_create(struct inode *dir, struct path *path, int mode) +{ + int err; + struct dentry *d; + + IMustLock(dir); + + d = path->dentry; + path->dentry = d->d_parent; + err = security_path_mknod(path, d, mode, 0); + path->dentry = d; + if (unlikely(err)) + goto out; + + if (au_test_fs_null_nd(dir->i_sb)) + err = vfs_create(dir, path->dentry, mode, NULL); + else { + struct nameidata h_nd; + + memset(&h_nd, 0, sizeof(h_nd)); + h_nd.flags = LOOKUP_CREATE; + h_nd.intent.open.flags = O_CREAT + | vfsub_fmode_to_uint(FMODE_READ); + h_nd.intent.open.create_mode = mode; + h_nd.path.dentry = path->dentry->d_parent; + h_nd.path.mnt = path->mnt; + path_get(&h_nd.path); + err = vfs_create(dir, path->dentry, mode, &h_nd); + path_put(&h_nd.path); + } + + if (!err) { + struct path tmp = *path; + int did; + + vfsub_update_h_iattr(&tmp, &did); + if (did) { + tmp.dentry = path->dentry->d_parent; + vfsub_update_h_iattr(&tmp, /*did*/NULL); + } + /*ignore*/ + } + +out: + return err; +} + +int vfsub_symlink(struct inode *dir, struct path *path, const char *symname) +{ + int err; + struct dentry *d; + + IMustLock(dir); + + d = path->dentry; + path->dentry = d->d_parent; + err = security_path_symlink(path, d, symname); + path->dentry = d; + if (unlikely(err)) + goto out; + + err = vfs_symlink(dir, path->dentry, symname); + if (!err) { + struct path tmp = *path; + int did; + + vfsub_update_h_iattr(&tmp, &did); + if (did) { + tmp.dentry = path->dentry->d_parent; + vfsub_update_h_iattr(&tmp, /*did*/NULL); + } + /*ignore*/ + } + +out: + return err; +} + +int vfsub_mknod(struct inode *dir, struct path *path, int mode, dev_t dev) +{ + int err; + struct dentry *d; + + IMustLock(dir); + + d = path->dentry; + path->dentry = d->d_parent; + err = security_path_mknod(path, d, mode, new_encode_dev(dev)); + path->dentry = d; + if (unlikely(err)) + goto out; + + err = vfs_mknod(dir, path->dentry, mode, dev); + if (!err) { + struct path tmp = *path; + int did; + + vfsub_update_h_iattr(&tmp, &did); + if (did) { + tmp.dentry = path->dentry->d_parent; + vfsub_update_h_iattr(&tmp, /*did*/NULL); + } + /*ignore*/ + } + +out: + return err; +} + +static int au_test_nlink(struct inode *inode) +{ + const unsigned int link_max = UINT_MAX >> 1; /* rough margin */ + + if (!au_test_fs_no_limit_nlink(inode->i_sb) + || inode->i_nlink < link_max) + return 0; + return -EMLINK; +} + +int vfsub_link(struct dentry *src_dentry, struct inode *dir, struct path *path) +{ + int err; + struct dentry *d; + + IMustLock(dir); + + err = au_test_nlink(src_dentry->d_inode); + if (unlikely(err)) + return err; + + d = path->dentry; + path->dentry = d->d_parent; + err = security_path_link(src_dentry, path, d); + path->dentry = d; + if (unlikely(err)) + goto out; + + lockdep_off(); + err = vfs_link(src_dentry, dir, path->dentry); + lockdep_on(); + if (!err) { + struct path tmp = *path; + int did; + + /* fuse has different memory inode for the same inumber */ + vfsub_update_h_iattr(&tmp, &did); + if (did) { + tmp.dentry = path->dentry->d_parent; + vfsub_update_h_iattr(&tmp, /*did*/NULL); + tmp.dentry = src_dentry; + vfsub_update_h_iattr(&tmp, /*did*/NULL); + } + /*ignore*/ + } + +out: + return err; +} + +int vfsub_rename(struct inode *src_dir, struct dentry *src_dentry, + struct inode *dir, struct path *path) +{ + int err; + struct path tmp = { + .mnt = path->mnt + }; + struct dentry *d; + + IMustLock(dir); + IMustLock(src_dir); + + d = path->dentry; + path->dentry = d->d_parent; + tmp.dentry = src_dentry->d_parent; + err = security_path_rename(&tmp, src_dentry, path, d); + path->dentry = d; + if (unlikely(err)) + goto out; + + lockdep_off(); + err = vfs_rename(src_dir, src_dentry, dir, path->dentry); + lockdep_on(); + if (!err) { + int did; + + tmp.dentry = d->d_parent; + vfsub_update_h_iattr(&tmp, &did); + if (did) { + tmp.dentry = src_dentry; + vfsub_update_h_iattr(&tmp, /*did*/NULL); + tmp.dentry = src_dentry->d_parent; + vfsub_update_h_iattr(&tmp, /*did*/NULL); + } + /*ignore*/ + } + +out: + return err; +} + +int vfsub_mkdir(struct inode *dir, struct path *path, int mode) +{ + int err; + struct dentry *d; + + IMustLock(dir); + + d = path->dentry; + path->dentry = d->d_parent; + err = security_path_mkdir(path, d, mode); + path->dentry = d; + if (unlikely(err)) + goto out; + + err = vfs_mkdir(dir, path->dentry, mode); + if (!err) { + struct path tmp = *path; + int did; + + vfsub_update_h_iattr(&tmp, &did); + if (did) { + tmp.dentry = path->dentry->d_parent; + vfsub_update_h_iattr(&tmp, /*did*/NULL); + } + /*ignore*/ + } + +out: + return err; +} + +int vfsub_rmdir(struct inode *dir, struct path *path) +{ + int err; + struct dentry *d; + + IMustLock(dir); + + d = path->dentry; + path->dentry = d->d_parent; + err = security_path_rmdir(path, d); + path->dentry = d; + if (unlikely(err)) + goto out; + + lockdep_off(); + err = vfs_rmdir(dir, path->dentry); + lockdep_on(); + if (!err) { + struct path tmp = { + .dentry = path->dentry->d_parent, + .mnt = path->mnt + }; + + vfsub_update_h_iattr(&tmp, /*did*/NULL); /*ignore*/ + } + +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* todo: support mmap_sem? */ +ssize_t vfsub_read_u(struct file *file, char __user *ubuf, size_t count, + loff_t *ppos) +{ + ssize_t err; + + lockdep_off(); + err = vfs_read(file, ubuf, count, ppos); + lockdep_on(); + if (err >= 0) + vfsub_update_h_iattr(&file->f_path, /*did*/NULL); /*ignore*/ + return err; +} + +/* todo: kernel_read()? */ +ssize_t vfsub_read_k(struct file *file, void *kbuf, size_t count, + loff_t *ppos) +{ + ssize_t err; + mm_segment_t oldfs; + union { + void *k; + char __user *u; + } buf; + + buf.k = kbuf; + oldfs = get_fs(); + set_fs(KERNEL_DS); + err = vfsub_read_u(file, buf.u, count, ppos); + set_fs(oldfs); + return err; +} + +ssize_t vfsub_write_u(struct file *file, const char __user *ubuf, size_t count, + loff_t *ppos) +{ + ssize_t err; + + lockdep_off(); + err = vfs_write(file, ubuf, count, ppos); + lockdep_on(); + if (err >= 0) + vfsub_update_h_iattr(&file->f_path, /*did*/NULL); /*ignore*/ + return err; +} + +ssize_t vfsub_write_k(struct file *file, void *kbuf, size_t count, loff_t *ppos) +{ + ssize_t err; + mm_segment_t oldfs; + union { + void *k; + const char __user *u; + } buf; + + buf.k = kbuf; + oldfs = get_fs(); + set_fs(KERNEL_DS); + err = vfsub_write_u(file, buf.u, count, ppos); + set_fs(oldfs); + return err; +} + +int vfsub_flush(struct file *file, fl_owner_t id) +{ + int err; + + err = 0; + if (file->f_op && file->f_op->flush) { + if (!au_test_nfs(file->f_dentry->d_sb)) + err = file->f_op->flush(file, id); + else { + lockdep_off(); + err = file->f_op->flush(file, id); + lockdep_on(); + } + if (!err) + vfsub_update_h_iattr(&file->f_path, /*did*/NULL); + /*ignore*/ + } + return err; +} + +int vfsub_readdir(struct file *file, filldir_t filldir, void *arg) +{ + int err; + + lockdep_off(); + err = vfs_readdir(file, filldir, arg); + lockdep_on(); + if (err >= 0) + vfsub_update_h_iattr(&file->f_path, /*did*/NULL); /*ignore*/ + return err; +} + +long vfsub_splice_to(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) +{ + long err; + + lockdep_off(); + err = do_splice_to(in, ppos, pipe, len, flags); + lockdep_on(); + file_accessed(in); + if (err >= 0) + vfsub_update_h_iattr(&in->f_path, /*did*/NULL); /*ignore*/ + return err; +} + +long vfsub_splice_from(struct pipe_inode_info *pipe, struct file *out, + loff_t *ppos, size_t len, unsigned int flags) +{ + long err; + + lockdep_off(); + err = do_splice_from(pipe, out, ppos, len, flags); + lockdep_on(); + if (err >= 0) + vfsub_update_h_iattr(&out->f_path, /*did*/NULL); /*ignore*/ + return err; +} + +int vfsub_fsync(struct file *file, struct path *path, int datasync) +{ + int err; + + /* file can be NULL */ + lockdep_off(); + err = vfs_fsync(file, datasync); + lockdep_on(); + if (!err) { + if (!path) { + AuDebugOn(!file); + path = &file->f_path; + } + vfsub_update_h_iattr(path, /*did*/NULL); /*ignore*/ + } + return err; +} + +/* cf. open.c:do_sys_truncate() and do_sys_ftruncate() */ +int vfsub_trunc(struct path *h_path, loff_t length, unsigned int attr, + struct file *h_file) +{ + int err; + struct inode *h_inode; + + h_inode = h_path->dentry->d_inode; + if (!h_file) { + err = mnt_want_write(h_path->mnt); + if (err) + goto out; + err = inode_permission(h_inode, MAY_WRITE); + if (err) + goto out_mnt; + err = get_write_access(h_inode); + if (err) + goto out_mnt; + err = break_lease(h_inode, O_WRONLY); + if (err) + goto out_inode; + } + + err = locks_verify_truncate(h_inode, h_file, length); + if (!err) + err = security_path_truncate(h_path); + if (!err) { + lockdep_off(); + err = do_truncate(h_path->dentry, length, attr, h_file); + lockdep_on(); + } + +out_inode: + if (!h_file) + put_write_access(h_inode); +out_mnt: + if (!h_file) + mnt_drop_write(h_path->mnt); +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +struct au_vfsub_mkdir_args { + int *errp; + struct inode *dir; + struct path *path; + int mode; +}; + +static void au_call_vfsub_mkdir(void *args) +{ + struct au_vfsub_mkdir_args *a = args; + *a->errp = vfsub_mkdir(a->dir, a->path, a->mode); +} + +int vfsub_sio_mkdir(struct inode *dir, struct path *path, int mode) +{ + int err, do_sio, wkq_err; + + do_sio = au_test_h_perm_sio(dir, MAY_EXEC | MAY_WRITE); + if (!do_sio) + err = vfsub_mkdir(dir, path, mode); + else { + struct au_vfsub_mkdir_args args = { + .errp = &err, + .dir = dir, + .path = path, + .mode = mode + }; + wkq_err = au_wkq_wait(au_call_vfsub_mkdir, &args); + if (unlikely(wkq_err)) + err = wkq_err; + } + + return err; +} + +struct au_vfsub_rmdir_args { + int *errp; + struct inode *dir; + struct path *path; +}; + +static void au_call_vfsub_rmdir(void *args) +{ + struct au_vfsub_rmdir_args *a = args; + *a->errp = vfsub_rmdir(a->dir, a->path); +} + +int vfsub_sio_rmdir(struct inode *dir, struct path *path) +{ + int err, do_sio, wkq_err; + + do_sio = au_test_h_perm_sio(dir, MAY_EXEC | MAY_WRITE); + if (!do_sio) + err = vfsub_rmdir(dir, path); + else { + struct au_vfsub_rmdir_args args = { + .errp = &err, + .dir = dir, + .path = path + }; + wkq_err = au_wkq_wait(au_call_vfsub_rmdir, &args); + if (unlikely(wkq_err)) + err = wkq_err; + } + + return err; +} + +/* ---------------------------------------------------------------------- */ + +struct notify_change_args { + int *errp; + struct path *path; + struct iattr *ia; +}; + +static void call_notify_change(void *args) +{ + struct notify_change_args *a = args; + struct inode *h_inode; + + h_inode = a->path->dentry->d_inode; + IMustLock(h_inode); + + *a->errp = -EPERM; + if (!IS_IMMUTABLE(h_inode) && !IS_APPEND(h_inode)) { + *a->errp = notify_change(a->path->dentry, a->ia); + if (!*a->errp) + vfsub_update_h_iattr(a->path, /*did*/NULL); /*ignore*/ + } + AuTraceErr(*a->errp); +} + +int vfsub_notify_change(struct path *path, struct iattr *ia) +{ + int err; + struct notify_change_args args = { + .errp = &err, + .path = path, + .ia = ia + }; + + call_notify_change(&args); + + return err; +} + +int vfsub_sio_notify_change(struct path *path, struct iattr *ia) +{ + int err, wkq_err; + struct notify_change_args args = { + .errp = &err, + .path = path, + .ia = ia + }; + + wkq_err = au_wkq_wait(call_notify_change, &args); + if (unlikely(wkq_err)) + err = wkq_err; + + return err; +} + +/* ---------------------------------------------------------------------- */ + +struct unlink_args { + int *errp; + struct inode *dir; + struct path *path; +}; + +static void call_unlink(void *args) +{ + struct unlink_args *a = args; + struct dentry *d = a->path->dentry; + struct inode *h_inode; + const int stop_sillyrename = (au_test_nfs(d->d_sb) + && d->d_count == 1); + + IMustLock(a->dir); + + a->path->dentry = d->d_parent; + *a->errp = security_path_unlink(a->path, d); + a->path->dentry = d; + if (unlikely(*a->errp)) + return; + + if (!stop_sillyrename) + dget(d); + h_inode = d->d_inode; + if (h_inode) + ihold(h_inode); + + lockdep_off(); + *a->errp = vfs_unlink(a->dir, d); + lockdep_on(); + if (!*a->errp) { + struct path tmp = { + .dentry = d->d_parent, + .mnt = a->path->mnt + }; + vfsub_update_h_iattr(&tmp, /*did*/NULL); /*ignore*/ + } + + if (!stop_sillyrename) + dput(d); + if (h_inode) + iput(h_inode); + + AuTraceErr(*a->errp); +} + +/* + * @dir: must be locked. + * @dentry: target dentry. + */ +int vfsub_unlink(struct inode *dir, struct path *path, int force) +{ + int err; + struct unlink_args args = { + .errp = &err, + .dir = dir, + .path = path + }; + + if (!force) + call_unlink(&args); + else { + int wkq_err; + + wkq_err = au_wkq_wait(call_unlink, &args); + if (unlikely(wkq_err)) + err = wkq_err; + } + + return err; +} diff --git a/ubuntu/aufs/vfsub.h b/ubuntu/aufs/vfsub.h new file mode 100644 index 000000000000..ce4d5b683eb0 --- /dev/null +++ b/ubuntu/aufs/vfsub.h @@ -0,0 +1,232 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * sub-routines for VFS + */ + +#ifndef __AUFS_VFSUB_H__ +#define __AUFS_VFSUB_H__ + +#ifdef __KERNEL__ + +#include <linux/fs.h> +#include <linux/lglock.h> +#include "debug.h" + +/* copied from linux/fs/internal.h */ +/* todo: BAD approach!! */ +DECLARE_BRLOCK(vfsmount_lock); +extern void file_sb_list_del(struct file *f); +extern spinlock_t inode_sb_list_lock; + +/* copied from linux/fs/file_table.c */ +DECLARE_LGLOCK(files_lglock); +#ifdef CONFIG_SMP +/* + * These macros iterate all files on all CPUs for a given superblock. + * files_lglock must be held globally. + */ +#define do_file_list_for_each_entry(__sb, __file) \ +{ \ + int i; \ + for_each_possible_cpu(i) { \ + struct list_head *list; \ + list = per_cpu_ptr((__sb)->s_files, i); \ + list_for_each_entry((__file), list, f_u.fu_list) + +#define while_file_list_for_each_entry \ + } \ +} + +#else + +#define do_file_list_for_each_entry(__sb, __file) \ +{ \ + struct list_head *list; \ + list = &(sb)->s_files; \ + list_for_each_entry((__file), list, f_u.fu_list) + +#define while_file_list_for_each_entry \ +} +#endif + +/* ---------------------------------------------------------------------- */ + +/* lock subclass for lower inode */ +/* default MAX_LOCKDEP_SUBCLASSES(8) is not enough */ +/* reduce? gave up. */ +enum { + AuLsc_I_Begin = I_MUTEX_QUOTA, /* 4 */ + AuLsc_I_PARENT, /* lower inode, parent first */ + AuLsc_I_PARENT2, /* copyup dirs */ + AuLsc_I_PARENT3, /* copyup wh */ + AuLsc_I_CHILD, + AuLsc_I_CHILD2, + AuLsc_I_End +}; + +/* to debug easier, do not make them inlined functions */ +#define MtxMustLock(mtx) AuDebugOn(!mutex_is_locked(mtx)) +#define IMustLock(i) MtxMustLock(&(i)->i_mutex) + +/* ---------------------------------------------------------------------- */ + +static inline void vfsub_drop_nlink(struct inode *inode) +{ + AuDebugOn(!inode->i_nlink); + drop_nlink(inode); +} + +static inline void vfsub_dead_dir(struct inode *inode) +{ + AuDebugOn(!S_ISDIR(inode->i_mode)); + inode->i_flags |= S_DEAD; + clear_nlink(inode); +} + +/* ---------------------------------------------------------------------- */ + +int vfsub_update_h_iattr(struct path *h_path, int *did); +struct file *vfsub_dentry_open(struct path *path, int flags); +struct file *vfsub_filp_open(const char *path, int oflags, int mode); +int vfsub_kern_path(const char *name, unsigned int flags, struct path *path); +struct dentry *vfsub_lookup_one_len(const char *name, struct dentry *parent, + int len); +struct dentry *vfsub_lookup_hash(struct nameidata *nd); +int vfsub_name_hash(const char *name, struct qstr *this, int len); + +/* ---------------------------------------------------------------------- */ + +struct au_hinode; +struct dentry *vfsub_lock_rename(struct dentry *d1, struct au_hinode *hdir1, + struct dentry *d2, struct au_hinode *hdir2); +void vfsub_unlock_rename(struct dentry *d1, struct au_hinode *hdir1, + struct dentry *d2, struct au_hinode *hdir2); + +int vfsub_create(struct inode *dir, struct path *path, int mode); +int vfsub_symlink(struct inode *dir, struct path *path, + const char *symname); +int vfsub_mknod(struct inode *dir, struct path *path, int mode, dev_t dev); +int vfsub_link(struct dentry *src_dentry, struct inode *dir, + struct path *path); +int vfsub_rename(struct inode *src_hdir, struct dentry *src_dentry, + struct inode *hdir, struct path *path); +int vfsub_mkdir(struct inode *dir, struct path *path, int mode); +int vfsub_rmdir(struct inode *dir, struct path *path); + +/* ---------------------------------------------------------------------- */ + +ssize_t vfsub_read_u(struct file *file, char __user *ubuf, size_t count, + loff_t *ppos); +ssize_t vfsub_read_k(struct file *file, void *kbuf, size_t count, + loff_t *ppos); +ssize_t vfsub_write_u(struct file *file, const char __user *ubuf, size_t count, + loff_t *ppos); +ssize_t vfsub_write_k(struct file *file, void *kbuf, size_t count, + loff_t *ppos); +int vfsub_flush(struct file *file, fl_owner_t id); +int vfsub_readdir(struct file *file, filldir_t filldir, void *arg); + +static inline unsigned int vfsub_file_flags(struct file *file) +{ + unsigned int flags; + + spin_lock(&file->f_lock); + flags = file->f_flags; + spin_unlock(&file->f_lock); + + return flags; +} + +static inline void vfsub_file_accessed(struct file *h_file) +{ + file_accessed(h_file); + vfsub_update_h_iattr(&h_file->f_path, /*did*/NULL); /*ignore*/ +} + +static inline void vfsub_touch_atime(struct vfsmount *h_mnt, + struct dentry *h_dentry) +{ + struct path h_path = { + .dentry = h_dentry, + .mnt = h_mnt + }; + touch_atime(h_mnt, h_dentry); + vfsub_update_h_iattr(&h_path, /*did*/NULL); /*ignore*/ +} + +long vfsub_splice_to(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags); +long vfsub_splice_from(struct pipe_inode_info *pipe, struct file *out, + loff_t *ppos, size_t len, unsigned int flags); +int vfsub_trunc(struct path *h_path, loff_t length, unsigned int attr, + struct file *h_file); +int vfsub_fsync(struct file *file, struct path *path, int datasync); + +/* ---------------------------------------------------------------------- */ + +static inline loff_t vfsub_llseek(struct file *file, loff_t offset, int origin) +{ + loff_t err; + + lockdep_off(); + err = vfs_llseek(file, offset, origin); + lockdep_on(); + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* dirty workaround for strict type of fmode_t */ +union vfsub_fmu { + fmode_t fm; + unsigned int ui; +}; + +static inline unsigned int vfsub_fmode_to_uint(fmode_t fm) +{ + union vfsub_fmu u = { + .fm = fm + }; + + BUILD_BUG_ON(sizeof(u.fm) != sizeof(u.ui)); + + return u.ui; +} + +static inline fmode_t vfsub_uint_to_fmode(unsigned int ui) +{ + union vfsub_fmu u = { + .ui = ui + }; + + return u.fm; +} + +/* ---------------------------------------------------------------------- */ + +int vfsub_sio_mkdir(struct inode *dir, struct path *path, int mode); +int vfsub_sio_rmdir(struct inode *dir, struct path *path); +int vfsub_sio_notify_change(struct path *path, struct iattr *ia); +int vfsub_notify_change(struct path *path, struct iattr *ia); +int vfsub_unlink(struct inode *dir, struct path *path, int force); + +#endif /* __KERNEL__ */ +#endif /* __AUFS_VFSUB_H__ */ diff --git a/ubuntu/aufs/wbr_policy.c b/ubuntu/aufs/wbr_policy.c new file mode 100644 index 000000000000..2bf2efaa33b4 --- /dev/null +++ b/ubuntu/aufs/wbr_policy.c @@ -0,0 +1,700 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * policies for selecting one among multiple writable branches + */ + +#include <linux/statfs.h> +#include "aufs.h" + +/* subset of cpup_attr() */ +static noinline_for_stack +int au_cpdown_attr(struct path *h_path, struct dentry *h_src) +{ + int err, sbits; + struct iattr ia; + struct inode *h_isrc; + + h_isrc = h_src->d_inode; + ia.ia_valid = ATTR_FORCE | ATTR_MODE | ATTR_UID | ATTR_GID; + ia.ia_mode = h_isrc->i_mode; + ia.ia_uid = h_isrc->i_uid; + ia.ia_gid = h_isrc->i_gid; + sbits = !!(ia.ia_mode & (S_ISUID | S_ISGID)); + au_cpup_attr_flags(h_path->dentry->d_inode, h_isrc); + err = vfsub_sio_notify_change(h_path, &ia); + + /* is this nfs only? */ + if (!err && sbits && au_test_nfs(h_path->dentry->d_sb)) { + ia.ia_valid = ATTR_FORCE | ATTR_MODE; + ia.ia_mode = h_isrc->i_mode; + err = vfsub_sio_notify_change(h_path, &ia); + } + + return err; +} + +#define AuCpdown_PARENT_OPQ 1 +#define AuCpdown_WHED (1 << 1) +#define AuCpdown_MADE_DIR (1 << 2) +#define AuCpdown_DIROPQ (1 << 3) +#define au_ftest_cpdown(flags, name) ((flags) & AuCpdown_##name) +#define au_fset_cpdown(flags, name) \ + do { (flags) |= AuCpdown_##name; } while (0) +#define au_fclr_cpdown(flags, name) \ + do { (flags) &= ~AuCpdown_##name; } while (0) + +struct au_cpdown_dir_args { + struct dentry *parent; + unsigned int flags; +}; + +static int au_cpdown_dir_opq(struct dentry *dentry, aufs_bindex_t bdst, + struct au_cpdown_dir_args *a) +{ + int err; + struct dentry *opq_dentry; + + opq_dentry = au_diropq_create(dentry, bdst); + err = PTR_ERR(opq_dentry); + if (IS_ERR(opq_dentry)) + goto out; + dput(opq_dentry); + au_fset_cpdown(a->flags, DIROPQ); + +out: + return err; +} + +static int au_cpdown_dir_wh(struct dentry *dentry, struct dentry *h_parent, + struct inode *dir, aufs_bindex_t bdst) +{ + int err; + struct path h_path; + struct au_branch *br; + + br = au_sbr(dentry->d_sb, bdst); + h_path.dentry = au_wh_lkup(h_parent, &dentry->d_name, br); + err = PTR_ERR(h_path.dentry); + if (IS_ERR(h_path.dentry)) + goto out; + + err = 0; + if (h_path.dentry->d_inode) { + h_path.mnt = br->br_mnt; + err = au_wh_unlink_dentry(au_h_iptr(dir, bdst), &h_path, + dentry); + } + dput(h_path.dentry); + +out: + return err; +} + +static int au_cpdown_dir(struct dentry *dentry, aufs_bindex_t bdst, + struct dentry *h_parent, void *arg) +{ + int err, rerr; + aufs_bindex_t bopq, bstart; + struct path h_path; + struct dentry *parent; + struct inode *h_dir, *h_inode, *inode, *dir; + struct au_cpdown_dir_args *args = arg; + + bstart = au_dbstart(dentry); + /* dentry is di-locked */ + parent = dget_parent(dentry); + dir = parent->d_inode; + h_dir = h_parent->d_inode; + AuDebugOn(h_dir != au_h_iptr(dir, bdst)); + IMustLock(h_dir); + + err = au_lkup_neg(dentry, bdst); + if (unlikely(err < 0)) + goto out; + h_path.dentry = au_h_dptr(dentry, bdst); + h_path.mnt = au_sbr_mnt(dentry->d_sb, bdst); + err = vfsub_sio_mkdir(au_h_iptr(dir, bdst), &h_path, + S_IRWXU | S_IRUGO | S_IXUGO); + if (unlikely(err)) + goto out_put; + au_fset_cpdown(args->flags, MADE_DIR); + + bopq = au_dbdiropq(dentry); + au_fclr_cpdown(args->flags, WHED); + au_fclr_cpdown(args->flags, DIROPQ); + if (au_dbwh(dentry) == bdst) + au_fset_cpdown(args->flags, WHED); + if (!au_ftest_cpdown(args->flags, PARENT_OPQ) && bopq <= bdst) + au_fset_cpdown(args->flags, PARENT_OPQ); + h_inode = h_path.dentry->d_inode; + mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD); + if (au_ftest_cpdown(args->flags, WHED)) { + err = au_cpdown_dir_opq(dentry, bdst, args); + if (unlikely(err)) { + mutex_unlock(&h_inode->i_mutex); + goto out_dir; + } + } + + err = au_cpdown_attr(&h_path, au_h_dptr(dentry, bstart)); + mutex_unlock(&h_inode->i_mutex); + if (unlikely(err)) + goto out_opq; + + if (au_ftest_cpdown(args->flags, WHED)) { + err = au_cpdown_dir_wh(dentry, h_parent, dir, bdst); + if (unlikely(err)) + goto out_opq; + } + + inode = dentry->d_inode; + if (au_ibend(inode) < bdst) + au_set_ibend(inode, bdst); + au_set_h_iptr(inode, bdst, au_igrab(h_inode), + au_hi_flags(inode, /*isdir*/1)); + goto out; /* success */ + + /* revert */ +out_opq: + if (au_ftest_cpdown(args->flags, DIROPQ)) { + mutex_lock_nested(&h_inode->i_mutex, AuLsc_I_CHILD); + rerr = au_diropq_remove(dentry, bdst); + mutex_unlock(&h_inode->i_mutex); + if (unlikely(rerr)) { + AuIOErr("failed removing diropq for %.*s b%d (%d)\n", + AuDLNPair(dentry), bdst, rerr); + err = -EIO; + goto out; + } + } +out_dir: + if (au_ftest_cpdown(args->flags, MADE_DIR)) { + rerr = vfsub_sio_rmdir(au_h_iptr(dir, bdst), &h_path); + if (unlikely(rerr)) { + AuIOErr("failed removing %.*s b%d (%d)\n", + AuDLNPair(dentry), bdst, rerr); + err = -EIO; + } + } +out_put: + au_set_h_dptr(dentry, bdst, NULL); + if (au_dbend(dentry) == bdst) + au_update_dbend(dentry); +out: + dput(parent); + return err; +} + +int au_cpdown_dirs(struct dentry *dentry, aufs_bindex_t bdst) +{ + int err; + struct au_cpdown_dir_args args = { + .parent = dget_parent(dentry), + .flags = 0 + }; + + err = au_cp_dirs(dentry, bdst, au_cpdown_dir, &args); + dput(args.parent); + + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* policies for create */ + +static int au_wbr_nonopq(struct dentry *dentry, aufs_bindex_t bindex) +{ + int err, i, j, ndentry; + aufs_bindex_t bopq; + struct au_dcsub_pages dpages; + struct au_dpage *dpage; + struct dentry **dentries, *parent, *d; + + err = au_dpages_init(&dpages, GFP_NOFS); + if (unlikely(err)) + goto out; + parent = dget_parent(dentry); + err = au_dcsub_pages_rev_aufs(&dpages, parent, /*do_include*/0); + if (unlikely(err)) + goto out_free; + + err = bindex; + for (i = 0; i < dpages.ndpage; i++) { + dpage = dpages.dpages + i; + dentries = dpage->dentries; + ndentry = dpage->ndentry; + for (j = 0; j < ndentry; j++) { + d = dentries[j]; + di_read_lock_parent2(d, !AuLock_IR); + bopq = au_dbdiropq(d); + di_read_unlock(d, !AuLock_IR); + if (bopq >= 0 && bopq < err) + err = bopq; + } + } + +out_free: + dput(parent); + au_dpages_free(&dpages); +out: + return err; +} + +static int au_wbr_bu(struct super_block *sb, aufs_bindex_t bindex) +{ + for (; bindex >= 0; bindex--) + if (!au_br_rdonly(au_sbr(sb, bindex))) + return bindex; + return -EROFS; +} + +/* top down parent */ +static int au_wbr_create_tdp(struct dentry *dentry, int isdir __maybe_unused) +{ + int err; + aufs_bindex_t bstart, bindex; + struct super_block *sb; + struct dentry *parent, *h_parent; + + sb = dentry->d_sb; + bstart = au_dbstart(dentry); + err = bstart; + if (!au_br_rdonly(au_sbr(sb, bstart))) + goto out; + + err = -EROFS; + parent = dget_parent(dentry); + for (bindex = au_dbstart(parent); bindex < bstart; bindex++) { + h_parent = au_h_dptr(parent, bindex); + if (!h_parent || !h_parent->d_inode) + continue; + + if (!au_br_rdonly(au_sbr(sb, bindex))) { + err = bindex; + break; + } + } + dput(parent); + + /* bottom up here */ + if (unlikely(err < 0)) { + err = au_wbr_bu(sb, bstart - 1); + if (err >= 0) + err = au_wbr_nonopq(dentry, err); + } + +out: + AuDbg("b%d\n", err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* an exception for the policy other than tdp */ +static int au_wbr_create_exp(struct dentry *dentry) +{ + int err; + aufs_bindex_t bwh, bdiropq; + struct dentry *parent; + + err = -1; + bwh = au_dbwh(dentry); + parent = dget_parent(dentry); + bdiropq = au_dbdiropq(parent); + if (bwh >= 0) { + if (bdiropq >= 0) + err = min(bdiropq, bwh); + else + err = bwh; + AuDbg("%d\n", err); + } else if (bdiropq >= 0) { + err = bdiropq; + AuDbg("%d\n", err); + } + dput(parent); + + if (err >= 0) + err = au_wbr_nonopq(dentry, err); + + if (err >= 0 && au_br_rdonly(au_sbr(dentry->d_sb, err))) + err = -1; + + AuDbg("%d\n", err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* round robin */ +static int au_wbr_create_init_rr(struct super_block *sb) +{ + int err; + + err = au_wbr_bu(sb, au_sbend(sb)); + atomic_set(&au_sbi(sb)->si_wbr_rr_next, -err); /* less important */ + /* smp_mb(); */ + + AuDbg("b%d\n", err); + return err; +} + +static int au_wbr_create_rr(struct dentry *dentry, int isdir) +{ + int err, nbr; + unsigned int u; + aufs_bindex_t bindex, bend; + struct super_block *sb; + atomic_t *next; + + err = au_wbr_create_exp(dentry); + if (err >= 0) + goto out; + + sb = dentry->d_sb; + next = &au_sbi(sb)->si_wbr_rr_next; + bend = au_sbend(sb); + nbr = bend + 1; + for (bindex = 0; bindex <= bend; bindex++) { + if (!isdir) { + err = atomic_dec_return(next) + 1; + /* modulo for 0 is meaningless */ + if (unlikely(!err)) + err = atomic_dec_return(next) + 1; + } else + err = atomic_read(next); + AuDbg("%d\n", err); + u = err; + err = u % nbr; + AuDbg("%d\n", err); + if (!au_br_rdonly(au_sbr(sb, err))) + break; + err = -EROFS; + } + + if (err >= 0) + err = au_wbr_nonopq(dentry, err); + +out: + AuDbg("%d\n", err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* most free space */ +static void au_mfs(struct dentry *dentry) +{ + struct super_block *sb; + struct au_branch *br; + struct au_wbr_mfs *mfs; + aufs_bindex_t bindex, bend; + int err; + unsigned long long b, bavail; + struct path h_path; + /* reduce the stack usage */ + struct kstatfs *st; + + st = kmalloc(sizeof(*st), GFP_NOFS); + if (unlikely(!st)) { + AuWarn1("failed updating mfs(%d), ignored\n", -ENOMEM); + return; + } + + bavail = 0; + sb = dentry->d_sb; + mfs = &au_sbi(sb)->si_wbr_mfs; + MtxMustLock(&mfs->mfs_lock); + mfs->mfs_bindex = -EROFS; + mfs->mfsrr_bytes = 0; + bend = au_sbend(sb); + for (bindex = 0; bindex <= bend; bindex++) { + br = au_sbr(sb, bindex); + if (au_br_rdonly(br)) + continue; + + /* sb->s_root for NFS is unreliable */ + h_path.mnt = br->br_mnt; + h_path.dentry = h_path.mnt->mnt_root; + err = vfs_statfs(&h_path, st); + if (unlikely(err)) { + AuWarn1("failed statfs, b%d, %d\n", bindex, err); + continue; + } + + /* when the available size is equal, select the lower one */ + BUILD_BUG_ON(sizeof(b) < sizeof(st->f_bavail) + || sizeof(b) < sizeof(st->f_bsize)); + b = st->f_bavail * st->f_bsize; + br->br_wbr->wbr_bytes = b; + if (b >= bavail) { + bavail = b; + mfs->mfs_bindex = bindex; + mfs->mfs_jiffy = jiffies; + } + } + + mfs->mfsrr_bytes = bavail; + AuDbg("b%d\n", mfs->mfs_bindex); + kfree(st); +} + +static int au_wbr_create_mfs(struct dentry *dentry, int isdir __maybe_unused) +{ + int err; + struct super_block *sb; + struct au_wbr_mfs *mfs; + + err = au_wbr_create_exp(dentry); + if (err >= 0) + goto out; + + sb = dentry->d_sb; + mfs = &au_sbi(sb)->si_wbr_mfs; + mutex_lock(&mfs->mfs_lock); + if (time_after(jiffies, mfs->mfs_jiffy + mfs->mfs_expire) + || mfs->mfs_bindex < 0 + || au_br_rdonly(au_sbr(sb, mfs->mfs_bindex))) + au_mfs(dentry); + mutex_unlock(&mfs->mfs_lock); + err = mfs->mfs_bindex; + + if (err >= 0) + err = au_wbr_nonopq(dentry, err); + +out: + AuDbg("b%d\n", err); + return err; +} + +static int au_wbr_create_init_mfs(struct super_block *sb) +{ + struct au_wbr_mfs *mfs; + + mfs = &au_sbi(sb)->si_wbr_mfs; + mutex_init(&mfs->mfs_lock); + mfs->mfs_jiffy = 0; + mfs->mfs_bindex = -EROFS; + + return 0; +} + +static int au_wbr_create_fin_mfs(struct super_block *sb __maybe_unused) +{ + mutex_destroy(&au_sbi(sb)->si_wbr_mfs.mfs_lock); + return 0; +} + +/* ---------------------------------------------------------------------- */ + +/* most free space and then round robin */ +static int au_wbr_create_mfsrr(struct dentry *dentry, int isdir) +{ + int err; + struct au_wbr_mfs *mfs; + + err = au_wbr_create_mfs(dentry, isdir); + if (err >= 0) { + mfs = &au_sbi(dentry->d_sb)->si_wbr_mfs; + mutex_lock(&mfs->mfs_lock); + if (mfs->mfsrr_bytes < mfs->mfsrr_watermark) + err = au_wbr_create_rr(dentry, isdir); + mutex_unlock(&mfs->mfs_lock); + } + + AuDbg("b%d\n", err); + return err; +} + +static int au_wbr_create_init_mfsrr(struct super_block *sb) +{ + int err; + + au_wbr_create_init_mfs(sb); /* ignore */ + err = au_wbr_create_init_rr(sb); + + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* top down parent and most free space */ +static int au_wbr_create_pmfs(struct dentry *dentry, int isdir) +{ + int err, e2; + unsigned long long b; + aufs_bindex_t bindex, bstart, bend; + struct super_block *sb; + struct dentry *parent, *h_parent; + struct au_branch *br; + + err = au_wbr_create_tdp(dentry, isdir); + if (unlikely(err < 0)) + goto out; + parent = dget_parent(dentry); + bstart = au_dbstart(parent); + bend = au_dbtaildir(parent); + if (bstart == bend) + goto out_parent; /* success */ + + e2 = au_wbr_create_mfs(dentry, isdir); + if (e2 < 0) + goto out_parent; /* success */ + + /* when the available size is equal, select upper one */ + sb = dentry->d_sb; + br = au_sbr(sb, err); + b = br->br_wbr->wbr_bytes; + AuDbg("b%d, %llu\n", err, b); + + for (bindex = bstart; bindex <= bend; bindex++) { + h_parent = au_h_dptr(parent, bindex); + if (!h_parent || !h_parent->d_inode) + continue; + + br = au_sbr(sb, bindex); + if (!au_br_rdonly(br) && br->br_wbr->wbr_bytes > b) { + b = br->br_wbr->wbr_bytes; + err = bindex; + AuDbg("b%d, %llu\n", err, b); + } + } + + if (err >= 0) + err = au_wbr_nonopq(dentry, err); + +out_parent: + dput(parent); +out: + AuDbg("b%d\n", err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* policies for copyup */ + +/* top down parent */ +static int au_wbr_copyup_tdp(struct dentry *dentry) +{ + return au_wbr_create_tdp(dentry, /*isdir, anything is ok*/0); +} + +/* bottom up parent */ +static int au_wbr_copyup_bup(struct dentry *dentry) +{ + int err; + aufs_bindex_t bindex, bstart; + struct dentry *parent, *h_parent; + struct super_block *sb; + + err = -EROFS; + sb = dentry->d_sb; + parent = dget_parent(dentry); + bstart = au_dbstart(parent); + for (bindex = au_dbstart(dentry); bindex >= bstart; bindex--) { + h_parent = au_h_dptr(parent, bindex); + if (!h_parent || !h_parent->d_inode) + continue; + + if (!au_br_rdonly(au_sbr(sb, bindex))) { + err = bindex; + break; + } + } + dput(parent); + + /* bottom up here */ + if (unlikely(err < 0)) + err = au_wbr_bu(sb, bstart - 1); + + AuDbg("b%d\n", err); + return err; +} + +/* bottom up */ +static int au_wbr_copyup_bu(struct dentry *dentry) +{ + int err; + aufs_bindex_t bstart; + + bstart = au_dbstart(dentry); + err = au_wbr_bu(dentry->d_sb, bstart); + AuDbg("b%d\n", err); + if (err > bstart) + err = au_wbr_nonopq(dentry, err); + + AuDbg("b%d\n", err); + return err; +} + +/* ---------------------------------------------------------------------- */ + +struct au_wbr_copyup_operations au_wbr_copyup_ops[] = { + [AuWbrCopyup_TDP] = { + .copyup = au_wbr_copyup_tdp + }, + [AuWbrCopyup_BUP] = { + .copyup = au_wbr_copyup_bup + }, + [AuWbrCopyup_BU] = { + .copyup = au_wbr_copyup_bu + } +}; + +struct au_wbr_create_operations au_wbr_create_ops[] = { + [AuWbrCreate_TDP] = { + .create = au_wbr_create_tdp + }, + [AuWbrCreate_RR] = { + .create = au_wbr_create_rr, + .init = au_wbr_create_init_rr + }, + [AuWbrCreate_MFS] = { + .create = au_wbr_create_mfs, + .init = au_wbr_create_init_mfs, + .fin = au_wbr_create_fin_mfs + }, + [AuWbrCreate_MFSV] = { + .create = au_wbr_create_mfs, + .init = au_wbr_create_init_mfs, + .fin = au_wbr_create_fin_mfs + }, + [AuWbrCreate_MFSRR] = { + .create = au_wbr_create_mfsrr, + .init = au_wbr_create_init_mfsrr, + .fin = au_wbr_create_fin_mfs + }, + [AuWbrCreate_MFSRRV] = { + .create = au_wbr_create_mfsrr, + .init = au_wbr_create_init_mfsrr, + .fin = au_wbr_create_fin_mfs + }, + [AuWbrCreate_PMFS] = { + .create = au_wbr_create_pmfs, + .init = au_wbr_create_init_mfs, + .fin = au_wbr_create_fin_mfs + }, + [AuWbrCreate_PMFSV] = { + .create = au_wbr_create_pmfs, + .init = au_wbr_create_init_mfs, + .fin = au_wbr_create_fin_mfs + } +}; diff --git a/ubuntu/aufs/whout.c b/ubuntu/aufs/whout.c new file mode 100644 index 000000000000..676486362d54 --- /dev/null +++ b/ubuntu/aufs/whout.c @@ -0,0 +1,1049 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * whiteout for logical deletion and opaque directory + */ + +#include "aufs.h" + +#define WH_MASK S_IRUGO + +/* + * If a directory contains this file, then it is opaque. We start with the + * .wh. flag so that it is blocked by lookup. + */ +static struct qstr diropq_name = { + .name = AUFS_WH_DIROPQ, + .len = sizeof(AUFS_WH_DIROPQ) - 1 +}; + +/* + * generate whiteout name, which is NOT terminated by NULL. + * @name: original d_name.name + * @len: original d_name.len + * @wh: whiteout qstr + * returns zero when succeeds, otherwise error. + * succeeded value as wh->name should be freed by kfree(). + */ +int au_wh_name_alloc(struct qstr *wh, const struct qstr *name) +{ + char *p; + + if (unlikely(name->len > PATH_MAX - AUFS_WH_PFX_LEN)) + return -ENAMETOOLONG; + + wh->len = name->len + AUFS_WH_PFX_LEN; + p = kmalloc(wh->len, GFP_NOFS); + wh->name = p; + if (p) { + memcpy(p, AUFS_WH_PFX, AUFS_WH_PFX_LEN); + memcpy(p + AUFS_WH_PFX_LEN, name->name, name->len); + /* smp_mb(); */ + return 0; + } + return -ENOMEM; +} + +/* ---------------------------------------------------------------------- */ + +/* + * test if the @wh_name exists under @h_parent. + * @try_sio specifies the necessary of super-io. + */ +int au_wh_test(struct dentry *h_parent, struct qstr *wh_name, + struct au_branch *br, int try_sio) +{ + int err; + struct dentry *wh_dentry; + + if (!try_sio) + wh_dentry = au_lkup_one(wh_name, h_parent, br, /*nd*/NULL); + else + wh_dentry = au_sio_lkup_one(wh_name, h_parent, br); + err = PTR_ERR(wh_dentry); + if (IS_ERR(wh_dentry)) + goto out; + + err = 0; + if (!wh_dentry->d_inode) + goto out_wh; /* success */ + + err = 1; + if (S_ISREG(wh_dentry->d_inode->i_mode)) + goto out_wh; /* success */ + + err = -EIO; + AuIOErr("%.*s Invalid whiteout entry type 0%o.\n", + AuDLNPair(wh_dentry), wh_dentry->d_inode->i_mode); + +out_wh: + dput(wh_dentry); +out: + return err; +} + +/* + * test if the @h_dentry sets opaque or not. + */ +int au_diropq_test(struct dentry *h_dentry, struct au_branch *br) +{ + int err; + struct inode *h_dir; + + h_dir = h_dentry->d_inode; + err = au_wh_test(h_dentry, &diropq_name, br, + au_test_h_perm_sio(h_dir, MAY_EXEC)); + return err; +} + +/* + * returns a negative dentry whose name is unique and temporary. + */ +struct dentry *au_whtmp_lkup(struct dentry *h_parent, struct au_branch *br, + struct qstr *prefix) +{ + struct dentry *dentry; + int i; + char defname[NAME_MAX - AUFS_MAX_NAMELEN + DNAME_INLINE_LEN + 1], + *name, *p; + /* strict atomic_t is unnecessary here */ + static unsigned short cnt; + struct qstr qs; + + BUILD_BUG_ON(sizeof(cnt) * 2 > AUFS_WH_TMP_LEN); + + name = defname; + qs.len = sizeof(defname) - DNAME_INLINE_LEN + prefix->len - 1; + if (unlikely(prefix->len > DNAME_INLINE_LEN)) { + dentry = ERR_PTR(-ENAMETOOLONG); + if (unlikely(qs.len > NAME_MAX)) + goto out; + dentry = ERR_PTR(-ENOMEM); + name = kmalloc(qs.len + 1, GFP_NOFS); + if (unlikely(!name)) + goto out; + } + + /* doubly whiteout-ed */ + memcpy(name, AUFS_WH_PFX AUFS_WH_PFX, AUFS_WH_PFX_LEN * 2); + p = name + AUFS_WH_PFX_LEN * 2; + memcpy(p, prefix->name, prefix->len); + p += prefix->len; + *p++ = '.'; + AuDebugOn(name + qs.len + 1 - p <= AUFS_WH_TMP_LEN); + + qs.name = name; + for (i = 0; i < 3; i++) { + sprintf(p, "%.*x", AUFS_WH_TMP_LEN, cnt++); + dentry = au_sio_lkup_one(&qs, h_parent, br); + if (IS_ERR(dentry) || !dentry->d_inode) + goto out_name; + dput(dentry); + } + /* pr_warning("could not get random name\n"); */ + dentry = ERR_PTR(-EEXIST); + AuDbg("%.*s\n", AuLNPair(&qs)); + BUG(); + +out_name: + if (name != defname) + kfree(name); +out: + AuTraceErrPtr(dentry); + return dentry; +} + +/* + * rename the @h_dentry on @br to the whiteouted temporary name. + */ +int au_whtmp_ren(struct dentry *h_dentry, struct au_branch *br) +{ + int err; + struct path h_path = { + .mnt = br->br_mnt + }; + struct inode *h_dir; + struct dentry *h_parent; + + h_parent = h_dentry->d_parent; /* dir inode is locked */ + h_dir = h_parent->d_inode; + IMustLock(h_dir); + + h_path.dentry = au_whtmp_lkup(h_parent, br, &h_dentry->d_name); + err = PTR_ERR(h_path.dentry); + if (IS_ERR(h_path.dentry)) + goto out; + + /* under the same dir, no need to lock_rename() */ + err = vfsub_rename(h_dir, h_dentry, h_dir, &h_path); + AuTraceErr(err); + dput(h_path.dentry); + +out: + AuTraceErr(err); + return err; +} + +/* ---------------------------------------------------------------------- */ +/* + * functions for removing a whiteout + */ + +static int do_unlink_wh(struct inode *h_dir, struct path *h_path) +{ + int force; + + /* + * forces superio when the dir has a sticky bit. + * this may be a violation of unix fs semantics. + */ + force = (h_dir->i_mode & S_ISVTX) + && h_path->dentry->d_inode->i_uid != current_fsuid(); + return vfsub_unlink(h_dir, h_path, force); +} + +int au_wh_unlink_dentry(struct inode *h_dir, struct path *h_path, + struct dentry *dentry) +{ + int err; + + err = do_unlink_wh(h_dir, h_path); + if (!err && dentry) + au_set_dbwh(dentry, -1); + + return err; +} + +static int unlink_wh_name(struct dentry *h_parent, struct qstr *wh, + struct au_branch *br) +{ + int err; + struct path h_path = { + .mnt = br->br_mnt + }; + + err = 0; + h_path.dentry = au_lkup_one(wh, h_parent, br, /*nd*/NULL); + if (IS_ERR(h_path.dentry)) + err = PTR_ERR(h_path.dentry); + else { + if (h_path.dentry->d_inode + && S_ISREG(h_path.dentry->d_inode->i_mode)) + err = do_unlink_wh(h_parent->d_inode, &h_path); + dput(h_path.dentry); + } + + return err; +} + +/* ---------------------------------------------------------------------- */ +/* + * initialize/clean whiteout for a branch + */ + +static void au_wh_clean(struct inode *h_dir, struct path *whpath, + const int isdir) +{ + int err; + + if (!whpath->dentry->d_inode) + return; + + err = mnt_want_write(whpath->mnt); + if (!err) { + if (isdir) + err = vfsub_rmdir(h_dir, whpath); + else + err = vfsub_unlink(h_dir, whpath, /*force*/0); + mnt_drop_write(whpath->mnt); + } + if (unlikely(err)) + pr_warning("failed removing %.*s (%d), ignored.\n", + AuDLNPair(whpath->dentry), err); +} + +static int test_linkable(struct dentry *h_root) +{ + struct inode *h_dir = h_root->d_inode; + + if (h_dir->i_op->link) + return 0; + + pr_err("%.*s (%s) doesn't support link(2), use noplink and rw+nolwh\n", + AuDLNPair(h_root), au_sbtype(h_root->d_sb)); + return -ENOSYS; +} + +/* todo: should this mkdir be done in /sbin/mount.aufs helper? */ +static int au_whdir(struct inode *h_dir, struct path *path) +{ + int err; + + err = -EEXIST; + if (!path->dentry->d_inode) { + int mode = S_IRWXU; + + if (au_test_nfs(path->dentry->d_sb)) + mode |= S_IXUGO; + err = mnt_want_write(path->mnt); + if (!err) { + err = vfsub_mkdir(h_dir, path, mode); + mnt_drop_write(path->mnt); + } + } else if (S_ISDIR(path->dentry->d_inode->i_mode)) + err = 0; + else + pr_err("unknown %.*s exists\n", AuDLNPair(path->dentry)); + + return err; +} + +struct au_wh_base { + const struct qstr *name; + struct dentry *dentry; +}; + +static void au_wh_init_ro(struct inode *h_dir, struct au_wh_base base[], + struct path *h_path) +{ + h_path->dentry = base[AuBrWh_BASE].dentry; + au_wh_clean(h_dir, h_path, /*isdir*/0); + h_path->dentry = base[AuBrWh_PLINK].dentry; + au_wh_clean(h_dir, h_path, /*isdir*/1); + h_path->dentry = base[AuBrWh_ORPH].dentry; + au_wh_clean(h_dir, h_path, /*isdir*/1); +} + +/* + * returns tri-state, + * minus: error, caller should print the mesage + * zero: succuess + * plus: error, caller should NOT print the mesage + */ +static int au_wh_init_rw_nolink(struct dentry *h_root, struct au_wbr *wbr, + int do_plink, struct au_wh_base base[], + struct path *h_path) +{ + int err; + struct inode *h_dir; + + h_dir = h_root->d_inode; + h_path->dentry = base[AuBrWh_BASE].dentry; + au_wh_clean(h_dir, h_path, /*isdir*/0); + h_path->dentry = base[AuBrWh_PLINK].dentry; + if (do_plink) { + err = test_linkable(h_root); + if (unlikely(err)) { + err = 1; + goto out; + } + + err = au_whdir(h_dir, h_path); + if (unlikely(err)) + goto out; + wbr->wbr_plink = dget(base[AuBrWh_PLINK].dentry); + } else + au_wh_clean(h_dir, h_path, /*isdir*/1); + h_path->dentry = base[AuBrWh_ORPH].dentry; + err = au_whdir(h_dir, h_path); + if (unlikely(err)) + goto out; + wbr->wbr_orph = dget(base[AuBrWh_ORPH].dentry); + +out: + return err; +} + +/* + * for the moment, aufs supports the branch filesystem which does not support + * link(2). testing on FAT which does not support i_op->setattr() fully either, + * copyup failed. finally, such filesystem will not be used as the writable + * branch. + * + * returns tri-state, see above. + */ +static int au_wh_init_rw(struct dentry *h_root, struct au_wbr *wbr, + int do_plink, struct au_wh_base base[], + struct path *h_path) +{ + int err; + struct inode *h_dir; + + WbrWhMustWriteLock(wbr); + + err = test_linkable(h_root); + if (unlikely(err)) { + err = 1; + goto out; + } + + /* + * todo: should this create be done in /sbin/mount.aufs helper? + */ + err = -EEXIST; + h_dir = h_root->d_inode; + if (!base[AuBrWh_BASE].dentry->d_inode) { + err = mnt_want_write(h_path->mnt); + if (!err) { + h_path->dentry = base[AuBrWh_BASE].dentry; + err = vfsub_create(h_dir, h_path, WH_MASK); + mnt_drop_write(h_path->mnt); + } + } else if (S_ISREG(base[AuBrWh_BASE].dentry->d_inode->i_mode)) + err = 0; + else + pr_err("unknown %.*s/%.*s exists\n", + AuDLNPair(h_root), AuDLNPair(base[AuBrWh_BASE].dentry)); + if (unlikely(err)) + goto out; + + h_path->dentry = base[AuBrWh_PLINK].dentry; + if (do_plink) { + err = au_whdir(h_dir, h_path); + if (unlikely(err)) + goto out; + wbr->wbr_plink = dget(base[AuBrWh_PLINK].dentry); + } else + au_wh_clean(h_dir, h_path, /*isdir*/1); + wbr->wbr_whbase = dget(base[AuBrWh_BASE].dentry); + + h_path->dentry = base[AuBrWh_ORPH].dentry; + err = au_whdir(h_dir, h_path); + if (unlikely(err)) + goto out; + wbr->wbr_orph = dget(base[AuBrWh_ORPH].dentry); + +out: + return err; +} + +/* + * initialize the whiteout base file/dir for @br. + */ +int au_wh_init(struct dentry *h_root, struct au_branch *br, + struct super_block *sb) +{ + int err, i; + const unsigned char do_plink + = !!au_opt_test(au_mntflags(sb), PLINK); + struct path path = { + .mnt = br->br_mnt + }; + struct inode *h_dir; + struct au_wbr *wbr = br->br_wbr; + static const struct qstr base_name[] = { + [AuBrWh_BASE] = { + .name = AUFS_BASE_NAME, + .len = sizeof(AUFS_BASE_NAME) - 1 + }, + [AuBrWh_PLINK] = { + .name = AUFS_PLINKDIR_NAME, + .len = sizeof(AUFS_PLINKDIR_NAME) - 1 + }, + [AuBrWh_ORPH] = { + .name = AUFS_ORPHDIR_NAME, + .len = sizeof(AUFS_ORPHDIR_NAME) - 1 + } + }; + struct au_wh_base base[] = { + [AuBrWh_BASE] = { + .name = base_name + AuBrWh_BASE, + .dentry = NULL + }, + [AuBrWh_PLINK] = { + .name = base_name + AuBrWh_PLINK, + .dentry = NULL + }, + [AuBrWh_ORPH] = { + .name = base_name + AuBrWh_ORPH, + .dentry = NULL + } + }; + + if (wbr) + WbrWhMustWriteLock(wbr); + + for (i = 0; i < AuBrWh_Last; i++) { + /* doubly whiteouted */ + struct dentry *d; + + d = au_wh_lkup(h_root, (void *)base[i].name, br); + err = PTR_ERR(d); + if (IS_ERR(d)) + goto out; + + base[i].dentry = d; + AuDebugOn(wbr + && wbr->wbr_wh[i] + && wbr->wbr_wh[i] != base[i].dentry); + } + + if (wbr) + for (i = 0; i < AuBrWh_Last; i++) { + dput(wbr->wbr_wh[i]); + wbr->wbr_wh[i] = NULL; + } + + err = 0; + if (!au_br_writable(br->br_perm)) { + h_dir = h_root->d_inode; + au_wh_init_ro(h_dir, base, &path); + } else if (!au_br_wh_linkable(br->br_perm)) { + err = au_wh_init_rw_nolink(h_root, wbr, do_plink, base, &path); + if (err > 0) + goto out; + else if (err) + goto out_err; + } else { + err = au_wh_init_rw(h_root, wbr, do_plink, base, &path); + if (err > 0) + goto out; + else if (err) + goto out_err; + } + goto out; /* success */ + +out_err: + pr_err("an error(%d) on the writable branch %.*s(%s)\n", + err, AuDLNPair(h_root), au_sbtype(h_root->d_sb)); +out: + for (i = 0; i < AuBrWh_Last; i++) + dput(base[i].dentry); + return err; +} + +/* ---------------------------------------------------------------------- */ +/* + * whiteouts are all hard-linked usually. + * when its link count reaches a ceiling, we create a new whiteout base + * asynchronously. + */ + +struct reinit_br_wh { + struct super_block *sb; + struct au_branch *br; +}; + +static void reinit_br_wh(void *arg) +{ + int err; + aufs_bindex_t bindex; + struct path h_path; + struct reinit_br_wh *a = arg; + struct au_wbr *wbr; + struct inode *dir; + struct dentry *h_root; + struct au_hinode *hdir; + + err = 0; + wbr = a->br->br_wbr; + /* big aufs lock */ + si_noflush_write_lock(a->sb); + if (!au_br_writable(a->br->br_perm)) + goto out; + bindex = au_br_index(a->sb, a->br->br_id); + if (unlikely(bindex < 0)) + goto out; + + di_read_lock_parent(a->sb->s_root, AuLock_IR); + dir = a->sb->s_root->d_inode; + hdir = au_hi(dir, bindex); + h_root = au_h_dptr(a->sb->s_root, bindex); + + au_hn_imtx_lock_nested(hdir, AuLsc_I_PARENT); + wbr_wh_write_lock(wbr); + err = au_h_verify(wbr->wbr_whbase, au_opt_udba(a->sb), hdir->hi_inode, + h_root, a->br); + if (!err) { + err = mnt_want_write(a->br->br_mnt); + if (!err) { + h_path.dentry = wbr->wbr_whbase; + h_path.mnt = a->br->br_mnt; + err = vfsub_unlink(hdir->hi_inode, &h_path, /*force*/0); + mnt_drop_write(a->br->br_mnt); + } + } else { + pr_warning("%.*s is moved, ignored\n", + AuDLNPair(wbr->wbr_whbase)); + err = 0; + } + dput(wbr->wbr_whbase); + wbr->wbr_whbase = NULL; + if (!err) + err = au_wh_init(h_root, a->br, a->sb); + wbr_wh_write_unlock(wbr); + au_hn_imtx_unlock(hdir); + di_read_unlock(a->sb->s_root, AuLock_IR); + +out: + if (wbr) + atomic_dec(&wbr->wbr_wh_running); + atomic_dec(&a->br->br_count); + si_write_unlock(a->sb); + au_nwt_done(&au_sbi(a->sb)->si_nowait); + kfree(arg); + if (unlikely(err)) + AuIOErr("err %d\n", err); +} + +static void kick_reinit_br_wh(struct super_block *sb, struct au_branch *br) +{ + int do_dec, wkq_err; + struct reinit_br_wh *arg; + + do_dec = 1; + if (atomic_inc_return(&br->br_wbr->wbr_wh_running) != 1) + goto out; + + /* ignore ENOMEM */ + arg = kmalloc(sizeof(*arg), GFP_NOFS); + if (arg) { + /* + * dec(wh_running), kfree(arg) and dec(br_count) + * in reinit function + */ + arg->sb = sb; + arg->br = br; + atomic_inc(&br->br_count); + wkq_err = au_wkq_nowait(reinit_br_wh, arg, sb, /*flags*/0); + if (unlikely(wkq_err)) { + atomic_dec(&br->br_wbr->wbr_wh_running); + atomic_dec(&br->br_count); + kfree(arg); + } + do_dec = 0; + } + +out: + if (do_dec) + atomic_dec(&br->br_wbr->wbr_wh_running); +} + +/* ---------------------------------------------------------------------- */ + +/* + * create the whiteout @wh. + */ +static int link_or_create_wh(struct super_block *sb, aufs_bindex_t bindex, + struct dentry *wh) +{ + int err; + struct path h_path = { + .dentry = wh + }; + struct au_branch *br; + struct au_wbr *wbr; + struct dentry *h_parent; + struct inode *h_dir; + + h_parent = wh->d_parent; /* dir inode is locked */ + h_dir = h_parent->d_inode; + IMustLock(h_dir); + + br = au_sbr(sb, bindex); + h_path.mnt = br->br_mnt; + wbr = br->br_wbr; + wbr_wh_read_lock(wbr); + if (wbr->wbr_whbase) { + err = vfsub_link(wbr->wbr_whbase, h_dir, &h_path); + if (!err || err != -EMLINK) + goto out; + + /* link count full. re-initialize br_whbase. */ + kick_reinit_br_wh(sb, br); + } + + /* return this error in this context */ + err = vfsub_create(h_dir, &h_path, WH_MASK); + +out: + wbr_wh_read_unlock(wbr); + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* + * create or remove the diropq. + */ +static struct dentry *do_diropq(struct dentry *dentry, aufs_bindex_t bindex, + unsigned int flags) +{ + struct dentry *opq_dentry, *h_dentry; + struct super_block *sb; + struct au_branch *br; + int err; + + sb = dentry->d_sb; + br = au_sbr(sb, bindex); + h_dentry = au_h_dptr(dentry, bindex); + opq_dentry = au_lkup_one(&diropq_name, h_dentry, br, /*nd*/NULL); + if (IS_ERR(opq_dentry)) + goto out; + + if (au_ftest_diropq(flags, CREATE)) { + err = link_or_create_wh(sb, bindex, opq_dentry); + if (!err) { + au_set_dbdiropq(dentry, bindex); + goto out; /* success */ + } + } else { + struct path tmp = { + .dentry = opq_dentry, + .mnt = br->br_mnt + }; + err = do_unlink_wh(au_h_iptr(dentry->d_inode, bindex), &tmp); + if (!err) + au_set_dbdiropq(dentry, -1); + } + dput(opq_dentry); + opq_dentry = ERR_PTR(err); + +out: + return opq_dentry; +} + +struct do_diropq_args { + struct dentry **errp; + struct dentry *dentry; + aufs_bindex_t bindex; + unsigned int flags; +}; + +static void call_do_diropq(void *args) +{ + struct do_diropq_args *a = args; + *a->errp = do_diropq(a->dentry, a->bindex, a->flags); +} + +struct dentry *au_diropq_sio(struct dentry *dentry, aufs_bindex_t bindex, + unsigned int flags) +{ + struct dentry *diropq, *h_dentry; + + h_dentry = au_h_dptr(dentry, bindex); + if (!au_test_h_perm_sio(h_dentry->d_inode, MAY_EXEC | MAY_WRITE)) + diropq = do_diropq(dentry, bindex, flags); + else { + int wkq_err; + struct do_diropq_args args = { + .errp = &diropq, + .dentry = dentry, + .bindex = bindex, + .flags = flags + }; + + wkq_err = au_wkq_wait(call_do_diropq, &args); + if (unlikely(wkq_err)) + diropq = ERR_PTR(wkq_err); + } + + return diropq; +} + +/* ---------------------------------------------------------------------- */ + +/* + * lookup whiteout dentry. + * @h_parent: lower parent dentry which must exist and be locked + * @base_name: name of dentry which will be whiteouted + * returns dentry for whiteout. + */ +struct dentry *au_wh_lkup(struct dentry *h_parent, struct qstr *base_name, + struct au_branch *br) +{ + int err; + struct qstr wh_name; + struct dentry *wh_dentry; + + err = au_wh_name_alloc(&wh_name, base_name); + wh_dentry = ERR_PTR(err); + if (!err) { + wh_dentry = au_lkup_one(&wh_name, h_parent, br, /*nd*/NULL); + kfree(wh_name.name); + } + return wh_dentry; +} + +/* + * link/create a whiteout for @dentry on @bindex. + */ +struct dentry *au_wh_create(struct dentry *dentry, aufs_bindex_t bindex, + struct dentry *h_parent) +{ + struct dentry *wh_dentry; + struct super_block *sb; + int err; + + sb = dentry->d_sb; + wh_dentry = au_wh_lkup(h_parent, &dentry->d_name, au_sbr(sb, bindex)); + if (!IS_ERR(wh_dentry) && !wh_dentry->d_inode) { + err = link_or_create_wh(sb, bindex, wh_dentry); + if (!err) + au_set_dbwh(dentry, bindex); + else { + dput(wh_dentry); + wh_dentry = ERR_PTR(err); + } + } + + return wh_dentry; +} + +/* ---------------------------------------------------------------------- */ + +/* Delete all whiteouts in this directory on branch bindex. */ +static int del_wh_children(struct dentry *h_dentry, struct au_nhash *whlist, + aufs_bindex_t bindex, struct au_branch *br) +{ + int err; + unsigned long ul, n; + struct qstr wh_name; + char *p; + struct hlist_head *head; + struct au_vdir_wh *tpos; + struct hlist_node *pos; + struct au_vdir_destr *str; + + err = -ENOMEM; + p = __getname_gfp(GFP_NOFS); + wh_name.name = p; + if (unlikely(!wh_name.name)) + goto out; + + err = 0; + memcpy(p, AUFS_WH_PFX, AUFS_WH_PFX_LEN); + p += AUFS_WH_PFX_LEN; + n = whlist->nh_num; + head = whlist->nh_head; + for (ul = 0; !err && ul < n; ul++, head++) { + hlist_for_each_entry(tpos, pos, head, wh_hash) { + if (tpos->wh_bindex != bindex) + continue; + + str = &tpos->wh_str; + if (str->len + AUFS_WH_PFX_LEN <= PATH_MAX) { + memcpy(p, str->name, str->len); + wh_name.len = AUFS_WH_PFX_LEN + str->len; + err = unlink_wh_name(h_dentry, &wh_name, br); + if (!err) + continue; + break; + } + AuIOErr("whiteout name too long %.*s\n", + str->len, str->name); + err = -EIO; + break; + } + } + __putname(wh_name.name); + +out: + return err; +} + +struct del_wh_children_args { + int *errp; + struct dentry *h_dentry; + struct au_nhash *whlist; + aufs_bindex_t bindex; + struct au_branch *br; +}; + +static void call_del_wh_children(void *args) +{ + struct del_wh_children_args *a = args; + *a->errp = del_wh_children(a->h_dentry, a->whlist, a->bindex, a->br); +} + +/* ---------------------------------------------------------------------- */ + +struct au_whtmp_rmdir *au_whtmp_rmdir_alloc(struct super_block *sb, gfp_t gfp) +{ + struct au_whtmp_rmdir *whtmp; + int err; + unsigned int rdhash; + + SiMustAnyLock(sb); + + whtmp = kmalloc(sizeof(*whtmp), gfp); + if (unlikely(!whtmp)) { + whtmp = ERR_PTR(-ENOMEM); + goto out; + } + + whtmp->dir = NULL; + whtmp->br = NULL; + whtmp->wh_dentry = NULL; + /* no estimation for dir size */ + rdhash = au_sbi(sb)->si_rdhash; + if (!rdhash) + rdhash = AUFS_RDHASH_DEF; + err = au_nhash_alloc(&whtmp->whlist, rdhash, gfp); + if (unlikely(err)) { + kfree(whtmp); + whtmp = ERR_PTR(err); + } + +out: + return whtmp; +} + +void au_whtmp_rmdir_free(struct au_whtmp_rmdir *whtmp) +{ + if (whtmp->br) + atomic_dec(&whtmp->br->br_count); + dput(whtmp->wh_dentry); + iput(whtmp->dir); + au_nhash_wh_free(&whtmp->whlist); + kfree(whtmp); +} + +/* + * rmdir the whiteouted temporary named dir @h_dentry. + * @whlist: whiteouted children. + */ +int au_whtmp_rmdir(struct inode *dir, aufs_bindex_t bindex, + struct dentry *wh_dentry, struct au_nhash *whlist) +{ + int err; + struct path h_tmp; + struct inode *wh_inode, *h_dir; + struct au_branch *br; + + h_dir = wh_dentry->d_parent->d_inode; /* dir inode is locked */ + IMustLock(h_dir); + + br = au_sbr(dir->i_sb, bindex); + wh_inode = wh_dentry->d_inode; + mutex_lock_nested(&wh_inode->i_mutex, AuLsc_I_CHILD); + + /* + * someone else might change some whiteouts while we were sleeping. + * it means this whlist may have an obsoleted entry. + */ + if (!au_test_h_perm_sio(wh_inode, MAY_EXEC | MAY_WRITE)) + err = del_wh_children(wh_dentry, whlist, bindex, br); + else { + int wkq_err; + struct del_wh_children_args args = { + .errp = &err, + .h_dentry = wh_dentry, + .whlist = whlist, + .bindex = bindex, + .br = br + }; + + wkq_err = au_wkq_wait(call_del_wh_children, &args); + if (unlikely(wkq_err)) + err = wkq_err; + } + mutex_unlock(&wh_inode->i_mutex); + + if (!err) { + h_tmp.dentry = wh_dentry; + h_tmp.mnt = br->br_mnt; + err = vfsub_rmdir(h_dir, &h_tmp); + } + + if (!err) { + if (au_ibstart(dir) == bindex) { + /* todo: dir->i_mutex is necessary */ + au_cpup_attr_timesizes(dir); + vfsub_drop_nlink(dir); + } + return 0; /* success */ + } + + pr_warning("failed removing %.*s(%d), ignored\n", + AuDLNPair(wh_dentry), err); + return err; +} + +static void call_rmdir_whtmp(void *args) +{ + int err; + aufs_bindex_t bindex; + struct au_whtmp_rmdir *a = args; + struct super_block *sb; + struct dentry *h_parent; + struct inode *h_dir; + struct au_hinode *hdir; + + /* rmdir by nfsd may cause deadlock with this i_mutex */ + /* mutex_lock(&a->dir->i_mutex); */ + err = -EROFS; + sb = a->dir->i_sb; + si_read_lock(sb, !AuLock_FLUSH); + if (!au_br_writable(a->br->br_perm)) + goto out; + bindex = au_br_index(sb, a->br->br_id); + if (unlikely(bindex < 0)) + goto out; + + err = -EIO; + ii_write_lock_parent(a->dir); + h_parent = dget_parent(a->wh_dentry); + h_dir = h_parent->d_inode; + hdir = au_hi(a->dir, bindex); + au_hn_imtx_lock_nested(hdir, AuLsc_I_PARENT); + err = au_h_verify(a->wh_dentry, au_opt_udba(sb), h_dir, h_parent, + a->br); + if (!err) { + err = mnt_want_write(a->br->br_mnt); + if (!err) { + err = au_whtmp_rmdir(a->dir, bindex, a->wh_dentry, + &a->whlist); + mnt_drop_write(a->br->br_mnt); + } + } + au_hn_imtx_unlock(hdir); + dput(h_parent); + ii_write_unlock(a->dir); + +out: + /* mutex_unlock(&a->dir->i_mutex); */ + au_whtmp_rmdir_free(a); + si_read_unlock(sb); + au_nwt_done(&au_sbi(sb)->si_nowait); + if (unlikely(err)) + AuIOErr("err %d\n", err); +} + +void au_whtmp_kick_rmdir(struct inode *dir, aufs_bindex_t bindex, + struct dentry *wh_dentry, struct au_whtmp_rmdir *args) +{ + int wkq_err; + struct super_block *sb; + + IMustLock(dir); + + /* all post-process will be done in do_rmdir_whtmp(). */ + sb = dir->i_sb; + args->dir = au_igrab(dir); + args->br = au_sbr(sb, bindex); + atomic_inc(&args->br->br_count); + args->wh_dentry = dget(wh_dentry); + wkq_err = au_wkq_nowait(call_rmdir_whtmp, args, sb, /*flags*/0); + if (unlikely(wkq_err)) { + pr_warning("rmdir error %.*s (%d), ignored\n", + AuDLNPair(wh_dentry), wkq_err); + au_whtmp_rmdir_free(args); + } +} diff --git a/ubuntu/aufs/whout.h b/ubuntu/aufs/whout.h new file mode 100644 index 000000000000..f7c45f0998fa --- /dev/null +++ b/ubuntu/aufs/whout.h @@ -0,0 +1,88 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * whiteout for logical deletion and opaque directory + */ + +#ifndef __AUFS_WHOUT_H__ +#define __AUFS_WHOUT_H__ + +#ifdef __KERNEL__ + +#include "dir.h" + +/* whout.c */ +int au_wh_name_alloc(struct qstr *wh, const struct qstr *name); +struct au_branch; +int au_wh_test(struct dentry *h_parent, struct qstr *wh_name, + struct au_branch *br, int try_sio); +int au_diropq_test(struct dentry *h_dentry, struct au_branch *br); +struct dentry *au_whtmp_lkup(struct dentry *h_parent, struct au_branch *br, + struct qstr *prefix); +int au_whtmp_ren(struct dentry *h_dentry, struct au_branch *br); +int au_wh_unlink_dentry(struct inode *h_dir, struct path *h_path, + struct dentry *dentry); +int au_wh_init(struct dentry *h_parent, struct au_branch *br, + struct super_block *sb); + +/* diropq flags */ +#define AuDiropq_CREATE 1 +#define au_ftest_diropq(flags, name) ((flags) & AuDiropq_##name) +#define au_fset_diropq(flags, name) \ + do { (flags) |= AuDiropq_##name; } while (0) +#define au_fclr_diropq(flags, name) \ + do { (flags) &= ~AuDiropq_##name; } while (0) + +struct dentry *au_diropq_sio(struct dentry *dentry, aufs_bindex_t bindex, + unsigned int flags); +struct dentry *au_wh_lkup(struct dentry *h_parent, struct qstr *base_name, + struct au_branch *br); +struct dentry *au_wh_create(struct dentry *dentry, aufs_bindex_t bindex, + struct dentry *h_parent); + +/* real rmdir for the whiteout-ed dir */ +struct au_whtmp_rmdir { + struct inode *dir; + struct au_branch *br; + struct dentry *wh_dentry; + struct au_nhash whlist; +}; + +struct au_whtmp_rmdir *au_whtmp_rmdir_alloc(struct super_block *sb, gfp_t gfp); +void au_whtmp_rmdir_free(struct au_whtmp_rmdir *whtmp); +int au_whtmp_rmdir(struct inode *dir, aufs_bindex_t bindex, + struct dentry *wh_dentry, struct au_nhash *whlist); +void au_whtmp_kick_rmdir(struct inode *dir, aufs_bindex_t bindex, + struct dentry *wh_dentry, struct au_whtmp_rmdir *args); + +/* ---------------------------------------------------------------------- */ + +static inline struct dentry *au_diropq_create(struct dentry *dentry, + aufs_bindex_t bindex) +{ + return au_diropq_sio(dentry, bindex, AuDiropq_CREATE); +} + +static inline int au_diropq_remove(struct dentry *dentry, aufs_bindex_t bindex) +{ + return PTR_ERR(au_diropq_sio(dentry, bindex, !AuDiropq_CREATE)); +} + +#endif /* __KERNEL__ */ +#endif /* __AUFS_WHOUT_H__ */ diff --git a/ubuntu/aufs/wkq.c b/ubuntu/aufs/wkq.c new file mode 100644 index 000000000000..91c739f476f3 --- /dev/null +++ b/ubuntu/aufs/wkq.c @@ -0,0 +1,214 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * workqueue for asynchronous/super-io operations + * todo: try new dredential scheme + */ + +#include <linux/module.h> +#include "aufs.h" + +/* internal workqueue named AUFS_WKQ_NAME */ + +static struct workqueue_struct *au_wkq; + +struct au_wkinfo { + struct work_struct wk; + struct kobject *kobj; + + unsigned int flags; /* see wkq.h */ + + au_wkq_func_t func; + void *args; + + struct completion *comp; +}; + +/* ---------------------------------------------------------------------- */ + +static void wkq_func(struct work_struct *wk) +{ + struct au_wkinfo *wkinfo = container_of(wk, struct au_wkinfo, wk); + + AuDebugOn(current_fsuid()); + AuDebugOn(rlimit(RLIMIT_FSIZE) != RLIM_INFINITY); + + wkinfo->func(wkinfo->args); + if (au_ftest_wkq(wkinfo->flags, WAIT)) + complete(wkinfo->comp); + else { + kobject_put(wkinfo->kobj); + module_put(THIS_MODULE); /* todo: ?? */ + kfree(wkinfo); + } +} + +/* + * Since struct completion is large, try allocating it dynamically. + */ +#if defined(CONFIG_4KSTACKS) || defined(AuTest4KSTACKS) +#define AuWkqCompDeclare(name) struct completion *comp = NULL + +static int au_wkq_comp_alloc(struct au_wkinfo *wkinfo, struct completion **comp) +{ + *comp = kmalloc(sizeof(**comp), GFP_NOFS); + if (*comp) { + init_completion(*comp); + wkinfo->comp = *comp; + return 0; + } + return -ENOMEM; +} + +static void au_wkq_comp_free(struct completion *comp) +{ + kfree(comp); +} + +#else + +/* no braces */ +#define AuWkqCompDeclare(name) \ + DECLARE_COMPLETION_ONSTACK(_ ## name); \ + struct completion *comp = &_ ## name + +static int au_wkq_comp_alloc(struct au_wkinfo *wkinfo, struct completion **comp) +{ + wkinfo->comp = *comp; + return 0; +} + +static void au_wkq_comp_free(struct completion *comp __maybe_unused) +{ + /* empty */ +} +#endif /* 4KSTACKS */ + +static void au_wkq_run(struct au_wkinfo *wkinfo) +{ + if (au_ftest_wkq(wkinfo->flags, NEST)) { + if (au_wkq_test()) { + AuWarn1("wkq from wkq, due to a dead dir by UDBA?\n"); + AuDebugOn(au_ftest_wkq(wkinfo->flags, WAIT)); + } + } else + au_dbg_verify_kthread(); + + if (au_ftest_wkq(wkinfo->flags, WAIT)) { + INIT_WORK_ONSTACK(&wkinfo->wk, wkq_func); + queue_work(au_wkq, &wkinfo->wk); + } else { + INIT_WORK(&wkinfo->wk, wkq_func); + schedule_work(&wkinfo->wk); + } +} + +/* + * Be careful. It is easy to make deadlock happen. + * processA: lock, wkq and wait + * processB: wkq and wait, lock in wkq + * --> deadlock + */ +int au_wkq_do_wait(unsigned int flags, au_wkq_func_t func, void *args) +{ + int err; + AuWkqCompDeclare(comp); + struct au_wkinfo wkinfo = { + .flags = flags, + .func = func, + .args = args + }; + + err = au_wkq_comp_alloc(&wkinfo, &comp); + if (!err) { + au_wkq_run(&wkinfo); + /* no timeout, no interrupt */ + wait_for_completion(wkinfo.comp); + au_wkq_comp_free(comp); + destroy_work_on_stack(&wkinfo.wk); + } + + return err; + +} + +/* + * Note: dget/dput() in func for aufs dentries are not supported. It will be a + * problem in a concurrent umounting. + */ +int au_wkq_nowait(au_wkq_func_t func, void *args, struct super_block *sb, + unsigned int flags) +{ + int err; + struct au_wkinfo *wkinfo; + + atomic_inc(&au_sbi(sb)->si_nowait.nw_len); + + /* + * wkq_func() must free this wkinfo. + * it highly depends upon the implementation of workqueue. + */ + err = 0; + wkinfo = kmalloc(sizeof(*wkinfo), GFP_NOFS); + if (wkinfo) { + wkinfo->kobj = &au_sbi(sb)->si_kobj; + wkinfo->flags = flags & ~AuWkq_WAIT; + wkinfo->func = func; + wkinfo->args = args; + wkinfo->comp = NULL; + kobject_get(wkinfo->kobj); + __module_get(THIS_MODULE); /* todo: ?? */ + + au_wkq_run(wkinfo); + } else { + err = -ENOMEM; + au_nwt_done(&au_sbi(sb)->si_nowait); + } + + return err; +} + +/* ---------------------------------------------------------------------- */ + +void au_nwt_init(struct au_nowait_tasks *nwt) +{ + atomic_set(&nwt->nw_len, 0); + /* smp_mb(); */ /* atomic_set */ + init_waitqueue_head(&nwt->nw_wq); +} + +void au_wkq_fin(void) +{ + destroy_workqueue(au_wkq); +} + +int __init au_wkq_init(void) +{ + int err; + + err = 0; + BUILD_BUG_ON(!WQ_RESCUER); + au_wkq = alloc_workqueue(AUFS_WKQ_NAME, !WQ_RESCUER, WQ_DFL_ACTIVE); + if (IS_ERR(au_wkq)) + err = PTR_ERR(au_wkq); + else if (!au_wkq) + err = -ENOMEM; + + return err; +} diff --git a/ubuntu/aufs/wkq.h b/ubuntu/aufs/wkq.h new file mode 100644 index 000000000000..0e44f73c2a06 --- /dev/null +++ b/ubuntu/aufs/wkq.h @@ -0,0 +1,92 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * workqueue for asynchronous/super-io operations + * todo: try new credentials management scheme + */ + +#ifndef __AUFS_WKQ_H__ +#define __AUFS_WKQ_H__ + +#ifdef __KERNEL__ + +struct super_block; + +/* ---------------------------------------------------------------------- */ + +/* + * in the next operation, wait for the 'nowait' tasks in system-wide workqueue + */ +struct au_nowait_tasks { + atomic_t nw_len; + wait_queue_head_t nw_wq; +}; + +/* ---------------------------------------------------------------------- */ + +typedef void (*au_wkq_func_t)(void *args); + +/* wkq flags */ +#define AuWkq_WAIT 1 +#define AuWkq_NEST (1 << 1) +#define au_ftest_wkq(flags, name) ((flags) & AuWkq_##name) +#define au_fset_wkq(flags, name) \ + do { (flags) |= AuWkq_##name; } while (0) +#define au_fclr_wkq(flags, name) \ + do { (flags) &= ~AuWkq_##name; } while (0) + +#ifndef CONFIG_AUFS_HNOTIFY +#undef AuWkq_NEST +#define AuWkq_NEST 0 +#endif + +/* wkq.c */ +int au_wkq_do_wait(unsigned int flags, au_wkq_func_t func, void *args); +int au_wkq_nowait(au_wkq_func_t func, void *args, struct super_block *sb, + unsigned int flags); +void au_nwt_init(struct au_nowait_tasks *nwt); +int __init au_wkq_init(void); +void au_wkq_fin(void); + +/* ---------------------------------------------------------------------- */ + +static inline int au_wkq_test(void) +{ + return current->flags & PF_WQ_WORKER; +} + +static inline int au_wkq_wait(au_wkq_func_t func, void *args) +{ + return au_wkq_do_wait(AuWkq_WAIT, func, args); +} + +static inline void au_nwt_done(struct au_nowait_tasks *nwt) +{ + if (atomic_dec_and_test(&nwt->nw_len)) + wake_up_all(&nwt->nw_wq); +} + +static inline int au_nwt_flush(struct au_nowait_tasks *nwt) +{ + wait_event(nwt->nw_wq, !atomic_read(&nwt->nw_len)); + return 0; +} + +#endif /* __KERNEL__ */ +#endif /* __AUFS_WKQ_H__ */ diff --git a/ubuntu/aufs/xino.c b/ubuntu/aufs/xino.c new file mode 100644 index 000000000000..2285299293ef --- /dev/null +++ b/ubuntu/aufs/xino.c @@ -0,0 +1,1264 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +/* + * external inode number translation table and bitmap + */ + +#include <linux/seq_file.h> +#include "aufs.h" + +/* todo: unnecessary to support mmap_sem since kernel-space? */ +ssize_t xino_fread(au_readf_t func, struct file *file, void *kbuf, size_t size, + loff_t *pos) +{ + ssize_t err; + mm_segment_t oldfs; + union { + void *k; + char __user *u; + } buf; + + buf.k = kbuf; + oldfs = get_fs(); + set_fs(KERNEL_DS); + do { + /* todo: signal_pending? */ + err = func(file, buf.u, size, pos); + } while (err == -EAGAIN || err == -EINTR); + set_fs(oldfs); + +#if 0 /* reserved for future use */ + if (err > 0) + fsnotify_access(file->f_dentry); +#endif + + return err; +} + +/* ---------------------------------------------------------------------- */ + +static ssize_t do_xino_fwrite(au_writef_t func, struct file *file, void *kbuf, + size_t size, loff_t *pos) +{ + ssize_t err; + mm_segment_t oldfs; + union { + void *k; + const char __user *u; + } buf; + + buf.k = kbuf; + oldfs = get_fs(); + set_fs(KERNEL_DS); + do { + /* todo: signal_pending? */ + err = func(file, buf.u, size, pos); + } while (err == -EAGAIN || err == -EINTR); + set_fs(oldfs); + +#if 0 /* reserved for future use */ + if (err > 0) + fsnotify_modify(file->f_dentry); +#endif + + return err; +} + +struct do_xino_fwrite_args { + ssize_t *errp; + au_writef_t func; + struct file *file; + void *buf; + size_t size; + loff_t *pos; +}; + +static void call_do_xino_fwrite(void *args) +{ + struct do_xino_fwrite_args *a = args; + *a->errp = do_xino_fwrite(a->func, a->file, a->buf, a->size, a->pos); +} + +ssize_t xino_fwrite(au_writef_t func, struct file *file, void *buf, size_t size, + loff_t *pos) +{ + ssize_t err; + + /* todo: signal block and no wkq? */ + if (rlimit(RLIMIT_FSIZE) == RLIM_INFINITY) { + lockdep_off(); + err = do_xino_fwrite(func, file, buf, size, pos); + lockdep_on(); + } else { + /* + * it breaks RLIMIT_FSIZE and normal user's limit, + * users should care about quota and real 'filesystem full.' + */ + int wkq_err; + struct do_xino_fwrite_args args = { + .errp = &err, + .func = func, + .file = file, + .buf = buf, + .size = size, + .pos = pos + }; + + wkq_err = au_wkq_wait(call_do_xino_fwrite, &args); + if (unlikely(wkq_err)) + err = wkq_err; + } + + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* + * create a new xinofile at the same place/path as @base_file. + */ +struct file *au_xino_create2(struct file *base_file, struct file *copy_src) +{ + struct file *file; + struct dentry *base, *parent; + struct inode *dir; + struct qstr *name; + struct path path; + int err; + + base = base_file->f_dentry; + parent = base->d_parent; /* dir inode is locked */ + dir = parent->d_inode; + IMustLock(dir); + + file = ERR_PTR(-EINVAL); + name = &base->d_name; + path.dentry = vfsub_lookup_one_len(name->name, parent, name->len); + if (IS_ERR(path.dentry)) { + file = (void *)path.dentry; + pr_err("%.*s lookup err %ld\n", + AuLNPair(name), PTR_ERR(path.dentry)); + goto out; + } + + /* no need to mnt_want_write() since we call dentry_open() later */ + err = vfs_create(dir, path.dentry, S_IRUGO | S_IWUGO, NULL); + if (unlikely(err)) { + file = ERR_PTR(err); + pr_err("%.*s create err %d\n", AuLNPair(name), err); + goto out_dput; + } + + path.mnt = base_file->f_vfsmnt; + file = vfsub_dentry_open(&path, + O_RDWR | O_CREAT | O_EXCL | O_LARGEFILE + /* | __FMODE_NONOTIFY */); + if (IS_ERR(file)) { + pr_err("%.*s open err %ld\n", AuLNPair(name), PTR_ERR(file)); + goto out_dput; + } + + err = vfsub_unlink(dir, &file->f_path, /*force*/0); + if (unlikely(err)) { + pr_err("%.*s unlink err %d\n", AuLNPair(name), err); + goto out_fput; + } + + if (copy_src) { + /* no one can touch copy_src xino */ + err = au_copy_file(file, copy_src, + i_size_read(copy_src->f_dentry->d_inode)); + if (unlikely(err)) { + pr_err("%.*s copy err %d\n", AuLNPair(name), err); + goto out_fput; + } + } + goto out_dput; /* success */ + +out_fput: + fput(file); + file = ERR_PTR(err); +out_dput: + dput(path.dentry); +out: + return file; +} + +struct au_xino_lock_dir { + struct au_hinode *hdir; + struct dentry *parent; + struct mutex *mtx; +}; + +static void au_xino_lock_dir(struct super_block *sb, struct file *xino, + struct au_xino_lock_dir *ldir) +{ + aufs_bindex_t brid, bindex; + + ldir->hdir = NULL; + bindex = -1; + brid = au_xino_brid(sb); + if (brid >= 0) + bindex = au_br_index(sb, brid); + if (bindex >= 0) { + ldir->hdir = au_hi(sb->s_root->d_inode, bindex); + au_hn_imtx_lock_nested(ldir->hdir, AuLsc_I_PARENT); + } else { + ldir->parent = dget_parent(xino->f_dentry); + ldir->mtx = &ldir->parent->d_inode->i_mutex; + mutex_lock_nested(ldir->mtx, AuLsc_I_PARENT); + } +} + +static void au_xino_unlock_dir(struct au_xino_lock_dir *ldir) +{ + if (ldir->hdir) + au_hn_imtx_unlock(ldir->hdir); + else { + mutex_unlock(ldir->mtx); + dput(ldir->parent); + } +} + +/* ---------------------------------------------------------------------- */ + +/* trucate xino files asynchronously */ + +int au_xino_trunc(struct super_block *sb, aufs_bindex_t bindex) +{ + int err; + aufs_bindex_t bi, bend; + struct au_branch *br; + struct file *new_xino, *file; + struct super_block *h_sb; + struct au_xino_lock_dir ldir; + + err = -EINVAL; + bend = au_sbend(sb); + if (unlikely(bindex < 0 || bend < bindex)) + goto out; + br = au_sbr(sb, bindex); + file = br->br_xino.xi_file; + if (!file) + goto out; + + au_xino_lock_dir(sb, file, &ldir); + /* mnt_want_write() is unnecessary here */ + new_xino = au_xino_create2(file, file); + au_xino_unlock_dir(&ldir); + err = PTR_ERR(new_xino); + if (IS_ERR(new_xino)) + goto out; + err = 0; + fput(file); + br->br_xino.xi_file = new_xino; + + h_sb = br->br_mnt->mnt_sb; + for (bi = 0; bi <= bend; bi++) { + if (unlikely(bi == bindex)) + continue; + br = au_sbr(sb, bi); + if (br->br_mnt->mnt_sb != h_sb) + continue; + + fput(br->br_xino.xi_file); + br->br_xino.xi_file = new_xino; + get_file(new_xino); + } + +out: + return err; +} + +struct xino_do_trunc_args { + struct super_block *sb; + struct au_branch *br; +}; + +static void xino_do_trunc(void *_args) +{ + struct xino_do_trunc_args *args = _args; + struct super_block *sb; + struct au_branch *br; + struct inode *dir; + int err; + aufs_bindex_t bindex; + + err = 0; + sb = args->sb; + dir = sb->s_root->d_inode; + br = args->br; + + si_noflush_write_lock(sb); + ii_read_lock_parent(dir); + bindex = au_br_index(sb, br->br_id); + err = au_xino_trunc(sb, bindex); + if (!err + && br->br_xino.xi_file->f_dentry->d_inode->i_blocks + >= br->br_xino_upper) + br->br_xino_upper += AUFS_XINO_TRUNC_STEP; + + ii_read_unlock(dir); + if (unlikely(err)) + pr_warning("err b%d, (%d)\n", bindex, err); + atomic_dec(&br->br_xino_running); + atomic_dec(&br->br_count); + si_write_unlock(sb); + au_nwt_done(&au_sbi(sb)->si_nowait); + kfree(args); +} + +static void xino_try_trunc(struct super_block *sb, struct au_branch *br) +{ + struct xino_do_trunc_args *args; + int wkq_err; + + if (br->br_xino.xi_file->f_dentry->d_inode->i_blocks + < br->br_xino_upper) + return; + + if (atomic_inc_return(&br->br_xino_running) > 1) + goto out; + + /* lock and kfree() will be called in trunc_xino() */ + args = kmalloc(sizeof(*args), GFP_NOFS); + if (unlikely(!args)) { + AuErr1("no memory\n"); + goto out_args; + } + + atomic_inc(&br->br_count); + args->sb = sb; + args->br = br; + wkq_err = au_wkq_nowait(xino_do_trunc, args, sb, /*flags*/0); + if (!wkq_err) + return; /* success */ + + pr_err("wkq %d\n", wkq_err); + atomic_dec(&br->br_count); + +out_args: + kfree(args); +out: + atomic_dec(&br->br_xino_running); +} + +/* ---------------------------------------------------------------------- */ + +static int au_xino_do_write(au_writef_t write, struct file *file, + ino_t h_ino, ino_t ino) +{ + loff_t pos; + ssize_t sz; + + pos = h_ino; + if (unlikely(au_loff_max / sizeof(ino) - 1 < pos)) { + AuIOErr1("too large hi%lu\n", (unsigned long)h_ino); + return -EFBIG; + } + pos *= sizeof(ino); + sz = xino_fwrite(write, file, &ino, sizeof(ino), &pos); + if (sz == sizeof(ino)) + return 0; /* success */ + + AuIOErr("write failed (%zd)\n", sz); + return -EIO; +} + +/* + * write @ino to the xinofile for the specified branch{@sb, @bindex} + * at the position of @h_ino. + * even if @ino is zero, it is written to the xinofile and means no entry. + * if the size of the xino file on a specific filesystem exceeds the watermark, + * try truncating it. + */ +int au_xino_write(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, + ino_t ino) +{ + int err; + unsigned int mnt_flags; + struct au_branch *br; + + BUILD_BUG_ON(sizeof(long long) != sizeof(au_loff_max) + || ((loff_t)-1) > 0); + SiMustAnyLock(sb); + + mnt_flags = au_mntflags(sb); + if (!au_opt_test(mnt_flags, XINO)) + return 0; + + br = au_sbr(sb, bindex); + err = au_xino_do_write(au_sbi(sb)->si_xwrite, br->br_xino.xi_file, + h_ino, ino); + if (!err) { + if (au_opt_test(mnt_flags, TRUNC_XINO) + && au_test_fs_trunc_xino(br->br_mnt->mnt_sb)) + xino_try_trunc(sb, br); + return 0; /* success */ + } + + AuIOErr("write failed (%d)\n", err); + return -EIO; +} + +/* ---------------------------------------------------------------------- */ + +/* aufs inode number bitmap */ + +static const int page_bits = (int)PAGE_SIZE * BITS_PER_BYTE; +static ino_t xib_calc_ino(unsigned long pindex, int bit) +{ + ino_t ino; + + AuDebugOn(bit < 0 || page_bits <= bit); + ino = AUFS_FIRST_INO + pindex * page_bits + bit; + return ino; +} + +static void xib_calc_bit(ino_t ino, unsigned long *pindex, int *bit) +{ + AuDebugOn(ino < AUFS_FIRST_INO); + ino -= AUFS_FIRST_INO; + *pindex = ino / page_bits; + *bit = ino % page_bits; +} + +static int xib_pindex(struct super_block *sb, unsigned long pindex) +{ + int err; + loff_t pos; + ssize_t sz; + struct au_sbinfo *sbinfo; + struct file *xib; + unsigned long *p; + + sbinfo = au_sbi(sb); + MtxMustLock(&sbinfo->si_xib_mtx); + AuDebugOn(pindex > ULONG_MAX / PAGE_SIZE + || !au_opt_test(sbinfo->si_mntflags, XINO)); + + if (pindex == sbinfo->si_xib_last_pindex) + return 0; + + xib = sbinfo->si_xib; + p = sbinfo->si_xib_buf; + pos = sbinfo->si_xib_last_pindex; + pos *= PAGE_SIZE; + sz = xino_fwrite(sbinfo->si_xwrite, xib, p, PAGE_SIZE, &pos); + if (unlikely(sz != PAGE_SIZE)) + goto out; + + pos = pindex; + pos *= PAGE_SIZE; + if (i_size_read(xib->f_dentry->d_inode) >= pos + PAGE_SIZE) + sz = xino_fread(sbinfo->si_xread, xib, p, PAGE_SIZE, &pos); + else { + memset(p, 0, PAGE_SIZE); + sz = xino_fwrite(sbinfo->si_xwrite, xib, p, PAGE_SIZE, &pos); + } + if (sz == PAGE_SIZE) { + sbinfo->si_xib_last_pindex = pindex; + return 0; /* success */ + } + +out: + AuIOErr1("write failed (%zd)\n", sz); + err = sz; + if (sz >= 0) + err = -EIO; + return err; +} + +/* ---------------------------------------------------------------------- */ + +static void au_xib_clear_bit(struct inode *inode) +{ + int err, bit; + unsigned long pindex; + struct super_block *sb; + struct au_sbinfo *sbinfo; + + AuDebugOn(inode->i_nlink); + + sb = inode->i_sb; + xib_calc_bit(inode->i_ino, &pindex, &bit); + AuDebugOn(page_bits <= bit); + sbinfo = au_sbi(sb); + mutex_lock(&sbinfo->si_xib_mtx); + err = xib_pindex(sb, pindex); + if (!err) { + clear_bit(bit, sbinfo->si_xib_buf); + sbinfo->si_xib_next_bit = bit; + } + mutex_unlock(&sbinfo->si_xib_mtx); +} + +/* for s_op->delete_inode() */ +void au_xino_delete_inode(struct inode *inode, const int unlinked) +{ + int err; + unsigned int mnt_flags; + aufs_bindex_t bindex, bend, bi; + unsigned char try_trunc; + struct au_iinfo *iinfo; + struct super_block *sb; + struct au_hinode *hi; + struct inode *h_inode; + struct au_branch *br; + au_writef_t xwrite; + + sb = inode->i_sb; + mnt_flags = au_mntflags(sb); + if (!au_opt_test(mnt_flags, XINO) + || inode->i_ino == AUFS_ROOT_INO) + return; + + if (unlinked) { + au_xigen_inc(inode); + au_xib_clear_bit(inode); + } + + iinfo = au_ii(inode); + if (!iinfo) + return; + + bindex = iinfo->ii_bstart; + if (bindex < 0) + return; + + xwrite = au_sbi(sb)->si_xwrite; + try_trunc = !!au_opt_test(mnt_flags, TRUNC_XINO); + hi = iinfo->ii_hinode + bindex; + bend = iinfo->ii_bend; + for (; bindex <= bend; bindex++, hi++) { + h_inode = hi->hi_inode; + if (!h_inode + || (!unlinked && h_inode->i_nlink)) + continue; + + /* inode may not be revalidated */ + bi = au_br_index(sb, hi->hi_id); + if (bi < 0) + continue; + + br = au_sbr(sb, bi); + err = au_xino_do_write(xwrite, br->br_xino.xi_file, + h_inode->i_ino, /*ino*/0); + if (!err && try_trunc + && au_test_fs_trunc_xino(br->br_mnt->mnt_sb)) + xino_try_trunc(sb, br); + } +} + +/* get an unused inode number from bitmap */ +ino_t au_xino_new_ino(struct super_block *sb) +{ + ino_t ino; + unsigned long *p, pindex, ul, pend; + struct au_sbinfo *sbinfo; + struct file *file; + int free_bit, err; + + if (!au_opt_test(au_mntflags(sb), XINO)) + return iunique(sb, AUFS_FIRST_INO); + + sbinfo = au_sbi(sb); + mutex_lock(&sbinfo->si_xib_mtx); + p = sbinfo->si_xib_buf; + free_bit = sbinfo->si_xib_next_bit; + if (free_bit < page_bits && !test_bit(free_bit, p)) + goto out; /* success */ + free_bit = find_first_zero_bit(p, page_bits); + if (free_bit < page_bits) + goto out; /* success */ + + pindex = sbinfo->si_xib_last_pindex; + for (ul = pindex - 1; ul < ULONG_MAX; ul--) { + err = xib_pindex(sb, ul); + if (unlikely(err)) + goto out_err; + free_bit = find_first_zero_bit(p, page_bits); + if (free_bit < page_bits) + goto out; /* success */ + } + + file = sbinfo->si_xib; + pend = i_size_read(file->f_dentry->d_inode) / PAGE_SIZE; + for (ul = pindex + 1; ul <= pend; ul++) { + err = xib_pindex(sb, ul); + if (unlikely(err)) + goto out_err; + free_bit = find_first_zero_bit(p, page_bits); + if (free_bit < page_bits) + goto out; /* success */ + } + BUG(); + +out: + set_bit(free_bit, p); + sbinfo->si_xib_next_bit = free_bit + 1; + pindex = sbinfo->si_xib_last_pindex; + mutex_unlock(&sbinfo->si_xib_mtx); + ino = xib_calc_ino(pindex, free_bit); + AuDbg("i%lu\n", (unsigned long)ino); + return ino; +out_err: + mutex_unlock(&sbinfo->si_xib_mtx); + AuDbg("i0\n"); + return 0; +} + +/* + * read @ino from xinofile for the specified branch{@sb, @bindex} + * at the position of @h_ino. + * if @ino does not exist and @do_new is true, get new one. + */ +int au_xino_read(struct super_block *sb, aufs_bindex_t bindex, ino_t h_ino, + ino_t *ino) +{ + int err; + ssize_t sz; + loff_t pos; + struct file *file; + struct au_sbinfo *sbinfo; + + *ino = 0; + if (!au_opt_test(au_mntflags(sb), XINO)) + return 0; /* no xino */ + + err = 0; + sbinfo = au_sbi(sb); + pos = h_ino; + if (unlikely(au_loff_max / sizeof(*ino) - 1 < pos)) { + AuIOErr1("too large hi%lu\n", (unsigned long)h_ino); + return -EFBIG; + } + pos *= sizeof(*ino); + + file = au_sbr(sb, bindex)->br_xino.xi_file; + if (i_size_read(file->f_dentry->d_inode) < pos + sizeof(*ino)) + return 0; /* no ino */ + + sz = xino_fread(sbinfo->si_xread, file, ino, sizeof(*ino), &pos); + if (sz == sizeof(*ino)) + return 0; /* success */ + + err = sz; + if (unlikely(sz >= 0)) { + err = -EIO; + AuIOErr("xino read error (%zd)\n", sz); + } + + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* create and set a new xino file */ + +struct file *au_xino_create(struct super_block *sb, char *fname, int silent) +{ + struct file *file; + struct dentry *h_parent, *d; + struct inode *h_dir; + int err; + + /* + * at mount-time, and the xino file is the default path, + * hnotify is disabled so we have no notify events to ignore. + * when a user specified the xino, we cannot get au_hdir to be ignored. + */ + file = vfsub_filp_open(fname, O_RDWR | O_CREAT | O_EXCL | O_LARGEFILE + /* | __FMODE_NONOTIFY */, + S_IRUGO | S_IWUGO); + if (IS_ERR(file)) { + if (!silent) + pr_err("open %s(%ld)\n", fname, PTR_ERR(file)); + return file; + } + + /* keep file count */ + h_parent = dget_parent(file->f_dentry); + h_dir = h_parent->d_inode; + mutex_lock_nested(&h_dir->i_mutex, AuLsc_I_PARENT); + /* mnt_want_write() is unnecessary here */ + err = vfsub_unlink(h_dir, &file->f_path, /*force*/0); + mutex_unlock(&h_dir->i_mutex); + dput(h_parent); + if (unlikely(err)) { + if (!silent) + pr_err("unlink %s(%d)\n", fname, err); + goto out; + } + + err = -EINVAL; + d = file->f_dentry; + if (unlikely(sb == d->d_sb)) { + if (!silent) + pr_err("%s must be outside\n", fname); + goto out; + } + if (unlikely(au_test_fs_bad_xino(d->d_sb))) { + if (!silent) + pr_err("xino doesn't support %s(%s)\n", + fname, au_sbtype(d->d_sb)); + goto out; + } + return file; /* success */ + +out: + fput(file); + file = ERR_PTR(err); + return file; +} + +/* + * find another branch who is on the same filesystem of the specified + * branch{@btgt}. search until @bend. + */ +static int is_sb_shared(struct super_block *sb, aufs_bindex_t btgt, + aufs_bindex_t bend) +{ + aufs_bindex_t bindex; + struct super_block *tgt_sb = au_sbr_sb(sb, btgt); + + for (bindex = 0; bindex < btgt; bindex++) + if (unlikely(tgt_sb == au_sbr_sb(sb, bindex))) + return bindex; + for (bindex++; bindex <= bend; bindex++) + if (unlikely(tgt_sb == au_sbr_sb(sb, bindex))) + return bindex; + return -1; +} + +/* ---------------------------------------------------------------------- */ + +/* + * initialize the xinofile for the specified branch @br + * at the place/path where @base_file indicates. + * test whether another branch is on the same filesystem or not, + * if @do_test is true. + */ +int au_xino_br(struct super_block *sb, struct au_branch *br, ino_t h_ino, + struct file *base_file, int do_test) +{ + int err; + ino_t ino; + aufs_bindex_t bend, bindex; + struct au_branch *shared_br, *b; + struct file *file; + struct super_block *tgt_sb; + + shared_br = NULL; + bend = au_sbend(sb); + if (do_test) { + tgt_sb = br->br_mnt->mnt_sb; + for (bindex = 0; bindex <= bend; bindex++) { + b = au_sbr(sb, bindex); + if (tgt_sb == b->br_mnt->mnt_sb) { + shared_br = b; + break; + } + } + } + + if (!shared_br || !shared_br->br_xino.xi_file) { + struct au_xino_lock_dir ldir; + + au_xino_lock_dir(sb, base_file, &ldir); + /* mnt_want_write() is unnecessary here */ + file = au_xino_create2(base_file, NULL); + au_xino_unlock_dir(&ldir); + err = PTR_ERR(file); + if (IS_ERR(file)) + goto out; + br->br_xino.xi_file = file; + } else { + br->br_xino.xi_file = shared_br->br_xino.xi_file; + get_file(br->br_xino.xi_file); + } + + ino = AUFS_ROOT_INO; + err = au_xino_do_write(au_sbi(sb)->si_xwrite, br->br_xino.xi_file, + h_ino, ino); + if (unlikely(err)) { + fput(br->br_xino.xi_file); + br->br_xino.xi_file = NULL; + } + +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* trucate a xino bitmap file */ + +/* todo: slow */ +static int do_xib_restore(struct super_block *sb, struct file *file, void *page) +{ + int err, bit; + ssize_t sz; + unsigned long pindex; + loff_t pos, pend; + struct au_sbinfo *sbinfo; + au_readf_t func; + ino_t *ino; + unsigned long *p; + + err = 0; + sbinfo = au_sbi(sb); + MtxMustLock(&sbinfo->si_xib_mtx); + p = sbinfo->si_xib_buf; + func = sbinfo->si_xread; + pend = i_size_read(file->f_dentry->d_inode); + pos = 0; + while (pos < pend) { + sz = xino_fread(func, file, page, PAGE_SIZE, &pos); + err = sz; + if (unlikely(sz <= 0)) + goto out; + + err = 0; + for (ino = page; sz > 0; ino++, sz -= sizeof(ino)) { + if (unlikely(*ino < AUFS_FIRST_INO)) + continue; + + xib_calc_bit(*ino, &pindex, &bit); + AuDebugOn(page_bits <= bit); + err = xib_pindex(sb, pindex); + if (!err) + set_bit(bit, p); + else + goto out; + } + } + +out: + return err; +} + +static int xib_restore(struct super_block *sb) +{ + int err; + aufs_bindex_t bindex, bend; + void *page; + + err = -ENOMEM; + page = (void *)__get_free_page(GFP_NOFS); + if (unlikely(!page)) + goto out; + + err = 0; + bend = au_sbend(sb); + for (bindex = 0; !err && bindex <= bend; bindex++) + if (!bindex || is_sb_shared(sb, bindex, bindex - 1) < 0) + err = do_xib_restore + (sb, au_sbr(sb, bindex)->br_xino.xi_file, page); + else + AuDbg("b%d\n", bindex); + free_page((unsigned long)page); + +out: + return err; +} + +int au_xib_trunc(struct super_block *sb) +{ + int err; + ssize_t sz; + loff_t pos; + struct au_xino_lock_dir ldir; + struct au_sbinfo *sbinfo; + unsigned long *p; + struct file *file; + + SiMustWriteLock(sb); + + err = 0; + sbinfo = au_sbi(sb); + if (!au_opt_test(sbinfo->si_mntflags, XINO)) + goto out; + + file = sbinfo->si_xib; + if (i_size_read(file->f_dentry->d_inode) <= PAGE_SIZE) + goto out; + + au_xino_lock_dir(sb, file, &ldir); + /* mnt_want_write() is unnecessary here */ + file = au_xino_create2(sbinfo->si_xib, NULL); + au_xino_unlock_dir(&ldir); + err = PTR_ERR(file); + if (IS_ERR(file)) + goto out; + fput(sbinfo->si_xib); + sbinfo->si_xib = file; + + p = sbinfo->si_xib_buf; + memset(p, 0, PAGE_SIZE); + pos = 0; + sz = xino_fwrite(sbinfo->si_xwrite, sbinfo->si_xib, p, PAGE_SIZE, &pos); + if (unlikely(sz != PAGE_SIZE)) { + err = sz; + AuIOErr("err %d\n", err); + if (sz >= 0) + err = -EIO; + goto out; + } + + mutex_lock(&sbinfo->si_xib_mtx); + /* mnt_want_write() is unnecessary here */ + err = xib_restore(sb); + mutex_unlock(&sbinfo->si_xib_mtx); + +out: + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* + * xino mount option handlers + */ +static au_readf_t find_readf(struct file *h_file) +{ + const struct file_operations *fop = h_file->f_op; + + if (fop) { + if (fop->read) + return fop->read; + if (fop->aio_read) + return do_sync_read; + } + return ERR_PTR(-ENOSYS); +} + +static au_writef_t find_writef(struct file *h_file) +{ + const struct file_operations *fop = h_file->f_op; + + if (fop) { + if (fop->write) + return fop->write; + if (fop->aio_write) + return do_sync_write; + } + return ERR_PTR(-ENOSYS); +} + +/* xino bitmap */ +static void xino_clear_xib(struct super_block *sb) +{ + struct au_sbinfo *sbinfo; + + SiMustWriteLock(sb); + + sbinfo = au_sbi(sb); + sbinfo->si_xread = NULL; + sbinfo->si_xwrite = NULL; + if (sbinfo->si_xib) + fput(sbinfo->si_xib); + sbinfo->si_xib = NULL; + free_page((unsigned long)sbinfo->si_xib_buf); + sbinfo->si_xib_buf = NULL; +} + +static int au_xino_set_xib(struct super_block *sb, struct file *base) +{ + int err; + loff_t pos; + struct au_sbinfo *sbinfo; + struct file *file; + + SiMustWriteLock(sb); + + sbinfo = au_sbi(sb); + file = au_xino_create2(base, sbinfo->si_xib); + err = PTR_ERR(file); + if (IS_ERR(file)) + goto out; + if (sbinfo->si_xib) + fput(sbinfo->si_xib); + sbinfo->si_xib = file; + sbinfo->si_xread = find_readf(file); + sbinfo->si_xwrite = find_writef(file); + + err = -ENOMEM; + if (!sbinfo->si_xib_buf) + sbinfo->si_xib_buf = (void *)get_zeroed_page(GFP_NOFS); + if (unlikely(!sbinfo->si_xib_buf)) + goto out_unset; + + sbinfo->si_xib_last_pindex = 0; + sbinfo->si_xib_next_bit = 0; + if (i_size_read(file->f_dentry->d_inode) < PAGE_SIZE) { + pos = 0; + err = xino_fwrite(sbinfo->si_xwrite, file, sbinfo->si_xib_buf, + PAGE_SIZE, &pos); + if (unlikely(err != PAGE_SIZE)) + goto out_free; + } + err = 0; + goto out; /* success */ + +out_free: + free_page((unsigned long)sbinfo->si_xib_buf); + sbinfo->si_xib_buf = NULL; + if (err >= 0) + err = -EIO; +out_unset: + fput(sbinfo->si_xib); + sbinfo->si_xib = NULL; + sbinfo->si_xread = NULL; + sbinfo->si_xwrite = NULL; +out: + return err; +} + +/* xino for each branch */ +static void xino_clear_br(struct super_block *sb) +{ + aufs_bindex_t bindex, bend; + struct au_branch *br; + + bend = au_sbend(sb); + for (bindex = 0; bindex <= bend; bindex++) { + br = au_sbr(sb, bindex); + if (!br || !br->br_xino.xi_file) + continue; + + fput(br->br_xino.xi_file); + br->br_xino.xi_file = NULL; + } +} + +static int au_xino_set_br(struct super_block *sb, struct file *base) +{ + int err; + ino_t ino; + aufs_bindex_t bindex, bend, bshared; + struct { + struct file *old, *new; + } *fpair, *p; + struct au_branch *br; + struct inode *inode; + au_writef_t writef; + + SiMustWriteLock(sb); + + err = -ENOMEM; + bend = au_sbend(sb); + fpair = kcalloc(bend + 1, sizeof(*fpair), GFP_NOFS); + if (unlikely(!fpair)) + goto out; + + inode = sb->s_root->d_inode; + ino = AUFS_ROOT_INO; + writef = au_sbi(sb)->si_xwrite; + for (bindex = 0, p = fpair; bindex <= bend; bindex++, p++) { + br = au_sbr(sb, bindex); + bshared = is_sb_shared(sb, bindex, bindex - 1); + if (bshared >= 0) { + /* shared xino */ + *p = fpair[bshared]; + get_file(p->new); + } + + if (!p->new) { + /* new xino */ + p->old = br->br_xino.xi_file; + p->new = au_xino_create2(base, br->br_xino.xi_file); + err = PTR_ERR(p->new); + if (IS_ERR(p->new)) { + p->new = NULL; + goto out_pair; + } + } + + err = au_xino_do_write(writef, p->new, + au_h_iptr(inode, bindex)->i_ino, ino); + if (unlikely(err)) + goto out_pair; + } + + for (bindex = 0, p = fpair; bindex <= bend; bindex++, p++) { + br = au_sbr(sb, bindex); + if (br->br_xino.xi_file) + fput(br->br_xino.xi_file); + get_file(p->new); + br->br_xino.xi_file = p->new; + } + +out_pair: + for (bindex = 0, p = fpair; bindex <= bend; bindex++, p++) + if (p->new) + fput(p->new); + else + break; + kfree(fpair); +out: + return err; +} + +void au_xino_clr(struct super_block *sb) +{ + struct au_sbinfo *sbinfo; + + au_xigen_clr(sb); + xino_clear_xib(sb); + xino_clear_br(sb); + sbinfo = au_sbi(sb); + /* lvalue, do not call au_mntflags() */ + au_opt_clr(sbinfo->si_mntflags, XINO); +} + +int au_xino_set(struct super_block *sb, struct au_opt_xino *xino, int remount) +{ + int err, skip; + struct dentry *parent, *cur_parent; + struct qstr *dname, *cur_name; + struct file *cur_xino; + struct inode *dir; + struct au_sbinfo *sbinfo; + + SiMustWriteLock(sb); + + err = 0; + sbinfo = au_sbi(sb); + parent = dget_parent(xino->file->f_dentry); + if (remount) { + skip = 0; + dname = &xino->file->f_dentry->d_name; + cur_xino = sbinfo->si_xib; + if (cur_xino) { + cur_parent = dget_parent(cur_xino->f_dentry); + cur_name = &cur_xino->f_dentry->d_name; + skip = (cur_parent == parent + && dname->len == cur_name->len + && !memcmp(dname->name, cur_name->name, + dname->len)); + dput(cur_parent); + } + if (skip) + goto out; + } + + au_opt_set(sbinfo->si_mntflags, XINO); + dir = parent->d_inode; + mutex_lock_nested(&dir->i_mutex, AuLsc_I_PARENT); + /* mnt_want_write() is unnecessary here */ + err = au_xino_set_xib(sb, xino->file); + if (!err) + err = au_xigen_set(sb, xino->file); + if (!err) + err = au_xino_set_br(sb, xino->file); + mutex_unlock(&dir->i_mutex); + if (!err) + goto out; /* success */ + + /* reset all */ + AuIOErr("failed creating xino(%d).\n", err); + +out: + dput(parent); + return err; +} + +/* ---------------------------------------------------------------------- */ + +/* + * create a xinofile at the default place/path. + */ +struct file *au_xino_def(struct super_block *sb) +{ + struct file *file; + char *page, *p; + struct au_branch *br; + struct super_block *h_sb; + struct path path; + aufs_bindex_t bend, bindex, bwr; + + br = NULL; + bend = au_sbend(sb); + bwr = -1; + for (bindex = 0; bindex <= bend; bindex++) { + br = au_sbr(sb, bindex); + if (au_br_writable(br->br_perm) + && !au_test_fs_bad_xino(br->br_mnt->mnt_sb)) { + bwr = bindex; + break; + } + } + + if (bwr >= 0) { + file = ERR_PTR(-ENOMEM); + page = __getname_gfp(GFP_NOFS); + if (unlikely(!page)) + goto out; + path.mnt = br->br_mnt; + path.dentry = au_h_dptr(sb->s_root, bwr); + p = d_path(&path, page, PATH_MAX - sizeof(AUFS_XINO_FNAME)); + file = (void *)p; + if (!IS_ERR(p)) { + strcat(p, "/" AUFS_XINO_FNAME); + AuDbg("%s\n", p); + file = au_xino_create(sb, p, /*silent*/0); + if (!IS_ERR(file)) + au_xino_brid_set(sb, br->br_id); + } + __putname(page); + } else { + file = au_xino_create(sb, AUFS_XINO_DEFPATH, /*silent*/0); + if (IS_ERR(file)) + goto out; + h_sb = file->f_dentry->d_sb; + if (unlikely(au_test_fs_bad_xino(h_sb))) { + pr_err("xino doesn't support %s(%s)\n", + AUFS_XINO_DEFPATH, au_sbtype(h_sb)); + fput(file); + file = ERR_PTR(-EINVAL); + } + if (!IS_ERR(file)) + au_xino_brid_set(sb, -1); + } + +out: + return file; +} + +/* ---------------------------------------------------------------------- */ + +int au_xino_path(struct seq_file *seq, struct file *file) +{ + int err; + + err = au_seq_path(seq, &file->f_path); + if (unlikely(err < 0)) + goto out; + + err = 0; +#define Deleted "\\040(deleted)" + seq->count -= sizeof(Deleted) - 1; + AuDebugOn(memcmp(seq->buf + seq->count, Deleted, + sizeof(Deleted) - 1)); +#undef Deleted + +out: + return err; +} diff --git a/ubuntu/dm-raid4-5/BOM b/ubuntu/dm-raid4-5/BOM new file mode 100644 index 000000000000..dd29442289da --- /dev/null +++ b/ubuntu/dm-raid4-5/BOM @@ -0,0 +1,3 @@ +Downloaded from: http://people.redhat.com/~heinzm/sw/dm/dm-raid45/ +Current Version: 2009.04.24 (2.6.30-rc3) +Comments: All of the patches to dmraid1/dm-log, etc are upstream. diff --git a/ubuntu/dm-raid4-5/Kconfig b/ubuntu/dm-raid4-5/Kconfig new file mode 100644 index 000000000000..03fab6438d4d --- /dev/null +++ b/ubuntu/dm-raid4-5/Kconfig @@ -0,0 +1,6 @@ +config DM_RAID45 + tristate "RAID 4/5 target (EXPERIMENTAL)" + depends on BLK_DEV_DM && XOR_BLOCKS && EXPERIMENTAL + default m + ---help--- + A target that supports RAID4 and RAID5 mappings. diff --git a/ubuntu/dm-raid4-5/Makefile b/ubuntu/dm-raid4-5/Makefile new file mode 100644 index 000000000000..9a32796d73f1 --- /dev/null +++ b/ubuntu/dm-raid4-5/Makefile @@ -0,0 +1,4 @@ +EXTRA_CFLAGS += -I$(srctree)/drivers/md + +obj-$(CONFIG_DM_RAID45) := dm-raid45.o +dm-raid45-objs := dm-raid4-5.o dm-memcache.o dm-region-hash.o dm-message.o diff --git a/ubuntu/dm-raid4-5/dm-memcache.c b/ubuntu/dm-raid4-5/dm-memcache.c new file mode 100644 index 000000000000..346abb431b3f --- /dev/null +++ b/ubuntu/dm-raid4-5/dm-memcache.c @@ -0,0 +1,303 @@ +/* + * Copyright (C) 2006-2008 Red Hat, Inc. All rights reserved. + * + * Module Author: Heinz Mauelshagen <heinzm@redhat.com> + * + * Device-mapper memory object handling: + * + * o allocate/free total_pages in a per client page pool. + * + * o allocate/free memory objects with chunks (1..n) of + * pages_per_chunk pages hanging off. + * + * This file is released under the GPL. + */ + +#define DM_MEM_CACHE_VERSION "0.2" + +#include "dm.h" +#include "dm-memcache.h" +#include <linux/dm-io.h> +#include <linux/slab.h> +#include <linux/module.h> + +struct dm_mem_cache_client { + spinlock_t lock; + mempool_t *objs_pool; + struct page_list *free_list; + unsigned objects; + unsigned chunks; + unsigned pages_per_chunk; + unsigned free_pages; + unsigned total_pages; +}; + +/* + * Free pages and page_list elements of client. + */ +static void free_cache_pages(struct page_list *list) +{ + while (list) { + struct page_list *pl = list; + + list = pl->next; + BUG_ON(!pl->page); + __free_page(pl->page); + kfree(pl); + } +} + +/* + * Alloc number of pages and page_list elements as required by client. + */ +static struct page_list *alloc_cache_pages(unsigned pages) +{ + struct page_list *pl, *ret = NULL; + struct page *page; + + while (pages--) { + page = alloc_page(GFP_NOIO); + if (!page) + goto err; + + pl = kmalloc(sizeof(*pl), GFP_NOIO); + if (!pl) { + __free_page(page); + goto err; + } + + pl->page = page; + pl->next = ret; + ret = pl; + } + + return ret; + +err: + free_cache_pages(ret); + return NULL; +} + +/* + * Allocate page_list elements from the pool to chunks of the memory object. + */ +static void alloc_chunks(struct dm_mem_cache_client *cl, + struct dm_mem_cache_object *obj) +{ + unsigned chunks = cl->chunks; + unsigned long flags; + + local_irq_save(flags); + local_irq_disable(); + while (chunks--) { + unsigned p = cl->pages_per_chunk; + + obj[chunks].pl = NULL; + + while (p--) { + struct page_list *pl; + + /* Take next element from free list */ + spin_lock(&cl->lock); + pl = cl->free_list; + BUG_ON(!pl); + cl->free_list = pl->next; + spin_unlock(&cl->lock); + + pl->next = obj[chunks].pl; + obj[chunks].pl = pl; + } + } + + local_irq_restore(flags); +} + +/* + * Free page_list elements putting them back onto free list + */ +static void free_chunks(struct dm_mem_cache_client *cl, + struct dm_mem_cache_object *obj) +{ + unsigned chunks = cl->chunks; + unsigned long flags; + struct page_list *next, *pl; + + local_irq_save(flags); + local_irq_disable(); + while (chunks--) { + for (pl = obj[chunks].pl; pl; pl = next) { + next = pl->next; + + spin_lock(&cl->lock); + pl->next = cl->free_list; + cl->free_list = pl; + cl->free_pages++; + spin_unlock(&cl->lock); + } + } + + local_irq_restore(flags); +} + +/* + * Create/destroy dm memory cache client resources. + */ +struct dm_mem_cache_client * +dm_mem_cache_client_create(unsigned objects, unsigned chunks, + unsigned pages_per_chunk) +{ + unsigned total_pages = objects * chunks * pages_per_chunk; + struct dm_mem_cache_client *client; + + BUG_ON(!total_pages); + client = kzalloc(sizeof(*client), GFP_KERNEL); + if (!client) + return ERR_PTR(-ENOMEM); + + client->objs_pool = mempool_create_kmalloc_pool(objects, + chunks * sizeof(struct dm_mem_cache_object)); + if (!client->objs_pool) + goto err; + + client->free_list = alloc_cache_pages(total_pages); + if (!client->free_list) + goto err1; + + spin_lock_init(&client->lock); + client->objects = objects; + client->chunks = chunks; + client->pages_per_chunk = pages_per_chunk; + client->free_pages = client->total_pages = total_pages; + return client; + +err1: + mempool_destroy(client->objs_pool); +err: + kfree(client); + return ERR_PTR(-ENOMEM); +} +EXPORT_SYMBOL(dm_mem_cache_client_create); + +void dm_mem_cache_client_destroy(struct dm_mem_cache_client *cl) +{ + BUG_ON(cl->free_pages != cl->total_pages); + free_cache_pages(cl->free_list); + mempool_destroy(cl->objs_pool); + kfree(cl); +} +EXPORT_SYMBOL(dm_mem_cache_client_destroy); + +/* + * Grow a clients cache by an amount of pages. + * + * Don't call from interrupt context! + */ +int dm_mem_cache_grow(struct dm_mem_cache_client *cl, unsigned objects) +{ + unsigned pages = objects * cl->chunks * cl->pages_per_chunk; + struct page_list *pl, *last; + + BUG_ON(!pages); + pl = alloc_cache_pages(pages); + if (!pl) + return -ENOMEM; + + last = pl; + while (last->next) + last = last->next; + + spin_lock_irq(&cl->lock); + last->next = cl->free_list; + cl->free_list = pl; + cl->free_pages += pages; + cl->total_pages += pages; + cl->objects++; + spin_unlock_irq(&cl->lock); + + mempool_resize(cl->objs_pool, cl->objects, GFP_NOIO); + return 0; +} +EXPORT_SYMBOL(dm_mem_cache_grow); + +/* Shrink a clients cache by an amount of pages */ +int dm_mem_cache_shrink(struct dm_mem_cache_client *cl, unsigned objects) +{ + int r; + unsigned pages = objects * cl->chunks * cl->pages_per_chunk, p = pages; + unsigned long flags; + struct page_list *last = NULL, *pl, *pos; + + BUG_ON(!pages); + + spin_lock_irqsave(&cl->lock, flags); + pl = pos = cl->free_list; + while (p-- && pos->next) { + last = pos; + pos = pos->next; + } + + if (++p) + r = -ENOMEM; + else { + r = 0; + cl->free_list = pos; + cl->free_pages -= pages; + cl->total_pages -= pages; + cl->objects--; + last->next = NULL; + } + spin_unlock_irqrestore(&cl->lock, flags); + + if (!r) { + free_cache_pages(pl); + mempool_resize(cl->objs_pool, cl->objects, GFP_NOIO); + } + + return r; +} +EXPORT_SYMBOL(dm_mem_cache_shrink); + +/* + * Allocate/free a memory object + * + * Can be called from interrupt context + */ +struct dm_mem_cache_object *dm_mem_cache_alloc(struct dm_mem_cache_client *cl) +{ + int r = 0; + unsigned pages = cl->chunks * cl->pages_per_chunk; + unsigned long flags; + struct dm_mem_cache_object *obj; + + obj = mempool_alloc(cl->objs_pool, GFP_NOIO); + if (!obj) + return ERR_PTR(-ENOMEM); + + spin_lock_irqsave(&cl->lock, flags); + if (pages > cl->free_pages) + r = -ENOMEM; + else + cl->free_pages -= pages; + spin_unlock_irqrestore(&cl->lock, flags); + + if (r) { + mempool_free(obj, cl->objs_pool); + return ERR_PTR(r); + } + + alloc_chunks(cl, obj); + return obj; +} +EXPORT_SYMBOL(dm_mem_cache_alloc); + +void dm_mem_cache_free(struct dm_mem_cache_client *cl, + struct dm_mem_cache_object *obj) +{ + free_chunks(cl, obj); + mempool_free(obj, cl->objs_pool); +} +EXPORT_SYMBOL(dm_mem_cache_free); + +MODULE_DESCRIPTION(DM_NAME " dm memory cache"); +MODULE_AUTHOR("Heinz Mauelshagen <hjm@redhat.com>"); +MODULE_LICENSE("GPL"); diff --git a/ubuntu/dm-raid4-5/dm-memcache.h b/ubuntu/dm-raid4-5/dm-memcache.h new file mode 100644 index 000000000000..87e4256daf5d --- /dev/null +++ b/ubuntu/dm-raid4-5/dm-memcache.h @@ -0,0 +1,68 @@ +/* + * Copyright (C) 2006-2008 Red Hat, Inc. All rights reserved. + * + * Module Author: Heinz Mauelshagen <Mauelshagen@RedHat.com> + * + * Device-mapper memory object handling: + * + * o allocate/free total_pages in a per client page pool. + * + * o allocate/free memory objects with chunks (1..n) of + * pages_per_chunk pages hanging off. + * + * This file is released under the GPL. + */ + +#ifndef _DM_MEM_CACHE_H +#define _DM_MEM_CACHE_H + +#define DM_MEM_CACHE_H_VERSION "0.1" + +#include "dm.h" +#include <linux/dm-io.h> + +static inline struct page_list *pl_elem(struct page_list *pl, unsigned p) +{ + while (pl && p--) + pl = pl->next; + + return pl; +} + +struct dm_mem_cache_object { + struct page_list *pl; /* Dynamically allocated array */ + void *private; /* Caller context reference */ +}; + +struct dm_mem_cache_client; + +/* + * Create/destroy dm memory cache client resources. + * + * On creation, a number of @objects with @chunks of + * @pages_per_chunk pages will be allocated. + */ +struct dm_mem_cache_client * +dm_mem_cache_client_create(unsigned objects, unsigned chunks, + unsigned pages_per_chunk); +void dm_mem_cache_client_destroy(struct dm_mem_cache_client *client); + +/* + * Grow/shrink a dm memory cache client resources + * by @objetcs amount of objects. + */ +int dm_mem_cache_grow(struct dm_mem_cache_client *client, unsigned objects); +int dm_mem_cache_shrink(struct dm_mem_cache_client *client, unsigned objects); + +/* + * Allocate/free a memory object + * + * On allocation one object with an amount of chunks and + * an amount of pages per chunk will be returned on success. + */ +struct dm_mem_cache_object * +dm_mem_cache_alloc(struct dm_mem_cache_client *client); +void dm_mem_cache_free(struct dm_mem_cache_client *client, + struct dm_mem_cache_object *object); + +#endif diff --git a/ubuntu/dm-raid4-5/dm-message.c b/ubuntu/dm-raid4-5/dm-message.c new file mode 100644 index 000000000000..de21e52c76ef --- /dev/null +++ b/ubuntu/dm-raid4-5/dm-message.c @@ -0,0 +1,184 @@ +/* + * Copyright (C) 2007,2008 Red Hat Inc. All rights reserved. + * + * Module Author: Heinz Mauelshagen <heinzm@redhat.com> + * + * General device-mapper message interface argument parser. + * + * This file is released under the GPL. + * + * device-mapper message parser. + * + */ + +#include "dm.h" +#include "dm-message.h" +#include <linux/kernel.h> +#include <linux/module.h> + +#define DM_MSG_PREFIX "dm_message" + +/* Basename of a path. */ +static inline char * +basename(char *s) +{ + char *p = strrchr(s, '/'); + + return p ? p + 1 : s; +} + +/* Get an argument depending on type. */ +static void +message_arguments(struct dm_msg *msg, int argc, char **argv) +{ + + if (argc) { + int i; + struct dm_message_argument *args = msg->spec->args; + + for (i = 0; i < args->num_args; i++) { + int r; + unsigned long **ptr = args->ptr; + enum dm_message_argument_type type = args->types[i]; + + switch (type) { + case dm_msg_base_t: + ((char **) ptr)[i] = basename(argv[i]); + break; + + case dm_msg_str_t: + ((char **) ptr)[i] = argv[i]; + break; + + case dm_msg_int_t: + r = sscanf(argv[i], "%d", ((int **) ptr)[i]); + goto check; + + case dm_msg_uint_t: + r = sscanf(argv[i], "%u", + ((unsigned **) ptr)[i]); + goto check; + + case dm_msg_uint64_t: + r = sscanf(argv[i], "%llu", + ((unsigned long long **) ptr)[i]); + +check: + if (r != 1) { + set_bit(dm_msg_ret_undef, &msg->ret); + set_bit(dm_msg_ret_arg, &msg->ret); + } + } + } + } +} + +/* Parse message options. */ +static void +message_options_parse(struct dm_msg *msg, int argc, char **argv) +{ + int hit = 0; + unsigned long *action; + size_t l1 = strlen(*argv), l_hit = 0; + struct dm_message_option *o = msg->spec->options; + char **option, **option_end = o->options + o->num_options; + + for (option = o->options, action = o->actions; + option < option_end; option++, action++) { + size_t l2 = strlen(*option); + + if (!strnicmp(*argv, *option, min(l1, l2))) { + hit++; + l_hit = l2; + set_bit(*action, &msg->action); + } + } + + /* Assume error. */ + msg->ret = 0; + set_bit(dm_msg_ret_option, &msg->ret); + if (!hit || l1 > l_hit) + set_bit(dm_msg_ret_undef, &msg->ret); /* Undefined option. */ + else if (hit > 1) + set_bit(dm_msg_ret_ambiguous, &msg->ret); /* Ambiguous option.*/ + else { + clear_bit(dm_msg_ret_option, &msg->ret); /* Option OK. */ + message_arguments(msg, --argc, ++argv); + } +} + +static inline void +print_ret(const char *caller, unsigned long ret) +{ + struct { + unsigned long err; + const char *err_str; + } static err_msg[] = { + { dm_msg_ret_ambiguous, "message ambiguous" }, + { dm_msg_ret_inval, "message invalid" }, + { dm_msg_ret_undef, "message undefined" }, + { dm_msg_ret_arg, "message argument" }, + { dm_msg_ret_argcount, "message argument count" }, + { dm_msg_ret_option, "option" }, + }, *e = ARRAY_END(err_msg); + + while (e-- > err_msg) { + if (test_bit(e->err, &ret)) + DMERR("%s %s", caller, e->err_str); + } +} + +/* Parse a message action. */ +int +dm_message_parse(const char *caller, struct dm_msg *msg, void *context, + int argc, char **argv) +{ + int hit = 0; + size_t l1, l_hit = 0; + struct dm_msg_spec *s, *s_hit = NULL, + *s_end = msg->specs + msg->num_specs; + + if (argc < 2) + return -EINVAL; + + l1 = strlen(*argv); + for (s = msg->specs; s < s_end; s++) { + size_t l2 = strlen(s->cmd); + + if (!strnicmp(*argv, s->cmd, min(l1, l2))) { + hit++; + l_hit = l2; + s_hit = s; + } + } + + msg->ret = 0; + if (!hit || l1 > l_hit) /* No hit or message string too long. */ + set_bit(dm_msg_ret_undef, &msg->ret); + else if (hit > 1) /* Ambiguous message. */ + set_bit(dm_msg_ret_ambiguous, &msg->ret); + else if (argc - 2 != s_hit->args->num_args) { + set_bit(dm_msg_ret_undef, &msg->ret); + set_bit(dm_msg_ret_argcount, &msg->ret); + } + + if (msg->ret) + goto bad; + + msg->action = 0; + msg->spec = s_hit; + set_bit(s_hit->action, &msg->action); + message_options_parse(msg, --argc, ++argv); + + if (!msg->ret) + return msg->spec->f(msg, context); + +bad: + print_ret(caller, msg->ret); + return -EINVAL; +} +EXPORT_SYMBOL(dm_message_parse); + +MODULE_DESCRIPTION(DM_NAME " device-mapper target message parser"); +MODULE_AUTHOR("Heinz Mauelshagen <hjm@redhat.com>"); +MODULE_LICENSE("GPL"); diff --git a/ubuntu/dm-raid4-5/dm-message.h b/ubuntu/dm-raid4-5/dm-message.h new file mode 100644 index 000000000000..2024534c5bf0 --- /dev/null +++ b/ubuntu/dm-raid4-5/dm-message.h @@ -0,0 +1,91 @@ +/* + * Copyright (C) 2007,2008 Red Hat, Inc. All rights reserved. + * + * Module Author: Heinz Mauelshagen <Mauelshagen@RedHat.de> + * + * General device-mapper message interface argument parser. + * + * This file is released under the GPL. + * + */ + +#ifndef DM_MESSAGE_H +#define DM_MESSAGE_H + +/* Factor out to dm.h. */ +/* Reference to array end. */ +#define ARRAY_END(a) ((a) + ARRAY_SIZE(a)) + +/* Message return bits. */ +enum dm_message_return { + dm_msg_ret_ambiguous, /* Action ambiguous. */ + dm_msg_ret_inval, /* Action invalid. */ + dm_msg_ret_undef, /* Action undefined. */ + + dm_msg_ret_option, /* Option error. */ + dm_msg_ret_arg, /* Argument error. */ + dm_msg_ret_argcount, /* Argument count error. */ +}; + +/* Message argument type conversions. */ +enum dm_message_argument_type { + dm_msg_base_t, /* Basename string. */ + dm_msg_str_t, /* String. */ + dm_msg_int_t, /* Signed int. */ + dm_msg_uint_t, /* Unsigned int. */ + dm_msg_uint64_t, /* Unsigned int 64. */ +}; + +/* A message option. */ +struct dm_message_option { + unsigned num_options; + char **options; + unsigned long *actions; +}; + +/* Message arguments and types. */ +struct dm_message_argument { + unsigned num_args; + unsigned long **ptr; + enum dm_message_argument_type types[]; +}; + +/* Client message. */ +struct dm_msg { + unsigned long action; /* Identified action. */ + unsigned long ret; /* Return bits. */ + unsigned num_specs; /* # of sepcifications listed. */ + struct dm_msg_spec *specs; /* Specification list. */ + struct dm_msg_spec *spec; /* Specification selected. */ +}; + +/* Secification of the message. */ +struct dm_msg_spec { + const char *cmd; /* Name of the command (i.e. 'bandwidth'). */ + unsigned long action; + struct dm_message_option *options; + struct dm_message_argument *args; + unsigned long parm; /* Parameter to pass through to callback. */ + /* Function to process for action. */ + int (*f) (struct dm_msg *msg, void *context); +}; + +/* Parameter access macros. */ +#define DM_MSG_PARM(msg) ((msg)->spec->parm) + +#define DM_MSG_STR_ARGS(msg, idx) ((char *) *(msg)->spec->args->ptr[idx]) +#define DM_MSG_INT_ARGS(msg, idx) ((int) *(msg)->spec->args->ptr[idx]) +#define DM_MSG_UINT_ARGS(msg, idx) ((unsigned) DM_MSG_INT_ARG(msg, idx)) +#define DM_MSG_UINT64_ARGS(msg, idx) ((uint64_t) *(msg)->spec->args->ptr[idx]) + +#define DM_MSG_STR_ARG(msg) DM_MSG_STR_ARGS(msg, 0) +#define DM_MSG_INT_ARG(msg) DM_MSG_INT_ARGS(msg, 0) +#define DM_MSG_UINT_ARG(msg) DM_MSG_UINT_ARGS(msg, 0) +#define DM_MSG_UINT64_ARG(msg) DM_MSG_UINT64_ARGS(msg, 0) + + +/* Parse a message and its options and optionally call a function back. */ +int dm_message_parse(const char *caller, struct dm_msg *msg, void *context, + int argc, char **argv); + +#endif diff --git a/ubuntu/dm-raid4-5/dm-raid4-5.c b/ubuntu/dm-raid4-5/dm-raid4-5.c new file mode 100644 index 000000000000..e05b0e14e347 --- /dev/null +++ b/ubuntu/dm-raid4-5/dm-raid4-5.c @@ -0,0 +1,4539 @@ +/*[A[A + * Copyright (C) 2005-2009 Red Hat, Inc. All rights reserved. + * + * Module Author: Heinz Mauelshagen <heinzm@redhat.com> + * + * This file is released under the GPL. + * + * + * Linux 2.6 Device Mapper RAID4 and RAID5 target. + * + * Supports: + * o RAID4 with dedicated and selectable parity device + * o RAID5 with rotating parity (left+right, symmetric+asymmetric) + * o recovery of out of sync device for initial + * RAID set creation or after dead drive replacement + * o run time optimization of xor algorithm used to calculate parity + * + * + * Thanks to MD for: + * o the raid address calculation algorithm + * o the base of the biovec <-> page list copier. + * + * + * Uses region hash to keep track of how many writes are in flight to + * regions in order to use dirty log to keep state of regions to recover: + * + * o clean regions (those which are synchronized + * and don't have write io in flight) + * o dirty regions (those with write io in flight) + * + * + * On startup, any dirty regions are migrated to the + * 'nosync' state and are subject to recovery by the daemon. + * + * See raid_ctr() for table definition. + * + * FIXME: recovery bandwidth + */ + +static const char *version = "v0.2594b"; + +#include "dm.h" +#include "dm-memcache.h" +#include "dm-message.h" +#include "dm-raid45.h" + +#include <linux/kernel.h> +#include <linux/vmalloc.h> +#include <linux/raid/xor.h> + +#include <linux/bio.h> +#include <linux/dm-io.h> +#include <linux/dm-dirty-log.h> +#include "dm-region-hash.h" + +#include <linux/slab.h> +#include <linux/module.h> + +/* + * Configurable parameters + */ + +/* Minimum/maximum and default # of selectable stripes. */ +#define STRIPES_MIN 8 +#define STRIPES_MAX 16384 +#define STRIPES_DEFAULT 80 + +/* Maximum and default chunk size in sectors if not set in constructor. */ +#define CHUNK_SIZE_MIN 8 +#define CHUNK_SIZE_MAX 16384 +#define CHUNK_SIZE_DEFAULT 64 + +/* Default io size in sectors if not set in constructor. */ +#define IO_SIZE_MIN CHUNK_SIZE_MIN +#define IO_SIZE_DEFAULT IO_SIZE_MIN + +/* Recover io size default in sectors. */ +#define RECOVER_IO_SIZE_MIN 64 +#define RECOVER_IO_SIZE_DEFAULT 256 + +/* Default, minimum and maximum percentage of recover io bandwidth. */ +#define BANDWIDTH_DEFAULT 10 +#define BANDWIDTH_MIN 1 +#define BANDWIDTH_MAX 100 + +/* # of parallel recovered regions */ +#define RECOVERY_STRIPES_MIN 1 +#define RECOVERY_STRIPES_MAX 64 +#define RECOVERY_STRIPES_DEFAULT RECOVERY_STRIPES_MIN +/* + * END Configurable parameters + */ + +#define TARGET "dm-raid45" +#define DAEMON "kraid45d" +#define DM_MSG_PREFIX TARGET + +#define SECTORS_PER_PAGE (PAGE_SIZE >> SECTOR_SHIFT) + +/* Amount/size for __xor(). */ +#define XOR_SIZE PAGE_SIZE + +/* Check value in range. */ +#define range_ok(i, min, max) (i >= min && i <= max) + +/* Check argument is power of 2. */ +#define POWER_OF_2(a) (!(a & (a - 1))) + +/* Structure access macros. */ +/* Derive raid_set from stripe_cache pointer. */ +#define RS(x) container_of(x, struct raid_set, sc) + +/* Page reference. */ +#define PAGE(stripe, p) ((stripe)->obj[p].pl->page) + +/* Stripe chunk reference. */ +#define CHUNK(stripe, p) ((stripe)->chunk + p) + +/* Bio list reference. */ +#define BL(stripe, p, rw) (stripe->chunk[p].bl + rw) +#define BL_CHUNK(chunk, rw) (chunk->bl + rw) + +/* Page list reference. */ +#define PL(stripe, p) (stripe->obj[p].pl) +/* END: structure access macros. */ + +/* Factor out to dm-bio-list.h */ +static inline void bio_list_push(struct bio_list *bl, struct bio *bio) +{ + bio->bi_next = bl->head; + bl->head = bio; + + if (!bl->tail) + bl->tail = bio; +} + +/* Factor out to dm.h */ +#define TI_ERR_RET(str, ret) \ + do { ti->error = str; return ret; } while (0); +#define TI_ERR(str) TI_ERR_RET(str, -EINVAL) + +/* Macro to define access IO flags access inline functions. */ +#define BITOPS(name, what, var, flag) \ +static inline int TestClear ## name ## what(struct var *v) \ +{ return test_and_clear_bit(flag, &v->io.flags); } \ +static inline int TestSet ## name ## what(struct var *v) \ +{ return test_and_set_bit(flag, &v->io.flags); } \ +static inline void Clear ## name ## what(struct var *v) \ +{ clear_bit(flag, &v->io.flags); } \ +static inline void Set ## name ## what(struct var *v) \ +{ set_bit(flag, &v->io.flags); } \ +static inline int name ## what(struct var *v) \ +{ return test_bit(flag, &v->io.flags); } + +/*----------------------------------------------------------------- + * Stripe cache + * + * Cache for all reads and writes to raid sets (operational or degraded) + * + * We need to run all data to and from a RAID set through this cache, + * because parity chunks need to get calculated from data chunks + * or, in the degraded/resynchronization case, missing chunks need + * to be reconstructed using the other chunks of the stripe. + *---------------------------------------------------------------*/ +/* A chunk within a stripe (holds bios hanging off). */ +/* IO status flags for chunks of a stripe. */ +enum chunk_flags { + CHUNK_DIRTY, /* Pages of chunk dirty; need writing. */ + CHUNK_ERROR, /* IO error on any chunk page. */ + CHUNK_IO, /* Allow/prohibit IO on chunk pages. */ + CHUNK_LOCKED, /* Chunk pages locked during IO. */ + CHUNK_MUST_IO, /* Chunk must io. */ + CHUNK_UNLOCK, /* Enforce chunk unlock. */ + CHUNK_UPTODATE, /* Chunk pages are uptodate. */ +}; + +/* + * This does not work anymore with __REQ_* values being enums + * +#if READ != 0 || WRITE != 1 +#error dm-raid45: READ/WRITE != 0/1 used as index!!! +#endif +*/ + +enum bl_type { + WRITE_QUEUED = WRITE + 1, + WRITE_MERGED, + NR_BL_TYPES, /* Must be last one! */ +}; +struct stripe_chunk { + atomic_t cnt; /* Reference count. */ + struct stripe *stripe; /* Backpointer to stripe for endio(). */ + /* Bio lists for reads, writes, and writes merged. */ + struct bio_list bl[NR_BL_TYPES]; + struct { + unsigned long flags; /* IO status flags. */ + } io; +}; + +/* Define chunk bit operations. */ +BITOPS(Chunk, Dirty, stripe_chunk, CHUNK_DIRTY) +BITOPS(Chunk, Error, stripe_chunk, CHUNK_ERROR) +BITOPS(Chunk, Io, stripe_chunk, CHUNK_IO) +BITOPS(Chunk, Locked, stripe_chunk, CHUNK_LOCKED) +BITOPS(Chunk, MustIo, stripe_chunk, CHUNK_MUST_IO) +BITOPS(Chunk, Unlock, stripe_chunk, CHUNK_UNLOCK) +BITOPS(Chunk, Uptodate, stripe_chunk, CHUNK_UPTODATE) + +/* + * Stripe linked list indexes. Keep order, because the stripe + * and the stripe cache rely on the first 3! + */ +enum list_types { + LIST_FLUSH, /* Stripes to flush for io. */ + LIST_ENDIO, /* Stripes to endio. */ + LIST_LRU, /* Least recently used stripes. */ + SC_NR_LISTS, /* # of lists in stripe cache. */ + LIST_HASH = SC_NR_LISTS, /* Hashed stripes. */ + LIST_RECOVER = LIST_HASH, /* For recovery type stripes only. */ + STRIPE_NR_LISTS,/* To size array in struct stripe. */ +}; + +/* Adressing region recovery. */ +struct recover_addr { + struct dm_region *reg; /* Actual region to recover. */ + sector_t pos; /* Position within region to recover. */ + sector_t end; /* End of region to recover. */ +}; + +/* A stripe: the io object to handle all reads and writes to a RAID set. */ +struct stripe { + atomic_t cnt; /* Reference count. */ + struct stripe_cache *sc; /* Backpointer to stripe cache. */ + + /* + * 4 linked lists: + * o io list to flush io + * o endio list + * o LRU list to put stripes w/o reference count on + * o stripe cache hash + */ + struct list_head lists[STRIPE_NR_LISTS]; + + sector_t key; /* Hash key. */ + region_t region; /* Region stripe is mapped to. */ + + struct { + unsigned long flags; /* Stripe state flags (see below). */ + + /* + * Pending ios in flight: + * + * used to control move of stripe to endio list + */ + atomic_t pending; + + /* Sectors to read and write for multi page stripe sets. */ + unsigned size; + } io; + + /* Address region recovery. */ + struct recover_addr *recover; + + /* Lock on stripe (Future: for clustering). */ + void *lock; + + struct { + unsigned short parity; /* Parity chunk index. */ + short recover; /* Recovery chunk index. */ + } idx; + + /* + * This stripe's memory cache object (dm-mem-cache); + * i.e. the io chunk pages. + */ + struct dm_mem_cache_object *obj; + + /* Array of stripe sets (dynamically allocated). */ + struct stripe_chunk chunk[0]; +}; + +/* States stripes can be in (flags field). */ +enum stripe_states { + STRIPE_ERROR, /* io error on stripe. */ + STRIPE_MERGED, /* Writes got merged to be written. */ + STRIPE_RBW, /* Read-before-write stripe. */ + STRIPE_RECONSTRUCT, /* Reconstruct of a missing chunk required. */ + STRIPE_RECONSTRUCTED, /* Reconstructed of a missing chunk. */ + STRIPE_RECOVER, /* Stripe used for RAID set recovery. */ +}; + +/* Define stripe bit operations. */ +BITOPS(Stripe, Error, stripe, STRIPE_ERROR) +BITOPS(Stripe, Merged, stripe, STRIPE_MERGED) +BITOPS(Stripe, RBW, stripe, STRIPE_RBW) +BITOPS(Stripe, Reconstruct, stripe, STRIPE_RECONSTRUCT) +BITOPS(Stripe, Reconstructed, stripe, STRIPE_RECONSTRUCTED) +BITOPS(Stripe, Recover, stripe, STRIPE_RECOVER) + +/* A stripe hash. */ +struct stripe_hash { + struct list_head *hash; + unsigned buckets; + unsigned mask; + unsigned prime; + unsigned shift; +}; + +enum sc_lock_types { + LOCK_ENDIO, /* Protect endio list. */ + LOCK_LRU, /* Protect LRU list. */ + NR_LOCKS, /* To size array in struct stripe_cache. */ +}; + +/* A stripe cache. */ +struct stripe_cache { + /* Stripe hash. */ + struct stripe_hash hash; + + spinlock_t locks[NR_LOCKS]; /* Locks to protect lists. */ + + /* Stripes with io to flush, stripes to endio and LRU lists. */ + struct list_head lists[SC_NR_LISTS]; + + /* Slab cache to allocate stripes from. */ + struct { + struct kmem_cache *cache; /* Cache itself. */ + char name[32]; /* Unique name. */ + } kc; + + struct dm_io_client *dm_io_client; /* dm-io client resource context. */ + + /* dm-mem-cache client resource context. */ + struct dm_mem_cache_client *mem_cache_client; + + int stripes_parm; /* # stripes parameter from constructor. */ + atomic_t stripes; /* actual # of stripes in cache. */ + atomic_t stripes_to_set; /* # of stripes to resize cache to. */ + atomic_t stripes_last; /* last # of stripes in cache. */ + atomic_t active_stripes; /* actual # of active stripes in cache. */ + + /* REMOVEME: */ + atomic_t active_stripes_max; /* actual # of active stripes in cache. */ +}; + +/* Flag specs for raid_dev */ ; +enum raid_dev_flags { + DEV_FAILED, /* Device failed. */ + DEV_IO_QUEUED, /* Io got queued to device. */ +}; + +/* The raid device in a set. */ +struct raid_dev { + struct dm_dev *dev; + sector_t start; /* Offset to map to. */ + struct { /* Using struct to be able to BITOPS(). */ + unsigned long flags; /* raid_dev_flags. */ + } io; +}; + +BITOPS(Dev, Failed, raid_dev, DEV_FAILED) +BITOPS(Dev, IoQueued, raid_dev, DEV_IO_QUEUED) + +/* Flags spec for raid_set. */ +enum raid_set_flags { + RS_CHECK_OVERWRITE, /* Check for chunk overwrites. */ + RS_DEAD, /* RAID set inoperational. */ + RS_DEGRADED, /* Io errors on RAID device. */ + RS_DEVEL_STATS, /* REMOVEME: display status information. */ + RS_RECOVER, /* Do recovery. */ + RS_RECOVERY_BANDWIDTH, /* Allow recovery bandwidth (delayed bios). */ + RS_SC_BUSY, /* Stripe cache busy -> send an event. */ + RS_SUSPEND, /* Suspend RAID set. */ +}; + +/* REMOVEME: devel stats counters. */ +enum stats_types { + S_BIOS_READ, + S_BIOS_ADDED_READ, + S_BIOS_ENDIO_READ, + S_BIOS_WRITE, + S_BIOS_ADDED_WRITE, + S_BIOS_ENDIO_WRITE, + S_CAN_MERGE, + S_CANT_MERGE, + S_CONGESTED, + S_DM_IO_READ, + S_DM_IO_WRITE, + S_BANDWIDTH, + S_BARRIER, + S_BIO_COPY_PL_NEXT, + S_DEGRADED, + S_DELAYED_BIOS, + S_FLUSHS, + S_HITS_1ST, + S_IOS_POST, + S_INSCACHE, + S_MAX_LOOKUP, + S_CHUNK_LOCKED, + S_NO_BANDWIDTH, + S_NOT_CONGESTED, + S_NO_RW, + S_NOSYNC, + S_OVERWRITE, + S_PROHIBITCHUNKIO, + S_RECONSTRUCT_EI, + S_RECONSTRUCT_DEV, + S_RECONSTRUCT_SET, + S_RECONSTRUCTED, + S_REQUEUE, + S_STRIPE_ERROR, + S_SUM_DELAYED_BIOS, + S_XORS, + S_NR_STATS, /* # of stats counters. Must be last! */ +}; + +/* Status type -> string mappings. */ +struct stats_map { + const enum stats_types type; + const char *str; +}; + +static struct stats_map stats_map[] = { + { S_BIOS_READ, "r=" }, + { S_BIOS_ADDED_READ, "/" }, + { S_BIOS_ENDIO_READ, "/" }, + { S_BIOS_WRITE, " w=" }, + { S_BIOS_ADDED_WRITE, "/" }, + { S_BIOS_ENDIO_WRITE, "/" }, + { S_DM_IO_READ, " rc=" }, + { S_DM_IO_WRITE, " wc=" }, + { S_BANDWIDTH, "\nbw=" }, + { S_NO_BANDWIDTH, " no_bw=" }, + { S_BARRIER, "\nbarrier=" }, + { S_BIO_COPY_PL_NEXT, "\nbio_cp_next=" }, + { S_CAN_MERGE, "\nmerge=" }, + { S_CANT_MERGE, "/no_merge=" }, + { S_CHUNK_LOCKED, "\nchunk_locked=" }, + { S_CONGESTED, "\ncgst=" }, + { S_NOT_CONGESTED, "/not_cgst=" }, + { S_DEGRADED, "\ndegraded=" }, + { S_DELAYED_BIOS, "\ndel_bios=" }, + { S_SUM_DELAYED_BIOS, "/sum_del_bios=" }, + { S_FLUSHS, "\nflushs=" }, + { S_HITS_1ST, "\nhits_1st=" }, + { S_IOS_POST, " ios_post=" }, + { S_INSCACHE, " inscache=" }, + { S_MAX_LOOKUP, " maxlookup=" }, + { S_NO_RW, "\nno_rw=" }, + { S_NOSYNC, " nosync=" }, + { S_OVERWRITE, " ovr=" }, + { S_PROHIBITCHUNKIO, " prhbt_io=" }, + { S_RECONSTRUCT_EI, "\nrec_ei=" }, + { S_RECONSTRUCT_DEV, " rec_dev=" }, + { S_RECONSTRUCT_SET, " rec_set=" }, + { S_RECONSTRUCTED, " rec=" }, + { S_REQUEUE, " requeue=" }, + { S_STRIPE_ERROR, " stripe_err=" }, + { S_XORS, " xors=" }, +}; + +/* + * A RAID set. + */ +#define dm_rh_client dm_region_hash +enum count_type { IO_WORK = 0, IO_RECOVER, IO_NR_COUNT }; +typedef void (*xor_function_t)(unsigned count, unsigned long **data); +struct raid_set { + struct dm_target *ti; /* Target pointer. */ + + struct { + unsigned long flags; /* State flags. */ + struct mutex in_lock; /* Protects central input list below. */ + struct bio_list in; /* Pending ios (central input list). */ + struct bio_list work; /* ios work set. */ + wait_queue_head_t suspendq; /* suspend synchronization. */ + atomic_t in_process; /* counter of queued bios (suspendq). */ + atomic_t in_process_max;/* counter of queued bios max. */ + + /* io work. */ + struct workqueue_struct *wq; + struct delayed_work dws_do_raid; /* For main worker. */ + struct work_struct ws_do_table_event; /* For event worker. */ + } io; + + /* Stripe locking abstraction. */ + struct dm_raid45_locking_type *locking; + + struct stripe_cache sc; /* Stripe cache for this set. */ + + /* Xor optimization. */ + struct { + struct xor_func *f; + unsigned chunks; + unsigned speed; + } xor; + + /* Recovery parameters. */ + struct recover { + struct dm_dirty_log *dl; /* Dirty log. */ + struct dm_rh_client *rh; /* Region hash. */ + + struct dm_io_client *dm_io_client; /* recovery dm-io client. */ + /* dm-mem-cache client resource context for recovery stripes. */ + struct dm_mem_cache_client *mem_cache_client; + + struct list_head stripes; /* List of recovery stripes. */ + + region_t nr_regions; + region_t nr_regions_to_recover; + region_t nr_regions_recovered; + unsigned long start_jiffies; + unsigned long end_jiffies; + + unsigned bandwidth; /* Recovery bandwidth [%]. */ + unsigned bandwidth_work; /* Recovery bandwidth [factor]. */ + unsigned bandwidth_parm; /* " constructor parm. */ + unsigned io_size; /* recovery io size <= region size. */ + unsigned io_size_parm; /* recovery io size ctr parameter. */ + unsigned recovery; /* Recovery allowed/prohibited. */ + unsigned recovery_stripes; /* # of parallel recovery stripes. */ + + /* recovery io throttling. */ + atomic_t io_count[IO_NR_COUNT]; /* counter recover/regular io.*/ + unsigned long last_jiffies; + } recover; + + /* RAID set parameters. */ + struct { + struct raid_type *raid_type; /* RAID type (eg, RAID4). */ + unsigned raid_parms; /* # variable raid parameters. */ + + unsigned chunk_size; /* Sectors per chunk. */ + unsigned chunk_size_parm; + unsigned chunk_shift; /* rsector chunk size shift. */ + + unsigned io_size; /* Sectors per io. */ + unsigned io_size_parm; + unsigned io_mask; /* Mask for bio_copy_page_list(). */ + unsigned io_inv_mask; /* Mask for raid_address(). */ + + sector_t sectors_per_dev; /* Sectors per device. */ + + atomic_t failed_devs; /* Amount of devices failed. */ + + /* Index of device to initialize. */ + int dev_to_init; + int dev_to_init_parm; + + /* Raid devices dynamically allocated. */ + unsigned raid_devs; /* # of RAID devices below. */ + unsigned data_devs; /* # of RAID data devices. */ + + int ei; /* index of failed RAID device. */ + + /* Index of dedicated parity device (i.e. RAID4). */ + int pi; + int pi_parm; /* constructor parm for status output. */ + } set; + + /* REMOVEME: devel stats counters. */ + atomic_t stats[S_NR_STATS]; + + /* Dynamically allocated temporary pointers for xor(). */ + unsigned long **data; + + /* Dynamically allocated RAID devices. Alignment? */ + struct raid_dev dev[0]; +}; + +/* Define RAID set bit operations. */ +BITOPS(RS, Bandwidth, raid_set, RS_RECOVERY_BANDWIDTH) +BITOPS(RS, CheckOverwrite, raid_set, RS_CHECK_OVERWRITE) +BITOPS(RS, Dead, raid_set, RS_DEAD) +BITOPS(RS, Degraded, raid_set, RS_DEGRADED) +BITOPS(RS, DevelStats, raid_set, RS_DEVEL_STATS) +BITOPS(RS, Recover, raid_set, RS_RECOVER) +BITOPS(RS, ScBusy, raid_set, RS_SC_BUSY) +BITOPS(RS, Suspend, raid_set, RS_SUSPEND) +#undef BITOPS + +/*----------------------------------------------------------------- + * Raid-4/5 set structures. + *---------------------------------------------------------------*/ +/* RAID level definitions. */ +enum raid_level { + raid4, + raid5, +}; + +/* Symmetric/Asymmetric, Left/Right parity rotating algorithms. */ +enum raid_algorithm { + none, + left_asym, + right_asym, + left_sym, + right_sym, +}; + +struct raid_type { + const char *name; /* RAID algorithm. */ + const char *descr; /* Descriptor text for logging. */ + const unsigned parity_devs; /* # of parity devices. */ + const unsigned minimal_devs; /* minimal # of devices in set. */ + const enum raid_level level; /* RAID level. */ + const enum raid_algorithm algorithm; /* RAID algorithm. */ +}; + +/* Supported raid types and properties. */ +static struct raid_type raid_types[] = { + {"raid4", "RAID4 (dedicated parity disk)", 1, 3, raid4, none}, + {"raid5_la", "RAID5 (left asymmetric)", 1, 3, raid5, left_asym}, + {"raid5_ra", "RAID5 (right asymmetric)", 1, 3, raid5, right_asym}, + {"raid5_ls", "RAID5 (left symmetric)", 1, 3, raid5, left_sym}, + {"raid5_rs", "RAID5 (right symmetric)", 1, 3, raid5, right_sym}, +}; + +/* Address as calculated by raid_address(). */ +struct raid_address { + sector_t key; /* Hash key (address of stripe % chunk_size). */ + unsigned di, pi; /* Data and parity disks index. */ +}; + +/* REMOVEME: reset statistics counters. */ +static void stats_reset(struct raid_set *rs) +{ + unsigned s = S_NR_STATS; + + while (s--) + atomic_set(rs->stats + s, 0); +} + +/*---------------------------------------------------------------- + * RAID set management routines. + *--------------------------------------------------------------*/ +/* + * Begin small helper functions. + */ +/* No need to be called from region hash indirectly at dm_rh_dec(). */ +static void wake_dummy(void *context) {} + +/* Return # of io reference. */ +static int io_ref(struct raid_set *rs) +{ + return atomic_read(&rs->io.in_process); +} + +/* Get an io reference. */ +static void io_get(struct raid_set *rs) +{ + int p = atomic_inc_return(&rs->io.in_process); + + if (p > atomic_read(&rs->io.in_process_max)) + atomic_set(&rs->io.in_process_max, p); /* REMOVEME: max. */ +} + +/* Put the io reference and conditionally wake io waiters. */ +static void io_put(struct raid_set *rs) +{ + /* Intel: rebuild data corrupter? */ + if (atomic_dec_and_test(&rs->io.in_process)) + wake_up(&rs->io.suspendq); + else + BUG_ON(io_ref(rs) < 0); +} + +/* Wait until all io has been processed. */ +static void wait_ios(struct raid_set *rs) +{ + wait_event(rs->io.suspendq, !io_ref(rs)); +} + +/* Queue (optionally delayed) io work. */ +static void wake_do_raid_delayed(struct raid_set *rs, unsigned long delay) +{ + queue_delayed_work(rs->io.wq, &rs->io.dws_do_raid, delay); +} + +/* Queue io work immediately (called from region hash too). */ +static void wake_do_raid(void *context) +{ + struct raid_set *rs = context; + + queue_work(rs->io.wq, &rs->io.dws_do_raid.work); +} + +/* Calculate device sector offset. */ +static sector_t _sector(struct raid_set *rs, struct bio *bio) +{ + sector_t sector = bio->bi_sector; + + sector_div(sector, rs->set.data_devs); + return sector; +} + +/* Return # of active stripes in stripe cache. */ +static int sc_active(struct stripe_cache *sc) +{ + return atomic_read(&sc->active_stripes); +} + +/* Stripe cache busy indicator. */ +static int sc_busy(struct raid_set *rs) +{ + return sc_active(&rs->sc) > + atomic_read(&rs->sc.stripes) - (STRIPES_MIN / 2); +} + +/* Set chunks states. */ +enum chunk_dirty_type { CLEAN, DIRTY, ERROR }; +static void chunk_set(struct stripe_chunk *chunk, enum chunk_dirty_type type) +{ + switch (type) { + case CLEAN: + ClearChunkDirty(chunk); + break; + case DIRTY: + SetChunkDirty(chunk); + break; + case ERROR: + SetChunkError(chunk); + SetStripeError(chunk->stripe); + return; + default: + BUG(); + } + + SetChunkUptodate(chunk); + SetChunkIo(chunk); + ClearChunkError(chunk); +} + +/* Return region state for a sector. */ +static int region_state(struct raid_set *rs, sector_t sector, + enum dm_rh_region_states state) +{ + struct dm_rh_client *rh = rs->recover.rh; + region_t region = dm_rh_sector_to_region(rh, sector); + + return !!(dm_rh_get_state(rh, region, 1) & state); +} + +/* + * Return true in case a chunk should be read/written + * + * Conditions to read/write: + * o chunk not uptodate + * o chunk dirty + * + * Conditios to avoid io: + * o io already ongoing on chunk + * o io explitely prohibited + */ +static int chunk_io(struct stripe_chunk *chunk) +{ + /* 2nd run optimization (flag set below on first run). */ + if (TestClearChunkMustIo(chunk)) + return 1; + + /* Avoid io if prohibited or a locked chunk. */ + if (!ChunkIo(chunk) || ChunkLocked(chunk)) + return 0; + + if (!ChunkUptodate(chunk) || ChunkDirty(chunk)) { + SetChunkMustIo(chunk); /* 2nd run optimization. */ + return 1; + } + + return 0; +} + +/* Call a function on each chunk needing io unless device failed. */ +static unsigned for_each_io_dev(struct stripe *stripe, + void (*f_io)(struct stripe *stripe, unsigned p)) +{ + struct raid_set *rs = RS(stripe->sc); + unsigned p, r = 0; + + for (p = 0; p < rs->set.raid_devs; p++) { + if (chunk_io(CHUNK(stripe, p)) && !DevFailed(rs->dev + p)) { + f_io(stripe, p); + r++; + } + } + + return r; +} + +/* + * Index of device to calculate parity on. + * + * Either the parity device index *or* the selected + * device to init after a spare replacement. + */ +static int dev_for_parity(struct stripe *stripe, int *sync) +{ + struct raid_set *rs = RS(stripe->sc); + int r = region_state(rs, stripe->key, DM_RH_NOSYNC | DM_RH_RECOVERING); + + *sync = !r; + + /* Reconstruct a particular device ?. */ + if (r && rs->set.dev_to_init > -1) + return rs->set.dev_to_init; + else if (rs->set.raid_type->level == raid4) + return rs->set.pi; + else if (!StripeRecover(stripe)) + return stripe->idx.parity; + else + return -1; +} + +/* RAID set congested function. */ +static int rs_congested(void *congested_data, int bdi_bits) +{ + int r; + unsigned p; + struct raid_set *rs = congested_data; + + if (sc_busy(rs) || RSSuspend(rs)) + r = 1; + else for (r = 0, p = rs->set.raid_devs; !r && p--; ) { + /* If any of our component devices are overloaded. */ + struct request_queue *q = bdev_get_queue(rs->dev[p].dev->bdev); + + r |= bdi_congested(&q->backing_dev_info, bdi_bits); + } + + /* REMOVEME: statistics. */ + atomic_inc(rs->stats + (r ? S_CONGESTED : S_NOT_CONGESTED)); + return r; +} + +/* RAID device degrade check. */ +static void rs_check_degrade_dev(struct raid_set *rs, + struct stripe *stripe, unsigned p) +{ + if (TestSetDevFailed(rs->dev + p)) + return; + + /* Through an event in case of member device errors. */ + if (atomic_inc_return(&rs->set.failed_devs) > + rs->set.raid_type->parity_devs && + !TestSetRSDead(rs)) { + /* Display RAID set dead message once. */ + unsigned p; + char buf[BDEVNAME_SIZE]; + + DMERR("FATAL: too many devices failed -> RAID set broken"); + for (p = 0; p < rs->set.raid_devs; p++) { + if (DevFailed(rs->dev + p)) + DMERR("device /dev/%s failed", + bdevname(rs->dev[p].dev->bdev, buf)); + } + } + + /* Only log the first member error. */ + if (!TestSetRSDegraded(rs)) { + char buf[BDEVNAME_SIZE]; + + /* Store index for recovery. */ + rs->set.ei = p; + DMERR("CRITICAL: %sio error on device /dev/%s " + "in region=%llu; DEGRADING RAID set\n", + stripe ? "" : "FAKED ", + bdevname(rs->dev[p].dev->bdev, buf), + (unsigned long long) (stripe ? stripe->key : 0)); + DMERR("further device error messages suppressed"); + } + + schedule_work(&rs->io.ws_do_table_event); +} + +/* RAID set degrade check. */ +static void rs_check_degrade(struct stripe *stripe) +{ + struct raid_set *rs = RS(stripe->sc); + unsigned p = rs->set.raid_devs; + + while (p--) { + if (ChunkError(CHUNK(stripe, p))) + rs_check_degrade_dev(rs, stripe, p); + } +} + +/* Lookup a RAID device by name or by major:minor number. */ +static int raid_dev_lookup(struct raid_set *rs, struct raid_dev *dev_lookup) +{ + unsigned p; + struct raid_dev *dev; + + /* + * Must be an incremental loop, because the device array + * can have empty slots still on calls from raid_ctr() + */ + for (dev = rs->dev, p = 0; + dev->dev && p < rs->set.raid_devs; + dev++, p++) { + if (dev_lookup->dev->bdev->bd_dev == dev->dev->bdev->bd_dev) + return p; + } + + return -ENODEV; +} +/* + * End small helper functions. + */ + +/* + * Stripe hash functions + */ +/* Initialize/destroy stripe hash. */ +static int hash_init(struct stripe_hash *hash, unsigned stripes) +{ + unsigned buckets = 2, max_buckets = stripes >> 1; + static unsigned hash_primes[] = { + /* Table of primes for hash_fn/table size optimization. */ + 1, 2, 3, 7, 13, 27, 53, 97, 193, 389, 769, + 1543, 3079, 6151, 12289, 24593, 49157, 98317, + }; + + /* Calculate number of buckets (2^^n <= stripes / 2). */ + while (buckets < max_buckets) + buckets <<= 1; + + /* Allocate stripe hash buckets. */ + hash->hash = vmalloc(buckets * sizeof(*hash->hash)); + if (!hash->hash) + return -ENOMEM; + + hash->buckets = buckets; + hash->mask = buckets - 1; + hash->shift = ffs(buckets); + if (hash->shift > ARRAY_SIZE(hash_primes)) + hash->shift = ARRAY_SIZE(hash_primes) - 1; + + BUG_ON(hash->shift < 2); + hash->prime = hash_primes[hash->shift]; + + /* Initialize buckets. */ + while (buckets--) + INIT_LIST_HEAD(hash->hash + buckets); + return 0; +} + +static void hash_exit(struct stripe_hash *hash) +{ + if (hash->hash) { + vfree(hash->hash); + hash->hash = NULL; + } +} + +static unsigned hash_fn(struct stripe_hash *hash, sector_t key) +{ + return (unsigned) (((key * hash->prime) >> hash->shift) & hash->mask); +} + +static struct list_head *hash_bucket(struct stripe_hash *hash, sector_t key) +{ + return hash->hash + hash_fn(hash, key); +} + +/* Insert an entry into a hash. */ +static void stripe_insert(struct stripe_hash *hash, struct stripe *stripe) +{ + list_add(stripe->lists + LIST_HASH, hash_bucket(hash, stripe->key)); +} + +/* Lookup an entry in the stripe hash. */ +static struct stripe *stripe_lookup(struct stripe_cache *sc, sector_t key) +{ + unsigned look = 0; + struct stripe *stripe; + struct list_head *bucket = hash_bucket(&sc->hash, key); + + list_for_each_entry(stripe, bucket, lists[LIST_HASH]) { + look++; + + if (stripe->key == key) { + /* REMOVEME: statisics. */ + if (look > atomic_read(RS(sc)->stats + S_MAX_LOOKUP)) + atomic_set(RS(sc)->stats + S_MAX_LOOKUP, look); + return stripe; + } + } + + return NULL; +} + +/* Resize the stripe cache hash on size changes. */ +static int sc_hash_resize(struct stripe_cache *sc) +{ + /* Resize indicated ? */ + if (atomic_read(&sc->stripes) != atomic_read(&sc->stripes_last)) { + int r; + struct stripe_hash hash; + + r = hash_init(&hash, atomic_read(&sc->stripes)); + if (r) + return r; + + if (sc->hash.hash) { + unsigned b = sc->hash.buckets; + struct list_head *pos, *tmp; + + /* Walk old buckets and insert into new. */ + while (b--) { + list_for_each_safe(pos, tmp, sc->hash.hash + b) + stripe_insert(&hash, + list_entry(pos, struct stripe, + lists[LIST_HASH])); + } + + } + + hash_exit(&sc->hash); + memcpy(&sc->hash, &hash, sizeof(sc->hash)); + atomic_set(&sc->stripes_last, atomic_read(&sc->stripes)); + } + + return 0; +} +/* End hash stripe hash function. */ + +/* List add, delete, push and pop functions. */ +/* Add stripe to flush list. */ +#define DEL_LIST(lh) \ + if (!list_empty(lh)) \ + list_del_init(lh); + +/* Delete stripe from hash. */ +static void stripe_hash_del(struct stripe *stripe) +{ + DEL_LIST(stripe->lists + LIST_HASH); +} + +/* Return stripe reference count. */ +static inline int stripe_ref(struct stripe *stripe) +{ + return atomic_read(&stripe->cnt); +} + +static void stripe_flush_add(struct stripe *stripe) +{ + struct stripe_cache *sc = stripe->sc; + struct list_head *lh = stripe->lists + LIST_FLUSH; + + if (!StripeReconstruct(stripe) && list_empty(lh)) + list_add_tail(lh, sc->lists + LIST_FLUSH); +} + +/* + * Add stripe to LRU (inactive) list. + * + * Need lock, because of concurrent access from message interface. + */ +static void stripe_lru_add(struct stripe *stripe) +{ + if (!StripeRecover(stripe)) { + unsigned long flags; + struct list_head *lh = stripe->lists + LIST_LRU; + spinlock_t *lock = stripe->sc->locks + LOCK_LRU; + + spin_lock_irqsave(lock, flags); + if (list_empty(lh)) + list_add_tail(lh, stripe->sc->lists + LIST_LRU); + spin_unlock_irqrestore(lock, flags); + } +} + +#define POP_LIST(list) \ + do { \ + if (list_empty(sc->lists + (list))) \ + stripe = NULL; \ + else { \ + stripe = list_first_entry(sc->lists + (list), \ + struct stripe, \ + lists[(list)]); \ + list_del_init(stripe->lists + (list)); \ + } \ + } while (0); + +/* Pop an available stripe off the LRU list. */ +static struct stripe *stripe_lru_pop(struct stripe_cache *sc) +{ + struct stripe *stripe; + spinlock_t *lock = sc->locks + LOCK_LRU; + + spin_lock_irq(lock); + POP_LIST(LIST_LRU); + spin_unlock_irq(lock); + + return stripe; +} + +/* Pop an available stripe off the io list. */ +static struct stripe *stripe_io_pop(struct stripe_cache *sc) +{ + struct stripe *stripe; + + POP_LIST(LIST_FLUSH); + return stripe; +} + +/* Push a stripe safely onto the endio list to be handled by do_endios(). */ +static void stripe_endio_push(struct stripe *stripe) +{ + unsigned long flags; + struct stripe_cache *sc = stripe->sc; + struct list_head *stripe_list = stripe->lists + LIST_ENDIO, + *sc_list = sc->lists + LIST_ENDIO; + spinlock_t *lock = sc->locks + LOCK_ENDIO; + + /* This runs in parallel with do_endios(). */ + spin_lock_irqsave(lock, flags); + if (list_empty(stripe_list)) + list_add_tail(stripe_list, sc_list); + spin_unlock_irqrestore(lock, flags); + + wake_do_raid(RS(sc)); /* Wake myself. */ +} + +/* Pop a stripe off safely off the endio list. */ +static struct stripe *stripe_endio_pop(struct stripe_cache *sc) +{ + struct stripe *stripe; + spinlock_t *lock = sc->locks + LOCK_ENDIO; + + /* This runs in parallel with endio(). */ + spin_lock_irq(lock); + POP_LIST(LIST_ENDIO) + spin_unlock_irq(lock); + return stripe; +} +#undef POP_LIST + +/* + * Stripe cache locking functions + */ +/* Dummy lock function for single host RAID4+5. */ +static void *no_lock(sector_t key, enum dm_lock_type type) +{ + return &no_lock; +} + +/* Dummy unlock function for single host RAID4+5. */ +static void no_unlock(void *lock_handle) +{ +} + +/* No locking (for single host RAID 4+5). */ +static struct dm_raid45_locking_type locking_none = { + .lock = no_lock, + .unlock = no_unlock, +}; + +/* Lock a stripe (for clustering). */ +static int +stripe_lock(struct stripe *stripe, int rw, sector_t key) +{ + stripe->lock = RS(stripe->sc)->locking->lock(key, rw == READ ? DM_RAID45_SHARED : DM_RAID45_EX); + return stripe->lock ? 0 : -EPERM; +} + +/* Unlock a stripe (for clustering). */ +static void stripe_unlock(struct stripe *stripe) +{ + RS(stripe->sc)->locking->unlock(stripe->lock); + stripe->lock = NULL; +} + +/* Test io pending on stripe. */ +static int stripe_io_ref(struct stripe *stripe) +{ + return atomic_read(&stripe->io.pending); +} + +static void stripe_io_get(struct stripe *stripe) +{ + if (atomic_inc_return(&stripe->io.pending) == 1) + /* REMOVEME: statistics */ + atomic_inc(&stripe->sc->active_stripes); + else + BUG_ON(stripe_io_ref(stripe) < 0); +} + +static void stripe_io_put(struct stripe *stripe) +{ + if (atomic_dec_and_test(&stripe->io.pending)) { + if (unlikely(StripeRecover(stripe))) + /* Don't put recovery stripe on endio list. */ + wake_do_raid(RS(stripe->sc)); + else + /* Add regular stripe to endio list and wake daemon. */ + stripe_endio_push(stripe); + + /* REMOVEME: statistics */ + atomic_dec(&stripe->sc->active_stripes); + } else + BUG_ON(stripe_io_ref(stripe) < 0); +} + +/* Take stripe reference out. */ +static int stripe_get(struct stripe *stripe) +{ + int r; + struct list_head *lh = stripe->lists + LIST_LRU; + spinlock_t *lock = stripe->sc->locks + LOCK_LRU; + + /* Delete stripe from LRU (inactive) list if on. */ + spin_lock_irq(lock); + DEL_LIST(lh); + spin_unlock_irq(lock); + + BUG_ON(stripe_ref(stripe) < 0); + + /* Lock stripe on first reference */ + r = (atomic_inc_return(&stripe->cnt) == 1) ? + stripe_lock(stripe, WRITE, stripe->key) : 0; + + return r; +} +#undef DEL_LIST + +/* Return references on a chunk. */ +static int chunk_ref(struct stripe_chunk *chunk) +{ + return atomic_read(&chunk->cnt); +} + +/* Take out reference on a chunk. */ +static int chunk_get(struct stripe_chunk *chunk) +{ + return atomic_inc_return(&chunk->cnt); +} + +/* Drop reference on a chunk. */ +static void chunk_put(struct stripe_chunk *chunk) +{ + BUG_ON(atomic_dec_return(&chunk->cnt) < 0); +} + +/* + * Drop reference on a stripe. + * + * Move it to list of LRU stripes if zero. + */ +static void stripe_put(struct stripe *stripe) +{ + if (atomic_dec_and_test(&stripe->cnt)) { + BUG_ON(stripe_io_ref(stripe)); + stripe_unlock(stripe); + } else + BUG_ON(stripe_ref(stripe) < 0); +} + +/* Helper needed by for_each_io_dev(). */ +static void stripe_get_references(struct stripe *stripe, unsigned p) +{ + + /* + * Another one to reference the stripe in + * order to protect vs. LRU list moves. + */ + io_get(RS(stripe->sc)); /* Global io references. */ + stripe_get(stripe); + stripe_io_get(stripe); /* One for each chunk io. */ +} + +/* Helper for endio() to put all take references. */ +static void stripe_put_references(struct stripe *stripe) +{ + stripe_io_put(stripe); /* One for each chunk io. */ + stripe_put(stripe); + io_put(RS(stripe->sc)); +} + +/* + * Stripe cache functions. + */ +/* + * Invalidate all chunks (i.e. their pages) of a stripe. + * + * I only keep state for the whole chunk. + */ +static inline void stripe_chunk_invalidate(struct stripe_chunk *chunk) +{ + chunk->io.flags = 0; +} + +static void +stripe_chunks_invalidate(struct stripe *stripe) +{ + unsigned p = RS(stripe->sc)->set.raid_devs; + + while (p--) + stripe_chunk_invalidate(CHUNK(stripe, p)); +} + +/* Prepare stripe for (re)use. */ +static void stripe_invalidate(struct stripe *stripe) +{ + stripe->io.flags = 0; + stripe->idx.parity = stripe->idx.recover = -1; + stripe_chunks_invalidate(stripe); +} + +/* + * Allow io on all chunks of a stripe. + * If not set, IO will not occur; i.e. it's prohibited. + * + * Actual IO submission for allowed chunks depends + * on their !uptodate or dirty state. + */ +static void stripe_allow_io(struct stripe *stripe) +{ + unsigned p = RS(stripe->sc)->set.raid_devs; + + while (p--) + SetChunkIo(CHUNK(stripe, p)); +} + +/* Initialize a stripe. */ +static void stripe_init(struct stripe_cache *sc, struct stripe *stripe) +{ + unsigned i, p = RS(sc)->set.raid_devs; + + /* Work all io chunks. */ + while (p--) { + struct stripe_chunk *chunk = CHUNK(stripe, p); + + atomic_set(&chunk->cnt, 0); + chunk->stripe = stripe; + i = ARRAY_SIZE(chunk->bl); + while (i--) + bio_list_init(chunk->bl + i); + } + + stripe->sc = sc; + + + i = ARRAY_SIZE(stripe->lists); + while (i--) + INIT_LIST_HEAD(stripe->lists + i); + + stripe->io.size = RS(sc)->set.io_size; + atomic_set(&stripe->cnt, 0); + atomic_set(&stripe->io.pending, 0); + stripe_invalidate(stripe); +} + +/* Number of pages per chunk. */ +static inline unsigned chunk_pages(unsigned sectors) +{ + return dm_div_up(sectors, SECTORS_PER_PAGE); +} + +/* Number of pages per stripe. */ +static inline unsigned stripe_pages(struct raid_set *rs, unsigned io_size) +{ + return chunk_pages(io_size) * rs->set.raid_devs; +} + +/* Initialize part of page_list (recovery). */ +static void stripe_zero_pl_part(struct stripe *stripe, int p, + unsigned start, unsigned count) +{ + unsigned o = start / SECTORS_PER_PAGE, pages = chunk_pages(count); + /* Get offset into the page_list. */ + struct page_list *pl = pl_elem(PL(stripe, p), o); + + BUG_ON(!pl); + while (pl && pages--) { + BUG_ON(!pl->page); + memset(page_address(pl->page), 0, PAGE_SIZE); + pl = pl->next; + } +} + +/* Initialize parity chunk of stripe. */ +static void stripe_zero_chunk(struct stripe *stripe, int p) +{ + if (p > -1) + stripe_zero_pl_part(stripe, p, 0, stripe->io.size); +} + +/* Return dynamic stripe structure size. */ +static size_t stripe_size(struct raid_set *rs) +{ + return sizeof(struct stripe) + + rs->set.raid_devs * sizeof(struct stripe_chunk); +} + +/* Allocate a stripe and its memory object. */ +/* XXX adjust to cope with stripe cache and recovery stripe caches. */ +enum grow { SC_GROW, SC_KEEP }; +static struct stripe *stripe_alloc(struct stripe_cache *sc, + struct dm_mem_cache_client *mc, + enum grow grow) +{ + int r; + struct stripe *stripe; + + stripe = kmem_cache_zalloc(sc->kc.cache, GFP_KERNEL); + if (stripe) { + /* Grow the dm-mem-cache by one object. */ + if (grow == SC_GROW) { + r = dm_mem_cache_grow(mc, 1); + if (r) + goto err_free; + } + + stripe->obj = dm_mem_cache_alloc(mc); + if (!stripe->obj) + goto err_shrink; + + stripe_init(sc, stripe); + } + + return stripe; + +err_shrink: + if (grow == SC_GROW) + dm_mem_cache_shrink(mc, 1); +err_free: + kmem_cache_free(sc->kc.cache, stripe); + return NULL; +} + +/* + * Free a stripes memory object, shrink the + * memory cache and free the stripe itself. + */ +static void stripe_free(struct stripe *stripe, struct dm_mem_cache_client *mc) +{ + dm_mem_cache_free(mc, stripe->obj); + dm_mem_cache_shrink(mc, 1); + kmem_cache_free(stripe->sc->kc.cache, stripe); +} + +/* Free the recovery stripe. */ +static void stripe_recover_free(struct raid_set *rs) +{ + struct recover *rec = &rs->recover; + struct dm_mem_cache_client *mc; + + mc = rec->mem_cache_client; + rec->mem_cache_client = NULL; + if (mc) { + struct stripe *stripe; + + while (!list_empty(&rec->stripes)) { + stripe = list_first_entry(&rec->stripes, struct stripe, + lists[LIST_RECOVER]); + list_del(stripe->lists + LIST_RECOVER); + kfree(stripe->recover); + stripe_free(stripe, mc); + } + + dm_mem_cache_client_destroy(mc); + dm_io_client_destroy(rec->dm_io_client); + rec->dm_io_client = NULL; + } +} + +/* Grow stripe cache. */ +static int sc_grow(struct stripe_cache *sc, unsigned stripes, enum grow grow) +{ + int r = 0; + + /* Try to allocate this many (additional) stripes. */ + while (stripes--) { + struct stripe *stripe = + stripe_alloc(sc, sc->mem_cache_client, grow); + + if (likely(stripe)) { + stripe_lru_add(stripe); + atomic_inc(&sc->stripes); + } else { + r = -ENOMEM; + break; + } + } + + return r ? r : sc_hash_resize(sc); +} + +/* Shrink stripe cache. */ +static int sc_shrink(struct stripe_cache *sc, unsigned stripes) +{ + int r = 0; + + /* Try to get unused stripe from LRU list. */ + while (stripes--) { + struct stripe *stripe; + + stripe = stripe_lru_pop(sc); + if (stripe) { + /* An LRU stripe may never have ios pending! */ + BUG_ON(stripe_io_ref(stripe)); + BUG_ON(stripe_ref(stripe)); + atomic_dec(&sc->stripes); + /* Remove from hash if on before deletion. */ + stripe_hash_del(stripe); + stripe_free(stripe, sc->mem_cache_client); + } else { + r = -ENOENT; + break; + } + } + + /* Check if stats are still sane. */ + if (atomic_read(&sc->active_stripes_max) > + atomic_read(&sc->stripes)) + atomic_set(&sc->active_stripes_max, 0); + + if (r) + return r; + + return atomic_read(&sc->stripes) ? sc_hash_resize(sc) : 0; +} + +/* Create stripe cache and recovery. */ +static int sc_init(struct raid_set *rs, unsigned stripes) +{ + unsigned i, r, rstripes; + struct stripe_cache *sc = &rs->sc; + struct stripe *stripe; + struct recover *rec = &rs->recover; + struct mapped_device *md; + struct gendisk *disk; + + /* Initialize lists and locks. */ + i = ARRAY_SIZE(sc->lists); + while (i--) + INIT_LIST_HEAD(sc->lists + i); + + INIT_LIST_HEAD(&rec->stripes); + + /* Initialize endio and LRU list locks. */ + i = NR_LOCKS; + while (i--) + spin_lock_init(sc->locks + i); + + /* Initialize atomic variables. */ + atomic_set(&sc->stripes, 0); + atomic_set(&sc->stripes_to_set, 0); + atomic_set(&sc->active_stripes, 0); + atomic_set(&sc->active_stripes_max, 0); /* REMOVEME: statistics. */ + + /* + * We need a runtime unique # to suffix the kmem cache name + * because we'll have one for each active RAID set. + */ + md = dm_table_get_md(rs->ti->table); + disk = dm_disk(md); + sprintf(sc->kc.name, "%s-%d", TARGET, disk->first_minor); + dm_put(md); + sc->kc.cache = kmem_cache_create(sc->kc.name, stripe_size(rs), + 0, 0, NULL); + if (!sc->kc.cache) + return -ENOMEM; + + /* Create memory cache client context for RAID stripe cache. */ + sc->mem_cache_client = + dm_mem_cache_client_create(stripes, rs->set.raid_devs, + chunk_pages(rs->set.io_size)); + if (IS_ERR(sc->mem_cache_client)) + return PTR_ERR(sc->mem_cache_client); + + /* Create memory cache client context for RAID recovery stripe(s). */ + rstripes = rec->recovery_stripes; + rec->mem_cache_client = + dm_mem_cache_client_create(rstripes, rs->set.raid_devs, + chunk_pages(rec->io_size)); + if (IS_ERR(rec->mem_cache_client)) + return PTR_ERR(rec->mem_cache_client); + + /* Create dm-io client context for IO stripes. */ + sc->dm_io_client = + dm_io_client_create(); + if (IS_ERR(sc->dm_io_client)) + return PTR_ERR(sc->dm_io_client); + + /* FIXME: intermingeled with stripe cache initialization. */ + /* Create dm-io client context for recovery stripes. */ + rec->dm_io_client = + dm_io_client_create(); + if (IS_ERR(rec->dm_io_client)) + return PTR_ERR(rec->dm_io_client); + + /* Allocate stripes for set recovery. */ + while (rstripes--) { + stripe = stripe_alloc(sc, rec->mem_cache_client, SC_KEEP); + if (!stripe) + return -ENOMEM; + + stripe->recover = kzalloc(sizeof(*stripe->recover), GFP_KERNEL); + if (!stripe->recover) { + stripe_free(stripe, rec->mem_cache_client); + return -ENOMEM; + } + + SetStripeRecover(stripe); + stripe->io.size = rec->io_size; + list_add_tail(stripe->lists + LIST_RECOVER, &rec->stripes); + /* Don't add recovery stripes to LRU list! */ + } + + /* + * Allocate the stripe objetcs from the + * cache and add them to the LRU list. + */ + r = sc_grow(sc, stripes, SC_KEEP); + if (!r) + atomic_set(&sc->stripes_last, stripes); + + return r; +} + +/* Destroy the stripe cache. */ +static void sc_exit(struct stripe_cache *sc) +{ + struct raid_set *rs = RS(sc); + + if (sc->kc.cache) { + stripe_recover_free(rs); + BUG_ON(sc_shrink(sc, atomic_read(&sc->stripes))); + kmem_cache_destroy(sc->kc.cache); + sc->kc.cache = NULL; + + if (sc->mem_cache_client && !IS_ERR(sc->mem_cache_client)) + dm_mem_cache_client_destroy(sc->mem_cache_client); + + if (sc->dm_io_client && !IS_ERR(sc->dm_io_client)) + dm_io_client_destroy(sc->dm_io_client); + + hash_exit(&sc->hash); + } +} + +/* + * Calculate RAID address + * + * Delivers tuple with the index of the data disk holding the chunk + * in the set, the parity disks index and the start of the stripe + * within the address space of the set (used as the stripe cache hash key). + */ +/* thx MD. */ +static struct raid_address *raid_address(struct raid_set *rs, sector_t sector, + struct raid_address *addr) +{ + sector_t stripe, tmp; + + /* + * chunk_number = sector / chunk_size + * stripe_number = chunk_number / data_devs + * di = stripe % data_devs; + */ + stripe = sector >> rs->set.chunk_shift; + addr->di = sector_div(stripe, rs->set.data_devs); + + switch (rs->set.raid_type->level) { + case raid4: + addr->pi = rs->set.pi; + goto check_shift_di; + case raid5: + tmp = stripe; + addr->pi = sector_div(tmp, rs->set.raid_devs); + + switch (rs->set.raid_type->algorithm) { + case left_asym: /* Left asymmetric. */ + addr->pi = rs->set.data_devs - addr->pi; + case right_asym: /* Right asymmetric. */ +check_shift_di: + if (addr->di >= addr->pi) + addr->di++; + break; + case left_sym: /* Left symmetric. */ + addr->pi = rs->set.data_devs - addr->pi; + case right_sym: /* Right symmetric. */ + addr->di = (addr->pi + addr->di + 1) % + rs->set.raid_devs; + break; + case none: /* Ain't happen: RAID4 algorithm placeholder. */ + BUG(); + } + } + + /* + * Start offset of the stripes chunk on any single device of the RAID + * set, adjusted in case io size differs from chunk size. + */ + addr->key = (stripe << rs->set.chunk_shift) + + (sector & rs->set.io_inv_mask); + return addr; +} + +/* + * Copy data across between stripe pages and bio vectors. + * + * Pay attention to data alignment in stripe and bio pages. + */ +static void bio_copy_page_list(int rw, struct stripe *stripe, + struct page_list *pl, struct bio *bio) +{ + unsigned i, page_offset; + void *page_addr; + struct raid_set *rs = RS(stripe->sc); + struct bio_vec *bv; + + /* Get start page in page list for this sector. */ + i = (bio->bi_sector & rs->set.io_mask) / SECTORS_PER_PAGE; + pl = pl_elem(pl, i); + BUG_ON(!pl); + BUG_ON(!pl->page); + + page_addr = page_address(pl->page); + page_offset = to_bytes(bio->bi_sector & (SECTORS_PER_PAGE - 1)); + + /* Walk all segments and copy data across between bio_vecs and pages. */ + bio_for_each_segment(bv, bio, i) { + int len = bv->bv_len, size; + unsigned bio_offset = 0; + void *bio_addr = __bio_kmap_atomic(bio, i, KM_USER0); +redo: + size = (page_offset + len > PAGE_SIZE) ? + PAGE_SIZE - page_offset : len; + + if (rw == READ) + memcpy(bio_addr + bio_offset, + page_addr + page_offset, size); + else + memcpy(page_addr + page_offset, + bio_addr + bio_offset, size); + + page_offset += size; + if (page_offset == PAGE_SIZE) { + /* + * We reached the end of the chunk page -> + * need to refer to the next one to copy more data. + */ + len -= size; + if (len) { + /* Get next page. */ + pl = pl->next; + BUG_ON(!pl); + BUG_ON(!pl->page); + page_addr = page_address(pl->page); + page_offset = 0; + bio_offset += size; + /* REMOVEME: statistics. */ + atomic_inc(rs->stats + S_BIO_COPY_PL_NEXT); + goto redo; + } + } + + __bio_kunmap_atomic(bio_addr, KM_USER0); + } +} + +/* + * Xor optimization macros. + */ +/* Xor data pointer declaration and initialization macros. */ +#define DECLARE_2 unsigned long *d0 = data[0], *d1 = data[1] +#define DECLARE_3 DECLARE_2, *d2 = data[2] +#define DECLARE_4 DECLARE_3, *d3 = data[3] +#define DECLARE_5 DECLARE_4, *d4 = data[4] +#define DECLARE_6 DECLARE_5, *d5 = data[5] +#define DECLARE_7 DECLARE_6, *d6 = data[6] +#define DECLARE_8 DECLARE_7, *d7 = data[7] + +/* Xor unrole macros. */ +#define D2(n) d0[n] = d0[n] ^ d1[n] +#define D3(n) D2(n) ^ d2[n] +#define D4(n) D3(n) ^ d3[n] +#define D5(n) D4(n) ^ d4[n] +#define D6(n) D5(n) ^ d5[n] +#define D7(n) D6(n) ^ d6[n] +#define D8(n) D7(n) ^ d7[n] + +#define X_2(macro, offset) macro(offset); macro(offset + 1); +#define X_4(macro, offset) X_2(macro, offset); X_2(macro, offset + 2); +#define X_8(macro, offset) X_4(macro, offset); X_4(macro, offset + 4); +#define X_16(macro, offset) X_8(macro, offset); X_8(macro, offset + 8); +#define X_32(macro, offset) X_16(macro, offset); X_16(macro, offset + 16); +#define X_64(macro, offset) X_32(macro, offset); X_32(macro, offset + 32); + +/* Define a _xor_#chunks_#xors_per_run() function. */ +#define _XOR(chunks, xors_per_run) \ +static void _xor ## chunks ## _ ## xors_per_run(unsigned long **data) \ +{ \ + unsigned end = XOR_SIZE / sizeof(data[0]), i; \ + DECLARE_ ## chunks; \ +\ + for (i = 0; i < end; i += xors_per_run) { \ + X_ ## xors_per_run(D ## chunks, i); \ + } \ +} + +/* Define xor functions for 2 - 8 chunks and xors per run. */ +#define MAKE_XOR_PER_RUN(xors_per_run) \ + _XOR(2, xors_per_run); _XOR(3, xors_per_run); \ + _XOR(4, xors_per_run); _XOR(5, xors_per_run); \ + _XOR(6, xors_per_run); _XOR(7, xors_per_run); \ + _XOR(8, xors_per_run); + +MAKE_XOR_PER_RUN(8) /* Define _xor_*_8() functions. */ +MAKE_XOR_PER_RUN(16) /* Define _xor_*_16() functions. */ +MAKE_XOR_PER_RUN(32) /* Define _xor_*_32() functions. */ +MAKE_XOR_PER_RUN(64) /* Define _xor_*_64() functions. */ + +#define MAKE_XOR(xors_per_run) \ +struct { \ + void (*f)(unsigned long **); \ +} static xor_funcs ## xors_per_run[] = { \ + { NULL }, /* NULL pointers to optimize indexing in xor(). */ \ + { NULL }, \ + { _xor2_ ## xors_per_run }, \ + { _xor3_ ## xors_per_run }, \ + { _xor4_ ## xors_per_run }, \ + { _xor5_ ## xors_per_run }, \ + { _xor6_ ## xors_per_run }, \ + { _xor7_ ## xors_per_run }, \ + { _xor8_ ## xors_per_run }, \ +}; \ +\ +static void xor_ ## xors_per_run(unsigned n, unsigned long **data) \ +{ \ + /* Call respective function for amount of chunks. */ \ + xor_funcs ## xors_per_run[n].f(data); \ +} + +/* Define xor_8() - xor_64 functions. */ +MAKE_XOR(8) +MAKE_XOR(16) +MAKE_XOR(32) +MAKE_XOR(64) + +/* Maximum number of chunks, which can be xor'ed in one go. */ +#define XOR_CHUNKS_MAX (ARRAY_SIZE(xor_funcs8) - 1) + +static void xor_blocks_wrapper(unsigned n, unsigned long **data) +{ + BUG_ON(n < 2 || n > MAX_XOR_BLOCKS + 1); + xor_blocks(n - 1, XOR_SIZE, (void *) data[0], (void **) data + 1); +} + +struct xor_func { + xor_function_t f; + const char *name; +} static xor_funcs[] = { + { xor_8, "xor_8" }, + { xor_16, "xor_16" }, + { xor_32, "xor_32" }, + { xor_64, "xor_64" }, + { xor_blocks_wrapper, "xor_blocks" }, +}; + +/* + * Check, if chunk has to be xored in/out: + * + * o if writes are queued + * o if writes are merged + * o if stripe is to be reconstructed + * o if recovery stripe + */ +static inline int chunk_must_xor(struct stripe_chunk *chunk) +{ + if (ChunkUptodate(chunk)) { + BUG_ON(!bio_list_empty(BL_CHUNK(chunk, WRITE_QUEUED)) && + !bio_list_empty(BL_CHUNK(chunk, WRITE_MERGED))); + + if (!bio_list_empty(BL_CHUNK(chunk, WRITE_QUEUED)) || + !bio_list_empty(BL_CHUNK(chunk, WRITE_MERGED))) + return 1; + + if (StripeReconstruct(chunk->stripe) || + StripeRecover(chunk->stripe)) + return 1; + } + + return 0; +} + +/* + * Calculate crc. + * + * This indexes into the chunks of a stripe and their pages. + * + * All chunks will be xored into the indexed (@pi) + * chunk in maximum groups of xor.chunks. + * + */ +static void xor(struct stripe *stripe, unsigned pi, unsigned sector) +{ + struct raid_set *rs = RS(stripe->sc); + unsigned max_chunks = rs->xor.chunks, n = 1, + o = sector / SECTORS_PER_PAGE, /* Offset into the page_list. */ + p = rs->set.raid_devs; + unsigned long **d = rs->data; + xor_function_t xor_f = rs->xor.f->f; + + BUG_ON(sector > stripe->io.size); + + /* Address of parity page to xor into. */ + d[0] = page_address(pl_elem(PL(stripe, pi), o)->page); + + while (p--) { + /* Preset pointers to data pages. */ + if (p != pi && chunk_must_xor(CHUNK(stripe, p))) + d[n++] = page_address(pl_elem(PL(stripe, p), o)->page); + + /* If max chunks -> xor. */ + if (n == max_chunks) { + xor_f(n, d); + n = 1; + } + } + + /* If chunks -> xor. */ + if (n > 1) + xor_f(n, d); +} + +/* Common xor loop through all stripe page lists. */ +static void common_xor(struct stripe *stripe, sector_t count, + unsigned off, unsigned pi) +{ + unsigned sector; + + BUG_ON(!count); + for (sector = off; sector < count; sector += SECTORS_PER_PAGE) + xor(stripe, pi, sector); + + /* Set parity page uptodate and clean. */ + chunk_set(CHUNK(stripe, pi), CLEAN); + atomic_inc(RS(stripe->sc)->stats + S_XORS); /* REMOVEME: statistics. */ +} + +/* + * Calculate parity sectors on intact stripes. + * + * Need to calculate raid address for recover stripe, because its + * chunk sizes differs and is typically larger than io chunk size. + */ +static void parity_xor(struct stripe *stripe) +{ + struct raid_set *rs = RS(stripe->sc); + unsigned chunk_size = rs->set.chunk_size, io_size = stripe->io.size, + xor_size = chunk_size > io_size ? io_size : chunk_size; + sector_t off; + + /* This can be the recover stripe with a larger io size. */ + for (off = 0; off < io_size; off += xor_size) { + /* + * Recover stripe is likely bigger than regular io + * ones and has no precalculated parity disk index -> + * need to calculate RAID address. + */ + if (unlikely(StripeRecover(stripe))) { + struct raid_address addr; + + raid_address(rs, + (stripe->key + off) * rs->set.data_devs, + &addr); + stripe->idx.parity = addr.pi; + stripe_zero_pl_part(stripe, addr.pi, off, xor_size); + } + + common_xor(stripe, xor_size, off, stripe->idx.parity); + chunk_set(CHUNK(stripe, stripe->idx.parity), DIRTY); + } +} + +/* Reconstruct missing chunk. */ +static void stripe_reconstruct(struct stripe *stripe) +{ + struct raid_set *rs = RS(stripe->sc); + int p = rs->set.raid_devs, pr = stripe->idx.recover; + + BUG_ON(pr < 0); + + /* Check if all but the chunk to be reconstructed are uptodate. */ + while (p--) + BUG_ON(p != pr && !ChunkUptodate(CHUNK(stripe, p))); + + /* REMOVEME: statistics. */ + atomic_inc(rs->stats + (RSDegraded(rs) ? S_RECONSTRUCT_EI : + S_RECONSTRUCT_DEV)); + /* Zero chunk to be reconstructed. */ + stripe_zero_chunk(stripe, pr); + common_xor(stripe, stripe->io.size, 0, pr); + stripe->idx.recover = -1; +} + +/* + * Recovery io throttling + */ +/* Conditionally reset io counters. */ +static int recover_io_reset(struct raid_set *rs) +{ + unsigned long j = jiffies; + + /* Pay attention to jiffies overflows. */ + if (j > rs->recover.last_jiffies + HZ / 20 || + j < rs->recover.last_jiffies) { + atomic_set(rs->recover.io_count + IO_WORK, 0); + atomic_set(rs->recover.io_count + IO_RECOVER, 0); + rs->recover.last_jiffies = j; + return 1; + } + + return 0; +} + +/* Count ios. */ +static void recover_io_count(struct stripe *stripe) +{ + struct raid_set *rs = RS(stripe->sc); + + recover_io_reset(rs); + atomic_inc(rs->recover.io_count + + (StripeRecover(stripe) ? IO_RECOVER : IO_WORK)); +} + +/* Try getting a stripe either from the hash or from the LRU list. */ +static struct stripe *stripe_find(struct raid_set *rs, + struct raid_address *addr) +{ + int r; + struct stripe_cache *sc = &rs->sc; + struct stripe *stripe; + + /* Try stripe from hash. */ + stripe = stripe_lookup(sc, addr->key); + if (stripe) { + r = stripe_get(stripe); + if (r) + goto get_lock_failed; + + atomic_inc(rs->stats + S_HITS_1ST); /* REMOVEME: statistics. */ + } else { + /* Not in hash -> try to get an LRU stripe. */ + stripe = stripe_lru_pop(sc); + if (stripe) { + /* + * An LRU stripe may not be referenced + * and may never have ios pending! + */ + BUG_ON(stripe_ref(stripe)); + BUG_ON(stripe_io_ref(stripe)); + + /* Remove from hash if on before reuse. */ + stripe_hash_del(stripe); + + /* Invalidate before reinserting with changed key. */ + stripe_invalidate(stripe); + + stripe->key = addr->key; + stripe->region = dm_rh_sector_to_region(rs->recover.rh, + addr->key); + stripe->idx.parity = addr->pi; + r = stripe_get(stripe); + if (r) + goto get_lock_failed; + + /* Insert stripe into the stripe hash. */ + stripe_insert(&sc->hash, stripe); + /* REMOVEME: statistics. */ + atomic_inc(rs->stats + S_INSCACHE); + } + } + + return stripe; + +get_lock_failed: + stripe_put(stripe); + return NULL; +} + +/* + * Process end io + * + * I need to do it here because I can't in interrupt + */ +/* End io all bios on a bio list. */ +static void bio_list_endio(struct stripe *stripe, struct bio_list *bl, + int p, int error) +{ + struct raid_set *rs = RS(stripe->sc); + struct bio *bio; + struct page_list *pl = PL(stripe, p); + struct stripe_chunk *chunk = CHUNK(stripe, p); + + /* Update region counters. */ + while ((bio = bio_list_pop(bl))) { + if (bio_data_dir(bio) == WRITE) + /* Drop io pending count for any writes. */ + dm_rh_dec(rs->recover.rh, stripe->region); + else if (!error) + /* Copy data accross. */ + bio_copy_page_list(READ, stripe, pl, bio); + + bio_endio(bio, error); + + /* REMOVEME: statistics. */ + atomic_inc(rs->stats + (bio_data_dir(bio) == READ ? + S_BIOS_ENDIO_READ : S_BIOS_ENDIO_WRITE)); + + chunk_put(chunk); + stripe_put(stripe); + io_put(rs); /* Wake any suspend waiters on last bio. */ + } +} + +/* + * End io all reads/writes on a stripe copying + * read data accross from stripe to bios and + * decrementing region counters for writes. + * + * Processing of ios depeding on state: + * o no chunk error -> endio ok + * o degraded: + * - chunk error and read -> ignore to be requeued + * - chunk error and write -> endio ok + * o dead (more than parity_devs failed) and chunk_error-> endio failed + */ +static void stripe_endio(int rw, struct stripe *stripe) +{ + struct raid_set *rs = RS(stripe->sc); + unsigned p = rs->set.raid_devs; + int write = (rw != READ); + + while (p--) { + struct stripe_chunk *chunk = CHUNK(stripe, p); + struct bio_list *bl; + + BUG_ON(ChunkLocked(chunk)); + + bl = BL_CHUNK(chunk, rw); + if (bio_list_empty(bl)) + continue; + + if (unlikely(ChunkError(chunk) || !ChunkUptodate(chunk))) { + /* RAID set dead. */ + if (unlikely(RSDead(rs))) + bio_list_endio(stripe, bl, p, -EIO); + /* RAID set degraded. */ + else if (write) + bio_list_endio(stripe, bl, p, 0); + } else { + BUG_ON(!RSDegraded(rs) && ChunkDirty(chunk)); + bio_list_endio(stripe, bl, p, 0); + } + } +} + +/* Fail all ios hanging off all bio lists of a stripe. */ +static void stripe_fail_io(struct stripe *stripe) +{ + struct raid_set *rs = RS(stripe->sc); + unsigned p = rs->set.raid_devs; + + while (p--) { + struct stripe_chunk *chunk = CHUNK(stripe, p); + int i = ARRAY_SIZE(chunk->bl); + + /* Fail all bios on all bio lists of the stripe. */ + while (i--) { + struct bio_list *bl = chunk->bl + i; + + if (!bio_list_empty(bl)) + bio_list_endio(stripe, bl, p, -EIO); + } + } + + /* Put stripe on LRU list. */ + BUG_ON(stripe_io_ref(stripe)); + BUG_ON(stripe_ref(stripe)); +} + +/* Unlock all required chunks. */ +static void stripe_chunks_unlock(struct stripe *stripe) +{ + unsigned p = RS(stripe->sc)->set.raid_devs; + struct stripe_chunk *chunk; + + while (p--) { + chunk = CHUNK(stripe, p); + + if (TestClearChunkUnlock(chunk)) + ClearChunkLocked(chunk); + } +} + +/* + * Queue reads and writes to a stripe by hanging + * their bios off the stripesets read/write lists. + */ +static int stripe_queue_bio(struct raid_set *rs, struct bio *bio, + struct bio_list *reject) +{ + struct raid_address addr; + struct stripe *stripe; + + stripe = stripe_find(rs, raid_address(rs, bio->bi_sector, &addr)); + if (stripe) { + int r = 0, rw = bio_data_dir(bio); + + /* Distinguish reads and writes. */ + bio_list_add(BL(stripe, addr.di, rw), bio); + + if (rw == READ) + /* REMOVEME: statistics. */ + atomic_inc(rs->stats + S_BIOS_ADDED_READ); + else { + /* Inrement pending write count on region. */ + dm_rh_inc(rs->recover.rh, stripe->region); + r = 1; + + /* REMOVEME: statistics. */ + atomic_inc(rs->stats + S_BIOS_ADDED_WRITE); + } + + /* + * Put on io (flush) list in case of + * initial bio queued to chunk. + */ + if (chunk_get(CHUNK(stripe, addr.di)) == 1) + stripe_flush_add(stripe); + + return r; + } + + /* Got no stripe from cache or failed to lock it -> reject bio. */ + bio_list_add(reject, bio); + atomic_inc(rs->stats + S_IOS_POST); /* REMOVEME: statistics. */ + return 0; +} + +/* + * Handle all stripes by handing them to the daemon, because we can't + * map their chunk pages to copy the data in interrupt context. + * + * We don't want to handle them here either, while interrupts are disabled. + */ + +/* Read/write endio function for dm-io (interrupt context). */ +static void endio(unsigned long error, void *context) +{ + struct stripe_chunk *chunk = context; + + if (unlikely(error)) { + chunk_set(chunk, ERROR); + /* REMOVEME: statistics. */ + atomic_inc(RS(chunk->stripe->sc)->stats + S_STRIPE_ERROR); + } else + chunk_set(chunk, CLEAN); + + /* + * For recovery stripes, I need to reset locked locked + * here, because those aren't processed in do_endios(). + */ + if (unlikely(StripeRecover(chunk->stripe))) + ClearChunkLocked(chunk); + else + SetChunkUnlock(chunk); + + /* Indirectly puts stripe on cache's endio list via stripe_io_put(). */ + stripe_put_references(chunk->stripe); +} + +/* Read/Write a chunk asynchronously. */ +static void stripe_chunk_rw(struct stripe *stripe, unsigned p) +{ + struct stripe_cache *sc = stripe->sc; + struct raid_set *rs = RS(sc); + struct dm_mem_cache_object *obj = stripe->obj + p; + struct page_list *pl = obj->pl; + struct stripe_chunk *chunk = CHUNK(stripe, p); + struct raid_dev *dev = rs->dev + p; + struct dm_io_region io = { + .bdev = dev->dev->bdev, + .sector = stripe->key, + .count = stripe->io.size, + }; + struct dm_io_request control = { + .bi_rw = ChunkDirty(chunk) ? WRITE : READ, + .mem = { + .type = DM_IO_PAGE_LIST, + .ptr.pl = pl, + .offset = 0, + }, + .notify = { + .fn = endio, + .context = chunk, + }, + .client = StripeRecover(stripe) ? rs->recover.dm_io_client : + sc->dm_io_client, + }; + + BUG_ON(ChunkLocked(chunk)); + BUG_ON(!ChunkUptodate(chunk) && ChunkDirty(chunk)); + BUG_ON(ChunkUptodate(chunk) && !ChunkDirty(chunk)); + + /* + * Don't rw past end of device, which can happen, because + * typically sectors_per_dev isn't divisible by io_size. + */ + if (unlikely(io.sector + io.count > rs->set.sectors_per_dev)) + io.count = rs->set.sectors_per_dev - io.sector; + + BUG_ON(!io.count); + io.sector += dev->start; /* Add <offset>. */ + if (RSRecover(rs)) + recover_io_count(stripe); /* Recovery io accounting. */ + + /* REMOVEME: statistics. */ + atomic_inc(rs->stats + (ChunkDirty(chunk) ? S_DM_IO_WRITE : + S_DM_IO_READ)); + SetChunkLocked(chunk); + SetDevIoQueued(dev); + BUG_ON(dm_io(&control, 1, &io, NULL)); +} + +/* + * Write dirty or read not uptodate page lists of a stripe. + */ +static int stripe_chunks_rw(struct stripe *stripe) +{ + int r; + struct raid_set *rs = RS(stripe->sc); + + /* + * Increment the pending count on the stripe + * first, so that we don't race in endio(). + * + * An inc (IO) is needed for any chunk unless !ChunkIo(chunk): + * + * o not uptodate + * o dirtied by writes merged + * o dirtied by parity calculations + */ + r = for_each_io_dev(stripe, stripe_get_references); + if (r) { + /* Io needed: chunks are either not uptodate or dirty. */ + int max; /* REMOVEME: */ + struct stripe_cache *sc = &rs->sc; + + /* Submit actual io. */ + for_each_io_dev(stripe, stripe_chunk_rw); + + /* REMOVEME: statistics */ + max = sc_active(sc); + if (atomic_read(&sc->active_stripes_max) < max) + atomic_set(&sc->active_stripes_max, max); + + atomic_inc(rs->stats + S_FLUSHS); + /* END REMOVEME: statistics */ + } + + return r; +} + +/* Merge in all writes hence dirtying respective chunks. */ +static void stripe_merge_writes(struct stripe *stripe) +{ + unsigned p = RS(stripe->sc)->set.raid_devs; + + while (p--) { + struct stripe_chunk *chunk = CHUNK(stripe, p); + struct bio_list *write = BL_CHUNK(chunk, WRITE_QUEUED); + + if (!bio_list_empty(write)) { + struct bio *bio; + struct page_list *pl = stripe->obj[p].pl; + + /* + * We can play with the lists without holding a lock, + * because it is just us accessing them anyway. + */ + bio_list_for_each(bio, write) + bio_copy_page_list(WRITE, stripe, pl, bio); + + bio_list_merge(BL_CHUNK(chunk, WRITE_MERGED), write); + bio_list_init(write); + chunk_set(chunk, DIRTY); + } + } +} + +/* Queue all writes to get merged. */ +static int stripe_queue_writes(struct stripe *stripe) +{ + int r = 0; + unsigned p = RS(stripe->sc)->set.raid_devs; + + while (p--) { + struct stripe_chunk *chunk = CHUNK(stripe, p); + struct bio_list *write = BL_CHUNK(chunk, WRITE); + + if (!bio_list_empty(write)) { + bio_list_merge(BL_CHUNK(chunk, WRITE_QUEUED), write); + bio_list_init(write); +SetChunkIo(chunk); + r = 1; + } + } + + return r; +} + + +/* Check, if a chunk gets completely overwritten. */ +static int stripe_check_chunk_overwrite(struct stripe *stripe, unsigned p) +{ + unsigned sectors = 0; + struct bio *bio; + struct bio_list *bl = BL(stripe, p, WRITE_QUEUED); + + bio_list_for_each(bio, bl) + sectors += bio_sectors(bio); + + BUG_ON(sectors > RS(stripe->sc)->set.io_size); + return sectors == RS(stripe->sc)->set.io_size; +} + +/* + * Avoid io on broken/reconstructed drive in order to + * reconstruct date on endio. + * + * (*1*) We set StripeReconstruct() in here, so that _do_endios() + * will trigger a reconstruct call before resetting it. + */ +static int stripe_chunk_set_io_flags(struct stripe *stripe, int pr) +{ + struct stripe_chunk *chunk = CHUNK(stripe, pr); + + /* + * Allow io on all chunks but the indexed one, + * because we're either degraded or prohibit it + * on the one for later reconstruction. + */ + /* Includes ClearChunkIo(), ClearChunkUptodate(). */ + stripe_chunk_invalidate(chunk); + stripe->idx.recover = pr; + SetStripeReconstruct(stripe); + + /* REMOVEME: statistics. */ + atomic_inc(RS(stripe->sc)->stats + S_PROHIBITCHUNKIO); + return -EPERM; +} + +/* Chunk locked/uptodate and device failed tests. */ +static struct stripe_chunk * +stripe_chunk_check(struct stripe *stripe, unsigned p, unsigned *chunks_uptodate) +{ + struct raid_set *rs = RS(stripe->sc); + struct stripe_chunk *chunk = CHUNK(stripe, p); + + /* Can't access active chunks. */ + if (ChunkLocked(chunk)) { + /* REMOVEME: statistics. */ + atomic_inc(rs->stats + S_CHUNK_LOCKED); + return NULL; + } + + /* Can't access broken devive. */ + if (ChunkError(chunk) || DevFailed(rs->dev + p)) + return NULL; + + /* Can access uptodate chunks. */ + if (ChunkUptodate(chunk)) { + (*chunks_uptodate)++; + return NULL; + } + + return chunk; +} + +/* + * Degraded/reconstruction mode. + * + * Check stripe state to figure which chunks don't need IO. + * + * Returns 0 for fully operational, -EPERM for degraded/resynchronizing. + */ +static int stripe_check_reconstruct(struct stripe *stripe) +{ + struct raid_set *rs = RS(stripe->sc); + + if (RSDead(rs)) { + ClearStripeReconstruct(stripe); + ClearStripeReconstructed(stripe); + stripe_allow_io(stripe); + return 0; + } + + /* Avoid further reconstruction setting, when already set. */ + if (StripeReconstruct(stripe)) { + /* REMOVEME: statistics. */ + atomic_inc(rs->stats + S_RECONSTRUCT_SET); + return -EBUSY; + } + + /* Initially allow io on all chunks. */ + stripe_allow_io(stripe); + + /* Return if stripe is already reconstructed. */ + if (StripeReconstructed(stripe)) { + atomic_inc(rs->stats + S_RECONSTRUCTED); + return 0; + } + + /* + * Degraded/reconstruction mode (device failed) -> + * avoid io on the failed device. + */ + if (unlikely(RSDegraded(rs))) { + /* REMOVEME: statistics. */ + atomic_inc(rs->stats + S_DEGRADED); + /* Allow IO on all devices but the dead one. */ + BUG_ON(rs->set.ei < 0); + return stripe_chunk_set_io_flags(stripe, rs->set.ei); + } else { + int sync, pi = dev_for_parity(stripe, &sync); + + /* + * Reconstruction mode (ie. a particular (replaced) device or + * some (rotating) parity chunk is being resynchronized) -> + * o make sure all needed chunks are read in + * o writes are allowed to go through + */ + if (!sync) { + /* REMOVEME: statistics. */ + atomic_inc(rs->stats + S_NOSYNC); + /* Allow IO on all devs but the one to reconstruct. */ + return stripe_chunk_set_io_flags(stripe, pi); + } + } + + return 0; +} + +/* + * Check, if stripe is ready to merge writes. + * I.e. if all chunks present to allow to merge bios. + * + * We prohibit io on: + * + * o chunks without bios + * o chunks which get completely written over + */ +static int stripe_merge_possible(struct stripe *stripe, int nosync) +{ + struct raid_set *rs = RS(stripe->sc); + unsigned chunks_overwrite = 0, chunks_prohibited = 0, + chunks_uptodate = 0, p = rs->set.raid_devs; + + /* Walk all chunks. */ + while (p--) { + struct stripe_chunk *chunk; + + /* Prohibit io on broken devices. */ + if (DevFailed(rs->dev + p)) { + chunk = CHUNK(stripe, p); + goto prohibit_io; + } + + /* We can't optimize any further if no chunk. */ + chunk = stripe_chunk_check(stripe, p, &chunks_uptodate); + if (!chunk || nosync) + continue; + + /* + * We have a chunk, which is not uptodate. + * + * If this is not parity and we don't have + * reads queued, we can optimize further. + */ + if (p != stripe->idx.parity && + bio_list_empty(BL_CHUNK(chunk, READ)) && + bio_list_empty(BL_CHUNK(chunk, WRITE_MERGED))) { + if (bio_list_empty(BL_CHUNK(chunk, WRITE_QUEUED))) + goto prohibit_io; + else if (RSCheckOverwrite(rs) && + stripe_check_chunk_overwrite(stripe, p)) + /* Completely overwritten chunk. */ + chunks_overwrite++; + } + + /* Allow io for chunks with bios and overwritten ones. */ + SetChunkIo(chunk); + continue; + +prohibit_io: + /* No io for broken devices or for chunks w/o bios. */ + ClearChunkIo(chunk); + chunks_prohibited++; + /* REMOVEME: statistics. */ + atomic_inc(RS(stripe->sc)->stats + S_PROHIBITCHUNKIO); + } + + /* All data chunks will get written over. */ + if (chunks_overwrite == rs->set.data_devs) + atomic_inc(rs->stats + S_OVERWRITE); /* REMOVEME: statistics.*/ + else if (chunks_uptodate + chunks_prohibited < rs->set.raid_devs) { + /* We don't have enough chunks to merge. */ + atomic_inc(rs->stats + S_CANT_MERGE); /* REMOVEME: statistics.*/ + return -EPERM; + } + + /* + * If we have all chunks up to date or overwrite them, we + * just zero the parity chunk and let stripe_rw() recreate it. + */ + if (chunks_uptodate == rs->set.raid_devs || + chunks_overwrite == rs->set.data_devs) { + stripe_zero_chunk(stripe, stripe->idx.parity); + BUG_ON(StripeReconstruct(stripe)); + SetStripeReconstruct(stripe); /* Enforce xor in caller. */ + } else { + /* + * With less chunks, we xor parity out. + * + * (*4*) We rely on !StripeReconstruct() in chunk_must_xor(), + * so that only chunks with queued or merged writes + * are being xored. + */ + parity_xor(stripe); + } + + /* + * We do have enough chunks to merge. + * All chunks are uptodate or get written over. + */ + atomic_inc(rs->stats + S_CAN_MERGE); /* REMOVEME: statistics. */ + return 0; +} + +/* + * Avoid reading chunks in case we're fully operational. + * + * We prohibit io on any chunks without bios but the parity chunk. + */ +static void stripe_avoid_reads(struct stripe *stripe) +{ + struct raid_set *rs = RS(stripe->sc); + unsigned dummy = 0, p = rs->set.raid_devs; + + /* Walk all chunks. */ + while (p--) { + struct stripe_chunk *chunk = + stripe_chunk_check(stripe, p, &dummy); + + if (!chunk) + continue; + + /* If parity or any bios pending -> allow io. */ + if (chunk_ref(chunk) || p == stripe->idx.parity) + SetChunkIo(chunk); + else { + ClearChunkIo(chunk); + /* REMOVEME: statistics. */ + atomic_inc(RS(stripe->sc)->stats + S_PROHIBITCHUNKIO); + } + } +} + +/* + * Read/write a stripe. + * + * All stripe read/write activity goes through this function + * unless recovery, which has to call stripe_chunk_rw() directly. + * + * Make sure we don't try already merged stripes in order + * to avoid data corruption. + * + * Check the state of the RAID set and if degraded (or + * resynchronizing for reads), read in all other chunks but + * the one on the dead/resynchronizing device in order to be + * able to reconstruct the missing one in _do_endios(). + * + * Can be called on active stripes in order + * to dispatch new io on inactive chunks. + * + * States to cover: + * o stripe to read and/or write + * o stripe with error to reconstruct + */ +static void stripe_rw(struct stripe *stripe) +{ + int nosync, r; + struct raid_set *rs = RS(stripe->sc); + + /* + * Check, if a chunk needs to be reconstructed + * because of a degraded set or a region out of sync. + */ + nosync = stripe_check_reconstruct(stripe); + switch (nosync) { + case -EBUSY: + return; /* Wait for stripe reconstruction to finish. */ + case -EPERM: + goto io; + } + + /* + * If we don't have merged writes pending, we can schedule + * queued writes to be merged next without corrupting data. + */ + if (!StripeMerged(stripe)) { + r = stripe_queue_writes(stripe); + if (r) + /* Writes got queued -> flag RBW. */ + SetStripeRBW(stripe); + } + + /* + * Merge all writes hanging off uptodate/overwritten + * chunks of the stripe. + */ + if (StripeRBW(stripe)) { + r = stripe_merge_possible(stripe, nosync); + if (!r) { /* Merge possible. */ + struct stripe_chunk *chunk; + + /* + * I rely on valid parity in order + * to xor a fraction of chunks out + * of parity and back in. + */ + stripe_merge_writes(stripe); /* Merge writes in. */ + parity_xor(stripe); /* Update parity. */ + ClearStripeReconstruct(stripe); /* Reset xor enforce. */ + SetStripeMerged(stripe); /* Writes merged. */ + ClearStripeRBW(stripe); /* Disable RBW. */ + + /* + * REMOVEME: sanity check on parity chunk + * states after writes got merged. + */ + chunk = CHUNK(stripe, stripe->idx.parity); + BUG_ON(ChunkLocked(chunk)); + BUG_ON(!ChunkUptodate(chunk)); + BUG_ON(!ChunkDirty(chunk)); + BUG_ON(!ChunkIo(chunk)); + } + } else if (!nosync && !StripeMerged(stripe)) + /* Read avoidance if not degraded/resynchronizing/merged. */ + stripe_avoid_reads(stripe); + +io: + /* Now submit any reads/writes for non-uptodate or dirty chunks. */ + r = stripe_chunks_rw(stripe); + if (!r) { + /* + * No io submitted because of chunk io + * prohibited or locked chunks/failed devices + * -> push to end io list for processing. + */ + stripe_endio_push(stripe); + atomic_inc(rs->stats + S_NO_RW); /* REMOVEME: statistics. */ + } +} + +/* + * Recovery functions + */ +/* Read a stripe off a raid set for recovery. */ +static int stripe_recover_read(struct stripe *stripe, int pi) +{ + BUG_ON(stripe_io_ref(stripe)); + + /* Invalidate all chunks so that they get read in. */ + stripe_chunks_invalidate(stripe); + stripe_allow_io(stripe); /* Allow io on all recovery chunks. */ + + /* + * If we are reconstructing a perticular device, we can avoid + * reading the respective chunk in, because we're going to + * reconstruct it anyway. + * + * We can't do that for resynchronization of rotating parity, + * because the recovery stripe chunk size is typically larger + * than the sets chunk size. + */ + if (pi > -1) + ClearChunkIo(CHUNK(stripe, pi)); + + return stripe_chunks_rw(stripe); +} + +/* Write a stripe to a raid set for recovery. */ +static int stripe_recover_write(struct stripe *stripe, int pi) +{ + BUG_ON(stripe_io_ref(stripe)); + + /* + * If this is a reconstruct of a particular device, then + * reconstruct the respective chunk, else create parity chunk. + */ + if (pi > -1) { + stripe_zero_chunk(stripe, pi); + common_xor(stripe, stripe->io.size, 0, pi); + chunk_set(CHUNK(stripe, pi), DIRTY); + } else + parity_xor(stripe); + + return stripe_chunks_rw(stripe); +} + +/* Read/write a recovery stripe. */ +static int stripe_recover_rw(struct stripe *stripe) +{ + int r = 0, sync = 0; + + /* Read/write flip-flop. */ + if (TestClearStripeRBW(stripe)) { + SetStripeMerged(stripe); + stripe->key = stripe->recover->pos; + r = stripe_recover_read(stripe, dev_for_parity(stripe, &sync)); + BUG_ON(!r); + } else if (TestClearStripeMerged(stripe)) { + r = stripe_recover_write(stripe, dev_for_parity(stripe, &sync)); + BUG_ON(!r); + } + + BUG_ON(sync); + return r; +} + +/* Recover bandwidth available ?. */ +static int recover_bandwidth(struct raid_set *rs) +{ + int r, work; + + /* On reset or when bios delayed -> allow recovery. */ + r = recover_io_reset(rs); + if (r || RSBandwidth(rs)) + goto out; + + work = atomic_read(rs->recover.io_count + IO_WORK); + if (work) { + /* Pay attention to larger recover stripe size. */ + int recover = atomic_read(rs->recover.io_count + IO_RECOVER) * + rs->recover.io_size / rs->set.io_size; + + /* + * Don't use more than given bandwidth + * of the work io for recovery. + */ + if (recover > work / rs->recover.bandwidth_work) { + /* REMOVEME: statistics. */ + atomic_inc(rs->stats + S_NO_BANDWIDTH); + return 0; + } + } + +out: + atomic_inc(rs->stats + S_BANDWIDTH); /* REMOVEME: statistics. */ + return 1; +} + +/* Try to get a region to recover. */ +static int stripe_recover_get_region(struct stripe *stripe) +{ + struct raid_set *rs = RS(stripe->sc); + struct recover *rec = &rs->recover; + struct recover_addr *addr = stripe->recover; + struct dm_dirty_log *dl = rec->dl; + struct dm_rh_client *rh = rec->rh; + + BUG_ON(!dl); + BUG_ON(!rh); + + /* Return, that we have region first to finish it during suspension. */ + if (addr->reg) + return 1; + + if (RSSuspend(rs)) + return -EPERM; + + if (dl->type->get_sync_count(dl) >= rec->nr_regions) + return -ENOENT; + + /* If we don't have enough bandwidth, we don't proceed recovering. */ + if (!recover_bandwidth(rs)) + return -EAGAIN; + + /* Start quiescing a region. */ + dm_rh_recovery_prepare(rh); + addr->reg = dm_rh_recovery_start(rh); + if (!addr->reg) + return -EAGAIN; + + addr->pos = dm_rh_region_to_sector(rh, dm_rh_get_region_key(addr->reg)); + addr->end = addr->pos + dm_rh_get_region_size(rh); + + /* + * Take one global io reference out for the + * whole region, which is going to be released + * when the region is completely done with. + */ + io_get(rs); + return 0; +} + +/* Update region hash state. */ +enum recover_type { REC_FAILURE = 0, REC_SUCCESS = 1 }; +static void recover_rh_update(struct stripe *stripe, enum recover_type success) +{ + struct recover_addr *addr = stripe->recover; + struct raid_set *rs = RS(stripe->sc); + struct recover *rec = &rs->recover; + + if (!addr->reg) { + DMERR("%s- Called w/o region", __func__); + return; + } + + dm_rh_recovery_end(addr->reg, success); + if (success) + rec->nr_regions_recovered++; + + addr->reg = NULL; + + /* + * Completely done with this region -> + * release the 1st io reference. + */ + io_put(rs); +} + +/* Set start of recovery state. */ +static void set_start_recovery(struct raid_set *rs) +{ + /* Initialize recovery. */ + rs->recover.start_jiffies = jiffies; + rs->recover.end_jiffies = 0; +} + +/* Set end of recovery state. */ +static void set_end_recovery(struct raid_set *rs) +{ + ClearRSRecover(rs); + rs->set.dev_to_init = -1; + + /* Check for jiffies overrun. */ + rs->recover.end_jiffies = jiffies; + if (rs->recover.end_jiffies < rs->recover.start_jiffies) + rs->recover.end_jiffies = ~0; +} + +/* Handle recovery on one recovery stripe. */ +static int _do_recovery(struct stripe *stripe) +{ + int r; + struct raid_set *rs = RS(stripe->sc); + struct recover_addr *addr = stripe->recover; + + /* If recovery is active -> return. */ + if (stripe_io_ref(stripe)) + return 1; + + /* IO error is fatal for recovery -> stop it. */ + if (unlikely(StripeError(stripe))) + goto err; + + /* Recovery end required. */ + if (!RSRecover(rs)) + goto err; + + /* Get a region to recover. */ + r = stripe_recover_get_region(stripe); + switch (r) { + case 0: /* Got a new region: flag initial read before write. */ + SetStripeRBW(stripe); + case 1: /* Have a region in the works. */ + break; + case -EAGAIN: + /* No bandwidth/quiesced region yet, try later. */ + if (!io_ref(rs)) + wake_do_raid_delayed(rs, HZ / 4); + case -EPERM: + /* Suspend. */ + return 1; + case -ENOENT: /* No more regions to recover. */ + schedule_work(&rs->io.ws_do_table_event); + return 0; + default: + BUG(); + } + + /* Read/write a recover stripe. */ + r = stripe_recover_rw(stripe); + if (r) + /* IO initiated. */ + return 1; + + /* Read and write finished-> update recovery position within region. */ + addr->pos += stripe->io.size; + + /* If we're at end of region, update region hash. */ + if (addr->pos >= addr->end || + addr->pos >= rs->set.sectors_per_dev) + recover_rh_update(stripe, REC_SUCCESS); + else + /* Prepare to read next region segment. */ + SetStripeRBW(stripe); + + /* Schedule myself for another round... */ + wake_do_raid(rs); + return 1; + +err: + /* FIXME: rather try recovering other regions on error? */ + rs_check_degrade(stripe); + recover_rh_update(stripe, REC_FAILURE); + + /* Check state of partially recovered array. */ + if (RSDegraded(rs) && !RSDead(rs) && + rs->set.dev_to_init != -1 && + rs->set.ei != rs->set.dev_to_init) + /* Broken drive != drive to recover -> FATAL. */ + SetRSDead(rs); + + if (StripeError(stripe)) { + char buf[BDEVNAME_SIZE]; + + DMERR("stopping recovery due to " + "ERROR on /dev/%s, stripe at offset %llu", + bdevname(rs->dev[rs->set.ei].dev->bdev, buf), + (unsigned long long) stripe->key); + + } + + /* Make sure, that all quiesced regions get released. */ + while (addr->reg) { + dm_rh_recovery_end(addr->reg, -EIO); + addr->reg = dm_rh_recovery_start(rs->recover.rh); + } + + return 0; +} + +/* Called by main io daemon to recover regions. */ +static void do_recovery(struct raid_set *rs) +{ + if (RSRecover(rs)) { + int r = 0; + struct stripe *stripe; + + list_for_each_entry(stripe, &rs->recover.stripes, + lists[LIST_RECOVER]) + r += _do_recovery(stripe); + + if (!r) { + set_end_recovery(rs); + stripe_recover_free(rs); + } + } +} + +/* + * END recovery functions + */ + +/* End io process all stripes handed in by endio() callback. */ +static void _do_endios(struct raid_set *rs, struct stripe *stripe, + struct list_head *flush_list) +{ + /* First unlock all required chunks. */ + stripe_chunks_unlock(stripe); + + /* + * If an io error on a stripe occured, degrade the RAID set + * and try to endio as many bios as possible. If any bios can't + * be endio processed, requeue the stripe (stripe_ref() != 0). + */ + if (TestClearStripeError(stripe)) { + /* + * FIXME: if read, rewrite the failed chunk after reconstruction + * in order to trigger disk bad sector relocation. + */ + rs_check_degrade(stripe); /* Resets ChunkError(). */ + ClearStripeReconstruct(stripe); + ClearStripeReconstructed(stripe); + } + + /* Got to reconstruct a missing chunk. */ + if (StripeReconstruct(stripe)) { + /* + * (*2*) We use StripeReconstruct() to allow for + * all chunks to be xored into the reconstructed + * one (see chunk_must_xor()). + */ + stripe_reconstruct(stripe); + + /* + * (*3*) Now we reset StripeReconstruct() and flag + * StripeReconstructed() to show to stripe_rw(), + * that we have reconstructed a missing chunk. + */ + ClearStripeReconstruct(stripe); + SetStripeReconstructed(stripe); + + /* FIXME: reschedule to be written in case of read. */ + // if (!StripeRBW(stripe)) { + // chunk_set(CHUNK(stripe, pr), DIRTY); + // stripe_chunks_rw(stripe); + // } + } + + /* + * Now that we eventually got a complete stripe, we + * can process the rest of the end ios on reads. + */ + stripe_endio(READ, stripe); + + /* End io all merged writes. */ + if (TestClearStripeMerged(stripe)) + stripe_endio(WRITE_MERGED, stripe); + + /* If RAID set is dead -> fail any ios to dead drives. */ + if (RSDead(rs)) { + DMERR_LIMIT("RAID set dead: failing ios to dead devices"); + stripe_fail_io(stripe); + } + + /* + * We have stripe references still, + * beacuse of read befeore writes or IO errors -> + * got to put on flush list for processing. + */ + if (stripe_ref(stripe)) { + BUG_ON(!list_empty(stripe->lists + LIST_LRU)); + list_add_tail(stripe->lists + LIST_FLUSH, flush_list); + atomic_inc(rs->stats + S_REQUEUE); /* REMOVEME: statistics. */ + } else + stripe_lru_add(stripe); +} + +/* Pop any endio stripes off of the endio list and belabour them. */ +static void do_endios(struct raid_set *rs) +{ + struct stripe_cache *sc = &rs->sc; + struct stripe *stripe; + /* IO flush list for sorted requeued stripes. */ + struct list_head flush_list; + + INIT_LIST_HEAD(&flush_list); + + while ((stripe = stripe_endio_pop(sc))) { + /* Avoid endio on stripes with newly io'ed chunks. */ + if (!stripe_io_ref(stripe)) + _do_endios(rs, stripe, &flush_list); + } + + /* + * Insert any requeued stripes in the proper + * order at the beginning of the io (flush) list. + */ + list_splice(&flush_list, sc->lists + LIST_FLUSH); +} + +/* Flush any stripes on the io list. */ +static void do_flush(struct raid_set *rs) +{ + struct stripe *stripe; + + while ((stripe = stripe_io_pop(&rs->sc))) + stripe_rw(stripe); /* Read/write stripe. */ +} + +/* Stripe cache resizing. */ +static void do_sc_resize(struct raid_set *rs) +{ + unsigned set = atomic_read(&rs->sc.stripes_to_set); + + if (set) { + unsigned cur = atomic_read(&rs->sc.stripes); + int r = (set > cur) ? sc_grow(&rs->sc, set - cur, SC_GROW) : + sc_shrink(&rs->sc, cur - set); + + /* Flag end of resizeing if ok. */ + if (!r) + atomic_set(&rs->sc.stripes_to_set, 0); + } +} + +/* + * Process all ios + * + * We do different things with the io depending + * on the state of the region that it is in: + * + * o reads: hang off stripe cache or postpone if full + * + * o writes: + * + * CLEAN/DIRTY/NOSYNC: increment pending and hang io off stripe's stripe set. + * In case stripe cache is full or busy, postpone the io. + * + * RECOVERING: delay the io until recovery of the region completes. + * + */ +static void do_ios(struct raid_set *rs, struct bio_list *ios) +{ + int r; + unsigned flush = 0, delay = 0; + sector_t sector; + struct dm_rh_client *rh = rs->recover.rh; + struct bio *bio; + struct bio_list reject; + + bio_list_init(&reject); + + /* + * Classify each io: + * o delay writes to recovering regions (let reads go through) + * o queue io to all other regions + */ + while ((bio = bio_list_pop(ios))) { + /* + * In case we get a barrier bio, push it back onto + * the input queue unless all work queues are empty + * and the stripe cache is inactive. + */ + if (unlikely(bio->bi_rw & REQ_FLUSH)) { + /* REMOVEME: statistics. */ + atomic_inc(rs->stats + S_BARRIER); + if (delay || + !list_empty(rs->sc.lists + LIST_FLUSH) || + !bio_list_empty(&reject) || + sc_active(&rs->sc)) { + bio_list_push(ios, bio); + break; + } + } + + /* Check for recovering regions. */ + sector = _sector(rs, bio); + r = region_state(rs, sector, DM_RH_RECOVERING); + if (unlikely(r && bio_data_dir(bio) == WRITE)) { + delay++; + /* Wait writing to recovering regions. */ + dm_rh_delay_by_region(rh, bio, + dm_rh_sector_to_region(rh, + sector)); + /* REMOVEME: statistics.*/ + atomic_inc(rs->stats + S_DELAYED_BIOS); + atomic_inc(rs->stats + S_SUM_DELAYED_BIOS); + + /* Force bandwidth tests in recovery. */ + SetRSBandwidth(rs); + } else { + /* + * Process ios to non-recovering regions by queueing + * them to stripes (does dm_rh_inc()) for writes). + */ + flush += stripe_queue_bio(rs, bio, &reject); + } + } + + if (flush) { + /* FIXME: better error handling. */ + r = dm_rh_flush(rh); /* Writes got queued -> flush dirty log. */ + if (r) + DMERR_LIMIT("dirty log flush"); + } + + /* Merge any rejected bios back to the head of the input list. */ + bio_list_merge_head(ios, &reject); +} + +/* Send an event in case we're getting too busy. */ +static void do_busy_event(struct raid_set *rs) +{ + if (sc_busy(rs)) { + if (!TestSetRSScBusy(rs)) + schedule_work(&rs->io.ws_do_table_event); + } + + ClearRSScBusy(rs); +} + +/* Throw an event. */ +static void do_table_event(struct work_struct *ws) +{ + struct raid_set *rs = container_of(ws, struct raid_set, + io.ws_do_table_event); + dm_table_event(rs->ti->table); +} + + +/*----------------------------------------------------------------- + * RAID daemon + *---------------------------------------------------------------*/ +/* + * o belabour all end ios + * o update the region hash states + * o optionally shrink the stripe cache + * o optionally do recovery + * o unplug any component raid devices with queued bios + * o grab the input queue + * o work an all requeued or new ios and perform stripe cache flushs + * o unplug any component raid devices with queued bios + * o check, if the stripe cache gets too busy and throw an event if so + */ +static void do_raid(struct work_struct *ws) +{ + struct raid_set *rs = container_of(ws, struct raid_set, + io.dws_do_raid.work); + struct bio_list *ios = &rs->io.work, *ios_in = &rs->io.in; + struct blk_plug plug; + + /* + * We always need to end io, so that ios can get errored in + * case the set failed and the region counters get decremented + * before we update region hash states and go any further. + */ + do_endios(rs); + dm_rh_update_states(rs->recover.rh, 1); + + /* + * Now that we've end io'd, which may have put stripes on the LRU list + * to allow for shrinking, we resize the stripe cache if requested. + */ + do_sc_resize(rs); + + /* Try to recover regions. */ + blk_start_plug(&plug); + do_recovery(rs); + blk_finish_plug(&plug); /* Unplug the queue */ + + /* Quickly grab all new ios queued and add them to the work list. */ + mutex_lock(&rs->io.in_lock); + bio_list_merge(ios, ios_in); + bio_list_init(ios_in); + mutex_unlock(&rs->io.in_lock); + + blk_start_plug(&plug); + if (!bio_list_empty(ios)) + do_ios(rs, ios); /* Got ios to work into the cache. */ + + do_flush(rs); /* Flush any stripes on io list. */ + blk_finish_plug(&plug); /* Unplug the queue */ + do_busy_event(rs); /* Check if we got too busy. */ +} + +/* + * Callback for region hash to dispatch + * delayed bios queued to recovered regions + * (gets called via dm_rh_update_states()). + */ +static void dispatch_delayed_bios(void *context, struct bio_list *bl) +{ + struct raid_set *rs = context; + struct bio *bio; + + /* REMOVEME: statistics; decrement pending delayed bios counter. */ + bio_list_for_each(bio, bl) + atomic_dec(rs->stats + S_DELAYED_BIOS); + + /* Merge region hash private list to work list. */ + bio_list_merge_head(&rs->io.work, bl); + bio_list_init(bl); + ClearRSBandwidth(rs); +} + +/************************************************************* + * Constructor helpers + *************************************************************/ +/* Calculate MB/sec. */ +static unsigned mbpers(struct raid_set *rs, unsigned speed) +{ + return to_bytes(speed * rs->set.data_devs * + rs->recover.io_size * HZ >> 10) >> 10; +} + +/* + * Discover fastest xor algorithm and # of chunks combination. + */ +/* Calculate speed for algorithm and # of chunks. */ +static unsigned xor_speed(struct stripe *stripe) +{ + unsigned r = 0; + unsigned long j; + + /* Wait for next tick. */ + for (j = jiffies; j == jiffies; ) + ; + + /* Do xors for a full tick. */ + for (j = jiffies; j == jiffies; ) { + mb(); + common_xor(stripe, stripe->io.size, 0, 0); + mb(); + r++; + } + + return r; +} + +/* Optimize xor algorithm for this RAID set. */ +static unsigned xor_optimize(struct raid_set *rs) +{ + unsigned chunks_max = 2, p = rs->set.raid_devs, speed_max = 0; + struct xor_func *f = ARRAY_END(xor_funcs), *f_max = NULL; + struct stripe *stripe; + + BUG_ON(list_empty(&rs->recover.stripes)); + stripe = list_first_entry(&rs->recover.stripes, struct stripe, + lists[LIST_RECOVER]); + + /* Must set uptodate so that xor() will belabour chunks. */ + while (p--) + SetChunkUptodate(CHUNK(stripe, p)); + + /* Try all xor functions. */ + while (f-- > xor_funcs) { + unsigned speed; + + /* Set actual xor function for common_xor(). */ + rs->xor.f = f; + rs->xor.chunks = (f->f == xor_blocks_wrapper ? + (MAX_XOR_BLOCKS + 1) : XOR_CHUNKS_MAX) + 1; + + while (rs->xor.chunks-- > 2) { + speed = xor_speed(stripe); + if (speed > speed_max) { + speed_max = speed; + chunks_max = rs->xor.chunks; + f_max = f; + } + } + } + + /* Memorize optimum parameters. */ + rs->xor.f = f_max; + rs->xor.chunks = chunks_max; + return speed_max; +} + +/* + * Allocate a RAID context (a RAID set) + */ +/* Structure for variable RAID parameters. */ +struct variable_parms { + int bandwidth; + int bandwidth_parm; + int chunk_size; + int chunk_size_parm; + int io_size; + int io_size_parm; + int stripes; + int stripes_parm; + int recover_io_size; + int recover_io_size_parm; + int raid_parms; + int recovery; + int recovery_stripes; + int recovery_stripes_parm; +}; + +static struct raid_set * +context_alloc(struct raid_type *raid_type, struct variable_parms *p, + unsigned raid_devs, sector_t sectors_per_dev, + struct dm_target *ti, unsigned dl_parms, char **argv) +{ + int r; + size_t len; + sector_t region_size, ti_len; + struct raid_set *rs = NULL; + struct dm_dirty_log *dl; + struct recover *rec; + + /* + * Create the dirty log + * + * We need to change length for the dirty log constructor, + * because we want an amount of regions for all stripes derived + * from the single device size, so that we can keep region + * size = 2^^n independant of the number of devices + */ + ti_len = ti->len; + ti->len = sectors_per_dev; + dl = dm_dirty_log_create(argv[0], ti, NULL, dl_parms, argv + 2); + ti->len = ti_len; + if (!dl) + goto bad_dirty_log; + + /* Chunk size *must* be smaller than region size. */ + region_size = dl->type->get_region_size(dl); + if (p->chunk_size > region_size) + goto bad_chunk_size; + + /* Recover io size *must* be smaller than region size as well. */ + if (p->recover_io_size > region_size) + goto bad_recover_io_size; + + /* Size and allocate the RAID set structure. */ + len = sizeof(*rs->data) + sizeof(*rs->dev); + if (dm_array_too_big(sizeof(*rs), len, raid_devs)) + goto bad_array; + + len = sizeof(*rs) + raid_devs * len; + rs = kzalloc(len, GFP_KERNEL); + if (!rs) + goto bad_alloc; + + rec = &rs->recover; + atomic_set(&rs->io.in_process, 0); + atomic_set(&rs->io.in_process_max, 0); + rec->io_size = p->recover_io_size; + + /* Pointer to data array. */ + rs->data = (unsigned long **) + ((void *) rs->dev + raid_devs * sizeof(*rs->dev)); + rec->dl = dl; + rs->set.raid_devs = raid_devs; + rs->set.data_devs = raid_devs - raid_type->parity_devs; + rs->set.raid_type = raid_type; + + rs->set.raid_parms = p->raid_parms; + rs->set.chunk_size_parm = p->chunk_size_parm; + rs->set.io_size_parm = p->io_size_parm; + rs->sc.stripes_parm = p->stripes_parm; + rec->io_size_parm = p->recover_io_size_parm; + rec->bandwidth_parm = p->bandwidth_parm; + rec->recovery = p->recovery; + rec->recovery_stripes = p->recovery_stripes; + + /* + * Set chunk and io size and respective shifts + * (used to avoid divisions) + */ + rs->set.chunk_size = p->chunk_size; + rs->set.chunk_shift = ffs(p->chunk_size) - 1; + + rs->set.io_size = p->io_size; + rs->set.io_mask = p->io_size - 1; + /* Mask to adjust address key in case io_size != chunk_size. */ + rs->set.io_inv_mask = (p->chunk_size - 1) & ~rs->set.io_mask; + + rs->set.sectors_per_dev = sectors_per_dev; + + rs->set.ei = -1; /* Indicate no failed device. */ + atomic_set(&rs->set.failed_devs, 0); + + rs->ti = ti; + + atomic_set(rec->io_count + IO_WORK, 0); + atomic_set(rec->io_count + IO_RECOVER, 0); + + /* Initialize io lock and queues. */ + mutex_init(&rs->io.in_lock); + bio_list_init(&rs->io.in); + bio_list_init(&rs->io.work); + + init_waitqueue_head(&rs->io.suspendq); /* Suspend waiters (dm-io). */ + + rec->nr_regions = dm_sector_div_up(sectors_per_dev, region_size); + rec->rh = dm_region_hash_create(rs, dispatch_delayed_bios, + wake_dummy, wake_do_raid, 0, p->recovery_stripes, + dl, region_size, rec->nr_regions); + if (IS_ERR(rec->rh)) + goto bad_rh; + + /* Initialize stripe cache. */ + r = sc_init(rs, p->stripes); + if (r) + goto bad_sc; + + /* REMOVEME: statistics. */ + stats_reset(rs); + ClearRSDevelStats(rs); /* Disnable development status. */ + return rs; + +bad_dirty_log: + TI_ERR_RET("Error creating dirty log", ERR_PTR(-ENOMEM)); + +bad_chunk_size: + dm_dirty_log_destroy(dl); + TI_ERR_RET("Chunk size larger than region size", ERR_PTR(-EINVAL)); + +bad_recover_io_size: + dm_dirty_log_destroy(dl); + TI_ERR_RET("Recover stripe io size larger than region size", + ERR_PTR(-EINVAL)); + +bad_array: + dm_dirty_log_destroy(dl); + TI_ERR_RET("Arry too big", ERR_PTR(-EINVAL)); + +bad_alloc: + dm_dirty_log_destroy(dl); + TI_ERR_RET("Cannot allocate raid context", ERR_PTR(-ENOMEM)); + +bad_rh: + dm_dirty_log_destroy(dl); + ti->error = DM_MSG_PREFIX "Error creating dirty region hash"; + goto free_rs; + +bad_sc: + dm_region_hash_destroy(rec->rh); /* Destroys dirty log too. */ + sc_exit(&rs->sc); + ti->error = DM_MSG_PREFIX "Error creating stripe cache"; +free_rs: + kfree(rs); + return ERR_PTR(-ENOMEM); +} + +/* Free a RAID context (a RAID set). */ +static void context_free(struct raid_set *rs, unsigned p) +{ + while (p--) + dm_put_device(rs->ti, rs->dev[p].dev); + + sc_exit(&rs->sc); + dm_region_hash_destroy(rs->recover.rh); /* Destroys dirty log too. */ + kfree(rs); +} + +/* Create work queue and initialize delayed work. */ +static int rs_workqueue_init(struct raid_set *rs) +{ + struct dm_target *ti = rs->ti; + + rs->io.wq = create_singlethread_workqueue(DAEMON); + if (!rs->io.wq) + TI_ERR_RET("failed to create " DAEMON, -ENOMEM); + + INIT_DELAYED_WORK(&rs->io.dws_do_raid, do_raid); + INIT_WORK(&rs->io.ws_do_table_event, do_table_event); + return 0; +} + +/* Return pointer to raid_type structure for raid name. */ +static struct raid_type *get_raid_type(char *name) +{ + struct raid_type *r = ARRAY_END(raid_types); + + while (r-- > raid_types) { + if (!strcmp(r->name, name)) + return r; + } + + return NULL; +} + +/* FIXME: factor out to dm core. */ +static int multiple(sector_t a, sector_t b, sector_t *n) +{ + sector_t r = a; + + sector_div(r, b); + *n = r; + return a == r * b; +} + +/* Log RAID set information to kernel log. */ +static void rs_log(struct raid_set *rs, unsigned speed) +{ + unsigned p; + char buf[BDEVNAME_SIZE]; + + for (p = 0; p < rs->set.raid_devs; p++) + DMINFO("/dev/%s is raid disk %u%s", + bdevname(rs->dev[p].dev->bdev, buf), p, + (p == rs->set.pi) ? " (parity)" : ""); + + DMINFO("%d/%d/%d sectors chunk/io/recovery size, %u stripes\n" + "algorithm \"%s\", %u chunks with %uMB/s\n" + "%s set with net %u/%u devices", + rs->set.chunk_size, rs->set.io_size, rs->recover.io_size, + atomic_read(&rs->sc.stripes), + rs->xor.f->name, rs->xor.chunks, mbpers(rs, speed), + rs->set.raid_type->descr, rs->set.data_devs, rs->set.raid_devs); +} + +/* Get all devices and offsets. */ +static int dev_parms(struct raid_set *rs, char **argv, int *p) +{ + struct dm_target *ti = rs->ti; + + for (*p = 0; *p < rs->set.raid_devs; (*p)++, argv += 2) { + int r; + unsigned long long tmp; + struct raid_dev *dev = rs->dev + *p; + + /* Get offset and device. */ + if (sscanf(argv[1], "%llu", &tmp) != 1 || + tmp > rs->set.sectors_per_dev) + TI_ERR("Invalid RAID device offset parameter"); + + dev->start = tmp; + r = dm_get_device(ti, *argv, dm_table_get_mode(ti->table), &dev->dev); + if (r) + TI_ERR_RET("RAID device lookup failure", r); + + r = raid_dev_lookup(rs, dev); + if (r != -ENODEV && r < *p) { + (*p)++; /* Ensure dm_put_device() on actual device. */ + TI_ERR_RET("Duplicate RAID device", -ENXIO); + } + } + + return 0; +} + +/* Set recovery bandwidth. */ +static void +recover_set_bandwidth(struct raid_set *rs, unsigned bandwidth) +{ + rs->recover.bandwidth = bandwidth; + rs->recover.bandwidth_work = 100 / bandwidth; +} + +/* Handle variable number of RAID parameters. */ +static int get_raid_variable_parms(struct dm_target *ti, char **argv, + struct variable_parms *vp) +{ + int p, value; + struct { + int action; /* -1: skip, 0: no pwer2 check, 1: power2 check */ + char *errmsg; + int min, max; + int *var, *var2, *var3; + } argctr[] = { + { 1, + "Invalid chunk size; must be -1 or 2^^n and <= 16384", + IO_SIZE_MIN, CHUNK_SIZE_MAX, + &vp->chunk_size_parm, &vp->chunk_size, &vp->io_size }, + { 0, + "Invalid number of stripes: must be -1 or >= 8 and <= 16384", + STRIPES_MIN, STRIPES_MAX, + &vp->stripes_parm, &vp->stripes, NULL }, + { 1, + "Invalid io size; must -1 or >= 8, 2^^n and less equal " + "min(BIO_MAX_SECTORS/2, chunk size)", + IO_SIZE_MIN, 0, /* Needs to be updated in loop below. */ + &vp->io_size_parm, &vp->io_size, NULL }, + { 1, + "Invalid recovery io size; must be -1 or " + "2^^n and less equal BIO_MAX_SECTORS/2", + RECOVER_IO_SIZE_MIN, BIO_MAX_SECTORS / 2, + &vp->recover_io_size_parm, &vp->recover_io_size, NULL }, + { 0, + "Invalid recovery bandwidth percentage; " + "must be -1 or > 0 and <= 100", + BANDWIDTH_MIN, BANDWIDTH_MAX, + &vp->bandwidth_parm, &vp->bandwidth, NULL }, + /* Handle sync argument seperately in loop. */ + { -1, + "Invalid recovery switch; must be \"sync\" or \"nosync\"" }, + { 0, + "Invalid number of recovery stripes;" + "must be -1, > 0 and <= 16384", + RECOVERY_STRIPES_MIN, RECOVERY_STRIPES_MAX, + &vp->recovery_stripes_parm, &vp->recovery_stripes, NULL }, + }, *varp; + + /* Fetch # of variable raid parameters. */ + if (sscanf(*(argv++), "%d", &vp->raid_parms) != 1 || + !range_ok(vp->raid_parms, 0, 7)) + TI_ERR("Bad variable raid parameters number"); + + /* Preset variable RAID parameters. */ + vp->chunk_size = CHUNK_SIZE_DEFAULT; + vp->io_size = IO_SIZE_DEFAULT; + vp->stripes = STRIPES_DEFAULT; + vp->recover_io_size = RECOVER_IO_SIZE_DEFAULT; + vp->bandwidth = BANDWIDTH_DEFAULT; + vp->recovery = 1; + vp->recovery_stripes = RECOVERY_STRIPES_DEFAULT; + + /* Walk the array of argument constraints for all given ones. */ + for (p = 0, varp = argctr; p < vp->raid_parms; p++, varp++) { + BUG_ON(varp >= ARRAY_END(argctr)); + + /* Special case for "[no]sync" string argument. */ + if (varp->action < 0) { + if (!strcmp(*argv, "sync")) + ; + else if (!strcmp(*argv, "nosync")) + vp->recovery = 0; + else + TI_ERR(varp->errmsg); + + argv++; + continue; + } + + /* + * Special case for io_size depending + * on previously set chunk size. + */ + if (p == 2) + varp->max = min(BIO_MAX_SECTORS / 2, vp->chunk_size); + + if (sscanf(*(argv++), "%d", &value) != 1 || + (value != -1 && + ((varp->action && !POWER_OF_2(value)) || + !range_ok(value, varp->min, varp->max)))) + TI_ERR(varp->errmsg); + + *varp->var = value; + if (value != -1) { + if (varp->var2) + *varp->var2 = value; + if (varp->var3) + *varp->var3 = value; + } + } + + return 0; +} + +/* Parse optional locking parameters. */ +static int get_raid_locking_parms(struct dm_target *ti, char **argv, + int *locking_parms, + struct dm_raid45_locking_type **locking_type) +{ + if (!strnicmp(argv[0], "locking", strlen(argv[0]))) { + char *lckstr = argv[1]; + size_t lcksz = strlen(lckstr); + + if (!strnicmp(lckstr, "none", lcksz)) { + *locking_type = &locking_none; + *locking_parms = 2; + } else if (!strnicmp(lckstr, "cluster", lcksz)) { + DMERR("locking type \"%s\" not yet implemented", + lckstr); + return -EINVAL; + } else { + DMERR("unknown locking type \"%s\"", lckstr); + return -EINVAL; + } + } + + *locking_parms = 0; + *locking_type = &locking_none; + return 0; +} + +/* Set backing device read ahead properties of RAID set. */ +static void rs_set_read_ahead(struct raid_set *rs, + unsigned sectors, unsigned stripes) +{ + unsigned ra_pages = dm_div_up(sectors, SECTORS_PER_PAGE); + struct mapped_device *md = dm_table_get_md(rs->ti->table); + struct backing_dev_info *bdi = &dm_disk(md)->queue->backing_dev_info; + + /* Set read-ahead for the RAID set and the component devices. */ + if (ra_pages) { + unsigned p = rs->set.raid_devs; + + bdi->ra_pages = stripes * ra_pages * rs->set.data_devs; + + while (p--) { + struct request_queue *q = + bdev_get_queue(rs->dev[p].dev->bdev); + + q->backing_dev_info.ra_pages = ra_pages; + } + } + + dm_put(md); +} + +/* Set congested function. */ +static void rs_set_congested_fn(struct raid_set *rs) +{ + struct mapped_device *md = dm_table_get_md(rs->ti->table); + struct backing_dev_info *bdi = &dm_disk(md)->queue->backing_dev_info; + + /* Set congested function and data. */ + bdi->congested_fn = rs_congested; + bdi->congested_data = rs; + dm_put(md); +} + +/* + * Construct a RAID4/5 mapping: + * + * log_type #log_params <log_params> \ + * raid_type [#parity_dev] #raid_variable_params <raid_params> \ + * [locking "none"/"cluster"] + * #raid_devs #dev_to_initialize [<dev_path> <offset>]{3,} + * + * log_type = "core"/"disk", + * #log_params = 1-3 (1-2 for core dirty log type, 3 for disk dirty log only) + * log_params = [dirty_log_path] region_size [[no]sync]) + * + * raid_type = "raid4", "raid5_la", "raid5_ra", "raid5_ls", "raid5_rs" + * + * #parity_dev = N if raid_type = "raid4" + * o N = -1: pick default = last device + * o N >= 0 and < #raid_devs: parity device index + * + * #raid_variable_params = 0-7; raid_params (-1 = default): + * [chunk_size [#stripes [io_size [recover_io_size \ + * [%recovery_bandwidth [recovery_switch [#recovery_stripes]]]]]]] + * o chunk_size (unit to calculate drive addresses; must be 2^^n, > 8 + * and <= CHUNK_SIZE_MAX) + * o #stripes is number of stripes allocated to stripe cache + * (must be > 1 and < STRIPES_MAX) + * o io_size (io unit size per device in sectors; must be 2^^n and > 8) + * o recover_io_size (io unit size per device for recovery in sectors; + must be 2^^n, > SECTORS_PER_PAGE and <= region_size) + * o %recovery_bandwith is the maximum amount spend for recovery during + * application io (1-100%) + * o recovery switch = [sync|nosync] + * o #recovery_stripes is the number of recovery stripes used for + * parallel recovery of the RAID set + * If raid_variable_params = 0, defaults will be used. + * Any raid_variable_param can be set to -1 to apply a default + * + * #raid_devs = N (N >= 3) + * + * #dev_to_initialize = N + * -1: initialize parity on all devices + * >= 0 and < #raid_devs: initialize raid_path; used to force reconstruction + * of a failed devices content after replacement + * + * <dev_path> = device_path (eg, /dev/sdd1) + * <offset> = begin at offset on <dev_path> + * + */ +#define MIN_PARMS 13 +static int raid_ctr(struct dm_target *ti, unsigned argc, char **argv) +{ + int dev_to_init, dl_parms, i, locking_parms, + parity_parm, pi = -1, r, raid_devs; + unsigned speed; + sector_t tmp, sectors_per_dev; + struct dm_raid45_locking_type *locking; + struct raid_set *rs; + struct raid_type *raid_type; + struct variable_parms parms; + + /* Ensure minimum number of parameters. */ + if (argc < MIN_PARMS) + TI_ERR("Not enough parameters"); + + /* Fetch # of dirty log parameters. */ + if (sscanf(argv[1], "%d", &dl_parms) != 1 || + !range_ok(dl_parms, 1, 4711)) /* ;-) */ + TI_ERR("Bad dirty log parameters number"); + + /* Check raid_type. */ + raid_type = get_raid_type(argv[dl_parms + 2]); + if (!raid_type) + TI_ERR("Bad raid type"); + + /* In case of RAID4, parity drive is selectable. */ + parity_parm = !!(raid_type->level == raid4); + + /* Handle variable number of RAID parameters. */ + r = get_raid_variable_parms(ti, argv + dl_parms + parity_parm + 3, + &parms); + if (r) + return r; + + /* Handle any locking parameters. */ + r = get_raid_locking_parms(ti, + argv + dl_parms + parity_parm + + parms.raid_parms + 4, + &locking_parms, &locking); + if (r) + return r; + + /* # of raid devices. */ + i = dl_parms + parity_parm + parms.raid_parms + locking_parms + 4; + if (sscanf(argv[i], "%d", &raid_devs) != 1 || + raid_devs < raid_type->minimal_devs) + TI_ERR("Invalid number of raid devices"); + + /* In case of RAID4, check parity drive index is in limits. */ + if (raid_type->level == raid4) { + /* Fetch index of parity device. */ + if (sscanf(argv[dl_parms + 3], "%d", &pi) != 1 || + (pi != -1 && !range_ok(pi, 0, raid_devs - 1))) + TI_ERR("Invalid RAID4 parity device index"); + } + + /* + * Index of device to initialize starts at 0 + * + * o -1 -> don't initialize a selected device; + * initialize parity conforming to algorithm + * o 0..raid_devs-1 -> initialize respective device + * (used for reconstruction of a replaced device) + */ + if (sscanf(argv[dl_parms + parity_parm + parms.raid_parms + + locking_parms + 5], "%d", &dev_to_init) != 1 || + !range_ok(dev_to_init, -1, raid_devs - 1)) + TI_ERR("Invalid number for raid device to initialize"); + + /* Check # of raid device arguments. */ + if (argc - dl_parms - parity_parm - parms.raid_parms - 6 != + 2 * raid_devs) + TI_ERR("Wrong number of raid device/offset arguments"); + + /* + * Check that the table length is devisable + * w/o rest by (raid_devs - parity_devs) + */ + if (!multiple(ti->len, raid_devs - raid_type->parity_devs, + §ors_per_dev)) + TI_ERR("Target length not divisible by number of data devices"); + + /* + * Check that the device size is + * devisable w/o rest by chunk size + */ + if (!multiple(sectors_per_dev, parms.chunk_size, &tmp)) + TI_ERR("Device length not divisible by chunk_size"); + + /**************************************************************** + * Now that we checked the constructor arguments -> + * let's allocate the RAID set + ****************************************************************/ + rs = context_alloc(raid_type, &parms, raid_devs, sectors_per_dev, + ti, dl_parms, argv); + if (IS_ERR(rs)) + return PTR_ERR(rs); + + + rs->set.dev_to_init = rs->set.dev_to_init_parm = dev_to_init; + rs->set.pi = rs->set.pi_parm = pi; + + /* Set RAID4 parity drive index. */ + if (raid_type->level == raid4) + rs->set.pi = (pi == -1) ? rs->set.data_devs : pi; + + recover_set_bandwidth(rs, parms.bandwidth); + + /* Use locking type to lock stripe access. */ + rs->locking = locking; + + /* Get the device/offset tupels. */ + argv += dl_parms + 6 + parity_parm + parms.raid_parms; + r = dev_parms(rs, argv, &i); + if (r) + goto err; + + /* Set backing device information (eg. read ahead). */ + rs_set_read_ahead(rs, 2 * rs->set.chunk_size, 4 /* stripes */); + rs_set_congested_fn(rs); /* Set congested function. */ + SetRSCheckOverwrite(rs); /* Allow chunk overwrite checks. */ + speed = xor_optimize(rs); /* Select best xor algorithm. */ + + /* Set for recovery of any nosync regions. */ + if (parms.recovery) + SetRSRecover(rs); + else { + /* + * Need to free recovery stripe(s) here in case + * of nosync, because xor_optimize uses one. + */ + set_start_recovery(rs); + set_end_recovery(rs); + stripe_recover_free(rs); + } + + /* + * Make sure that dm core only hands maximum io size + * length down and pays attention to io boundaries. + */ + ti->split_io = rs->set.io_size; + ti->private = rs; + + /* Initialize work queue to handle this RAID set's io. */ + r = rs_workqueue_init(rs); + if (r) + goto err; + + rs_log(rs, speed); /* Log information about RAID set. */ + return 0; + +err: + context_free(rs, i); + return r; +} + +/* + * Destruct a raid mapping + */ +static void raid_dtr(struct dm_target *ti) +{ + struct raid_set *rs = ti->private; + + destroy_workqueue(rs->io.wq); + context_free(rs, rs->set.raid_devs); +} + +/* Raid mapping function. */ +static int raid_map(struct dm_target *ti, struct bio *bio, + union map_info *map_context) +{ + /* I don't want to waste stripe cache capacity. */ + if (bio_rw(bio) == READA) + return -EIO; + else { + struct raid_set *rs = ti->private; + + /* + * Get io reference to be waiting for to drop + * to zero on device suspension/destruction. + */ + io_get(rs); + bio->bi_sector -= ti->begin; /* Remap sector. */ + + /* Queue io to RAID set. */ + mutex_lock(&rs->io.in_lock); + bio_list_add(&rs->io.in, bio); + mutex_unlock(&rs->io.in_lock); + + /* Wake daemon to process input list. */ + wake_do_raid(rs); + + /* REMOVEME: statistics. */ + atomic_inc(rs->stats + (bio_data_dir(bio) == READ ? + S_BIOS_READ : S_BIOS_WRITE)); + return DM_MAPIO_SUBMITTED; /* Handle later. */ + } +} + +/* Device suspend. */ +static void raid_presuspend(struct dm_target *ti) +{ + struct raid_set *rs = ti->private; + struct dm_dirty_log *dl = rs->recover.dl; + + SetRSSuspend(rs); + + if (RSRecover(rs)) + dm_rh_stop_recovery(rs->recover.rh); + + cancel_delayed_work(&rs->io.dws_do_raid); + flush_workqueue(rs->io.wq); + wait_ios(rs); /* Wait for completion of all ios being processed. */ + + if (dl->type->presuspend && dl->type->presuspend(dl)) + /* FIXME: need better error handling. */ + DMWARN("log presuspend failed"); +} + +static void raid_postsuspend(struct dm_target *ti) +{ + struct raid_set *rs = ti->private; + struct dm_dirty_log *dl = rs->recover.dl; + + if (dl->type->postsuspend && dl->type->postsuspend(dl)) + /* FIXME: need better error handling. */ + DMWARN("log postsuspend failed"); + +} + +/* Device resume. */ +static void raid_resume(struct dm_target *ti) +{ + struct raid_set *rs = ti->private; + struct recover *rec = &rs->recover; + struct dm_dirty_log *dl = rec->dl; + + if (dl->type->resume && dl->type->resume(dl)) + /* Resume dirty log. */ + /* FIXME: need better error handling. */ + DMWARN("log resume failed"); + + rec->nr_regions_to_recover = + rec->nr_regions - dl->type->get_sync_count(dl); + + /* Restart any unfinished recovery. */ + if (RSRecover(rs)) { + set_start_recovery(rs); + dm_rh_start_recovery(rec->rh); + } + + ClearRSSuspend(rs); + wake_do_raid(rs); +} + +/* Return stripe cache size. */ +static unsigned sc_size(struct raid_set *rs) +{ + return to_sector(atomic_read(&rs->sc.stripes) * + (sizeof(struct stripe) + + (sizeof(struct stripe_chunk) + + (sizeof(struct page_list) + + to_bytes(rs->set.io_size) * + rs->set.raid_devs)) + + (rs->recover.end_jiffies ? + 0 : rs->recover.recovery_stripes * + to_bytes(rs->set.raid_devs * rs->recover.io_size)))); +} + +/* REMOVEME: status output for development. */ +static void raid_devel_stats(struct dm_target *ti, char *result, + unsigned *size, unsigned maxlen) +{ + unsigned sz = *size; + unsigned long j; + char buf[BDEVNAME_SIZE], *p; + struct stats_map *sm; + struct raid_set *rs = ti->private; + struct recover *rec = &rs->recover; + struct timespec ts; + + DMEMIT("%s %s %u\n", version, rs->xor.f->name, rs->xor.chunks); + DMEMIT("act_ios=%d ", io_ref(rs)); + DMEMIT("act_ios_max=%d\n", atomic_read(&rs->io.in_process_max)); + DMEMIT("act_stripes=%d ", sc_active(&rs->sc)); + DMEMIT("act_stripes_max=%d\n", + atomic_read(&rs->sc.active_stripes_max)); + + for (sm = stats_map; sm < ARRAY_END(stats_map); sm++) + DMEMIT("%s%d", sm->str, atomic_read(rs->stats + sm->type)); + + DMEMIT(" checkovr=%s\n", RSCheckOverwrite(rs) ? "on" : "off"); + DMEMIT("sc=%u/%u/%u/%u/%u/%u/%u\n", rs->set.chunk_size, + atomic_read(&rs->sc.stripes), rs->set.io_size, + rec->recovery_stripes, rec->io_size, rs->sc.hash.buckets, + sc_size(rs)); + + j = (rec->end_jiffies ? rec->end_jiffies : jiffies) - + rec->start_jiffies; + jiffies_to_timespec(j, &ts); + sprintf(buf, "%ld.%ld", ts.tv_sec, ts.tv_nsec); + p = strchr(buf, '.'); + p[3] = 0; + + DMEMIT("rg=%llu/%llu/%llu/%u %s\n", + (unsigned long long) rec->nr_regions_recovered, + (unsigned long long) rec->nr_regions_to_recover, + (unsigned long long) rec->nr_regions, rec->bandwidth, buf); + + *size = sz; +} + +static int raid_status(struct dm_target *ti, status_type_t type, + char *result, unsigned maxlen) +{ + unsigned p, sz = 0; + char buf[BDEVNAME_SIZE]; + struct raid_set *rs = ti->private; + int raid_parms[] = { + rs->set.chunk_size_parm, + rs->sc.stripes_parm, + rs->set.io_size_parm, + rs->recover.io_size_parm, + rs->recover.bandwidth_parm, + -2, + rs->recover.recovery_stripes, + }; + + switch (type) { + case STATUSTYPE_INFO: + /* REMOVEME: statistics. */ + if (RSDevelStats(rs)) + raid_devel_stats(ti, result, &sz, maxlen); + + DMEMIT("%u ", rs->set.raid_devs); + + for (p = 0; p < rs->set.raid_devs; p++) + DMEMIT("%s ", + format_dev_t(buf, rs->dev[p].dev->bdev->bd_dev)); + + DMEMIT("1 "); + for (p = 0; p < rs->set.raid_devs; p++) { + DMEMIT("%c", !DevFailed(rs->dev + p) ? 'A' : 'D'); + + if (p == rs->set.pi) + DMEMIT("p"); + + if (rs->set.dev_to_init == p) + DMEMIT("i"); + } + + break; + case STATUSTYPE_TABLE: + sz = rs->recover.dl->type->status(rs->recover.dl, type, + result, maxlen); + DMEMIT("%s %u ", rs->set.raid_type->name, + rs->set.raid_parms); + + for (p = 0; p < rs->set.raid_parms; p++) { + if (raid_parms[p] > -2) + DMEMIT("%d ", raid_parms[p]); + else + DMEMIT("%s ", rs->recover.recovery ? + "sync" : "nosync"); + } + + DMEMIT("%u %d ", rs->set.raid_devs, rs->set.dev_to_init); + + for (p = 0; p < rs->set.raid_devs; p++) + DMEMIT("%s %llu ", + format_dev_t(buf, rs->dev[p].dev->bdev->bd_dev), + (unsigned long long) rs->dev[p].start); + } + + return 0; +} + +/* + * Message interface + */ +enum raid_msg_actions { + act_bw, /* Recovery bandwidth switch. */ + act_dev, /* Device failure switch. */ + act_overwrite, /* Stripe overwrite check. */ + act_stats, /* Development statistics switch. */ + act_sc, /* Stripe cache switch. */ + + act_on, /* Set entity on. */ + act_off, /* Set entity off. */ + act_reset, /* Reset entity. */ + + act_set = act_on, /* Set # absolute. */ + act_grow = act_off, /* Grow # by an amount. */ + act_shrink = act_reset, /* Shrink # by an amount. */ +}; + +/* Turn a delta into an absolute value. */ +static int _absolute(unsigned long action, int act, int r) +{ + /* Make delta absolute. */ + if (test_bit(act_set, &action)) + ; + else if (test_bit(act_grow, &action)) + r += act; + else if (test_bit(act_shrink, &action)) + r = act - r; + else + r = -EINVAL; + + return r; +} + + /* Change recovery io bandwidth. */ +static int bandwidth_change(struct dm_msg *msg, void *context) +{ + struct raid_set *rs = context; + int act = rs->recover.bandwidth; + int bandwidth = DM_MSG_INT_ARG(msg); + + if (range_ok(bandwidth, BANDWIDTH_MIN, BANDWIDTH_MAX)) { + /* Make delta bandwidth absolute. */ + bandwidth = _absolute(msg->action, act, bandwidth); + + /* Check range. */ + if (range_ok(bandwidth, BANDWIDTH_MIN, BANDWIDTH_MAX)) { + recover_set_bandwidth(rs, bandwidth); + return 0; + } + } + + set_bit(dm_msg_ret_arg, &msg->ret); + set_bit(dm_msg_ret_inval, &msg->ret); + return -EINVAL; +} + +/* Set/reset development feature flags. */ +static int devel_flags(struct dm_msg *msg, void *context) +{ + struct raid_set *rs = context; + + if (test_bit(act_on, &msg->action)) + return test_and_set_bit(msg->spec->parm, + &rs->io.flags) ? -EPERM : 0; + else if (test_bit(act_off, &msg->action)) + return test_and_clear_bit(msg->spec->parm, + &rs->io.flags) ? 0 : -EPERM; + else if (test_bit(act_reset, &msg->action)) { + if (test_bit(act_stats, &msg->action)) { + stats_reset(rs); + goto on; + } else if (test_bit(act_overwrite, &msg->action)) { +on: + set_bit(msg->spec->parm, &rs->io.flags); + return 0; + } + } + + return -EINVAL; +} + +/* Resize the stripe cache. */ +static int sc_resize(struct dm_msg *msg, void *context) +{ + int act, stripes; + struct raid_set *rs = context; + + /* Deny permission in case the daemon is still resizing!. */ + if (atomic_read(&rs->sc.stripes_to_set)) + return -EPERM; + + stripes = DM_MSG_INT_ARG(msg); + if (stripes > 0) { + act = atomic_read(&rs->sc.stripes); + + /* Make delta stripes absolute. */ + stripes = _absolute(msg->action, act, stripes); + + /* + * Check range and that the # of stripes changes. + * We leave the resizing to the wroker. + */ + if (range_ok(stripes, STRIPES_MIN, STRIPES_MAX) && + stripes != atomic_read(&rs->sc.stripes)) { + atomic_set(&rs->sc.stripes_to_set, stripes); + wake_do_raid(rs); + return 0; + } + } + + set_bit(dm_msg_ret_arg, &msg->ret); + set_bit(dm_msg_ret_inval, &msg->ret); + return -EINVAL; +} + +/* Parse the RAID message action. */ +/* + * 'ba[ndwidth] {se[t],g[row],sh[rink]} #' # e.g 'ba se 50' + * "o[verwrite] {on,of[f],r[eset]}' # e.g. 'o of' + * 'sta[tistics] {on,of[f],r[eset]}' # e.g. 'stat of' + * 'str[ipecache] {se[t],g[row],sh[rink]} #' # e.g. 'stripe set 1024' + * + */ +static int raid_message(struct dm_target *ti, unsigned argc, char **argv) +{ + /* Variables to store the parsed parameters im. */ + static int i[2]; + static unsigned long *i_arg[] = { + (unsigned long *) i + 0, + (unsigned long *) i + 1, + }; + + /* Declare all message option strings. */ + static char *str_sgs[] = { "set", "grow", "shrink" }; + static char *str_oor[] = { "on", "off", "reset" }; + + /* Declare all actions. */ + static unsigned long act_sgs[] = { act_set, act_grow, act_shrink }; + static unsigned long act_oor[] = { act_on, act_off, act_reset }; + + /* Bandwidth option. */ + static struct dm_message_option bw_opt = { 3, str_sgs, act_sgs }; + static struct dm_message_argument bw_args = { + 1, i_arg, { dm_msg_int_t } + }; + + static struct dm_message_argument null_args = { + 0, NULL, { dm_msg_int_t } + }; + + /* Overwrite and statistics option. */ + static struct dm_message_option ovr_stats_opt = { 3, str_oor, act_oor }; + + /* Sripecache option. */ + static struct dm_message_option stripe_opt = { 3, str_sgs, act_sgs }; + + /* Declare messages. */ + static struct dm_msg_spec specs[] = { + { "bandwidth", act_bw, &bw_opt, &bw_args, + 0, bandwidth_change }, + { "overwrite", act_overwrite, &ovr_stats_opt, &null_args, + RS_CHECK_OVERWRITE, devel_flags }, + { "statistics", act_stats, &ovr_stats_opt, &null_args, + RS_DEVEL_STATS, devel_flags }, + { "stripecache", act_sc, &stripe_opt, &bw_args, + 0, sc_resize }, + }; + + /* The message for the parser. */ + struct dm_msg msg = { + .num_specs = ARRAY_SIZE(specs), + .specs = specs, + }; + + return dm_message_parse(TARGET, &msg, ti->private, argc, argv); +} +/* + * END message interface + */ + +static struct target_type raid_target = { + .name = "raid45", + .version = {1, 0, 0}, + .module = THIS_MODULE, + .ctr = raid_ctr, + .dtr = raid_dtr, + .map = raid_map, + .presuspend = raid_presuspend, + .postsuspend = raid_postsuspend, + .resume = raid_resume, + .status = raid_status, + .message = raid_message, +}; + +static void init_exit(const char *bad_msg, const char *good_msg, int r) +{ + if (r) + DMERR("Failed to %sregister target [%d]", bad_msg, r); + else + DMINFO("%s %s", good_msg, version); +} + +static int __init dm_raid_init(void) +{ + int r = dm_register_target(&raid_target); + + init_exit("", "initialized", r); + return r; +} + +static void __exit dm_raid_exit(void) +{ + dm_unregister_target(&raid_target); + init_exit("un", "exit", 0); +} + +/* Module hooks. */ +module_init(dm_raid_init); +module_exit(dm_raid_exit); + +MODULE_DESCRIPTION(DM_NAME " raid4/5 target"); +MODULE_AUTHOR("Heinz Mauelshagen <hjm@redhat.com>"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("dm-raid4"); +MODULE_ALIAS("dm-raid5"); diff --git a/ubuntu/dm-raid4-5/dm-raid4-5.h b/ubuntu/dm-raid4-5/dm-raid4-5.h new file mode 100644 index 000000000000..a0fe7c0621fa --- /dev/null +++ b/ubuntu/dm-raid4-5/dm-raid4-5.h @@ -0,0 +1,27 @@ +/* + * Copyright (C) 2006 Red Hat GmbH + * + * Module Author: Heinz Mauelshagen (Mauelshagen@RedHat.com) + * + * This file is released under the GPL. + * + */ + +#ifndef _DM_RAID45_H +#define _DM_RAID45_H + +/* Factor out to dm.h! */ +#define STR_LEN(ptr, str) ptr, str, strlen(ptr) + +enum lock_type { RAID45_EX, RAID45_SHARED }; + +struct dmraid45_locking_type { + /* Request a lock on a stripe. */ + void* (*lock)(sector_t key, enum lock_type type); + + /* Release a lock on a stripe. */ + void (*unlock)(void *lock_handle); + +}; + +#endif diff --git a/ubuntu/dm-raid4-5/dm-raid45.h b/ubuntu/dm-raid4-5/dm-raid45.h new file mode 100644 index 000000000000..786ba7af6425 --- /dev/null +++ b/ubuntu/dm-raid4-5/dm-raid45.h @@ -0,0 +1,28 @@ +/* + * Copyright (C) 2006-2008 Red Hat, Inc. All rights reserved. + * + * Module Author: Heinz Mauelshagen (Mauelshagen@RedHat.com) + * + * Locking definitions for the device-mapper RAID45 target. + * + * This file is released under the GPL. + * + */ + +#ifndef _DM_RAID45_H +#define _DM_RAID45_H + +/* Factor out to dm.h! */ +#define STR_LEN(ptr, str) (ptr), (str), strlen((ptr)) + +enum dm_lock_type { DM_RAID45_EX, DM_RAID45_SHARED }; + +struct dm_raid45_locking_type { + /* Request a lock on a stripe. */ + void* (*lock)(sector_t key, enum dm_lock_type type); + + /* Release a lock on a stripe. */ + void (*unlock)(void *lock_handle); +}; + +#endif diff --git a/ubuntu/dm-raid4-5/dm-region-hash.c b/ubuntu/dm-raid4-5/dm-region-hash.c new file mode 100644 index 000000000000..59429f68d2b5 --- /dev/null +++ b/ubuntu/dm-raid4-5/dm-region-hash.c @@ -0,0 +1,719 @@ +/* + * Copyright (C) 2003 Sistina Software Limited. + * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. + * + * This file is released under the GPL. + */ + +#include <linux/dm-dirty-log.h> +#include "dm-region-hash.h" + +#include <linux/ctype.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> + +#include "dm.h" + +#define DM_MSG_PREFIX "region hash" + +/*----------------------------------------------------------------- + * Region hash + * + * The mirror splits itself up into discrete regions. Each + * region can be in one of three states: clean, dirty, + * nosync. There is no need to put clean regions in the hash. + * + * In addition to being present in the hash table a region _may_ + * be present on one of three lists. + * + * clean_regions: Regions on this list have no io pending to + * them, they are in sync, we are no longer interested in them, + * they are dull. dm_rh_update_states() will remove them from the + * hash table. + * + * quiesced_regions: These regions have been spun down, ready + * for recovery. rh_recovery_start() will remove regions from + * this list and hand them to kmirrord, which will schedule the + * recovery io with kcopyd. + * + * recovered_regions: Regions that kcopyd has successfully + * recovered. dm_rh_update_states() will now schedule any delayed + * io, up the recovery_count, and remove the region from the + * hash. + * + * There are 2 locks: + * A rw spin lock 'hash_lock' protects just the hash table, + * this is never held in write mode from interrupt context, + * which I believe means that we only have to disable irqs when + * doing a write lock. + * + * An ordinary spin lock 'region_lock' that protects the three + * lists in the region_hash, with the 'state', 'list' and + * 'delayed_bios' fields of the regions. This is used from irq + * context, so all other uses will have to suspend local irqs. + *---------------------------------------------------------------*/ +struct dm_region_hash { + uint32_t region_size; + unsigned region_shift; + + /* holds persistent region state */ + struct dm_dirty_log *log; + + /* hash table */ + rwlock_t hash_lock; + mempool_t *region_pool; + unsigned mask; + unsigned nr_buckets; + unsigned prime; + unsigned shift; + struct list_head *buckets; + + unsigned max_recovery; /* Max # of regions to recover in parallel */ + + spinlock_t region_lock; + atomic_t recovery_in_flight; + struct semaphore recovery_count; + struct list_head clean_regions; + struct list_head quiesced_regions; + struct list_head recovered_regions; + struct list_head failed_recovered_regions; + + void *context; + sector_t target_begin; + + /* Callback function to schedule bios writes */ + void (*dispatch_bios)(void *context, struct bio_list *bios); + + /* Callback function to wakeup callers worker thread. */ + void (*wakeup_workers)(void *context); + + /* Callback function to wakeup callers recovery waiters. */ + void (*wakeup_all_recovery_waiters)(void *context); +}; + +struct dm_region { + struct dm_region_hash *rh; /* FIXME: can we get rid of this ? */ + region_t key; + int state; + + struct list_head hash_list; + struct list_head list; + + atomic_t pending; + struct bio_list delayed_bios; +}; + +/* + * Conversion fns + */ +region_t dm_rh_sector_to_region(struct dm_region_hash *rh, sector_t sector) +{ + return sector >> rh->region_shift; +} +// EXPORT_SYMBOL_GPL(dm_rh_sector_to_region); + +sector_t dm_rh_region_to_sector(struct dm_region_hash *rh, region_t region) +{ + return region << rh->region_shift; +} +// EXPORT_SYMBOL_GPL(dm_rh_region_to_sector); + +region_t dm_rh_bio_to_region(struct dm_region_hash *rh, struct bio *bio) +{ + return dm_rh_sector_to_region(rh, bio->bi_sector - rh->target_begin); +} +// EXPORT_SYMBOL_GPL(dm_rh_bio_to_region); + +void *dm_rh_region_context(struct dm_region *reg) +{ + return reg->rh->context; +} +// EXPORT_SYMBOL_GPL(dm_rh_region_context); + +region_t dm_rh_get_region_key(struct dm_region *reg) +{ + return reg->key; +} +// EXPORT_SYMBOL_GPL(dm_rh_get_region_key); + +sector_t dm_rh_get_region_size(struct dm_region_hash *rh) +{ + return rh->region_size; +} +// EXPORT_SYMBOL_GPL(dm_rh_get_region_size); + +/* + * FIXME: shall we pass in a structure instead of all these args to + * dm_region_hash_create()???? + */ +#define RH_HASH_MULT 2654435387U +#define RH_HASH_SHIFT 12 + +#define MIN_REGIONS 64 +struct dm_region_hash *dm_region_hash_create( + void *context, void (*dispatch_bios)(void *context, + struct bio_list *bios), + void (*wakeup_workers)(void *context), + void (*wakeup_all_recovery_waiters)(void *context), + sector_t target_begin, unsigned max_recovery, + struct dm_dirty_log *log, uint32_t region_size, + region_t nr_regions) +{ + struct dm_region_hash *rh; + unsigned nr_buckets, max_buckets; + size_t i; + + /* + * Calculate a suitable number of buckets for our hash + * table. + */ + max_buckets = nr_regions >> 6; + for (nr_buckets = 128u; nr_buckets < max_buckets; nr_buckets <<= 1) + ; + nr_buckets >>= 1; + + rh = kmalloc(sizeof(*rh), GFP_KERNEL); + if (!rh) { + DMERR("unable to allocate region hash memory"); + return ERR_PTR(-ENOMEM); + } + + rh->context = context; + rh->dispatch_bios = dispatch_bios; + rh->wakeup_workers = wakeup_workers; + rh->wakeup_all_recovery_waiters = wakeup_all_recovery_waiters; + rh->target_begin = target_begin; + rh->max_recovery = max_recovery; + rh->log = log; + rh->region_size = region_size; + rh->region_shift = ffs(region_size) - 1; + rwlock_init(&rh->hash_lock); + rh->mask = nr_buckets - 1; + rh->nr_buckets = nr_buckets; + + rh->shift = RH_HASH_SHIFT; + rh->prime = RH_HASH_MULT; + + rh->buckets = vmalloc(nr_buckets * sizeof(*rh->buckets)); + if (!rh->buckets) { + DMERR("unable to allocate region hash bucket memory"); + kfree(rh); + return ERR_PTR(-ENOMEM); + } + + for (i = 0; i < nr_buckets; i++) + INIT_LIST_HEAD(rh->buckets + i); + + spin_lock_init(&rh->region_lock); + sema_init(&rh->recovery_count, 0); + atomic_set(&rh->recovery_in_flight, 0); + INIT_LIST_HEAD(&rh->clean_regions); + INIT_LIST_HEAD(&rh->quiesced_regions); + INIT_LIST_HEAD(&rh->recovered_regions); + INIT_LIST_HEAD(&rh->failed_recovered_regions); + + rh->region_pool = mempool_create_kmalloc_pool(MIN_REGIONS, + sizeof(struct dm_region)); + if (!rh->region_pool) { + vfree(rh->buckets); + kfree(rh); + rh = ERR_PTR(-ENOMEM); + } + + return rh; +} +// EXPORT_SYMBOL_GPL(dm_region_hash_create); + +void dm_region_hash_destroy(struct dm_region_hash *rh) +{ + unsigned h; + struct dm_region *reg, *nreg; + + BUG_ON(!list_empty(&rh->quiesced_regions)); + for (h = 0; h < rh->nr_buckets; h++) { + list_for_each_entry_safe(reg, nreg, rh->buckets + h, + hash_list) { + BUG_ON(atomic_read(®->pending)); + mempool_free(reg, rh->region_pool); + } + } + + if (rh->log) + dm_dirty_log_destroy(rh->log); + + if (rh->region_pool) + mempool_destroy(rh->region_pool); + + vfree(rh->buckets); + kfree(rh); +} +// EXPORT_SYMBOL_GPL(dm_region_hash_destroy); + +struct dm_dirty_log *dm_rh_dirty_log(struct dm_region_hash *rh) +{ + return rh->log; +} +// EXPORT_SYMBOL_GPL(dm_rh_dirty_log); + +static unsigned rh_hash(struct dm_region_hash *rh, region_t region) +{ + return (unsigned) ((region * rh->prime) >> rh->shift) & rh->mask; +} + +static struct dm_region *__rh_lookup(struct dm_region_hash *rh, region_t region) +{ + struct dm_region *reg; + struct list_head *bucket = rh->buckets + rh_hash(rh, region); + + list_for_each_entry(reg, bucket, hash_list) + if (reg->key == region) + return reg; + + return NULL; +} + +static void __rh_insert(struct dm_region_hash *rh, struct dm_region *reg) +{ + list_add(®->hash_list, rh->buckets + rh_hash(rh, reg->key)); +} + +static struct dm_region *__rh_alloc(struct dm_region_hash *rh, region_t region) +{ + struct dm_region *reg, *nreg; + + nreg = mempool_alloc(rh->region_pool, GFP_ATOMIC); + if (unlikely(!nreg)) + nreg = kmalloc(sizeof(*nreg), GFP_NOIO | __GFP_NOFAIL); + + nreg->state = rh->log->type->in_sync(rh->log, region, 1) ? + DM_RH_CLEAN : DM_RH_NOSYNC; + nreg->rh = rh; + nreg->key = region; + INIT_LIST_HEAD(&nreg->list); + atomic_set(&nreg->pending, 0); + bio_list_init(&nreg->delayed_bios); + + write_lock_irq(&rh->hash_lock); + reg = __rh_lookup(rh, region); + if (reg) + /* We lost the race. */ + mempool_free(nreg, rh->region_pool); + else { + __rh_insert(rh, nreg); + if (nreg->state == DM_RH_CLEAN) { + spin_lock(&rh->region_lock); + list_add(&nreg->list, &rh->clean_regions); + spin_unlock(&rh->region_lock); + } + + reg = nreg; + } + write_unlock_irq(&rh->hash_lock); + + return reg; +} + +static struct dm_region *__rh_find(struct dm_region_hash *rh, region_t region) +{ + struct dm_region *reg; + + reg = __rh_lookup(rh, region); + if (!reg) { + read_unlock(&rh->hash_lock); + reg = __rh_alloc(rh, region); + read_lock(&rh->hash_lock); + } + + return reg; +} + +int dm_rh_get_state(struct dm_region_hash *rh, region_t region, int may_block) +{ + int r; + struct dm_region *reg; + + read_lock(&rh->hash_lock); + reg = __rh_lookup(rh, region); + read_unlock(&rh->hash_lock); + + if (reg) + return reg->state; + + /* + * The region wasn't in the hash, so we fall back to the + * dirty log. + */ + r = rh->log->type->in_sync(rh->log, region, may_block); + + /* + * Any error from the dirty log (eg. -EWOULDBLOCK) gets + * taken as a DM_RH_NOSYNC + */ + return r == 1 ? DM_RH_CLEAN : DM_RH_NOSYNC; +} +// EXPORT_SYMBOL_GPL(dm_rh_get_state); + +static void complete_resync_work(struct dm_region *reg, int success) +{ + struct dm_region_hash *rh = reg->rh; + + rh->log->type->set_region_sync(rh->log, reg->key, success); + + /* + * Dispatch the bios before we call 'wake_up_all'. + * This is important because if we are suspending, + * we want to know that recovery is complete and + * the work queue is flushed. If we wake_up_all + * before we dispatch_bios (queue bios and call wake()), + * then we risk suspending before the work queue + * has been properly flushed. + */ + rh->dispatch_bios(rh->context, ®->delayed_bios); + if (atomic_dec_and_test(&rh->recovery_in_flight)) + rh->wakeup_all_recovery_waiters(rh->context); + up(&rh->recovery_count); +} + +/* dm_rh_mark_nosync + * @ms + * @bio + * @done + * @error + * + * The bio was written on some mirror(s) but failed on other mirror(s). + * We can successfully endio the bio but should avoid the region being + * marked clean by setting the state DM_RH_NOSYNC. + * + * This function is _not_ safe in interrupt context! + */ +void dm_rh_mark_nosync(struct dm_region_hash *rh, + struct bio *bio, unsigned done, int error) +{ + unsigned long flags; + struct dm_dirty_log *log = rh->log; + struct dm_region *reg; + region_t region = dm_rh_bio_to_region(rh, bio); + int recovering = 0; + + /* We must inform the log that the sync count has changed. */ + log->type->set_region_sync(log, region, 0); + + read_lock(&rh->hash_lock); + reg = __rh_find(rh, region); + read_unlock(&rh->hash_lock); + + /* region hash entry should exist because write was in-flight */ + BUG_ON(!reg); + BUG_ON(!list_empty(®->list)); + + spin_lock_irqsave(&rh->region_lock, flags); + /* + * Possible cases: + * 1) DM_RH_DIRTY + * 2) DM_RH_NOSYNC: was dirty, other preceeding writes failed + * 3) DM_RH_RECOVERING: flushing pending writes + * Either case, the region should have not been connected to list. + */ + recovering = (reg->state == DM_RH_RECOVERING); + reg->state = DM_RH_NOSYNC; + BUG_ON(!list_empty(®->list)); + spin_unlock_irqrestore(&rh->region_lock, flags); + + bio_endio(bio, error); + if (recovering) + complete_resync_work(reg, 0); +} +// EXPORT_SYMBOL_GPL(dm_rh_mark_nosync); + +void dm_rh_update_states(struct dm_region_hash *rh, int errors_handled) +{ + struct dm_region *reg, *next; + + LIST_HEAD(clean); + LIST_HEAD(recovered); + LIST_HEAD(failed_recovered); + + /* + * Quickly grab the lists. + */ + write_lock_irq(&rh->hash_lock); + spin_lock(&rh->region_lock); + if (!list_empty(&rh->clean_regions)) { + list_splice_init(&rh->clean_regions, &clean); + + list_for_each_entry(reg, &clean, list) + list_del(®->hash_list); + } + + if (!list_empty(&rh->recovered_regions)) { + list_splice_init(&rh->recovered_regions, &recovered); + + list_for_each_entry(reg, &recovered, list) + list_del(®->hash_list); + } + + if (!list_empty(&rh->failed_recovered_regions)) { + list_splice_init(&rh->failed_recovered_regions, + &failed_recovered); + + list_for_each_entry(reg, &failed_recovered, list) + list_del(®->hash_list); + } + + spin_unlock(&rh->region_lock); + write_unlock_irq(&rh->hash_lock); + + /* + * All the regions on the recovered and clean lists have + * now been pulled out of the system, so no need to do + * any more locking. + */ + list_for_each_entry_safe(reg, next, &recovered, list) { + rh->log->type->clear_region(rh->log, reg->key); + complete_resync_work(reg, 1); + mempool_free(reg, rh->region_pool); + } + + list_for_each_entry_safe(reg, next, &failed_recovered, list) { + complete_resync_work(reg, errors_handled ? 0 : 1); + mempool_free(reg, rh->region_pool); + } + + list_for_each_entry_safe(reg, next, &clean, list) { + rh->log->type->clear_region(rh->log, reg->key); + mempool_free(reg, rh->region_pool); + } + + rh->log->type->flush(rh->log); +} +// EXPORT_SYMBOL_GPL(dm_rh_update_states); + +void dm_rh_inc(struct dm_region_hash *rh, region_t region) +{ + struct dm_region *reg; + + read_lock(&rh->hash_lock); + reg = __rh_find(rh, region); + + spin_lock_irq(&rh->region_lock); + atomic_inc(®->pending); + + if (reg->state == DM_RH_CLEAN) { + reg->state = DM_RH_DIRTY; + list_del_init(®->list); /* take off the clean list */ + spin_unlock_irq(&rh->region_lock); + + rh->log->type->mark_region(rh->log, reg->key); + } else + spin_unlock_irq(&rh->region_lock); + + + read_unlock(&rh->hash_lock); +} +// EXPORT_SYMBOL_GPL(dm_rh_inc); + +void dm_rh_inc_pending(struct dm_region_hash *rh, struct bio_list *bios) +{ + struct bio *bio; + + for (bio = bios->head; bio; bio = bio->bi_next) + dm_rh_inc(rh, dm_rh_bio_to_region(rh, bio)); +} +// EXPORT_SYMBOL_GPL(dm_rh_inc_pending); + +void dm_rh_dec(struct dm_region_hash *rh, region_t region) +{ + unsigned long flags; + struct dm_region *reg; + int should_wake = 0; + + read_lock(&rh->hash_lock); + reg = __rh_lookup(rh, region); + read_unlock(&rh->hash_lock); + + spin_lock_irqsave(&rh->region_lock, flags); + if (atomic_dec_and_test(®->pending)) { + /* + * There is no pending I/O for this region. + * We can move the region to corresponding list for next action. + * At this point, the region is not yet connected to any list. + * + * If the state is DM_RH_NOSYNC, the region should be kept off + * from clean list. + * The hash entry for DM_RH_NOSYNC will remain in memory + * until the region is recovered or the map is reloaded. + */ + + /* do nothing for DM_RH_NOSYNC */ + if (reg->state == DM_RH_RECOVERING) { + list_add_tail(®->list, &rh->quiesced_regions); + } else if (reg->state == DM_RH_DIRTY) { + reg->state = DM_RH_CLEAN; + list_add(®->list, &rh->clean_regions); + } + should_wake = 1; + } + spin_unlock_irqrestore(&rh->region_lock, flags); + + if (should_wake) + rh->wakeup_workers(rh->context); +} +// EXPORT_SYMBOL_GPL(dm_rh_dec); + +/* + * Starts quiescing a region in preparation for recovery. + */ +static int __rh_recovery_prepare(struct dm_region_hash *rh) +{ + int r; + region_t region; + struct dm_region *reg; + + /* + * Ask the dirty log what's next. + */ + r = rh->log->type->get_resync_work(rh->log, ®ion); + if (r <= 0) + return r; + + /* + * Get this region, and start it quiescing by setting the + * recovering flag. + */ + read_lock(&rh->hash_lock); + reg = __rh_find(rh, region); + read_unlock(&rh->hash_lock); + + spin_lock_irq(&rh->region_lock); + reg->state = DM_RH_RECOVERING; + + /* Already quiesced ? */ + if (atomic_read(®->pending)) + list_del_init(®->list); + else + list_move(®->list, &rh->quiesced_regions); + + spin_unlock_irq(&rh->region_lock); + + return 1; +} + +void dm_rh_recovery_prepare(struct dm_region_hash *rh) +{ + /* Extra reference to avoid race with dm_rh_stop_recovery */ + atomic_inc(&rh->recovery_in_flight); + + while (!down_trylock(&rh->recovery_count)) { + atomic_inc(&rh->recovery_in_flight); + if (__rh_recovery_prepare(rh) <= 0) { + atomic_dec(&rh->recovery_in_flight); + up(&rh->recovery_count); + break; + } + } + + /* Drop the extra reference */ + if (atomic_dec_and_test(&rh->recovery_in_flight)) + rh->wakeup_all_recovery_waiters(rh->context); +} +// EXPORT_SYMBOL_GPL(dm_rh_recovery_prepare); + +/* + * Returns any quiesced regions. + */ +struct dm_region *dm_rh_recovery_start(struct dm_region_hash *rh) +{ + struct dm_region *reg = NULL; + + spin_lock_irq(&rh->region_lock); + if (!list_empty(&rh->quiesced_regions)) { + reg = list_entry(rh->quiesced_regions.next, + struct dm_region, list); + list_del_init(®->list); /* remove from the quiesced list */ + } + spin_unlock_irq(&rh->region_lock); + + return reg; +} +// EXPORT_SYMBOL_GPL(dm_rh_recovery_start); + +void dm_rh_recovery_end(struct dm_region *reg, int success) +{ + struct dm_region_hash *rh = reg->rh; + + spin_lock_irq(&rh->region_lock); + if (success) + list_add(®->list, ®->rh->recovered_regions); + else { + reg->state = DM_RH_NOSYNC; + list_add(®->list, ®->rh->failed_recovered_regions); + } + spin_unlock_irq(&rh->region_lock); + + rh->wakeup_workers(rh->context); +} +// EXPORT_SYMBOL_GPL(dm_rh_recovery_end); + +/* Return recovery in flight count. */ +int dm_rh_recovery_in_flight(struct dm_region_hash *rh) +{ + return atomic_read(&rh->recovery_in_flight); +} +// EXPORT_SYMBOL_GPL(dm_rh_recovery_in_flight); + +int dm_rh_flush(struct dm_region_hash *rh) +{ + return rh->log->type->flush(rh->log); +} +// EXPORT_SYMBOL_GPL(dm_rh_flush); + +void dm_rh_delay(struct dm_region_hash *rh, struct bio *bio) +{ + struct dm_region *reg; + + read_lock(&rh->hash_lock); + reg = __rh_find(rh, dm_rh_bio_to_region(rh, bio)); + bio_list_add(®->delayed_bios, bio); + read_unlock(&rh->hash_lock); +} +// EXPORT_SYMBOL_GPL(dm_rh_delay); + +void dm_rh_delay_by_region(struct dm_region_hash *rh, + struct bio *bio, region_t region) +{ + struct dm_region *reg; + + /* FIXME: locking. */ + read_lock(&rh->hash_lock); + reg = __rh_find(rh, region); + bio_list_add(®->delayed_bios, bio); + read_unlock(&rh->hash_lock); +} +// EXPORT_SYMBOL_GPL(dm_rh_delay_by_region); + +void dm_rh_stop_recovery(struct dm_region_hash *rh) +{ + int i; + + /* wait for any recovering regions */ + for (i = 0; i < rh->max_recovery; i++) + down(&rh->recovery_count); +} +// EXPORT_SYMBOL_GPL(dm_rh_stop_recovery); + +void dm_rh_start_recovery(struct dm_region_hash *rh) +{ + int i; + + for (i = 0; i < rh->max_recovery; i++) + up(&rh->recovery_count); + + rh->wakeup_workers(rh->context); +} +// EXPORT_SYMBOL_GPL(dm_rh_start_recovery); + +MODULE_DESCRIPTION(DM_NAME " region hash"); +MODULE_AUTHOR("Joe Thornber/Heinz Mauelshagen <dm-devel@redhat.com>"); +MODULE_LICENSE("GPL"); diff --git a/ubuntu/dm-raid4-5/dm-region-hash.h b/ubuntu/dm-raid4-5/dm-region-hash.h new file mode 100644 index 000000000000..bfd21cb9f768 --- /dev/null +++ b/ubuntu/dm-raid4-5/dm-region-hash.h @@ -0,0 +1,108 @@ +/* + * Copyright (C) 2003 Sistina Software Limited. + * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. + * + * Device-Mapper dirty region hash interface. + * + * This file is released under the GPL. + */ + +#ifndef DM_REGION_HASH_H +#define DM_REGION_HASH_H + +#include <linux/dm-dirty-log.h> + +/*----------------------------------------------------------------- + * Region hash + *----------------------------------------------------------------*/ +struct dm_region_hash; +struct dm_region; + +/* + * States a region can have. + */ +enum dm_rh_region_states { + DM_RH_CLEAN = 0x01, /* No writes in flight. */ + DM_RH_DIRTY = 0x02, /* Writes in flight. */ + DM_RH_NOSYNC = 0x04, /* Out of sync. */ + DM_RH_RECOVERING = 0x08, /* Under resynchronization. */ +}; + +/* + * Region hash create/destroy. + */ +struct bio_list; +struct dm_region_hash *dm_region_hash_create( + void *context, void (*dispatch_bios)(void *context, + struct bio_list *bios), + void (*wakeup_workers)(void *context), + void (*wakeup_all_recovery_waiters)(void *context), + sector_t target_begin, unsigned max_recovery, + struct dm_dirty_log *log, uint32_t region_size, + region_t nr_regions); +void dm_region_hash_destroy(struct dm_region_hash *rh); + +struct dm_dirty_log *dm_rh_dirty_log(struct dm_region_hash *rh); + +/* + * Conversion functions. + */ +region_t dm_rh_bio_to_region(struct dm_region_hash *rh, struct bio *bio); +sector_t dm_rh_region_to_sector(struct dm_region_hash *rh, region_t region); +region_t dm_rh_sector_to_region(struct dm_region_hash *rh, sector_t sector); +void *dm_rh_region_context(struct dm_region *reg); + +/* + * Get region size and key (ie. number of the region). + */ +sector_t dm_rh_get_region_size(struct dm_region_hash *rh); +region_t dm_rh_get_region_key(struct dm_region *reg); + +/* + * Get/set/update region state (and dirty log). + * + */ +int dm_rh_get_state(struct dm_region_hash *rh, region_t region, int may_block); +void dm_rh_set_state(struct dm_region_hash *rh, region_t region, + enum dm_rh_region_states state, int may_block); + +/* Non-zero errors_handled leaves the state of the region NOSYNC */ +void dm_rh_update_states(struct dm_region_hash *rh, int errors_handled); + +/* Flush the region hash and dirty log. */ +int dm_rh_flush(struct dm_region_hash *rh); + +/* Inc/dec pending count on regions. */ +void dm_rh_inc(struct dm_region_hash *rh, region_t region); +void dm_rh_inc_pending(struct dm_region_hash *rh, struct bio_list *bios); +void dm_rh_dec(struct dm_region_hash *rh, region_t region); + +/* Delay bios on regions. */ +void dm_rh_delay(struct dm_region_hash *rh, struct bio *bio); +void dm_rh_delay_by_region(struct dm_region_hash *rh, struct bio *bio, + region_t region); + +void dm_rh_mark_nosync(struct dm_region_hash *rh, + struct bio *bio, unsigned done, int error); + +/* + * Region recovery control. + */ + +/* Prepare some regions for recovery by starting to quiesce them. */ +void dm_rh_recovery_prepare(struct dm_region_hash *rh); + +/* Try fetching a quiesced region for recovery. */ +struct dm_region *dm_rh_recovery_start(struct dm_region_hash *rh); + +/* Report recovery end on a region. */ +void dm_rh_recovery_end(struct dm_region *reg, int error); + +/* Returns number of regions with recovery work outstanding. */ +int dm_rh_recovery_in_flight(struct dm_region_hash *rh); + +/* Start/stop recovery. */ +void dm_rh_start_recovery(struct dm_region_hash *rh); +void dm_rh_stop_recovery(struct dm_region_hash *rh); + +#endif /* DM_REGION_HASH_H */ diff --git a/ubuntu/include/Kbuild b/ubuntu/include/Kbuild new file mode 100644 index 000000000000..c9a138f17b7e --- /dev/null +++ b/ubuntu/include/Kbuild @@ -0,0 +1 @@ +header-y += linux/ diff --git a/ubuntu/include/README b/ubuntu/include/README new file mode 100644 index 000000000000..adc8d33e6d8e --- /dev/null +++ b/ubuntu/include/README @@ -0,0 +1,4 @@ +Only use this directory for things which need to share their headers with +other parts of the kernel or other modules in ubuntu/ + +Otherwise, keep them local to the module directory. diff --git a/ubuntu/include/linux/Kbuild b/ubuntu/include/linux/Kbuild new file mode 100644 index 000000000000..50d9e8c3c627 --- /dev/null +++ b/ubuntu/include/linux/Kbuild @@ -0,0 +1 @@ +header-y += aufs_type.h diff --git a/ubuntu/include/linux/aufs_type.h b/ubuntu/include/linux/aufs_type.h new file mode 100644 index 000000000000..2f2fbcdbcce5 --- /dev/null +++ b/ubuntu/include/linux/aufs_type.h @@ -0,0 +1,233 @@ +/* + * Copyright (C) 2005-2012 Junjiro R. Okajima + * + * This program, aufs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +#ifndef __AUFS_TYPE_H__ +#define __AUFS_TYPE_H__ + +#define AUFS_NAME "aufs" + +#ifdef __KERNEL__ +/* + * define it before including all other headers. + * sched.h may use pr_* macros before defining "current", so define the + * no-current version first, and re-define later. + */ +#define pr_fmt(fmt) AUFS_NAME " %s:%d: " fmt, __func__, __LINE__ +#include <linux/sched.h> +#undef pr_fmt +#define pr_fmt(fmt) AUFS_NAME " %s:%d:%s[%d]: " fmt, \ + __func__, __LINE__, current->comm, current->pid +#else +#include <stdint.h> +#include <sys/types.h> +#endif /* __KERNEL__ */ + +#include <linux/limits.h> + +#define AUFS_VERSION "3.2-20120109" + +/* todo? move this to linux-2.6.19/include/magic.h */ +#define AUFS_SUPER_MAGIC ('a' << 24 | 'u' << 16 | 'f' << 8 | 's') + +/* ---------------------------------------------------------------------- */ + +#ifdef CONFIG_AUFS_BRANCH_MAX_127 +typedef int8_t aufs_bindex_t; +#define AUFS_BRANCH_MAX 127 +#else +typedef int16_t aufs_bindex_t; +#ifdef CONFIG_AUFS_BRANCH_MAX_511 +#define AUFS_BRANCH_MAX 511 +#elif defined(CONFIG_AUFS_BRANCH_MAX_1023) +#define AUFS_BRANCH_MAX 1023 +#elif defined(CONFIG_AUFS_BRANCH_MAX_32767) +#define AUFS_BRANCH_MAX 32767 +#endif +#endif + +#ifdef __KERNEL__ +#ifndef AUFS_BRANCH_MAX +#error unknown CONFIG_AUFS_BRANCH_MAX value +#endif +#endif /* __KERNEL__ */ + +/* ---------------------------------------------------------------------- */ + +#define AUFS_FSTYPE AUFS_NAME + +#define AUFS_ROOT_INO 2 +#define AUFS_FIRST_INO 11 + +#define AUFS_WH_PFX ".wh." +#define AUFS_WH_PFX_LEN ((int)sizeof(AUFS_WH_PFX) - 1) +#define AUFS_WH_TMP_LEN 4 +/* a limit for rmdir/rename a dir */ +#define AUFS_MAX_NAMELEN (NAME_MAX \ + - AUFS_WH_PFX_LEN * 2 /* doubly whiteouted */\ + - 1 /* dot */\ + - AUFS_WH_TMP_LEN) /* hex */ +#define AUFS_XINO_FNAME "." AUFS_NAME ".xino" +#define AUFS_XINO_DEFPATH "/tmp/" AUFS_XINO_FNAME +#define AUFS_XINO_TRUNC_INIT 64 /* blocks */ +#define AUFS_XINO_TRUNC_STEP 4 /* blocks */ +#define AUFS_DIRWH_DEF 3 +#define AUFS_RDCACHE_DEF 10 /* seconds */ +#define AUFS_RDCACHE_MAX 3600 /* seconds */ +#define AUFS_RDBLK_DEF 512 /* bytes */ +#define AUFS_RDHASH_DEF 32 +#define AUFS_WKQ_NAME AUFS_NAME "d" +#define AUFS_MFS_DEF_SEC 30 /* seconds */ +#define AUFS_MFS_MAX_SEC 3600 /* seconds */ +#define AUFS_PLINK_WARN 100 /* number of plinks */ + +/* pseudo-link maintenace under /proc */ +#define AUFS_PLINK_MAINT_NAME "plink_maint" +#define AUFS_PLINK_MAINT_DIR "fs/" AUFS_NAME +#define AUFS_PLINK_MAINT_PATH AUFS_PLINK_MAINT_DIR "/" AUFS_PLINK_MAINT_NAME + +#define AUFS_DIROPQ_NAME AUFS_WH_PFX ".opq" /* whiteouted doubly */ +#define AUFS_WH_DIROPQ AUFS_WH_PFX AUFS_DIROPQ_NAME + +#define AUFS_BASE_NAME AUFS_WH_PFX AUFS_NAME +#define AUFS_PLINKDIR_NAME AUFS_WH_PFX "plnk" +#define AUFS_ORPHDIR_NAME AUFS_WH_PFX "orph" + +/* doubly whiteouted */ +#define AUFS_WH_BASE AUFS_WH_PFX AUFS_BASE_NAME +#define AUFS_WH_PLINKDIR AUFS_WH_PFX AUFS_PLINKDIR_NAME +#define AUFS_WH_ORPHDIR AUFS_WH_PFX AUFS_ORPHDIR_NAME + +/* branch permissions and attributes */ +#define AUFS_BRPERM_RW "rw" +#define AUFS_BRPERM_RO "ro" +#define AUFS_BRPERM_RR "rr" +#define AUFS_BRRATTR_WH "wh" +#define AUFS_BRWATTR_NLWH "nolwh" + +/* ---------------------------------------------------------------------- */ + +/* ioctl */ +enum { + /* readdir in userspace */ + AuCtl_RDU, + AuCtl_RDU_INO, + + /* pathconf wrapper */ + AuCtl_WBR_FD, + + /* busy inode */ + AuCtl_IBUSY +}; + +/* borrowed from linux/include/linux/kernel.h */ +#ifndef ALIGN +#define ALIGN(x, a) __ALIGN_MASK(x, (typeof(x))(a)-1) +#define __ALIGN_MASK(x, mask) (((x)+(mask))&~(mask)) +#endif + +/* borrowed from linux/include/linux/compiler-gcc3.h */ +#ifndef __aligned +#define __aligned(x) __attribute__((aligned(x))) +#endif + +#ifdef __KERNEL__ +#ifndef __packed +#define __packed __attribute__((packed)) +#endif +#endif + +struct au_rdu_cookie { + uint64_t h_pos; + int16_t bindex; + uint8_t flags; + uint8_t pad; + uint32_t generation; +} __aligned(8); + +struct au_rdu_ent { + uint64_t ino; + int16_t bindex; + uint8_t type; + uint8_t nlen; + uint8_t wh; + char name[0]; +} __aligned(8); + +static inline int au_rdu_len(int nlen) +{ + /* include the terminating NULL */ + return ALIGN(sizeof(struct au_rdu_ent) + nlen + 1, + sizeof(uint64_t)); +} + +union au_rdu_ent_ul { + struct au_rdu_ent __user *e; + uint64_t ul; +}; + +enum { + AufsCtlRduV_SZ, + AufsCtlRduV_End +}; + +struct aufs_rdu { + /* input */ + union { + uint64_t sz; /* AuCtl_RDU */ + uint64_t nent; /* AuCtl_RDU_INO */ + }; + union au_rdu_ent_ul ent; + uint16_t verify[AufsCtlRduV_End]; + + /* input/output */ + uint32_t blk; + + /* output */ + union au_rdu_ent_ul tail; + /* number of entries which were added in a single call */ + uint64_t rent; + uint8_t full; + uint8_t shwh; + + struct au_rdu_cookie cookie; +} __aligned(8); + +/* ---------------------------------------------------------------------- */ + +struct aufs_wbr_fd { + uint32_t oflags; + int16_t brid; +} __aligned(8); + +/* ---------------------------------------------------------------------- */ + +struct aufs_ibusy { + uint64_t ino, h_ino; + int16_t bindex; +} __aligned(8); + +/* ---------------------------------------------------------------------- */ + +#define AuCtlType 'A' +#define AUFS_CTL_RDU _IOWR(AuCtlType, AuCtl_RDU, struct aufs_rdu) +#define AUFS_CTL_RDU_INO _IOWR(AuCtlType, AuCtl_RDU_INO, struct aufs_rdu) +#define AUFS_CTL_WBR_FD _IOW(AuCtlType, AuCtl_WBR_FD, \ + struct aufs_wbr_fd) +#define AUFS_CTL_IBUSY _IOWR(AuCtlType, AuCtl_IBUSY, struct aufs_ibusy) + +#endif /* __AUFS_TYPE_H__ */ |