linux_dsm_epyc7002/include/linux/fs.h

2922 lines
96 KiB
C
Raw Normal View History

#ifndef _LINUX_FS_H
#define _LINUX_FS_H
#include <linux/linkage.h>
#include <linux/wait.h>
#include <linux/kdev_t.h>
#include <linux/dcache.h>
#include <linux/path.h>
#include <linux/stat.h>
#include <linux/cache.h>
#include <linux/list.h>
#include <linux/list_lru.h>
#include <linux/llist.h>
#include <linux/radix-tree.h>
#include <linux/rbtree.h>
#include <linux/init.h>
#include <linux/pid.h>
#include <linux/bug.h>
#include <linux/mutex.h>
#include <linux/rwsem.h>
#include <linux/capability.h>
#include <linux/semaphore.h>
#include <linux/fiemap.h>
#include <linux/rculist_bl.h>
#include <linux/atomic.h>
#include <linux/shrinker.h>
#include <linux/migrate_mode.h>
#include <linux/uidgid.h>
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 21:20:34 +07:00
#include <linux/lockdep.h>
#include <linux/percpu-rwsem.h>
#include <linux/blk_types.h>
#include <asm/byteorder.h>
#include <uapi/linux/fs.h>
struct backing_dev_info;
struct export_operations;
struct hd_geometry;
struct iovec;
struct nameidata;
struct kiocb;
struct kobject;
struct pipe_inode_info;
struct poll_table_struct;
struct kstatfs;
struct vm_area_struct;
struct vfsmount;
struct cred;
struct swap_info_struct;
struct seq_file;
struct workqueue_struct;
struct iov_iter;
struct vm_fault;
extern void __init inode_init(void);
extern void __init inode_init_early(void);
extern void __init files_init(unsigned long);
extern struct files_stat_struct files_stat;
fs: allow for more than 2^31 files Robin Holt tried to boot a 16TB system and found af_unix was overflowing a 32bit value : <quote> We were seeing a failure which prevented boot. The kernel was incapable of creating either a named pipe or unix domain socket. This comes down to a common kernel function called unix_create1() which does: atomic_inc(&unix_nr_socks); if (atomic_read(&unix_nr_socks) > 2 * get_max_files()) goto out; The function get_max_files() is a simple return of files_stat.max_files. files_stat.max_files is a signed integer and is computed in fs/file_table.c's files_init(). n = (mempages * (PAGE_SIZE / 1024)) / 10; files_stat.max_files = n; In our case, mempages (total_ram_pages) is approx 3,758,096,384 (0xe0000000). That leaves max_files at approximately 1,503,238,553. This causes 2 * get_max_files() to integer overflow. </quote> Fix is to let /proc/sys/fs/file-nr & /proc/sys/fs/file-max use long integers, and change af_unix to use an atomic_long_t instead of atomic_t. get_max_files() is changed to return an unsigned long. get_nr_files() is changed to return a long. unix_nr_socks is changed from atomic_t to atomic_long_t, while not strictly needed to address Robin problem. Before patch (on a 64bit kernel) : # echo 2147483648 >/proc/sys/fs/file-max # cat /proc/sys/fs/file-max -18446744071562067968 After patch: # echo 2147483648 >/proc/sys/fs/file-max # cat /proc/sys/fs/file-max 2147483648 # cat /proc/sys/fs/file-nr 704 0 2147483648 Reported-by: Robin Holt <holt@sgi.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Acked-by: David Miller <davem@davemloft.net> Reviewed-by: Robin Holt <holt@sgi.com> Tested-by: Robin Holt <holt@sgi.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-27 04:22:44 +07:00
extern unsigned long get_max_files(void);
extern int sysctl_nr_open;
extern struct inodes_stat_t inodes_stat;
extern int leases_enable, lease_break_time;
fs: add link restrictions This adds symlink and hardlink restrictions to the Linux VFS. 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 The solution is to 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. Some pointers to the history of earlier discussion that I could find: 1996 Aug, Zygo Blaxell http://marc.info/?l=bugtraq&m=87602167419830&w=2 1996 Oct, Andrew Tridgell http://lkml.indiana.edu/hypermail/linux/kernel/9610.2/0086.html 1997 Dec, Albert D Cahalan http://lkml.org/lkml/1997/12/16/4 2005 Feb, Lorenzo Hernández García-Hierro http://lkml.indiana.edu/hypermail/linux/kernel/0502.0/1896.html 2010 May, Kees Cook https://lkml.org/lkml/2010/5/30/144 Past objections and rebuttals could be summarized as: - Violates POSIX. - POSIX didn't consider this situation and it's not useful to follow a broken specification at the cost of security. - Might break unknown applications that use this feature. - Applications that break because of the change are easy to spot and fix. Applications that are vulnerable to symlink ToCToU by not having the change aren't. Additionally, no applications have yet been found that rely on this behavior. - Applications should just use mkstemp() or O_CREATE|O_EXCL. - True, but applications are not perfect, and new software is written all the time that makes these mistakes; blocking this flaw at the kernel is a single solution to the entire class of vulnerability. - This should live in the core VFS. - This should live in an LSM. (https://lkml.org/lkml/2010/5/31/135) - This should live in an LSM. - This should live in the core VFS. (https://lkml.org/lkml/2010/8/2/188) Hardlinks: On systems that have user-writable directories on the same partition as system files, a long-standing class of security issues is the hardlink-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 hardlink (i.e. a root process follows a hardlink created by another user). Additionally, an issue exists where users can "pin" a potentially vulnerable setuid/setgid file so that an administrator will not actually upgrade a system fully. The solution is to permit hardlinks to only be created when the user is already the existing file's owner, or if they already have read/write access to the existing file. Many Linux users are surprised when they learn they can link to files they have no access to, so this change appears to follow the doctrine of "least surprise". Additionally, this change does not violate POSIX, which states "the implementation may require that the calling process has permission to access the existing file"[1]. This change is known to break some implementations of the "at" daemon, though the version used by Fedora and Ubuntu has been fixed[2] for a while. Otherwise, the change has been undisruptive while in use in Ubuntu for the last 1.5 years. [1] http://pubs.opengroup.org/onlinepubs/9699919799/functions/linkat.html [2] http://anonscm.debian.org/gitweb/?p=collab-maint/at.git;a=commitdiff;h=f4114656c3a6c6f6070e315ffdf940a49eda3279 This patch is based on the patches in Openwall and grsecurity, along with suggestions from Al Viro. I have added a sysctl to enable the protected behavior, and documentation. Signed-off-by: Kees Cook <keescook@chromium.org> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-07-26 07:29:07 +07:00
extern int sysctl_protected_symlinks;
extern int sysctl_protected_hardlinks;
struct buffer_head;
typedef int (get_block_t)(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
ssize_t bytes, void *private);
#define MAY_EXEC 0x00000001
#define MAY_WRITE 0x00000002
#define MAY_READ 0x00000004
#define MAY_APPEND 0x00000008
#define MAY_ACCESS 0x00000010
#define MAY_OPEN 0x00000020
#define MAY_CHDIR 0x00000040
/* called from RCU mode, don't block */
#define MAY_NOT_BLOCK 0x00000080
/*
* flags in file.f_mode. Note that FMODE_READ and FMODE_WRITE must correspond
* to O_WRONLY and O_RDWR via the strange trick in __dentry_open()
*/
/* file is open for reading */
#define FMODE_READ ((__force fmode_t)0x1)
/* file is open for writing */
#define FMODE_WRITE ((__force fmode_t)0x2)
/* file is seekable */
#define FMODE_LSEEK ((__force fmode_t)0x4)
/* file can be accessed using pread */
#define FMODE_PREAD ((__force fmode_t)0x8)
/* file can be accessed using pwrite */
#define FMODE_PWRITE ((__force fmode_t)0x10)
/* File is opened for execution with sys_execve / sys_uselib */
#define FMODE_EXEC ((__force fmode_t)0x20)
/* File is opened with O_NDELAY (only set for block devices) */
#define FMODE_NDELAY ((__force fmode_t)0x40)
/* File is opened with O_EXCL (only set for block devices) */
#define FMODE_EXCL ((__force fmode_t)0x80)
/* File is opened using open(.., 3, ..) and is writeable only for ioctls
(specialy hack for floppy.c) */
#define FMODE_WRITE_IOCTL ((__force fmode_t)0x100)
/* 32bit hashes as llseek() offset (for directories) */
#define FMODE_32BITHASH ((__force fmode_t)0x200)
/* 64bit hashes as llseek() offset (for directories) */
#define FMODE_64BITHASH ((__force fmode_t)0x400)
/*
* Don't update ctime and mtime.
*
* Currently a special hack for the XFS open_by_handle ioctl, but we'll
* hopefully graduate it to a proper O_CMTIME flag supported by open(2) soon.
*/
#define FMODE_NOCMTIME ((__force fmode_t)0x800)
/* Expect random access pattern */
#define FMODE_RANDOM ((__force fmode_t)0x1000)
/* File is huge (eg. /dev/kmem): treat loff_t as unsigned */
#define FMODE_UNSIGNED_OFFSET ((__force fmode_t)0x2000)
/* File is opened with O_PATH; almost nothing can be done with it */
#define FMODE_PATH ((__force fmode_t)0x4000)
/* File needs atomic accesses to f_pos */
#define FMODE_ATOMIC_POS ((__force fmode_t)0x8000)
/* Write access to underlying fs */
#define FMODE_WRITER ((__force fmode_t)0x10000)
/* Has read method(s) */
#define FMODE_CAN_READ ((__force fmode_t)0x20000)
/* Has write method(s) */
#define FMODE_CAN_WRITE ((__force fmode_t)0x40000)
/* File was opened by fanotify and shouldn't generate fanotify events */
#define FMODE_NONOTIFY ((__force fmode_t)0x4000000)
/*
* Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector
* that indicates that they should check the contents of the iovec are
* valid, but not check the memory that the iovec elements
* points too.
*/
#define CHECK_IOVEC_ONLY -1
/*
* The below are the various read and write types that we support. Some of
* them include behavioral modifiers that send information down to the
* block layer and IO scheduler. Terminology:
*
* The block layer uses device plugging to defer IO a little bit, in
* the hope that we will see more IO very shortly. This increases
* coalescing of adjacent IO and thus reduces the number of IOs we
* have to send to the device. It also allows for better queuing,
* if the IO isn't mergeable. If the caller is going to be waiting
* for the IO, then he must ensure that the device is unplugged so
* that the IO is dispatched to the driver.
*
* All IO is handled async in Linux. This is fine for background
* writes, but for reads or writes that someone waits for completion
* on, we want to notify the block layer and IO scheduler so that they
* know about it. That allows them to make better scheduling
* decisions. So when the below references 'sync' and 'async', it
* is referencing this priority hint.
*
* With that in mind, the available types are:
*
* READ A normal read operation. Device will be plugged.
* READ_SYNC A synchronous read. Device is not plugged, caller can
* immediately wait on this read without caring about
* unplugging.
* READA Used for read-ahead operations. Lower priority, and the
* block layer could (in theory) choose to ignore this
* request if it runs into resource problems.
* WRITE A normal async write. Device will be plugged.
* WRITE_SYNC Synchronous write. Identical to WRITE, but passes down
* the hint that someone will be waiting on this IO
* shortly. The write equivalent of READ_SYNC.
* WRITE_ODIRECT Special case write for O_DIRECT only.
* WRITE_FLUSH Like WRITE_SYNC but with preceding cache flush.
* WRITE_FUA Like WRITE_SYNC but data is guaranteed to be on
* non-volatile media on completion.
* WRITE_FLUSH_FUA Combination of WRITE_FLUSH and FUA. The IO is preceded
* by a cache flush and data is guaranteed to be on
* non-volatile media on completion.
*
*/
#define RW_MASK REQ_WRITE
#define RWA_MASK REQ_RAHEAD
#define READ 0
#define WRITE RW_MASK
#define READA RWA_MASK
#define READ_SYNC (READ | REQ_SYNC)
#define WRITE_SYNC (WRITE | REQ_SYNC | REQ_NOIDLE)
#define WRITE_ODIRECT (WRITE | REQ_SYNC)
#define WRITE_FLUSH (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH)
#define WRITE_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FUA)
#define WRITE_FLUSH_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH | REQ_FUA)
/*
* Attribute flags. These should be or-ed together to figure out what
* has been changed!
*/
#define ATTR_MODE (1 << 0)
#define ATTR_UID (1 << 1)
#define ATTR_GID (1 << 2)
#define ATTR_SIZE (1 << 3)
#define ATTR_ATIME (1 << 4)
#define ATTR_MTIME (1 << 5)
#define ATTR_CTIME (1 << 6)
#define ATTR_ATIME_SET (1 << 7)
#define ATTR_MTIME_SET (1 << 8)
#define ATTR_FORCE (1 << 9) /* Not a change, but a change it */
#define ATTR_ATTR_FLAG (1 << 10)
#define ATTR_KILL_SUID (1 << 11)
#define ATTR_KILL_SGID (1 << 12)
#define ATTR_FILE (1 << 13)
#define ATTR_KILL_PRIV (1 << 14)
#define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */
#define ATTR_TIMES_SET (1 << 16)
/*
* Whiteout is represented by a char device. The following constants define the
* mode and device number to use.
*/
#define WHITEOUT_MODE 0
#define WHITEOUT_DEV 0
/*
* This is the Inode Attributes structure, used for notify_change(). It
* uses the above definitions as flags, to know which values have changed.
* Also, in this manner, a Filesystem can look at only the values it cares
* about. Basically, these are the attributes that the VFS layer can
* request to change from the FS layer.
*
* Derek Atkins <warlord@MIT.EDU> 94-10-20
*/
struct iattr {
unsigned int ia_valid;
umode_t ia_mode;
kuid_t ia_uid;
kgid_t ia_gid;
loff_t ia_size;
struct timespec ia_atime;
struct timespec ia_mtime;
struct timespec ia_ctime;
/*
* Not an attribute, but an auxiliary info for filesystems wanting to
* implement an ftruncate() like method. NOTE: filesystem should
* check for (ia_valid & ATTR_FILE), and not for (ia_file != NULL).
*/
struct file *ia_file;
};
/*
* Includes for diskquotas.
*/
#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
*
* @AOP_WRITEPAGE_ACTIVATE: Informs the caller that page writeback has
* completed, that the page is still locked, and
* should be considered active. The VM uses this hint
* to return the page to the active list -- it won't
* be a candidate for writeback again in the near
* future. Other callers must be careful to unlock
* the page if they get this return. Returned by
* writepage();
*
* @AOP_TRUNCATED_PAGE: The AOP method that was handed a locked page has
* unlocked it and the page might have been truncated.
* The caller should back up to acquiring a new page and
* trying again. The aop will be taking reasonable
* precautions not to livelock. If the caller held a page
* reference, it should drop it before retrying. Returned
* by readpage().
*
* address_space_operation functions return these large constants to indicate
* special semantics to the caller. These are much larger than the bytes in a
* page to allow for functions that return the number of bytes operated on in a
* given page.
*/
enum positive_aop_returns {
AOP_WRITEPAGE_ACTIVATE = 0x80000,
AOP_TRUNCATED_PAGE = 0x80001,
};
#define AOP_FLAG_UNINTERRUPTIBLE 0x0001 /* will not do a short write */
#define AOP_FLAG_CONT_EXPAND 0x0002 /* called from cont_expand */
fs: symlink write_begin allocation context fix With the write_begin/write_end aops, page_symlink was broken because it could no longer pass a GFP_NOFS type mask into the point where the allocations happened. They are done in write_begin, which would always assume that the filesystem can be entered from reclaim. This bug could cause filesystem deadlocks. The funny thing with having a gfp_t mask there is that it doesn't really allow the caller to arbitrarily tinker with the context in which it can be called. It couldn't ever be GFP_ATOMIC, for example, because it needs to take the page lock. The only thing any callers care about is __GFP_FS anyway, so turn that into a single flag. Add a new flag for write_begin, AOP_FLAG_NOFS. Filesystems can now act on this flag in their write_begin function. Change __grab_cache_page to accept a nofs argument as well, to honour that flag (while we're there, change the name to grab_cache_page_write_begin which is more instructive and does away with random leading underscores). This is really a more flexible way to go in the end anyway -- if a filesystem happens to want any extra allocations aside from the pagecache ones in ints write_begin function, it may now use GFP_KERNEL (rather than GFP_NOFS) for common case allocations (eg. ocfs2_alloc_write_ctxt, for a random example). [kosaki.motohiro@jp.fujitsu.com: fix ubifs] [kosaki.motohiro@jp.fujitsu.com: fix fuse] Signed-off-by: Nick Piggin <npiggin@suse.de> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: <stable@kernel.org> [2.6.28.x] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> [ Cleaned up the calling convention: just pass in the AOP flags untouched to the grab_cache_page_write_begin() function. That just simplifies everybody, and may even allow future expansion of the logic. - Linus ] Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-05 03:00:53 +07:00
#define AOP_FLAG_NOFS 0x0004 /* used by filesystem to direct
* helper code (eg buffer layer)
* to clear GFP_FS from alloc */
/*
* oh the beauties of C type declarations.
*/
struct page;
struct address_space;
struct writeback_control;
vfs: pagecache usage optimization for pagesize!=blocksize When we read some part of a file through pagecache, if there is a pagecache of corresponding index but this page is not uptodate, read IO is issued and this page will be uptodate. I think this is good for pagesize == blocksize environment but there is room for improvement on pagesize != blocksize environment. Because in this case a page can have multiple buffers and even if a page is not uptodate, some buffers can be uptodate. So I suggest that when all buffers which correspond to a part of a file that we want to read are uptodate, use this pagecache and copy data from this pagecache to user buffer even if a page is not uptodate. This can reduce read IO and improve system throughput. I wrote a benchmark program and got result number with this program. This benchmark do: 1: mount and open a test file. 2: create a 512MB file. 3: close a file and umount. 4: mount and again open a test file. 5: pwrite randomly 300000 times on a test file. offset is aligned by IO size(1024bytes). 6: measure time of preading randomly 100000 times on a test file. The result was: 2.6.26 330 sec 2.6.26-patched 226 sec Arch:i386 Filesystem:ext3 Blocksize:1024 bytes Memory: 1GB On ext3/4, a file is written through buffer/block. So random read/write mixed workloads or random read after random write workloads are optimized with this patch under pagesize != blocksize environment. This test result showed this. The benchmark program is as follows: #include <stdio.h> #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h> #include <unistd.h> #include <time.h> #include <stdlib.h> #include <string.h> #include <sys/mount.h> #define LEN 1024 #define LOOP 1024*512 /* 512MB */ main(void) { unsigned long i, offset, filesize; int fd; char buf[LEN]; time_t t1, t2; if (mount("/dev/sda1", "/root/test1/", "ext3", 0, 0) < 0) { perror("cannot mount\n"); exit(1); } memset(buf, 0, LEN); fd = open("/root/test1/testfile", O_CREAT|O_RDWR|O_TRUNC); if (fd < 0) { perror("cannot open file\n"); exit(1); } for (i = 0; i < LOOP; i++) write(fd, buf, LEN); close(fd); if (umount("/root/test1/") < 0) { perror("cannot umount\n"); exit(1); } if (mount("/dev/sda1", "/root/test1/", "ext3", 0, 0) < 0) { perror("cannot mount\n"); exit(1); } fd = open("/root/test1/testfile", O_RDWR); if (fd < 0) { perror("cannot open file\n"); exit(1); } filesize = LEN * LOOP; for (i = 0; i < 300000; i++){ offset = (random() % filesize) & (~(LEN - 1)); pwrite(fd, buf, LEN, offset); } printf("start test\n"); time(&t1); for (i = 0; i < 100000; i++){ offset = (random() % filesize) & (~(LEN - 1)); pread(fd, buf, LEN, offset); } time(&t2); printf("%ld sec\n", t2-t1); close(fd); if (umount("/root/test1/") < 0) { perror("cannot umount\n"); exit(1); } } Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Christoph Hellwig <hch@infradead.org> Cc: Jan Kara <jack@ucw.cz> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-29 05:46:36 +07:00
/*
* "descriptor" for what we're up to with a read.
* This allows us to use the same read code yet
* have multiple different users of the data that
* we read from a file.
*
* The simplest case just copies the data to user
* mode.
*/
typedef struct {
size_t written;
size_t count;
union {
char __user *buf;
void *data;
} arg;
int error;
} read_descriptor_t;
typedef int (*read_actor_t)(read_descriptor_t *, struct page *,
unsigned long, unsigned long);
struct address_space_operations {
int (*writepage)(struct page *page, struct writeback_control *wbc);
int (*readpage)(struct file *, struct page *);
/* Write back some dirty pages from this mapping. */
int (*writepages)(struct address_space *, struct writeback_control *);
/* Set a page dirty. Return true if this dirtied it */
int (*set_page_dirty)(struct page *page);
int (*readpages)(struct file *filp, struct address_space *mapping,
struct list_head *pages, unsigned nr_pages);
int (*write_begin)(struct file *, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata);
int (*write_end)(struct file *, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata);
/* Unfortunately this kludge is needed for FIBMAP. Don't use it */
sector_t (*bmap)(struct address_space *, sector_t);
void (*invalidatepage) (struct page *, unsigned int, unsigned int);
int (*releasepage) (struct page *, gfp_t);
void (*freepage)(struct page *);
ssize_t (*direct_IO)(int, struct kiocb *, struct iov_iter *iter, loff_t offset);
/*
* migrate the contents of a page to the specified target. If
* migrate_mode is MIGRATE_ASYNC, it must not block.
*/
int (*migratepage) (struct address_space *,
struct page *, struct page *, enum migrate_mode);
int (*launder_page) (struct page *);
int (*is_partially_uptodate) (struct page *, unsigned long,
vfs: pagecache usage optimization for pagesize!=blocksize When we read some part of a file through pagecache, if there is a pagecache of corresponding index but this page is not uptodate, read IO is issued and this page will be uptodate. I think this is good for pagesize == blocksize environment but there is room for improvement on pagesize != blocksize environment. Because in this case a page can have multiple buffers and even if a page is not uptodate, some buffers can be uptodate. So I suggest that when all buffers which correspond to a part of a file that we want to read are uptodate, use this pagecache and copy data from this pagecache to user buffer even if a page is not uptodate. This can reduce read IO and improve system throughput. I wrote a benchmark program and got result number with this program. This benchmark do: 1: mount and open a test file. 2: create a 512MB file. 3: close a file and umount. 4: mount and again open a test file. 5: pwrite randomly 300000 times on a test file. offset is aligned by IO size(1024bytes). 6: measure time of preading randomly 100000 times on a test file. The result was: 2.6.26 330 sec 2.6.26-patched 226 sec Arch:i386 Filesystem:ext3 Blocksize:1024 bytes Memory: 1GB On ext3/4, a file is written through buffer/block. So random read/write mixed workloads or random read after random write workloads are optimized with this patch under pagesize != blocksize environment. This test result showed this. The benchmark program is as follows: #include <stdio.h> #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h> #include <unistd.h> #include <time.h> #include <stdlib.h> #include <string.h> #include <sys/mount.h> #define LEN 1024 #define LOOP 1024*512 /* 512MB */ main(void) { unsigned long i, offset, filesize; int fd; char buf[LEN]; time_t t1, t2; if (mount("/dev/sda1", "/root/test1/", "ext3", 0, 0) < 0) { perror("cannot mount\n"); exit(1); } memset(buf, 0, LEN); fd = open("/root/test1/testfile", O_CREAT|O_RDWR|O_TRUNC); if (fd < 0) { perror("cannot open file\n"); exit(1); } for (i = 0; i < LOOP; i++) write(fd, buf, LEN); close(fd); if (umount("/root/test1/") < 0) { perror("cannot umount\n"); exit(1); } if (mount("/dev/sda1", "/root/test1/", "ext3", 0, 0) < 0) { perror("cannot mount\n"); exit(1); } fd = open("/root/test1/testfile", O_RDWR); if (fd < 0) { perror("cannot open file\n"); exit(1); } filesize = LEN * LOOP; for (i = 0; i < 300000; i++){ offset = (random() % filesize) & (~(LEN - 1)); pwrite(fd, buf, LEN, offset); } printf("start test\n"); time(&t1); for (i = 0; i < 100000; i++){ offset = (random() % filesize) & (~(LEN - 1)); pread(fd, buf, LEN, offset); } time(&t2); printf("%ld sec\n", t2-t1); close(fd); if (umount("/root/test1/") < 0) { perror("cannot umount\n"); exit(1); } } Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Christoph Hellwig <hch@infradead.org> Cc: Jan Kara <jack@ucw.cz> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-29 05:46:36 +07:00
unsigned long);
mm: vmscan: take page buffers dirty and locked state into account Page reclaim keeps track of dirty and under writeback pages and uses it to determine if wait_iff_congested() should stall or if kswapd should begin writing back pages. This fails to account for buffer pages that can be under writeback but not PageWriteback which is the case for filesystems like ext3 ordered mode. Furthermore, PageDirty buffer pages can have all the buffers clean and writepage does no IO so it should not be accounted as congested. This patch adds an address_space operation that filesystems may optionally use to check if a page is really dirty or really under writeback. An implementation is provided for for buffer_heads is added and used for block operations and ext3 in ordered mode. By default the page flags are obeyed. Credit goes to Jan Kara for identifying that the page flags alone are not sufficient for ext3 and sanity checking a number of ideas on how the problem could be addressed. Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Rik van Riel <riel@redhat.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Jiri Slaby <jslaby@suse.cz> Cc: Valdis Kletnieks <Valdis.Kletnieks@vt.edu> Cc: Zlatko Calusic <zcalusic@bitsync.net> Cc: dormando <dormando@rydia.net> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-07-04 05:02:05 +07:00
void (*is_dirty_writeback) (struct page *, bool *, bool *);
int (*error_remove_page)(struct address_space *, struct page *);
mm: add support for a filesystem to activate swap files and use direct_IO for writing swap pages Currently swapfiles are managed entirely by the core VM by using ->bmap to allocate space and write to the blocks directly. This effectively ensures that the underlying blocks are allocated and avoids the need for the swap subsystem to locate what physical blocks store offsets within a file. If the swap subsystem is to use the filesystem information to locate the blocks, it is critical that information such as block groups, block bitmaps and the block descriptor table that map the swap file were resident in memory. This patch adds address_space_operations that the VM can call when activating or deactivating swap backed by a file. int swap_activate(struct file *); int swap_deactivate(struct file *); The ->swap_activate() method is used to communicate to the file that the VM relies on it, and the address_space should take adequate measures such as reserving space in the underlying device, reserving memory for mempools and pinning information such as the block descriptor table in memory. The ->swap_deactivate() method is called on sys_swapoff() if ->swap_activate() returned success. After a successful swapfile ->swap_activate, the swapfile is marked SWP_FILE and swapper_space.a_ops will proxy to sis->swap_file->f_mappings->a_ops using ->direct_io to write swapcache pages and ->readpage to read. It is perfectly possible that direct_IO be used to read the swap pages but it is an unnecessary complication. Similarly, it is possible that ->writepage be used instead of direct_io to write the pages but filesystem developers have stated that calling writepage from the VM is undesirable for a variety of reasons and using direct_IO opens up the possibility of writing back batches of swap pages in the future. [a.p.zijlstra@chello.nl: Original patch] Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: Rik van Riel <riel@redhat.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: David S. Miller <davem@davemloft.net> Cc: Eric B Munson <emunson@mgebm.net> Cc: Eric Paris <eparis@redhat.com> Cc: James Morris <jmorris@namei.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Mike Christie <michaelc@cs.wisc.edu> Cc: Neil Brown <neilb@suse.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: Xiaotian Feng <dfeng@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-08-01 06:44:55 +07:00
/* swapfile support */
int (*swap_activate)(struct swap_info_struct *sis, struct file *file,
sector_t *span);
void (*swap_deactivate)(struct file *file);
};
extern const struct address_space_operations empty_aops;
/*
* pagecache_write_begin/pagecache_write_end must be used by general code
* to write into the pagecache.
*/
int pagecache_write_begin(struct file *, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata);
int pagecache_write_end(struct file *, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata);
struct address_space {
struct inode *host; /* owner: inode, block_device */
struct radix_tree_root page_tree; /* radix tree of all pages */
spinlock_t tree_lock; /* and lock protecting it */
atomic_t i_mmap_writable;/* count VM_SHARED mappings */
struct rb_root i_mmap; /* tree of private and shared mappings */
struct rw_semaphore i_mmap_rwsem; /* protect tree, count, list */
/* Protected by tree_lock together with the radix tree */
unsigned long nrpages; /* number of total pages */
mm + fs: store shadow entries in page cache Reclaim will be leaving shadow entries in the page cache radix tree upon evicting the real page. As those pages are found from the LRU, an iput() can lead to the inode being freed concurrently. At this point, reclaim must no longer install shadow pages because the inode freeing code needs to ensure the page tree is really empty. Add an address_space flag, AS_EXITING, that the inode freeing code sets under the tree lock before doing the final truncate. Reclaim will check for this flag before installing shadow pages. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-04 04:47:49 +07:00
unsigned long nrshadows; /* number of shadow entries */
pgoff_t writeback_index;/* writeback starts here */
const struct address_space_operations *a_ops; /* methods */
unsigned long flags; /* error bits/gfp mask */
spinlock_t private_lock; /* for use by the address_space */
struct list_head private_list; /* ditto */
void *private_data; /* ditto */
} __attribute__((aligned(sizeof(long))));
/*
* On most architectures that alignment is already the case; but
* must be enforced here for CRIS, to let the least significant bit
* of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON.
*/
struct request_queue;
struct block_device {
dev_t bd_dev; /* not a kdev_t - it's a search key */
int bd_openers;
struct inode * bd_inode; /* will die */
struct super_block * bd_super;
struct mutex bd_mutex; /* open/close mutex */
struct list_head bd_inodes;
block: implement bd_claiming and claiming block Currently, device claiming for exclusive open is done after low level open - disk->fops->open() - has completed successfully. This means that exclusive open attempts while a device is already exclusively open will fail only after disk->fops->open() is called. cdrom driver issues commands during open() which means that O_EXCL open attempt can unintentionally inject commands to in-progress command stream for burning thus disturbing burning process. In most cases, this doesn't cause problems because the first command to be issued is TUR which most devices can process in the middle of burning. However, depending on how a device replies to TUR during burning, cdrom driver may end up issuing further commands. This can't be resolved trivially by moving bd_claim() before doing actual open() because that means an open attempt which will end up failing could interfere other legit O_EXCL open attempts. ie. unconfirmed open attempts can fail others. This patch resolves the problem by introducing claiming block which is started by bd_start_claiming() and terminated either by bd_claim() or bd_abort_claiming(). bd_claim() from inside a claiming block is guaranteed to succeed and once a claiming block is started, other bd_start_claiming() or bd_claim() attempts block till the current claiming block is terminated. bd_claim() can still be used standalone although now it always synchronizes against claiming blocks, so the existing users will keep working without any change. blkdev_open() and open_bdev_exclusive() are converted to use claiming blocks so that exclusive open attempts from these functions don't interfere with the existing exclusive open. This problem was discovered while investigating bko#15403. https://bugzilla.kernel.org/show_bug.cgi?id=15403 The burning problem itself can be resolved by updating userspace probing tools to always open w/ O_EXCL. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Matthias-Christian Ott <ott@mirix.org> Cc: Kay Sievers <kay.sievers@vrfy.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2010-04-07 16:53:59 +07:00
void * bd_claiming;
void * bd_holder;
int bd_holders;
implement in-kernel gendisk events handling Currently, media presence polling for removeable block devices is done from userland. There are several issues with this. * Polling is done by periodically opening the device. For SCSI devices, the command sequence generated by such action involves a few different commands including TEST_UNIT_READY. This behavior, while perfectly legal, is different from Windows which only issues single command, GET_EVENT_STATUS_NOTIFICATION. Unfortunately, some ATAPI devices lock up after being periodically queried such command sequences. * There is no reliable and unintrusive way for a userland program to tell whether the target device is safe for media presence polling. For example, polling for media presence during an on-going burning session can make it fail. The polling program can avoid this by opening the device with O_EXCL but then it risks making a valid exclusive user of the device fail w/ -EBUSY. * Userland polling is unnecessarily heavy and in-kernel implementation is lighter and better coordinated (workqueue, timer slack). This patch implements framework for in-kernel disk event handling, which includes media presence polling. * bdops->check_events() is added, which supercedes ->media_changed(). It should check whether there's any pending event and return if so. Currently, two events are defined - DISK_EVENT_MEDIA_CHANGE and DISK_EVENT_EJECT_REQUEST. ->check_events() is guaranteed not to be called parallelly. * gendisk->events and ->async_events are added. These should be initialized by block driver before passing the device to add_disk(). The former contains the mask of all supported events and the latter the mask of all events which the device can report without polling. /sys/block/*/events[_async] export these to userland. * Kernel parameter block.events_dfl_poll_msecs controls the system polling interval (default is 0 which means disable) and /sys/block/*/events_poll_msecs control polling intervals for individual devices (default is -1 meaning use system setting). Note that if a device can report all supported events asynchronously and its polling interval isn't explicitly set, the device won't be polled regardless of the system polling interval. * If a device is opened exclusively with write access, event checking is automatically disabled until all write exclusive accesses are released. * There are event 'clearing' events. For example, both of currently defined events are cleared after the device has been successfully opened. This information is passed to ->check_events() callback using @clearing argument as a hint. * Event checking is always performed from system_nrt_wq and timer slack is set to 25% for polling. * Nothing changes for drivers which implement ->media_changed() but not ->check_events(). Going forward, all drivers will be converted to ->check_events() and ->media_change() will be dropped. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Kay Sievers <kay.sievers@vrfy.org> Cc: Jan Kara <jack@suse.cz> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2010-12-09 02:57:37 +07:00
bool bd_write_holder;
#ifdef CONFIG_SYSFS
struct list_head bd_holder_disks;
#endif
struct block_device * bd_contains;
unsigned bd_block_size;
struct hd_struct * bd_part;
/* number of times partitions within this device have been opened. */
unsigned bd_part_count;
int bd_invalidated;
struct gendisk * bd_disk;
struct request_queue * bd_queue;
struct list_head bd_list;
/*
* Private data. You must have bd_claim'ed the block_device
* to use this. NOTE: bd_claim allows an owner to claim
* the same device multiple times, the owner must take special
* care to not mess up bd_private for that case.
*/
unsigned long bd_private;
/* The counter of freeze processes */
int bd_fsfreeze_count;
/* Mutex for freeze */
struct mutex bd_fsfreeze_mutex;
};
/*
* Radix-tree tags, for tagging dirty and writeback pages within the pagecache
* radix trees
*/
#define PAGECACHE_TAG_DIRTY 0
#define PAGECACHE_TAG_WRITEBACK 1
#define PAGECACHE_TAG_TOWRITE 2
int mapping_tagged(struct address_space *mapping, int tag);
mm,fs: introduce helpers around the i_mmap_mutex This series is a continuation of the conversion of the i_mmap_mutex to rwsem, following what we have for the anon memory counterpart. With Hugh's feedback from the first iteration. Ultimately, the most obvious paths that require exclusive ownership of the lock is when we modify the VMA interval tree, via vma_interval_tree_insert() and vma_interval_tree_remove() families. Cases such as unmapping, where the ptes content is changed but the tree remains untouched should make it safe to share the i_mmap_rwsem. As such, the code of course is straightforward, however the devil is very much in the details. While its been tested on a number of workloads without anything exploding, I would not be surprised if there are some less documented/known assumptions about the lock that could suffer from these changes. Or maybe I'm just missing something, but either way I believe its at the point where it could use more eyes and hopefully some time in linux-next. Because the lock type conversion is the heart of this patchset, its worth noting a few comparisons between mutex vs rwsem (xadd): (i) Same size, no extra footprint. (ii) Both have CONFIG_XXX_SPIN_ON_OWNER capabilities for exclusive lock ownership. (iii) Both can be slightly unfair wrt exclusive ownership, with writer lock stealing properties, not necessarily respecting FIFO order for granting the lock when contended. (iv) Mutexes can be slightly faster than rwsems when the lock is non-contended. (v) Both suck at performance for debug (slowpaths), which shouldn't matter anyway. Sharing the lock is obviously beneficial, and sem writer ownership is close enough to mutexes. The biggest winner of these changes is migration. As for concrete numbers, the following performance results are for a 4-socket 60-core IvyBridge-EX with 130Gb of RAM. Both alltests and disk (xfs+ramdisk) workloads of aim7 suite do quite well with this set, with a steady ~60% throughput (jpm) increase for alltests and up to ~30% for disk for high amounts of concurrency. Lower counts of workload users (< 100) does not show much difference at all, so at least no regressions. 3.18-rc1 3.18-rc1-i_mmap_rwsem alltests-100 17918.72 ( 0.00%) 28417.97 ( 58.59%) alltests-200 16529.39 ( 0.00%) 26807.92 ( 62.18%) alltests-300 16591.17 ( 0.00%) 26878.08 ( 62.00%) alltests-400 16490.37 ( 0.00%) 26664.63 ( 61.70%) alltests-500 16593.17 ( 0.00%) 26433.72 ( 59.30%) alltests-600 16508.56 ( 0.00%) 26409.20 ( 59.97%) alltests-700 16508.19 ( 0.00%) 26298.58 ( 59.31%) alltests-800 16437.58 ( 0.00%) 26433.02 ( 60.81%) alltests-900 16418.35 ( 0.00%) 26241.61 ( 59.83%) alltests-1000 16369.00 ( 0.00%) 26195.76 ( 60.03%) alltests-1100 16330.11 ( 0.00%) 26133.46 ( 60.03%) alltests-1200 16341.30 ( 0.00%) 26084.03 ( 59.62%) alltests-1300 16304.75 ( 0.00%) 26024.74 ( 59.61%) alltests-1400 16231.08 ( 0.00%) 25952.35 ( 59.89%) alltests-1500 16168.06 ( 0.00%) 25850.58 ( 59.89%) alltests-1600 16142.56 ( 0.00%) 25767.42 ( 59.62%) alltests-1700 16118.91 ( 0.00%) 25689.58 ( 59.38%) alltests-1800 16068.06 ( 0.00%) 25599.71 ( 59.32%) alltests-1900 16046.94 ( 0.00%) 25525.92 ( 59.07%) alltests-2000 16007.26 ( 0.00%) 25513.07 ( 59.38%) disk-100 7582.14 ( 0.00%) 7257.48 ( -4.28%) disk-200 6962.44 ( 0.00%) 7109.15 ( 2.11%) disk-300 6435.93 ( 0.00%) 6904.75 ( 7.28%) disk-400 6370.84 ( 0.00%) 6861.26 ( 7.70%) disk-500 6353.42 ( 0.00%) 6846.71 ( 7.76%) disk-600 6368.82 ( 0.00%) 6806.75 ( 6.88%) disk-700 6331.37 ( 0.00%) 6796.01 ( 7.34%) disk-800 6324.22 ( 0.00%) 6788.00 ( 7.33%) disk-900 6253.52 ( 0.00%) 6750.43 ( 7.95%) disk-1000 6242.53 ( 0.00%) 6855.11 ( 9.81%) disk-1100 6234.75 ( 0.00%) 6858.47 ( 10.00%) disk-1200 6312.76 ( 0.00%) 6845.13 ( 8.43%) disk-1300 6309.95 ( 0.00%) 6834.51 ( 8.31%) disk-1400 6171.76 ( 0.00%) 6787.09 ( 9.97%) disk-1500 6139.81 ( 0.00%) 6761.09 ( 10.12%) disk-1600 4807.12 ( 0.00%) 6725.33 ( 39.90%) disk-1700 4669.50 ( 0.00%) 5985.38 ( 28.18%) disk-1800 4663.51 ( 0.00%) 5972.99 ( 28.08%) disk-1900 4674.31 ( 0.00%) 5949.94 ( 27.29%) disk-2000 4668.36 ( 0.00%) 5834.93 ( 24.99%) In addition, a 67.5% increase in successfully migrated NUMA pages, thus improving node locality. The patch layout is simple but designed for bisection (in case reversion is needed if the changes break upstream) and easier review: o Patches 1-4 convert the i_mmap lock from mutex to rwsem. o Patches 5-10 share the lock in specific paths, each patch details the rationale behind why it should be safe. This patchset has been tested with: postgres 9.4 (with brand new hugetlb support), hugetlbfs test suite (all tests pass, in fact more tests pass with these changes than with an upstream kernel), ltp, aim7 benchmarks, memcached and iozone with the -B option for mmap'ing. *Untested* paths are nommu, memory-failure, uprobes and xip. This patch (of 8): Various parts of the kernel acquire and release this mutex, so add i_mmap_lock_write() and immap_unlock_write() helper functions that will encapsulate this logic. The next patch will make use of these. Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: "Kirill A. Shutemov" <kirill@shutemov.name> Acked-by: Hugh Dickins <hughd@google.com> Cc: Oleg Nesterov <oleg@redhat.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Acked-by: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-13 07:54:18 +07:00
static inline void i_mmap_lock_write(struct address_space *mapping)
{
down_write(&mapping->i_mmap_rwsem);
mm,fs: introduce helpers around the i_mmap_mutex This series is a continuation of the conversion of the i_mmap_mutex to rwsem, following what we have for the anon memory counterpart. With Hugh's feedback from the first iteration. Ultimately, the most obvious paths that require exclusive ownership of the lock is when we modify the VMA interval tree, via vma_interval_tree_insert() and vma_interval_tree_remove() families. Cases such as unmapping, where the ptes content is changed but the tree remains untouched should make it safe to share the i_mmap_rwsem. As such, the code of course is straightforward, however the devil is very much in the details. While its been tested on a number of workloads without anything exploding, I would not be surprised if there are some less documented/known assumptions about the lock that could suffer from these changes. Or maybe I'm just missing something, but either way I believe its at the point where it could use more eyes and hopefully some time in linux-next. Because the lock type conversion is the heart of this patchset, its worth noting a few comparisons between mutex vs rwsem (xadd): (i) Same size, no extra footprint. (ii) Both have CONFIG_XXX_SPIN_ON_OWNER capabilities for exclusive lock ownership. (iii) Both can be slightly unfair wrt exclusive ownership, with writer lock stealing properties, not necessarily respecting FIFO order for granting the lock when contended. (iv) Mutexes can be slightly faster than rwsems when the lock is non-contended. (v) Both suck at performance for debug (slowpaths), which shouldn't matter anyway. Sharing the lock is obviously beneficial, and sem writer ownership is close enough to mutexes. The biggest winner of these changes is migration. As for concrete numbers, the following performance results are for a 4-socket 60-core IvyBridge-EX with 130Gb of RAM. Both alltests and disk (xfs+ramdisk) workloads of aim7 suite do quite well with this set, with a steady ~60% throughput (jpm) increase for alltests and up to ~30% for disk for high amounts of concurrency. Lower counts of workload users (< 100) does not show much difference at all, so at least no regressions. 3.18-rc1 3.18-rc1-i_mmap_rwsem alltests-100 17918.72 ( 0.00%) 28417.97 ( 58.59%) alltests-200 16529.39 ( 0.00%) 26807.92 ( 62.18%) alltests-300 16591.17 ( 0.00%) 26878.08 ( 62.00%) alltests-400 16490.37 ( 0.00%) 26664.63 ( 61.70%) alltests-500 16593.17 ( 0.00%) 26433.72 ( 59.30%) alltests-600 16508.56 ( 0.00%) 26409.20 ( 59.97%) alltests-700 16508.19 ( 0.00%) 26298.58 ( 59.31%) alltests-800 16437.58 ( 0.00%) 26433.02 ( 60.81%) alltests-900 16418.35 ( 0.00%) 26241.61 ( 59.83%) alltests-1000 16369.00 ( 0.00%) 26195.76 ( 60.03%) alltests-1100 16330.11 ( 0.00%) 26133.46 ( 60.03%) alltests-1200 16341.30 ( 0.00%) 26084.03 ( 59.62%) alltests-1300 16304.75 ( 0.00%) 26024.74 ( 59.61%) alltests-1400 16231.08 ( 0.00%) 25952.35 ( 59.89%) alltests-1500 16168.06 ( 0.00%) 25850.58 ( 59.89%) alltests-1600 16142.56 ( 0.00%) 25767.42 ( 59.62%) alltests-1700 16118.91 ( 0.00%) 25689.58 ( 59.38%) alltests-1800 16068.06 ( 0.00%) 25599.71 ( 59.32%) alltests-1900 16046.94 ( 0.00%) 25525.92 ( 59.07%) alltests-2000 16007.26 ( 0.00%) 25513.07 ( 59.38%) disk-100 7582.14 ( 0.00%) 7257.48 ( -4.28%) disk-200 6962.44 ( 0.00%) 7109.15 ( 2.11%) disk-300 6435.93 ( 0.00%) 6904.75 ( 7.28%) disk-400 6370.84 ( 0.00%) 6861.26 ( 7.70%) disk-500 6353.42 ( 0.00%) 6846.71 ( 7.76%) disk-600 6368.82 ( 0.00%) 6806.75 ( 6.88%) disk-700 6331.37 ( 0.00%) 6796.01 ( 7.34%) disk-800 6324.22 ( 0.00%) 6788.00 ( 7.33%) disk-900 6253.52 ( 0.00%) 6750.43 ( 7.95%) disk-1000 6242.53 ( 0.00%) 6855.11 ( 9.81%) disk-1100 6234.75 ( 0.00%) 6858.47 ( 10.00%) disk-1200 6312.76 ( 0.00%) 6845.13 ( 8.43%) disk-1300 6309.95 ( 0.00%) 6834.51 ( 8.31%) disk-1400 6171.76 ( 0.00%) 6787.09 ( 9.97%) disk-1500 6139.81 ( 0.00%) 6761.09 ( 10.12%) disk-1600 4807.12 ( 0.00%) 6725.33 ( 39.90%) disk-1700 4669.50 ( 0.00%) 5985.38 ( 28.18%) disk-1800 4663.51 ( 0.00%) 5972.99 ( 28.08%) disk-1900 4674.31 ( 0.00%) 5949.94 ( 27.29%) disk-2000 4668.36 ( 0.00%) 5834.93 ( 24.99%) In addition, a 67.5% increase in successfully migrated NUMA pages, thus improving node locality. The patch layout is simple but designed for bisection (in case reversion is needed if the changes break upstream) and easier review: o Patches 1-4 convert the i_mmap lock from mutex to rwsem. o Patches 5-10 share the lock in specific paths, each patch details the rationale behind why it should be safe. This patchset has been tested with: postgres 9.4 (with brand new hugetlb support), hugetlbfs test suite (all tests pass, in fact more tests pass with these changes than with an upstream kernel), ltp, aim7 benchmarks, memcached and iozone with the -B option for mmap'ing. *Untested* paths are nommu, memory-failure, uprobes and xip. This patch (of 8): Various parts of the kernel acquire and release this mutex, so add i_mmap_lock_write() and immap_unlock_write() helper functions that will encapsulate this logic. The next patch will make use of these. Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: "Kirill A. Shutemov" <kirill@shutemov.name> Acked-by: Hugh Dickins <hughd@google.com> Cc: Oleg Nesterov <oleg@redhat.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Acked-by: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-13 07:54:18 +07:00
}
static inline void i_mmap_unlock_write(struct address_space *mapping)
{
up_write(&mapping->i_mmap_rwsem);
mm,fs: introduce helpers around the i_mmap_mutex This series is a continuation of the conversion of the i_mmap_mutex to rwsem, following what we have for the anon memory counterpart. With Hugh's feedback from the first iteration. Ultimately, the most obvious paths that require exclusive ownership of the lock is when we modify the VMA interval tree, via vma_interval_tree_insert() and vma_interval_tree_remove() families. Cases such as unmapping, where the ptes content is changed but the tree remains untouched should make it safe to share the i_mmap_rwsem. As such, the code of course is straightforward, however the devil is very much in the details. While its been tested on a number of workloads without anything exploding, I would not be surprised if there are some less documented/known assumptions about the lock that could suffer from these changes. Or maybe I'm just missing something, but either way I believe its at the point where it could use more eyes and hopefully some time in linux-next. Because the lock type conversion is the heart of this patchset, its worth noting a few comparisons between mutex vs rwsem (xadd): (i) Same size, no extra footprint. (ii) Both have CONFIG_XXX_SPIN_ON_OWNER capabilities for exclusive lock ownership. (iii) Both can be slightly unfair wrt exclusive ownership, with writer lock stealing properties, not necessarily respecting FIFO order for granting the lock when contended. (iv) Mutexes can be slightly faster than rwsems when the lock is non-contended. (v) Both suck at performance for debug (slowpaths), which shouldn't matter anyway. Sharing the lock is obviously beneficial, and sem writer ownership is close enough to mutexes. The biggest winner of these changes is migration. As for concrete numbers, the following performance results are for a 4-socket 60-core IvyBridge-EX with 130Gb of RAM. Both alltests and disk (xfs+ramdisk) workloads of aim7 suite do quite well with this set, with a steady ~60% throughput (jpm) increase for alltests and up to ~30% for disk for high amounts of concurrency. Lower counts of workload users (< 100) does not show much difference at all, so at least no regressions. 3.18-rc1 3.18-rc1-i_mmap_rwsem alltests-100 17918.72 ( 0.00%) 28417.97 ( 58.59%) alltests-200 16529.39 ( 0.00%) 26807.92 ( 62.18%) alltests-300 16591.17 ( 0.00%) 26878.08 ( 62.00%) alltests-400 16490.37 ( 0.00%) 26664.63 ( 61.70%) alltests-500 16593.17 ( 0.00%) 26433.72 ( 59.30%) alltests-600 16508.56 ( 0.00%) 26409.20 ( 59.97%) alltests-700 16508.19 ( 0.00%) 26298.58 ( 59.31%) alltests-800 16437.58 ( 0.00%) 26433.02 ( 60.81%) alltests-900 16418.35 ( 0.00%) 26241.61 ( 59.83%) alltests-1000 16369.00 ( 0.00%) 26195.76 ( 60.03%) alltests-1100 16330.11 ( 0.00%) 26133.46 ( 60.03%) alltests-1200 16341.30 ( 0.00%) 26084.03 ( 59.62%) alltests-1300 16304.75 ( 0.00%) 26024.74 ( 59.61%) alltests-1400 16231.08 ( 0.00%) 25952.35 ( 59.89%) alltests-1500 16168.06 ( 0.00%) 25850.58 ( 59.89%) alltests-1600 16142.56 ( 0.00%) 25767.42 ( 59.62%) alltests-1700 16118.91 ( 0.00%) 25689.58 ( 59.38%) alltests-1800 16068.06 ( 0.00%) 25599.71 ( 59.32%) alltests-1900 16046.94 ( 0.00%) 25525.92 ( 59.07%) alltests-2000 16007.26 ( 0.00%) 25513.07 ( 59.38%) disk-100 7582.14 ( 0.00%) 7257.48 ( -4.28%) disk-200 6962.44 ( 0.00%) 7109.15 ( 2.11%) disk-300 6435.93 ( 0.00%) 6904.75 ( 7.28%) disk-400 6370.84 ( 0.00%) 6861.26 ( 7.70%) disk-500 6353.42 ( 0.00%) 6846.71 ( 7.76%) disk-600 6368.82 ( 0.00%) 6806.75 ( 6.88%) disk-700 6331.37 ( 0.00%) 6796.01 ( 7.34%) disk-800 6324.22 ( 0.00%) 6788.00 ( 7.33%) disk-900 6253.52 ( 0.00%) 6750.43 ( 7.95%) disk-1000 6242.53 ( 0.00%) 6855.11 ( 9.81%) disk-1100 6234.75 ( 0.00%) 6858.47 ( 10.00%) disk-1200 6312.76 ( 0.00%) 6845.13 ( 8.43%) disk-1300 6309.95 ( 0.00%) 6834.51 ( 8.31%) disk-1400 6171.76 ( 0.00%) 6787.09 ( 9.97%) disk-1500 6139.81 ( 0.00%) 6761.09 ( 10.12%) disk-1600 4807.12 ( 0.00%) 6725.33 ( 39.90%) disk-1700 4669.50 ( 0.00%) 5985.38 ( 28.18%) disk-1800 4663.51 ( 0.00%) 5972.99 ( 28.08%) disk-1900 4674.31 ( 0.00%) 5949.94 ( 27.29%) disk-2000 4668.36 ( 0.00%) 5834.93 ( 24.99%) In addition, a 67.5% increase in successfully migrated NUMA pages, thus improving node locality. The patch layout is simple but designed for bisection (in case reversion is needed if the changes break upstream) and easier review: o Patches 1-4 convert the i_mmap lock from mutex to rwsem. o Patches 5-10 share the lock in specific paths, each patch details the rationale behind why it should be safe. This patchset has been tested with: postgres 9.4 (with brand new hugetlb support), hugetlbfs test suite (all tests pass, in fact more tests pass with these changes than with an upstream kernel), ltp, aim7 benchmarks, memcached and iozone with the -B option for mmap'ing. *Untested* paths are nommu, memory-failure, uprobes and xip. This patch (of 8): Various parts of the kernel acquire and release this mutex, so add i_mmap_lock_write() and immap_unlock_write() helper functions that will encapsulate this logic. The next patch will make use of these. Signed-off-by: Davidlohr Bueso <dbueso@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: "Kirill A. Shutemov" <kirill@shutemov.name> Acked-by: Hugh Dickins <hughd@google.com> Cc: Oleg Nesterov <oleg@redhat.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Acked-by: Mel Gorman <mgorman@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-13 07:54:18 +07:00
}
static inline void i_mmap_lock_read(struct address_space *mapping)
{
down_read(&mapping->i_mmap_rwsem);
}
static inline void i_mmap_unlock_read(struct address_space *mapping)
{
up_read(&mapping->i_mmap_rwsem);
}
/*
* Might pages of this file be mapped into userspace?
*/
static inline int mapping_mapped(struct address_space *mapping)
{
return !RB_EMPTY_ROOT(&mapping->i_mmap);
}
/*
* Might pages of this file have been modified in userspace?
* Note that i_mmap_writable counts all VM_SHARED vmas: do_mmap_pgoff
* marks vma as VM_SHARED if it is shared, and the file was opened for
* writing i.e. vma may be mprotected writable even if now readonly.
*
* If i_mmap_writable is negative, no new writable mappings are allowed. You
* can only deny writable mappings, if none exists right now.
*/
static inline int mapping_writably_mapped(struct address_space *mapping)
{
return atomic_read(&mapping->i_mmap_writable) > 0;
}
static inline int mapping_map_writable(struct address_space *mapping)
{
return atomic_inc_unless_negative(&mapping->i_mmap_writable) ?
0 : -EPERM;
}
static inline void mapping_unmap_writable(struct address_space *mapping)
{
atomic_dec(&mapping->i_mmap_writable);
}
static inline int mapping_deny_writable(struct address_space *mapping)
{
return atomic_dec_unless_positive(&mapping->i_mmap_writable) ?
0 : -EBUSY;
}
static inline void mapping_allow_writable(struct address_space *mapping)
{
atomic_inc(&mapping->i_mmap_writable);
}
/*
* Use sequence counter to get consistent i_size on 32-bit processors.
*/
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
#include <linux/seqlock.h>
#define __NEED_I_SIZE_ORDERED
#define i_size_ordered_init(inode) seqcount_init(&inode->i_size_seqcount)
#else
#define i_size_ordered_init(inode) do { } while (0)
#endif
struct posix_acl;
#define ACL_NOT_CACHED ((void *)(-1))
#define IOP_FASTPERM 0x0001
#define IOP_LOOKUP 0x0002
#define IOP_NOFOLLOW 0x0004
/*
* Keep mostly read-only and often accessed (especially for
* the RCU path lookup and 'stat' data) fields at the beginning
* of the 'struct inode'
*/
struct inode {
umode_t i_mode;
unsigned short i_opflags;
kuid_t i_uid;
kgid_t i_gid;
unsigned int i_flags;
#ifdef CONFIG_FS_POSIX_ACL
struct posix_acl *i_acl;
struct posix_acl *i_default_acl;
#endif
const struct inode_operations *i_op;
struct super_block *i_sb;
struct address_space *i_mapping;
#ifdef CONFIG_SECURITY
void *i_security;
#endif
/* Stat data, not accessed from path walking */
unsigned long i_ino;
/*
* Filesystems may only read i_nlink directly. They shall use the
* following functions for modification:
*
* (set|clear|inc|drop)_nlink
* inode_(inc|dec)_link_count
*/
union {
const unsigned int i_nlink;
unsigned int __i_nlink;
};
dev_t i_rdev;
loff_t i_size;
struct timespec i_atime;
struct timespec i_mtime;
struct timespec i_ctime;
spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */
unsigned short i_bytes;
unsigned int i_blkbits;
blkcnt_t i_blocks;
#ifdef __NEED_I_SIZE_ORDERED
seqcount_t i_size_seqcount;
#endif
/* Misc */
unsigned long i_state;
struct mutex i_mutex;
unsigned long dirtied_when; /* jiffies of first dirtying */
unsigned long dirtied_time_when;
struct hlist_node i_hash;
struct list_head i_wb_list; /* backing dev IO list */
struct list_head i_lru; /* inode LRU list */
struct list_head i_sb_list;
2011-01-07 13:49:49 +07:00
union {
struct hlist_head i_dentry;
2011-01-07 13:49:49 +07:00
struct rcu_head i_rcu;
};
u64 i_version;
atomic_t i_count;
atomic_t i_dio_count;
atomic_t i_writecount;
#ifdef CONFIG_IMA
atomic_t i_readcount; /* struct files open RO */
#endif
const struct file_operations *i_fop; /* former ->i_op->default_file_ops */
struct file_lock_context *i_flctx;
struct address_space i_data;
struct list_head i_devices;
union {
struct pipe_inode_info *i_pipe;
struct block_device *i_bdev;
struct cdev *i_cdev;
};
__u32 i_generation;
#ifdef CONFIG_FSNOTIFY
__u32 i_fsnotify_mask; /* all events this inode cares about */
struct hlist_head i_fsnotify_marks;
#endif
void *i_private; /* fs or device private pointer */
};
static inline int inode_unhashed(struct inode *inode)
{
return hlist_unhashed(&inode->i_hash);
}
/*
* inode->i_mutex nesting subclasses for the lock validator:
*
* 0: the object of the current VFS operation
* 1: parent
* 2: child/target
* 3: xattr
* 4: second non-directory
* 5: second parent (when locking independent directories in rename)
*
* I_MUTEX_NONDIR2 is for certain operations (such as rename) which lock two
* non-directories at once.
*
* The locking order between these classes is
* parent[2] -> child -> grandchild -> normal -> xattr -> second non-directory
*/
enum inode_i_mutex_lock_class
{
I_MUTEX_NORMAL,
I_MUTEX_PARENT,
I_MUTEX_CHILD,
I_MUTEX_XATTR,
I_MUTEX_NONDIR2,
I_MUTEX_PARENT2,
};
void lock_two_nondirectories(struct inode *, struct inode*);
void unlock_two_nondirectories(struct inode *, struct inode*);
/*
* NOTE: in a 32bit arch with a preemptable kernel and
* an UP compile the i_size_read/write must be atomic
* with respect to the local cpu (unlike with preempt disabled),
* but they don't need to be atomic with respect to other cpus like in
* true SMP (so they need either to either locally disable irq around
* the read or for example on x86 they can be still implemented as a
* cmpxchg8b without the need of the lock prefix). For SMP compiles
* and 64bit archs it makes no difference if preempt is enabled or not.
*/
static inline loff_t i_size_read(const struct inode *inode)
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
loff_t i_size;
unsigned int seq;
do {
seq = read_seqcount_begin(&inode->i_size_seqcount);
i_size = inode->i_size;
} while (read_seqcount_retry(&inode->i_size_seqcount, seq));
return i_size;
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
loff_t i_size;
preempt_disable();
i_size = inode->i_size;
preempt_enable();
return i_size;
#else
return inode->i_size;
#endif
}
/*
* NOTE: unlike i_size_read(), i_size_write() does need locking around it
* (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount
* can be lost, resulting in subsequent i_size_read() calls spinning forever.
*/
static inline void i_size_write(struct inode *inode, loff_t i_size)
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
preempt_disable();
write_seqcount_begin(&inode->i_size_seqcount);
inode->i_size = i_size;
write_seqcount_end(&inode->i_size_seqcount);
preempt_enable();
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
preempt_disable();
inode->i_size = i_size;
preempt_enable();
#else
inode->i_size = i_size;
#endif
}
/* Helper functions so that in most cases filesystems will
* not need to deal directly with kuid_t and kgid_t and can
* instead deal with the raw numeric values that are stored
* in the filesystem.
*/
static inline uid_t i_uid_read(const struct inode *inode)
{
return from_kuid(&init_user_ns, inode->i_uid);
}
static inline gid_t i_gid_read(const struct inode *inode)
{
return from_kgid(&init_user_ns, inode->i_gid);
}
static inline void i_uid_write(struct inode *inode, uid_t uid)
{
inode->i_uid = make_kuid(&init_user_ns, uid);
}
static inline void i_gid_write(struct inode *inode, gid_t gid)
{
inode->i_gid = make_kgid(&init_user_ns, gid);
}
static inline unsigned iminor(const struct inode *inode)
{
return MINOR(inode->i_rdev);
}
static inline unsigned imajor(const struct inode *inode)
{
return MAJOR(inode->i_rdev);
}
extern struct block_device *I_BDEV(struct inode *inode);
struct fown_struct {
rwlock_t lock; /* protects pid, uid, euid fields */
struct pid *pid; /* pid or -pgrp where SIGIO should be sent */
enum pid_type pid_type; /* Kind of process group SIGIO should be sent to */
kuid_t uid, euid; /* uid/euid of process setting the owner */
int signum; /* posix.1b rt signal to be delivered on IO */
};
/*
* Track a single file's readahead state
*/
struct file_ra_state {
pgoff_t start; /* where readahead started */
unsigned int size; /* # of readahead pages */
unsigned int async_size; /* do asynchronous readahead when
there are only # of pages ahead */
unsigned int ra_pages; /* Maximum readahead window */
unsigned int mmap_miss; /* Cache miss stat for mmap accesses */
loff_t prev_pos; /* Cache last read() position */
};
/*
* Check if @index falls in the readahead windows.
*/
static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
{
return (index >= ra->start &&
index < ra->start + ra->size);
}
struct file {
union {
struct llist_node fu_llist;
struct rcu_head fu_rcuhead;
} f_u;
struct path f_path;
struct inode *f_inode; /* cached value */
const struct file_operations *f_op;
vfs: do (nearly) lockless generic_file_llseek The i_mutex lock use of generic _file_llseek hurts. Independent processes accessing the same file synchronize over a single lock, even though they have no need for synchronization at all. Under high utilization this can cause llseek to scale very poorly on larger systems. This patch does some rethinking of the llseek locking model: First the 64bit f_pos is not necessarily atomic without locks on 32bit systems. This can already cause races with read() today. This was discussed on linux-kernel in the past and deemed acceptable. The patch does not change that. Let's look at the different seek variants: SEEK_SET: Doesn't really need any locking. If there's a race one writer wins, the other loses. For 32bit the non atomic update races against read() stay the same. Without a lock they can also happen against write() now. The read() race was deemed acceptable in past discussions, and I think if it's ok for read it's ok for write too. => Don't need a lock. SEEK_END: This behaves like SEEK_SET plus it reads the maximum size too. Reading the maximum size would have the 32bit atomic problem. But luckily we already have a way to read the maximum size without locking (i_size_read), so we can just use that instead. Without i_mutex there is no synchronization with write() anymore, however since the write() update is atomic on 64bit it just behaves like another racy SEEK_SET. On non atomic 32bit it's the same as SEEK_SET. => Don't need a lock, but need to use i_size_read() SEEK_CUR: This has a read-modify-write race window on the same file. One could argue that any application doing unsynchronized seeks on the same file is already broken. But for the sake of not adding a regression here I'm using the file->f_lock to synchronize this. Using this lock is much better than the inode mutex because it doesn't synchronize between processes. => So still need a lock, but can use a f_lock. This patch implements this new scheme in generic_file_llseek. I dropped generic_file_llseek_unlocked and changed all callers. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
2011-09-16 06:06:48 +07:00
/*
* Protects f_ep_links, f_flags.
vfs: do (nearly) lockless generic_file_llseek The i_mutex lock use of generic _file_llseek hurts. Independent processes accessing the same file synchronize over a single lock, even though they have no need for synchronization at all. Under high utilization this can cause llseek to scale very poorly on larger systems. This patch does some rethinking of the llseek locking model: First the 64bit f_pos is not necessarily atomic without locks on 32bit systems. This can already cause races with read() today. This was discussed on linux-kernel in the past and deemed acceptable. The patch does not change that. Let's look at the different seek variants: SEEK_SET: Doesn't really need any locking. If there's a race one writer wins, the other loses. For 32bit the non atomic update races against read() stay the same. Without a lock they can also happen against write() now. The read() race was deemed acceptable in past discussions, and I think if it's ok for read it's ok for write too. => Don't need a lock. SEEK_END: This behaves like SEEK_SET plus it reads the maximum size too. Reading the maximum size would have the 32bit atomic problem. But luckily we already have a way to read the maximum size without locking (i_size_read), so we can just use that instead. Without i_mutex there is no synchronization with write() anymore, however since the write() update is atomic on 64bit it just behaves like another racy SEEK_SET. On non atomic 32bit it's the same as SEEK_SET. => Don't need a lock, but need to use i_size_read() SEEK_CUR: This has a read-modify-write race window on the same file. One could argue that any application doing unsynchronized seeks on the same file is already broken. But for the sake of not adding a regression here I'm using the file->f_lock to synchronize this. Using this lock is much better than the inode mutex because it doesn't synchronize between processes. => So still need a lock, but can use a f_lock. This patch implements this new scheme in generic_file_llseek. I dropped generic_file_llseek_unlocked and changed all callers. Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
2011-09-16 06:06:48 +07:00
* Must not be taken from IRQ context.
*/
spinlock_t f_lock;
atomic_long_t f_count;
unsigned int f_flags;
fmode_t f_mode;
struct mutex f_pos_lock;
loff_t f_pos;
struct fown_struct f_owner;
const struct cred *f_cred;
struct file_ra_state f_ra;
u64 f_version;
#ifdef CONFIG_SECURITY
void *f_security;
#endif
/* needed for tty driver, and maybe others */
void *private_data;
#ifdef CONFIG_EPOLL
/* Used by fs/eventpoll.c to link all the hooks to this file */
struct list_head f_ep_links;
epoll: limit paths The current epoll code can be tickled to run basically indefinitely in both loop detection path check (on ep_insert()), and in the wakeup paths. The programs that tickle this behavior set up deeply linked networks of epoll file descriptors that cause the epoll algorithms to traverse them indefinitely. A couple of these sample programs have been previously posted in this thread: https://lkml.org/lkml/2011/2/25/297. To fix the loop detection path check algorithms, I simply keep track of the epoll nodes that have been already visited. Thus, the loop detection becomes proportional to the number of epoll file descriptor and links. This dramatically decreases the run-time of the loop check algorithm. In one diabolical case I tried it reduced the run-time from 15 mintues (all in kernel time) to .3 seconds. Fixing the wakeup paths could be done at wakeup time in a similar manner by keeping track of nodes that have already been visited, but the complexity is harder, since there can be multiple wakeups on different cpus...Thus, I've opted to limit the number of possible wakeup paths when the paths are created. This is accomplished, by noting that the end file descriptor points that are found during the loop detection pass (from the newly added link), are actually the sources for wakeup events. I keep a list of these file descriptors and limit the number and length of these paths that emanate from these 'source file descriptors'. In the current implemetation I allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of length 4 and 10 of length 5. Note that it is sufficient to check the 'source file descriptors' reachable from the newly added link, since no other 'source file descriptors' will have newly added links. This allows us to check only the wakeup paths that may have gotten too long, and not re-check all possible wakeup paths on the system. In terms of the path limit selection, I think its first worth noting that the most common case for epoll, is probably the model where you have 1 epoll file descriptor that is monitoring n number of 'source file descriptors'. In this case, each 'source file descriptor' has a 1 path of length 1. Thus, I believe that the limits I'm proposing are quite reasonable and in fact may be too generous. Thus, I'm hoping that the proposed limits will not prevent any workloads that currently work to fail. In terms of locking, I have extended the use of the 'epmutex' to all epoll_ctl add and remove operations. Currently its only used in a subset of the add paths. I need to hold the epmutex, so that we can correctly traverse a coherent graph, to check the number of paths. I believe that this additional locking is probably ok, since its in the setup/teardown paths, and doesn't affect the running paths, but it certainly is going to add some extra overhead. Also, worth noting is that the epmuex was recently added to the ep_ctl add operations in the initial path loop detection code using the argument that it was not on a critical path. Another thing to note here, is the length of epoll chains that is allowed. Currently, eventpoll.c defines: /* Maximum number of nesting allowed inside epoll sets */ #define EP_MAX_NESTS 4 This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS + 1). However, this limit is currently only enforced during the loop check detection code, and only when the epoll file descriptors are added in a certain order. Thus, this limit is currently easily bypassed. The newly added check for wakeup paths, stricly limits the wakeup paths to a length of 5, regardless of the order in which ep's are linked together. Thus, a side-effect of the new code is a more consistent enforcement of the graph depth. Thus far, I've tested this, using the sample programs previously mentioned, which now either return quickly or return -EINVAL. I've also testing using the piptest.c epoll tester, which showed no difference in performance. I've also created a number of different epoll networks and tested that they behave as expectded. I believe this solves the original diabolical test cases, while still preserving the sane epoll nesting. Signed-off-by: Jason Baron <jbaron@redhat.com> Cc: Nelson Elhage <nelhage@ksplice.com> Cc: Davide Libenzi <davidel@xmailserver.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-13 08:17:43 +07:00
struct list_head f_tfile_llink;
#endif /* #ifdef CONFIG_EPOLL */
struct address_space *f_mapping;
} __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */
struct file_handle {
__u32 handle_bytes;
int handle_type;
/* file identifier */
unsigned char f_handle[0];
};
static inline struct file *get_file(struct file *f)
{
atomic_long_inc(&f->f_count);
return f;
}
#define fput_atomic(x) atomic_long_add_unless(&(x)->f_count, -1, 1)
#define file_count(x) atomic_long_read(&(x)->f_count)
#define MAX_NON_LFS ((1UL<<31) - 1)
/* Page cache limit. The filesystems should put that into their s_maxbytes
limits, otherwise bad things can happen in VM. */
#if BITS_PER_LONG==32
#define MAX_LFS_FILESIZE (((loff_t)PAGE_CACHE_SIZE << (BITS_PER_LONG-1))-1)
#elif BITS_PER_LONG==64
#define MAX_LFS_FILESIZE ((loff_t)0x7fffffffffffffffLL)
#endif
#define FL_POSIX 1
#define FL_FLOCK 2
#define FL_DELEG 4 /* NFSv4 delegation */
#define FL_ACCESS 8 /* not trying to lock, just looking */
#define FL_EXISTS 16 /* when unlocking, test for existence */
#define FL_LEASE 32 /* lease held on this file */
#define FL_CLOSE 64 /* unlock on close */
#define FL_SLEEP 128 /* A blocking lock */
#define FL_DOWNGRADE_PENDING 256 /* Lease is being downgraded */
#define FL_UNLOCK_PENDING 512 /* Lease is being broken */
#define FL_OFDLCK 1024 /* lock is "owned" by struct file */
#define FL_LAYOUT 2048 /* outstanding pNFS layout */
/*
* Special return value from posix_lock_file() and vfs_lock_file() for
* asynchronous locking.
*/
#define FILE_LOCK_DEFERRED 1
/* legacy typedef, should eventually be removed */
typedef void *fl_owner_t;
struct file_lock;
struct file_lock_operations {
void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
void (*fl_release_private)(struct file_lock *);
};
struct lock_manager_operations {
int (*lm_compare_owner)(struct file_lock *, struct file_lock *);
unsigned long (*lm_owner_key)(struct file_lock *);
void (*lm_get_owner)(struct file_lock *, struct file_lock *);
void (*lm_put_owner)(struct file_lock *);
void (*lm_notify)(struct file_lock *); /* unblock callback */
int (*lm_grant)(struct file_lock *, int);
bool (*lm_break)(struct file_lock *);
int (*lm_change)(struct file_lock *, int, struct list_head *);
void (*lm_setup)(struct file_lock *, void **);
};
struct lock_manager {
struct list_head list;
};
struct net;
void locks_start_grace(struct net *, struct lock_manager *);
void locks_end_grace(struct lock_manager *);
int locks_in_grace(struct net *);
/* that will die - we need it for nfs_lock_info */
#include <linux/nfs_fs_i.h>
/*
* struct file_lock represents a generic "file lock". It's used to represent
* POSIX byte range locks, BSD (flock) locks, and leases. It's important to
* note that the same struct is used to represent both a request for a lock and
* the lock itself, but the same object is never used for both.
*
* FIXME: should we create a separate "struct lock_request" to help distinguish
* these two uses?
*
* The varous i_flctx lists are ordered by:
*
* 1) lock owner
* 2) lock range start
* 3) lock range end
*
* Obviously, the last two criteria only matter for POSIX locks.
*/
struct file_lock {
struct file_lock *fl_next; /* singly linked list for this inode */
struct list_head fl_list; /* link into file_lock_context */
struct hlist_node fl_link; /* node in global lists */
struct list_head fl_block; /* circular list of blocked processes */
fl_owner_t fl_owner;
unsigned int fl_flags;
unsigned char fl_type;
unsigned int fl_pid;
int fl_link_cpu; /* what cpu's list is this on? */
struct pid *fl_nspid;
wait_queue_head_t fl_wait;
struct file *fl_file;
loff_t fl_start;
loff_t fl_end;
struct fasync_struct * fl_fasync; /* for lease break notifications */
/* for lease breaks: */
unsigned long fl_break_time;
unsigned long fl_downgrade_time;
const struct file_lock_operations *fl_ops; /* Callbacks for filesystems */
const struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */
union {
struct nfs_lock_info nfs_fl;
struct nfs4_lock_info nfs4_fl;
struct {
struct list_head link; /* link in AFS vnode's pending_locks list */
int state; /* state of grant or error if -ve */
} afs;
} fl_u;
};
struct file_lock_context {
spinlock_t flc_lock;
struct list_head flc_flock;
struct list_head flc_posix;
struct list_head flc_lease;
};
/* The following constant reflects the upper bound of the file/locking space */
#ifndef OFFSET_MAX
#define INT_LIMIT(x) (~((x)1 << (sizeof(x)*8 - 1)))
#define OFFSET_MAX INT_LIMIT(loff_t)
#define OFFT_OFFSET_MAX INT_LIMIT(off_t)
#endif
#include <linux/fcntl.h>
extern void send_sigio(struct fown_struct *fown, int fd, int band);
#ifdef CONFIG_FILE_LOCKING
extern int fcntl_getlk(struct file *, unsigned int, struct flock __user *);
[PATCH] stale POSIX lock handling I believe that there is a problem with the handling of POSIX locks, which the attached patch should address. The problem appears to be a race between fcntl(2) and close(2). A multithreaded application could close a file descriptor at the same time as it is trying to acquire a lock using the same file descriptor. I would suggest that that multithreaded application is not providing the proper synchronization for itself, but the OS should still behave correctly. SUS3 (Single UNIX Specification Version 3, read: POSIX) indicates that when a file descriptor is closed, that all POSIX locks on the file, owned by the process which closed the file descriptor, should be released. The trick here is when those locks are released. The current code releases all locks which exist when close is processing, but any locks in progress are handled when the last reference to the open file is released. There are three cases to consider. One is the simple case, a multithreaded (mt) process has a file open and races to close it and acquire a lock on it. In this case, the close will release one reference to the open file and when the fcntl is done, it will release the other reference. For this situation, no locks should exist on the file when both the close and fcntl operations are done. The current system will handle this case because the last reference to the open file is being released. The second case is when the mt process has dup(2)'d the file descriptor. The close will release one reference to the file and the fcntl, when done, will release another, but there will still be at least one more reference to the open file. One could argue that the existence of a lock on the file after the close has completed is okay, because it was acquired after the close operation and there is still a way for the application to release the lock on the file, using an existing file descriptor. The third case is when the mt process has forked, after opening the file and either before or after becoming an mt process. In this case, each process would hold a reference to the open file. For each process, this degenerates to first case above. However, the lock continues to exist until both processes have released their references to the open file. This lock could block other lock requests. The changes to release the lock when the last reference to the open file aren't quite right because they would allow the lock to exist as long as there was a reference to the open file. This is too long. The new proposed solution is to add support in the fcntl code path to detect a race with close and then to release the lock which was just acquired when such as race is detected. This causes locks to be released in a timely fashion and for the system to conform to the POSIX semantic specification. This was tested by instrumenting a kernel to detect the handling locks and then running a program which generates case #3 above. A dangling lock could be reliably generated. When the changes to detect the close/fcntl race were added, a dangling lock could no longer be generated. Cc: Matthew Wilcox <willy@debian.org> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-07-28 01:45:09 +07:00
extern int fcntl_setlk(unsigned int, struct file *, unsigned int,
struct flock __user *);
#if BITS_PER_LONG == 32
extern int fcntl_getlk64(struct file *, unsigned int, struct flock64 __user *);
[PATCH] stale POSIX lock handling I believe that there is a problem with the handling of POSIX locks, which the attached patch should address. The problem appears to be a race between fcntl(2) and close(2). A multithreaded application could close a file descriptor at the same time as it is trying to acquire a lock using the same file descriptor. I would suggest that that multithreaded application is not providing the proper synchronization for itself, but the OS should still behave correctly. SUS3 (Single UNIX Specification Version 3, read: POSIX) indicates that when a file descriptor is closed, that all POSIX locks on the file, owned by the process which closed the file descriptor, should be released. The trick here is when those locks are released. The current code releases all locks which exist when close is processing, but any locks in progress are handled when the last reference to the open file is released. There are three cases to consider. One is the simple case, a multithreaded (mt) process has a file open and races to close it and acquire a lock on it. In this case, the close will release one reference to the open file and when the fcntl is done, it will release the other reference. For this situation, no locks should exist on the file when both the close and fcntl operations are done. The current system will handle this case because the last reference to the open file is being released. The second case is when the mt process has dup(2)'d the file descriptor. The close will release one reference to the file and the fcntl, when done, will release another, but there will still be at least one more reference to the open file. One could argue that the existence of a lock on the file after the close has completed is okay, because it was acquired after the close operation and there is still a way for the application to release the lock on the file, using an existing file descriptor. The third case is when the mt process has forked, after opening the file and either before or after becoming an mt process. In this case, each process would hold a reference to the open file. For each process, this degenerates to first case above. However, the lock continues to exist until both processes have released their references to the open file. This lock could block other lock requests. The changes to release the lock when the last reference to the open file aren't quite right because they would allow the lock to exist as long as there was a reference to the open file. This is too long. The new proposed solution is to add support in the fcntl code path to detect a race with close and then to release the lock which was just acquired when such as race is detected. This causes locks to be released in a timely fashion and for the system to conform to the POSIX semantic specification. This was tested by instrumenting a kernel to detect the handling locks and then running a program which generates case #3 above. A dangling lock could be reliably generated. When the changes to detect the close/fcntl race were added, a dangling lock could no longer be generated. Cc: Matthew Wilcox <willy@debian.org> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-07-28 01:45:09 +07:00
extern int fcntl_setlk64(unsigned int, struct file *, unsigned int,
struct flock64 __user *);
#endif
extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg);
extern int fcntl_getlease(struct file *filp);
/* fs/locks.c */
void locks_free_lock_context(struct file_lock_context *ctx);
void locks_free_lock(struct file_lock *fl);
extern void locks_init_lock(struct file_lock *);
extern struct file_lock * locks_alloc_lock(void);
extern void locks_copy_lock(struct file_lock *, struct file_lock *);
extern void locks_copy_conflock(struct file_lock *, struct file_lock *);
extern void locks_remove_posix(struct file *, fl_owner_t);
extern void locks_remove_file(struct file *);
extern void locks_release_private(struct file_lock *);
extern void posix_test_lock(struct file *, struct file_lock *);
extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *);
extern int posix_lock_file_wait(struct file *, struct file_lock *);
extern int posix_unblock_lock(struct file_lock *);
extern int vfs_test_lock(struct file *, struct file_lock *);
extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *);
extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl);
extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type);
extern void lease_get_mtime(struct inode *, struct timespec *time);
extern int generic_setlease(struct file *, long, struct file_lock **, void **priv);
extern int vfs_setlease(struct file *, long, struct file_lock **, void **);
extern int lease_modify(struct file_lock *, int, struct list_head *);
#else /* !CONFIG_FILE_LOCKING */
static inline int fcntl_getlk(struct file *file, unsigned int cmd,
struct flock __user *user)
{
return -EINVAL;
}
static inline int fcntl_setlk(unsigned int fd, struct file *file,
unsigned int cmd, struct flock __user *user)
{
return -EACCES;
}
#if BITS_PER_LONG == 32
static inline int fcntl_getlk64(struct file *file, unsigned int cmd,
struct flock64 __user *user)
{
return -EINVAL;
}
static inline int fcntl_setlk64(unsigned int fd, struct file *file,
unsigned int cmd, struct flock64 __user *user)
{
return -EACCES;
}
#endif
static inline int fcntl_setlease(unsigned int fd, struct file *filp, long arg)
{
return -EINVAL;
}
static inline int fcntl_getlease(struct file *filp)
{
return F_UNLCK;
}
static inline void
locks_free_lock_context(struct file_lock_context *ctx)
{
}
static inline void locks_init_lock(struct file_lock *fl)
{
return;
}
static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl)
{
return;
}
static inline void locks_copy_lock(struct file_lock *new, struct file_lock *fl)
{
return;
}
static inline void locks_remove_posix(struct file *filp, fl_owner_t owner)
{
return;
}
static inline void locks_remove_file(struct file *filp)
{
return;
}
static inline void posix_test_lock(struct file *filp, struct file_lock *fl)
{
return;
}
static inline int posix_lock_file(struct file *filp, struct file_lock *fl,
struct file_lock *conflock)
{
return -ENOLCK;
}
static inline int posix_lock_file_wait(struct file *filp, struct file_lock *fl)
{
return -ENOLCK;
}
static inline int posix_unblock_lock(struct file_lock *waiter)
{
return -ENOENT;
}
static inline int vfs_test_lock(struct file *filp, struct file_lock *fl)
{
return 0;
}
static inline int vfs_lock_file(struct file *filp, unsigned int cmd,
struct file_lock *fl, struct file_lock *conf)
{
return -ENOLCK;
}
static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl)
{
return 0;
}
static inline int flock_lock_file_wait(struct file *filp,
struct file_lock *request)
{
return -ENOLCK;
}
static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
{
return 0;
}
static inline void lease_get_mtime(struct inode *inode, struct timespec *time)
{
return;
}
static inline int generic_setlease(struct file *filp, long arg,
struct file_lock **flp, void **priv)
{
return -EINVAL;
}
static inline int vfs_setlease(struct file *filp, long arg,
struct file_lock **lease, void **priv)
{
return -EINVAL;
}
static inline int lease_modify(struct file_lock *fl, int arg,
struct list_head *dispose)
{
return -EINVAL;
}
#endif /* !CONFIG_FILE_LOCKING */
struct fasync_struct {
spinlock_t fa_lock;
int magic;
int fa_fd;
struct fasync_struct *fa_next; /* singly linked list */
struct file *fa_file;
struct rcu_head fa_rcu;
};
#define FASYNC_MAGIC 0x4601
/* SMP safe fasync helpers: */
extern int fasync_helper(int, struct file *, int, struct fasync_struct **);
extern struct fasync_struct *fasync_insert_entry(int, struct file *, struct fasync_struct **, struct fasync_struct *);
extern int fasync_remove_entry(struct file *, struct fasync_struct **);
extern struct fasync_struct *fasync_alloc(void);
extern void fasync_free(struct fasync_struct *);
/* can be called from interrupts */
extern void kill_fasync(struct fasync_struct **, int, int);
extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
extern void f_setown(struct file *filp, unsigned long arg, int force);
extern void f_delown(struct file *filp);
extern pid_t f_getown(struct file *filp);
extern int send_sigurg(struct fown_struct *fown);
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 21:20:34 +07:00
struct mm_struct;
/*
* Umount options
*/
#define MNT_FORCE 0x00000001 /* Attempt to forcibily umount */
#define MNT_DETACH 0x00000002 /* Just detach from the tree */
#define MNT_EXPIRE 0x00000004 /* Mark for expiry */
#define UMOUNT_NOFOLLOW 0x00000008 /* Don't follow symlink on umount */
#define UMOUNT_UNUSED 0x80000000 /* Flag guaranteed to be unused */
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 21:20:34 +07:00
/* Possible states of 'frozen' field */
enum {
SB_UNFROZEN = 0, /* FS is unfrozen */
SB_FREEZE_WRITE = 1, /* Writes, dir ops, ioctls frozen */
SB_FREEZE_PAGEFAULT = 2, /* Page faults stopped as well */
SB_FREEZE_FS = 3, /* For internal FS use (e.g. to stop
* internal threads if needed) */
SB_FREEZE_COMPLETE = 4, /* ->freeze_fs finished successfully */
};
#define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1)
struct sb_writers {
/* Counters for counting writers at each level */
struct percpu_counter counter[SB_FREEZE_LEVELS];
wait_queue_head_t wait; /* queue for waiting for
writers / faults to finish */
int frozen; /* Is sb frozen? */
wait_queue_head_t wait_unfrozen; /* queue for waiting for
sb to be thawed */
#ifdef CONFIG_DEBUG_LOCK_ALLOC
struct lockdep_map lock_map[SB_FREEZE_LEVELS];
#endif
};
struct super_block {
struct list_head s_list; /* Keep this first */
dev_t s_dev; /* search index; _not_ kdev_t */
unsigned char s_blocksize_bits;
unsigned long s_blocksize;
loff_t s_maxbytes; /* Max file size */
struct file_system_type *s_type;
const struct super_operations *s_op;
const struct dquot_operations *dq_op;
const struct quotactl_ops *s_qcop;
const struct export_operations *s_export_op;
unsigned long s_flags;
unsigned long s_magic;
struct dentry *s_root;
struct rw_semaphore s_umount;
int s_count;
atomic_t s_active;
#ifdef CONFIG_SECURITY
void *s_security;
#endif
const struct xattr_handler **s_xattr;
struct list_head s_inodes; /* all inodes */
struct hlist_bl_head s_anon; /* anonymous dentries for (nfs) exporting */
struct list_head s_mounts; /* list of mounts; _not_ for fs use */
struct block_device *s_bdev;
struct backing_dev_info *s_bdi;
struct mtd_info *s_mtd;
struct hlist_node s_instances;
unsigned int s_quota_types; /* Bitmask of supported quota types */
struct quota_info s_dquot; /* Diskquota specific options */
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 21:20:34 +07:00
struct sb_writers s_writers;
char s_id[32]; /* Informational name */
u8 s_uuid[16]; /* UUID */
void *s_fs_info; /* Filesystem private info */
unsigned int s_max_links;
fmode_t s_mode;
/* Granularity of c/m/atime in ns.
Cannot be worse than a second */
u32 s_time_gran;
/*
* The next field is for VFS *only*. No filesystems have any business
* even looking at it. You had been warned.
*/
struct mutex s_vfs_rename_mutex; /* Kludge */
/*
* Filesystem subtype. If non-empty the filesystem type field
* in /proc/mounts will be "type.subtype"
*/
char *s_subtype;
/*
* Saved mount options for lazy filesystems using
* generic_show_options()
*/
char __rcu *s_options;
const struct dentry_operations *s_d_op; /* default d_op for dentries */
/*
* Saved pool identifier for cleancache (-1 means none)
*/
int cleancache_poolid;
struct shrinker s_shrink; /* per-sb shrinker handle */
/* Number of inodes with nlink == 0 but still referenced */
atomic_long_t s_remove_count;
/* Being remounted read-only */
int s_readonly_remount;
/* AIO completions deferred from interrupt context */
struct workqueue_struct *s_dio_done_wq;
struct hlist_head s_pins;
/*
* Keep the lru lists last in the structure so they always sit on their
* own individual cachelines.
*/
struct list_lru s_dentry_lru ____cacheline_aligned_in_smp;
struct list_lru s_inode_lru ____cacheline_aligned_in_smp;
struct rcu_head rcu;
/*
* Indicates how deep in a filesystem stack this SB is
*/
int s_stack_depth;
};
extern struct timespec current_fs_time(struct super_block *sb);
/*
* Snapshotting support.
*/
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 21:20:34 +07:00
void __sb_end_write(struct super_block *sb, int level);
int __sb_start_write(struct super_block *sb, int level, bool wait);
/**
* sb_end_write - drop write access to a superblock
* @sb: the super we wrote to
*
* Decrement number of writers to the filesystem. Wake up possible waiters
* wanting to freeze the filesystem.
*/
static inline void sb_end_write(struct super_block *sb)
{
__sb_end_write(sb, SB_FREEZE_WRITE);
}
/**
* sb_end_pagefault - drop write access to a superblock from a page fault
* @sb: the super we wrote to
*
* Decrement number of processes handling write page fault to the filesystem.
* Wake up possible waiters wanting to freeze the filesystem.
*/
static inline void sb_end_pagefault(struct super_block *sb)
{
__sb_end_write(sb, SB_FREEZE_PAGEFAULT);
}
/**
* sb_end_intwrite - drop write access to a superblock for internal fs purposes
* @sb: the super we wrote to
*
* Decrement fs-internal number of writers to the filesystem. Wake up possible
* waiters wanting to freeze the filesystem.
*/
static inline void sb_end_intwrite(struct super_block *sb)
{
__sb_end_write(sb, SB_FREEZE_FS);
}
/**
* sb_start_write - get write access to a superblock
* @sb: the super we write to
*
* When a process wants to write data or metadata to a file system (i.e. dirty
* a page or an inode), it should embed the operation in a sb_start_write() -
* sb_end_write() pair to get exclusion against file system freezing. This
* function increments number of writers preventing freezing. If the file
* system is already frozen, the function waits until the file system is
* thawed.
*
* Since freeze protection behaves as a lock, users have to preserve
* ordering of freeze protection and other filesystem locks. Generally,
* freeze protection should be the outermost lock. In particular, we have:
*
* sb_start_write
* -> i_mutex (write path, truncate, directory ops, ...)
* -> s_umount (freeze_super, thaw_super)
*/
static inline void sb_start_write(struct super_block *sb)
{
__sb_start_write(sb, SB_FREEZE_WRITE, true);
}
static inline int sb_start_write_trylock(struct super_block *sb)
{
return __sb_start_write(sb, SB_FREEZE_WRITE, false);
}
/**
* sb_start_pagefault - get write access to a superblock from a page fault
* @sb: the super we write to
*
* When a process starts handling write page fault, it should embed the
* operation into sb_start_pagefault() - sb_end_pagefault() pair to get
* exclusion against file system freezing. This is needed since the page fault
* is going to dirty a page. This function increments number of running page
* faults preventing freezing. If the file system is already frozen, the
* function waits until the file system is thawed.
*
* Since page fault freeze protection behaves as a lock, users have to preserve
* ordering of freeze protection and other filesystem locks. It is advised to
* put sb_start_pagefault() close to mmap_sem in lock ordering. Page fault
* handling code implies lock dependency:
*
* mmap_sem
* -> sb_start_pagefault
*/
static inline void sb_start_pagefault(struct super_block *sb)
{
__sb_start_write(sb, SB_FREEZE_PAGEFAULT, true);
}
/*
* sb_start_intwrite - get write access to a superblock for internal fs purposes
* @sb: the super we write to
*
* This is the third level of protection against filesystem freezing. It is
* free for use by a filesystem. The only requirement is that it must rank
* below sb_start_pagefault.
*
* For example filesystem can call sb_start_intwrite() when starting a
* transaction which somewhat eases handling of freezing for internal sources
* of filesystem changes (internal fs threads, discarding preallocation on file
* close, etc.).
*/
static inline void sb_start_intwrite(struct super_block *sb)
{
__sb_start_write(sb, SB_FREEZE_FS, true);
}
extern bool inode_owner_or_capable(const struct inode *inode);
/*
* VFS helper functions..
*/
extern int vfs_create(struct inode *, struct dentry *, umode_t, bool);
extern int vfs_mkdir(struct inode *, struct dentry *, umode_t);
extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
extern int vfs_symlink(struct inode *, struct dentry *, const char *);
extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct inode **);
extern int vfs_rmdir(struct inode *, struct dentry *);
extern int vfs_unlink(struct inode *, struct dentry *, struct inode **);
extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int);
extern int vfs_whiteout(struct inode *, struct dentry *);
/*
* VFS dentry helper functions.
*/
extern void dentry_unhash(struct dentry *dentry);
/*
* VFS file helper functions.
*/
extern void inode_init_owner(struct inode *inode, const struct inode *dir,
umode_t mode);
/*
* VFS FS_IOC_FIEMAP helper definitions.
*/
struct fiemap_extent_info {
unsigned int fi_flags; /* Flags as passed from user */
unsigned int fi_extents_mapped; /* Number of mapped extents */
unsigned int fi_extents_max; /* Size of fiemap_extent array */
struct fiemap_extent __user *fi_extents_start; /* Start of
fiemap_extent array */
};
int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical,
u64 phys, u64 len, u32 flags);
int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags);
/*
* File types
*
* NOTE! These match bits 12..15 of stat.st_mode
* (ie "(i_mode >> 12) & 15").
*/
#define DT_UNKNOWN 0
#define DT_FIFO 1
#define DT_CHR 2
#define DT_DIR 4
#define DT_BLK 6
#define DT_REG 8
#define DT_LNK 10
#define DT_SOCK 12
#define DT_WHT 14
/*
* This is the "filldir" function type, used by readdir() to let
* the kernel specify what kind of dirent layout it wants to have.
* This allows the kernel to read directories into kernel space or
* to have different dirent layouts depending on the binary type.
*/
struct dir_context;
typedef int (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64,
unsigned);
struct dir_context {
const filldir_t actor;
loff_t pos;
};
struct block_device_operations;
/* These macros are for out of kernel modules to test that
* the kernel supports the unlocked_ioctl and compat_ioctl
* fields in struct file_operations. */
#define HAVE_COMPAT_IOCTL 1
#define HAVE_UNLOCKED_IOCTL 1
/*
* These flags let !MMU mmap() govern direct device mapping vs immediate
* copying more easily for MAP_PRIVATE, especially for ROM filesystems.
*
* NOMMU_MAP_COPY: Copy can be mapped (MAP_PRIVATE)
* NOMMU_MAP_DIRECT: Can be mapped directly (MAP_SHARED)
* NOMMU_MAP_READ: Can be mapped for reading
* NOMMU_MAP_WRITE: Can be mapped for writing
* NOMMU_MAP_EXEC: Can be mapped for execution
*/
#define NOMMU_MAP_COPY 0x00000001
#define NOMMU_MAP_DIRECT 0x00000008
#define NOMMU_MAP_READ VM_MAYREAD
#define NOMMU_MAP_WRITE VM_MAYWRITE
#define NOMMU_MAP_EXEC VM_MAYEXEC
#define NOMMU_VMFLAGS \
(NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC)
struct iov_iter;
struct file_operations {
struct module *owner;
loff_t (*llseek) (struct file *, loff_t, int);
ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
int (*iterate) (struct file *, struct dir_context *);
unsigned int (*poll) (struct file *, struct poll_table_struct *);
long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
int (*mmap) (struct file *, struct vm_area_struct *);
aio: Make it possible to remap aio ring There are actually two issues this patch addresses. Let me start with the one I tried to solve in the beginning. So, in the checkpoint-restore project (criu) we try to dump tasks' state and restore one back exactly as it was. One of the tasks' state bits is rings set up with io_setup() call. There's (almost) no problems in dumping them, there's a problem restoring them -- if I dump a task with aio ring originally mapped at address A, I want to restore one back at exactly the same address A. Unfortunately, the io_setup() does not allow for that -- it mmaps the ring at whatever place mm finds appropriate (it calls do_mmap_pgoff() with zero address and without the MAP_FIXED flag). To make restore possible I'm going to mremap() the freshly created ring into the address A (under which it was seen before dump). The problem is that the ring's virtual address is passed back to the user-space as the context ID and this ID is then used as search key by all the other io_foo() calls. Reworking this ID to be just some integer doesn't seem to work, as this value is already used by libaio as a pointer using which this library accesses memory for aio meta-data. So, to make restore work we need to make sure that a) ring is mapped at desired virtual address b) kioctx->user_id matches this value Having said that, the patch makes mremap() on aio region update the kioctx's user_id and mmap_base values. Here appears the 2nd issue I mentioned in the beginning of this mail. If (regardless of the C/R dances I do) someone creates an io context with io_setup(), then mremap()-s the ring and then destroys the context, the kill_ioctx() routine will call munmap() on wrong (old) address. This will result in a) aio ring remaining in memory and b) some other vma get unexpectedly unmapped. What do you think? Signed-off-by: Pavel Emelyanov <xemul@parallels.com> Acked-by: Dmitry Monakhov <dmonakhov@openvz.org> Signed-off-by: Benjamin LaHaise <bcrl@kvack.org>
2014-09-18 22:56:17 +07:00
void (*mremap)(struct file *, struct vm_area_struct *);
int (*open) (struct inode *, struct file *);
int (*flush) (struct file *, fl_owner_t id);
int (*release) (struct inode *, struct file *);
int (*fsync) (struct file *, loff_t, loff_t, int datasync);
int (*aio_fsync) (struct kiocb *, int datasync);
int (*fasync) (int, struct file *, int);
int (*lock) (struct file *, int, struct file_lock *);
ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int);
unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
int (*check_flags)(int);
int (*flock) (struct file *, int, struct file_lock *);
ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int);
int (*setlease)(struct file *, long, struct file_lock **, void **);
long (*fallocate)(struct file *file, int mode, loff_t offset,
loff_t len);
void (*show_fdinfo)(struct seq_file *m, struct file *f);
#ifndef CONFIG_MMU
unsigned (*mmap_capabilities)(struct file *);
#endif
};
struct inode_operations {
struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
void * (*follow_link) (struct dentry *, struct nameidata *);
int (*permission) (struct inode *, int);
struct posix_acl * (*get_acl)(struct inode *, int);
int (*readlink) (struct dentry *, char __user *,int);
void (*put_link) (struct dentry *, struct nameidata *, void *);
int (*create) (struct inode *,struct dentry *, umode_t, bool);
int (*link) (struct dentry *,struct inode *,struct dentry *);
int (*unlink) (struct inode *,struct dentry *);
int (*symlink) (struct inode *,struct dentry *,const char *);
int (*mkdir) (struct inode *,struct dentry *,umode_t);
int (*rmdir) (struct inode *,struct dentry *);
int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
int (*rename) (struct inode *, struct dentry *,
struct inode *, struct dentry *);
int (*rename2) (struct inode *, struct dentry *,
struct inode *, struct dentry *, unsigned int);
int (*setattr) (struct dentry *, struct iattr *);
int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *);
int (*setxattr) (struct dentry *, const char *,const void *,size_t,int);
ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t);
ssize_t (*listxattr) (struct dentry *, char *, size_t);
int (*removexattr) (struct dentry *, const char *);
int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
u64 len);
int (*update_time)(struct inode *, struct timespec *, int);
int (*atomic_open)(struct inode *, struct dentry *,
struct file *, unsigned open_flag,
umode_t create_mode, int *opened);
int (*tmpfile) (struct inode *, struct dentry *, umode_t);
int (*set_acl)(struct inode *, struct posix_acl *, int);
/* WARNING: probably going away soon, do not use! */
int (*dentry_open)(struct dentry *, struct file *, const struct cred *);
} ____cacheline_aligned;
ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
Cross Memory Attach The basic idea behind cross memory attach is to allow MPI programs doing intra-node communication to do a single copy of the message rather than a double copy of the message via shared memory. The following patch attempts to achieve this by allowing a destination process, given an address and size from a source process, to copy memory directly from the source process into its own address space via a system call. There is also a symmetrical ability to copy from the current process's address space into a destination process's address space. - Use of /proc/pid/mem has been considered, but there are issues with using it: - Does not allow for specifying iovecs for both src and dest, assuming preadv or pwritev was implemented either the area read from or written to would need to be contiguous. - Currently mem_read allows only processes who are currently ptrace'ing the target and are still able to ptrace the target to read from the target. This check could possibly be moved to the open call, but its not clear exactly what race this restriction is stopping (reason appears to have been lost) - Having to send the fd of /proc/self/mem via SCM_RIGHTS on unix domain socket is a bit ugly from a userspace point of view, especially when you may have hundreds if not (eventually) thousands of processes that all need to do this with each other - Doesn't allow for some future use of the interface we would like to consider adding in the future (see below) - Interestingly reading from /proc/pid/mem currently actually involves two copies! (But this could be fixed pretty easily) As mentioned previously use of vmsplice instead was considered, but has problems. Since you need the reader and writer working co-operatively if the pipe is not drained then you block. Which requires some wrapping to do non blocking on the send side or polling on the receive. In all to all communication it requires ordering otherwise you can deadlock. And in the example of many MPI tasks writing to one MPI task vmsplice serialises the copying. There are some cases of MPI collectives where even a single copy interface does not get us the performance gain we could. For example in an MPI_Reduce rather than copy the data from the source we would like to instead use it directly in a mathops (say the reduce is doing a sum) as this would save us doing a copy. We don't need to keep a copy of the data from the source. I haven't implemented this, but I think this interface could in the future do all this through the use of the flags - eg could specify the math operation and type and the kernel rather than just copying the data would apply the specified operation between the source and destination and store it in the destination. Although we don't have a "second user" of the interface (though I've had some nibbles from people who may be interested in using it for intra process messaging which is not MPI). This interface is something which hardware vendors are already doing for their custom drivers to implement fast local communication. And so in addition to this being useful for OpenMPI it would mean the driver maintainers don't have to fix things up when the mm changes. There was some discussion about how much faster a true zero copy would go. Here's a link back to the email with some testing I did on that: http://marc.info/?l=linux-mm&m=130105930902915&w=2 There is a basic man page for the proposed interface here: http://ozlabs.org/~cyeoh/cma/process_vm_readv.txt This has been implemented for x86 and powerpc, other architecture should mainly (I think) just need to add syscall numbers for the process_vm_readv and process_vm_writev. There are 32 bit compatibility versions for 64-bit kernels. For arch maintainers there are some simple tests to be able to quickly verify that the syscalls are working correctly here: http://ozlabs.org/~cyeoh/cma/cma-test-20110718.tgz Signed-off-by: Chris Yeoh <yeohc@au1.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Howells <dhowells@redhat.com> Cc: James Morris <jmorris@namei.org> Cc: <linux-man@vger.kernel.org> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-11-01 07:06:39 +07:00
unsigned long nr_segs, unsigned long fast_segs,
struct iovec *fast_pointer,
struct iovec **ret_pointer);
extern ssize_t __vfs_read(struct file *, char __user *, size_t, loff_t *);
extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
extern ssize_t vfs_readv(struct file *, const struct iovec __user *,
unsigned long, loff_t *);
extern ssize_t vfs_writev(struct file *, const struct iovec __user *,
unsigned long, loff_t *);
struct super_operations {
struct inode *(*alloc_inode)(struct super_block *sb);
void (*destroy_inode)(struct inode *);
void (*dirty_inode) (struct inode *, int flags);
int (*write_inode) (struct inode *, struct writeback_control *wbc);
int (*drop_inode) (struct inode *);
void (*evict_inode) (struct inode *);
void (*put_super) (struct super_block *);
int (*sync_fs)(struct super_block *sb, int wait);
int (*freeze_super) (struct super_block *);
filesystem freeze: add error handling of write_super_lockfs/unlockfs Currently, ext3 in mainline Linux doesn't have the freeze feature which suspends write requests. So, we cannot take a backup which keeps the filesystem's consistency with the storage device's features (snapshot and replication) while it is mounted. In many case, a commercial filesystem (e.g. VxFS) has the freeze feature and it would be used to get the consistent backup. If Linux's standard filesystem ext3 has the freeze feature, we can do it without a commercial filesystem. So I have implemented the ioctls of the freeze feature. I think we can take the consistent backup with the following steps. 1. Freeze the filesystem with the freeze ioctl. 2. Separate the replication volume or create the snapshot with the storage device's feature. 3. Unfreeze the filesystem with the unfreeze ioctl. 4. Take the backup from the separated replication volume or the snapshot. This patch: VFS: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they can return an error. Rename write_super_lockfs and unlockfs of the super block operation freeze_fs and unfreeze_fs to avoid a confusion. ext3, ext4, xfs, gfs2, jfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that write_super_lockfs returns an error if needed, and unlockfs always returns 0. reiserfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they always return 0 (success) to keep a current behavior. Signed-off-by: Takashi Sato <t-sato@yk.jp.nec.com> Signed-off-by: Masayuki Hamaguchi <m-hamaguchi@ys.jp.nec.com> Cc: <xfs-masters@oss.sgi.com> Cc: <linux-ext4@vger.kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Dave Kleikamp <shaggy@austin.ibm.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Alasdair G Kergon <agk@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-10 07:40:58 +07:00
int (*freeze_fs) (struct super_block *);
int (*thaw_super) (struct super_block *);
filesystem freeze: add error handling of write_super_lockfs/unlockfs Currently, ext3 in mainline Linux doesn't have the freeze feature which suspends write requests. So, we cannot take a backup which keeps the filesystem's consistency with the storage device's features (snapshot and replication) while it is mounted. In many case, a commercial filesystem (e.g. VxFS) has the freeze feature and it would be used to get the consistent backup. If Linux's standard filesystem ext3 has the freeze feature, we can do it without a commercial filesystem. So I have implemented the ioctls of the freeze feature. I think we can take the consistent backup with the following steps. 1. Freeze the filesystem with the freeze ioctl. 2. Separate the replication volume or create the snapshot with the storage device's feature. 3. Unfreeze the filesystem with the unfreeze ioctl. 4. Take the backup from the separated replication volume or the snapshot. This patch: VFS: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they can return an error. Rename write_super_lockfs and unlockfs of the super block operation freeze_fs and unfreeze_fs to avoid a confusion. ext3, ext4, xfs, gfs2, jfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that write_super_lockfs returns an error if needed, and unlockfs always returns 0. reiserfs: Changed the type of write_super_lockfs and unlockfs from "void" to "int" so that they always return 0 (success) to keep a current behavior. Signed-off-by: Takashi Sato <t-sato@yk.jp.nec.com> Signed-off-by: Masayuki Hamaguchi <m-hamaguchi@ys.jp.nec.com> Cc: <xfs-masters@oss.sgi.com> Cc: <linux-ext4@vger.kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Dave Kleikamp <shaggy@austin.ibm.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Alasdair G Kergon <agk@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-10 07:40:58 +07:00
int (*unfreeze_fs) (struct super_block *);
int (*statfs) (struct dentry *, struct kstatfs *);
int (*remount_fs) (struct super_block *, int *, char *);
void (*umount_begin) (struct super_block *);
int (*show_options)(struct seq_file *, struct dentry *);
int (*show_devname)(struct seq_file *, struct dentry *);
int (*show_path)(struct seq_file *, struct dentry *);
int (*show_stats)(struct seq_file *, struct dentry *);
#ifdef CONFIG_QUOTA
ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
struct dquot **(*get_dquots)(struct inode *);
#endif
int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
long (*nr_cached_objects)(struct super_block *,
struct shrink_control *);
long (*free_cached_objects)(struct super_block *,
struct shrink_control *);
};
/*
* Inode flags - they have no relation to superblock flags now
*/
#define S_SYNC 1 /* Writes are synced at once */
#define S_NOATIME 2 /* Do not update access times */
#define S_APPEND 4 /* Append-only file */
#define S_IMMUTABLE 8 /* Immutable file */
#define S_DEAD 16 /* removed, but still open directory */
#define S_NOQUOTA 32 /* Inode is not counted to quota */
#define S_DIRSYNC 64 /* Directory modifications are synchronous */
#define S_NOCMTIME 128 /* Do not update file c/mtime */
#define S_SWAPFILE 256 /* Do not truncate: swapon got its bmaps */
#define S_PRIVATE 512 /* Inode is fs-internal */
#define S_IMA 1024 /* Inode has an associated IMA struct */
#define S_AUTOMOUNT 2048 /* Automount/referral quasi-directory */
#define S_NOSEC 4096 /* no suid or xattr security attributes */
#ifdef CONFIG_FS_DAX
#define S_DAX 8192 /* Direct Access, avoiding the page cache */
#else
#define S_DAX 0 /* Make all the DAX code disappear */
#endif
/*
* Note that nosuid etc flags are inode-specific: setting some file-system
* flags just means all the inodes inherit those flags by default. It might be
* possible to override it selectively if you really wanted to with some
* ioctl() that is not currently implemented.
*
* Exception: MS_RDONLY is always applied to the entire file system.
*
* Unfortunately, it is possible to change a filesystems flags with it mounted
* with files in use. This means that all of the inodes will not have their
* i_flags updated. Hence, i_flags no longer inherit the superblock mount
* flags, so these have to be checked separately. -- rmk@arm.uk.linux.org
*/
#define __IS_FLG(inode, flg) ((inode)->i_sb->s_flags & (flg))
#define IS_RDONLY(inode) ((inode)->i_sb->s_flags & MS_RDONLY)
#define IS_SYNC(inode) (__IS_FLG(inode, MS_SYNCHRONOUS) || \
((inode)->i_flags & S_SYNC))
#define IS_DIRSYNC(inode) (__IS_FLG(inode, MS_SYNCHRONOUS|MS_DIRSYNC) || \
((inode)->i_flags & (S_SYNC|S_DIRSYNC)))
#define IS_MANDLOCK(inode) __IS_FLG(inode, MS_MANDLOCK)
#define IS_NOATIME(inode) __IS_FLG(inode, MS_RDONLY|MS_NOATIME)
#define IS_I_VERSION(inode) __IS_FLG(inode, MS_I_VERSION)
#define IS_NOQUOTA(inode) ((inode)->i_flags & S_NOQUOTA)
#define IS_APPEND(inode) ((inode)->i_flags & S_APPEND)
#define IS_IMMUTABLE(inode) ((inode)->i_flags & S_IMMUTABLE)
#define IS_POSIXACL(inode) __IS_FLG(inode, MS_POSIXACL)
#define IS_DEADDIR(inode) ((inode)->i_flags & S_DEAD)
#define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME)
#define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE)
#define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE)
#define IS_IMA(inode) ((inode)->i_flags & S_IMA)
#define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT)
#define IS_NOSEC(inode) ((inode)->i_flags & S_NOSEC)
#define IS_DAX(inode) ((inode)->i_flags & S_DAX)
#define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \
(inode)->i_rdev == WHITEOUT_DEV)
/*
* Inode state bits. Protected by inode->i_lock
*
* Three bits determine the dirty state of the inode, I_DIRTY_SYNC,
* I_DIRTY_DATASYNC and I_DIRTY_PAGES.
*
* Four bits define the lifetime of an inode. Initially, inodes are I_NEW,
* until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at
* various stages of removing an inode.
*
* Two bits are used for locking and completion notification, I_NEW and I_SYNC.
*
* I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on
* fdatasync(). i_atime is the usual cause.
* I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of
* these changes separately from I_DIRTY_SYNC so that we
* don't have to write inode on fdatasync() when only
* mtime has changed in it.
* I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean.
* I_NEW Serves as both a mutex and completion notification.
* New inodes set I_NEW. If two processes both create
* the same inode, one of them will release its inode and
* wait for I_NEW to be released before returning.
* Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can
* also cause waiting on I_NEW, without I_NEW actually
* being set. find_inode() uses this to prevent returning
* nearly-dead inodes.
* I_WILL_FREE Must be set when calling write_inode_now() if i_count
* is zero. I_FREEING must be set when I_WILL_FREE is
* cleared.
* I_FREEING Set when inode is about to be freed but still has dirty
* pages or buffers attached or the inode itself is still
* dirty.
* I_CLEAR Added by clear_inode(). In this state the inode is
* clean and can be destroyed. Inode keeps I_FREEING.
*
* Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are
* prohibited for many purposes. iget() must wait for
* the inode to be completely released, then create it
* anew. Other functions will just ignore such inodes,
* if appropriate. I_NEW is used for waiting.
*
* I_SYNC Writeback of inode is running. The bit is set during
* data writeback, and cleared with a wakeup on the bit
* address once it is done. The bit is also used to pin
* the inode in memory for flusher thread.
*
* I_REFERENCED Marks the inode as recently references on the LRU list.
*
* I_DIO_WAKEUP Never set. Only used as a key for wait_on_bit().
*
* Q: What is the difference between I_WILL_FREE and I_FREEING?
*/
#define I_DIRTY_SYNC (1 << 0)
#define I_DIRTY_DATASYNC (1 << 1)
#define I_DIRTY_PAGES (1 << 2)
#define __I_NEW 3
#define I_NEW (1 << __I_NEW)
#define I_WILL_FREE (1 << 4)
#define I_FREEING (1 << 5)
#define I_CLEAR (1 << 6)
#define __I_SYNC 7
#define I_SYNC (1 << __I_SYNC)
#define I_REFERENCED (1 << 8)
#define __I_DIO_WAKEUP 9
#define I_DIO_WAKEUP (1 << I_DIO_WAKEUP)
#define I_LINKABLE (1 << 10)
#define I_DIRTY_TIME (1 << 11)
#define __I_DIRTY_TIME_EXPIRED 12
#define I_DIRTY_TIME_EXPIRED (1 << __I_DIRTY_TIME_EXPIRED)
#define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES)
#define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME)
extern void __mark_inode_dirty(struct inode *, int);
static inline void mark_inode_dirty(struct inode *inode)
{
__mark_inode_dirty(inode, I_DIRTY);
}
static inline void mark_inode_dirty_sync(struct inode *inode)
{
__mark_inode_dirty(inode, I_DIRTY_SYNC);
}
extern void inc_nlink(struct inode *inode);
extern void drop_nlink(struct inode *inode);
extern void clear_nlink(struct inode *inode);
extern void set_nlink(struct inode *inode, unsigned int nlink);
static inline void inode_inc_link_count(struct inode *inode)
{
inc_nlink(inode);
mark_inode_dirty(inode);
}
static inline void inode_dec_link_count(struct inode *inode)
{
drop_nlink(inode);
mark_inode_dirty(inode);
}
/**
* inode_inc_iversion - increments i_version
* @inode: inode that need to be updated
*
* Every time the inode is modified, the i_version field will be incremented.
* The filesystem has to be mounted with i_version flag
*/
static inline void inode_inc_iversion(struct inode *inode)
{
spin_lock(&inode->i_lock);
inode->i_version++;
spin_unlock(&inode->i_lock);
}
enum file_time_flags {
S_ATIME = 1,
S_MTIME = 2,
S_CTIME = 4,
S_VERSION = 8,
};
extern void touch_atime(const struct path *);
static inline void file_accessed(struct file *file)
{
if (!(file->f_flags & O_NOATIME))
touch_atime(&file->f_path);
}
int sync_inode(struct inode *inode, struct writeback_control *wbc);
int sync_inode_metadata(struct inode *inode, int wait);
struct file_system_type {
const char *name;
int fs_flags;
#define FS_REQUIRES_DEV 1
#define FS_BINARY_MOUNTDATA 2
#define FS_HAS_SUBTYPE 4
#define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */
#define FS_USERNS_DEV_MOUNT 16 /* A userns mount does not imply MNT_NODEV */
#define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */
struct dentry *(*mount) (struct file_system_type *, int,
const char *, void *);
void (*kill_sb) (struct super_block *);
struct module *owner;
struct file_system_type * next;
struct hlist_head fs_supers;
struct lock_class_key s_lock_key;
struct lock_class_key s_umount_key;
vfs: add lockdep annotation to s_vfs_rename_key for ecryptfs > ============================================= > [ INFO: possible recursive locking detected ] > 2.6.31-2-generic #14~rbd3 > --------------------------------------------- > firefox-3.5/4162 is trying to acquire lock: > (&s->s_vfs_rename_mutex){+.+.+.}, at: [<ffffffff81139d31>] lock_rename+0x41/0xf0 > > but task is already holding lock: > (&s->s_vfs_rename_mutex){+.+.+.}, at: [<ffffffff81139d31>] lock_rename+0x41/0xf0 > > other info that might help us debug this: > 3 locks held by firefox-3.5/4162: > #0: (&s->s_vfs_rename_mutex){+.+.+.}, at: [<ffffffff81139d31>] lock_rename+0x41/0xf0 > #1: (&sb->s_type->i_mutex_key#11/1){+.+.+.}, at: [<ffffffff81139d5a>] lock_rename+0x6a/0xf0 > #2: (&sb->s_type->i_mutex_key#11/2){+.+.+.}, at: [<ffffffff81139d6f>] lock_rename+0x7f/0xf0 > > stack backtrace: > Pid: 4162, comm: firefox-3.5 Tainted: G C 2.6.31-2-generic #14~rbd3 > Call Trace: > [<ffffffff8108ae74>] print_deadlock_bug+0xf4/0x100 > [<ffffffff8108ce26>] validate_chain+0x4c6/0x750 > [<ffffffff8108d2e7>] __lock_acquire+0x237/0x430 > [<ffffffff8108d585>] lock_acquire+0xa5/0x150 > [<ffffffff81139d31>] ? lock_rename+0x41/0xf0 > [<ffffffff815526ad>] __mutex_lock_common+0x4d/0x3d0 > [<ffffffff81139d31>] ? lock_rename+0x41/0xf0 > [<ffffffff81139d31>] ? lock_rename+0x41/0xf0 > [<ffffffff8120eaf9>] ? ecryptfs_rename+0x99/0x170 > [<ffffffff81552b36>] mutex_lock_nested+0x46/0x60 > [<ffffffff81139d31>] lock_rename+0x41/0xf0 > [<ffffffff8120eb2a>] ecryptfs_rename+0xca/0x170 > [<ffffffff81139a9e>] vfs_rename_dir+0x13e/0x160 > [<ffffffff8113ac7e>] vfs_rename+0xee/0x290 > [<ffffffff8113c212>] ? __lookup_hash+0x102/0x160 > [<ffffffff8113d512>] sys_renameat+0x252/0x280 > [<ffffffff81133eb4>] ? cp_new_stat+0xe4/0x100 > [<ffffffff8101316a>] ? sysret_check+0x2e/0x69 > [<ffffffff8108c34d>] ? trace_hardirqs_on_caller+0x14d/0x190 > [<ffffffff8113d55b>] sys_rename+0x1b/0x20 > [<ffffffff81013132>] system_call_fastpath+0x16/0x1b The trace above is totally reproducible by doing a cross-directory rename on an ecryptfs directory. The issue seems to be that sys_renameat() does lock_rename() then calls into the filesystem; if the filesystem is ecryptfs, then ecryptfs_rename() again does lock_rename() on the lower filesystem, and lockdep can't tell that the two s_vfs_rename_mutexes are different. It seems an annotation like the following is sufficient to fix this (it does get rid of the lockdep trace in my simple tests); however I would like to make sure I'm not misunderstanding the locking, hence the CC list... Signed-off-by: Roland Dreier <rdreier@cisco.com> Cc: Tyler Hicks <tyhicks@linux.vnet.ibm.com> Cc: Dustin Kirkland <kirkland@canonical.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-04-28 04:23:57 +07:00
struct lock_class_key s_vfs_rename_key;
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 21:20:34 +07:00
struct lock_class_key s_writers_key[SB_FREEZE_LEVELS];
struct lock_class_key i_lock_key;
struct lock_class_key i_mutex_key;
struct lock_class_key i_mutex_dir_key;
};
fs: Limit sys_mount to only request filesystem modules. Modify the request_module to prefix the file system type with "fs-" and add aliases to all of the filesystems that can be built as modules to match. A common practice is to build all of the kernel code and leave code that is not commonly needed as modules, with the result that many users are exposed to any bug anywhere in the kernel. Looking for filesystems with a fs- prefix limits the pool of possible modules that can be loaded by mount to just filesystems trivially making things safer with no real cost. Using aliases means user space can control the policy of which filesystem modules are auto-loaded by editing /etc/modprobe.d/*.conf with blacklist and alias directives. Allowing simple, safe, well understood work-arounds to known problematic software. This also addresses a rare but unfortunate problem where the filesystem name is not the same as it's module name and module auto-loading would not work. While writing this patch I saw a handful of such cases. The most significant being autofs that lives in the module autofs4. This is relevant to user namespaces because we can reach the request module in get_fs_type() without having any special permissions, and people get uncomfortable when a user specified string (in this case the filesystem type) goes all of the way to request_module. After having looked at this issue I don't think there is any particular reason to perform any filtering or permission checks beyond making it clear in the module request that we want a filesystem module. The common pattern in the kernel is to call request_module() without regards to the users permissions. In general all a filesystem module does once loaded is call register_filesystem() and go to sleep. Which means there is not much attack surface exposed by loading a filesytem module unless the filesystem is mounted. In a user namespace filesystems are not mounted unless .fs_flags = FS_USERNS_MOUNT, which most filesystems do not set today. Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Acked-by: Kees Cook <keescook@chromium.org> Reported-by: Kees Cook <keescook@google.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2013-03-03 10:39:14 +07:00
#define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME)
extern struct dentry *mount_ns(struct file_system_type *fs_type, int flags,
void *data, int (*fill_super)(struct super_block *, void *, int));
extern struct dentry *mount_bdev(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data,
int (*fill_super)(struct super_block *, void *, int));
extern struct dentry *mount_single(struct file_system_type *fs_type,
int flags, void *data,
int (*fill_super)(struct super_block *, void *, int));
extern struct dentry *mount_nodev(struct file_system_type *fs_type,
int flags, void *data,
int (*fill_super)(struct super_block *, void *, int));
extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path);
void generic_shutdown_super(struct super_block *sb);
void kill_block_super(struct super_block *sb);
void kill_anon_super(struct super_block *sb);
void kill_litter_super(struct super_block *sb);
void deactivate_super(struct super_block *sb);
void deactivate_locked_super(struct super_block *sb);
int set_anon_super(struct super_block *s, void *data);
int get_anon_bdev(dev_t *);
void free_anon_bdev(dev_t);
struct super_block *sget(struct file_system_type *type,
int (*test)(struct super_block *,void *),
int (*set)(struct super_block *,void *),
int flags, void *data);
extern struct dentry *mount_pseudo(struct file_system_type *, char *,
const struct super_operations *ops,
const struct dentry_operations *dops,
unsigned long);
/* Alas, no aliases. Too much hassle with bringing module.h everywhere */
#define fops_get(fops) \
(((fops) && try_module_get((fops)->owner) ? (fops) : NULL))
#define fops_put(fops) \
do { if (fops) module_put((fops)->owner); } while(0)
/*
* This one is to be used *ONLY* from ->open() instances.
* fops must be non-NULL, pinned down *and* module dependencies
* should be sufficient to pin the caller down as well.
*/
#define replace_fops(f, fops) \
do { \
struct file *__file = (f); \
fops_put(__file->f_op); \
BUG_ON(!(__file->f_op = (fops))); \
} while(0)
extern int register_filesystem(struct file_system_type *);
extern int unregister_filesystem(struct file_system_type *);
extern struct vfsmount *kern_mount_data(struct file_system_type *, void *data);
#define kern_mount(type) kern_mount_data(type, NULL)
extern void kern_unmount(struct vfsmount *mnt);
extern int may_umount_tree(struct vfsmount *);
extern int may_umount(struct vfsmount *);
extern long do_mount(const char *, const char __user *,
const char *, unsigned long, void *);
extern struct vfsmount *collect_mounts(struct path *);
extern void drop_collected_mounts(struct vfsmount *);
extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
struct vfsmount *);
extern int vfs_statfs(struct path *, struct kstatfs *);
extern int user_statfs(const char __user *, struct kstatfs *);
extern int fd_statfs(int, struct kstatfs *);
extern int vfs_ustat(dev_t, struct kstatfs *);
extern int freeze_super(struct super_block *super);
extern int thaw_super(struct super_block *super);
fix apparmor dereferencing potentially freed dentry, sanitize __d_path() API __d_path() API is asking for trouble and in case of apparmor d_namespace_path() getting just that. The root cause is that when __d_path() misses the root it had been told to look for, it stores the location of the most remote ancestor in *root. Without grabbing references. Sure, at the moment of call it had been pinned down by what we have in *path. And if we raced with umount -l, we could have very well stopped at vfsmount/dentry that got freed as soon as prepend_path() dropped vfsmount_lock. It is safe to compare these pointers with pre-existing (and known to be still alive) vfsmount and dentry, as long as all we are asking is "is it the same address?". Dereferencing is not safe and apparmor ended up stepping into that. d_namespace_path() really wants to examine the place where we stopped, even if it's not connected to our namespace. As the result, it looked at ->d_sb->s_magic of a dentry that might've been already freed by that point. All other callers had been careful enough to avoid that, but it's really a bad interface - it invites that kind of trouble. The fix is fairly straightforward, even though it's bigger than I'd like: * prepend_path() root argument becomes const. * __d_path() is never called with NULL/NULL root. It was a kludge to start with. Instead, we have an explicit function - d_absolute_root(). Same as __d_path(), except that it doesn't get root passed and stops where it stops. apparmor and tomoyo are using it. * __d_path() returns NULL on path outside of root. The main caller is show_mountinfo() and that's precisely what we pass root for - to skip those outside chroot jail. Those who don't want that can (and do) use d_path(). * __d_path() root argument becomes const. Everyone agrees, I hope. * apparmor does *NOT* try to use __d_path() or any of its variants when it sees that path->mnt is an internal vfsmount. In that case it's definitely not mounted anywhere and dentry_path() is exactly what we want there. Handling of sysctl()-triggered weirdness is moved to that place. * if apparmor is asked to do pathname relative to chroot jail and __d_path() tells it we it's not in that jail, the sucker just calls d_absolute_path() instead. That's the other remaining caller of __d_path(), BTW. * seq_path_root() does _NOT_ return -ENAMETOOLONG (it's stupid anyway - the normal seq_file logics will take care of growing the buffer and redoing the call of ->show() just fine). However, if it gets path not reachable from root, it returns SEQ_SKIP. The only caller adjusted (i.e. stopped ignoring the return value as it used to do). Reviewed-by: John Johansen <john.johansen@canonical.com> ACKed-by: John Johansen <john.johansen@canonical.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Cc: stable@vger.kernel.org
2011-12-05 20:43:34 +07:00
extern bool our_mnt(struct vfsmount *mnt);
extern bool fs_fully_visible(struct file_system_type *);
extern int current_umask(void);
extern void ihold(struct inode * inode);
extern void iput(struct inode *);
extern int generic_update_time(struct inode *, struct timespec *, int);
static inline struct inode *file_inode(const struct file *f)
{
return f->f_inode;
}
/* /sys/fs */
extern struct kobject *fs_kobj;
#define MAX_RW_COUNT (INT_MAX & PAGE_CACHE_MASK)
#define FLOCK_VERIFY_READ 1
#define FLOCK_VERIFY_WRITE 2
#ifdef CONFIG_FILE_LOCKING
extern int locks_mandatory_locked(struct file *);
extern int locks_mandatory_area(int, struct inode *, struct file *, loff_t, size_t);
/*
* Candidates for mandatory locking have the setgid bit set
* but no group execute bit - an otherwise meaningless combination.
*/
static inline int __mandatory_lock(struct inode *ino)
{
return (ino->i_mode & (S_ISGID | S_IXGRP)) == S_ISGID;
}
/*
* ... and these candidates should be on MS_MANDLOCK mounted fs,
* otherwise these will be advisory locks
*/
static inline int mandatory_lock(struct inode *ino)
{
return IS_MANDLOCK(ino) && __mandatory_lock(ino);
}
static inline int locks_verify_locked(struct file *file)
{
if (mandatory_lock(file_inode(file)))
return locks_mandatory_locked(file);
return 0;
}
static inline int locks_verify_truncate(struct inode *inode,
struct file *filp,
loff_t size)
{
if (inode->i_flctx && mandatory_lock(inode))
return locks_mandatory_area(
FLOCK_VERIFY_WRITE, inode, filp,
size < inode->i_size ? size : inode->i_size,
(size < inode->i_size ? inode->i_size - size
: size - inode->i_size)
);
return 0;
}
static inline int break_lease(struct inode *inode, unsigned int mode)
{
/*
* Since this check is lockless, we must ensure that any refcounts
* taken are done before checking i_flctx->flc_lease. Otherwise, we
* could end up racing with tasks trying to set a new lease on this
* file.
*/
smp_mb();
if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
return __break_lease(inode, mode, FL_LEASE);
return 0;
}
static inline int break_deleg(struct inode *inode, unsigned int mode)
{
/*
* Since this check is lockless, we must ensure that any refcounts
* taken are done before checking i_flctx->flc_lease. Otherwise, we
* could end up racing with tasks trying to set a new lease on this
* file.
*/
smp_mb();
if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
return __break_lease(inode, mode, FL_DELEG);
return 0;
}
static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode)
{
int ret;
ret = break_deleg(inode, O_WRONLY|O_NONBLOCK);
if (ret == -EWOULDBLOCK && delegated_inode) {
*delegated_inode = inode;
ihold(inode);
}
return ret;
}
static inline int break_deleg_wait(struct inode **delegated_inode)
{
int ret;
ret = break_deleg(*delegated_inode, O_WRONLY);
iput(*delegated_inode);
*delegated_inode = NULL;
return ret;
}
static inline int break_layout(struct inode *inode, bool wait)
{
smp_mb();
if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
return __break_lease(inode,
wait ? O_WRONLY : O_WRONLY | O_NONBLOCK,
FL_LAYOUT);
return 0;
}
#else /* !CONFIG_FILE_LOCKING */
static inline int locks_mandatory_locked(struct file *file)
{
return 0;
}
static inline int locks_mandatory_area(int rw, struct inode *inode,
struct file *filp, loff_t offset,
size_t count)
{
return 0;
}
static inline int __mandatory_lock(struct inode *inode)
{
return 0;
}
static inline int mandatory_lock(struct inode *inode)
{
return 0;
}
static inline int locks_verify_locked(struct file *file)
{
return 0;
}
static inline int locks_verify_truncate(struct inode *inode, struct file *filp,
size_t size)
{
return 0;
}
static inline int break_lease(struct inode *inode, unsigned int mode)
{
return 0;
}
static inline int break_deleg(struct inode *inode, unsigned int mode)
{
return 0;
}
static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode)
{
return 0;
}
static inline int break_deleg_wait(struct inode **delegated_inode)
{
BUG();
return 0;
}
static inline int break_layout(struct inode *inode, bool wait)
{
return 0;
}
#endif /* CONFIG_FILE_LOCKING */
/* fs/open.c */
struct audit_names;
struct filename {
const char *name; /* pointer to actual string */
const __user char *uptr; /* original userland pointer */
struct audit_names *aname;
int refcnt;
bool separate; /* should "name" be freed? */
};
extern long vfs_truncate(struct path *, loff_t);
extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs,
struct file *filp);
extern int vfs_fallocate(struct file *file, int mode, loff_t offset,
loff_t len);
extern long do_sys_open(int dfd, const char __user *filename, int flags,
umode_t mode);
extern struct file *file_open_name(struct filename *, int, umode_t);
extern struct file *filp_open(const char *, int, umode_t);
extern struct file *file_open_root(struct dentry *, struct vfsmount *,
const char *, int);
extern int vfs_open(const struct path *, struct file *, const struct cred *);
extern struct file * dentry_open(const struct path *, int, const struct cred *);
extern int filp_close(struct file *, fl_owner_t id);
syscalls: implement execveat() system call This patchset adds execveat(2) for x86, and is derived from Meredydd Luff's patch from Sept 2012 (https://lkml.org/lkml/2012/9/11/528). The primary aim of adding an execveat syscall is to allow an implementation of fexecve(3) that does not rely on the /proc filesystem, at least for executables (rather than scripts). The current glibc version of fexecve(3) is implemented via /proc, which causes problems in sandboxed or otherwise restricted environments. Given the desire for a /proc-free fexecve() implementation, HPA suggested (https://lkml.org/lkml/2006/7/11/556) that an execveat(2) syscall would be an appropriate generalization. Also, having a new syscall means that it can take a flags argument without back-compatibility concerns. The current implementation just defines the AT_EMPTY_PATH and AT_SYMLINK_NOFOLLOW flags, but other flags could be added in future -- for example, flags for new namespaces (as suggested at https://lkml.org/lkml/2006/7/11/474). Related history: - https://lkml.org/lkml/2006/12/27/123 is an example of someone realizing that fexecve() is likely to fail in a chroot environment. - http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=514043 covered documenting the /proc requirement of fexecve(3) in its manpage, to "prevent other people from wasting their time". - https://bugzilla.redhat.com/show_bug.cgi?id=241609 described a problem where a process that did setuid() could not fexecve() because it no longer had access to /proc/self/fd; this has since been fixed. This patch (of 4): Add a new execveat(2) system call. execveat() is to execve() as openat() is to open(): it takes a file descriptor that refers to a directory, and resolves the filename relative to that. In addition, if the filename is empty and AT_EMPTY_PATH is specified, execveat() executes the file to which the file descriptor refers. This replicates the functionality of fexecve(), which is a system call in other UNIXen, but in Linux glibc it depends on opening "/proc/self/fd/<fd>" (and so relies on /proc being mounted). The filename fed to the executed program as argv[0] (or the name of the script fed to a script interpreter) will be of the form "/dev/fd/<fd>" (for an empty filename) or "/dev/fd/<fd>/<filename>", effectively reflecting how the executable was found. This does however mean that execution of a script in a /proc-less environment won't work; also, script execution via an O_CLOEXEC file descriptor fails (as the file will not be accessible after exec). Based on patches by Meredydd Luff. Signed-off-by: David Drysdale <drysdale@google.com> Cc: Meredydd Luff <meredydd@senatehouse.org> Cc: Shuah Khan <shuah.kh@samsung.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Kees Cook <keescook@chromium.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Rich Felker <dalias@aerifal.cx> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-13 07:57:29 +07:00
extern struct filename *getname_flags(const char __user *, int, int *);
extern struct filename *getname(const char __user *);
extern struct filename *getname_kernel(const char *);
extern void putname(struct filename *name);
enum {
FILE_CREATED = 1,
FILE_OPENED = 2
};
extern int finish_open(struct file *file, struct dentry *dentry,
int (*open)(struct inode *, struct file *),
int *opened);
extern int finish_no_open(struct file *file, struct dentry *dentry);
/* fs/ioctl.c */
extern int ioctl_preallocate(struct file *filp, void __user *argp);
/* fs/dcache.c */
extern void __init vfs_caches_init_early(void);
extern void __init vfs_caches_init(unsigned long);
extern struct kmem_cache *names_cachep;
#define __getname() kmem_cache_alloc(names_cachep, GFP_KERNEL)
#define __putname(name) kmem_cache_free(names_cachep, (void *)(name))
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 01:45:40 +07:00
#ifdef CONFIG_BLOCK
extern int register_blkdev(unsigned int, const char *);
extern void unregister_blkdev(unsigned int, const char *);
extern struct block_device *bdget(dev_t);
extern struct block_device *bdgrab(struct block_device *bdev);
extern void bd_set_size(struct block_device *, loff_t size);
extern void bd_forget(struct inode *inode);
extern void bdput(struct block_device *);
extern void invalidate_bdev(struct block_device *);
extern void iterate_bdevs(void (*)(struct block_device *, void *), void *);
extern int sync_blockdev(struct block_device *bdev);
extern void kill_bdev(struct block_device *);
extern struct super_block *freeze_bdev(struct block_device *);
extern void emergency_thaw_all(void);
extern int thaw_bdev(struct block_device *bdev, struct super_block *sb);
extern int fsync_bdev(struct block_device *);
extern int sb_is_blkdev_sb(struct super_block *sb);
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 01:45:40 +07:00
#else
static inline void bd_forget(struct inode *inode) {}
static inline int sync_blockdev(struct block_device *bdev) { return 0; }
static inline void kill_bdev(struct block_device *bdev) {}
static inline void invalidate_bdev(struct block_device *bdev) {}
static inline struct super_block *freeze_bdev(struct block_device *sb)
{
return NULL;
}
static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb)
{
return 0;
}
static inline void iterate_bdevs(void (*f)(struct block_device *, void *), void *arg)
{
}
static inline int sb_is_blkdev_sb(struct super_block *sb)
{
return 0;
}
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 01:45:40 +07:00
#endif
extern int sync_filesystem(struct super_block *);
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 01:45:40 +07:00
extern const struct file_operations def_blk_fops;
extern const struct file_operations def_chr_fops;
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 01:45:40 +07:00
#ifdef CONFIG_BLOCK
extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long);
extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long);
extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
block: make blkdev_get/put() handle exclusive access Over time, block layer has accumulated a set of APIs dealing with bdev open, close, claim and release. * blkdev_get/put() are the primary open and close functions. * bd_claim/release() deal with exclusive open. * open/close_bdev_exclusive() are combination of open and claim and the other way around, respectively. * bd_link/unlink_disk_holder() to create and remove holder/slave symlinks. * open_by_devnum() wraps bdget() + blkdev_get(). The interface is a bit confusing and the decoupling of open and claim makes it impossible to properly guarantee exclusive access as in-kernel open + claim sequence can disturb the existing exclusive open even before the block layer knows the current open if for another exclusive access. Reorganize the interface such that, * blkdev_get() is extended to include exclusive access management. @holder argument is added and, if is @FMODE_EXCL specified, it will gain exclusive access atomically w.r.t. other exclusive accesses. * blkdev_put() is similarly extended. It now takes @mode argument and if @FMODE_EXCL is set, it releases an exclusive access. Also, when the last exclusive claim is released, the holder/slave symlinks are removed automatically. * bd_claim/release() and close_bdev_exclusive() are no longer necessary and either made static or removed. * bd_link_disk_holder() remains the same but bd_unlink_disk_holder() is no longer necessary and removed. * open_bdev_exclusive() becomes a simple wrapper around lookup_bdev() and blkdev_get(). It also has an unexpected extra bdev_read_only() test which probably should be moved into blkdev_get(). * open_by_devnum() is modified to take @holder argument and pass it to blkdev_get(). Most of bdev open/close operations are unified into blkdev_get/put() and most exclusive accesses are tested atomically at the open time (as it should). This cleans up code and removes some, both valid and invalid, but unnecessary all the same, corner cases. open_bdev_exclusive() and open_by_devnum() can use further cleanup - rename to blkdev_get_by_path() and blkdev_get_by_devt() and drop special features. Well, let's leave them for another day. Most conversions are straight-forward. drbd conversion is a bit more involved as there was some reordering, but the logic should stay the same. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Neil Brown <neilb@suse.de> Acked-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> Acked-by: Mike Snitzer <snitzer@redhat.com> Acked-by: Philipp Reisner <philipp.reisner@linbit.com> Cc: Peter Osterlund <petero2@telia.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Jan Kara <jack@suse.cz> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <joel.becker@oracle.com> Cc: Alex Elder <aelder@sgi.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: dm-devel@redhat.com Cc: drbd-dev@lists.linbit.com Cc: Leo Chen <leochen@broadcom.com> Cc: Scott Branden <sbranden@broadcom.com> Cc: Chris Mason <chris.mason@oracle.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@linux.vnet.ibm.com> Cc: Joern Engel <joern@logfs.org> Cc: reiserfs-devel@vger.kernel.org Cc: Alexander Viro <viro@zeniv.linux.org.uk>
2010-11-13 17:55:17 +07:00
extern int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder);
extern struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
void *holder);
extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode,
void *holder);
extern void blkdev_put(struct block_device *bdev, fmode_t mode);
#ifdef CONFIG_SYSFS
extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk);
extern void bd_unlink_disk_holder(struct block_device *bdev,
struct gendisk *disk);
#else
static inline int bd_link_disk_holder(struct block_device *bdev,
struct gendisk *disk)
{
return 0;
}
static inline void bd_unlink_disk_holder(struct block_device *bdev,
struct gendisk *disk)
{
}
#endif
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 01:45:40 +07:00
#endif
/* fs/char_dev.c */
#define CHRDEV_MAJOR_HASH_SIZE 255
extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *);
extern int register_chrdev_region(dev_t, unsigned, const char *);
extern int __register_chrdev(unsigned int major, unsigned int baseminor,
unsigned int count, const char *name,
const struct file_operations *fops);
extern void __unregister_chrdev(unsigned int major, unsigned int baseminor,
unsigned int count, const char *name);
extern void unregister_chrdev_region(dev_t, unsigned);
extern void chrdev_show(struct seq_file *,off_t);
static inline int register_chrdev(unsigned int major, const char *name,
const struct file_operations *fops)
{
return __register_chrdev(major, 0, 256, name, fops);
}
static inline void unregister_chrdev(unsigned int major, const char *name)
{
__unregister_chrdev(major, 0, 256, name);
}
/* fs/block_dev.c */
#define BDEVNAME_SIZE 32 /* Largest string for a blockdev identifier */
#define BDEVT_SIZE 10 /* Largest string for MAJ:MIN for blkdev */
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 01:45:40 +07:00
#ifdef CONFIG_BLOCK
#define BLKDEV_MAJOR_HASH_SIZE 255
extern const char *__bdevname(dev_t, char *buffer);
extern const char *bdevname(struct block_device *bdev, char *buffer);
extern struct block_device *lookup_bdev(const char *);
extern void blkdev_show(struct seq_file *,off_t);
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 01:45:40 +07:00
#else
#define BLKDEV_MAJOR_HASH_SIZE 0
#endif
extern void init_special_inode(struct inode *, umode_t, dev_t);
/* Invalid inode operations -- fs/bad_inode.c */
extern void make_bad_inode(struct inode *);
extern int is_bad_inode(struct inode *);
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 01:45:40 +07:00
#ifdef CONFIG_BLOCK
/*
* return READ, READA, or WRITE
*/
#define bio_rw(bio) ((bio)->bi_rw & (RW_MASK | RWA_MASK))
/*
* return data direction, READ or WRITE
*/
#define bio_data_dir(bio) ((bio)->bi_rw & 1)
extern void check_disk_size_change(struct gendisk *disk,
struct block_device *bdev);
extern int revalidate_disk(struct gendisk *);
extern int check_disk_change(struct block_device *);
Fix over-zealous flush_disk when changing device size. There are two cases when we call flush_disk. In one, the device has disappeared (check_disk_change) so any data will hold becomes irrelevant. In the oter, the device has changed size (check_disk_size_change) so data we hold may be irrelevant. In both cases it makes sense to discard any 'clean' buffers, so they will be read back from the device if needed. In the former case it makes sense to discard 'dirty' buffers as there will never be anywhere safe to write the data. In the second case it *does*not* make sense to discard dirty buffers as that will lead to file system corruption when you simply enlarge the containing devices. flush_disk calls __invalidate_devices. __invalidate_device calls both invalidate_inodes and invalidate_bdev. invalidate_inodes *does* discard I_DIRTY inodes and this does lead to fs corruption. invalidate_bev *does*not* discard dirty pages, but I don't really care about that at present. So this patch adds a flag to __invalidate_device (calling it __invalidate_device2) to indicate whether dirty buffers should be killed, and this is passed to invalidate_inodes which can choose to skip dirty inodes. flusk_disk then passes true from check_disk_change and false from check_disk_size_change. dm avoids tripping over this problem by calling i_size_write directly rathher than using check_disk_size_change. md does use check_disk_size_change and so is affected. This regression was introduced by commit 608aeef17a which causes check_disk_size_change to call flush_disk, so it is suitable for any kernel since 2.6.27. Cc: stable@kernel.org Acked-by: Jeff Moyer <jmoyer@redhat.com> Cc: Andrew Patterson <andrew.patterson@hp.com> Cc: Jens Axboe <axboe@kernel.dk> Signed-off-by: NeilBrown <neilb@suse.de>
2011-02-24 13:25:47 +07:00
extern int __invalidate_device(struct block_device *, bool);
extern int invalidate_partition(struct gendisk *, int);
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 01:45:40 +07:00
#endif
unsigned long invalidate_mapping_pages(struct address_space *mapping,
pgoff_t start, pgoff_t end);
static inline void invalidate_remote_inode(struct inode *inode)
{
if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
S_ISLNK(inode->i_mode))
invalidate_mapping_pages(inode->i_mapping, 0, -1);
}
extern int invalidate_inode_pages2(struct address_space *mapping);
extern int invalidate_inode_pages2_range(struct address_space *mapping,
pgoff_t start, pgoff_t end);
extern int write_inode_now(struct inode *, int);
extern int filemap_fdatawrite(struct address_space *);
extern int filemap_flush(struct address_space *);
extern int filemap_fdatawait(struct address_space *);
extern int filemap_fdatawait_range(struct address_space *, loff_t lstart,
loff_t lend);
extern int filemap_write_and_wait(struct address_space *mapping);
extern int filemap_write_and_wait_range(struct address_space *mapping,
loff_t lstart, loff_t lend);
[PATCH] fadvise(): write commands Add two new linux-specific fadvise extensions(): LINUX_FADV_ASYNC_WRITE: start async writeout of any dirty pages between file offsets `offset' and `offset+len'. Any pages which are currently under writeout are skipped, whether or not they are dirty. LINUX_FADV_WRITE_WAIT: wait upon writeout of any dirty pages between file offsets `offset' and `offset+len'. By combining these two operations the application may do several things: LINUX_FADV_ASYNC_WRITE: push some or all of the dirty pages at the disk. LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE: push all of the currently dirty pages at the disk. LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE, LINUX_FADV_WRITE_WAIT: push all of the currently dirty pages at the disk, wait until they have been written. It should be noted that none of these operations write out the file's metadata. So unless the application is strictly performing overwrites of already-instantiated disk blocks, there are no guarantees here that the data will be available after a crash. To complete this suite of operations I guess we should have a "sync file metadata only" operation. This gives applications access to all the building blocks needed for all sorts of sync operations. But sync-metadata doesn't fit well with the fadvise() interface. Probably it should be a new syscall: sys_fmetadatasync(). The patch also diddles with the meaning of `endbyte' in sys_fadvise64_64(). It is made to represent that last affected byte in the file (ie: it is inclusive). Generally, all these byterange and pagerange functions are inclusive so we can easily represent EOF with -1. As Ulrich notes, these two functions are somewhat abusive of the fadvise() concept, which appears to be "set the future policy for this fd". But these commands are a perfect fit with the fadvise() impementation, and several of the existing fadvise() commands are synchronous and don't affect future policy either. I think we can live with the slight incongruity. Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-24 18:18:04 +07:00
extern int __filemap_fdatawrite_range(struct address_space *mapping,
loff_t start, loff_t end, int sync_mode);
extern int filemap_fdatawrite_range(struct address_space *mapping,
loff_t start, loff_t end);
[PATCH] fadvise(): write commands Add two new linux-specific fadvise extensions(): LINUX_FADV_ASYNC_WRITE: start async writeout of any dirty pages between file offsets `offset' and `offset+len'. Any pages which are currently under writeout are skipped, whether or not they are dirty. LINUX_FADV_WRITE_WAIT: wait upon writeout of any dirty pages between file offsets `offset' and `offset+len'. By combining these two operations the application may do several things: LINUX_FADV_ASYNC_WRITE: push some or all of the dirty pages at the disk. LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE: push all of the currently dirty pages at the disk. LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE, LINUX_FADV_WRITE_WAIT: push all of the currently dirty pages at the disk, wait until they have been written. It should be noted that none of these operations write out the file's metadata. So unless the application is strictly performing overwrites of already-instantiated disk blocks, there are no guarantees here that the data will be available after a crash. To complete this suite of operations I guess we should have a "sync file metadata only" operation. This gives applications access to all the building blocks needed for all sorts of sync operations. But sync-metadata doesn't fit well with the fadvise() interface. Probably it should be a new syscall: sys_fmetadatasync(). The patch also diddles with the meaning of `endbyte' in sys_fadvise64_64(). It is made to represent that last affected byte in the file (ie: it is inclusive). Generally, all these byterange and pagerange functions are inclusive so we can easily represent EOF with -1. As Ulrich notes, these two functions are somewhat abusive of the fadvise() concept, which appears to be "set the future policy for this fd". But these commands are a perfect fit with the fadvise() impementation, and several of the existing fadvise() commands are synchronous and don't affect future policy either. I think we can live with the slight incongruity. Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-24 18:18:04 +07:00
extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end,
int datasync);
extern int vfs_fsync(struct file *file, int datasync);
static inline int generic_write_sync(struct file *file, loff_t pos, loff_t count)
{
if (!(file->f_flags & O_DSYNC) && !IS_SYNC(file->f_mapping->host))
return 0;
return vfs_fsync_range(file, pos, pos + count - 1,
(file->f_flags & __O_SYNC) ? 0 : 1);
}
extern void emergency_sync(void);
extern void emergency_remount(void);
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 01:45:40 +07:00
#ifdef CONFIG_BLOCK
extern sector_t bmap(struct inode *, sector_t);
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 01:45:40 +07:00
#endif
extern int notify_change(struct dentry *, struct iattr *, struct inode **);
extern int inode_permission(struct inode *, int);
extern int __inode_permission(struct inode *, int);
extern int generic_permission(struct inode *, int);
extern int __check_sticky(struct inode *dir, struct inode *inode);
static inline bool execute_ok(struct inode *inode)
{
return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode);
}
static inline void file_start_write(struct file *file)
{
if (!S_ISREG(file_inode(file)->i_mode))
return;
__sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true);
}
static inline bool file_start_write_trylock(struct file *file)
{
if (!S_ISREG(file_inode(file)->i_mode))
return true;
return __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, false);
}
static inline void file_end_write(struct file *file)
{
if (!S_ISREG(file_inode(file)->i_mode))
return;
__sb_end_write(file_inode(file)->i_sb, SB_FREEZE_WRITE);
}
/*
* get_write_access() gets write permission for a file.
* put_write_access() releases this write permission.
* This is used for regular files.
* We cannot support write (and maybe mmap read-write shared) accesses and
* MAP_DENYWRITE mmappings simultaneously. The i_writecount field of an inode
* can have the following values:
* 0: no writers, no VM_DENYWRITE mappings
* < 0: (-i_writecount) vm_area_structs with VM_DENYWRITE set exist
* > 0: (i_writecount) users are writing to the file.
*
* Normally we operate on that counter with atomic_{inc,dec} and it's safe
* except for the cases where we don't hold i_writecount yet. Then we need to
* use {get,deny}_write_access() - these functions check the sign and refuse
* to do the change if sign is wrong.
*/
static inline int get_write_access(struct inode *inode)
{
return atomic_inc_unless_negative(&inode->i_writecount) ? 0 : -ETXTBSY;
}
static inline int deny_write_access(struct file *file)
{
struct inode *inode = file_inode(file);
return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY;
}
static inline void put_write_access(struct inode * inode)
{
atomic_dec(&inode->i_writecount);
}
static inline void allow_write_access(struct file *file)
{
if (file)
atomic_inc(&file_inode(file)->i_writecount);
}
NFS: Use i_writecount to control whether to get an fscache cookie in nfs_open() Use i_writecount to control whether to get an fscache cookie in nfs_open() as NFS does not do write caching yet. I *think* this is the cause of a problem encountered by Mark Moseley whereby __fscache_uncache_page() gets a NULL pointer dereference because cookie->def is NULL: BUG: unable to handle kernel NULL pointer dereference at 0000000000000010 IP: [<ffffffff812a1903>] __fscache_uncache_page+0x23/0x160 PGD 0 Thread overran stack, or stack corrupted Oops: 0000 [#1] SMP Modules linked in: ... CPU: 7 PID: 18993 Comm: php Not tainted 3.11.1 #1 Hardware name: Dell Inc. PowerEdge R420/072XWF, BIOS 1.3.5 08/21/2012 task: ffff8804203460c0 ti: ffff880420346640 RIP: 0010:[<ffffffff812a1903>] __fscache_uncache_page+0x23/0x160 RSP: 0018:ffff8801053af878 EFLAGS: 00210286 RAX: 0000000000000000 RBX: ffff8800be2f8780 RCX: ffff88022ffae5e8 RDX: 0000000000004c66 RSI: ffffea00055ff440 RDI: ffff8800be2f8780 RBP: ffff8801053af898 R08: 0000000000000001 R09: 0000000000000003 R10: 0000000000000000 R11: 0000000000000000 R12: ffffea00055ff440 R13: 0000000000001000 R14: ffff8800c50be538 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff88042fc60000(0063) knlGS:00000000e439c700 CS: 0010 DS: 002b ES: 002b CR0: 0000000080050033 CR2: 0000000000000010 CR3: 0000000001d8f000 CR4: 00000000000607f0 Stack: ... Call Trace: [<ffffffff81365a72>] __nfs_fscache_invalidate_page+0x42/0x70 [<ffffffff813553d5>] nfs_invalidate_page+0x75/0x90 [<ffffffff811b8f5e>] truncate_inode_page+0x8e/0x90 [<ffffffff811b90ad>] truncate_inode_pages_range.part.12+0x14d/0x620 [<ffffffff81d6387d>] ? __mutex_lock_slowpath+0x1fd/0x2e0 [<ffffffff811b95d3>] truncate_inode_pages_range+0x53/0x70 [<ffffffff811b969d>] truncate_inode_pages+0x2d/0x40 [<ffffffff811b96ff>] truncate_pagecache+0x4f/0x70 [<ffffffff81356840>] nfs_setattr_update_inode+0xa0/0x120 [<ffffffff81368de4>] nfs3_proc_setattr+0xc4/0xe0 [<ffffffff81357f78>] nfs_setattr+0xc8/0x150 [<ffffffff8122d95b>] notify_change+0x1cb/0x390 [<ffffffff8120a55b>] do_truncate+0x7b/0xc0 [<ffffffff8121f96c>] do_last+0xa4c/0xfd0 [<ffffffff8121ffbc>] path_openat+0xcc/0x670 [<ffffffff81220a0e>] do_filp_open+0x4e/0xb0 [<ffffffff8120ba1f>] do_sys_open+0x13f/0x2b0 [<ffffffff8126aaf6>] compat_SyS_open+0x36/0x50 [<ffffffff81d7204c>] sysenter_dispatch+0x7/0x24 The code at the instruction pointer was disassembled: > (gdb) disas __fscache_uncache_page > Dump of assembler code for function __fscache_uncache_page: > ... > 0xffffffff812a18ff <+31>: mov 0x48(%rbx),%rax > 0xffffffff812a1903 <+35>: cmpb $0x0,0x10(%rax) > 0xffffffff812a1907 <+39>: je 0xffffffff812a19cd <__fscache_uncache_page+237> These instructions make up: ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX); That cmpb is the faulting instruction (%rax is 0). So cookie->def is NULL - which presumably means that the cookie has already been at least partway through __fscache_relinquish_cookie(). What I think may be happening is something like a three-way race on the same file: PROCESS 1 PROCESS 2 PROCESS 3 =============== =============== =============== open(O_TRUNC|O_WRONLY) open(O_RDONLY) open(O_WRONLY) -->nfs_open() -->nfs_fscache_set_inode_cookie() nfs_fscache_inode_lock() nfs_fscache_disable_inode_cookie() __fscache_relinquish_cookie() nfs_inode->fscache = NULL <--nfs_fscache_set_inode_cookie() -->nfs_open() -->nfs_fscache_set_inode_cookie() nfs_fscache_inode_lock() nfs_fscache_enable_inode_cookie() __fscache_acquire_cookie() nfs_inode->fscache = cookie <--nfs_fscache_set_inode_cookie() <--nfs_open() -->nfs_setattr() ... ... -->nfs_invalidate_page() -->__nfs_fscache_invalidate_page() cookie = nfsi->fscache -->nfs_open() -->nfs_fscache_set_inode_cookie() nfs_fscache_inode_lock() nfs_fscache_disable_inode_cookie() -->__fscache_relinquish_cookie() -->__fscache_uncache_page(cookie) <crash> <--__fscache_relinquish_cookie() nfs_inode->fscache = NULL <--nfs_fscache_set_inode_cookie() What is needed is something to prevent process #2 from reacquiring the cookie - and I think checking i_writecount should do the trick. It's also possible to have a two-way race on this if the file is opened O_TRUNC|O_RDONLY instead. Reported-by: Mark Moseley <moseleymark@gmail.com> Signed-off-by: David Howells <dhowells@redhat.com>
2013-09-27 17:20:03 +07:00
static inline bool inode_is_open_for_write(const struct inode *inode)
{
return atomic_read(&inode->i_writecount) > 0;
}
#ifdef CONFIG_IMA
static inline void i_readcount_dec(struct inode *inode)
{
BUG_ON(!atomic_read(&inode->i_readcount));
atomic_dec(&inode->i_readcount);
}
static inline void i_readcount_inc(struct inode *inode)
{
atomic_inc(&inode->i_readcount);
}
#else
static inline void i_readcount_dec(struct inode *inode)
{
return;
}
static inline void i_readcount_inc(struct inode *inode)
{
return;
}
#endif
flag parameters: pipe This patch introduces the new syscall pipe2 which is like pipe but it also takes an additional parameter which takes a flag value. This patch implements the handling of O_CLOEXEC for the flag. I did not add support for the new syscall for the architectures which have a special sys_pipe implementation. I think the maintainers of those archs have the chance to go with the unified implementation but that's up to them. The implementation introduces do_pipe_flags. I did that instead of changing all callers of do_pipe because some of the callers are written in assembler. I would probably screw up changing the assembly code. To avoid breaking code do_pipe is now a small wrapper around do_pipe_flags. Once all callers are changed over to do_pipe_flags the old do_pipe function can be removed. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include <fcntl.h> #include <stdio.h> #include <unistd.h> #include <sys/syscall.h> #ifndef __NR_pipe2 # ifdef __x86_64__ # define __NR_pipe2 293 # elif defined __i386__ # define __NR_pipe2 331 # else # error "need __NR_pipe2" # endif #endif int main (void) { int fd[2]; if (syscall (__NR_pipe2, fd, 0) != 0) { puts ("pipe2(0) failed"); return 1; } for (int i = 0; i < 2; ++i) { int coe = fcntl (fd[i], F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { printf ("pipe2(0) set close-on-exit for fd[%d]\n", i); return 1; } } close (fd[0]); close (fd[1]); if (syscall (__NR_pipe2, fd, O_CLOEXEC) != 0) { puts ("pipe2(O_CLOEXEC) failed"); return 1; } for (int i = 0; i < 2; ++i) { int coe = fcntl (fd[i], F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { printf ("pipe2(O_CLOEXEC) does not set close-on-exit for fd[%d]\n", i); return 1; } } close (fd[0]); close (fd[1]); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper <drepper@redhat.com> Acked-by: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk.manpages@googlemail.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 11:29:30 +07:00
extern int do_pipe_flags(int *, int);
extern int kernel_read(struct file *, loff_t, char *, unsigned long);
extern ssize_t kernel_write(struct file *, const char *, size_t, loff_t);
extern ssize_t __kernel_write(struct file *, const char *, size_t, loff_t *);
extern struct file * open_exec(const char *);
/* fs/dcache.c -- generic fs support functions */
extern int is_subdir(struct dentry *, struct dentry *);
extern int path_is_under(struct path *, struct path *);
#include <linux/err.h>
/* needed for stackable file system support */
extern loff_t default_llseek(struct file *file, loff_t offset, int whence);
extern loff_t vfs_llseek(struct file *file, loff_t offset, int whence);
extern int inode_init_always(struct super_block *, struct inode *);
extern void inode_init_once(struct inode *);
mm: prevent concurrent unmap_mapping_range() on the same inode Michael Leun reported that running parallel opens on a fuse filesystem can trigger a "kernel BUG at mm/truncate.c:475" Gurudas Pai reported the same bug on NFS. The reason is, unmap_mapping_range() is not prepared for more than one concurrent invocation per inode. For example: thread1: going through a big range, stops in the middle of a vma and stores the restart address in vm_truncate_count. thread2: comes in with a small (e.g. single page) unmap request on the same vma, somewhere before restart_address, finds that the vma was already unmapped up to the restart address and happily returns without doing anything. Another scenario would be two big unmap requests, both having to restart the unmapping and each one setting vm_truncate_count to its own value. This could go on forever without any of them being able to finish. Truncate and hole punching already serialize with i_mutex. Other callers of unmap_mapping_range() do not, and it's difficult to get i_mutex protection for all callers. In particular ->d_revalidate(), which calls invalidate_inode_pages2_range() in fuse, may be called with or without i_mutex. This patch adds a new mutex to 'struct address_space' to prevent running multiple concurrent unmap_mapping_range() on the same mapping. [ We'll hopefully get rid of all this with the upcoming mm preemptibility series by Peter Zijlstra, the "mm: Remove i_mmap_mutex lockbreak" patch in particular. But that is for 2.6.39 ] Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Reported-by: Michael Leun <lkml20101129@newton.leun.net> Reported-by: Gurudas Pai <gurudas.pai@oracle.com> Tested-by: Gurudas Pai <gurudas.pai@oracle.com> Acked-by: Hugh Dickins <hughd@google.com> Cc: stable@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-02-23 19:49:47 +07:00
extern void address_space_init_once(struct address_space *mapping);
extern struct inode * igrab(struct inode *);
extern ino_t iunique(struct super_block *, ino_t);
extern int inode_needs_sync(struct inode *inode);
extern int generic_delete_inode(struct inode *inode);
static inline int generic_drop_inode(struct inode *inode)
{
return !inode->i_nlink || inode_unhashed(inode);
}
[PATCH] Fix soft lockup due to NTFS: VFS part and explanation Something has changed in the core kernel such that we now get concurrent inode write outs, one e.g via pdflush and one via sys_sync or whatever. This causes a nasty deadlock in ntfs. The only clean solution unfortunately requires a minor vfs api extension. First the deadlock analysis: Prerequisive knowledge: NTFS has a file $MFT (inode 0) loaded at mount time. The NTFS driver uses the page cache for storing the file contents as usual. More interestingly this file contains the table of on-disk inodes as a sequence of MFT_RECORDs. Thus NTFS driver accesses the on-disk inodes by accessing the MFT_RECORDs in the page cache pages of the loaded inode $MFT. The situation: VFS inode X on a mounted ntfs volume is dirty. For same inode X, the ntfs_inode is dirty and thus corresponding on-disk inode, which is as explained above in a dirty PAGE_CACHE_PAGE belonging to the table of inodes ($MFT, inode 0). What happens: Process 1: sys_sync()/umount()/whatever... calls __sync_single_inode() for $MFT -> do_writepages() -> write_page for the dirty page containing the on-disk inode X, the page is now locked -> ntfs_write_mst_block() which clears PageUptodate() on the page to prevent anyone else getting hold of it whilst it does the write out (this is necessary as the on-disk inode needs "fixups" applied before the write to disk which are removed again after the write and PageUptodate is then set again). It then analyses the page looking for dirty on-disk inodes and when it finds one it calls ntfs_may_write_mft_record() to see if it is safe to write this on-disk inode. This then calls ilookup5() to check if the corresponding VFS inode is in icache(). This in turn calls ifind() which waits on the inode lock via wait_on_inode whilst holding the global inode_lock. Process 2: pdflush results in a call to __sync_single_inode for the same VFS inode X on the ntfs volume. This locks the inode (I_LOCK) then calls write-inode -> ntfs_write_inode -> map_mft_record() -> read_cache_page() of the page (in page cache of table of inodes $MFT, inode 0) containing the on-disk inode. This page has PageUptodate() clear because of Process 1 (see above) so read_cache_page() blocks when tries to take the page lock for the page so it can call ntfs_read_page(). Thus Process 1 is holding the page lock on the page containing the on-disk inode X and it is waiting on the inode X to be unlocked in ifind() so it can write the page out and then unlock the page. And Process 2 is holding the inode lock on inode X and is waiting for the page to be unlocked so it can call ntfs_readpage() or discover that Process 1 set PageUptodate() again and use the page. Thus we have a deadlock due to ifind() waiting on the inode lock. The only sensible solution: NTFS does not care whether the VFS inode is locked or not when it calls ilookup5() (it doesn't use the VFS inode at all, it just uses it to find the corresponding ntfs_inode which is of course attached to the VFS inode (both are one single struct); and it uses the ntfs_inode which is subject to its own locking so I_LOCK is irrelevant) hence we want a modified ilookup5_nowait() which is the same as ilookup5() but it does not wait on the inode lock. Without such functionality I would have to keep my own ntfs_inode cache in the NTFS driver just so I can find ntfs_inodes independent of their VFS inodes which would be slow, memory and cpu cycle wasting, and incredibly stupid given the icache already exists in the VFS. Below is a patch that does the ilookup5_nowait() implementation in fs/inode.c and exports it. ilookup5_nowait.diff: Introduce ilookup5_nowait() which is basically the same as ilookup5() but it does not wait on the inode's lock (i.e. it omits the wait_on_inode() done in ifind()). This is needed to avoid a nasty deadlock in NTFS. Signed-off-by: Anton Altaparmakov <aia21@cantab.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-07-13 15:10:44 +07:00
extern struct inode *ilookup5_nowait(struct super_block *sb,
unsigned long hashval, int (*test)(struct inode *, void *),
void *data);
extern struct inode *ilookup5(struct super_block *sb, unsigned long hashval,
int (*test)(struct inode *, void *), void *data);
extern struct inode *ilookup(struct super_block *sb, unsigned long ino);
extern struct inode * iget5_locked(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *);
extern struct inode * iget_locked(struct super_block *, unsigned long);
extern struct inode *find_inode_nowait(struct super_block *,
unsigned long,
int (*match)(struct inode *,
unsigned long, void *),
void *data);
extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *);
extern int insert_inode_locked(struct inode *);
lockdep: Add helper function for dir vs file i_mutex annotation Purely in-memory filesystems do not use the inode hash as the dcache tells us if an entry already exists. As a result, they do not call unlock_new_inode, and thus directory inodes do not get put into a different lockdep class for i_sem. We need the different lockdep classes, because the locking order for i_mutex is different for directory inodes and regular inodes. Directory inodes can do "readdir()", which takes i_mutex *before* possibly taking mm->mmap_sem (due to a page fault while copying the directory entry to user space). In contrast, regular inodes can be mmap'ed, which takes mm->mmap_sem before accessing i_mutex. The two cases can never happen for the same inode, so no real deadlock can occur, but without the different lockdep classes, lockdep cannot understand that. As a result, if CONFIG_DEBUG_LOCK_ALLOC is set, this can lead to false positives from lockdep like below: find/645 is trying to acquire lock: (&mm->mmap_sem){++++++}, at: [<ffffffff81109514>] might_fault+0x5c/0xac but task is already holding lock: (&sb->s_type->i_mutex_key#15){+.+.+.}, at: [<ffffffff81149f34>] vfs_readdir+0x5b/0xb4 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&sb->s_type->i_mutex_key#15){+.+.+.}: [<ffffffff8108ac26>] lock_acquire+0xbf/0x103 [<ffffffff814db822>] __mutex_lock_common+0x4c/0x361 [<ffffffff814dbc46>] mutex_lock_nested+0x40/0x45 [<ffffffff811daa87>] hugetlbfs_file_mmap+0x82/0x110 [<ffffffff81111557>] mmap_region+0x258/0x432 [<ffffffff811119dd>] do_mmap_pgoff+0x2ac/0x306 [<ffffffff81111b4f>] sys_mmap_pgoff+0x118/0x16a [<ffffffff8100c858>] sys_mmap+0x22/0x24 [<ffffffff814e3ec2>] system_call_fastpath+0x16/0x1b -> #0 (&mm->mmap_sem){++++++}: [<ffffffff8108a4bc>] __lock_acquire+0xa1a/0xcf7 [<ffffffff8108ac26>] lock_acquire+0xbf/0x103 [<ffffffff81109541>] might_fault+0x89/0xac [<ffffffff81149cff>] filldir+0x6f/0xc7 [<ffffffff811586ea>] dcache_readdir+0x67/0x205 [<ffffffff81149f54>] vfs_readdir+0x7b/0xb4 [<ffffffff8114a073>] sys_getdents+0x7e/0xd1 [<ffffffff814e3ec2>] system_call_fastpath+0x16/0x1b This patch moves the directory vs file lockdep annotation into a helper function that can be called by in-memory filesystems and has hugetlbfs call it. Signed-off-by: Josh Boyer <jwboyer@redhat.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-08-25 18:48:12 +07:00
#ifdef CONFIG_DEBUG_LOCK_ALLOC
extern void lockdep_annotate_inode_mutex_key(struct inode *inode);
#else
static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { };
#endif
extern void unlock_new_inode(struct inode *);
extern unsigned int get_next_ino(void);
extern void __iget(struct inode * inode);
extern void iget_failed(struct inode *);
extern void clear_inode(struct inode *);
extern void __destroy_inode(struct inode *);
extern struct inode *new_inode_pseudo(struct super_block *sb);
extern struct inode *new_inode(struct super_block *sb);
extern void free_inode_nonrcu(struct inode *inode);
extern int should_remove_suid(struct dentry *);
extern int file_remove_suid(struct file *);
extern void __insert_inode_hash(struct inode *, unsigned long hashval);
static inline void insert_inode_hash(struct inode *inode)
{
__insert_inode_hash(inode, inode->i_ino);
}
extern void __remove_inode_hash(struct inode *);
static inline void remove_inode_hash(struct inode *inode)
{
if (!inode_unhashed(inode))
__remove_inode_hash(inode);
}
extern void inode_sb_list_add(struct inode *inode);
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 01:45:40 +07:00
#ifdef CONFIG_BLOCK
extern void submit_bio(int, struct bio *);
extern int bdev_read_only(struct block_device *);
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 01:45:40 +07:00
#endif
extern int set_blocksize(struct block_device *, int);
extern int sb_set_blocksize(struct super_block *, int);
extern int sb_min_blocksize(struct super_block *, int);
extern int generic_file_mmap(struct file *, struct vm_area_struct *);
extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk);
extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *);
extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *);
extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *, loff_t);
extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t);
extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos);
extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos);
extern ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos);
extern ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos);
ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos);
ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos);
/* fs/block_dev.c */
extern ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to);
extern ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from);
extern int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
int datasync);
extern void block_sync_page(struct page *page);
/* fs/splice.c */
extern ssize_t generic_file_splice_read(struct file *, loff_t *,
struct pipe_inode_info *, size_t, unsigned int);
extern ssize_t default_file_splice_read(struct file *, loff_t *,
struct pipe_inode_info *, size_t, unsigned int);
extern ssize_t iter_file_splice_write(struct pipe_inode_info *,
struct file *, loff_t *, size_t, unsigned int);
extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
struct file *out, loff_t *, size_t len, unsigned int flags);
extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
loff_t *opos, size_t len, unsigned int flags);
extern void
file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping);
extern loff_t noop_llseek(struct file *file, loff_t offset, int whence);
extern loff_t no_llseek(struct file *file, loff_t offset, int whence);
extern loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize);
extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence);
extern loff_t generic_file_llseek_size(struct file *file, loff_t offset,
int whence, loff_t maxsize, loff_t eof);
extern loff_t fixed_size_llseek(struct file *file, loff_t offset,
int whence, loff_t size);
extern int generic_file_open(struct inode * inode, struct file * filp);
extern int nonseekable_open(struct inode * inode, struct file * filp);
ssize_t dax_do_io(int rw, struct kiocb *, struct inode *, struct iov_iter *,
loff_t, get_block_t, dio_iodone_t, int flags);
int dax_clear_blocks(struct inode *, sector_t block, long size);
int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
int dax_truncate_page(struct inode *, loff_t from, get_block_t);
int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t);
#define dax_mkwrite(vma, vmf, gb) dax_fault(vma, vmf, gb)
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 01:45:40 +07:00
#ifdef CONFIG_BLOCK
typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode,
loff_t file_offset);
enum {
/* need locking between buffered and direct access */
DIO_LOCKING = 0x01,
/* filesystem does not support filling holes */
DIO_SKIP_HOLES = 0x02,
/* filesystem can handle aio writes beyond i_size */
DIO_ASYNC_EXTEND = 0x04,
};
void dio_end_io(struct bio *bio, int error);
ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
struct block_device *bdev, struct iov_iter *iter, loff_t offset,
get_block_t get_block, dio_iodone_t end_io,
dio_submit_t submit_io, int flags);
fs: introduce new truncate sequence Introduce a new truncate calling sequence into fs/mm subsystems. Rather than setattr > vmtruncate > truncate, have filesystems call their truncate sequence from ->setattr if filesystem specific operations are required. vmtruncate is deprecated, and truncate_pagecache and inode_newsize_ok helpers introduced previously should be used. simple_setattr is introduced for simple in-ram filesystems to implement the new truncate sequence. Eventually all filesystems should be converted to implement a setattr, and the default code in notify_change should go away. simple_setsize is also introduced to perform just the ATTR_SIZE portion of simple_setattr (ie. changing i_size and trimming pagecache). To implement the new truncate sequence: - filesystem specific manipulations (eg freeing blocks) must be done in the setattr method rather than ->truncate. - vmtruncate can not be used by core code to trim blocks past i_size in the event of write failure after allocation, so this must be performed in the fs code. - convert usage of helpers block_write_begin, nobh_write_begin, cont_write_begin, and *blockdev_direct_IO* to use _newtrunc postfixed variants. These avoid calling vmtruncate to trim blocks (see previous). - inode_setattr should not be used. generic_setattr is a new function to be used to copy simple attributes into the generic inode. - make use of the better opportunity to handle errors with the new sequence. Big problem with the previous calling sequence: the filesystem is not called until i_size has already changed. This means it is not allowed to fail the call, and also it does not know what the previous i_size was. Also, generic code calling vmtruncate to truncate allocated blocks in case of error had no good way to return a meaningful error (or, for example, atomically handle block deallocation). Cc: Christoph Hellwig <hch@lst.de> Acked-by: Jan Kara <jack@suse.cz> Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-05-26 22:05:33 +07:00
static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb,
struct inode *inode, struct iov_iter *iter, loff_t offset,
get_block_t get_block)
{
return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iter,
offset, get_block, NULL, NULL,
DIO_LOCKING | DIO_SKIP_HOLES);
}
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 01:45:40 +07:00
#endif
void inode_dio_wait(struct inode *inode);
void inode_dio_done(struct inode *inode);
extern void inode_set_flags(struct inode *inode, unsigned int flags,
unsigned int mask);
extern const struct file_operations generic_ro_fops;
#define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m))
extern int readlink_copy(char __user *, int, const char *);
extern int page_readlink(struct dentry *, char __user *, int);
extern void *page_follow_link_light(struct dentry *, struct nameidata *);
extern void page_put_link(struct dentry *, struct nameidata *, void *);
extern int __page_symlink(struct inode *inode, const char *symname, int len,
fs: symlink write_begin allocation context fix With the write_begin/write_end aops, page_symlink was broken because it could no longer pass a GFP_NOFS type mask into the point where the allocations happened. They are done in write_begin, which would always assume that the filesystem can be entered from reclaim. This bug could cause filesystem deadlocks. The funny thing with having a gfp_t mask there is that it doesn't really allow the caller to arbitrarily tinker with the context in which it can be called. It couldn't ever be GFP_ATOMIC, for example, because it needs to take the page lock. The only thing any callers care about is __GFP_FS anyway, so turn that into a single flag. Add a new flag for write_begin, AOP_FLAG_NOFS. Filesystems can now act on this flag in their write_begin function. Change __grab_cache_page to accept a nofs argument as well, to honour that flag (while we're there, change the name to grab_cache_page_write_begin which is more instructive and does away with random leading underscores). This is really a more flexible way to go in the end anyway -- if a filesystem happens to want any extra allocations aside from the pagecache ones in ints write_begin function, it may now use GFP_KERNEL (rather than GFP_NOFS) for common case allocations (eg. ocfs2_alloc_write_ctxt, for a random example). [kosaki.motohiro@jp.fujitsu.com: fix ubifs] [kosaki.motohiro@jp.fujitsu.com: fix fuse] Signed-off-by: Nick Piggin <npiggin@suse.de> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: <stable@kernel.org> [2.6.28.x] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> [ Cleaned up the calling convention: just pass in the AOP flags untouched to the grab_cache_page_write_begin() function. That just simplifies everybody, and may even allow future expansion of the logic. - Linus ] Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-05 03:00:53 +07:00
int nofs);
extern int page_symlink(struct inode *inode, const char *symname, int len);
extern const struct inode_operations page_symlink_inode_operations;
extern void kfree_put_link(struct dentry *, struct nameidata *, void *);
extern int generic_readlink(struct dentry *, char __user *, int);
extern void generic_fillattr(struct inode *, struct kstat *);
int vfs_getattr_nosec(struct path *path, struct kstat *stat);
extern int vfs_getattr(struct path *, struct kstat *);
void __inode_add_bytes(struct inode *inode, loff_t bytes);
void inode_add_bytes(struct inode *inode, loff_t bytes);
void __inode_sub_bytes(struct inode *inode, loff_t bytes);
void inode_sub_bytes(struct inode *inode, loff_t bytes);
loff_t inode_get_bytes(struct inode *inode);
void inode_set_bytes(struct inode *inode, loff_t bytes);
extern int vfs_readdir(struct file *, filldir_t, void *);
extern int iterate_dir(struct file *, struct dir_context *);
extern int vfs_stat(const char __user *, struct kstat *);
extern int vfs_lstat(const char __user *, struct kstat *);
extern int vfs_fstat(unsigned int, struct kstat *);
extern int vfs_fstatat(int , const char __user *, struct kstat *, int);
extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
unsigned long arg);
extern int __generic_block_fiemap(struct inode *inode,
struct fiemap_extent_info *fieinfo,
loff_t start, loff_t len,
get_block_t *get_block);
extern int generic_block_fiemap(struct inode *inode,
struct fiemap_extent_info *fieinfo, u64 start,
u64 len, get_block_t *get_block);
extern void get_filesystem(struct file_system_type *fs);
extern void put_filesystem(struct file_system_type *fs);
extern struct file_system_type *get_fs_type(const char *name);
extern struct super_block *get_super(struct block_device *);
extern struct super_block *get_super_thawed(struct block_device *);
extern struct super_block *get_active_super(struct block_device *bdev);
extern void drop_super(struct super_block *sb);
extern void iterate_supers(void (*)(struct super_block *, void *), void *);
extern void iterate_supers_type(struct file_system_type *,
void (*)(struct super_block *, void *), void *);
extern int dcache_dir_open(struct inode *, struct file *);
extern int dcache_dir_close(struct inode *, struct file *);
extern loff_t dcache_dir_lseek(struct file *, loff_t, int);
extern int dcache_readdir(struct file *, struct dir_context *);
fs: introduce new truncate sequence Introduce a new truncate calling sequence into fs/mm subsystems. Rather than setattr > vmtruncate > truncate, have filesystems call their truncate sequence from ->setattr if filesystem specific operations are required. vmtruncate is deprecated, and truncate_pagecache and inode_newsize_ok helpers introduced previously should be used. simple_setattr is introduced for simple in-ram filesystems to implement the new truncate sequence. Eventually all filesystems should be converted to implement a setattr, and the default code in notify_change should go away. simple_setsize is also introduced to perform just the ATTR_SIZE portion of simple_setattr (ie. changing i_size and trimming pagecache). To implement the new truncate sequence: - filesystem specific manipulations (eg freeing blocks) must be done in the setattr method rather than ->truncate. - vmtruncate can not be used by core code to trim blocks past i_size in the event of write failure after allocation, so this must be performed in the fs code. - convert usage of helpers block_write_begin, nobh_write_begin, cont_write_begin, and *blockdev_direct_IO* to use _newtrunc postfixed variants. These avoid calling vmtruncate to trim blocks (see previous). - inode_setattr should not be used. generic_setattr is a new function to be used to copy simple attributes into the generic inode. - make use of the better opportunity to handle errors with the new sequence. Big problem with the previous calling sequence: the filesystem is not called until i_size has already changed. This means it is not allowed to fail the call, and also it does not know what the previous i_size was. Also, generic code calling vmtruncate to truncate allocated blocks in case of error had no good way to return a meaningful error (or, for example, atomically handle block deallocation). Cc: Christoph Hellwig <hch@lst.de> Acked-by: Jan Kara <jack@suse.cz> Signed-off-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-05-26 22:05:33 +07:00
extern int simple_setattr(struct dentry *, struct iattr *);
extern int simple_getattr(struct vfsmount *, struct dentry *, struct kstat *);
extern int simple_statfs(struct dentry *, struct kstatfs *);
extern int simple_open(struct inode *inode, struct file *file);
extern int simple_link(struct dentry *, struct inode *, struct dentry *);
extern int simple_unlink(struct inode *, struct dentry *);
extern int simple_rmdir(struct inode *, struct dentry *);
extern int simple_rename(struct inode *, struct dentry *, struct inode *, struct dentry *);
extern int noop_fsync(struct file *, loff_t, loff_t, int);
extern int simple_empty(struct dentry *);
extern int simple_readpage(struct file *file, struct page *page);
extern int simple_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata);
extern int simple_write_end(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata);
extern int always_delete_dentry(const struct dentry *);
extern struct inode *alloc_anon_inode(struct super_block *);
extern int simple_nosetlease(struct file *, long, struct file_lock **, void **);
extern const struct dentry_operations simple_dentry_operations;
extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags);
extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *);
extern const struct file_operations simple_dir_operations;
extern const struct inode_operations simple_dir_inode_operations;
struct tree_descr { char *name; const struct file_operations *ops; int mode; };
struct dentry *d_alloc_name(struct dentry *, const char *);
extern int simple_fill_super(struct super_block *, unsigned long, struct tree_descr *);
extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count);
extern void simple_release_fs(struct vfsmount **mount, int *count);
2008-06-06 12:46:21 +07:00
extern ssize_t simple_read_from_buffer(void __user *to, size_t count,
loff_t *ppos, const void *from, size_t available);
extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos,
const void __user *from, size_t count);
extern int __generic_file_fsync(struct file *, loff_t, loff_t, int);
extern int generic_file_fsync(struct file *, loff_t, loff_t, int);
extern int generic_check_addressable(unsigned, u64);
#ifdef CONFIG_MIGRATION
extern int buffer_migrate_page(struct address_space *,
struct page *, struct page *,
enum migrate_mode);
#else
#define buffer_migrate_page NULL
#endif
extern int inode_change_ok(const struct inode *, struct iattr *);
extern int inode_newsize_ok(const struct inode *, loff_t offset);
extern void setattr_copy(struct inode *inode, const struct iattr *attr);
extern int file_update_time(struct file *file);
extern int generic_show_options(struct seq_file *m, struct dentry *root);
extern void save_mount_options(struct super_block *sb, char *options);
extern void replace_mount_options(struct super_block *sb, char *options);
static inline bool io_is_direct(struct file *filp)
{
return (filp->f_flags & O_DIRECT) || IS_DAX(file_inode(filp));
}
static inline ino_t parent_ino(struct dentry *dentry)
{
ino_t res;
/*
* Don't strictly need d_lock here? If the parent ino could change
* then surely we'd have a deeper race in the caller?
*/
spin_lock(&dentry->d_lock);
res = dentry->d_parent->d_inode->i_ino;
spin_unlock(&dentry->d_lock);
return res;
}
/* Transaction based IO helpers */
/*
* An argresp is stored in an allocated page and holds the
* size of the argument or response, along with its content
*/
struct simple_transaction_argresp {
ssize_t size;
char data[0];
};
#define SIMPLE_TRANSACTION_LIMIT (PAGE_SIZE - sizeof(struct simple_transaction_argresp))
char *simple_transaction_get(struct file *file, const char __user *buf,
size_t size);
ssize_t simple_transaction_read(struct file *file, char __user *buf,
size_t size, loff_t *pos);
int simple_transaction_release(struct inode *inode, struct file *file);
void simple_transaction_set(struct file *file, size_t n);
/*
* simple attribute files
*
* These attributes behave similar to those in sysfs:
*
* Writing to an attribute immediately sets a value, an open file can be
* written to multiple times.
*
* Reading from an attribute creates a buffer from the value that might get
* read with multiple read calls. When the attribute has been read
* completely, no further read calls are possible until the file is opened
* again.
*
* All attributes contain a text representation of a numeric value
* that are accessed with the get() and set() functions.
*/
#define DEFINE_SIMPLE_ATTRIBUTE(__fops, __get, __set, __fmt) \
static int __fops ## _open(struct inode *inode, struct file *file) \
{ \
__simple_attr_check_format(__fmt, 0ull); \
return simple_attr_open(inode, file, __get, __set, __fmt); \
} \
static const struct file_operations __fops = { \
.owner = THIS_MODULE, \
.open = __fops ## _open, \
.release = simple_attr_release, \
.read = simple_attr_read, \
.write = simple_attr_write, \
.llseek = generic_file_llseek, \
}
static inline __printf(1, 2)
void __simple_attr_check_format(const char *fmt, ...)
{
/* don't do anything, just let the compiler check the arguments; */
}
int simple_attr_open(struct inode *inode, struct file *file,
int (*get)(void *, u64 *), int (*set)(void *, u64),
const char *fmt);
int simple_attr_release(struct inode *inode, struct file *file);
ssize_t simple_attr_read(struct file *file, char __user *buf,
size_t len, loff_t *ppos);
ssize_t simple_attr_write(struct file *file, const char __user *buf,
size_t len, loff_t *ppos);
struct ctl_table;
int proc_nr_files(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
int proc_nr_dentry(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
int proc_nr_inodes(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
int __init get_filesystem_list(char *buf);
#define __FMODE_EXEC ((__force int) FMODE_EXEC)
#define __FMODE_NONOTIFY ((__force int) FMODE_NONOTIFY)
#define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE])
#define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \
(flag & __FMODE_NONOTIFY)))
static inline int is_sxid(umode_t mode)
Cache xattr security drop check for write v2 Some recent benchmarking on btrfs showed that a major scaling bottleneck on large systems on btrfs is currently the xattr lookup on every write. Why xattr lookup on every write I hear you ask? write wants to drop suid and security related xattrs that could set o capabilities for executables. To do that it currently looks up security.capability on EVERY write (even for non executables) to decide whether to drop it or not. In btrfs this causes an additional tree walk, hitting some per file system locks and quite bad scalability. In a simple read workload on a 8S system I saw over 90% CPU time in spinlocks related to that. Chris Mason tells me this is also a problem in ext4, where it hits the global mbcache lock. This patch adds a simple per inode to avoid this problem. We only do the lookup once per file and then if there is no xattr cache the decision. All xattr changes clear the flag. I also used the same flag to avoid the suid check, although that one is pretty cheap. A file system can also set this flag when it creates the inode, if it has a cheap way to do so. This is done for some common file systems in followon patches. With this patch a major part of the lock contention disappears for btrfs. Some testing on smaller systems didn't show significant performance changes, but at least it helps the larger systems and is generally more efficient. v2: Rename is_sgid. add file system helper. Cc: chris.mason@oracle.com Cc: josef@redhat.com Cc: viro@zeniv.linux.org.uk Cc: agruen@linbit.com Cc: Serge E. Hallyn <serue@us.ibm.com> Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2011-05-28 22:25:51 +07:00
{
return (mode & S_ISUID) || ((mode & S_ISGID) && (mode & S_IXGRP));
}
static inline int check_sticky(struct inode *dir, struct inode *inode)
{
if (!(dir->i_mode & S_ISVTX))
return 0;
return __check_sticky(dir, inode);
}
Cache xattr security drop check for write v2 Some recent benchmarking on btrfs showed that a major scaling bottleneck on large systems on btrfs is currently the xattr lookup on every write. Why xattr lookup on every write I hear you ask? write wants to drop suid and security related xattrs that could set o capabilities for executables. To do that it currently looks up security.capability on EVERY write (even for non executables) to decide whether to drop it or not. In btrfs this causes an additional tree walk, hitting some per file system locks and quite bad scalability. In a simple read workload on a 8S system I saw over 90% CPU time in spinlocks related to that. Chris Mason tells me this is also a problem in ext4, where it hits the global mbcache lock. This patch adds a simple per inode to avoid this problem. We only do the lookup once per file and then if there is no xattr cache the decision. All xattr changes clear the flag. I also used the same flag to avoid the suid check, although that one is pretty cheap. A file system can also set this flag when it creates the inode, if it has a cheap way to do so. This is done for some common file systems in followon patches. With this patch a major part of the lock contention disappears for btrfs. Some testing on smaller systems didn't show significant performance changes, but at least it helps the larger systems and is generally more efficient. v2: Rename is_sgid. add file system helper. Cc: chris.mason@oracle.com Cc: josef@redhat.com Cc: viro@zeniv.linux.org.uk Cc: agruen@linbit.com Cc: Serge E. Hallyn <serue@us.ibm.com> Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2011-05-28 22:25:51 +07:00
static inline void inode_has_no_xattr(struct inode *inode)
{
if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & MS_NOSEC))
Cache xattr security drop check for write v2 Some recent benchmarking on btrfs showed that a major scaling bottleneck on large systems on btrfs is currently the xattr lookup on every write. Why xattr lookup on every write I hear you ask? write wants to drop suid and security related xattrs that could set o capabilities for executables. To do that it currently looks up security.capability on EVERY write (even for non executables) to decide whether to drop it or not. In btrfs this causes an additional tree walk, hitting some per file system locks and quite bad scalability. In a simple read workload on a 8S system I saw over 90% CPU time in spinlocks related to that. Chris Mason tells me this is also a problem in ext4, where it hits the global mbcache lock. This patch adds a simple per inode to avoid this problem. We only do the lookup once per file and then if there is no xattr cache the decision. All xattr changes clear the flag. I also used the same flag to avoid the suid check, although that one is pretty cheap. A file system can also set this flag when it creates the inode, if it has a cheap way to do so. This is done for some common file systems in followon patches. With this patch a major part of the lock contention disappears for btrfs. Some testing on smaller systems didn't show significant performance changes, but at least it helps the larger systems and is generally more efficient. v2: Rename is_sgid. add file system helper. Cc: chris.mason@oracle.com Cc: josef@redhat.com Cc: viro@zeniv.linux.org.uk Cc: agruen@linbit.com Cc: Serge E. Hallyn <serue@us.ibm.com> Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2011-05-28 22:25:51 +07:00
inode->i_flags |= S_NOSEC;
}
static inline bool is_root_inode(struct inode *inode)
{
return inode == inode->i_sb->s_root->d_inode;
}
static inline bool dir_emit(struct dir_context *ctx,
const char *name, int namelen,
u64 ino, unsigned type)
{
return ctx->actor(ctx, name, namelen, ctx->pos, ino, type) == 0;
}
static inline bool dir_emit_dot(struct file *file, struct dir_context *ctx)
{
return ctx->actor(ctx, ".", 1, ctx->pos,
file->f_path.dentry->d_inode->i_ino, DT_DIR) == 0;
}
static inline bool dir_emit_dotdot(struct file *file, struct dir_context *ctx)
{
return ctx->actor(ctx, "..", 2, ctx->pos,
parent_ino(file->f_path.dentry), DT_DIR) == 0;
}
static inline bool dir_emit_dots(struct file *file, struct dir_context *ctx)
{
if (ctx->pos == 0) {
if (!dir_emit_dot(file, ctx))
return false;
ctx->pos = 1;
}
if (ctx->pos == 1) {
if (!dir_emit_dotdot(file, ctx))
return false;
ctx->pos = 2;
}
return true;
}
static inline bool dir_relax(struct inode *inode)
{
mutex_unlock(&inode->i_mutex);
mutex_lock(&inode->i_mutex);
return !IS_DEADDIR(inode);
}
#endif /* _LINUX_FS_H */