WSL2-Linux-Kernel/include/linux/fs.h

2564 строки
86 KiB
C
Исходник Обычный вид История

#ifndef _LINUX_FS_H
#define _LINUX_FS_H
/*
* This file has definitions for some important file table
* structures etc.
*/
#include <linux/limits.h>
#include <linux/ioctl.h>
#include <linux/blk_types.h>
#include <linux/types.h>
/*
* It's silly to have NR_OPEN bigger than NR_FILE, but you can change
* the file limit at runtime and only root can increase the per-process
* nr_file rlimit, so it's safe to set up a ridiculously high absolute
* upper limit on files-per-process.
*
* Some programs (notably those using select()) may have to be
* recompiled to take full advantage of the new limits..
*/
/* Fixed constants first: */
#undef NR_OPEN
#define INR_OPEN 1024 /* Initial setting for nfile rlimits */
#define BLOCK_SIZE_BITS 10
#define BLOCK_SIZE (1<<BLOCK_SIZE_BITS)
#define SEEK_SET 0 /* seek relative to beginning of file */
#define SEEK_CUR 1 /* seek relative to current file position */
#define SEEK_END 2 /* seek relative to end of file */
#define SEEK_MAX SEEK_END
struct fstrim_range {
__u64 start;
__u64 len;
__u64 minlen;
};
/* And dynamically-tunable limits and defaults: */
struct files_stat_struct {
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 01:22:44 +04:00
unsigned long nr_files; /* read only */
unsigned long nr_free_files; /* read only */
unsigned long max_files; /* tunable */
};
struct inodes_stat_t {
int nr_inodes;
int nr_unused;
int dummy[5]; /* padding for sysctl ABI compatibility */
};
#define NR_FILE 8192 /* this can well be larger on a larger system */
#define MAY_EXEC 1
#define MAY_WRITE 2
#define MAY_READ 4
#define MAY_APPEND 8
#define MAY_ACCESS 16
#define MAY_OPEN 32
#define MAY_CHDIR 64
/*
* 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)
/*
* 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)
readahead: introduce FMODE_RANDOM for POSIX_FADV_RANDOM This fixes inefficient page-by-page reads on POSIX_FADV_RANDOM. POSIX_FADV_RANDOM used to set ra_pages=0, which leads to poor performance: a 16K read will be carried out in 4 _sync_ 1-page reads. In other places, ra_pages==0 means - it's ramfs/tmpfs/hugetlbfs/sysfs/configfs - some IO error happened where multi-page read IO won't help or should be avoided. POSIX_FADV_RANDOM actually want a different semantics: to disable the *heuristic* readahead algorithm, and to use a dumb one which faithfully submit read IO for whatever application requests. So introduce a flag FMODE_RANDOM for POSIX_FADV_RANDOM. Note that the random hint is not likely to help random reads performance noticeably. And it may be too permissive on huge request size (its IO size is not limited by read_ahead_kb). In Quentin's report (http://lkml.org/lkml/2009/12/24/145), the overall (NFS read) performance of the application increased by 313%! Tested-by: Quentin Barnes <qbarnes+nfs@yahoo-inc.com> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Andi Kleen <andi@firstfloor.org> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: David Howells <dhowells@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: <stable@kernel.org> [2.6.33.x] Cc: <qbarnes+nfs@yahoo-inc.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-03-06 00:42:03 +03:00
/* Expect random access pattern */
#define FMODE_RANDOM ((__force fmode_t)0x1000)
readahead: introduce FMODE_RANDOM for POSIX_FADV_RANDOM This fixes inefficient page-by-page reads on POSIX_FADV_RANDOM. POSIX_FADV_RANDOM used to set ra_pages=0, which leads to poor performance: a 16K read will be carried out in 4 _sync_ 1-page reads. In other places, ra_pages==0 means - it's ramfs/tmpfs/hugetlbfs/sysfs/configfs - some IO error happened where multi-page read IO won't help or should be avoided. POSIX_FADV_RANDOM actually want a different semantics: to disable the *heuristic* readahead algorithm, and to use a dumb one which faithfully submit read IO for whatever application requests. So introduce a flag FMODE_RANDOM for POSIX_FADV_RANDOM. Note that the random hint is not likely to help random reads performance noticeably. And it may be too permissive on huge request size (its IO size is not limited by read_ahead_kb). In Quentin's report (http://lkml.org/lkml/2009/12/24/145), the overall (NFS read) performance of the application increased by 313%! Tested-by: Quentin Barnes <qbarnes+nfs@yahoo-inc.com> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Andi Kleen <andi@firstfloor.org> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: David Howells <dhowells@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: <stable@kernel.org> [2.6.33.x] Cc: <qbarnes+nfs@yahoo-inc.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-03-06 00:42:03 +03:00
/* File is huge (eg. /dev/kmem): treat loff_t as unsigned */
#define FMODE_UNSIGNED_OFFSET ((__force fmode_t)0x2000)
/* File was opened by fanotify and shouldn't generate fanotify events */
#define FMODE_NONOTIFY ((__force fmode_t)0x1000000)
/*
* 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_PLUG Synchronous write. Identical to WRITE, but passes down
* the hint that someone will be waiting on this IO
* shortly. The device must still be unplugged explicitly,
* WRITE_SYNC_PLUG does not do this as we could be
* submitting more writes before we actually wait on any
* of them.
* WRITE_SYNC Like WRITE_SYNC_PLUG, but also unplugs the device
* immediately after submission. The write equivalent
* of READ_SYNC.
Fix regression in direct writes performance due to WRITE_ODIRECT flag removal There seems to be a regression in direct write path due to following commit in for-2.6.33 branch of block tree. commit 1af60fbd759d31f565552fea315c2033947cfbe6 Author: Jeff Moyer <jmoyer@redhat.com> Date: Fri Oct 2 18:56:53 2009 -0400 block: get rid of the WRITE_ODIRECT flag Marking direct writes as WRITE_SYNC_PLUG instead of WRITE_ODIRECT, sets the NOIDLE flag in bio and hence in request. This tells CFQ to not expect more request from the queue and not idle on it (despite the fact that queue's think time is less and it is not seeky). So direct writers lose big time when competing with sequential readers. Using fio, I have run one direct writer and two sequential readers and following are the results with 2.6.32-rc7 kernel and with for-2.6.33 branch. Test ==== 1 direct writer and 2 sequential reader running simultaneously. [global] directory=/mnt/sdc/fio/ runtime=10 [seqwrite] rw=write size=4G direct=1 [seqread] rw=read size=2G numjobs=2 2.6.32-rc7 ========== direct writes: aggrb=2,968KB/s readers : aggrb=101MB/s for-2.6.33 branch ================= direct write: aggrb=19KB/s readers aggrb=137MB/s This patch brings back the WRITE_ODIRECT flag, with the difference that we don't set the BIO_RW_UNPLUG flag so that device is not unplugged after submission of request and an explicit unplug from submitter is required. That way we fix the jeff's issue of not enough merging taking place in aio path as well as make sure direct writes get their fair share. After the fix ============= for-2.6.33 + fix ---------------- direct writes: aggrb=2,728KB/s reads: aggrb=103MB/s Thanks Vivek Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-11-26 11:45:40 +03:00
* WRITE_ODIRECT_PLUG Special case write for O_DIRECT only.
block: implement REQ_FLUSH/FUA based interface for FLUSH/FUA requests Now that the backend conversion is complete, export sequenced FLUSH/FUA capability through REQ_FLUSH/FUA flags. REQ_FLUSH means the device cache should be flushed before executing the request. REQ_FUA means that the data in the request should be on non-volatile media on completion. Block layer will choose the correct way of implementing the semantics and execute it. The request may be passed to the device directly if the device can handle it; otherwise, it will be sequenced using one or more proxy requests. Devices will never see REQ_FLUSH and/or FUA which it doesn't support. Also, unlike the original REQ_HARDBARRIER, REQ_FLUSH/FUA requests are never failed with -EOPNOTSUPP. If the underlying device doesn't support FLUSH/FUA, the block layer simply make those noop. IOW, it no longer distinguishes between writeback cache which doesn't support cache flush and writethrough/no cache. Devices which have WB cache w/o flush are very difficult to come by these days and there's nothing much we can do anyway, so it doesn't make sense to require everyone to implement -EOPNOTSUPP handling. This will simplify filesystems and block drivers as they can drop -EOPNOTSUPP retry logic for barriers. * QUEUE_ORDERED_* are removed and QUEUE_FSEQ_* are moved into blk-flush.c. * REQ_FLUSH w/o data can also be directly passed to drivers without sequencing but some drivers assume that zero length requests don't have rq->bio which isn't true for these requests requiring the use of proxy requests. * REQ_COMMON_MASK now includes REQ_FLUSH | REQ_FUA so that they are copied from bio to request. * WRITE_BARRIER is marked deprecated and WRITE_FLUSH, WRITE_FUA and WRITE_FLUSH_FUA are added. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2010-09-03 13:56:17 +04:00
* 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 | REQ_UNPLUG)
#define READ_META (READ | REQ_META)
#define WRITE_SYNC_PLUG (WRITE | REQ_SYNC | REQ_NOIDLE)
#define WRITE_SYNC (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG)
#define WRITE_ODIRECT_PLUG (WRITE | REQ_SYNC)
#define WRITE_META (WRITE | REQ_META)
block: implement REQ_FLUSH/FUA based interface for FLUSH/FUA requests Now that the backend conversion is complete, export sequenced FLUSH/FUA capability through REQ_FLUSH/FUA flags. REQ_FLUSH means the device cache should be flushed before executing the request. REQ_FUA means that the data in the request should be on non-volatile media on completion. Block layer will choose the correct way of implementing the semantics and execute it. The request may be passed to the device directly if the device can handle it; otherwise, it will be sequenced using one or more proxy requests. Devices will never see REQ_FLUSH and/or FUA which it doesn't support. Also, unlike the original REQ_HARDBARRIER, REQ_FLUSH/FUA requests are never failed with -EOPNOTSUPP. If the underlying device doesn't support FLUSH/FUA, the block layer simply make those noop. IOW, it no longer distinguishes between writeback cache which doesn't support cache flush and writethrough/no cache. Devices which have WB cache w/o flush are very difficult to come by these days and there's nothing much we can do anyway, so it doesn't make sense to require everyone to implement -EOPNOTSUPP handling. This will simplify filesystems and block drivers as they can drop -EOPNOTSUPP retry logic for barriers. * QUEUE_ORDERED_* are removed and QUEUE_FSEQ_* are moved into blk-flush.c. * REQ_FLUSH w/o data can also be directly passed to drivers without sequencing but some drivers assume that zero length requests don't have rq->bio which isn't true for these requests requiring the use of proxy requests. * REQ_COMMON_MASK now includes REQ_FLUSH | REQ_FUA so that they are copied from bio to request. * WRITE_BARRIER is marked deprecated and WRITE_FLUSH, WRITE_FUA and WRITE_FLUSH_FUA are added. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2010-09-03 13:56:17 +04:00
#define WRITE_FLUSH (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
REQ_FLUSH)
#define WRITE_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
REQ_FUA)
#define WRITE_FLUSH_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
REQ_FLUSH | REQ_FUA)
#define SEL_IN 1
#define SEL_OUT 2
#define SEL_EX 4
/* public flags for file_system_type */
#define FS_REQUIRES_DEV 1
#define FS_BINARY_MOUNTDATA 2
#define FS_HAS_SUBTYPE 4
#define FS_REVAL_DOT 16384 /* Check the paths ".", ".." for staleness */
#define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move()
* during rename() internally.
*/
/*
* These are the fs-independent mount-flags: up to 32 flags are supported
*/
#define MS_RDONLY 1 /* Mount read-only */
#define MS_NOSUID 2 /* Ignore suid and sgid bits */
#define MS_NODEV 4 /* Disallow access to device special files */
#define MS_NOEXEC 8 /* Disallow program execution */
#define MS_SYNCHRONOUS 16 /* Writes are synced at once */
#define MS_REMOUNT 32 /* Alter flags of a mounted FS */
#define MS_MANDLOCK 64 /* Allow mandatory locks on an FS */
#define MS_DIRSYNC 128 /* Directory modifications are synchronous */
#define MS_NOATIME 1024 /* Do not update access times. */
#define MS_NODIRATIME 2048 /* Do not update directory access times */
#define MS_BIND 4096
#define MS_MOVE 8192
#define MS_REC 16384
#define MS_VERBOSE 32768 /* War is peace. Verbosity is silence.
MS_VERBOSE is deprecated. */
#define MS_SILENT 32768
#define MS_POSIXACL (1<<16) /* VFS does not apply the umask */
#define MS_UNBINDABLE (1<<17) /* change to unbindable */
#define MS_PRIVATE (1<<18) /* change to private */
#define MS_SLAVE (1<<19) /* change to slave */
#define MS_SHARED (1<<20) /* change to shared */
#define MS_RELATIME (1<<21) /* Update atime relative to mtime/ctime. */
#define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */
#define MS_I_VERSION (1<<23) /* Update inode I_version field */
#define MS_STRICTATIME (1<<24) /* Always perform atime updates */
#define MS_BORN (1<<29)
#define MS_ACTIVE (1<<30)
#define MS_NOUSER (1<<31)
/*
* Superblock flags that can be altered by MS_REMOUNT
*/
#define MS_RMT_MASK (MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION)
/*
* Old magic mount flag and mask
*/
#define MS_MGC_VAL 0xC0ED0000
#define MS_MGC_MSK 0xffff0000
/* Inode flags - they have nothing 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 */
Add a dentry op to handle automounting rather than abusing follow_link() Add a dentry op (d_automount) to handle automounting directories rather than abusing the follow_link() inode operation. The operation is keyed off a new dentry flag (DCACHE_NEED_AUTOMOUNT). This also makes it easier to add an AT_ flag to suppress terminal segment automount during pathwalk and removes the need for the kludge code in the pathwalk algorithm to handle directories with follow_link() semantics. The ->d_automount() dentry operation: struct vfsmount *(*d_automount)(struct path *mountpoint); takes a pointer to the directory to be mounted upon, which is expected to provide sufficient data to determine what should be mounted. If successful, it should return the vfsmount struct it creates (which it should also have added to the namespace using do_add_mount() or similar). If there's a collision with another automount attempt, NULL should be returned. If the directory specified by the parameter should be used directly rather than being mounted upon, -EISDIR should be returned. In any other case, an error code should be returned. The ->d_automount() operation is called with no locks held and may sleep. At this point the pathwalk algorithm will be in ref-walk mode. Within fs/namei.c itself, a new pathwalk subroutine (follow_automount()) is added to handle mountpoints. It will return -EREMOTE if the automount flag was set, but no d_automount() op was supplied, -ELOOP if we've encountered too many symlinks or mountpoints, -EISDIR if the walk point should be used without mounting and 0 if successful. The path will be updated to point to the mounted filesystem if a successful automount took place. __follow_mount() is replaced by follow_managed() which is more generic (especially with the patch that adds ->d_manage()). This handles transits from directories during pathwalk, including automounting and skipping over mountpoints (and holding processes with the next patch). __follow_mount_rcu() will jump out of RCU-walk mode if it encounters an automount point with nothing mounted on it. follow_dotdot*() does not handle automounts as you don't want to trigger them whilst following "..". I've also extracted the mount/don't-mount logic from autofs4 and included it here. It makes the mount go ahead anyway if someone calls open() or creat(), tries to traverse the directory, tries to chdir/chroot/etc. into the directory, or sticks a '/' on the end of the pathname. If they do a stat(), however, they'll only trigger the automount if they didn't also say O_NOFOLLOW. I've also added an inode flag (S_AUTOMOUNT) so that filesystems can mark their inodes as automount points. This flag is automatically propagated to the dentry as DCACHE_NEED_AUTOMOUNT by __d_instantiate(). This saves NFS and could save AFS a private flag bit apiece, but is not strictly necessary. It would be preferable to do the propagation in d_set_d_op(), but that doesn't normally have access to the inode. [AV: fixed breakage in case if __follow_mount_rcu() fails and nameidata_drop_rcu() succeeds in RCU case of do_lookup(); we need to fall through to non-RCU case after that, rather than just returning with ungrabbed *path] Signed-off-by: David Howells <dhowells@redhat.com> Was-Acked-by: Ian Kent <raven@themaw.net> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2011-01-14 21:45:21 +03:00
#define S_AUTOMOUNT 2048 /* Automount/referral quasi-directory */
/*
* 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)
Add a dentry op to handle automounting rather than abusing follow_link() Add a dentry op (d_automount) to handle automounting directories rather than abusing the follow_link() inode operation. The operation is keyed off a new dentry flag (DCACHE_NEED_AUTOMOUNT). This also makes it easier to add an AT_ flag to suppress terminal segment automount during pathwalk and removes the need for the kludge code in the pathwalk algorithm to handle directories with follow_link() semantics. The ->d_automount() dentry operation: struct vfsmount *(*d_automount)(struct path *mountpoint); takes a pointer to the directory to be mounted upon, which is expected to provide sufficient data to determine what should be mounted. If successful, it should return the vfsmount struct it creates (which it should also have added to the namespace using do_add_mount() or similar). If there's a collision with another automount attempt, NULL should be returned. If the directory specified by the parameter should be used directly rather than being mounted upon, -EISDIR should be returned. In any other case, an error code should be returned. The ->d_automount() operation is called with no locks held and may sleep. At this point the pathwalk algorithm will be in ref-walk mode. Within fs/namei.c itself, a new pathwalk subroutine (follow_automount()) is added to handle mountpoints. It will return -EREMOTE if the automount flag was set, but no d_automount() op was supplied, -ELOOP if we've encountered too many symlinks or mountpoints, -EISDIR if the walk point should be used without mounting and 0 if successful. The path will be updated to point to the mounted filesystem if a successful automount took place. __follow_mount() is replaced by follow_managed() which is more generic (especially with the patch that adds ->d_manage()). This handles transits from directories during pathwalk, including automounting and skipping over mountpoints (and holding processes with the next patch). __follow_mount_rcu() will jump out of RCU-walk mode if it encounters an automount point with nothing mounted on it. follow_dotdot*() does not handle automounts as you don't want to trigger them whilst following "..". I've also extracted the mount/don't-mount logic from autofs4 and included it here. It makes the mount go ahead anyway if someone calls open() or creat(), tries to traverse the directory, tries to chdir/chroot/etc. into the directory, or sticks a '/' on the end of the pathname. If they do a stat(), however, they'll only trigger the automount if they didn't also say O_NOFOLLOW. I've also added an inode flag (S_AUTOMOUNT) so that filesystems can mark their inodes as automount points. This flag is automatically propagated to the dentry as DCACHE_NEED_AUTOMOUNT by __d_instantiate(). This saves NFS and could save AFS a private flag bit apiece, but is not strictly necessary. It would be preferable to do the propagation in d_set_d_op(), but that doesn't normally have access to the inode. [AV: fixed breakage in case if __follow_mount_rcu() fails and nameidata_drop_rcu() succeeds in RCU case of do_lookup(); we need to fall through to non-RCU case after that, rather than just returning with ungrabbed *path] Signed-off-by: David Howells <dhowells@redhat.com> Was-Acked-by: Ian Kent <raven@themaw.net> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2011-01-14 21:45:21 +03:00
#define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT)
/* the read-only stuff doesn't really belong here, but any other place is
probably as bad and I don't want to create yet another include file. */
#define BLKROSET _IO(0x12,93) /* set device read-only (0 = read-write) */
#define BLKROGET _IO(0x12,94) /* get read-only status (0 = read_write) */
#define BLKRRPART _IO(0x12,95) /* re-read partition table */
#define BLKGETSIZE _IO(0x12,96) /* return device size /512 (long *arg) */
#define BLKFLSBUF _IO(0x12,97) /* flush buffer cache */
#define BLKRASET _IO(0x12,98) /* set read ahead for block device */
#define BLKRAGET _IO(0x12,99) /* get current read ahead setting */
#define BLKFRASET _IO(0x12,100)/* set filesystem (mm/filemap.c) read-ahead */
#define BLKFRAGET _IO(0x12,101)/* get filesystem (mm/filemap.c) read-ahead */
#define BLKSECTSET _IO(0x12,102)/* set max sectors per request (ll_rw_blk.c) */
#define BLKSECTGET _IO(0x12,103)/* get max sectors per request (ll_rw_blk.c) */
#define BLKSSZGET _IO(0x12,104)/* get block device sector size */
#if 0
#define BLKPG _IO(0x12,105)/* See blkpg.h */
/* Some people are morons. Do not use sizeof! */
#define BLKELVGET _IOR(0x12,106,size_t)/* elevator get */
#define BLKELVSET _IOW(0x12,107,size_t)/* elevator set */
/* This was here just to show that the number is taken -
probably all these _IO(0x12,*) ioctls should be moved to blkpg.h. */
#endif
/* A jump here: 108-111 have been used for various private purposes. */
#define BLKBSZGET _IOR(0x12,112,size_t)
#define BLKBSZSET _IOW(0x12,113,size_t)
#define BLKGETSIZE64 _IOR(0x12,114,size_t) /* return device size in bytes (u64 *arg) */
#define BLKTRACESETUP _IOWR(0x12,115,struct blk_user_trace_setup)
#define BLKTRACESTART _IO(0x12,116)
#define BLKTRACESTOP _IO(0x12,117)
#define BLKTRACETEARDOWN _IO(0x12,118)
#define BLKDISCARD _IO(0x12,119)
#define BLKIOMIN _IO(0x12,120)
#define BLKIOOPT _IO(0x12,121)
#define BLKALIGNOFF _IO(0x12,122)
#define BLKPBSZGET _IO(0x12,123)
#define BLKDISCARDZEROES _IO(0x12,124)
#define BLKSECDISCARD _IO(0x12,125)
#define BMAP_IOCTL 1 /* obsolete - kept for compatibility */
#define FIBMAP _IO(0x00,1) /* bmap access */
#define FIGETBSZ _IO(0x00,2) /* get the block size used for bmap */
#define FIFREEZE _IOWR('X', 119, int) /* Freeze */
#define FITHAW _IOWR('X', 120, int) /* Thaw */
#define FITRIM _IOWR('X', 121, struct fstrim_range) /* Trim */
#define FS_IOC_GETFLAGS _IOR('f', 1, long)
#define FS_IOC_SETFLAGS _IOW('f', 2, long)
#define FS_IOC_GETVERSION _IOR('v', 1, long)
#define FS_IOC_SETVERSION _IOW('v', 2, long)
#define FS_IOC_FIEMAP _IOWR('f', 11, struct fiemap)
#define FS_IOC32_GETFLAGS _IOR('f', 1, int)
#define FS_IOC32_SETFLAGS _IOW('f', 2, int)
#define FS_IOC32_GETVERSION _IOR('v', 1, int)
#define FS_IOC32_SETVERSION _IOW('v', 2, int)
/*
* Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
*/
#define FS_SECRM_FL 0x00000001 /* Secure deletion */
#define FS_UNRM_FL 0x00000002 /* Undelete */
#define FS_COMPR_FL 0x00000004 /* Compress file */
#define FS_SYNC_FL 0x00000008 /* Synchronous updates */
#define FS_IMMUTABLE_FL 0x00000010 /* Immutable file */
#define FS_APPEND_FL 0x00000020 /* writes to file may only append */
#define FS_NODUMP_FL 0x00000040 /* do not dump file */
#define FS_NOATIME_FL 0x00000080 /* do not update atime */
/* Reserved for compression usage... */
#define FS_DIRTY_FL 0x00000100
#define FS_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */
#define FS_NOCOMP_FL 0x00000400 /* Don't compress */
#define FS_ECOMPR_FL 0x00000800 /* Compression error */
/* End compression flags --- maybe not all used */
#define FS_BTREE_FL 0x00001000 /* btree format dir */
#define FS_INDEX_FL 0x00001000 /* hash-indexed directory */
#define FS_IMAGIC_FL 0x00002000 /* AFS directory */
#define FS_JOURNAL_DATA_FL 0x00004000 /* Reserved for ext3 */
#define FS_NOTAIL_FL 0x00008000 /* file tail should not be merged */
#define FS_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */
#define FS_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/
#define FS_EXTENT_FL 0x00080000 /* Extents */
#define FS_DIRECTIO_FL 0x00100000 /* Use direct i/o */
#define FS_RESERVED_FL 0x80000000 /* reserved for ext2 lib */
#define FS_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */
#define FS_FL_USER_MODIFIABLE 0x000380FF /* User modifiable flags */
#define SYNC_FILE_RANGE_WAIT_BEFORE 1
#define SYNC_FILE_RANGE_WRITE 2
#define SYNC_FILE_RANGE_WAIT_AFTER 4
#ifdef __KERNEL__
#include <linux/linkage.h>
#include <linux/wait.h>
#include <linux/types.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/radix-tree.h>
#include <linux/prio_tree.h>
#include <linux/init.h>
#include <linux/pid.h>
#include <linux/mutex.h>
#include <linux/capability.h>
#include <linux/semaphore.h>
#include <linux/fiemap.h>
#include <linux/rculist_bl.h>
#include <asm/atomic.h>
#include <asm/byteorder.h>
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;
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 01:22:44 +04:00
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;
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, int ret,
bool is_async);
/*
* 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)
/*
* 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;
uid_t ia_uid;
gid_t ia_gid;
loff_t ia_size;
struct timespec ia_atime;
struct timespec ia_mtime;
struct timespec ia_ctime;
/*
* Not an attribute, but an auxilary 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>
/**
* 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>
2009-01-04 23:00:53 +03:00
#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;
struct iov_iter {
const struct iovec *iov;
unsigned long nr_segs;
size_t iov_offset;
size_t count;
};
size_t iov_iter_copy_from_user_atomic(struct page *page,
struct iov_iter *i, unsigned long offset, size_t bytes);
size_t iov_iter_copy_from_user(struct page *page,
struct iov_iter *i, unsigned long offset, size_t bytes);
void iov_iter_advance(struct iov_iter *i, size_t bytes);
int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes);
size_t iov_iter_single_seg_count(struct iov_iter *i);
static inline void iov_iter_init(struct iov_iter *i,
const struct iovec *iov, unsigned long nr_segs,
size_t count, size_t written)
{
i->iov = iov;
i->nr_segs = nr_segs;
i->iov_offset = 0;
i->count = count + written;
iov_iter_advance(i, written);
}
static inline size_t iov_iter_count(struct iov_iter *i)
{
return i->count;
}
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 02:46:36 +04:00
/*
* "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 *);
void (*sync_page)(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 long);
int (*releasepage) (struct page *, gfp_t);
void (*freepage)(struct page *);
ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
loff_t offset, unsigned long nr_segs);
int (*get_xip_mem)(struct address_space *, pgoff_t, int,
void **, unsigned long *);
/* migrate the contents of a page to the specified target */
int (*migratepage) (struct address_space *,
struct page *, struct page *);
int (*launder_page) (struct page *);
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 02:46:36 +04:00
int (*is_partially_uptodate) (struct page *, read_descriptor_t *,
unsigned long);
int (*error_remove_page)(struct address_space *, struct page *);
};
/*
* 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 backing_dev_info;
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 */
unsigned int i_mmap_writable;/* count VM_SHARED mappings */
struct prio_tree_root i_mmap; /* tree of private and shared mappings */
struct list_head i_mmap_nonlinear;/*list VM_NONLINEAR mappings */
spinlock_t i_mmap_lock; /* protect tree, count, list */
unsigned int truncate_count; /* Cover race condition with truncate */
unsigned long nrpages; /* number of total pages */
pgoff_t writeback_index;/* writeback starts here */
const struct address_space_operations *a_ops; /* methods */
unsigned long flags; /* error bits/gfp mask */
struct backing_dev_info *backing_dev_info; /* device readahead, etc */
spinlock_t private_lock; /* for use by the address_space */
struct list_head private_list; /* ditto */
struct address_space *assoc_mapping; /* 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 signficant bit
* of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON.
*/
struct block_device {
dev_t bd_dev; /* not a kdev_t - it's a search key */
struct inode * bd_inode; /* will die */
struct super_block * bd_super;
int bd_openers;
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 13:53:59 +04:00
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>
2010-12-08 22:57:37 +03:00
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 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);
/*
* Might pages of this file be mapped into userspace?
*/
static inline int mapping_mapped(struct address_space *mapping)
{
return !prio_tree_empty(&mapping->i_mmap) ||
!list_empty(&mapping->i_mmap_nonlinear);
}
/*
* 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.
*/
static inline int mapping_writably_mapped(struct address_space *mapping)
{
return mapping->i_mmap_writable != 0;
}
/*
* 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))
struct inode {
/* RCU path lookup touches following: */
umode_t i_mode;
uid_t i_uid;
gid_t i_gid;
const struct inode_operations *i_op;
struct super_block *i_sb;
spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */
unsigned int i_flags;
struct mutex i_mutex;
unsigned long i_state;
unsigned long dirtied_when; /* jiffies of first dirtying */
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 09:49:49 +03:00
union {
struct list_head i_dentry;
struct rcu_head i_rcu;
};
unsigned long i_ino;
atomic_t i_count;
unsigned int i_nlink;
dev_t i_rdev;
unsigned int i_blkbits;
u64 i_version;
loff_t i_size;
#ifdef __NEED_I_SIZE_ORDERED
seqcount_t i_size_seqcount;
#endif
struct timespec i_atime;
struct timespec i_mtime;
struct timespec i_ctime;
blkcnt_t i_blocks;
unsigned short i_bytes;
struct rw_semaphore i_alloc_sem;
const struct file_operations *i_fop; /* former ->i_op->default_file_ops */
struct file_lock *i_flock;
struct address_space *i_mapping;
struct address_space i_data;
#ifdef CONFIG_QUOTA
struct dquot *i_dquot[MAXQUOTAS];
#endif
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
#ifdef CONFIG_IMA
/* protected by i_lock */
unsigned int i_readcount; /* struct files open RO */
#endif
atomic_t i_writecount;
#ifdef CONFIG_SECURITY
void *i_security;
#endif
#ifdef CONFIG_FS_POSIX_ACL
struct posix_acl *i_acl;
struct posix_acl *i_default_acl;
#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: quota file
*
* The locking order between these classes is
* parent -> child -> normal -> xattr -> quota
*/
enum inode_i_mutex_lock_class
{
I_MUTEX_NORMAL,
I_MUTEX_PARENT,
I_MUTEX_CHILD,
I_MUTEX_XATTR,
I_MUTEX_QUOTA
};
/*
* 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)
write_seqcount_begin(&inode->i_size_seqcount);
inode->i_size = i_size;
write_seqcount_end(&inode->i_size_seqcount);
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
preempt_disable();
inode->i_size = i_size;
preempt_enable();
#else
inode->i_size = i_size;
#endif
}
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 */
uid_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);
}
#define FILE_MNT_WRITE_TAKEN 1
#define FILE_MNT_WRITE_RELEASED 2
struct file {
/*
* fu_list becomes invalid after file_free is called and queued via
* fu_rcuhead for RCU freeing
*/
union {
struct list_head fu_list;
struct rcu_head fu_rcuhead;
} f_u;
struct path f_path;
#define f_dentry f_path.dentry
#define f_vfsmnt f_path.mnt
const struct file_operations *f_op;
spinlock_t f_lock; /* f_ep_links, f_flags, no IRQ */
fs: scale files_lock fs: scale files_lock Improve scalability of files_lock by adding per-cpu, per-sb files lists, protected with an lglock. The lglock provides fast access to the per-cpu lists to add and remove files. It also provides a snapshot of all the per-cpu lists (although this is very slow). One difficulty with this approach is that a file can be removed from the list by another CPU. We must track which per-cpu list the file is on with a new variale in the file struct (packed into a hole on 64-bit archs). Scalability could suffer if files are frequently removed from different cpu's list. However loads with frequent removal of files imply short interval between adding and removing the files, and the scheduler attempts to avoid moving processes too far away. Also, even in the case of cross-CPU removal, the hardware has much more opportunity to parallelise cacheline transfers with N cachelines than with 1. A worst-case test of 1 CPU allocating files subsequently being freed by N CPUs degenerates to contending on a single lock, which is no worse than before. When more than one CPU are allocating files, even if they are always freed by different CPUs, there will be more parallelism than the single-lock case. Testing results: On a 2 socket, 8 core opteron, I measure the number of times the lock is taken to remove the file, the number of times it is removed by the same CPU that added it, and the number of times it is removed by the same node that added it. Booting: locks= 25049 cpu-hits= 23174 (92.5%) node-hits= 23945 (95.6%) kbuild -j16 locks=2281913 cpu-hits=2208126 (96.8%) node-hits=2252674 (98.7%) dbench 64 locks=4306582 cpu-hits=4287247 (99.6%) node-hits=4299527 (99.8%) So a file is removed from the same CPU it was added by over 90% of the time. It remains within the same node 95% of the time. Tim Chen ran some numbers for a 64 thread Nehalem system performing a compile. throughput 2.6.34-rc2 24.5 +patch 24.9 us sys idle IO wait (in %) 2.6.34-rc2 51.25 28.25 17.25 3.25 +patch 53.75 18.5 19 8.75 So significantly less CPU time spent in kernel code, higher idle time and slightly higher throughput. Single threaded performance difference was within the noise of microbenchmarks. That is not to say penalty does not exist, the code is larger and more memory accesses required so it will be slightly slower. Cc: linux-kernel@vger.kernel.org Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Signed-off-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-17 22:37:38 +04:00
#ifdef CONFIG_SMP
int f_sb_list_cpu;
#endif
atomic_long_t f_count;
unsigned int f_flags;
fmode_t f_mode;
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;
#endif /* #ifdef CONFIG_EPOLL */
struct address_space *f_mapping;
#ifdef CONFIG_DEBUG_WRITECOUNT
unsigned long f_mnt_write_state;
#endif
};
#define get_file(x) atomic_long_inc(&(x)->f_count)
#define fput_atomic(x) atomic_long_add_unless(&(x)->f_count, -1, 1)
#define file_count(x) atomic_long_read(&(x)->f_count)
#ifdef CONFIG_DEBUG_WRITECOUNT
static inline void file_take_write(struct file *f)
{
WARN_ON(f->f_mnt_write_state != 0);
f->f_mnt_write_state = FILE_MNT_WRITE_TAKEN;
}
static inline void file_release_write(struct file *f)
{
f->f_mnt_write_state |= FILE_MNT_WRITE_RELEASED;
}
static inline void file_reset_write(struct file *f)
{
f->f_mnt_write_state = 0;
}
static inline void file_check_state(struct file *f)
{
/*
* At this point, either both or neither of these bits
* should be set.
*/
WARN_ON(f->f_mnt_write_state == FILE_MNT_WRITE_TAKEN);
WARN_ON(f->f_mnt_write_state == FILE_MNT_WRITE_RELEASED);
}
static inline int file_check_writeable(struct file *f)
{
if (f->f_mnt_write_state == FILE_MNT_WRITE_TAKEN)
return 0;
printk(KERN_WARNING "writeable file with no "
"mnt_want_write()\n");
WARN_ON(1);
return -EINVAL;
}
#else /* !CONFIG_DEBUG_WRITECOUNT */
static inline void file_take_write(struct file *filp) {}
static inline void file_release_write(struct file *filp) {}
static inline void file_reset_write(struct file *filp) {}
static inline void file_check_state(struct file *filp) {}
static inline int file_check_writeable(struct file *filp)
{
return 0;
}
#endif /* CONFIG_DEBUG_WRITECOUNT */
#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 (((u64)PAGE_CACHE_SIZE << (BITS_PER_LONG-1))-1)
#elif BITS_PER_LONG==64
#define MAX_LFS_FILESIZE 0x7fffffffffffffffUL
#endif
#define FL_POSIX 1
#define FL_FLOCK 2
#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 */
/*
* Special return value from posix_lock_file() and vfs_lock_file() for
* asynchronous locking.
*/
#define FILE_LOCK_DEFERRED 1
/*
* The POSIX file lock owner is determined by
* the "struct files_struct" in the thread group
* (or NULL for no owner - BSD locks).
*
* Lockd stuffs a "host" pointer into this.
*/
typedef struct files_struct *fl_owner_t;
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 (*fl_compare_owner)(struct file_lock *, struct file_lock *);
void (*fl_notify)(struct file_lock *); /* unblock callback */
int (*fl_grant)(struct file_lock *, struct file_lock *, int);
void (*fl_release_private)(struct file_lock *);
void (*fl_break)(struct file_lock *);
int (*fl_change)(struct file_lock **, int);
};
struct lock_manager {
struct list_head list;
};
void locks_start_grace(struct lock_manager *);
void locks_end_grace(struct lock_manager *);
int locks_in_grace(void);
/* that will die - we need it for nfs_lock_info */
#include <linux/nfs_fs_i.h>
struct file_lock {
struct file_lock *fl_next; /* singly linked list for this inode */
struct list_head fl_link; /* doubly linked list of all locks */
struct list_head fl_block; /* circular list of blocked processes */
fl_owner_t fl_owner;
unsigned char fl_flags;
unsigned char fl_type;
unsigned int fl_pid;
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 */
unsigned long fl_break_time; /* for nonblocking lease breaks */
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;
};
/* 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 *, 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>
2005-07-27 22:45:09 +04:00
extern int fcntl_setlk(unsigned int, struct file *, unsigned int,
struct flock __user *);
#if BITS_PER_LONG == 32
extern int fcntl_getlk64(struct file *, 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>
2005-07-27 22:45:09 +04:00
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(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_lock(struct file_lock *, const struct file_lock *);
extern void locks_remove_posix(struct file *, fl_owner_t);
extern void locks_remove_flock(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 *, 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);
extern void lease_get_mtime(struct inode *, struct timespec *time);
extern int generic_setlease(struct file *, long, struct file_lock **);
extern int vfs_setlease(struct file *, long, struct file_lock **);
extern int lease_modify(struct file_lock **, int);
extern int lock_may_read(struct inode *, loff_t start, unsigned long count);
extern int lock_may_write(struct inode *, loff_t start, unsigned long count);
extern void lock_flocks(void);
extern void unlock_flocks(void);
#else /* !CONFIG_FILE_LOCKING */
static inline int fcntl_getlk(struct file *file, 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, 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 0;
}
static inline int fcntl_getlease(struct file *filp)
{
return 0;
}
static inline void locks_init_lock(struct file_lock *fl)
{
return;
}
static inline void __locks_copy_lock(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_flock(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 *filp,
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)
{
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)
{
return -EINVAL;
}
static inline int vfs_setlease(struct file *filp, long arg,
struct file_lock **lease)
{
return -EINVAL;
}
static inline int lease_modify(struct file_lock **before, int arg)
{
return -EINVAL;
}
static inline int lock_may_read(struct inode *inode, loff_t start,
unsigned long len)
{
return 1;
}
static inline int lock_may_write(struct inode *inode, loff_t start,
unsigned long len)
{
return 1;
}
static inline void lock_flocks(void)
{
}
static inline void unlock_flocks(void)
{
}
#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 int __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
extern int 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);
/*
* 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 */
extern struct list_head super_blocks;
extern spinlock_t sb_lock;
struct super_block {
struct list_head s_list; /* Keep this first */
dev_t s_dev; /* search index; _not_ kdev_t */
unsigned char s_dirt;
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;
struct mutex s_lock;
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 */
fs: scale files_lock fs: scale files_lock Improve scalability of files_lock by adding per-cpu, per-sb files lists, protected with an lglock. The lglock provides fast access to the per-cpu lists to add and remove files. It also provides a snapshot of all the per-cpu lists (although this is very slow). One difficulty with this approach is that a file can be removed from the list by another CPU. We must track which per-cpu list the file is on with a new variale in the file struct (packed into a hole on 64-bit archs). Scalability could suffer if files are frequently removed from different cpu's list. However loads with frequent removal of files imply short interval between adding and removing the files, and the scheduler attempts to avoid moving processes too far away. Also, even in the case of cross-CPU removal, the hardware has much more opportunity to parallelise cacheline transfers with N cachelines than with 1. A worst-case test of 1 CPU allocating files subsequently being freed by N CPUs degenerates to contending on a single lock, which is no worse than before. When more than one CPU are allocating files, even if they are always freed by different CPUs, there will be more parallelism than the single-lock case. Testing results: On a 2 socket, 8 core opteron, I measure the number of times the lock is taken to remove the file, the number of times it is removed by the same CPU that added it, and the number of times it is removed by the same node that added it. Booting: locks= 25049 cpu-hits= 23174 (92.5%) node-hits= 23945 (95.6%) kbuild -j16 locks=2281913 cpu-hits=2208126 (96.8%) node-hits=2252674 (98.7%) dbench 64 locks=4306582 cpu-hits=4287247 (99.6%) node-hits=4299527 (99.8%) So a file is removed from the same CPU it was added by over 90% of the time. It remains within the same node 95% of the time. Tim Chen ran some numbers for a 64 thread Nehalem system performing a compile. throughput 2.6.34-rc2 24.5 +patch 24.9 us sys idle IO wait (in %) 2.6.34-rc2 51.25 28.25 17.25 3.25 +patch 53.75 18.5 19 8.75 So significantly less CPU time spent in kernel code, higher idle time and slightly higher throughput. Single threaded performance difference was within the noise of microbenchmarks. That is not to say penalty does not exist, the code is larger and more memory accesses required so it will be slightly slower. Cc: linux-kernel@vger.kernel.org Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Signed-off-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-17 22:37:38 +04:00
#ifdef CONFIG_SMP
struct list_head __percpu *s_files;
#else
struct list_head s_files;
fs: scale files_lock fs: scale files_lock Improve scalability of files_lock by adding per-cpu, per-sb files lists, protected with an lglock. The lglock provides fast access to the per-cpu lists to add and remove files. It also provides a snapshot of all the per-cpu lists (although this is very slow). One difficulty with this approach is that a file can be removed from the list by another CPU. We must track which per-cpu list the file is on with a new variale in the file struct (packed into a hole on 64-bit archs). Scalability could suffer if files are frequently removed from different cpu's list. However loads with frequent removal of files imply short interval between adding and removing the files, and the scheduler attempts to avoid moving processes too far away. Also, even in the case of cross-CPU removal, the hardware has much more opportunity to parallelise cacheline transfers with N cachelines than with 1. A worst-case test of 1 CPU allocating files subsequently being freed by N CPUs degenerates to contending on a single lock, which is no worse than before. When more than one CPU are allocating files, even if they are always freed by different CPUs, there will be more parallelism than the single-lock case. Testing results: On a 2 socket, 8 core opteron, I measure the number of times the lock is taken to remove the file, the number of times it is removed by the same CPU that added it, and the number of times it is removed by the same node that added it. Booting: locks= 25049 cpu-hits= 23174 (92.5%) node-hits= 23945 (95.6%) kbuild -j16 locks=2281913 cpu-hits=2208126 (96.8%) node-hits=2252674 (98.7%) dbench 64 locks=4306582 cpu-hits=4287247 (99.6%) node-hits=4299527 (99.8%) So a file is removed from the same CPU it was added by over 90% of the time. It remains within the same node 95% of the time. Tim Chen ran some numbers for a 64 thread Nehalem system performing a compile. throughput 2.6.34-rc2 24.5 +patch 24.9 us sys idle IO wait (in %) 2.6.34-rc2 51.25 28.25 17.25 3.25 +patch 53.75 18.5 19 8.75 So significantly less CPU time spent in kernel code, higher idle time and slightly higher throughput. Single threaded performance difference was within the noise of microbenchmarks. That is not to say penalty does not exist, the code is larger and more memory accesses required so it will be slightly slower. Cc: linux-kernel@vger.kernel.org Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Signed-off-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-17 22:37:38 +04:00
#endif
/* s_dentry_lru, s_nr_dentry_unused protected by dcache.c lru locks */
fix soft lock up at NFS mount via per-SB LRU-list of unused dentries [Summary] Split LRU-list of unused dentries to one per superblock to avoid soft lock up during NFS mounts and remounting of any filesystem. Previously I posted here: http://lkml.org/lkml/2008/3/5/590 [Descriptions] - background dentry_unused is a list of dentries which are not referenced. dentry_unused grows up when references on directories or files are released. This list can be very long if there is huge free memory. - the problem When shrink_dcache_sb() is called, it scans all dentry_unused linearly under spin_lock(), and if dentry->d_sb is differnt from given superblock, scan next dentry. This scan costs very much if there are many entries, and very ineffective if there are many superblocks. IOW, When we need to shrink unused dentries on one dentry, but scans unused dentries on all superblocks in the system. For example, we scan 500 dentries to unmount a filesystem, but scans 1,000,000 or more unused dentries on other superblocks. In our case , At mounting NFS*, shrink_dcache_sb() is called to shrink unused dentries on NFS, but scans 100,000,000 unused dentries on superblocks in the system such as local ext3 filesystems. I hear NFS mounting took 1 min on some system in use. * : NFS uses virtual filesystem in rpc layer, so NFS is affected by this problem. 100,000,000 is possible number on large systems. Per-superblock LRU of unused dentried can reduce the cost in reasonable manner. - How to fix I found this problem is solved by David Chinner's "Per-superblock unused dentry LRU lists V3"(1), so I rebase it and add some fix to reclaim with fairness, which is in Andrew Morton's comments(2). 1) http://lkml.org/lkml/2006/5/25/318 2) http://lkml.org/lkml/2006/5/25/320 Split LRU-list of unused dentries to each superblocks. Then, NFS mounting will check dentries under a superblock instead of all. But this spliting will break LRU of dentry-unused. So, I've attempted to make reclaim unused dentrins with fairness by calculate number of dentries to scan on this sb based on following way number of dentries to scan on this sb = count * (number of dentries on this sb / number of dentries in the machine) - ToDo - I have to measuring performance number and do stress tests. - When unmount occurs during prune_dcache(), scanning on same superblock, It is unable to reach next superblock because it is gone away. We restart scannig superblock from first one, it causes unfairness of reclaim unused dentries on first superblock. But I think this happens very rarely. - Test Results Result on 6GB boxes with excessive unused dentries. Without patch: $ cat /proc/sys/fs/dentry-state 10181835 10180203 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m1.830s user 0m0.001s sys 0m1.653s With this patch: $ cat /proc/sys/fs/dentry-state 10236610 10234751 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m0.106s user 0m0.002s sys 0m0.032s [akpm@linux-foundation.org: fix comments] Signed-off-by: Kentaro Makita <k-makita@np.css.fujitsu.com> Cc: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: David Chinner <dgc@sgi.com> Cc: "J. Bruce Fields" <bfields@fieldses.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 08:27:13 +04:00
struct list_head s_dentry_lru; /* unused dentry lru */
int s_nr_dentry_unused; /* # of dentry on lru */
struct block_device *s_bdev;
struct backing_dev_info *s_bdi;
struct mtd_info *s_mtd;
struct list_head s_instances;
struct quota_info s_dquot; /* Diskquota specific options */
int s_frozen;
wait_queue_head_t s_wait_unfrozen;
char s_id[32]; /* Informational name */
void *s_fs_info; /* Filesystem private info */
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 */
};
extern struct timespec current_fs_time(struct super_block *sb);
/*
* Snapshotting support.
*/
enum {
SB_UNFROZEN = 0,
SB_FREEZE_WRITE = 1,
SB_FREEZE_TRANS = 2,
};
#define vfs_check_frozen(sb, level) \
wait_event((sb)->s_wait_unfrozen, ((sb)->s_frozen < (level)))
#define get_fs_excl() atomic_inc(&current->fs_excl)
#define put_fs_excl() atomic_dec(&current->fs_excl)
#define has_fs_excl() atomic_read(&current->fs_excl)
#define is_owner_or_cap(inode) \
((current_fsuid() == (inode)->i_uid) || capable(CAP_FOWNER))
/* not quite ready to be deprecated, but... */
extern void lock_super(struct super_block *);
extern void unlock_super(struct super_block *);
/*
* VFS helper functions..
*/
extern int vfs_create(struct inode *, struct dentry *, int, struct nameidata *);
extern int vfs_mkdir(struct inode *, struct dentry *, int);
extern int vfs_mknod(struct inode *, struct dentry *, int, dev_t);
extern int vfs_symlink(struct inode *, struct dentry *, const char *);
extern int vfs_link(struct dentry *, struct inode *, struct dentry *);
extern int vfs_rmdir(struct inode *, struct dentry *);
extern int vfs_unlink(struct inode *, struct dentry *);
extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *);
/*
* VFS dentry helper functions.
*/
extern void dentry_unhash(struct dentry *dentry);
/*
* VFS file helper functions.
*/
extern int file_permission(struct file *, int);
extern void inode_init_owner(struct inode *inode, const struct inode *dir,
mode_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.
*/
[PATCH] VFS: Make filldir_t and struct kstat deal in 64-bit inode numbers These patches make the kernel pass 64-bit inode numbers internally when communicating to userspace, even on a 32-bit system. They are required because some filesystems have intrinsic 64-bit inode numbers: NFS3+ and XFS for example. The 64-bit inode numbers are then propagated to userspace automatically where the arch supports it. Problems have been seen with userspace (eg: ld.so) using the 64-bit inode number returned by stat64() or getdents64() to differentiate files, and failing because the 64-bit inode number space was compressed to 32-bits, and so overlaps occur. This patch: Make filldir_t take a 64-bit inode number and struct kstat carry a 64-bit inode number so that 64-bit inode numbers can be passed back to userspace. The stat functions then returns the full 64-bit inode number where available and where possible. If it is not possible to represent the inode number supplied by the filesystem in the field provided by userspace, then error EOVERFLOW will be issued. Similarly, the getdents/readdir functions now pass the full 64-bit inode number to userspace where possible, returning EOVERFLOW instead when a directory entry is encountered that can't be properly represented. Note that this means that some inodes will not be stat'able on a 32-bit system with old libraries where they were before - but it does mean that there will be no ambiguity over what a 32-bit inode number refers to. Note similarly that directory scans may be cut short with an error on a 32-bit system with old libraries where the scan would work before for the same reasons. It is judged unlikely that this situation will occur because modern glibc uses 64-bit capable versions of stat and getdents class functions exclusively, and that older systems are unlikely to encounter unrepresentable inode numbers anyway. [akpm: alpha build fix] Signed-off-by: David Howells <dhowells@redhat.com> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-03 12:13:46 +04:00
typedef int (*filldir_t)(void *, const char *, int, loff_t, u64, unsigned);
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
/*
* NOTE:
* all file operations except setlease can be called without
* the big kernel lock held in all filesystems.
*/
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);
int (*readdir) (struct file *, void *, filldir_t);
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 *);
int (*open) (struct inode *, struct file *);
int (*flush) (struct file *, fl_owner_t id);
int (*release) (struct inode *, struct file *);
int (*fsync) (struct file *, 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 **);
long (*fallocate)(struct file *file, int mode, loff_t offset,
loff_t len);
};
#define IPERM_FLAG_RCU 0x0001
struct inode_operations {
struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameidata *);
void * (*follow_link) (struct dentry *, struct nameidata *);
int (*permission) (struct inode *, int, unsigned int);
int (*check_acl)(struct inode *, int, unsigned int);
int (*readlink) (struct dentry *, char __user *,int);
void (*put_link) (struct dentry *, struct nameidata *, void *);
int (*create) (struct inode *,struct dentry *,int, struct nameidata *);
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 *,int);
int (*rmdir) (struct inode *,struct dentry *);
int (*mknod) (struct inode *,struct dentry *,int,dev_t);
int (*rename) (struct inode *, struct dentry *,
struct inode *, struct dentry *);
void (*truncate) (struct inode *);
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 *);
[PATCH] madvise(MADV_REMOVE): remove pages from tmpfs shm backing store Here is the patch to implement madvise(MADV_REMOVE) - which frees up a given range of pages & its associated backing store. Current implementation supports only shmfs/tmpfs and other filesystems return -ENOSYS. "Some app allocates large tmpfs files, then when some task quits and some client disconnect, some memory can be released. However the only way to release tmpfs-swap is to MADV_REMOVE". - Andrea Arcangeli Databases want to use this feature to drop a section of their bufferpool (shared memory segments) - without writing back to disk/swap space. This feature is also useful for supporting hot-plug memory on UML. Concerns raised by Andrew Morton: - "We have no plan for holepunching! If we _do_ have such a plan (or might in the future) then what would the API look like? I think sys_holepunch(fd, start, len), so we should start out with that." - Using madvise is very weird, because people will ask "why do I need to mmap my file before I can stick a hole in it?" - None of the other madvise operations call into the filesystem in this manner. A broad question is: is this capability an MM operation or a filesytem operation? truncate, for example, is a filesystem operation which sometimes has MM side-effects. madvise is an mm operation and with this patch, it gains FS side-effects, only they're really, really significant ones." Comments: - Andrea suggested the fs operation too but then it's more efficient to have it as a mm operation with fs side effects, because they don't immediatly know fd and physical offset of the range. It's possible to fixup in userland and to use the fs operation but it's more expensive, the vmas are already in the kernel and we can use them. Short term plan & Future Direction: - We seem to need this interface only for shmfs/tmpfs files in the short term. We have to add hooks into the filesystem for correctness and completeness. This is what this patch does. - In the future, plan is to support both fs and mmap apis also. This also involves (other) filesystem specific functions to be implemented. - Current patch doesn't support VM_NONLINEAR - which can be addressed in the future. Signed-off-by: Badari Pulavarty <pbadari@us.ibm.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Andrea Arcangeli <andrea@suse.de> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Cc: Ulrich Drepper <drepper@redhat.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-06 11:10:38 +03:00
void (*truncate_range)(struct inode *, loff_t, loff_t);
int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
u64 len);
} ____cacheline_aligned;
struct seq_file;
ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
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_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 (*write_inode) (struct inode *, struct writeback_control *wbc);
int (*drop_inode) (struct inode *);
void (*evict_inode) (struct inode *);
void (*put_super) (struct super_block *);
void (*write_super) (struct super_block *);
int (*sync_fs)(struct super_block *sb, int wait);
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 03:40:58 +03:00
int (*freeze_fs) (struct super_block *);
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 vfsmount *);
int (*show_stats)(struct seq_file *, struct vfsmount *);
#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);
#endif
int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
};
/*
* Inode state bits. Protected by inode_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 end_writeback(). 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 Synchonized write of dirty inode data. The bits is
* set during data writeback, and cleared with a wakeup
* on the bit address once it is done.
*
* 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_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES)
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);
}
/**
* inc_nlink - directly increment an inode's link count
* @inode: inode
*
* This is a low-level filesystem helper to replace any
* direct filesystem manipulation of i_nlink. Currently,
* it is only here for parity with dec_nlink().
*/
static inline void inc_nlink(struct inode *inode)
{
inode->i_nlink++;
}
static inline void inode_inc_link_count(struct inode *inode)
{
inc_nlink(inode);
mark_inode_dirty(inode);
}
/**
* drop_nlink - directly drop an inode's link count
* @inode: inode
*
* This is a low-level filesystem helper to replace any
* direct filesystem manipulation of i_nlink. In cases
* where we are attempting to track writes to the
* filesystem, a decrement to zero means an imminent
* write when the file is truncated and actually unlinked
* on the filesystem.
*/
static inline void drop_nlink(struct inode *inode)
{
inode->i_nlink--;
}
/**
* clear_nlink - directly zero an inode's link count
* @inode: inode
*
* This is a low-level filesystem helper to replace any
* direct filesystem manipulation of i_nlink. See
* drop_nlink() for why we care about i_nlink hitting zero.
*/
static inline void clear_nlink(struct inode *inode)
{
inode->i_nlink = 0;
}
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);
}
extern void touch_atime(struct vfsmount *mnt, struct dentry *dentry);
static inline void file_accessed(struct file *file)
{
if (!(file->f_flags & O_NOATIME))
touch_atime(file->f_path.mnt, file->f_path.dentry);
}
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;
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 13:02:57 +04:00
int (*get_sb) (struct file_system_type *, int,
const char *, void *, struct vfsmount *);
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 list_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 01:23:57 +04:00
struct lock_class_key s_vfs_rename_key;
struct lock_class_key i_lock_key;
struct lock_class_key i_mutex_key;
struct lock_class_key i_mutex_dir_key;
struct lock_class_key i_alloc_sem_key;
};
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));
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 13:02:57 +04:00
extern int get_sb_bdev(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data,
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 13:02:57 +04:00
int (*fill_super)(struct super_block *, void *, int),
struct vfsmount *mnt);
extern struct dentry *mount_single(struct file_system_type *fs_type,
int flags, void *data,
int (*fill_super)(struct super_block *, void *, int));
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 13:02:57 +04:00
extern int get_sb_single(struct file_system_type *fs_type,
int flags, void *data,
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 13:02:57 +04:00
int (*fill_super)(struct super_block *, void *, int),
struct vfsmount *mnt);
extern struct dentry *mount_nodev(struct file_system_type *fs_type,
int flags, void *data,
int (*fill_super)(struct super_block *, void *, int));
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 13:02:57 +04:00
extern int get_sb_nodev(struct file_system_type *fs_type,
int flags, void *data,
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 13:02:57 +04:00
int (*fill_super)(struct super_block *, void *, int),
struct vfsmount *mnt);
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);
struct super_block *sget(struct file_system_type *type,
int (*test)(struct super_block *,void *),
int (*set)(struct super_block *,void *),
void *data);
extern struct dentry *mount_pseudo(struct file_system_type *, char *,
const struct super_operations *ops,
const struct dentry_operations *dops,
unsigned long);
extern void simple_set_mnt(struct vfsmount *mnt, struct super_block *sb);
static inline void sb_mark_dirty(struct super_block *sb)
{
sb->s_dirt = 1;
}
static inline void sb_mark_clean(struct super_block *sb)
{
sb->s_dirt = 0;
}
static inline int sb_is_dirty(struct super_block *sb)
{
return sb->s_dirt;
}
/* 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)
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 int may_umount_tree(struct vfsmount *);
extern int may_umount(struct vfsmount *);
extern long do_mount(char *, char *, 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 statfs_by_dentry(struct dentry *, struct kstatfs *);
extern int freeze_super(struct super_block *super);
extern int thaw_super(struct super_block *super);
extern int current_umask(void);
/* /sys/fs */
extern struct kobject *fs_kobj;
#define MAX_RW_COUNT (INT_MAX & PAGE_CACHE_MASK)
extern int rw_verify_area(int, struct file *, loff_t *, size_t);
#define FLOCK_VERIFY_READ 1
#define FLOCK_VERIFY_WRITE 2
#ifdef CONFIG_FILE_LOCKING
extern int locks_mandatory_locked(struct inode *);
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 inode *inode)
{
if (mandatory_lock(inode))
return locks_mandatory_locked(inode);
return 0;
}
static inline int locks_verify_truncate(struct inode *inode,
struct file *filp,
loff_t size)
{
if (inode->i_flock && 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)
{
if (inode->i_flock)
return __break_lease(inode, mode);
return 0;
}
#else /* !CONFIG_FILE_LOCKING */
static inline int locks_mandatory_locked(struct inode *inode)
{
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 inode *inode)
{
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;
}
#endif /* CONFIG_FILE_LOCKING */
/* fs/open.c */
extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs,
struct file *filp);
extern int do_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,
[PATCH] vfs: *at functions: core Here is a series of patches which introduce in total 13 new system calls which take a file descriptor/filename pair instead of a single file name. These functions, openat etc, have been discussed on numerous occasions. They are needed to implement race-free filesystem traversal, they are necessary to implement a virtual per-thread current working directory (think multi-threaded backup software), etc. We have in glibc today implementations of the interfaces which use the /proc/self/fd magic. But this code is rather expensive. Here are some results (similar to what Jim Meyering posted before). The test creates a deep directory hierarchy on a tmpfs filesystem. Then rm -fr is used to remove all directories. Without syscall support I get this: real 0m31.921s user 0m0.688s sys 0m31.234s With syscall support the results are much better: real 0m20.699s user 0m0.536s sys 0m20.149s The interfaces are for obvious reasons currently not much used. But they'll be used. coreutils (and Jeff's posixutils) are already using them. Furthermore, code like ftw/fts in libc (maybe even glob) will also start using them. I expect a patch to make follow soon. Every program which is walking the filesystem tree will benefit. Signed-off-by: Ulrich Drepper <drepper@redhat.com> Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Al Viro <viro@ftp.linux.org.uk> Acked-by: Ingo Molnar <mingo@elte.hu> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 04:43:53 +03:00
int mode);
extern struct file *filp_open(const char *, int, int);
extern struct file * dentry_open(struct dentry *, struct vfsmount *, int,
const struct cred *);
extern int filp_close(struct file *, fl_owner_t id);
extern char * getname(const char __user *);
/* 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_gfp(gfp) kmem_cache_alloc(names_cachep, (gfp))
#define __getname() __getname_gfp(GFP_KERNEL)
#define __putname(name) kmem_cache_free(names_cachep, (void *)(name))
#ifndef CONFIG_AUDITSYSCALL
#define putname(name) __putname(name)
#else
extern void putname(const char *name);
#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>
2006-09-30 22:45:40 +04:00
#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 int sync_blockdev(struct block_device *bdev);
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 *);
[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>
2006-09-30 22:45:40 +04:00
#else
static inline void bd_forget(struct inode *inode) {}
static inline int sync_blockdev(struct block_device *bdev) { return 0; }
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;
}
[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>
2006-09-30 22:45:40 +04:00
#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>
2006-09-30 22:45:40 +04:00
extern const struct file_operations def_blk_fops;
extern const struct file_operations def_chr_fops;
extern const struct file_operations bad_sock_fops;
extern const struct file_operations def_fifo_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>
2006-09-30 22:45:40 +04:00
#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 13:55:17 +03:00
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);
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 13:55:17 +03:00
extern int 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>
2006-09-30 22:45:40 +04:00
#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>
2006-09-30 22:45:40 +04:00
#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>
2006-09-30 22:45:40 +04:00
#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 *);
extern const struct file_operations read_pipefifo_fops;
extern const struct file_operations write_pipefifo_fops;
extern const struct file_operations rdwr_pipefifo_fops;
extern int fs_may_remount_ro(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>
2006-09-30 22:45:40 +04:00
#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 *);
extern int __invalidate_device(struct block_device *);
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>
2006-09-30 22:45:40 +04:00
#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 14:18:04 +03:00
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 14:18:04 +03:00
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);
extern int generic_write_sync(struct file *file, loff_t pos, loff_t count);
extern void sync_supers(void);
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>
2006-09-30 22:45:40 +04:00
#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>
2006-09-30 22:45:40 +04:00
#endif
extern int notify_change(struct dentry *, struct iattr *);
extern int inode_permission(struct inode *, int);
extern int generic_permission(struct inode *, int, unsigned int,
int (*check_acl)(struct inode *, int, unsigned int));
static inline bool execute_ok(struct inode *inode)
{
return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode);
}
extern int get_write_access(struct inode *);
extern int deny_write_access(struct file *);
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->f_path.dentry->d_inode->i_writecount);
}
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 08:29:30 +04:00
extern int do_pipe_flags(int *, int);
flag parameters: NONBLOCK in pipe This patch adds O_NONBLOCK support to pipe2. It is minimally more involved than the patches for eventfd et.al but still trivial. The interfaces of the create_write_pipe and create_read_pipe helper functions were changed and the one other caller as well. 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 fds[2]; if (syscall (__NR_pipe2, fds, 0) == -1) { puts ("pipe2(0) failed"); return 1; } for (int i = 0; i < 2; ++i) { int fl = fcntl (fds[i], F_GETFL); if (fl == -1) { puts ("fcntl failed"); return 1; } if (fl & O_NONBLOCK) { printf ("pipe2(0) set non-blocking mode for fds[%d]\n", i); return 1; } close (fds[i]); } if (syscall (__NR_pipe2, fds, O_NONBLOCK) == -1) { puts ("pipe2(O_NONBLOCK) failed"); return 1; } for (int i = 0; i < 2; ++i) { int fl = fcntl (fds[i], F_GETFL); if (fl == -1) { puts ("fcntl failed"); return 1; } if ((fl & O_NONBLOCK) == 0) { printf ("pipe2(O_NONBLOCK) does not set non-blocking mode for fds[%d]\n", i); return 1; } close (fds[i]); } 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> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 08:29:40 +04:00
extern struct file *create_read_pipe(struct file *f, int flags);
extern struct file *create_write_pipe(int flags);
extern void free_write_pipe(struct file *);
extern struct file *do_filp_open(int dfd, const char *pathname,
int open_flag, int mode, int acc_mode);
extern int may_open(struct path *, int, int);
extern int kernel_read(struct file *, loff_t, char *, unsigned long);
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 *);
extern ino_t find_inode_number(struct dentry *, struct qstr *);
#include <linux/err.h>
/* needed for stackable file system support */
extern loff_t default_llseek(struct file *file, loff_t offset, int origin);
extern loff_t vfs_llseek(struct file *file, loff_t offset, int origin);
extern int inode_init_always(struct super_block *, struct inode *);
extern void inode_init_once(struct inode *);
extern void ihold(struct inode * inode);
extern void iput(struct inode *);
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);
extern int generic_drop_inode(struct inode *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 12:10:44 +04:00
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 int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *);
extern int insert_inode_locked(struct inode *);
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 end_writeback(struct inode *);
extern void __destroy_inode(struct inode *);
extern struct inode *new_inode(struct super_block *);
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);
extern void remove_inode_hash(struct inode *);
static inline void insert_inode_hash(struct inode *inode)
{
__insert_inode_hash(inode, inode->i_ino);
}
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>
2006-09-30 22:45:40 +04:00
#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>
2006-09-30 22:45:40 +04:00
#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 *);
extern int file_read_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size);
int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk);
extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t);
extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long,
loff_t *);
extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t);
extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *,
unsigned long *, loff_t, loff_t *, size_t, size_t);
extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *,
unsigned long, loff_t, loff_t *, size_t, ssize_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 int generic_segment_checks(const struct iovec *iov,
unsigned long *nr_segs, size_t *count, int access_flags);
/* fs/block_dev.c */
extern ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos);
extern int blkdev_fsync(struct file *filp, int datasync);
/* 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 generic_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,
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 origin);
extern loff_t no_llseek(struct file *file, loff_t offset, int origin);
extern loff_t generic_file_llseek(struct file *file, loff_t offset, int origin);
extern loff_t generic_file_llseek_unlocked(struct file *file, loff_t offset,
int origin);
extern int generic_file_open(struct inode * inode, struct file * filp);
extern int nonseekable_open(struct inode * inode, struct file * filp);
#ifdef CONFIG_FS_XIP
extern ssize_t xip_file_read(struct file *filp, char __user *buf, size_t len,
loff_t *ppos);
extern int xip_file_mmap(struct file * file, struct vm_area_struct * vma);
extern ssize_t xip_file_write(struct file *filp, const char __user *buf,
size_t len, loff_t *ppos);
extern int xip_truncate_page(struct address_space *mapping, loff_t from);
#else
static inline int xip_truncate_page(struct address_space *mapping, loff_t from)
{
return 0;
}
#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>
2006-09-30 22:45:40 +04:00
#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,
};
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, const struct iovec *iov, loff_t offset,
unsigned long nr_segs, 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 19:05:33 +04:00
static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb,
struct inode *inode, struct block_device *bdev, const struct iovec *iov,
loff_t offset, unsigned long nr_segs, get_block_t get_block,
dio_iodone_t end_io)
{
return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
nr_segs, get_block, end_io, 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>
2006-09-30 22:45:40 +04:00
#endif
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 vfs_readlink(struct dentry *, char __user *, int, const char *);
extern int vfs_follow_link(struct nameidata *, 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>
2009-01-04 23:00:53 +03:00
int nofs);
extern int page_symlink(struct inode *inode, const char *symname, int len);
extern const struct inode_operations page_symlink_inode_operations;
extern int generic_readlink(struct dentry *, char __user *, int);
extern void generic_fillattr(struct inode *, struct kstat *);
extern int vfs_getattr(struct vfsmount *, struct dentry *, 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);
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 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_active_super(struct block_device *bdev);
extern struct super_block *user_get_super(dev_t);
extern void drop_super(struct super_block *sb);
extern void iterate_supers(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 *, void *, filldir_t);
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 19:05:33 +04:00
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_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 *, 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 struct dentry *simple_lookup(struct inode *, struct dentry *, struct nameidata *);
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 09:46:21 +04:00
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 *, int);
extern int generic_check_addressable(unsigned, u64);
#ifdef CONFIG_MIGRATION
extern int buffer_migrate_page(struct address_space *,
struct page *, struct page *);
#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 void file_update_time(struct file *file);
extern int generic_show_options(struct seq_file *m, struct vfsmount *mnt);
extern void save_mount_options(struct super_block *sb, char *options);
extern void replace_mount_options(struct super_block *sb, char *options);
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 void __attribute__((format(printf, 1, 2)))
__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 ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE])
#define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \
(flag & FMODE_NONOTIFY)))
#endif /* __KERNEL__ */
#endif /* _LINUX_FS_H */