2005-04-17 02:20:36 +04:00
|
|
|
#ifndef _LINUX_FS_H
|
|
|
|
#define _LINUX_FS_H
|
|
|
|
|
|
|
|
|
|
|
|
#include <linux/linkage.h>
|
|
|
|
#include <linux/wait.h>
|
|
|
|
#include <linux/kdev_t.h>
|
|
|
|
#include <linux/dcache.h>
|
2008-07-26 11:46:43 +04:00
|
|
|
#include <linux/path.h>
|
2005-04-17 02:20:36 +04:00
|
|
|
#include <linux/stat.h>
|
|
|
|
#include <linux/cache.h>
|
|
|
|
#include <linux/list.h>
|
2013-08-28 04:17:58 +04:00
|
|
|
#include <linux/list_lru.h>
|
2013-07-09 01:24:16 +04:00
|
|
|
#include <linux/llist.h>
|
2005-04-17 02:20:36 +04:00
|
|
|
#include <linux/radix-tree.h>
|
2012-10-09 03:31:25 +04:00
|
|
|
#include <linux/rbtree.h>
|
2005-04-17 02:20:36 +04:00
|
|
|
#include <linux/init.h>
|
2006-10-18 21:55:46 +04:00
|
|
|
#include <linux/pid.h>
|
2011-11-24 05:12:59 +04:00
|
|
|
#include <linux/bug.h>
|
2006-01-10 02:59:24 +03:00
|
|
|
#include <linux/mutex.h>
|
2007-07-17 13:30:08 +04:00
|
|
|
#include <linux/capability.h>
|
2008-04-19 06:21:05 +04:00
|
|
|
#include <linux/semaphore.h>
|
2008-10-09 03:44:18 +04:00
|
|
|
#include <linux/fiemap.h>
|
2011-01-07 09:50:05 +03:00
|
|
|
#include <linux/rculist_bl.h>
|
2011-06-20 18:52:57 +04:00
|
|
|
#include <linux/atomic.h>
|
2011-12-09 02:33:54 +04:00
|
|
|
#include <linux/shrinker.h>
|
2012-01-24 04:41:32 +04:00
|
|
|
#include <linux/migrate_mode.h>
|
2012-02-08 19:07:50 +04:00
|
|
|
#include <linux/uidgid.h>
|
2012-06-12 18:20:34 +04:00
|
|
|
#include <linux/lockdep.h>
|
2012-09-27 11:35:03 +04:00
|
|
|
#include <linux/percpu-rwsem.h>
|
2012-10-13 13:45:06 +04:00
|
|
|
#include <linux/blk_types.h>
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
#include <asm/byteorder.h>
|
2012-10-13 13:46:48 +04:00
|
|
|
#include <uapi/linux/fs.h>
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2007-07-17 15:04:28 +04:00
|
|
|
struct export_operations;
|
2006-01-08 12:02:50 +03:00
|
|
|
struct hd_geometry;
|
2005-04-17 02:20:36 +04:00
|
|
|
struct iovec;
|
|
|
|
struct nameidata;
|
2005-06-24 09:00:59 +04:00
|
|
|
struct kiocb;
|
2011-01-10 09:18:25 +03:00
|
|
|
struct kobject;
|
2005-04-17 02:20:36 +04:00
|
|
|
struct pipe_inode_info;
|
|
|
|
struct poll_table_struct;
|
|
|
|
struct kstatfs;
|
|
|
|
struct vm_area_struct;
|
|
|
|
struct vfsmount;
|
2008-11-14 02:39:22 +03:00
|
|
|
struct cred;
|
2012-08-01 03:44:57 +04:00
|
|
|
struct swap_info_struct;
|
2012-12-18 04:04:55 +04:00
|
|
|
struct seq_file;
|
2013-09-04 17:04:39 +04:00
|
|
|
struct workqueue_struct;
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2007-10-17 10:26:30 +04:00
|
|
|
extern void __init inode_init(void);
|
2005-04-17 02:20:36 +04:00
|
|
|
extern void __init inode_init_early(void);
|
|
|
|
extern void __init files_init(unsigned long);
|
|
|
|
|
2008-12-02 01:34:50 +03:00
|
|
|
extern struct files_stat_struct files_stat;
|
2010-10-27 01:22:44 +04:00
|
|
|
extern unsigned long get_max_files(void);
|
2008-12-02 01:34:50 +03:00
|
|
|
extern int sysctl_nr_open;
|
|
|
|
extern struct inodes_stat_t inodes_stat;
|
|
|
|
extern int leases_enable, lease_break_time;
|
fs: add link restrictions
This adds symlink and hardlink restrictions to the Linux VFS.
Symlinks:
A long-standing class of security issues is the symlink-based
time-of-check-time-of-use race, most commonly seen in world-writable
directories like /tmp. The common method of exploitation of this flaw
is to cross privilege boundaries when following a given symlink (i.e. a
root process follows a symlink belonging to another user). For a likely
incomplete list of hundreds of examples across the years, please see:
http://cve.mitre.org/cgi-bin/cvekey.cgi?keyword=/tmp
The solution is to permit symlinks to only be followed when outside
a sticky world-writable directory, or when the uid of the symlink and
follower match, or when the directory owner matches the symlink's owner.
Some pointers to the history of earlier discussion that I could find:
1996 Aug, Zygo Blaxell
http://marc.info/?l=bugtraq&m=87602167419830&w=2
1996 Oct, Andrew Tridgell
http://lkml.indiana.edu/hypermail/linux/kernel/9610.2/0086.html
1997 Dec, Albert D Cahalan
http://lkml.org/lkml/1997/12/16/4
2005 Feb, Lorenzo Hernández García-Hierro
http://lkml.indiana.edu/hypermail/linux/kernel/0502.0/1896.html
2010 May, Kees Cook
https://lkml.org/lkml/2010/5/30/144
Past objections and rebuttals could be summarized as:
- Violates POSIX.
- POSIX didn't consider this situation and it's not useful to follow
a broken specification at the cost of security.
- Might break unknown applications that use this feature.
- Applications that break because of the change are easy to spot and
fix. Applications that are vulnerable to symlink ToCToU by not having
the change aren't. Additionally, no applications have yet been found
that rely on this behavior.
- Applications should just use mkstemp() or O_CREATE|O_EXCL.
- True, but applications are not perfect, and new software is written
all the time that makes these mistakes; blocking this flaw at the
kernel is a single solution to the entire class of vulnerability.
- This should live in the core VFS.
- This should live in an LSM. (https://lkml.org/lkml/2010/5/31/135)
- This should live in an LSM.
- This should live in the core VFS. (https://lkml.org/lkml/2010/8/2/188)
Hardlinks:
On systems that have user-writable directories on the same partition
as system files, a long-standing class of security issues is the
hardlink-based time-of-check-time-of-use race, most commonly seen in
world-writable directories like /tmp. The common method of exploitation
of this flaw is to cross privilege boundaries when following a given
hardlink (i.e. a root process follows a hardlink created by another
user). Additionally, an issue exists where users can "pin" a potentially
vulnerable setuid/setgid file so that an administrator will not actually
upgrade a system fully.
The solution is to permit hardlinks to only be created when the user is
already the existing file's owner, or if they already have read/write
access to the existing file.
Many Linux users are surprised when they learn they can link to files
they have no access to, so this change appears to follow the doctrine
of "least surprise". Additionally, this change does not violate POSIX,
which states "the implementation may require that the calling process
has permission to access the existing file"[1].
This change is known to break some implementations of the "at" daemon,
though the version used by Fedora and Ubuntu has been fixed[2] for
a while. Otherwise, the change has been undisruptive while in use in
Ubuntu for the last 1.5 years.
[1] http://pubs.opengroup.org/onlinepubs/9699919799/functions/linkat.html
[2] http://anonscm.debian.org/gitweb/?p=collab-maint/at.git;a=commitdiff;h=f4114656c3a6c6f6070e315ffdf940a49eda3279
This patch is based on the patches in Openwall and grsecurity, along with
suggestions from Al Viro. I have added a sysctl to enable the protected
behavior, and documentation.
Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-07-26 04:29:07 +04:00
|
|
|
extern int sysctl_protected_symlinks;
|
|
|
|
extern int sysctl_protected_hardlinks;
|
2008-12-02 01:34:50 +03:00
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
struct buffer_head;
|
|
|
|
typedef int (get_block_t)(struct inode *inode, sector_t iblock,
|
|
|
|
struct buffer_head *bh_result, int create);
|
2005-06-24 09:00:59 +04:00
|
|
|
typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
|
2013-09-04 17:04:39 +04:00
|
|
|
ssize_t bytes, void *private);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2012-10-15 19:40:35 +04:00
|
|
|
#define MAY_EXEC 0x00000001
|
|
|
|
#define MAY_WRITE 0x00000002
|
|
|
|
#define MAY_READ 0x00000004
|
|
|
|
#define MAY_APPEND 0x00000008
|
|
|
|
#define MAY_ACCESS 0x00000010
|
|
|
|
#define MAY_OPEN 0x00000020
|
|
|
|
#define MAY_CHDIR 0x00000040
|
|
|
|
/* called from RCU mode, don't block */
|
|
|
|
#define MAY_NOT_BLOCK 0x00000080
|
|
|
|
|
|
|
|
/*
|
|
|
|
* flags in file.f_mode. Note that FMODE_READ and FMODE_WRITE must correspond
|
|
|
|
* to O_WRONLY and O_RDWR via the strange trick in __dentry_open()
|
|
|
|
*/
|
|
|
|
|
|
|
|
/* file is open for reading */
|
|
|
|
#define FMODE_READ ((__force fmode_t)0x1)
|
|
|
|
/* file is open for writing */
|
|
|
|
#define FMODE_WRITE ((__force fmode_t)0x2)
|
|
|
|
/* file is seekable */
|
|
|
|
#define FMODE_LSEEK ((__force fmode_t)0x4)
|
|
|
|
/* file can be accessed using pread */
|
|
|
|
#define FMODE_PREAD ((__force fmode_t)0x8)
|
|
|
|
/* file can be accessed using pwrite */
|
|
|
|
#define FMODE_PWRITE ((__force fmode_t)0x10)
|
|
|
|
/* File is opened for execution with sys_execve / sys_uselib */
|
|
|
|
#define FMODE_EXEC ((__force fmode_t)0x20)
|
|
|
|
/* File is opened with O_NDELAY (only set for block devices) */
|
|
|
|
#define FMODE_NDELAY ((__force fmode_t)0x40)
|
|
|
|
/* File is opened with O_EXCL (only set for block devices) */
|
|
|
|
#define FMODE_EXCL ((__force fmode_t)0x80)
|
|
|
|
/* File is opened using open(.., 3, ..) and is writeable only for ioctls
|
|
|
|
(specialy hack for floppy.c) */
|
|
|
|
#define FMODE_WRITE_IOCTL ((__force fmode_t)0x100)
|
|
|
|
/* 32bit hashes as llseek() offset (for directories) */
|
|
|
|
#define FMODE_32BITHASH ((__force fmode_t)0x200)
|
|
|
|
/* 64bit hashes as llseek() offset (for directories) */
|
|
|
|
#define FMODE_64BITHASH ((__force fmode_t)0x400)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Don't update ctime and mtime.
|
|
|
|
*
|
|
|
|
* Currently a special hack for the XFS open_by_handle ioctl, but we'll
|
|
|
|
* hopefully graduate it to a proper O_CMTIME flag supported by open(2) soon.
|
|
|
|
*/
|
|
|
|
#define FMODE_NOCMTIME ((__force fmode_t)0x800)
|
|
|
|
|
|
|
|
/* Expect random access pattern */
|
|
|
|
#define FMODE_RANDOM ((__force fmode_t)0x1000)
|
|
|
|
|
|
|
|
/* File is huge (eg. /dev/kmem): treat loff_t as unsigned */
|
|
|
|
#define FMODE_UNSIGNED_OFFSET ((__force fmode_t)0x2000)
|
|
|
|
|
|
|
|
/* File is opened with O_PATH; almost nothing can be done with it */
|
|
|
|
#define FMODE_PATH ((__force fmode_t)0x4000)
|
|
|
|
|
|
|
|
/* File was opened by fanotify and shouldn't generate fanotify events */
|
|
|
|
#define FMODE_NONOTIFY ((__force fmode_t)0x1000000)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector
|
|
|
|
* that indicates that they should check the contents of the iovec are
|
|
|
|
* valid, but not check the memory that the iovec elements
|
|
|
|
* points too.
|
|
|
|
*/
|
|
|
|
#define CHECK_IOVEC_ONLY -1
|
|
|
|
|
2012-10-13 13:45:06 +04:00
|
|
|
/*
|
|
|
|
* The below are the various read and write types that we support. Some of
|
|
|
|
* them include behavioral modifiers that send information down to the
|
|
|
|
* block layer and IO scheduler. Terminology:
|
|
|
|
*
|
|
|
|
* The block layer uses device plugging to defer IO a little bit, in
|
|
|
|
* the hope that we will see more IO very shortly. This increases
|
|
|
|
* coalescing of adjacent IO and thus reduces the number of IOs we
|
|
|
|
* have to send to the device. It also allows for better queuing,
|
|
|
|
* if the IO isn't mergeable. If the caller is going to be waiting
|
|
|
|
* for the IO, then he must ensure that the device is unplugged so
|
|
|
|
* that the IO is dispatched to the driver.
|
|
|
|
*
|
|
|
|
* All IO is handled async in Linux. This is fine for background
|
|
|
|
* writes, but for reads or writes that someone waits for completion
|
|
|
|
* on, we want to notify the block layer and IO scheduler so that they
|
|
|
|
* know about it. That allows them to make better scheduling
|
|
|
|
* decisions. So when the below references 'sync' and 'async', it
|
|
|
|
* is referencing this priority hint.
|
|
|
|
*
|
|
|
|
* With that in mind, the available types are:
|
|
|
|
*
|
|
|
|
* READ A normal read operation. Device will be plugged.
|
|
|
|
* READ_SYNC A synchronous read. Device is not plugged, caller can
|
|
|
|
* immediately wait on this read without caring about
|
|
|
|
* unplugging.
|
|
|
|
* READA Used for read-ahead operations. Lower priority, and the
|
|
|
|
* block layer could (in theory) choose to ignore this
|
|
|
|
* request if it runs into resource problems.
|
|
|
|
* WRITE A normal async write. Device will be plugged.
|
|
|
|
* WRITE_SYNC Synchronous write. Identical to WRITE, but passes down
|
|
|
|
* the hint that someone will be waiting on this IO
|
|
|
|
* shortly. The write equivalent of READ_SYNC.
|
|
|
|
* WRITE_ODIRECT Special case write for O_DIRECT only.
|
|
|
|
* WRITE_FLUSH Like WRITE_SYNC but with preceding cache flush.
|
|
|
|
* WRITE_FUA Like WRITE_SYNC but data is guaranteed to be on
|
|
|
|
* non-volatile media on completion.
|
|
|
|
* WRITE_FLUSH_FUA Combination of WRITE_FLUSH and FUA. The IO is preceded
|
|
|
|
* by a cache flush and data is guaranteed to be on
|
|
|
|
* non-volatile media on completion.
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
#define RW_MASK REQ_WRITE
|
|
|
|
#define RWA_MASK REQ_RAHEAD
|
|
|
|
|
|
|
|
#define READ 0
|
|
|
|
#define WRITE RW_MASK
|
|
|
|
#define READA RWA_MASK
|
|
|
|
#define KERNEL_READ (READ|REQ_KERNEL)
|
|
|
|
#define KERNEL_WRITE (WRITE|REQ_KERNEL)
|
|
|
|
|
|
|
|
#define READ_SYNC (READ | REQ_SYNC)
|
|
|
|
#define WRITE_SYNC (WRITE | REQ_SYNC | REQ_NOIDLE)
|
|
|
|
#define WRITE_ODIRECT (WRITE | REQ_SYNC)
|
|
|
|
#define WRITE_FLUSH (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH)
|
|
|
|
#define WRITE_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FUA)
|
|
|
|
#define WRITE_FLUSH_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH | REQ_FUA)
|
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
/*
|
|
|
|
* Attribute flags. These should be or-ed together to figure out what
|
|
|
|
* has been changed!
|
|
|
|
*/
|
2008-07-01 17:01:26 +04:00
|
|
|
#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)
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
/*
|
|
|
|
* 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;
|
2012-02-08 19:07:50 +04:00
|
|
|
kuid_t ia_uid;
|
|
|
|
kgid_t ia_gid;
|
2005-04-17 02:20:36 +04:00
|
|
|
loff_t ia_size;
|
|
|
|
struct timespec ia_atime;
|
|
|
|
struct timespec ia_mtime;
|
|
|
|
struct timespec ia_ctime;
|
2005-11-07 11:59:49 +03:00
|
|
|
|
|
|
|
/*
|
2011-03-31 05:57:33 +04:00
|
|
|
* Not an attribute, but an auxiliary info for filesystems wanting to
|
2005-11-07 11:59:49 +03:00
|
|
|
* implement an ftruncate() like method. NOTE: filesystem should
|
|
|
|
* check for (ia_valid & ATTR_FILE), and not for (ia_file != NULL).
|
|
|
|
*/
|
|
|
|
struct file *ia_file;
|
2005-04-17 02:20:36 +04:00
|
|
|
};
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Includes for diskquotas.
|
|
|
|
*/
|
|
|
|
#include <linux/quota.h>
|
|
|
|
|
2005-12-16 01:28:17 +03:00
|
|
|
/**
|
|
|
|
* 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
|
2007-10-16 12:25:26 +04:00
|
|
|
* by readpage().
|
2005-12-16 01:28:17 +03:00
|
|
|
*
|
|
|
|
* 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,
|
|
|
|
};
|
|
|
|
|
2007-10-16 12:25:01 +04:00
|
|
|
#define AOP_FLAG_UNINTERRUPTIBLE 0x0001 /* will not do a short write */
|
2007-10-16 12:25:07 +04:00
|
|
|
#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 */
|
2007-10-16 12:25:01 +04:00
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
/*
|
|
|
|
* oh the beauties of C type declarations.
|
|
|
|
*/
|
|
|
|
struct page;
|
|
|
|
struct address_space;
|
|
|
|
struct writeback_control;
|
|
|
|
|
2007-10-16 12:24:59 +04:00
|
|
|
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);
|
2007-10-16 12:25:01 +04:00
|
|
|
int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes);
|
2012-10-26 19:50:04 +04:00
|
|
|
size_t iov_iter_single_seg_count(const struct iov_iter *i);
|
2007-10-16 12:24:59 +04:00
|
|
|
|
|
|
|
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);
|
2007-10-16 12:24:59 +04:00
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
struct address_space_operations {
|
|
|
|
int (*writepage)(struct page *page, struct writeback_control *wbc);
|
|
|
|
int (*readpage)(struct file *, struct page *);
|
|
|
|
|
|
|
|
/* Write back some dirty pages from this mapping. */
|
|
|
|
int (*writepages)(struct address_space *, struct writeback_control *);
|
|
|
|
|
2006-03-24 14:18:11 +03:00
|
|
|
/* Set a page dirty. Return true if this dirtied it */
|
2005-04-17 02:20:36 +04:00
|
|
|
int (*set_page_dirty)(struct page *page);
|
|
|
|
|
|
|
|
int (*readpages)(struct file *filp, struct address_space *mapping,
|
|
|
|
struct list_head *pages, unsigned nr_pages);
|
|
|
|
|
2007-10-16 12:25:01 +04:00
|
|
|
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);
|
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
/* Unfortunately this kludge is needed for FIBMAP. Don't use it */
|
|
|
|
sector_t (*bmap)(struct address_space *, sector_t);
|
2013-05-22 07:17:23 +04:00
|
|
|
void (*invalidatepage) (struct page *, unsigned int, unsigned int);
|
2005-10-21 11:20:48 +04:00
|
|
|
int (*releasepage) (struct page *, gfp_t);
|
2010-12-01 21:35:19 +03:00
|
|
|
void (*freepage)(struct page *);
|
2005-04-17 02:20:36 +04:00
|
|
|
ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
|
|
|
|
loff_t offset, unsigned long nr_segs);
|
2008-04-28 13:13:02 +04:00
|
|
|
int (*get_xip_mem)(struct address_space *, pgoff_t, int,
|
|
|
|
void **, unsigned long *);
|
2012-01-13 05:19:34 +04:00
|
|
|
/*
|
2013-07-09 03:00:21 +04:00
|
|
|
* migrate the contents of a page to the specified target. If
|
|
|
|
* migrate_mode is MIGRATE_ASYNC, it must not block.
|
2012-01-13 05:19:34 +04:00
|
|
|
*/
|
2006-06-23 13:03:33 +04:00
|
|
|
int (*migratepage) (struct address_space *,
|
2012-01-13 05:19:43 +04:00
|
|
|
struct page *, struct page *, enum migrate_mode);
|
2007-01-11 10:15:39 +03:00
|
|
|
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);
|
2013-07-04 02:02:05 +04:00
|
|
|
void (*is_dirty_writeback) (struct page *, bool *, bool *);
|
2009-09-16 13:50:13 +04:00
|
|
|
int (*error_remove_page)(struct address_space *, struct page *);
|
2012-08-01 03:44:55 +04:00
|
|
|
|
|
|
|
/* swapfile support */
|
2012-08-01 03:44:57 +04:00
|
|
|
int (*swap_activate)(struct swap_info_struct *sis, struct file *file,
|
|
|
|
sector_t *span);
|
|
|
|
void (*swap_deactivate)(struct file *file);
|
2005-04-17 02:20:36 +04:00
|
|
|
};
|
|
|
|
|
2011-04-06 01:51:48 +04:00
|
|
|
extern const struct address_space_operations empty_aops;
|
|
|
|
|
2007-10-16 12:25:01 +04:00
|
|
|
/*
|
|
|
|
* 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);
|
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
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 */
|
2008-07-26 06:45:32 +04:00
|
|
|
spinlock_t tree_lock; /* and lock protecting it */
|
2005-04-17 02:20:36 +04:00
|
|
|
unsigned int i_mmap_writable;/* count VM_SHARED mappings */
|
2012-10-09 03:31:25 +04:00
|
|
|
struct rb_root i_mmap; /* tree of private and shared mappings */
|
2005-04-17 02:20:36 +04:00
|
|
|
struct list_head i_mmap_nonlinear;/*list VM_NONLINEAR mappings */
|
2011-05-25 04:12:06 +04:00
|
|
|
struct mutex i_mmap_mutex; /* protect tree, count, list */
|
2011-06-28 03:18:10 +04:00
|
|
|
/* Protected by tree_lock together with the radix tree */
|
2005-04-17 02:20:36 +04:00
|
|
|
unsigned long nrpages; /* number of total pages */
|
|
|
|
pgoff_t writeback_index;/* writeback starts here */
|
2006-06-28 15:26:44 +04:00
|
|
|
const struct address_space_operations *a_ops; /* methods */
|
2005-04-17 02:20:36 +04:00
|
|
|
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 */
|
2012-12-12 04:02:35 +04:00
|
|
|
void *private_data; /* ditto */
|
2005-04-17 02:20:36 +04:00
|
|
|
} __attribute__((aligned(sizeof(long))));
|
|
|
|
/*
|
|
|
|
* On most architectures that alignment is already the case; but
|
2011-03-31 05:57:33 +04:00
|
|
|
* must be enforced here for CRIS, to let the least significant bit
|
2005-04-17 02:20:36 +04:00
|
|
|
* of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON.
|
|
|
|
*/
|
2012-01-13 05:20:34 +04:00
|
|
|
struct request_queue;
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
struct block_device {
|
|
|
|
dev_t bd_dev; /* not a kdev_t - it's a search key */
|
2011-03-23 02:33:56 +03:00
|
|
|
int bd_openers;
|
2005-04-17 02:20:36 +04:00
|
|
|
struct inode * bd_inode; /* will die */
|
2009-01-03 17:47:09 +03:00
|
|
|
struct super_block * bd_super;
|
2006-03-23 14:00:28 +03:00
|
|
|
struct mutex bd_mutex; /* open/close mutex */
|
2005-04-17 02:20:36 +04:00
|
|
|
struct list_head bd_inodes;
|
2010-04-07 13:53:59 +04:00
|
|
|
void * bd_claiming;
|
2005-04-17 02:20:36 +04:00
|
|
|
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;
|
2006-03-27 13:17:57 +04:00
|
|
|
#ifdef CONFIG_SYSFS
|
2011-01-14 20:43:57 +03:00
|
|
|
struct list_head bd_holder_disks;
|
2006-03-27 13:17:57 +04:00
|
|
|
#endif
|
2005-04-17 02:20:36 +04:00
|
|
|
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;
|
2012-01-13 05:20:34 +04:00
|
|
|
struct request_queue * bd_queue;
|
2005-04-17 02:20:36 +04:00
|
|
|
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;
|
2009-01-10 03:40:59 +03:00
|
|
|
|
|
|
|
/* The counter of freeze processes */
|
|
|
|
int bd_fsfreeze_count;
|
|
|
|
/* Mutex for freeze */
|
|
|
|
struct mutex bd_fsfreeze_mutex;
|
2005-04-17 02:20:36 +04:00
|
|
|
};
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Radix-tree tags, for tagging dirty and writeback pages within the pagecache
|
|
|
|
* radix trees
|
|
|
|
*/
|
|
|
|
#define PAGECACHE_TAG_DIRTY 0
|
|
|
|
#define PAGECACHE_TAG_WRITEBACK 1
|
2010-08-10 04:19:12 +04:00
|
|
|
#define PAGECACHE_TAG_TOWRITE 2
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
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)
|
|
|
|
{
|
2012-10-09 03:31:25 +04:00
|
|
|
return !RB_EMPTY_ROOT(&mapping->i_mmap) ||
|
2005-04-17 02:20:36 +04:00
|
|
|
!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
|
|
|
|
|
2009-06-09 03:50:45 +04:00
|
|
|
struct posix_acl;
|
|
|
|
#define ACL_NOT_CACHED ((void *)(-1))
|
|
|
|
|
2011-08-07 09:45:50 +04:00
|
|
|
#define IOP_FASTPERM 0x0001
|
|
|
|
#define IOP_LOOKUP 0x0002
|
|
|
|
#define IOP_NOFOLLOW 0x0004
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Keep mostly read-only and often accessed (especially for
|
|
|
|
* the RCU path lookup and 'stat' data) fields at the beginning
|
|
|
|
* of the 'struct inode'
|
|
|
|
*/
|
2005-04-17 02:20:36 +04:00
|
|
|
struct inode {
|
2011-01-07 09:49:56 +03:00
|
|
|
umode_t i_mode;
|
2011-08-07 09:45:50 +04:00
|
|
|
unsigned short i_opflags;
|
2012-02-08 19:07:50 +04:00
|
|
|
kuid_t i_uid;
|
|
|
|
kgid_t i_gid;
|
2011-08-07 09:45:50 +04:00
|
|
|
unsigned int i_flags;
|
|
|
|
|
|
|
|
#ifdef CONFIG_FS_POSIX_ACL
|
|
|
|
struct posix_acl *i_acl;
|
|
|
|
struct posix_acl *i_default_acl;
|
|
|
|
#endif
|
|
|
|
|
2011-01-07 09:49:56 +03:00
|
|
|
const struct inode_operations *i_op;
|
|
|
|
struct super_block *i_sb;
|
2011-08-07 09:45:50 +04:00
|
|
|
struct address_space *i_mapping;
|
2011-01-07 09:49:56 +03:00
|
|
|
|
2011-06-09 02:18:19 +04:00
|
|
|
#ifdef CONFIG_SECURITY
|
|
|
|
void *i_security;
|
|
|
|
#endif
|
2011-01-07 09:49:56 +03:00
|
|
|
|
2011-08-07 09:45:50 +04:00
|
|
|
/* Stat data, not accessed from path walking */
|
|
|
|
unsigned long i_ino;
|
2011-10-28 16:13:30 +04:00
|
|
|
/*
|
|
|
|
* Filesystems may only read i_nlink directly. They shall use the
|
|
|
|
* following functions for modification:
|
|
|
|
*
|
|
|
|
* (set|clear|inc|drop)_nlink
|
|
|
|
* inode_(inc|dec)_link_count
|
|
|
|
*/
|
|
|
|
union {
|
|
|
|
const unsigned int i_nlink;
|
|
|
|
unsigned int __i_nlink;
|
|
|
|
};
|
2011-08-07 09:45:50 +04:00
|
|
|
dev_t i_rdev;
|
2012-06-04 01:50:19 +04:00
|
|
|
loff_t i_size;
|
2011-08-07 09:45:50 +04:00
|
|
|
struct timespec i_atime;
|
|
|
|
struct timespec i_mtime;
|
|
|
|
struct timespec i_ctime;
|
2011-10-29 16:24:18 +04:00
|
|
|
spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */
|
|
|
|
unsigned short i_bytes;
|
2012-06-04 01:50:19 +04:00
|
|
|
unsigned int i_blkbits;
|
2011-08-07 09:45:50 +04:00
|
|
|
blkcnt_t i_blocks;
|
|
|
|
|
|
|
|
#ifdef __NEED_I_SIZE_ORDERED
|
|
|
|
seqcount_t i_size_seqcount;
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/* Misc */
|
|
|
|
unsigned long i_state;
|
|
|
|
struct mutex i_mutex;
|
2011-06-09 02:18:19 +04:00
|
|
|
|
2011-01-07 09:49:56 +03:00
|
|
|
unsigned long dirtied_when; /* jiffies of first dirtying */
|
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
struct hlist_node i_hash;
|
2010-10-21 04:49:30 +04:00
|
|
|
struct list_head i_wb_list; /* backing dev IO list */
|
|
|
|
struct list_head i_lru; /* inode LRU list */
|
2005-04-17 02:20:36 +04:00
|
|
|
struct list_head i_sb_list;
|
2011-01-07 09:49:49 +03:00
|
|
|
union {
|
2012-06-09 21:51:19 +04:00
|
|
|
struct hlist_head i_dentry;
|
2011-01-07 09:49:49 +03:00
|
|
|
struct rcu_head i_rcu;
|
|
|
|
};
|
2008-01-29 07:58:27 +03:00
|
|
|
u64 i_version;
|
2012-06-04 01:50:19 +04:00
|
|
|
atomic_t i_count;
|
2011-06-24 22:29:43 +04:00
|
|
|
atomic_t i_dio_count;
|
2011-10-29 16:24:18 +04:00
|
|
|
atomic_t i_writecount;
|
2006-03-28 13:56:41 +04:00
|
|
|
const struct file_operations *i_fop; /* former ->i_op->default_file_ops */
|
2005-04-17 02:20:36 +04:00
|
|
|
struct file_lock *i_flock;
|
|
|
|
struct address_space i_data;
|
|
|
|
#ifdef CONFIG_QUOTA
|
|
|
|
struct dquot *i_dquot[MAXQUOTAS];
|
|
|
|
#endif
|
|
|
|
struct list_head i_devices;
|
2006-09-27 12:50:47 +04:00
|
|
|
union {
|
|
|
|
struct pipe_inode_info *i_pipe;
|
2006-09-27 12:50:48 +04:00
|
|
|
struct block_device *i_bdev;
|
2006-09-27 12:50:49 +04:00
|
|
|
struct cdev *i_cdev;
|
2006-09-27 12:50:47 +04:00
|
|
|
};
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
__u32 i_generation;
|
|
|
|
|
2009-05-22 01:01:26 +04:00
|
|
|
#ifdef CONFIG_FSNOTIFY
|
|
|
|
__u32 i_fsnotify_mask; /* all events this inode cares about */
|
2009-12-18 05:24:24 +03:00
|
|
|
struct hlist_head i_fsnotify_marks;
|
[PATCH] inotify
inotify is intended to correct the deficiencies of dnotify, particularly
its inability to scale and its terrible user interface:
* dnotify requires the opening of one fd per each directory
that you intend to watch. This quickly results in too many
open files and pins removable media, preventing unmount.
* dnotify is directory-based. You only learn about changes to
directories. Sure, a change to a file in a directory affects
the directory, but you are then forced to keep a cache of
stat structures.
* dnotify's interface to user-space is awful. Signals?
inotify provides a more usable, simple, powerful solution to file change
notification:
* inotify's interface is a system call that returns a fd, not SIGIO.
You get a single fd, which is select()-able.
* inotify has an event that says "the filesystem that the item
you were watching is on was unmounted."
* inotify can watch directories or files.
Inotify is currently used by Beagle (a desktop search infrastructure),
Gamin (a FAM replacement), and other projects.
See Documentation/filesystems/inotify.txt.
Signed-off-by: Robert Love <rml@novell.com>
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-07-13 01:06:03 +04:00
|
|
|
#endif
|
|
|
|
|
2010-10-25 22:41:59 +04:00
|
|
|
#ifdef CONFIG_IMA
|
2010-11-02 17:10:56 +03:00
|
|
|
atomic_t i_readcount; /* struct files open RO */
|
2010-10-25 22:41:59 +04:00
|
|
|
#endif
|
2006-09-27 12:50:46 +04:00
|
|
|
void *i_private; /* fs or device private pointer */
|
2005-04-17 02:20:36 +04:00
|
|
|
};
|
|
|
|
|
2010-10-23 23:19:20 +04:00
|
|
|
static inline int inode_unhashed(struct inode *inode)
|
|
|
|
{
|
|
|
|
return hlist_unhashed(&inode->i_hash);
|
|
|
|
}
|
|
|
|
|
2006-07-03 11:25:05 +04:00
|
|
|
/*
|
|
|
|
* 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
|
2006-08-27 12:23:56 +04:00
|
|
|
* parent -> child -> normal -> xattr -> quota
|
2006-07-03 11:25:05 +04:00
|
|
|
*/
|
|
|
|
enum inode_i_mutex_lock_class
|
|
|
|
{
|
|
|
|
I_MUTEX_NORMAL,
|
|
|
|
I_MUTEX_PARENT,
|
|
|
|
I_MUTEX_CHILD,
|
2006-08-27 12:23:56 +04:00
|
|
|
I_MUTEX_XATTR,
|
2006-07-03 11:25:05 +04:00
|
|
|
I_MUTEX_QUOTA
|
|
|
|
};
|
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*/
|
2006-12-07 07:35:37 +03:00
|
|
|
static inline loff_t i_size_read(const struct inode *inode)
|
2005-04-17 02:20:36 +04:00
|
|
|
{
|
|
|
|
#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
|
|
|
|
}
|
|
|
|
|
2006-10-17 11:10:07 +04:00
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*/
|
2005-04-17 02:20:36 +04:00
|
|
|
static inline void i_size_write(struct inode *inode, loff_t i_size)
|
|
|
|
{
|
|
|
|
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
|
2013-05-01 02:27:27 +04:00
|
|
|
preempt_disable();
|
2005-04-17 02:20:36 +04:00
|
|
|
write_seqcount_begin(&inode->i_size_seqcount);
|
|
|
|
inode->i_size = i_size;
|
|
|
|
write_seqcount_end(&inode->i_size_seqcount);
|
2013-05-01 02:27:27 +04:00
|
|
|
preempt_enable();
|
2005-04-17 02:20:36 +04:00
|
|
|
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
|
|
|
|
preempt_disable();
|
|
|
|
inode->i_size = i_size;
|
|
|
|
preempt_enable();
|
|
|
|
#else
|
|
|
|
inode->i_size = i_size;
|
|
|
|
#endif
|
|
|
|
}
|
|
|
|
|
2012-02-08 19:07:50 +04:00
|
|
|
/* Helper functions so that in most cases filesystems will
|
|
|
|
* not need to deal directly with kuid_t and kgid_t and can
|
|
|
|
* instead deal with the raw numeric values that are stored
|
|
|
|
* in the filesystem.
|
|
|
|
*/
|
|
|
|
static inline uid_t i_uid_read(const struct inode *inode)
|
|
|
|
{
|
|
|
|
return from_kuid(&init_user_ns, inode->i_uid);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline gid_t i_gid_read(const struct inode *inode)
|
|
|
|
{
|
|
|
|
return from_kgid(&init_user_ns, inode->i_gid);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void i_uid_write(struct inode *inode, uid_t uid)
|
|
|
|
{
|
|
|
|
inode->i_uid = make_kuid(&init_user_ns, uid);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void i_gid_write(struct inode *inode, gid_t gid)
|
|
|
|
{
|
|
|
|
inode->i_gid = make_kgid(&init_user_ns, gid);
|
|
|
|
}
|
|
|
|
|
2006-12-07 07:35:37 +03:00
|
|
|
static inline unsigned iminor(const struct inode *inode)
|
2005-04-17 02:20:36 +04:00
|
|
|
{
|
|
|
|
return MINOR(inode->i_rdev);
|
|
|
|
}
|
|
|
|
|
2006-12-07 07:35:37 +03:00
|
|
|
static inline unsigned imajor(const struct inode *inode)
|
2005-04-17 02:20:36 +04:00
|
|
|
{
|
|
|
|
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 */
|
2006-10-02 13:17:15 +04:00
|
|
|
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 */
|
2012-02-08 19:07:50 +04:00
|
|
|
kuid_t uid, euid; /* uid/euid of process setting the owner */
|
2005-04-17 02:20:36 +04:00
|
|
|
int signum; /* posix.1b rt signal to be delivered on IO */
|
|
|
|
};
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Track a single file's readahead state
|
|
|
|
*/
|
|
|
|
struct file_ra_state {
|
2007-10-16 12:24:31 +04:00
|
|
|
pgoff_t start; /* where readahead started */
|
|
|
|
unsigned int size; /* # of readahead pages */
|
|
|
|
unsigned int async_size; /* do asynchronous readahead when
|
2007-07-19 12:48:08 +04:00
|
|
|
there are only # of pages ahead */
|
2007-07-19 12:47:59 +04:00
|
|
|
|
2007-10-16 12:24:31 +04:00
|
|
|
unsigned int ra_pages; /* Maximum readahead window */
|
2009-06-17 02:31:19 +04:00
|
|
|
unsigned int mmap_miss; /* Cache miss stat for mmap accesses */
|
2007-10-16 12:24:33 +04:00
|
|
|
loff_t prev_pos; /* Cache last read() position */
|
2005-04-17 02:20:36 +04:00
|
|
|
};
|
|
|
|
|
2007-07-19 12:47:59 +04:00
|
|
|
/*
|
|
|
|
* Check if @index falls in the readahead windows.
|
|
|
|
*/
|
|
|
|
static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
|
|
|
|
{
|
2007-07-19 12:48:08 +04:00
|
|
|
return (index >= ra->start &&
|
|
|
|
index < ra->start + ra->size);
|
2007-07-19 12:47:59 +04:00
|
|
|
}
|
|
|
|
|
2008-02-16 01:38:01 +03:00
|
|
|
#define FILE_MNT_WRITE_TAKEN 1
|
|
|
|
#define FILE_MNT_WRITE_RELEASED 2
|
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
struct file {
|
2005-10-31 02:02:16 +03:00
|
|
|
/*
|
|
|
|
* fu_list becomes invalid after file_free is called and queued via
|
|
|
|
* fu_rcuhead for RCU freeing
|
|
|
|
*/
|
|
|
|
union {
|
|
|
|
struct list_head fu_list;
|
2013-07-09 01:24:16 +04:00
|
|
|
struct llist_node fu_llist;
|
2005-10-31 02:02:16 +03:00
|
|
|
struct rcu_head fu_rcuhead;
|
|
|
|
} f_u;
|
2006-12-08 13:36:35 +03:00
|
|
|
struct path f_path;
|
|
|
|
#define f_dentry f_path.dentry
|
2013-03-02 04:48:30 +04:00
|
|
|
struct inode *f_inode; /* cached value */
|
2006-03-28 13:56:41 +04:00
|
|
|
const struct file_operations *f_op;
|
2011-09-16 03:06:48 +04:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Protects f_ep_links, f_flags, f_pos vs i_size in lseek SEEK_CUR.
|
|
|
|
* Must not be taken from IRQ context.
|
|
|
|
*/
|
|
|
|
spinlock_t f_lock;
|
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
|
2008-07-26 08:39:17 +04:00
|
|
|
atomic_long_t f_count;
|
2005-04-17 02:20:36 +04:00
|
|
|
unsigned int f_flags;
|
2008-09-02 23:28:45 +04:00
|
|
|
fmode_t f_mode;
|
2005-04-17 02:20:36 +04:00
|
|
|
loff_t f_pos;
|
|
|
|
struct fown_struct f_owner;
|
2008-11-14 02:39:25 +03:00
|
|
|
const struct cred *f_cred;
|
2005-04-17 02:20:36 +04:00
|
|
|
struct file_ra_state f_ra;
|
|
|
|
|
2007-10-17 10:27:21 +04:00
|
|
|
u64 f_version;
|
[PATCH] fs.h: ifdef security fields
[assuming BSD security levels are deleted]
The only user of i_security, f_security, s_security fields is SELinux,
however, quite a few security modules are trying to get into kernel.
So, wrap them under CONFIG_SECURITY. Adding config option for each
security field is likely an overkill.
Following Stephen Smalley's suggestion, i_security initialization is
moved to security_inode_alloc() to not clutter core code with ifdefs
and make alloc_inode() codepath tiny little bit smaller and faster.
The user of (highly greppable) struct fown_struct::security field is
still to be found. I've checked every "fown_struct" and every "f_owner"
occurence. Additionally it's removal doesn't break i386 allmodconfig
build.
struct inode, struct file, struct super_block, struct fown_struct
become smaller.
P.S. Combined with two reiserfs inode shrinking patches sent to
linux-fsdevel, I can finally suck 12 reiserfs inodes into one page.
/proc/slabinfo
-ext2_inode_cache 388 10
+ext2_inode_cache 384 10
-inode_cache 280 14
+inode_cache 276 14
-proc_inode_cache 296 13
+proc_inode_cache 292 13
-reiser_inode_cache 336 11
+reiser_inode_cache 332 12 <=
-shmem_inode_cache 372 10
+shmem_inode_cache 368 10
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Stephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-29 13:00:01 +04:00
|
|
|
#ifdef CONFIG_SECURITY
|
2005-04-17 02:20:36 +04:00
|
|
|
void *f_security;
|
[PATCH] fs.h: ifdef security fields
[assuming BSD security levels are deleted]
The only user of i_security, f_security, s_security fields is SELinux,
however, quite a few security modules are trying to get into kernel.
So, wrap them under CONFIG_SECURITY. Adding config option for each
security field is likely an overkill.
Following Stephen Smalley's suggestion, i_security initialization is
moved to security_inode_alloc() to not clutter core code with ifdefs
and make alloc_inode() codepath tiny little bit smaller and faster.
The user of (highly greppable) struct fown_struct::security field is
still to be found. I've checked every "fown_struct" and every "f_owner"
occurence. Additionally it's removal doesn't break i386 allmodconfig
build.
struct inode, struct file, struct super_block, struct fown_struct
become smaller.
P.S. Combined with two reiserfs inode shrinking patches sent to
linux-fsdevel, I can finally suck 12 reiserfs inodes into one page.
/proc/slabinfo
-ext2_inode_cache 388 10
+ext2_inode_cache 384 10
-inode_cache 280 14
+inode_cache 276 14
-proc_inode_cache 296 13
+proc_inode_cache 292 13
-reiser_inode_cache 336 11
+reiser_inode_cache 332 12 <=
-shmem_inode_cache 372 10
+shmem_inode_cache 368 10
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Stephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-29 13:00:01 +04:00
|
|
|
#endif
|
2005-04-17 02:20:36 +04:00
|
|
|
/* needed for tty driver, and maybe others */
|
|
|
|
void *private_data;
|
|
|
|
|
|
|
|
#ifdef CONFIG_EPOLL
|
|
|
|
/* Used by fs/eventpoll.c to link all the hooks to this file */
|
|
|
|
struct list_head f_ep_links;
|
epoll: limit paths
The current epoll code can be tickled to run basically indefinitely in
both loop detection path check (on ep_insert()), and in the wakeup paths.
The programs that tickle this behavior set up deeply linked networks of
epoll file descriptors that cause the epoll algorithms to traverse them
indefinitely. A couple of these sample programs have been previously
posted in this thread: https://lkml.org/lkml/2011/2/25/297.
To fix the loop detection path check algorithms, I simply keep track of
the epoll nodes that have been already visited. Thus, the loop detection
becomes proportional to the number of epoll file descriptor and links.
This dramatically decreases the run-time of the loop check algorithm. In
one diabolical case I tried it reduced the run-time from 15 mintues (all
in kernel time) to .3 seconds.
Fixing the wakeup paths could be done at wakeup time in a similar manner
by keeping track of nodes that have already been visited, but the
complexity is harder, since there can be multiple wakeups on different
cpus...Thus, I've opted to limit the number of possible wakeup paths when
the paths are created.
This is accomplished, by noting that the end file descriptor points that
are found during the loop detection pass (from the newly added link), are
actually the sources for wakeup events. I keep a list of these file
descriptors and limit the number and length of these paths that emanate
from these 'source file descriptors'. In the current implemetation I
allow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of
length 4 and 10 of length 5. Note that it is sufficient to check the
'source file descriptors' reachable from the newly added link, since no
other 'source file descriptors' will have newly added links. This allows
us to check only the wakeup paths that may have gotten too long, and not
re-check all possible wakeup paths on the system.
In terms of the path limit selection, I think its first worth noting that
the most common case for epoll, is probably the model where you have 1
epoll file descriptor that is monitoring n number of 'source file
descriptors'. In this case, each 'source file descriptor' has a 1 path of
length 1. Thus, I believe that the limits I'm proposing are quite
reasonable and in fact may be too generous. Thus, I'm hoping that the
proposed limits will not prevent any workloads that currently work to
fail.
In terms of locking, I have extended the use of the 'epmutex' to all
epoll_ctl add and remove operations. Currently its only used in a subset
of the add paths. I need to hold the epmutex, so that we can correctly
traverse a coherent graph, to check the number of paths. I believe that
this additional locking is probably ok, since its in the setup/teardown
paths, and doesn't affect the running paths, but it certainly is going to
add some extra overhead. Also, worth noting is that the epmuex was
recently added to the ep_ctl add operations in the initial path loop
detection code using the argument that it was not on a critical path.
Another thing to note here, is the length of epoll chains that is allowed.
Currently, eventpoll.c defines:
/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4
This basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS
+ 1). However, this limit is currently only enforced during the loop
check detection code, and only when the epoll file descriptors are added
in a certain order. Thus, this limit is currently easily bypassed. The
newly added check for wakeup paths, stricly limits the wakeup paths to a
length of 5, regardless of the order in which ep's are linked together.
Thus, a side-effect of the new code is a more consistent enforcement of
the graph depth.
Thus far, I've tested this, using the sample programs previously
mentioned, which now either return quickly or return -EINVAL. I've also
testing using the piptest.c epoll tester, which showed no difference in
performance. I've also created a number of different epoll networks and
tested that they behave as expectded.
I believe this solves the original diabolical test cases, while still
preserving the sane epoll nesting.
Signed-off-by: Jason Baron <jbaron@redhat.com>
Cc: Nelson Elhage <nelhage@ksplice.com>
Cc: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-01-13 05:17:43 +04:00
|
|
|
struct list_head f_tfile_llink;
|
2005-04-17 02:20:36 +04:00
|
|
|
#endif /* #ifdef CONFIG_EPOLL */
|
|
|
|
struct address_space *f_mapping;
|
2008-02-16 01:38:01 +03:00
|
|
|
#ifdef CONFIG_DEBUG_WRITECOUNT
|
|
|
|
unsigned long f_mnt_write_state;
|
|
|
|
#endif
|
2005-04-17 02:20:36 +04:00
|
|
|
};
|
|
|
|
|
2011-01-29 16:13:26 +03:00
|
|
|
struct file_handle {
|
|
|
|
__u32 handle_bytes;
|
|
|
|
int handle_type;
|
|
|
|
/* file identifier */
|
|
|
|
unsigned char f_handle[0];
|
|
|
|
};
|
|
|
|
|
2012-08-27 22:48:26 +04:00
|
|
|
static inline struct file *get_file(struct file *f)
|
|
|
|
{
|
|
|
|
atomic_long_inc(&f->f_count);
|
|
|
|
return f;
|
|
|
|
}
|
2010-05-26 23:13:55 +04:00
|
|
|
#define fput_atomic(x) atomic_long_add_unless(&(x)->f_count, -1, 1)
|
2008-07-26 08:39:17 +04:00
|
|
|
#define file_count(x) atomic_long_read(&(x)->f_count)
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2008-02-16 01:38:01 +03:00
|
|
|
#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 */
|
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
#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
|
2012-09-24 22:51:48 +04:00
|
|
|
#define MAX_LFS_FILESIZE (((loff_t)PAGE_CACHE_SIZE << (BITS_PER_LONG-1))-1)
|
2005-04-17 02:20:36 +04:00
|
|
|
#elif BITS_PER_LONG==64
|
2012-10-10 09:06:20 +04:00
|
|
|
#define MAX_LFS_FILESIZE ((loff_t)0x7fffffffffffffffLL)
|
2005-04-17 02:20:36 +04:00
|
|
|
#endif
|
|
|
|
|
|
|
|
#define FL_POSIX 1
|
|
|
|
#define FL_FLOCK 2
|
|
|
|
#define FL_ACCESS 8 /* not trying to lock, just looking */
|
2006-06-30 00:38:32 +04:00
|
|
|
#define FL_EXISTS 16 /* when unlocking, test for existence */
|
2005-04-17 02:20:36 +04:00
|
|
|
#define FL_LEASE 32 /* lease held on this file */
|
2006-06-23 13:05:12 +04:00
|
|
|
#define FL_CLOSE 64 /* unlock on close */
|
2005-04-17 02:20:36 +04:00
|
|
|
#define FL_SLEEP 128 /* A blocking lock */
|
2011-07-27 02:25:49 +04:00
|
|
|
#define FL_DOWNGRADE_PENDING 256 /* Lease is being downgraded */
|
|
|
|
#define FL_UNLOCK_PENDING 512 /* Lease is being broken */
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2008-07-25 12:48:57 +04:00
|
|
|
/*
|
|
|
|
* Special return value from posix_lock_file() and vfs_lock_file() for
|
|
|
|
* asynchronous locking.
|
|
|
|
*/
|
|
|
|
#define FILE_LOCK_DEFERRED 1
|
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
/*
|
|
|
|
* 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 {
|
2011-07-21 04:21:59 +04:00
|
|
|
int (*lm_compare_owner)(struct file_lock *, struct file_lock *);
|
2013-06-21 16:58:19 +04:00
|
|
|
unsigned long (*lm_owner_key)(struct file_lock *);
|
2011-07-21 04:21:59 +04:00
|
|
|
void (*lm_notify)(struct file_lock *); /* unblock callback */
|
|
|
|
int (*lm_grant)(struct file_lock *, struct file_lock *, int);
|
|
|
|
void (*lm_break)(struct file_lock *);
|
|
|
|
int (*lm_change)(struct file_lock **, int);
|
2005-04-17 02:20:36 +04:00
|
|
|
};
|
|
|
|
|
2007-09-06 20:34:25 +04:00
|
|
|
struct lock_manager {
|
|
|
|
struct list_head list;
|
|
|
|
};
|
|
|
|
|
2012-07-25 16:57:22 +04:00
|
|
|
struct net;
|
|
|
|
void locks_start_grace(struct net *, struct lock_manager *);
|
2007-09-06 20:34:25 +04:00
|
|
|
void locks_end_grace(struct lock_manager *);
|
2012-07-25 16:57:22 +04:00
|
|
|
int locks_in_grace(struct net *);
|
2007-09-06 20:34:25 +04:00
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
/* that will die - we need it for nfs_lock_info */
|
|
|
|
#include <linux/nfs_fs_i.h>
|
|
|
|
|
2013-06-21 16:58:12 +04:00
|
|
|
/*
|
|
|
|
* struct file_lock represents a generic "file lock". It's used to represent
|
|
|
|
* POSIX byte range locks, BSD (flock) locks, and leases. It's important to
|
|
|
|
* note that the same struct is used to represent both a request for a lock and
|
|
|
|
* the lock itself, but the same object is never used for both.
|
|
|
|
*
|
|
|
|
* FIXME: should we create a separate "struct lock_request" to help distinguish
|
|
|
|
* these two uses?
|
|
|
|
*
|
|
|
|
* The i_flock list is ordered by:
|
|
|
|
*
|
|
|
|
* 1) lock type -- FL_LEASEs first, then FL_FLOCK, and finally FL_POSIX
|
|
|
|
* 2) lock owner
|
|
|
|
* 3) lock range start
|
|
|
|
* 4) lock range end
|
|
|
|
*
|
|
|
|
* Obviously, the last two criteria only matter for POSIX locks.
|
|
|
|
*/
|
2005-04-17 02:20:36 +04:00
|
|
|
struct file_lock {
|
|
|
|
struct file_lock *fl_next; /* singly linked list for this inode */
|
2013-06-21 16:58:17 +04:00
|
|
|
struct hlist_node fl_link; /* node in global lists */
|
2005-04-17 02:20:36 +04:00
|
|
|
struct list_head fl_block; /* circular list of blocked processes */
|
|
|
|
fl_owner_t fl_owner;
|
2011-07-27 00:28:29 +04:00
|
|
|
unsigned int fl_flags;
|
2008-07-12 04:20:49 +04:00
|
|
|
unsigned char fl_type;
|
2005-04-17 02:20:36 +04:00
|
|
|
unsigned int fl_pid;
|
2013-06-21 16:58:22 +04:00
|
|
|
int fl_link_cpu; /* what cpu's list is this on? */
|
2008-01-17 03:07:08 +03:00
|
|
|
struct pid *fl_nspid;
|
2005-04-17 02:20:36 +04:00
|
|
|
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 */
|
2011-07-27 02:25:49 +04:00
|
|
|
/* for lease breaks: */
|
|
|
|
unsigned long fl_break_time;
|
|
|
|
unsigned long fl_downgrade_time;
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2009-09-22 04:01:11 +04:00
|
|
|
const struct file_lock_operations *fl_ops; /* Callbacks for filesystems */
|
2009-09-22 04:01:12 +04:00
|
|
|
const struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */
|
2005-04-17 02:20:36 +04:00
|
|
|
union {
|
|
|
|
struct nfs_lock_info nfs_fl;
|
2005-06-22 21:16:32 +04:00
|
|
|
struct nfs4_lock_info nfs4_fl;
|
2007-07-16 10:40:12 +04:00
|
|
|
struct {
|
|
|
|
struct list_head link; /* link in AFS vnode's pending_locks list */
|
|
|
|
int state; /* state of grant or error if -ve */
|
|
|
|
} afs;
|
2005-04-17 02:20:36 +04:00
|
|
|
} 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>
|
|
|
|
|
2008-08-06 17:12:22 +04:00
|
|
|
extern void send_sigio(struct fown_struct *fown, int fd, int band);
|
|
|
|
|
|
|
|
#ifdef CONFIG_FILE_LOCKING
|
2005-04-17 02:20:36 +04:00
|
|
|
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 *);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
#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 *);
|
2005-04-17 02:20:36 +04:00
|
|
|
#endif
|
|
|
|
|
|
|
|
extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg);
|
|
|
|
extern int fcntl_getlease(struct file *filp);
|
|
|
|
|
|
|
|
/* fs/locks.c */
|
2010-10-31 01:31:15 +04:00
|
|
|
void locks_free_lock(struct file_lock *fl);
|
2005-04-17 02:20:36 +04:00
|
|
|
extern void locks_init_lock(struct file_lock *);
|
2010-10-27 17:46:08 +04:00
|
|
|
extern struct file_lock * locks_alloc_lock(void);
|
2005-04-17 02:20:36 +04:00
|
|
|
extern void locks_copy_lock(struct file_lock *, struct file_lock *);
|
2008-04-24 18:08:22 +04:00
|
|
|
extern void __locks_copy_lock(struct file_lock *, const struct file_lock *);
|
2005-04-17 02:20:36 +04:00
|
|
|
extern void locks_remove_posix(struct file *, fl_owner_t);
|
|
|
|
extern void locks_remove_flock(struct file *);
|
2009-04-01 00:12:56 +04:00
|
|
|
extern void locks_release_private(struct file_lock *);
|
2007-05-12 00:09:32 +04:00
|
|
|
extern void posix_test_lock(struct file *, struct file_lock *);
|
2007-01-19 00:15:35 +03:00
|
|
|
extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *);
|
2005-04-17 02:20:36 +04:00
|
|
|
extern int posix_lock_file_wait(struct file *, struct file_lock *);
|
2013-06-21 16:58:09 +04:00
|
|
|
extern int posix_unblock_lock(struct file_lock *);
|
2007-02-21 08:58:50 +03:00
|
|
|
extern int vfs_test_lock(struct file *, struct file_lock *);
|
2007-01-19 00:15:35 +03:00
|
|
|
extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *);
|
2007-01-19 01:52:58 +03:00
|
|
|
extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
|
2005-04-17 02:20:36 +04:00
|
|
|
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);
|
2007-07-31 11:39:22 +04:00
|
|
|
extern int generic_setlease(struct file *, long, struct file_lock **);
|
2007-06-08 01:09:49 +04:00
|
|
|
extern int vfs_setlease(struct file *, long, struct file_lock **);
|
2005-04-17 02:20:36 +04:00
|
|
|
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);
|
2008-08-06 17:12:22 +04:00
|
|
|
#else /* !CONFIG_FILE_LOCKING */
|
2009-01-20 13:29:45 +03:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2008-08-06 17:12:22 +04:00
|
|
|
#if BITS_PER_LONG == 32
|
2009-01-20 13:29:45 +03:00
|
|
|
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;
|
|
|
|
}
|
2008-08-06 17:12:22 +04:00
|
|
|
#endif
|
2009-01-20 13:29:45 +03:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2013-06-21 16:58:09 +04:00
|
|
|
static inline int posix_unblock_lock(struct file_lock *waiter)
|
2009-01-20 13:29:45 +03:00
|
|
|
{
|
|
|
|
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;
|
|
|
|
}
|
2008-08-06 17:12:22 +04:00
|
|
|
#endif /* !CONFIG_FILE_LOCKING */
|
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
struct fasync_struct {
|
2010-04-14 13:55:35 +04:00
|
|
|
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;
|
2005-04-17 02:20:36 +04:00
|
|
|
};
|
|
|
|
|
|
|
|
#define FASYNC_MAGIC 0x4601
|
|
|
|
|
|
|
|
/* SMP safe fasync helpers: */
|
|
|
|
extern int fasync_helper(int, struct file *, int, struct fasync_struct **);
|
2010-10-27 20:38:12 +04:00
|
|
|
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 *);
|
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
/* can be called from interrupts */
|
|
|
|
extern void kill_fasync(struct fasync_struct **, int, int);
|
|
|
|
|
2006-10-02 13:17:15 +04:00
|
|
|
extern int __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
|
2005-04-17 02:20:36 +04:00
|
|
|
extern int f_setown(struct file *filp, unsigned long arg, int force);
|
|
|
|
extern void f_delown(struct file *filp);
|
2006-10-02 13:17:15 +04:00
|
|
|
extern pid_t f_getown(struct file *filp);
|
2005-04-17 02:20:36 +04:00
|
|
|
extern int send_sigurg(struct fown_struct *fown);
|
|
|
|
|
2012-06-12 18:20:34 +04:00
|
|
|
struct mm_struct;
|
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
/*
|
|
|
|
* 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 */
|
2010-02-10 14:15:53 +03:00
|
|
|
#define UMOUNT_NOFOLLOW 0x00000008 /* Don't follow symlink on umount */
|
|
|
|
#define UMOUNT_UNUSED 0x80000000 /* Flag guaranteed to be unused */
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
extern struct list_head super_blocks;
|
|
|
|
extern spinlock_t sb_lock;
|
|
|
|
|
2012-06-12 18:20:34 +04:00
|
|
|
/* Possible states of 'frozen' field */
|
|
|
|
enum {
|
|
|
|
SB_UNFROZEN = 0, /* FS is unfrozen */
|
|
|
|
SB_FREEZE_WRITE = 1, /* Writes, dir ops, ioctls frozen */
|
|
|
|
SB_FREEZE_PAGEFAULT = 2, /* Page faults stopped as well */
|
|
|
|
SB_FREEZE_FS = 3, /* For internal FS use (e.g. to stop
|
|
|
|
* internal threads if needed) */
|
|
|
|
SB_FREEZE_COMPLETE = 4, /* ->freeze_fs finished successfully */
|
|
|
|
};
|
|
|
|
|
|
|
|
#define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1)
|
|
|
|
|
|
|
|
struct sb_writers {
|
|
|
|
/* Counters for counting writers at each level */
|
|
|
|
struct percpu_counter counter[SB_FREEZE_LEVELS];
|
|
|
|
wait_queue_head_t wait; /* queue for waiting for
|
|
|
|
writers / faults to finish */
|
|
|
|
int frozen; /* Is sb frozen? */
|
|
|
|
wait_queue_head_t wait_unfrozen; /* queue for waiting for
|
|
|
|
sb to be thawed */
|
|
|
|
#ifdef CONFIG_DEBUG_LOCK_ALLOC
|
|
|
|
struct lockdep_map lock_map[SB_FREEZE_LEVELS];
|
|
|
|
#endif
|
|
|
|
};
|
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
struct super_block {
|
|
|
|
struct list_head s_list; /* Keep this first */
|
|
|
|
dev_t s_dev; /* search index; _not_ kdev_t */
|
2010-01-26 17:12:43 +03:00
|
|
|
unsigned char s_blocksize_bits;
|
|
|
|
unsigned long s_blocksize;
|
2009-09-19 00:05:53 +04:00
|
|
|
loff_t s_maxbytes; /* Max file size */
|
2005-04-17 02:20:36 +04:00
|
|
|
struct file_system_type *s_type;
|
2007-02-12 11:55:41 +03:00
|
|
|
const struct super_operations *s_op;
|
2009-09-22 04:01:08 +04:00
|
|
|
const struct dquot_operations *dq_op;
|
2009-09-22 04:01:09 +04:00
|
|
|
const struct quotactl_ops *s_qcop;
|
2007-10-22 03:42:17 +04:00
|
|
|
const struct export_operations *s_export_op;
|
2005-04-17 02:20:36 +04:00
|
|
|
unsigned long s_flags;
|
|
|
|
unsigned long s_magic;
|
|
|
|
struct dentry *s_root;
|
|
|
|
struct rw_semaphore s_umount;
|
|
|
|
int s_count;
|
|
|
|
atomic_t s_active;
|
[PATCH] fs.h: ifdef security fields
[assuming BSD security levels are deleted]
The only user of i_security, f_security, s_security fields is SELinux,
however, quite a few security modules are trying to get into kernel.
So, wrap them under CONFIG_SECURITY. Adding config option for each
security field is likely an overkill.
Following Stephen Smalley's suggestion, i_security initialization is
moved to security_inode_alloc() to not clutter core code with ifdefs
and make alloc_inode() codepath tiny little bit smaller and faster.
The user of (highly greppable) struct fown_struct::security field is
still to be found. I've checked every "fown_struct" and every "f_owner"
occurence. Additionally it's removal doesn't break i386 allmodconfig
build.
struct inode, struct file, struct super_block, struct fown_struct
become smaller.
P.S. Combined with two reiserfs inode shrinking patches sent to
linux-fsdevel, I can finally suck 12 reiserfs inodes into one page.
/proc/slabinfo
-ext2_inode_cache 388 10
+ext2_inode_cache 384 10
-inode_cache 280 14
+inode_cache 276 14
-proc_inode_cache 296 13
+proc_inode_cache 292 13
-reiser_inode_cache 336 11
+reiser_inode_cache 332 12 <=
-shmem_inode_cache 372 10
+shmem_inode_cache 368 10
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Stephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-29 13:00:01 +04:00
|
|
|
#ifdef CONFIG_SECURITY
|
2005-04-17 02:20:36 +04:00
|
|
|
void *s_security;
|
[PATCH] fs.h: ifdef security fields
[assuming BSD security levels are deleted]
The only user of i_security, f_security, s_security fields is SELinux,
however, quite a few security modules are trying to get into kernel.
So, wrap them under CONFIG_SECURITY. Adding config option for each
security field is likely an overkill.
Following Stephen Smalley's suggestion, i_security initialization is
moved to security_inode_alloc() to not clutter core code with ifdefs
and make alloc_inode() codepath tiny little bit smaller and faster.
The user of (highly greppable) struct fown_struct::security field is
still to be found. I've checked every "fown_struct" and every "f_owner"
occurence. Additionally it's removal doesn't break i386 allmodconfig
build.
struct inode, struct file, struct super_block, struct fown_struct
become smaller.
P.S. Combined with two reiserfs inode shrinking patches sent to
linux-fsdevel, I can finally suck 12 reiserfs inodes into one page.
/proc/slabinfo
-ext2_inode_cache 388 10
+ext2_inode_cache 384 10
-inode_cache 280 14
+inode_cache 276 14
-proc_inode_cache 296 13
+proc_inode_cache 292 13
-reiser_inode_cache 336 11
+reiser_inode_cache 332 12 <=
-shmem_inode_cache 372 10
+shmem_inode_cache 368 10
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Stephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-29 13:00:01 +04:00
|
|
|
#endif
|
2010-05-14 04:53:14 +04:00
|
|
|
const struct xattr_handler **s_xattr;
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
struct list_head s_inodes; /* all inodes */
|
2011-01-07 09:50:05 +03:00
|
|
|
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
|
2005-04-17 02:20:36 +04:00
|
|
|
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
|
2011-11-21 15:11:30 +04:00
|
|
|
struct list_head s_mounts; /* list of mounts; _not_ for fs use */
|
2005-04-17 02:20:36 +04:00
|
|
|
struct block_device *s_bdev;
|
2009-09-16 17:02:33 +04:00
|
|
|
struct backing_dev_info *s_bdi;
|
2007-05-11 09:51:50 +04:00
|
|
|
struct mtd_info *s_mtd;
|
2011-12-13 07:53:00 +04:00
|
|
|
struct hlist_node s_instances;
|
2005-04-17 02:20:36 +04:00
|
|
|
struct quota_info s_dquot; /* Diskquota specific options */
|
|
|
|
|
2012-06-12 18:20:34 +04:00
|
|
|
struct sb_writers s_writers;
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
char s_id[32]; /* Informational name */
|
2011-04-13 02:21:04 +04:00
|
|
|
u8 s_uuid[16]; /* UUID */
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
void *s_fs_info; /* Filesystem private info */
|
2012-02-06 21:45:27 +04:00
|
|
|
unsigned int s_max_links;
|
2008-02-23 03:50:45 +03:00
|
|
|
fmode_t s_mode;
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2010-01-26 17:12:43 +03:00
|
|
|
/* Granularity of c/m/atime in ns.
|
|
|
|
Cannot be worse than a second */
|
|
|
|
u32 s_time_gran;
|
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
/*
|
|
|
|
* The next field is for VFS *only*. No filesystems have any business
|
|
|
|
* even looking at it. You had been warned.
|
|
|
|
*/
|
2006-03-23 14:00:33 +03:00
|
|
|
struct mutex s_vfs_rename_mutex; /* Kludge */
|
2005-04-17 02:20:36 +04:00
|
|
|
|
add filesystem subtype support
There's a slight problem with filesystem type representation in fuse
based filesystems.
From the kernel's view, there are just two filesystem types: fuse and
fuseblk. From the user's view there are lots of different filesystem
types. The user is not even much concerned if the filesystem is fuse based
or not. So there's a conflict of interest in how this should be
represented in fstab, mtab and /proc/mounts.
The current scheme is to encode the real filesystem type in the mount
source. So an sshfs mount looks like this:
sshfs#user@server:/ /mnt/server fuse rw,nosuid,nodev,...
This url-ish syntax works OK for sshfs and similar filesystems. However
for block device based filesystems (ntfs-3g, zfs) it doesn't work, since
the kernel expects the mount source to be a real device name.
A possibly better scheme would be to encode the real type in the type
field as "type.subtype". So fuse mounts would look like this:
/dev/hda1 /mnt/windows fuseblk.ntfs-3g rw,...
user@server:/ /mnt/server fuse.sshfs rw,nosuid,nodev,...
This patch adds the necessary code to the kernel so that this can be
correctly displayed in /proc/mounts.
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 11:25:43 +04:00
|
|
|
/*
|
|
|
|
* Filesystem subtype. If non-empty the filesystem type field
|
|
|
|
* in /proc/mounts will be "type.subtype"
|
|
|
|
*/
|
|
|
|
char *s_subtype;
|
2008-02-08 15:21:35 +03:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Saved mount options for lazy filesystems using
|
|
|
|
* generic_show_options()
|
|
|
|
*/
|
2010-02-24 22:01:56 +03:00
|
|
|
char __rcu *s_options;
|
2010-12-18 18:22:30 +03:00
|
|
|
const struct dentry_operations *s_d_op; /* default d_op for dentries */
|
2011-05-26 20:01:19 +04:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Saved pool identifier for cleancache (-1 means none)
|
|
|
|
*/
|
|
|
|
int cleancache_poolid;
|
2011-07-08 08:14:42 +04:00
|
|
|
|
|
|
|
struct shrinker s_shrink; /* per-sb shrinker handle */
|
2011-11-21 15:11:31 +04:00
|
|
|
|
2011-11-21 15:11:32 +04:00
|
|
|
/* Number of inodes with nlink == 0 but still referenced */
|
|
|
|
atomic_long_t s_remove_count;
|
|
|
|
|
2011-11-21 15:11:31 +04:00
|
|
|
/* Being remounted read-only */
|
|
|
|
int s_readonly_remount;
|
2013-09-04 17:04:39 +04:00
|
|
|
|
|
|
|
/* AIO completions deferred from interrupt context */
|
|
|
|
struct workqueue_struct *s_dio_done_wq;
|
2013-08-28 04:18:00 +04:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Keep the lru lists last in the structure so they always sit on their
|
|
|
|
* own individual cachelines.
|
|
|
|
*/
|
|
|
|
struct list_lru s_dentry_lru ____cacheline_aligned_in_smp;
|
|
|
|
struct list_lru s_inode_lru ____cacheline_aligned_in_smp;
|
2005-04-17 02:20:36 +04:00
|
|
|
};
|
|
|
|
|
|
|
|
extern struct timespec current_fs_time(struct super_block *sb);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Snapshotting support.
|
|
|
|
*/
|
|
|
|
|
2012-06-12 18:20:34 +04:00
|
|
|
void __sb_end_write(struct super_block *sb, int level);
|
|
|
|
int __sb_start_write(struct super_block *sb, int level, bool wait);
|
|
|
|
|
|
|
|
/**
|
|
|
|
* sb_end_write - drop write access to a superblock
|
|
|
|
* @sb: the super we wrote to
|
|
|
|
*
|
|
|
|
* Decrement number of writers to the filesystem. Wake up possible waiters
|
|
|
|
* wanting to freeze the filesystem.
|
|
|
|
*/
|
|
|
|
static inline void sb_end_write(struct super_block *sb)
|
|
|
|
{
|
|
|
|
__sb_end_write(sb, SB_FREEZE_WRITE);
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* sb_end_pagefault - drop write access to a superblock from a page fault
|
|
|
|
* @sb: the super we wrote to
|
|
|
|
*
|
|
|
|
* Decrement number of processes handling write page fault to the filesystem.
|
|
|
|
* Wake up possible waiters wanting to freeze the filesystem.
|
|
|
|
*/
|
|
|
|
static inline void sb_end_pagefault(struct super_block *sb)
|
|
|
|
{
|
|
|
|
__sb_end_write(sb, SB_FREEZE_PAGEFAULT);
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* sb_end_intwrite - drop write access to a superblock for internal fs purposes
|
|
|
|
* @sb: the super we wrote to
|
|
|
|
*
|
|
|
|
* Decrement fs-internal number of writers to the filesystem. Wake up possible
|
|
|
|
* waiters wanting to freeze the filesystem.
|
|
|
|
*/
|
|
|
|
static inline void sb_end_intwrite(struct super_block *sb)
|
|
|
|
{
|
|
|
|
__sb_end_write(sb, SB_FREEZE_FS);
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* sb_start_write - get write access to a superblock
|
|
|
|
* @sb: the super we write to
|
|
|
|
*
|
|
|
|
* When a process wants to write data or metadata to a file system (i.e. dirty
|
|
|
|
* a page or an inode), it should embed the operation in a sb_start_write() -
|
|
|
|
* sb_end_write() pair to get exclusion against file system freezing. This
|
|
|
|
* function increments number of writers preventing freezing. If the file
|
|
|
|
* system is already frozen, the function waits until the file system is
|
|
|
|
* thawed.
|
|
|
|
*
|
|
|
|
* Since freeze protection behaves as a lock, users have to preserve
|
|
|
|
* ordering of freeze protection and other filesystem locks. Generally,
|
|
|
|
* freeze protection should be the outermost lock. In particular, we have:
|
|
|
|
*
|
|
|
|
* sb_start_write
|
|
|
|
* -> i_mutex (write path, truncate, directory ops, ...)
|
|
|
|
* -> s_umount (freeze_super, thaw_super)
|
|
|
|
*/
|
|
|
|
static inline void sb_start_write(struct super_block *sb)
|
|
|
|
{
|
|
|
|
__sb_start_write(sb, SB_FREEZE_WRITE, true);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline int sb_start_write_trylock(struct super_block *sb)
|
|
|
|
{
|
|
|
|
return __sb_start_write(sb, SB_FREEZE_WRITE, false);
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* sb_start_pagefault - get write access to a superblock from a page fault
|
|
|
|
* @sb: the super we write to
|
|
|
|
*
|
|
|
|
* When a process starts handling write page fault, it should embed the
|
|
|
|
* operation into sb_start_pagefault() - sb_end_pagefault() pair to get
|
|
|
|
* exclusion against file system freezing. This is needed since the page fault
|
|
|
|
* is going to dirty a page. This function increments number of running page
|
|
|
|
* faults preventing freezing. If the file system is already frozen, the
|
|
|
|
* function waits until the file system is thawed.
|
|
|
|
*
|
|
|
|
* Since page fault freeze protection behaves as a lock, users have to preserve
|
|
|
|
* ordering of freeze protection and other filesystem locks. It is advised to
|
|
|
|
* put sb_start_pagefault() close to mmap_sem in lock ordering. Page fault
|
|
|
|
* handling code implies lock dependency:
|
|
|
|
*
|
|
|
|
* mmap_sem
|
|
|
|
* -> sb_start_pagefault
|
|
|
|
*/
|
|
|
|
static inline void sb_start_pagefault(struct super_block *sb)
|
|
|
|
{
|
|
|
|
__sb_start_write(sb, SB_FREEZE_PAGEFAULT, true);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* sb_start_intwrite - get write access to a superblock for internal fs purposes
|
|
|
|
* @sb: the super we write to
|
|
|
|
*
|
|
|
|
* This is the third level of protection against filesystem freezing. It is
|
|
|
|
* free for use by a filesystem. The only requirement is that it must rank
|
|
|
|
* below sb_start_pagefault.
|
|
|
|
*
|
|
|
|
* For example filesystem can call sb_start_intwrite() when starting a
|
|
|
|
* transaction which somewhat eases handling of freezing for internal sources
|
|
|
|
* of filesystem changes (internal fs threads, discarding preallocation on file
|
|
|
|
* close, etc.).
|
|
|
|
*/
|
|
|
|
static inline void sb_start_intwrite(struct super_block *sb)
|
|
|
|
{
|
|
|
|
__sb_start_write(sb, SB_FREEZE_FS, true);
|
|
|
|
}
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
|
2011-03-24 02:43:26 +03:00
|
|
|
extern bool inode_owner_or_capable(const struct inode *inode);
|
2007-07-17 13:30:08 +04:00
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
/*
|
|
|
|
* VFS helper functions..
|
|
|
|
*/
|
2012-06-11 02:09:36 +04:00
|
|
|
extern int vfs_create(struct inode *, struct dentry *, umode_t, bool);
|
2011-07-26 09:41:39 +04:00
|
|
|
extern int vfs_mkdir(struct inode *, struct dentry *, umode_t);
|
2011-07-26 09:52:52 +04:00
|
|
|
extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
|
2008-06-24 18:50:16 +04:00
|
|
|
extern int vfs_symlink(struct inode *, struct dentry *, const char *);
|
2005-04-17 02:20:36 +04:00
|
|
|
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);
|
|
|
|
|
2005-11-09 08:35:04 +03:00
|
|
|
/*
|
|
|
|
* VFS file helper functions.
|
|
|
|
*/
|
2010-03-04 17:29:14 +03:00
|
|
|
extern void inode_init_owner(struct inode *inode, const struct inode *dir,
|
2011-07-25 07:20:18 +04:00
|
|
|
umode_t mode);
|
2008-10-09 03:44:18 +04:00
|
|
|
/*
|
|
|
|
* 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 */
|
2011-01-16 17:28:17 +03:00
|
|
|
struct fiemap_extent __user *fi_extents_start; /* Start of
|
|
|
|
fiemap_extent array */
|
2008-10-09 03:44:18 +04:00
|
|
|
};
|
|
|
|
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);
|
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*/
|
2006-10-03 12:13:46 +04:00
|
|
|
typedef int (*filldir_t)(void *, const char *, int, loff_t, u64, unsigned);
|
2013-05-15 21:52:59 +04:00
|
|
|
struct dir_context {
|
2013-05-23 06:22:04 +04:00
|
|
|
const filldir_t actor;
|
2013-05-16 02:49:12 +04:00
|
|
|
loff_t pos;
|
2013-05-15 21:52:59 +04:00
|
|
|
};
|
2013-05-16 02:49:12 +04:00
|
|
|
|
2007-10-08 21:26:20 +04:00
|
|
|
struct block_device_operations;
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
/* 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
|
|
|
|
|
|
|
|
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 *);
|
2006-10-01 10:28:46 +04:00
|
|
|
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);
|
2013-05-16 02:49:12 +04:00
|
|
|
int (*iterate) (struct file *, struct dir_context *);
|
2005-04-17 02:20:36 +04:00
|
|
|
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 *);
|
2006-06-23 13:05:12 +04:00
|
|
|
int (*flush) (struct file *, fl_owner_t id);
|
2005-04-17 02:20:36 +04:00
|
|
|
int (*release) (struct inode *, struct file *);
|
2011-07-17 04:44:56 +04:00
|
|
|
int (*fsync) (struct file *, loff_t, loff_t, int datasync);
|
2005-04-17 02:20:36 +04:00
|
|
|
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 *);
|
2006-04-11 16:57:50 +04:00
|
|
|
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);
|
2006-11-14 23:51:40 +03:00
|
|
|
int (*setlease)(struct file *, long, struct file_lock **);
|
2011-01-14 15:07:43 +03:00
|
|
|
long (*fallocate)(struct file *file, int mode, loff_t offset,
|
|
|
|
loff_t len);
|
2012-12-18 04:04:55 +04:00
|
|
|
int (*show_fdinfo)(struct seq_file *m, struct file *f);
|
2005-04-17 02:20:36 +04:00
|
|
|
};
|
|
|
|
|
|
|
|
struct inode_operations {
|
2012-06-11 01:13:09 +04:00
|
|
|
struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
|
2011-01-07 09:49:56 +03:00
|
|
|
void * (*follow_link) (struct dentry *, struct nameidata *);
|
2011-06-21 03:28:19 +04:00
|
|
|
int (*permission) (struct inode *, int);
|
2011-07-23 19:37:31 +04:00
|
|
|
struct posix_acl * (*get_acl)(struct inode *, int);
|
2011-01-07 09:49:56 +03:00
|
|
|
|
|
|
|
int (*readlink) (struct dentry *, char __user *,int);
|
|
|
|
void (*put_link) (struct dentry *, struct nameidata *, void *);
|
|
|
|
|
2012-06-11 02:05:36 +04:00
|
|
|
int (*create) (struct inode *,struct dentry *, umode_t, bool);
|
2005-04-17 02:20:36 +04:00
|
|
|
int (*link) (struct dentry *,struct inode *,struct dentry *);
|
|
|
|
int (*unlink) (struct inode *,struct dentry *);
|
|
|
|
int (*symlink) (struct inode *,struct dentry *,const char *);
|
2011-07-26 09:41:39 +04:00
|
|
|
int (*mkdir) (struct inode *,struct dentry *,umode_t);
|
2005-04-17 02:20:36 +04:00
|
|
|
int (*rmdir) (struct inode *,struct dentry *);
|
2011-07-26 09:52:52 +04:00
|
|
|
int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
|
2005-04-17 02:20:36 +04:00
|
|
|
int (*rename) (struct inode *, struct dentry *,
|
|
|
|
struct inode *, struct dentry *);
|
|
|
|
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 *);
|
2008-10-09 03:44:18 +04:00
|
|
|
int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
|
|
|
|
u64 len);
|
2012-03-26 17:59:21 +04:00
|
|
|
int (*update_time)(struct inode *, struct timespec *, int);
|
2012-06-22 12:39:14 +04:00
|
|
|
int (*atomic_open)(struct inode *, struct dentry *,
|
2012-06-22 12:40:19 +04:00
|
|
|
struct file *, unsigned open_flag,
|
2012-06-22 12:39:14 +04:00
|
|
|
umode_t create_mode, int *opened);
|
2013-06-07 09:20:27 +04:00
|
|
|
int (*tmpfile) (struct inode *, struct dentry *, umode_t);
|
2011-01-07 09:49:56 +03:00
|
|
|
} ____cacheline_aligned;
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2006-10-01 10:28:49 +04:00
|
|
|
ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
|
2011-11-01 04:06:39 +04:00
|
|
|
unsigned long nr_segs, unsigned long fast_segs,
|
|
|
|
struct iovec *fast_pointer,
|
2012-06-01 03:26:42 +04:00
|
|
|
struct iovec **ret_pointer);
|
2006-10-01 10:28:49 +04:00
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
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 *);
|
|
|
|
|
2011-05-27 14:53:02 +04:00
|
|
|
void (*dirty_inode) (struct inode *, int flags);
|
2010-03-05 11:21:37 +03:00
|
|
|
int (*write_inode) (struct inode *, struct writeback_control *wbc);
|
2010-06-07 21:43:19 +04:00
|
|
|
int (*drop_inode) (struct inode *);
|
2010-06-05 03:40:39 +04:00
|
|
|
void (*evict_inode) (struct inode *);
|
2005-04-17 02:20:36 +04:00
|
|
|
void (*put_super) (struct super_block *);
|
|
|
|
int (*sync_fs)(struct super_block *sb, int wait);
|
2009-01-10 03:40:58 +03:00
|
|
|
int (*freeze_fs) (struct super_block *);
|
|
|
|
int (*unfreeze_fs) (struct super_block *);
|
2006-06-23 13:02:58 +04:00
|
|
|
int (*statfs) (struct dentry *, struct kstatfs *);
|
2005-04-17 02:20:36 +04:00
|
|
|
int (*remount_fs) (struct super_block *, int *, char *);
|
2008-04-24 15:21:56 +04:00
|
|
|
void (*umount_begin) (struct super_block *);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2011-12-09 06:32:45 +04:00
|
|
|
int (*show_options)(struct seq_file *, struct dentry *);
|
2011-12-09 06:32:45 +04:00
|
|
|
int (*show_devname)(struct seq_file *, struct dentry *);
|
2011-12-09 06:37:57 +04:00
|
|
|
int (*show_path)(struct seq_file *, struct dentry *);
|
2011-12-09 05:51:13 +04:00
|
|
|
int (*show_stats)(struct seq_file *, struct dentry *);
|
2006-09-29 12:59:56 +04:00
|
|
|
#ifdef CONFIG_QUOTA
|
2005-04-17 02:20:36 +04:00
|
|
|
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);
|
2006-09-29 12:59:56 +04:00
|
|
|
#endif
|
2009-01-03 17:47:09 +03:00
|
|
|
int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
|
2013-08-28 04:18:05 +04:00
|
|
|
long (*nr_cached_objects)(struct super_block *, int);
|
|
|
|
long (*free_cached_objects)(struct super_block *, long, int);
|
2005-04-17 02:20:36 +04:00
|
|
|
};
|
|
|
|
|
2012-10-15 19:40:35 +04:00
|
|
|
/*
|
|
|
|
* Inode flags - they have no relation to superblock flags now
|
|
|
|
*/
|
|
|
|
#define S_SYNC 1 /* Writes are synced at once */
|
|
|
|
#define S_NOATIME 2 /* Do not update access times */
|
|
|
|
#define S_APPEND 4 /* Append-only file */
|
|
|
|
#define S_IMMUTABLE 8 /* Immutable file */
|
|
|
|
#define S_DEAD 16 /* removed, but still open directory */
|
|
|
|
#define S_NOQUOTA 32 /* Inode is not counted to quota */
|
|
|
|
#define S_DIRSYNC 64 /* Directory modifications are synchronous */
|
|
|
|
#define S_NOCMTIME 128 /* Do not update file c/mtime */
|
|
|
|
#define S_SWAPFILE 256 /* Do not truncate: swapon got its bmaps */
|
|
|
|
#define S_PRIVATE 512 /* Inode is fs-internal */
|
|
|
|
#define S_IMA 1024 /* Inode has an associated IMA struct */
|
|
|
|
#define S_AUTOMOUNT 2048 /* Automount/referral quasi-directory */
|
|
|
|
#define S_NOSEC 4096 /* no suid or xattr security attributes */
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Note that nosuid etc flags are inode-specific: setting some file-system
|
|
|
|
* flags just means all the inodes inherit those flags by default. It might be
|
|
|
|
* possible to override it selectively if you really wanted to with some
|
|
|
|
* ioctl() that is not currently implemented.
|
|
|
|
*
|
|
|
|
* Exception: MS_RDONLY is always applied to the entire file system.
|
|
|
|
*
|
|
|
|
* Unfortunately, it is possible to change a filesystems flags with it mounted
|
|
|
|
* with files in use. This means that all of the inodes will not have their
|
|
|
|
* i_flags updated. Hence, i_flags no longer inherit the superblock mount
|
|
|
|
* flags, so these have to be checked separately. -- rmk@arm.uk.linux.org
|
|
|
|
*/
|
|
|
|
#define __IS_FLG(inode, flg) ((inode)->i_sb->s_flags & (flg))
|
|
|
|
|
|
|
|
#define IS_RDONLY(inode) ((inode)->i_sb->s_flags & MS_RDONLY)
|
|
|
|
#define IS_SYNC(inode) (__IS_FLG(inode, MS_SYNCHRONOUS) || \
|
|
|
|
((inode)->i_flags & S_SYNC))
|
|
|
|
#define IS_DIRSYNC(inode) (__IS_FLG(inode, MS_SYNCHRONOUS|MS_DIRSYNC) || \
|
|
|
|
((inode)->i_flags & (S_SYNC|S_DIRSYNC)))
|
|
|
|
#define IS_MANDLOCK(inode) __IS_FLG(inode, MS_MANDLOCK)
|
|
|
|
#define IS_NOATIME(inode) __IS_FLG(inode, MS_RDONLY|MS_NOATIME)
|
|
|
|
#define IS_I_VERSION(inode) __IS_FLG(inode, MS_I_VERSION)
|
|
|
|
|
|
|
|
#define IS_NOQUOTA(inode) ((inode)->i_flags & S_NOQUOTA)
|
|
|
|
#define IS_APPEND(inode) ((inode)->i_flags & S_APPEND)
|
|
|
|
#define IS_IMMUTABLE(inode) ((inode)->i_flags & S_IMMUTABLE)
|
|
|
|
#define IS_POSIXACL(inode) __IS_FLG(inode, MS_POSIXACL)
|
|
|
|
|
|
|
|
#define IS_DEADDIR(inode) ((inode)->i_flags & S_DEAD)
|
|
|
|
#define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME)
|
|
|
|
#define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE)
|
|
|
|
#define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE)
|
|
|
|
#define IS_IMA(inode) ((inode)->i_flags & S_IMA)
|
|
|
|
#define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT)
|
|
|
|
#define IS_NOSEC(inode) ((inode)->i_flags & S_NOSEC)
|
|
|
|
|
2007-10-17 10:30:44 +04:00
|
|
|
/*
|
2011-03-22 14:23:36 +03:00
|
|
|
* Inode state bits. Protected by inode->i_lock
|
2007-10-17 10:30:44 +04:00
|
|
|
*
|
|
|
|
* 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.
|
|
|
|
*
|
2009-12-17 16:25:01 +03:00
|
|
|
* Two bits are used for locking and completion notification, I_NEW and I_SYNC.
|
2007-10-17 10:30:44 +04:00
|
|
|
*
|
2008-02-06 12:36:59 +03:00
|
|
|
* I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on
|
|
|
|
* fdatasync(). i_atime is the usual cause.
|
2008-02-15 06:31:32 +03:00
|
|
|
* 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.
|
2007-10-17 10:30:44 +04:00
|
|
|
* I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean.
|
2009-12-17 16:25:01 +03:00
|
|
|
* 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.
|
2007-10-17 10:30:44 +04:00
|
|
|
* 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.
|
2012-05-03 16:48:02 +04:00
|
|
|
* I_CLEAR Added by clear_inode(). In this state the inode is
|
|
|
|
* clean and can be destroyed. Inode keeps I_FREEING.
|
2007-10-17 10:30:44 +04:00
|
|
|
*
|
|
|
|
* 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,
|
2009-12-17 16:25:01 +03:00
|
|
|
* if appropriate. I_NEW is used for waiting.
|
2007-10-17 10:30:44 +04:00
|
|
|
*
|
2012-05-03 16:48:03 +04:00
|
|
|
* I_SYNC Writeback of inode is running. The bit is set during
|
|
|
|
* data writeback, and cleared with a wakeup on the bit
|
|
|
|
* address once it is done. The bit is also used to pin
|
|
|
|
* the inode in memory for flusher thread.
|
2007-10-17 10:30:44 +04:00
|
|
|
*
|
2011-06-24 22:29:43 +04:00
|
|
|
* I_REFERENCED Marks the inode as recently references on the LRU list.
|
|
|
|
*
|
|
|
|
* I_DIO_WAKEUP Never set. Only used as a key for wait_on_bit().
|
|
|
|
*
|
2007-10-17 10:30:44 +04:00
|
|
|
* Q: What is the difference between I_WILL_FREE and I_FREEING?
|
|
|
|
*/
|
2010-10-23 14:55:17 +04:00
|
|
|
#define I_DIRTY_SYNC (1 << 0)
|
|
|
|
#define I_DIRTY_DATASYNC (1 << 1)
|
|
|
|
#define I_DIRTY_PAGES (1 << 2)
|
2009-12-17 16:25:01 +03:00
|
|
|
#define __I_NEW 3
|
|
|
|
#define I_NEW (1 << __I_NEW)
|
2010-10-23 14:55:17 +04:00
|
|
|
#define I_WILL_FREE (1 << 4)
|
|
|
|
#define I_FREEING (1 << 5)
|
|
|
|
#define I_CLEAR (1 << 6)
|
2009-12-17 16:25:01 +03:00
|
|
|
#define __I_SYNC 7
|
2007-10-17 10:30:44 +04:00
|
|
|
#define I_SYNC (1 << __I_SYNC)
|
2010-10-23 14:55:17 +04:00
|
|
|
#define I_REFERENCED (1 << 8)
|
2011-06-24 22:29:43 +04:00
|
|
|
#define __I_DIO_WAKEUP 9
|
|
|
|
#define I_DIO_WAKEUP (1 << I_DIO_WAKEUP)
|
2013-06-11 08:34:36 +04:00
|
|
|
#define I_LINKABLE (1 << 10)
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
#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);
|
|
|
|
}
|
|
|
|
|
2011-11-21 15:11:32 +04:00
|
|
|
extern void inc_nlink(struct inode *inode);
|
|
|
|
extern void drop_nlink(struct inode *inode);
|
|
|
|
extern void clear_nlink(struct inode *inode);
|
|
|
|
extern void set_nlink(struct inode *inode, unsigned int nlink);
|
2006-10-01 10:29:04 +04:00
|
|
|
|
|
|
|
static inline void inode_inc_link_count(struct inode *inode)
|
|
|
|
{
|
|
|
|
inc_nlink(inode);
|
2006-03-23 14:00:51 +03:00
|
|
|
mark_inode_dirty(inode);
|
|
|
|
}
|
|
|
|
|
2006-10-01 10:29:03 +04:00
|
|
|
static inline void inode_dec_link_count(struct inode *inode)
|
|
|
|
{
|
|
|
|
drop_nlink(inode);
|
2006-03-23 14:00:51 +03:00
|
|
|
mark_inode_dirty(inode);
|
|
|
|
}
|
|
|
|
|
2008-01-29 07:58:27 +03:00
|
|
|
/**
|
|
|
|
* 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);
|
|
|
|
}
|
|
|
|
|
2012-03-26 17:59:21 +04:00
|
|
|
enum file_time_flags {
|
|
|
|
S_ATIME = 1,
|
|
|
|
S_MTIME = 2,
|
|
|
|
S_CTIME = 4,
|
|
|
|
S_VERSION = 8,
|
|
|
|
};
|
|
|
|
|
2013-07-16 18:15:46 +04:00
|
|
|
extern void touch_atime(const struct path *);
|
2005-04-17 02:20:36 +04:00
|
|
|
static inline void file_accessed(struct file *file)
|
|
|
|
{
|
|
|
|
if (!(file->f_flags & O_NOATIME))
|
2012-03-15 16:21:57 +04:00
|
|
|
touch_atime(&file->f_path);
|
2005-04-17 02:20:36 +04:00
|
|
|
}
|
|
|
|
|
|
|
|
int sync_inode(struct inode *inode, struct writeback_control *wbc);
|
2010-10-06 12:48:20 +04:00
|
|
|
int sync_inode_metadata(struct inode *inode, int wait);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
struct file_system_type {
|
|
|
|
const char *name;
|
|
|
|
int fs_flags;
|
2012-10-15 19:40:35 +04:00
|
|
|
#define FS_REQUIRES_DEV 1
|
|
|
|
#define FS_BINARY_MOUNTDATA 2
|
|
|
|
#define FS_HAS_SUBTYPE 4
|
2012-07-27 08:42:03 +04:00
|
|
|
#define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */
|
|
|
|
#define FS_USERNS_DEV_MOUNT 16 /* A userns mount does not imply MNT_NODEV */
|
2012-10-15 19:40:35 +04:00
|
|
|
#define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */
|
2010-07-25 00:17:56 +04:00
|
|
|
struct dentry *(*mount) (struct file_system_type *, int,
|
|
|
|
const char *, void *);
|
2005-04-17 02:20:36 +04:00
|
|
|
void (*kill_sb) (struct super_block *);
|
|
|
|
struct module *owner;
|
|
|
|
struct file_system_type * next;
|
2011-12-13 07:53:00 +04:00
|
|
|
struct hlist_head fs_supers;
|
2007-10-15 16:51:31 +04:00
|
|
|
|
2006-07-03 11:25:27 +04:00
|
|
|
struct lock_class_key s_lock_key;
|
2006-07-03 11:25:28 +04:00
|
|
|
struct lock_class_key s_umount_key;
|
2010-04-28 01:23:57 +04:00
|
|
|
struct lock_class_key s_vfs_rename_key;
|
2012-06-12 18:20:34 +04:00
|
|
|
struct lock_class_key s_writers_key[SB_FREEZE_LEVELS];
|
2007-10-15 16:51:31 +04:00
|
|
|
|
|
|
|
struct lock_class_key i_lock_key;
|
|
|
|
struct lock_class_key i_mutex_key;
|
2007-10-14 03:38:33 +04:00
|
|
|
struct lock_class_key i_mutex_dir_key;
|
2005-04-17 02:20:36 +04:00
|
|
|
};
|
|
|
|
|
2013-03-03 07:39:14 +04:00
|
|
|
#define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME)
|
|
|
|
|
2010-07-26 13:16:50 +04:00
|
|
|
extern struct dentry *mount_ns(struct file_system_type *fs_type, int flags,
|
|
|
|
void *data, int (*fill_super)(struct super_block *, void *, int));
|
2010-07-25 00:46:55 +04:00
|
|
|
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));
|
2010-07-25 01:48:30 +04:00
|
|
|
extern struct dentry *mount_single(struct file_system_type *fs_type,
|
|
|
|
int flags, void *data,
|
|
|
|
int (*fill_super)(struct super_block *, void *, int));
|
2010-07-25 11:46:36 +04:00
|
|
|
extern struct dentry *mount_nodev(struct file_system_type *fs_type,
|
|
|
|
int flags, void *data,
|
|
|
|
int (*fill_super)(struct super_block *, void *, int));
|
2011-11-17 06:43:59 +04:00
|
|
|
extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path);
|
2005-04-17 02:20:36 +04:00
|
|
|
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);
|
2009-05-06 09:07:50 +04:00
|
|
|
void deactivate_locked_super(struct super_block *sb);
|
2005-04-17 02:20:36 +04:00
|
|
|
int set_anon_super(struct super_block *s, void *data);
|
2011-07-07 23:44:25 +04:00
|
|
|
int get_anon_bdev(dev_t *);
|
|
|
|
void free_anon_bdev(dev_t);
|
2005-04-17 02:20:36 +04:00
|
|
|
struct super_block *sget(struct file_system_type *type,
|
|
|
|
int (*test)(struct super_block *,void *),
|
|
|
|
int (*set)(struct super_block *,void *),
|
2012-06-25 15:55:37 +04:00
|
|
|
int flags, void *data);
|
2010-07-25 23:47:46 +04:00
|
|
|
extern struct dentry *mount_pseudo(struct file_system_type *, char *,
|
2011-01-13 00:59:34 +03:00
|
|
|
const struct super_operations *ops,
|
|
|
|
const struct dentry_operations *dops,
|
|
|
|
unsigned long);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
/* 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 *);
|
2007-10-19 10:40:02 +04:00
|
|
|
extern struct vfsmount *kern_mount_data(struct file_system_type *, void *data);
|
|
|
|
#define kern_mount(type) kern_mount_data(type, NULL)
|
2011-07-19 20:32:38 +04:00
|
|
|
extern void kern_unmount(struct vfsmount *mnt);
|
2005-04-17 02:20:36 +04:00
|
|
|
extern int may_umount_tree(struct vfsmount *);
|
|
|
|
extern int may_umount(struct vfsmount *);
|
2012-10-11 19:42:01 +04:00
|
|
|
extern long do_mount(const char *, const char *, const char *, unsigned long, void *);
|
2009-04-18 11:28:19 +04:00
|
|
|
extern struct vfsmount *collect_mounts(struct path *);
|
2007-06-07 20:20:32 +04:00
|
|
|
extern void drop_collected_mounts(struct vfsmount *);
|
2010-01-31 06:51:25 +03:00
|
|
|
extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
|
|
|
|
struct vfsmount *);
|
2010-07-07 20:53:11 +04:00
|
|
|
extern int vfs_statfs(struct path *, struct kstatfs *);
|
2011-03-12 18:41:39 +03:00
|
|
|
extern int user_statfs(const char __user *, struct kstatfs *);
|
|
|
|
extern int fd_statfs(int, struct kstatfs *);
|
2012-01-03 07:28:36 +04:00
|
|
|
extern int vfs_ustat(dev_t, struct kstatfs *);
|
2010-03-23 17:34:56 +03:00
|
|
|
extern int freeze_super(struct super_block *super);
|
|
|
|
extern int thaw_super(struct super_block *super);
|
fix apparmor dereferencing potentially freed dentry, sanitize __d_path() API
__d_path() API is asking for trouble and in case of apparmor d_namespace_path()
getting just that. The root cause is that when __d_path() misses the root
it had been told to look for, it stores the location of the most remote ancestor
in *root. Without grabbing references. Sure, at the moment of call it had
been pinned down by what we have in *path. And if we raced with umount -l, we
could have very well stopped at vfsmount/dentry that got freed as soon as
prepend_path() dropped vfsmount_lock.
It is safe to compare these pointers with pre-existing (and known to be still
alive) vfsmount and dentry, as long as all we are asking is "is it the same
address?". Dereferencing is not safe and apparmor ended up stepping into
that. d_namespace_path() really wants to examine the place where we stopped,
even if it's not connected to our namespace. As the result, it looked
at ->d_sb->s_magic of a dentry that might've been already freed by that point.
All other callers had been careful enough to avoid that, but it's really
a bad interface - it invites that kind of trouble.
The fix is fairly straightforward, even though it's bigger than I'd like:
* prepend_path() root argument becomes const.
* __d_path() is never called with NULL/NULL root. It was a kludge
to start with. Instead, we have an explicit function - d_absolute_root().
Same as __d_path(), except that it doesn't get root passed and stops where
it stops. apparmor and tomoyo are using it.
* __d_path() returns NULL on path outside of root. The main
caller is show_mountinfo() and that's precisely what we pass root for - to
skip those outside chroot jail. Those who don't want that can (and do)
use d_path().
* __d_path() root argument becomes const. Everyone agrees, I hope.
* apparmor does *NOT* try to use __d_path() or any of its variants
when it sees that path->mnt is an internal vfsmount. In that case it's
definitely not mounted anywhere and dentry_path() is exactly what we want
there. Handling of sysctl()-triggered weirdness is moved to that place.
* if apparmor is asked to do pathname relative to chroot jail
and __d_path() tells it we it's not in that jail, the sucker just calls
d_absolute_path() instead. That's the other remaining caller of __d_path(),
BTW.
* seq_path_root() does _NOT_ return -ENAMETOOLONG (it's stupid anyway -
the normal seq_file logics will take care of growing the buffer and redoing
the call of ->show() just fine). However, if it gets path not reachable
from root, it returns SEQ_SKIP. The only caller adjusted (i.e. stopped
ignoring the return value as it used to do).
Reviewed-by: John Johansen <john.johansen@canonical.com>
ACKed-by: John Johansen <john.johansen@canonical.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Cc: stable@vger.kernel.org
2011-12-05 17:43:34 +04:00
|
|
|
extern bool our_mnt(struct vfsmount *mnt);
|
2013-03-31 06:57:41 +04:00
|
|
|
extern bool fs_fully_visible(struct file_system_type *);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2009-03-30 03:08:22 +04:00
|
|
|
extern int current_umask(void);
|
|
|
|
|
2006-01-17 09:14:23 +03:00
|
|
|
/* /sys/fs */
|
2007-10-29 23:17:23 +03:00
|
|
|
extern struct kobject *fs_kobj;
|
2006-01-17 09:14:23 +03:00
|
|
|
|
2010-10-29 21:36:49 +04:00
|
|
|
#define MAX_RW_COUNT (INT_MAX & PAGE_CACHE_MASK)
|
2008-08-06 17:12:22 +04:00
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
#define FLOCK_VERIFY_READ 1
|
|
|
|
#define FLOCK_VERIFY_WRITE 2
|
|
|
|
|
2008-08-06 17:12:22 +04:00
|
|
|
#ifdef CONFIG_FILE_LOCKING
|
2005-04-17 02:20:36 +04:00
|
|
|
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.
|
|
|
|
*/
|
2007-10-02 01:41:11 +04:00
|
|
|
|
|
|
|
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);
|
|
|
|
}
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
static inline int locks_verify_locked(struct inode *inode)
|
|
|
|
{
|
2007-10-02 01:41:11 +04:00
|
|
|
if (mandatory_lock(inode))
|
2005-04-17 02:20:36 +04:00
|
|
|
return locks_mandatory_locked(inode);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline int locks_verify_truncate(struct inode *inode,
|
|
|
|
struct file *filp,
|
|
|
|
loff_t size)
|
|
|
|
{
|
2007-10-02 01:41:11 +04:00
|
|
|
if (inode->i_flock && mandatory_lock(inode))
|
2005-04-17 02:20:36 +04:00
|
|
|
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;
|
|
|
|
}
|
2008-08-06 17:12:22 +04:00
|
|
|
#else /* !CONFIG_FILE_LOCKING */
|
2009-01-20 13:29:46 +03:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2008-08-06 17:12:22 +04:00
|
|
|
#endif /* CONFIG_FILE_LOCKING */
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
/* fs/open.c */
|
2012-10-11 00:43:13 +04:00
|
|
|
struct audit_names;
|
2012-10-10 23:25:28 +04:00
|
|
|
struct filename {
|
2012-10-11 00:43:13 +04:00
|
|
|
const char *name; /* pointer to actual string */
|
|
|
|
const __user char *uptr; /* original userland pointer */
|
|
|
|
struct audit_names *aname;
|
2012-10-11 00:43:13 +04:00
|
|
|
bool separate; /* should "name" be freed? */
|
2012-10-10 23:25:28 +04:00
|
|
|
};
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2012-12-21 01:52:36 +04:00
|
|
|
extern long vfs_truncate(struct path *, loff_t);
|
2006-01-08 12:02:39 +03:00
|
|
|
extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs,
|
|
|
|
struct file *filp);
|
2009-06-19 22:28:07 +04:00
|
|
|
extern int do_fallocate(struct file *file, int mode, loff_t offset,
|
|
|
|
loff_t len);
|
2007-10-20 05:16:18 +04:00
|
|
|
extern long do_sys_open(int dfd, const char __user *filename, int flags,
|
2011-11-21 23:59:34 +04:00
|
|
|
umode_t mode);
|
2012-10-11 00:43:10 +04:00
|
|
|
extern struct file *file_open_name(struct filename *, int, umode_t);
|
2011-11-21 23:59:34 +04:00
|
|
|
extern struct file *filp_open(const char *, int, umode_t);
|
2011-03-11 20:08:24 +03:00
|
|
|
extern struct file *file_open_root(struct dentry *, struct vfsmount *,
|
|
|
|
const char *, int);
|
2012-06-26 21:58:53 +04:00
|
|
|
extern struct file * dentry_open(const struct path *, int, const struct cred *);
|
2005-04-17 02:20:36 +04:00
|
|
|
extern int filp_close(struct file *, fl_owner_t id);
|
2012-10-10 23:25:28 +04:00
|
|
|
|
|
|
|
extern struct filename *getname(const char __user *);
|
|
|
|
|
2012-06-10 13:01:45 +04:00
|
|
|
enum {
|
|
|
|
FILE_CREATED = 1,
|
|
|
|
FILE_OPENED = 2
|
|
|
|
};
|
2012-06-22 12:40:19 +04:00
|
|
|
extern int finish_open(struct file *file, struct dentry *dentry,
|
|
|
|
int (*open)(struct inode *, struct file *),
|
|
|
|
int *opened);
|
2012-06-10 14:48:09 +04:00
|
|
|
extern int finish_no_open(struct file *file, struct dentry *dentry);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2009-06-19 22:28:07 +04:00
|
|
|
/* fs/ioctl.c */
|
|
|
|
|
|
|
|
extern int ioctl_preallocate(struct file *filp, void __user *argp);
|
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
/* fs/dcache.c */
|
|
|
|
extern void __init vfs_caches_init_early(void);
|
|
|
|
extern void __init vfs_caches_init(unsigned long);
|
|
|
|
|
2006-12-07 07:32:57 +03:00
|
|
|
extern struct kmem_cache *names_cachep;
|
|
|
|
|
2012-10-10 23:25:28 +04:00
|
|
|
extern void final_putname(struct filename *name);
|
|
|
|
|
2012-10-10 23:25:26 +04:00
|
|
|
#define __getname() kmem_cache_alloc(names_cachep, GFP_KERNEL)
|
2009-05-16 13:22:14 +04:00
|
|
|
#define __putname(name) kmem_cache_free(names_cachep, (void *)(name))
|
2005-04-17 02:20:36 +04:00
|
|
|
#ifndef CONFIG_AUDITSYSCALL
|
2012-10-10 23:25:28 +04:00
|
|
|
#define putname(name) final_putname(name)
|
2005-04-17 02:20:36 +04:00
|
|
|
#else
|
2012-10-10 23:25:28 +04:00
|
|
|
extern void putname(struct filename *name);
|
2005-04-17 02:20:36 +04:00
|
|
|
#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
|
2005-04-17 02:20:36 +04:00
|
|
|
extern int register_blkdev(unsigned int, const char *);
|
2007-07-17 15:03:47 +04:00
|
|
|
extern void unregister_blkdev(unsigned int, const char *);
|
2005-04-17 02:20:36 +04:00
|
|
|
extern struct block_device *bdget(dev_t);
|
2009-07-29 23:07:55 +04:00
|
|
|
extern struct block_device *bdgrab(struct block_device *bdev);
|
2005-04-17 02:20:36 +04:00
|
|
|
extern void bd_set_size(struct block_device *, loff_t size);
|
|
|
|
extern void bd_forget(struct inode *inode);
|
|
|
|
extern void bdput(struct block_device *);
|
2009-02-25 12:44:19 +03:00
|
|
|
extern void invalidate_bdev(struct block_device *);
|
2012-07-03 18:45:31 +04:00
|
|
|
extern void iterate_bdevs(void (*)(struct block_device *, void *), void *);
|
2009-02-25 12:44:19 +03:00
|
|
|
extern int sync_blockdev(struct block_device *bdev);
|
2011-09-16 10:31:11 +04:00
|
|
|
extern void kill_bdev(struct block_device *);
|
2009-02-25 12:44:19 +03:00
|
|
|
extern struct super_block *freeze_bdev(struct block_device *);
|
2009-04-01 02:23:46 +04:00
|
|
|
extern void emergency_thaw_all(void);
|
2009-02-25 12:44:19 +03:00
|
|
|
extern int thaw_bdev(struct block_device *bdev, struct super_block *sb);
|
|
|
|
extern int fsync_bdev(struct block_device *);
|
2013-07-09 18:36:45 +04:00
|
|
|
extern int sb_is_blkdev_sb(struct super_block *sb);
|
[PATCH] BLOCK: Make it possible to disable the block layer [try #6]
Make it possible to disable the block layer. Not all embedded devices require
it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require
the block layer to be present.
This patch does the following:
(*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev
support.
(*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls
an item that uses the block layer. This includes:
(*) Block I/O tracing.
(*) Disk partition code.
(*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS.
(*) The SCSI layer. As far as I can tell, even SCSI chardevs use the
block layer to do scheduling. Some drivers that use SCSI facilities -
such as USB storage - end up disabled indirectly from this.
(*) Various block-based device drivers, such as IDE and the old CDROM
drivers.
(*) MTD blockdev handling and FTL.
(*) JFFS - which uses set_bdev_super(), something it could avoid doing by
taking a leaf out of JFFS2's book.
(*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and
linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is,
however, still used in places, and so is still available.
(*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and
parts of linux/fs.h.
(*) Makes a number of files in fs/ contingent on CONFIG_BLOCK.
(*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK.
(*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK
is not enabled.
(*) fs/no-block.c is created to hold out-of-line stubs and things that are
required when CONFIG_BLOCK is not set:
(*) Default blockdev file operations (to give error ENODEV on opening).
(*) Makes some /proc changes:
(*) /proc/devices does not list any blockdevs.
(*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK.
(*) Makes some compat ioctl handling contingent on CONFIG_BLOCK.
(*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if
given command other than Q_SYNC or if a special device is specified.
(*) In init/do_mounts.c, no reference is made to the blockdev routines if
CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2.
(*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return
error ENOSYS by way of cond_syscall if so).
(*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if
CONFIG_BLOCK is not set, since they can't then happen.
Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-09-30 22:45:40 +04:00
|
|
|
#else
|
|
|
|
static inline void bd_forget(struct inode *inode) {}
|
2009-04-01 15:07:16 +04:00
|
|
|
static inline int sync_blockdev(struct block_device *bdev) { return 0; }
|
2011-09-16 10:31:11 +04:00
|
|
|
static inline void kill_bdev(struct block_device *bdev) {}
|
2009-04-01 15:07:16 +04:00
|
|
|
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;
|
|
|
|
}
|
2012-07-03 18:45:31 +04:00
|
|
|
|
|
|
|
static inline void iterate_bdevs(void (*f)(struct block_device *, void *), void *arg)
|
|
|
|
{
|
|
|
|
}
|
2013-07-09 18:36:45 +04:00
|
|
|
|
|
|
|
static inline int sb_is_blkdev_sb(struct super_block *sb)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
[PATCH] BLOCK: Make it possible to disable the block layer [try #6]
Make it possible to disable the block layer. Not all embedded devices require
it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require
the block layer to be present.
This patch does the following:
(*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev
support.
(*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls
an item that uses the block layer. This includes:
(*) Block I/O tracing.
(*) Disk partition code.
(*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS.
(*) The SCSI layer. As far as I can tell, even SCSI chardevs use the
block layer to do scheduling. Some drivers that use SCSI facilities -
such as USB storage - end up disabled indirectly from this.
(*) Various block-based device drivers, such as IDE and the old CDROM
drivers.
(*) MTD blockdev handling and FTL.
(*) JFFS - which uses set_bdev_super(), something it could avoid doing by
taking a leaf out of JFFS2's book.
(*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and
linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is,
however, still used in places, and so is still available.
(*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and
parts of linux/fs.h.
(*) Makes a number of files in fs/ contingent on CONFIG_BLOCK.
(*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK.
(*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK
is not enabled.
(*) fs/no-block.c is created to hold out-of-line stubs and things that are
required when CONFIG_BLOCK is not set:
(*) Default blockdev file operations (to give error ENODEV on opening).
(*) Makes some /proc changes:
(*) /proc/devices does not list any blockdevs.
(*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK.
(*) Makes some compat ioctl handling contingent on CONFIG_BLOCK.
(*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if
given command other than Q_SYNC or if a special device is specified.
(*) In init/do_mounts.c, no reference is made to the blockdev routines if
CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2.
(*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return
error ENOSYS by way of cond_syscall if so).
(*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if
CONFIG_BLOCK is not set, since they can't then happen.
Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-09-30 22:45:40 +04:00
|
|
|
#endif
|
2009-04-27 18:43:53 +04:00
|
|
|
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;
|
2006-03-28 13:56:42 +04:00
|
|
|
extern const struct file_operations def_chr_fops;
|
|
|
|
extern const struct file_operations bad_sock_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
|
2005-04-17 02:20:36 +04:00
|
|
|
extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long);
|
2008-09-19 11:17:36 +04:00
|
|
|
extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long);
|
2005-04-17 02:20:36 +04:00
|
|
|
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);
|
2010-11-13 13:55:18 +03:00
|
|
|
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);
|
2013-05-06 06:11:03 +04:00
|
|
|
extern void blkdev_put(struct block_device *bdev, fmode_t mode);
|
2006-03-27 13:17:57 +04:00
|
|
|
#ifdef CONFIG_SYSFS
|
2010-11-13 13:55:17 +03:00
|
|
|
extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk);
|
2011-01-14 20:43:57 +03:00
|
|
|
extern void bd_unlink_disk_holder(struct block_device *bdev,
|
|
|
|
struct gendisk *disk);
|
2006-03-27 13:17:57 +04:00
|
|
|
#else
|
2010-11-13 13:55:17 +03:00
|
|
|
static inline int bd_link_disk_holder(struct block_device *bdev,
|
|
|
|
struct gendisk *disk)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
2011-01-14 20:43:57 +03:00
|
|
|
static inline void bd_unlink_disk_holder(struct block_device *bdev,
|
|
|
|
struct gendisk *disk)
|
|
|
|
{
|
|
|
|
}
|
2006-03-27 13:17:57 +04:00
|
|
|
#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
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
/* fs/char_dev.c */
|
2006-03-31 14:30:32 +04:00
|
|
|
#define CHRDEV_MAJOR_HASH_SIZE 255
|
2005-04-17 02:20:36 +04:00
|
|
|
extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *);
|
|
|
|
extern int register_chrdev_region(dev_t, unsigned, const char *);
|
2009-08-06 13:13:23 +04:00
|
|
|
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);
|
2005-04-17 02:20:36 +04:00
|
|
|
extern void unregister_chrdev_region(dev_t, unsigned);
|
2006-03-31 14:30:32 +04:00
|
|
|
extern void chrdev_show(struct seq_file *,off_t);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2009-08-06 13:13:23 +04:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
/* fs/block_dev.c */
|
|
|
|
#define BDEVNAME_SIZE 32 /* Largest string for a blockdev identifier */
|
2008-08-25 14:47:23 +04:00
|
|
|
#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
|
2005-04-17 02:20:36 +04:00
|
|
|
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 *);
|
2006-03-31 14:30:32 +04:00
|
|
|
extern void blkdev_show(struct seq_file *,off_t);
|
2008-02-23 03:50:45 +03:00
|
|
|
|
[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
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
extern void init_special_inode(struct inode *, umode_t, dev_t);
|
|
|
|
|
|
|
|
/* Invalid inode operations -- fs/bad_inode.c */
|
|
|
|
extern void make_bad_inode(struct inode *);
|
|
|
|
extern int is_bad_inode(struct inode *);
|
|
|
|
|
[PATCH] BLOCK: Make it possible to disable the block layer [try #6]
Make it possible to disable the block layer. Not all embedded devices require
it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require
the block layer to be present.
This patch does the following:
(*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev
support.
(*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls
an item that uses the block layer. This includes:
(*) Block I/O tracing.
(*) Disk partition code.
(*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS.
(*) The SCSI layer. As far as I can tell, even SCSI chardevs use the
block layer to do scheduling. Some drivers that use SCSI facilities -
such as USB storage - end up disabled indirectly from this.
(*) Various block-based device drivers, such as IDE and the old CDROM
drivers.
(*) MTD blockdev handling and FTL.
(*) JFFS - which uses set_bdev_super(), something it could avoid doing by
taking a leaf out of JFFS2's book.
(*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and
linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is,
however, still used in places, and so is still available.
(*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and
parts of linux/fs.h.
(*) Makes a number of files in fs/ contingent on CONFIG_BLOCK.
(*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK.
(*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK
is not enabled.
(*) fs/no-block.c is created to hold out-of-line stubs and things that are
required when CONFIG_BLOCK is not set:
(*) Default blockdev file operations (to give error ENODEV on opening).
(*) Makes some /proc changes:
(*) /proc/devices does not list any blockdevs.
(*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK.
(*) Makes some compat ioctl handling contingent on CONFIG_BLOCK.
(*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if
given command other than Q_SYNC or if a special device is specified.
(*) In init/do_mounts.c, no reference is made to the blockdev routines if
CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2.
(*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return
error ENOSYS by way of cond_syscall if so).
(*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if
CONFIG_BLOCK is not set, since they can't then happen.
Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-09-30 22:45:40 +04:00
|
|
|
#ifdef CONFIG_BLOCK
|
2005-04-17 02:20:36 +04:00
|
|
|
/*
|
|
|
|
* 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)
|
|
|
|
|
2008-09-05 00:27:25 +04:00
|
|
|
extern void check_disk_size_change(struct gendisk *disk,
|
|
|
|
struct block_device *bdev);
|
2008-09-05 00:27:20 +04:00
|
|
|
extern int revalidate_disk(struct gendisk *);
|
2005-04-17 02:20:36 +04:00
|
|
|
extern int check_disk_change(struct block_device *);
|
2011-02-24 09:25:47 +03:00
|
|
|
extern int __invalidate_device(struct block_device *, bool);
|
2005-04-17 02:20:36 +04:00
|
|
|
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
|
2005-04-17 02:20:36 +04:00
|
|
|
unsigned long invalidate_mapping_pages(struct address_space *mapping,
|
|
|
|
pgoff_t start, pgoff_t end);
|
2007-02-10 12:45:38 +03:00
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
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))
|
2007-02-10 12:45:39 +03:00
|
|
|
invalidate_mapping_pages(inode->i_mapping, 0, -1);
|
2005-04-17 02:20:36 +04:00
|
|
|
}
|
|
|
|
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 *);
|
2009-08-17 21:30:27 +04:00
|
|
|
extern int filemap_fdatawait_range(struct address_space *, loff_t lstart,
|
|
|
|
loff_t lend);
|
2005-04-17 02:20:36 +04:00
|
|
|
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);
|
2008-07-12 03:27:31 +04:00
|
|
|
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
|
|
|
|
2010-03-22 19:32:25 +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);
|
2009-08-17 21:52:36 +04:00
|
|
|
extern int generic_write_sync(struct file *file, loff_t pos, loff_t count);
|
2005-04-17 02:20:36 +04:00
|
|
|
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
|
2005-04-17 02:20:36 +04:00
|
|
|
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
|
2005-04-17 02:20:36 +04:00
|
|
|
extern int notify_change(struct dentry *, struct iattr *);
|
2008-07-22 08:07:17 +04:00
|
|
|
extern int inode_permission(struct inode *, int);
|
2011-06-21 03:16:29 +04:00
|
|
|
extern int generic_permission(struct inode *, int);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2008-07-31 15:41:58 +04:00
|
|
|
static inline bool execute_ok(struct inode *inode)
|
|
|
|
{
|
|
|
|
return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode);
|
|
|
|
}
|
|
|
|
|
2013-01-24 02:07:38 +04:00
|
|
|
static inline struct inode *file_inode(struct file *f)
|
|
|
|
{
|
2013-03-02 04:48:30 +04:00
|
|
|
return f->f_inode;
|
2013-01-24 02:07:38 +04:00
|
|
|
}
|
|
|
|
|
2013-03-20 05:01:03 +04:00
|
|
|
static inline void file_start_write(struct file *file)
|
|
|
|
{
|
|
|
|
if (!S_ISREG(file_inode(file)->i_mode))
|
|
|
|
return;
|
|
|
|
__sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true);
|
|
|
|
}
|
|
|
|
|
2013-05-04 02:11:23 +04:00
|
|
|
static inline bool file_start_write_trylock(struct file *file)
|
|
|
|
{
|
|
|
|
if (!S_ISREG(file_inode(file)->i_mode))
|
|
|
|
return true;
|
|
|
|
return __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, false);
|
|
|
|
}
|
|
|
|
|
2013-03-20 05:01:03 +04:00
|
|
|
static inline void file_end_write(struct file *file)
|
|
|
|
{
|
|
|
|
if (!S_ISREG(file_inode(file)->i_mode))
|
|
|
|
return;
|
|
|
|
__sb_end_write(file_inode(file)->i_sb, SB_FREEZE_WRITE);
|
|
|
|
}
|
|
|
|
|
2011-06-20 18:52:57 +04:00
|
|
|
/*
|
|
|
|
* get_write_access() gets write permission for a file.
|
|
|
|
* put_write_access() releases this write permission.
|
|
|
|
* This is used for regular files.
|
|
|
|
* We cannot support write (and maybe mmap read-write shared) accesses and
|
|
|
|
* MAP_DENYWRITE mmappings simultaneously. The i_writecount field of an inode
|
|
|
|
* can have the following values:
|
|
|
|
* 0: no writers, no VM_DENYWRITE mappings
|
|
|
|
* < 0: (-i_writecount) vm_area_structs with VM_DENYWRITE set exist
|
|
|
|
* > 0: (i_writecount) users are writing to the file.
|
|
|
|
*
|
|
|
|
* Normally we operate on that counter with atomic_{inc,dec} and it's safe
|
|
|
|
* except for the cases where we don't hold i_writecount yet. Then we need to
|
|
|
|
* use {get,deny}_write_access() - these functions check the sign and refuse
|
|
|
|
* to do the change if sign is wrong.
|
|
|
|
*/
|
|
|
|
static inline int get_write_access(struct inode *inode)
|
|
|
|
{
|
|
|
|
return atomic_inc_unless_negative(&inode->i_writecount) ? 0 : -ETXTBSY;
|
|
|
|
}
|
|
|
|
static inline int deny_write_access(struct file *file)
|
|
|
|
{
|
2013-01-24 02:07:38 +04:00
|
|
|
struct inode *inode = file_inode(file);
|
2011-06-20 18:52:57 +04:00
|
|
|
return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY;
|
|
|
|
}
|
2005-04-17 02:20:36 +04:00
|
|
|
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)
|
2013-01-24 02:07:38 +04:00
|
|
|
atomic_inc(&file_inode(file)->i_writecount);
|
2005-04-17 02:20:36 +04:00
|
|
|
}
|
2010-11-02 17:11:37 +03:00
|
|
|
#ifdef CONFIG_IMA
|
|
|
|
static inline void i_readcount_dec(struct inode *inode)
|
|
|
|
{
|
|
|
|
BUG_ON(!atomic_read(&inode->i_readcount));
|
|
|
|
atomic_dec(&inode->i_readcount);
|
|
|
|
}
|
|
|
|
static inline void i_readcount_inc(struct inode *inode)
|
|
|
|
{
|
|
|
|
atomic_inc(&inode->i_readcount);
|
|
|
|
}
|
|
|
|
#else
|
|
|
|
static inline void i_readcount_dec(struct inode *inode)
|
|
|
|
{
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
static inline void i_readcount_inc(struct inode *inode)
|
|
|
|
{
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
#endif
|
2008-07-24 08:29:30 +04:00
|
|
|
extern int do_pipe_flags(int *, int);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2009-08-21 22:32:48 +04:00
|
|
|
extern int kernel_read(struct file *, loff_t, char *, unsigned long);
|
2013-02-23 23:51:48 +04:00
|
|
|
extern ssize_t kernel_write(struct file *, const char *, size_t, loff_t);
|
2005-04-17 02:20:36 +04:00
|
|
|
extern struct file * open_exec(const char *);
|
|
|
|
|
|
|
|
/* fs/dcache.c -- generic fs support functions */
|
|
|
|
extern int is_subdir(struct dentry *, struct dentry *);
|
2010-01-30 21:16:21 +03:00
|
|
|
extern int path_is_under(struct path *, struct path *);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
#include <linux/err.h>
|
|
|
|
|
|
|
|
/* needed for stackable file system support */
|
2012-12-18 03:59:39 +04:00
|
|
|
extern loff_t default_llseek(struct file *file, loff_t offset, int whence);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2012-12-18 03:59:39 +04:00
|
|
|
extern loff_t vfs_llseek(struct file *file, loff_t offset, int whence);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2009-08-07 21:38:25 +04:00
|
|
|
extern int inode_init_always(struct super_block *, struct inode *);
|
2005-04-17 02:20:36 +04:00
|
|
|
extern void inode_init_once(struct inode *);
|
2011-02-23 15:49:47 +03:00
|
|
|
extern void address_space_init_once(struct address_space *mapping);
|
2010-10-23 19:11:40 +04:00
|
|
|
extern void ihold(struct inode * inode);
|
2005-04-17 02:20:36 +04:00
|
|
|
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);
|
2010-06-07 21:43:19 +04:00
|
|
|
extern int generic_delete_inode(struct inode *inode);
|
2012-02-13 04:43:17 +04:00
|
|
|
static inline int generic_drop_inode(struct inode *inode)
|
|
|
|
{
|
|
|
|
return !inode->i_nlink || inode_unhashed(inode);
|
|
|
|
}
|
2005-04-17 02:20:36 +04:00
|
|
|
|
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);
|
2005-04-17 02:20:36 +04:00
|
|
|
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);
|
2008-12-30 09:48:21 +03:00
|
|
|
extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *);
|
|
|
|
extern int insert_inode_locked(struct inode *);
|
lockdep: Add helper function for dir vs file i_mutex annotation
Purely in-memory filesystems do not use the inode hash as the dcache
tells us if an entry already exists. As a result, they do not call
unlock_new_inode, and thus directory inodes do not get put into a
different lockdep class for i_sem.
We need the different lockdep classes, because the locking order for
i_mutex is different for directory inodes and regular inodes. Directory
inodes can do "readdir()", which takes i_mutex *before* possibly taking
mm->mmap_sem (due to a page fault while copying the directory entry to
user space).
In contrast, regular inodes can be mmap'ed, which takes mm->mmap_sem
before accessing i_mutex.
The two cases can never happen for the same inode, so no real deadlock
can occur, but without the different lockdep classes, lockdep cannot
understand that. As a result, if CONFIG_DEBUG_LOCK_ALLOC is set, this
can lead to false positives from lockdep like below:
find/645 is trying to acquire lock:
(&mm->mmap_sem){++++++}, at: [<ffffffff81109514>] might_fault+0x5c/0xac
but task is already holding lock:
(&sb->s_type->i_mutex_key#15){+.+.+.}, at: [<ffffffff81149f34>]
vfs_readdir+0x5b/0xb4
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #1 (&sb->s_type->i_mutex_key#15){+.+.+.}:
[<ffffffff8108ac26>] lock_acquire+0xbf/0x103
[<ffffffff814db822>] __mutex_lock_common+0x4c/0x361
[<ffffffff814dbc46>] mutex_lock_nested+0x40/0x45
[<ffffffff811daa87>] hugetlbfs_file_mmap+0x82/0x110
[<ffffffff81111557>] mmap_region+0x258/0x432
[<ffffffff811119dd>] do_mmap_pgoff+0x2ac/0x306
[<ffffffff81111b4f>] sys_mmap_pgoff+0x118/0x16a
[<ffffffff8100c858>] sys_mmap+0x22/0x24
[<ffffffff814e3ec2>] system_call_fastpath+0x16/0x1b
-> #0 (&mm->mmap_sem){++++++}:
[<ffffffff8108a4bc>] __lock_acquire+0xa1a/0xcf7
[<ffffffff8108ac26>] lock_acquire+0xbf/0x103
[<ffffffff81109541>] might_fault+0x89/0xac
[<ffffffff81149cff>] filldir+0x6f/0xc7
[<ffffffff811586ea>] dcache_readdir+0x67/0x205
[<ffffffff81149f54>] vfs_readdir+0x7b/0xb4
[<ffffffff8114a073>] sys_getdents+0x7e/0xd1
[<ffffffff814e3ec2>] system_call_fastpath+0x16/0x1b
This patch moves the directory vs file lockdep annotation into a helper
function that can be called by in-memory filesystems and has hugetlbfs
call it.
Signed-off-by: Josh Boyer <jwboyer@redhat.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-08-25 15:48:12 +04:00
|
|
|
#ifdef CONFIG_DEBUG_LOCK_ALLOC
|
|
|
|
extern void lockdep_annotate_inode_mutex_key(struct inode *inode);
|
|
|
|
#else
|
|
|
|
static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { };
|
|
|
|
#endif
|
2005-04-17 02:20:36 +04:00
|
|
|
extern void unlock_new_inode(struct inode *);
|
2010-10-23 19:19:54 +04:00
|
|
|
extern unsigned int get_next_ino(void);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
extern void __iget(struct inode * inode);
|
2008-02-07 11:15:27 +03:00
|
|
|
extern void iget_failed(struct inode *);
|
2012-05-03 16:48:02 +04:00
|
|
|
extern void clear_inode(struct inode *);
|
2009-08-07 21:38:29 +04:00
|
|
|
extern void __destroy_inode(struct inode *);
|
2011-07-26 13:36:34 +04:00
|
|
|
extern struct inode *new_inode_pseudo(struct super_block *sb);
|
|
|
|
extern struct inode *new_inode(struct super_block *sb);
|
2011-01-07 09:49:50 +03:00
|
|
|
extern void free_inode_nonrcu(struct inode *inode);
|
2006-10-17 21:50:36 +04:00
|
|
|
extern int should_remove_suid(struct dentry *);
|
2008-06-24 18:50:14 +04:00
|
|
|
extern int file_remove_suid(struct file *);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
extern void __insert_inode_hash(struct inode *, unsigned long hashval);
|
2010-10-23 15:15:32 +04:00
|
|
|
static inline void insert_inode_hash(struct inode *inode)
|
|
|
|
{
|
2005-04-17 02:20:36 +04:00
|
|
|
__insert_inode_hash(inode, inode->i_ino);
|
|
|
|
}
|
2011-07-28 08:41:09 +04:00
|
|
|
|
|
|
|
extern void __remove_inode_hash(struct inode *);
|
|
|
|
static inline void remove_inode_hash(struct inode *inode)
|
|
|
|
{
|
|
|
|
if (!inode_unhashed(inode))
|
|
|
|
__remove_inode_hash(inode);
|
|
|
|
}
|
|
|
|
|
2010-10-23 15:15:32 +04:00
|
|
|
extern void inode_sb_list_add(struct inode *inode);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
[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
|
2005-04-17 02:20:36 +04:00
|
|
|
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
|
2005-04-17 02:20:36 +04:00
|
|
|
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 *);
|
2012-10-09 03:28:46 +04:00
|
|
|
extern int generic_file_remap_pages(struct vm_area_struct *, unsigned long addr,
|
|
|
|
unsigned long size, pgoff_t pgoff);
|
2005-04-17 02:20:36 +04:00
|
|
|
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);
|
2006-10-01 10:28:46 +04:00
|
|
|
extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t);
|
2009-08-17 20:10:06 +04:00
|
|
|
extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long,
|
|
|
|
loff_t *);
|
2006-10-01 10:28:46 +04:00
|
|
|
extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t);
|
2005-04-17 02:20:36 +04:00
|
|
|
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);
|
2007-05-08 11:23:02 +04:00
|
|
|
extern int generic_segment_checks(const struct iovec *iov,
|
|
|
|
unsigned long *nr_segs, size_t *count, int access_flags);
|
2006-04-11 15:59:36 +04:00
|
|
|
|
2009-08-20 19:43:41 +04:00
|
|
|
/* fs/block_dev.c */
|
|
|
|
extern ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
|
|
|
|
unsigned long nr_segs, loff_t pos);
|
2011-07-17 04:44:56 +04:00
|
|
|
extern int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
|
|
|
|
int datasync);
|
2011-09-16 10:31:11 +04:00
|
|
|
extern void block_sync_page(struct page *page);
|
2009-08-20 19:43:41 +04:00
|
|
|
|
2006-04-11 15:59:36 +04:00
|
|
|
/* fs/splice.c */
|
2006-04-11 16:57:50 +04:00
|
|
|
extern ssize_t generic_file_splice_read(struct file *, loff_t *,
|
2006-04-11 15:59:36 +04:00
|
|
|
struct pipe_inode_info *, size_t, unsigned int);
|
2009-05-07 17:37:36 +04:00
|
|
|
extern ssize_t default_file_splice_read(struct file *, loff_t *,
|
|
|
|
struct pipe_inode_info *, size_t, unsigned int);
|
2006-04-11 15:59:36 +04:00
|
|
|
extern ssize_t generic_file_splice_write(struct pipe_inode_info *,
|
2006-04-11 16:57:50 +04:00
|
|
|
struct file *, loff_t *, size_t, unsigned int);
|
2006-04-11 15:59:36 +04:00
|
|
|
extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
|
2006-04-11 16:57:50 +04:00
|
|
|
struct file *out, loff_t *, size_t len, unsigned int flags);
|
2006-04-11 15:59:36 +04:00
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
extern void
|
|
|
|
file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping);
|
2012-12-18 03:59:39 +04:00
|
|
|
extern loff_t noop_llseek(struct file *file, loff_t offset, int whence);
|
|
|
|
extern loff_t no_llseek(struct file *file, loff_t offset, int whence);
|
2013-06-25 08:02:13 +04:00
|
|
|
extern loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize);
|
2012-12-18 03:59:39 +04:00
|
|
|
extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence);
|
2011-09-16 03:06:50 +04:00
|
|
|
extern loff_t generic_file_llseek_size(struct file *file, loff_t offset,
|
2012-12-18 03:59:39 +04:00
|
|
|
int whence, loff_t maxsize, loff_t eof);
|
2013-06-16 20:27:42 +04:00
|
|
|
extern loff_t fixed_size_llseek(struct file *file, loff_t offset,
|
|
|
|
int whence, loff_t size);
|
2005-04-17 02:20:36 +04:00
|
|
|
extern int generic_file_open(struct inode * inode, struct file * filp);
|
|
|
|
extern int nonseekable_open(struct inode * inode, struct file * filp);
|
|
|
|
|
2005-06-24 09:05:25 +04:00
|
|
|
#ifdef CONFIG_FS_XIP
|
2005-06-24 09:05:28 +04:00
|
|
|
extern ssize_t xip_file_read(struct file *filp, char __user *buf, size_t len,
|
|
|
|
loff_t *ppos);
|
2005-06-24 09:05:25 +04:00
|
|
|
extern int xip_file_mmap(struct file * file, struct vm_area_struct * vma);
|
2005-06-24 09:05:28 +04:00
|
|
|
extern ssize_t xip_file_write(struct file *filp, const char __user *buf,
|
|
|
|
size_t len, loff_t *ppos);
|
2005-06-24 09:05:25 +04:00
|
|
|
extern int xip_truncate_page(struct address_space *mapping, loff_t from);
|
2005-06-24 09:05:26 +04:00
|
|
|
#else
|
|
|
|
static inline int xip_truncate_page(struct address_space *mapping, loff_t from)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
2005-06-24 09:05:25 +04:00
|
|
|
#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
|
2010-05-23 19:00:55 +04:00
|
|
|
typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode,
|
|
|
|
loff_t file_offset);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
enum {
|
cleanup blockdev_direct_IO locking
Currently the locking in blockdev_direct_IO is a mess, we have three different
locking types and very confusing checks for some of them. The most
complicated one is DIO_OWN_LOCKING for reads, which happens to not actually be
used.
This patch gets rid of the DIO_OWN_LOCKING - as mentioned above the read case
is unused anyway, and the write side is almost identical to DIO_NO_LOCKING.
The difference is that DIO_NO_LOCKING always sets the create argument for
the get_blocks callback to zero, but we can easily move that to the actual
get_blocks callbacks. There are four users of the DIO_NO_LOCKING mode:
gfs already ignores the create argument and thus is fine with the new
version, ocfs2 only errors out if create were ever set, and we can remove
this dead code now, the block device code only ever uses create for an
error message if we are fully beyond the device which can never happen,
and last but not least XFS will need the new behavour for writes.
Now we can replace the lock_type variable with a flags one, where no flag
means the DIO_NO_LOCKING behaviour and DIO_LOCKING is kept as the first
flag. Separate out the check for not allowing to fill holes into a separate
flag, although for now both flags always get set at the same time.
Also revamp the documentation of the locking scheme to actually make sense.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2009-11-03 18:44:53 +03:00
|
|
|
/* need locking between buffered and direct access */
|
|
|
|
DIO_LOCKING = 0x01,
|
|
|
|
|
|
|
|
/* filesystem does not support filling holes */
|
|
|
|
DIO_SKIP_HOLES = 0x02,
|
2005-04-17 02:20:36 +04:00
|
|
|
};
|
|
|
|
|
2010-06-04 13:29:53 +04:00
|
|
|
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
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb,
|
2011-06-24 22:29:47 +04:00
|
|
|
struct inode *inode, const struct iovec *iov, loff_t offset,
|
|
|
|
unsigned long nr_segs, get_block_t get_block)
|
2005-04-17 02:20:36 +04:00
|
|
|
{
|
2011-06-24 22:29:47 +04:00
|
|
|
return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
|
|
|
|
offset, nr_segs, get_block, NULL, NULL,
|
cleanup blockdev_direct_IO locking
Currently the locking in blockdev_direct_IO is a mess, we have three different
locking types and very confusing checks for some of them. The most
complicated one is DIO_OWN_LOCKING for reads, which happens to not actually be
used.
This patch gets rid of the DIO_OWN_LOCKING - as mentioned above the read case
is unused anyway, and the write side is almost identical to DIO_NO_LOCKING.
The difference is that DIO_NO_LOCKING always sets the create argument for
the get_blocks callback to zero, but we can easily move that to the actual
get_blocks callbacks. There are four users of the DIO_NO_LOCKING mode:
gfs already ignores the create argument and thus is fine with the new
version, ocfs2 only errors out if create were ever set, and we can remove
this dead code now, the block device code only ever uses create for an
error message if we are fully beyond the device which can never happen,
and last but not least XFS will need the new behavour for writes.
Now we can replace the lock_type variable with a flags one, where no flag
means the DIO_NO_LOCKING behaviour and DIO_LOCKING is kept as the first
flag. Separate out the check for not allowing to fill holes into a separate
flag, although for now both flags always get set at the same time.
Also revamp the documentation of the locking scheme to actually make sense.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2009-11-03 18:44:53 +03:00
|
|
|
DIO_LOCKING | DIO_SKIP_HOLES);
|
2005-04-17 02:20:36 +04:00
|
|
|
}
|
[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
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2012-05-31 20:22:33 +04:00
|
|
|
void inode_dio_wait(struct inode *inode);
|
|
|
|
void inode_dio_done(struct inode *inode);
|
|
|
|
|
2006-03-28 13:56:42 +04:00
|
|
|
extern const struct file_operations generic_ro_fops;
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
#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 page_readlink(struct dentry *, char __user *, int);
|
2005-08-20 05:02:56 +04:00
|
|
|
extern void *page_follow_link_light(struct dentry *, struct nameidata *);
|
|
|
|
extern void page_put_link(struct dentry *, struct nameidata *, void *);
|
2006-03-11 14:27:13 +03:00
|
|
|
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);
|
2005-04-17 02:20:36 +04:00
|
|
|
extern int page_symlink(struct inode *inode, const char *symname, int len);
|
2007-02-12 11:55:40 +03:00
|
|
|
extern const struct inode_operations page_symlink_inode_operations;
|
2005-04-17 02:20:36 +04:00
|
|
|
extern int generic_readlink(struct dentry *, char __user *, int);
|
|
|
|
extern void generic_fillattr(struct inode *, struct kstat *);
|
2013-01-24 11:18:08 +04:00
|
|
|
extern int vfs_getattr(struct path *, struct kstat *);
|
2009-12-14 15:21:12 +03:00
|
|
|
void __inode_add_bytes(struct inode *inode, loff_t bytes);
|
2005-04-17 02:20:36 +04:00
|
|
|
void inode_add_bytes(struct inode *inode, loff_t bytes);
|
2013-08-17 17:32:32 +04:00
|
|
|
void __inode_sub_bytes(struct inode *inode, loff_t bytes);
|
2005-04-17 02:20:36 +04:00
|
|
|
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 *);
|
2013-05-15 21:52:59 +04:00
|
|
|
extern int iterate_dir(struct file *, struct dir_context *);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2010-08-11 14:26:22 +04:00
|
|
|
extern int vfs_stat(const char __user *, struct kstat *);
|
|
|
|
extern int vfs_lstat(const char __user *, struct kstat *);
|
2005-04-17 02:20:36 +04:00
|
|
|
extern int vfs_fstat(unsigned int, struct kstat *);
|
2010-08-11 14:26:22 +04:00
|
|
|
extern int vfs_fstatat(int , const char __user *, struct kstat *, int);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2008-02-07 11:13:25 +03:00
|
|
|
extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
|
|
|
|
unsigned long arg);
|
2008-10-14 17:43:29 +04:00
|
|
|
extern int __generic_block_fiemap(struct inode *inode,
|
2010-04-23 20:17:17 +04:00
|
|
|
struct fiemap_extent_info *fieinfo,
|
|
|
|
loff_t start, loff_t len,
|
|
|
|
get_block_t *get_block);
|
2008-10-04 01:32:43 +04:00
|
|
|
extern int generic_block_fiemap(struct inode *inode,
|
|
|
|
struct fiemap_extent_info *fieinfo, u64 start,
|
|
|
|
u64 len, get_block_t *get_block);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2007-10-19 10:39:11 +04:00
|
|
|
extern void get_filesystem(struct file_system_type *fs);
|
|
|
|
extern void put_filesystem(struct file_system_type *fs);
|
2005-04-17 02:20:36 +04:00
|
|
|
extern struct file_system_type *get_fs_type(const char *name);
|
|
|
|
extern struct super_block *get_super(struct block_device *);
|
2012-02-10 14:03:00 +04:00
|
|
|
extern struct super_block *get_super_thawed(struct block_device *);
|
2009-08-04 01:28:35 +04:00
|
|
|
extern struct super_block *get_active_super(struct block_device *bdev);
|
2005-04-17 02:20:36 +04:00
|
|
|
extern void drop_super(struct super_block *sb);
|
2010-03-23 13:06:58 +03:00
|
|
|
extern void iterate_supers(void (*)(struct super_block *, void *), void *);
|
2011-06-04 04:16:57 +04:00
|
|
|
extern void iterate_supers_type(struct file_system_type *,
|
|
|
|
void (*)(struct super_block *, void *), void *);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
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);
|
2013-05-16 04:23:06 +04:00
|
|
|
extern int dcache_readdir(struct file *, struct dir_context *);
|
fs: introduce new truncate sequence
Introduce a new truncate calling sequence into fs/mm subsystems. Rather than
setattr > vmtruncate > truncate, have filesystems call their truncate sequence
from ->setattr if filesystem specific operations are required. vmtruncate is
deprecated, and truncate_pagecache and inode_newsize_ok helpers introduced
previously should be used.
simple_setattr is introduced for simple in-ram filesystems to implement
the new truncate sequence. Eventually all filesystems should be converted
to implement a setattr, and the default code in notify_change should go
away.
simple_setsize is also introduced to perform just the ATTR_SIZE portion
of simple_setattr (ie. changing i_size and trimming pagecache).
To implement the new truncate sequence:
- filesystem specific manipulations (eg freeing blocks) must be done in
the setattr method rather than ->truncate.
- vmtruncate can not be used by core code to trim blocks past i_size in
the event of write failure after allocation, so this must be performed
in the fs code.
- convert usage of helpers block_write_begin, nobh_write_begin,
cont_write_begin, and *blockdev_direct_IO* to use _newtrunc postfixed
variants. These avoid calling vmtruncate to trim blocks (see previous).
- inode_setattr should not be used. generic_setattr is a new function
to be used to copy simple attributes into the generic inode.
- make use of the better opportunity to handle errors with the new sequence.
Big problem with the previous calling sequence: the filesystem is not called
until i_size has already changed. This means it is not allowed to fail the
call, and also it does not know what the previous i_size was. Also, generic
code calling vmtruncate to truncate allocated blocks in case of error had
no good way to return a meaningful error (or, for example, atomically handle
block deallocation).
Cc: Christoph Hellwig <hch@lst.de>
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-05-26 19:05:33 +04:00
|
|
|
extern int simple_setattr(struct dentry *, struct iattr *);
|
2005-04-17 02:20:36 +04:00
|
|
|
extern int simple_getattr(struct vfsmount *, struct dentry *, struct kstat *);
|
2006-06-23 13:02:58 +04:00
|
|
|
extern int simple_statfs(struct dentry *, struct kstatfs *);
|
2012-04-06 01:25:09 +04:00
|
|
|
extern int simple_open(struct inode *inode, struct file *file);
|
2005-04-17 02:20:36 +04:00
|
|
|
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 *);
|
2011-07-17 04:44:56 +04:00
|
|
|
extern int noop_fsync(struct file *, loff_t, loff_t, int);
|
2005-04-17 02:20:36 +04:00
|
|
|
extern int simple_empty(struct dentry *);
|
|
|
|
extern int simple_readpage(struct file *file, struct page *page);
|
2007-10-16 12:25:01 +04:00
|
|
|
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);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2012-06-11 01:13:09 +04:00
|
|
|
extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags);
|
2005-04-17 02:20:36 +04:00
|
|
|
extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *);
|
2006-03-28 13:56:42 +04:00
|
|
|
extern const struct file_operations simple_dir_operations;
|
2007-02-12 11:55:40 +03:00
|
|
|
extern const struct inode_operations simple_dir_inode_operations;
|
2006-03-28 13:56:42 +04:00
|
|
|
struct tree_descr { char *name; const struct file_operations *ops; int mode; };
|
2005-04-17 02:20:36 +04:00
|
|
|
struct dentry *d_alloc_name(struct dentry *, const char *);
|
2010-06-03 13:58:28 +04:00
|
|
|
extern int simple_fill_super(struct super_block *, unsigned long, struct tree_descr *);
|
2006-06-09 17:34:16 +04:00
|
|
|
extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count);
|
2005-04-17 02:20:36 +04:00
|
|
|
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);
|
2010-05-02 01:51:22 +04:00
|
|
|
extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos,
|
|
|
|
const void __user *from, size_t count);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2011-07-17 04:44:56 +04:00
|
|
|
extern int generic_file_fsync(struct file *, loff_t, loff_t, int);
|
2009-06-07 22:56:44 +04:00
|
|
|
|
2010-07-23 02:03:41 +04:00
|
|
|
extern int generic_check_addressable(unsigned, u64);
|
|
|
|
|
2006-02-01 14:05:41 +03:00
|
|
|
#ifdef CONFIG_MIGRATION
|
2006-06-23 13:03:33 +04:00
|
|
|
extern int buffer_migrate_page(struct address_space *,
|
2012-01-13 05:19:43 +04:00
|
|
|
struct page *, struct page *,
|
|
|
|
enum migrate_mode);
|
2006-02-01 14:05:41 +03:00
|
|
|
#else
|
|
|
|
#define buffer_migrate_page NULL
|
|
|
|
#endif
|
|
|
|
|
2009-08-20 20:35:05 +04:00
|
|
|
extern int inode_change_ok(const struct inode *, struct iattr *);
|
|
|
|
extern int inode_newsize_ok(const struct inode *, loff_t offset);
|
2010-06-04 13:30:00 +04:00
|
|
|
extern void setattr_copy(struct inode *inode, const struct iattr *attr);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2012-03-26 17:59:21 +04:00
|
|
|
extern int file_update_time(struct file *file);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2011-12-09 06:32:45 +04:00
|
|
|
extern int generic_show_options(struct seq_file *m, struct dentry *root);
|
2008-02-08 15:21:35 +03:00
|
|
|
extern void save_mount_options(struct super_block *sb, char *options);
|
2009-05-09 00:05:57 +04:00
|
|
|
extern void replace_mount_options(struct super_block *sb, char *options);
|
2008-02-08 15:21:35 +03:00
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
static inline ino_t parent_ino(struct dentry *dentry)
|
|
|
|
{
|
|
|
|
ino_t res;
|
|
|
|
|
2011-01-07 09:49:38 +03:00
|
|
|
/*
|
|
|
|
* Don't strictly need d_lock here? If the parent ino could change
|
|
|
|
* then surely we'd have a deeper race in the caller?
|
|
|
|
*/
|
2005-04-17 02:20:36 +04:00
|
|
|
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);
|
|
|
|
|
2009-03-25 18:48:35 +03:00
|
|
|
void simple_transaction_set(struct file *file, size_t n);
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2005-05-18 16:40:59 +04:00
|
|
|
/*
|
|
|
|
* 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); \
|
|
|
|
} \
|
2009-10-02 02:43:56 +04:00
|
|
|
static const struct file_operations __fops = { \
|
2005-05-18 16:40:59 +04:00
|
|
|
.owner = THIS_MODULE, \
|
|
|
|
.open = __fops ## _open, \
|
2008-02-08 15:20:28 +03:00
|
|
|
.release = simple_attr_release, \
|
2005-05-18 16:40:59 +04:00
|
|
|
.read = simple_attr_read, \
|
|
|
|
.write = simple_attr_write, \
|
2010-08-15 23:50:52 +04:00
|
|
|
.llseek = generic_file_llseek, \
|
2005-05-18 16:40:59 +04:00
|
|
|
};
|
|
|
|
|
2011-11-01 04:11:33 +04:00
|
|
|
static inline __printf(1, 2)
|
|
|
|
void __simple_attr_check_format(const char *fmt, ...)
|
2005-05-18 16:40:59 +04:00
|
|
|
{
|
|
|
|
/* don't do anything, just let the compiler check the arguments; */
|
|
|
|
}
|
|
|
|
|
|
|
|
int simple_attr_open(struct inode *inode, struct file *file,
|
2008-02-08 15:20:26 +03:00
|
|
|
int (*get)(void *, u64 *), int (*set)(void *, u64),
|
2005-05-18 16:40:59 +04:00
|
|
|
const char *fmt);
|
2008-02-08 15:20:28 +03:00
|
|
|
int simple_attr_release(struct inode *inode, struct file *file);
|
2005-05-18 16:40:59 +04:00
|
|
|
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);
|
|
|
|
|
2007-10-17 10:26:21 +04:00
|
|
|
struct ctl_table;
|
2009-09-24 02:57:19 +04:00
|
|
|
int proc_nr_files(struct ctl_table *table, int write,
|
2007-07-17 15:03:45 +04:00
|
|
|
void __user *buffer, size_t *lenp, loff_t *ppos);
|
2010-10-10 13:36:23 +04:00
|
|
|
int proc_nr_dentry(struct ctl_table *table, int write,
|
|
|
|
void __user *buffer, size_t *lenp, loff_t *ppos);
|
2010-10-23 13:03:02 +04:00
|
|
|
int proc_nr_inodes(struct ctl_table *table, int write,
|
|
|
|
void __user *buffer, size_t *lenp, loff_t *ppos);
|
2009-04-09 15:17:52 +04:00
|
|
|
int __init get_filesystem_list(char *buf);
|
2007-07-17 15:03:45 +04:00
|
|
|
|
2011-02-02 02:52:46 +03:00
|
|
|
#define __FMODE_EXEC ((__force int) FMODE_EXEC)
|
2011-02-02 02:52:46 +03:00
|
|
|
#define __FMODE_NONOTIFY ((__force int) FMODE_NONOTIFY)
|
|
|
|
|
2009-12-24 14:58:56 +03:00
|
|
|
#define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE])
|
2009-12-18 05:24:25 +03:00
|
|
|
#define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \
|
2011-02-02 02:52:46 +03:00
|
|
|
(flag & __FMODE_NONOTIFY)))
|
2009-12-19 18:15:07 +03:00
|
|
|
|
2011-07-25 07:21:59 +04:00
|
|
|
static inline int is_sxid(umode_t mode)
|
2011-05-28 19:25:51 +04:00
|
|
|
{
|
|
|
|
return (mode & S_ISUID) || ((mode & S_ISGID) && (mode & S_IXGRP));
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void inode_has_no_xattr(struct inode *inode)
|
|
|
|
{
|
2011-06-04 02:24:58 +04:00
|
|
|
if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & MS_NOSEC))
|
2011-05-28 19:25:51 +04:00
|
|
|
inode->i_flags |= S_NOSEC;
|
|
|
|
}
|
|
|
|
|
2013-05-16 04:23:06 +04:00
|
|
|
static inline bool dir_emit(struct dir_context *ctx,
|
|
|
|
const char *name, int namelen,
|
|
|
|
u64 ino, unsigned type)
|
|
|
|
{
|
|
|
|
return ctx->actor(ctx, name, namelen, ctx->pos, ino, type) == 0;
|
|
|
|
}
|
|
|
|
static inline bool dir_emit_dot(struct file *file, struct dir_context *ctx)
|
|
|
|
{
|
|
|
|
return ctx->actor(ctx, ".", 1, ctx->pos,
|
|
|
|
file->f_path.dentry->d_inode->i_ino, DT_DIR) == 0;
|
|
|
|
}
|
|
|
|
static inline bool dir_emit_dotdot(struct file *file, struct dir_context *ctx)
|
|
|
|
{
|
|
|
|
return ctx->actor(ctx, "..", 2, ctx->pos,
|
|
|
|
parent_ino(file->f_path.dentry), DT_DIR) == 0;
|
|
|
|
}
|
|
|
|
static inline bool dir_emit_dots(struct file *file, struct dir_context *ctx)
|
|
|
|
{
|
|
|
|
if (ctx->pos == 0) {
|
|
|
|
if (!dir_emit_dot(file, ctx))
|
|
|
|
return false;
|
|
|
|
ctx->pos = 1;
|
|
|
|
}
|
|
|
|
if (ctx->pos == 1) {
|
|
|
|
if (!dir_emit_dotdot(file, ctx))
|
|
|
|
return false;
|
|
|
|
ctx->pos = 2;
|
|
|
|
}
|
|
|
|
return true;
|
|
|
|
}
|
2013-05-16 05:02:48 +04:00
|
|
|
static inline bool dir_relax(struct inode *inode)
|
|
|
|
{
|
|
|
|
mutex_unlock(&inode->i_mutex);
|
|
|
|
mutex_lock(&inode->i_mutex);
|
|
|
|
return !IS_DEADDIR(inode);
|
|
|
|
}
|
2013-05-16 04:23:06 +04:00
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
#endif /* _LINUX_FS_H */
|