linux-sg2042/fs/super.c

1425 lines
35 KiB
C
Raw Normal View History

/*
* linux/fs/super.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* super.c contains code to handle: - mount structures
* - super-block tables
* - filesystem drivers list
* - mount system call
* - umount system call
* - ustat system call
*
* GK 2/5/95 - Changed to support mounting the root fs via NFS
*
* Added kerneld support: Jacques Gelinas and Bjorn Ekwall
* Added change_root: Werner Almesberger & Hans Lermen, Feb '96
* Added options to /proc/mounts:
* Torbjörn Lindh (torbjorn.lindh@gopta.se), April 14, 1996.
* Added devfs support: Richard Gooch <rgooch@atnf.csiro.au>, 13-JAN-1998
* Heavily rewritten for 'one fs - one tree' dcache architecture. AV, Mar 2000
*/
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/acct.h>
#include <linux/blkdev.h>
#include <linux/mount.h>
#include <linux/security.h>
#include <linux/writeback.h> /* for the emergency remount stuff */
#include <linux/idr.h>
#include <linux/mutex.h>
#include <linux/backing-dev.h>
#include <linux/rculist_bl.h>
#include <linux/cleancache.h>
#include <linux/fsnotify.h>
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 22:20:34 +08:00
#include <linux/lockdep.h>
#include "internal.h"
LIST_HEAD(super_blocks);
DEFINE_SPINLOCK(sb_lock);
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 22:20:34 +08:00
static char *sb_writers_name[SB_FREEZE_LEVELS] = {
"sb_writers",
"sb_pagefaults",
"sb_internal",
};
/*
* One thing we have to be careful of with a per-sb shrinker is that we don't
* drop the last active reference to the superblock from within the shrinker.
* If that happens we could trigger unregistering the shrinker from within the
* shrinker path and that leads to deadlock on the shrinker_rwsem. Hence we
* take a passive reference to the superblock to avoid this from occurring.
*/
shrinker: convert superblock shrinkers to new API Convert superblock shrinker to use the new count/scan API, and propagate the API changes through to the filesystem callouts. The filesystem callouts already use a count/scan API, so it's just changing counters to longs to match the VM API. This requires the dentry and inode shrinker callouts to be converted to the count/scan API. This is mainly a mechanical change. [glommer@openvz.org: use mult_frac for fractional proportions, build fixes] Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> Acked-by: Mel Gorman <mgorman@suse.de> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Cc: Arve Hjønnevåg <arve@android.com> Cc: Carlos Maiolino <cmaiolino@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: David Rientjes <rientjes@google.com> Cc: Gleb Natapov <gleb@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: J. Bruce Fields <bfields@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Stultz <john.stultz@linaro.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Kent Overstreet <koverstreet@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 08:17:57 +08:00
static unsigned long super_cache_scan(struct shrinker *shrink,
struct shrink_control *sc)
{
struct super_block *sb;
shrinker: convert superblock shrinkers to new API Convert superblock shrinker to use the new count/scan API, and propagate the API changes through to the filesystem callouts. The filesystem callouts already use a count/scan API, so it's just changing counters to longs to match the VM API. This requires the dentry and inode shrinker callouts to be converted to the count/scan API. This is mainly a mechanical change. [glommer@openvz.org: use mult_frac for fractional proportions, build fixes] Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> Acked-by: Mel Gorman <mgorman@suse.de> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Cc: Arve Hjønnevåg <arve@android.com> Cc: Carlos Maiolino <cmaiolino@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: David Rientjes <rientjes@google.com> Cc: Gleb Natapov <gleb@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: J. Bruce Fields <bfields@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Stultz <john.stultz@linaro.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Kent Overstreet <koverstreet@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 08:17:57 +08:00
long fs_objects = 0;
long total_objects;
long freed = 0;
long dentries;
long inodes;
sb = container_of(shrink, struct super_block, s_shrink);
/*
* Deadlock avoidance. We may hold various FS locks, and we don't want
* to recurse into the FS that called us in clear_inode() and friends..
*/
shrinker: convert superblock shrinkers to new API Convert superblock shrinker to use the new count/scan API, and propagate the API changes through to the filesystem callouts. The filesystem callouts already use a count/scan API, so it's just changing counters to longs to match the VM API. This requires the dentry and inode shrinker callouts to be converted to the count/scan API. This is mainly a mechanical change. [glommer@openvz.org: use mult_frac for fractional proportions, build fixes] Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> Acked-by: Mel Gorman <mgorman@suse.de> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Cc: Arve Hjønnevåg <arve@android.com> Cc: Carlos Maiolino <cmaiolino@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: David Rientjes <rientjes@google.com> Cc: Gleb Natapov <gleb@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: J. Bruce Fields <bfields@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Stultz <john.stultz@linaro.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Kent Overstreet <koverstreet@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 08:17:57 +08:00
if (!(sc->gfp_mask & __GFP_FS))
return SHRINK_STOP;
if (!grab_super_passive(sb))
shrinker: convert superblock shrinkers to new API Convert superblock shrinker to use the new count/scan API, and propagate the API changes through to the filesystem callouts. The filesystem callouts already use a count/scan API, so it's just changing counters to longs to match the VM API. This requires the dentry and inode shrinker callouts to be converted to the count/scan API. This is mainly a mechanical change. [glommer@openvz.org: use mult_frac for fractional proportions, build fixes] Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> Acked-by: Mel Gorman <mgorman@suse.de> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Cc: Arve Hjønnevåg <arve@android.com> Cc: Carlos Maiolino <cmaiolino@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: David Rientjes <rientjes@google.com> Cc: Gleb Natapov <gleb@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: J. Bruce Fields <bfields@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Stultz <john.stultz@linaro.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Kent Overstreet <koverstreet@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 08:17:57 +08:00
return SHRINK_STOP;
if (sb->s_op->nr_cached_objects)
2013-08-28 08:18:05 +08:00
fs_objects = sb->s_op->nr_cached_objects(sb, sc->nid);
2013-08-28 08:18:05 +08:00
inodes = list_lru_count_node(&sb->s_inode_lru, sc->nid);
dentries = list_lru_count_node(&sb->s_dentry_lru, sc->nid);
total_objects = dentries + inodes + fs_objects + 1;
shrinker: convert superblock shrinkers to new API Convert superblock shrinker to use the new count/scan API, and propagate the API changes through to the filesystem callouts. The filesystem callouts already use a count/scan API, so it's just changing counters to longs to match the VM API. This requires the dentry and inode shrinker callouts to be converted to the count/scan API. This is mainly a mechanical change. [glommer@openvz.org: use mult_frac for fractional proportions, build fixes] Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> Acked-by: Mel Gorman <mgorman@suse.de> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Cc: Arve Hjønnevåg <arve@android.com> Cc: Carlos Maiolino <cmaiolino@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: David Rientjes <rientjes@google.com> Cc: Gleb Natapov <gleb@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: J. Bruce Fields <bfields@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Stultz <john.stultz@linaro.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Kent Overstreet <koverstreet@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 08:17:57 +08:00
/* proportion the scan between the caches */
dentries = mult_frac(sc->nr_to_scan, dentries, total_objects);
inodes = mult_frac(sc->nr_to_scan, inodes, total_objects);
shrinker: convert superblock shrinkers to new API Convert superblock shrinker to use the new count/scan API, and propagate the API changes through to the filesystem callouts. The filesystem callouts already use a count/scan API, so it's just changing counters to longs to match the VM API. This requires the dentry and inode shrinker callouts to be converted to the count/scan API. This is mainly a mechanical change. [glommer@openvz.org: use mult_frac for fractional proportions, build fixes] Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> Acked-by: Mel Gorman <mgorman@suse.de> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Cc: Arve Hjønnevåg <arve@android.com> Cc: Carlos Maiolino <cmaiolino@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: David Rientjes <rientjes@google.com> Cc: Gleb Natapov <gleb@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: J. Bruce Fields <bfields@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Stultz <john.stultz@linaro.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Kent Overstreet <koverstreet@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 08:17:57 +08:00
/*
* prune the dcache first as the icache is pinned by it, then
* prune the icache, followed by the filesystem specific caches
*/
2013-08-28 08:18:05 +08:00
freed = prune_dcache_sb(sb, dentries, sc->nid);
freed += prune_icache_sb(sb, inodes, sc->nid);
shrinker: convert superblock shrinkers to new API Convert superblock shrinker to use the new count/scan API, and propagate the API changes through to the filesystem callouts. The filesystem callouts already use a count/scan API, so it's just changing counters to longs to match the VM API. This requires the dentry and inode shrinker callouts to be converted to the count/scan API. This is mainly a mechanical change. [glommer@openvz.org: use mult_frac for fractional proportions, build fixes] Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> Acked-by: Mel Gorman <mgorman@suse.de> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Cc: Arve Hjønnevåg <arve@android.com> Cc: Carlos Maiolino <cmaiolino@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: David Rientjes <rientjes@google.com> Cc: Gleb Natapov <gleb@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: J. Bruce Fields <bfields@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Stultz <john.stultz@linaro.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Kent Overstreet <koverstreet@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 08:17:57 +08:00
if (fs_objects) {
fs_objects = mult_frac(sc->nr_to_scan, fs_objects,
total_objects);
2013-08-28 08:18:05 +08:00
freed += sb->s_op->free_cached_objects(sb, fs_objects,
sc->nid);
}
shrinker: convert superblock shrinkers to new API Convert superblock shrinker to use the new count/scan API, and propagate the API changes through to the filesystem callouts. The filesystem callouts already use a count/scan API, so it's just changing counters to longs to match the VM API. This requires the dentry and inode shrinker callouts to be converted to the count/scan API. This is mainly a mechanical change. [glommer@openvz.org: use mult_frac for fractional proportions, build fixes] Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> Acked-by: Mel Gorman <mgorman@suse.de> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Cc: Arve Hjønnevåg <arve@android.com> Cc: Carlos Maiolino <cmaiolino@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: David Rientjes <rientjes@google.com> Cc: Gleb Natapov <gleb@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: J. Bruce Fields <bfields@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Stultz <john.stultz@linaro.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Kent Overstreet <koverstreet@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 08:17:57 +08:00
drop_super(sb);
return freed;
}
static unsigned long super_cache_count(struct shrinker *shrink,
struct shrink_control *sc)
{
struct super_block *sb;
long total_objects = 0;
sb = container_of(shrink, struct super_block, s_shrink);
if (!grab_super_passive(sb))
return 0;
if (sb->s_op && sb->s_op->nr_cached_objects)
2013-08-28 08:18:05 +08:00
total_objects = sb->s_op->nr_cached_objects(sb,
sc->nid);
shrinker: convert superblock shrinkers to new API Convert superblock shrinker to use the new count/scan API, and propagate the API changes through to the filesystem callouts. The filesystem callouts already use a count/scan API, so it's just changing counters to longs to match the VM API. This requires the dentry and inode shrinker callouts to be converted to the count/scan API. This is mainly a mechanical change. [glommer@openvz.org: use mult_frac for fractional proportions, build fixes] Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> Acked-by: Mel Gorman <mgorman@suse.de> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Cc: Arve Hjønnevåg <arve@android.com> Cc: Carlos Maiolino <cmaiolino@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: David Rientjes <rientjes@google.com> Cc: Gleb Natapov <gleb@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: J. Bruce Fields <bfields@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Stultz <john.stultz@linaro.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Kent Overstreet <koverstreet@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 08:17:57 +08:00
2013-08-28 08:18:05 +08:00
total_objects += list_lru_count_node(&sb->s_dentry_lru,
sc->nid);
total_objects += list_lru_count_node(&sb->s_inode_lru,
sc->nid);
shrinker: convert superblock shrinkers to new API Convert superblock shrinker to use the new count/scan API, and propagate the API changes through to the filesystem callouts. The filesystem callouts already use a count/scan API, so it's just changing counters to longs to match the VM API. This requires the dentry and inode shrinker callouts to be converted to the count/scan API. This is mainly a mechanical change. [glommer@openvz.org: use mult_frac for fractional proportions, build fixes] Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> Acked-by: Mel Gorman <mgorman@suse.de> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Cc: Arve Hjønnevåg <arve@android.com> Cc: Carlos Maiolino <cmaiolino@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: David Rientjes <rientjes@google.com> Cc: Gleb Natapov <gleb@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: J. Bruce Fields <bfields@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Stultz <john.stultz@linaro.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Kent Overstreet <koverstreet@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 08:17:57 +08:00
super: fix calculation of shrinkable objects for small numbers The sysctl knob sysctl_vfs_cache_pressure is used to determine which percentage of the shrinkable objects in our cache we should actively try to shrink. It works great in situations in which we have many objects (at least more than 100), because the aproximation errors will be negligible. But if this is not the case, specially when total_objects < 100, we may end up concluding that we have no objects at all (total / 100 = 0, if total < 100). This is certainly not the biggest killer in the world, but may matter in very low kernel memory situations. Signed-off-by: Glauber Costa <glommer@openvz.org> Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com> Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Dave Chinner <david@fromorbit.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Cc: Arve Hjønnevåg <arve@android.com> Cc: Carlos Maiolino <cmaiolino@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: David Rientjes <rientjes@google.com> Cc: Gleb Natapov <gleb@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: J. Bruce Fields <bfields@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Stultz <john.stultz@linaro.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Kent Overstreet <koverstreet@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 08:17:53 +08:00
total_objects = vfs_pressure_ratio(total_objects);
drop_super(sb);
return total_objects;
}
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 22:20:34 +08:00
static int init_sb_writers(struct super_block *s, struct file_system_type *type)
{
int err;
int i;
for (i = 0; i < SB_FREEZE_LEVELS; i++) {
err = percpu_counter_init(&s->s_writers.counter[i], 0);
if (err < 0)
goto err_out;
lockdep_init_map(&s->s_writers.lock_map[i], sb_writers_name[i],
&type->s_writers_key[i], 0);
}
init_waitqueue_head(&s->s_writers.wait);
init_waitqueue_head(&s->s_writers.wait_unfrozen);
return 0;
err_out:
while (--i >= 0)
percpu_counter_destroy(&s->s_writers.counter[i]);
return err;
}
static void destroy_sb_writers(struct super_block *s)
{
int i;
for (i = 0; i < SB_FREEZE_LEVELS; i++)
percpu_counter_destroy(&s->s_writers.counter[i]);
}
/**
* alloc_super - create new superblock
* @type: filesystem type superblock should belong to
* @flags: the mount flags
*
* Allocates and initializes a new &struct super_block. alloc_super()
* returns a pointer new superblock or %NULL if allocation had failed.
*/
static struct super_block *alloc_super(struct file_system_type *type, int flags)
{
struct super_block *s = kzalloc(sizeof(struct super_block), GFP_USER);
static const struct super_operations default_op;
if (s) {
if (security_sb_alloc(s))
goto out_free_sb;
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>
2010-08-18 02:37:38 +08:00
#ifdef CONFIG_SMP
s->s_files = alloc_percpu(struct list_head);
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 22:20:34 +08:00
if (!s->s_files)
goto err_out;
else {
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>
2010-08-18 02:37:38 +08:00
int i;
for_each_possible_cpu(i)
INIT_LIST_HEAD(per_cpu_ptr(s->s_files, i));
}
#else
INIT_LIST_HEAD(&s->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>
2010-08-18 02:37:38 +08:00
#endif
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 22:20:34 +08:00
if (init_sb_writers(s, type))
goto err_out;
s->s_flags = flags;
s->s_bdi = &default_backing_dev_info;
INIT_HLIST_NODE(&s->s_instances);
INIT_HLIST_BL_HEAD(&s->s_anon);
INIT_LIST_HEAD(&s->s_inodes);
list_lru: dynamically adjust node arrays We currently use a compile-time constant to size the node array for the list_lru structure. Due to this, we don't need to allocate any memory at initialization time. But as a consequence, the structures that contain embedded list_lru lists can become way too big (the superblock for instance contains two of them). This patch aims at ameliorating this situation by dynamically allocating the node arrays with the firmware provided nr_node_ids. Signed-off-by: Glauber Costa <glommer@openvz.org> Cc: Dave Chinner <dchinner@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Cc: Arve Hjønnevåg <arve@android.com> Cc: Carlos Maiolino <cmaiolino@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: David Rientjes <rientjes@google.com> Cc: Gleb Natapov <gleb@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: J. Bruce Fields <bfields@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Stultz <john.stultz@linaro.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Kent Overstreet <koverstreet@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 08:18:18 +08:00
if (list_lru_init(&s->s_dentry_lru))
goto err_out;
if (list_lru_init(&s->s_inode_lru))
goto err_out_dentry_lru;
INIT_LIST_HEAD(&s->s_mounts);
init_rwsem(&s->s_umount);
lockdep_set_class(&s->s_umount, &type->s_umount_key);
fs/super.c: add lockdep annotation to s_umount Li Zefan said: Thread 1: for ((; ;)) { mount -t cpuset xxx /mnt > /dev/null 2>&1 cat /mnt/cpus > /dev/null 2>&1 umount /mnt > /dev/null 2>&1 } Thread 2: for ((; ;)) { mount -t cpuset xxx /mnt > /dev/null 2>&1 umount /mnt > /dev/null 2>&1 } (Note: It is irrelevant which cgroup subsys is used.) After a while a lockdep warning showed up: ============================================= [ INFO: possible recursive locking detected ] 2.6.28 #479 --------------------------------------------- mount/13554 is trying to acquire lock: (&type->s_umount_key#19){--..}, at: [<c049d888>] sget+0x5e/0x321 but task is already holding lock: (&type->s_umount_key#19){--..}, at: [<c049da0c>] sget+0x1e2/0x321 other info that might help us debug this: 1 lock held by mount/13554: #0: (&type->s_umount_key#19){--..}, at: [<c049da0c>] sget+0x1e2/0x321 stack backtrace: Pid: 13554, comm: mount Not tainted 2.6.28-mc #479 Call Trace: [<c044ad2e>] validate_chain+0x4c6/0xbbd [<c044ba9b>] __lock_acquire+0x676/0x700 [<c044bb82>] lock_acquire+0x5d/0x7a [<c049d888>] ? sget+0x5e/0x321 [<c061b9b8>] down_write+0x34/0x50 [<c049d888>] ? sget+0x5e/0x321 [<c049d888>] sget+0x5e/0x321 [<c045a2e7>] ? cgroup_set_super+0x0/0x3e [<c045959f>] ? cgroup_test_super+0x0/0x2f [<c045bcea>] cgroup_get_sb+0x98/0x2e7 [<c045cfb6>] cpuset_get_sb+0x4a/0x5f [<c049dfa4>] vfs_kern_mount+0x40/0x7b [<c049e02d>] do_kern_mount+0x37/0xbf [<c04af4a0>] do_mount+0x5c3/0x61a [<c04addd2>] ? copy_mount_options+0x2c/0x111 [<c04af560>] sys_mount+0x69/0xa0 [<c0403251>] sysenter_do_call+0x12/0x31 The cause is after alloc_super() and then retry, an old entry in list fs_supers is found, so grab_super(old) is called, but both functions hold s_umount lock: struct super_block *sget(...) { ... retry: spin_lock(&sb_lock); if (test) { list_for_each_entry(old, &type->fs_supers, s_instances) { if (!test(old, data)) continue; if (!grab_super(old)) <--- 2nd: down_write(&old->s_umount); goto retry; if (s) destroy_super(s); return old; } } if (!s) { spin_unlock(&sb_lock); s = alloc_super(type); <--- 1th: down_write(&s->s_umount) if (!s) return ERR_PTR(-ENOMEM); goto retry; } ... } It seems like a false positive, and seems like VFS but not cgroup needs to be fixed. Peter said: We can simply put the new s_umount instance in a but lockdep doesn't particularly cares about subclass order. If there's any issue with the callers of sget() assuming the s_umount lock being of sublcass 0, then there is another annotation we can use to fix that, but lets not bother with that if this is sufficient. Addresses http://bugzilla.kernel.org/show_bug.cgi?id=12673 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Tested-by: Li Zefan <lizf@cn.fujitsu.com> Reported-by: Li Zefan <lizf@cn.fujitsu.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Paul Menage <menage@google.com> Cc: Arjan van de Ven <arjan@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-19 06:48:30 +08:00
/*
* sget() can have s_umount recursion.
*
* When it cannot find a suitable sb, it allocates a new
* one (this one), and tries again to find a suitable old
* one.
*
* In case that succeeds, it will acquire the s_umount
* lock of the old one. Since these are clearly distrinct
* locks, and this object isn't exposed yet, there's no
* risk of deadlocks.
*
* Annotate this by putting this lock in a different
* subclass.
*/
down_write_nested(&s->s_umount, SINGLE_DEPTH_NESTING);
s->s_count = 1;
atomic_set(&s->s_active, 1);
mutex_init(&s->s_vfs_rename_mutex);
vfs: add lockdep annotation to s_vfs_rename_key for ecryptfs > ============================================= > [ INFO: possible recursive locking detected ] > 2.6.31-2-generic #14~rbd3 > --------------------------------------------- > firefox-3.5/4162 is trying to acquire lock: > (&s->s_vfs_rename_mutex){+.+.+.}, at: [<ffffffff81139d31>] lock_rename+0x41/0xf0 > > but task is already holding lock: > (&s->s_vfs_rename_mutex){+.+.+.}, at: [<ffffffff81139d31>] lock_rename+0x41/0xf0 > > other info that might help us debug this: > 3 locks held by firefox-3.5/4162: > #0: (&s->s_vfs_rename_mutex){+.+.+.}, at: [<ffffffff81139d31>] lock_rename+0x41/0xf0 > #1: (&sb->s_type->i_mutex_key#11/1){+.+.+.}, at: [<ffffffff81139d5a>] lock_rename+0x6a/0xf0 > #2: (&sb->s_type->i_mutex_key#11/2){+.+.+.}, at: [<ffffffff81139d6f>] lock_rename+0x7f/0xf0 > > stack backtrace: > Pid: 4162, comm: firefox-3.5 Tainted: G C 2.6.31-2-generic #14~rbd3 > Call Trace: > [<ffffffff8108ae74>] print_deadlock_bug+0xf4/0x100 > [<ffffffff8108ce26>] validate_chain+0x4c6/0x750 > [<ffffffff8108d2e7>] __lock_acquire+0x237/0x430 > [<ffffffff8108d585>] lock_acquire+0xa5/0x150 > [<ffffffff81139d31>] ? lock_rename+0x41/0xf0 > [<ffffffff815526ad>] __mutex_lock_common+0x4d/0x3d0 > [<ffffffff81139d31>] ? lock_rename+0x41/0xf0 > [<ffffffff81139d31>] ? lock_rename+0x41/0xf0 > [<ffffffff8120eaf9>] ? ecryptfs_rename+0x99/0x170 > [<ffffffff81552b36>] mutex_lock_nested+0x46/0x60 > [<ffffffff81139d31>] lock_rename+0x41/0xf0 > [<ffffffff8120eb2a>] ecryptfs_rename+0xca/0x170 > [<ffffffff81139a9e>] vfs_rename_dir+0x13e/0x160 > [<ffffffff8113ac7e>] vfs_rename+0xee/0x290 > [<ffffffff8113c212>] ? __lookup_hash+0x102/0x160 > [<ffffffff8113d512>] sys_renameat+0x252/0x280 > [<ffffffff81133eb4>] ? cp_new_stat+0xe4/0x100 > [<ffffffff8101316a>] ? sysret_check+0x2e/0x69 > [<ffffffff8108c34d>] ? trace_hardirqs_on_caller+0x14d/0x190 > [<ffffffff8113d55b>] sys_rename+0x1b/0x20 > [<ffffffff81013132>] system_call_fastpath+0x16/0x1b The trace above is totally reproducible by doing a cross-directory rename on an ecryptfs directory. The issue seems to be that sys_renameat() does lock_rename() then calls into the filesystem; if the filesystem is ecryptfs, then ecryptfs_rename() again does lock_rename() on the lower filesystem, and lockdep can't tell that the two s_vfs_rename_mutexes are different. It seems an annotation like the following is sufficient to fix this (it does get rid of the lockdep trace in my simple tests); however I would like to make sure I'm not misunderstanding the locking, hence the CC list... Signed-off-by: Roland Dreier <rdreier@cisco.com> Cc: Tyler Hicks <tyhicks@linux.vnet.ibm.com> Cc: Dustin Kirkland <kirkland@canonical.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-04-28 05:23:57 +08:00
lockdep_set_class(&s->s_vfs_rename_mutex, &type->s_vfs_rename_key);
mutex_init(&s->s_dquot.dqio_mutex);
mutex_init(&s->s_dquot.dqonoff_mutex);
init_rwsem(&s->s_dquot.dqptr_sem);
s->s_maxbytes = MAX_NON_LFS;
s->s_op = &default_op;
s->s_time_gran = 1000000000;
s->cleancache_poolid = -1;
s->s_shrink.seeks = DEFAULT_SEEKS;
shrinker: convert superblock shrinkers to new API Convert superblock shrinker to use the new count/scan API, and propagate the API changes through to the filesystem callouts. The filesystem callouts already use a count/scan API, so it's just changing counters to longs to match the VM API. This requires the dentry and inode shrinker callouts to be converted to the count/scan API. This is mainly a mechanical change. [glommer@openvz.org: use mult_frac for fractional proportions, build fixes] Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> Acked-by: Mel Gorman <mgorman@suse.de> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Cc: Arve Hjønnevåg <arve@android.com> Cc: Carlos Maiolino <cmaiolino@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: David Rientjes <rientjes@google.com> Cc: Gleb Natapov <gleb@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: J. Bruce Fields <bfields@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Stultz <john.stultz@linaro.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Kent Overstreet <koverstreet@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 08:17:57 +08:00
s->s_shrink.scan_objects = super_cache_scan;
s->s_shrink.count_objects = super_cache_count;
s->s_shrink.batch = 1024;
2013-08-28 08:18:05 +08:00
s->s_shrink.flags = SHRINKER_NUMA_AWARE;
}
out:
return s;
list_lru: dynamically adjust node arrays We currently use a compile-time constant to size the node array for the list_lru structure. Due to this, we don't need to allocate any memory at initialization time. But as a consequence, the structures that contain embedded list_lru lists can become way too big (the superblock for instance contains two of them). This patch aims at ameliorating this situation by dynamically allocating the node arrays with the firmware provided nr_node_ids. Signed-off-by: Glauber Costa <glommer@openvz.org> Cc: Dave Chinner <dchinner@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Cc: Arve Hjønnevåg <arve@android.com> Cc: Carlos Maiolino <cmaiolino@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Cc: David Rientjes <rientjes@google.com> Cc: Gleb Natapov <gleb@redhat.com> Cc: Greg Thelen <gthelen@google.com> Cc: J. Bruce Fields <bfields@redhat.com> Cc: Jan Kara <jack@suse.cz> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Stultz <john.stultz@linaro.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Kent Overstreet <koverstreet@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Thomas Hellstrom <thellstrom@vmware.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 08:18:18 +08:00
err_out_dentry_lru:
list_lru_destroy(&s->s_dentry_lru);
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 22:20:34 +08:00
err_out:
security_sb_free(s);
#ifdef CONFIG_SMP
if (s->s_files)
free_percpu(s->s_files);
#endif
destroy_sb_writers(s);
out_free_sb:
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 22:20:34 +08:00
kfree(s);
s = NULL;
goto out;
}
/**
* destroy_super - frees a superblock
* @s: superblock to free
*
* Frees a superblock.
*/
static inline void destroy_super(struct super_block *s)
{
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>
2010-08-18 02:37:38 +08:00
#ifdef CONFIG_SMP
free_percpu(s->s_files);
#endif
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 22:20:34 +08:00
destroy_sb_writers(s);
security_sb_free(s);
WARN_ON(!list_empty(&s->s_mounts));
kfree(s->s_subtype);
kfree(s->s_options);
kfree(s);
}
/* Superblock refcounting */
/*
* Drop a superblock's refcount. The caller must hold sb_lock.
*/
static void __put_super(struct super_block *sb)
{
if (!--sb->s_count) {
list_del_init(&sb->s_list);
destroy_super(sb);
}
}
/**
* put_super - drop a temporary reference to superblock
* @sb: superblock in question
*
* Drops a temporary reference, frees superblock if there's no
* references left.
*/
static void put_super(struct super_block *sb)
{
spin_lock(&sb_lock);
__put_super(sb);
spin_unlock(&sb_lock);
}
/**
* deactivate_locked_super - drop an active reference to superblock
* @s: superblock to deactivate
*
* Drops an active reference to superblock, converting it into a temprory
* one if there is no other active references left. In that case we
* tell fs driver to shut it down and drop the temporary reference we
* had just acquired.
*
* Caller holds exclusive lock on superblock; that lock is released.
*/
void deactivate_locked_super(struct super_block *s)
{
struct file_system_type *fs = s->s_type;
if (atomic_dec_and_test(&s->s_active)) {
cleancache_invalidate_fs(s);
fs->kill_sb(s);
/* caches are now gone, we can safely kill the shrinker now */
unregister_shrinker(&s->s_shrink);
list_lru_destroy(&s->s_dentry_lru);
list_lru_destroy(&s->s_inode_lru);
put_filesystem(fs);
put_super(s);
} else {
up_write(&s->s_umount);
}
}
EXPORT_SYMBOL(deactivate_locked_super);
/**
* deactivate_super - drop an active reference to superblock
* @s: superblock to deactivate
*
* Variant of deactivate_locked_super(), except that superblock is *not*
* locked by caller. If we are going to drop the final active reference,
* lock will be acquired prior to that.
*/
void deactivate_super(struct super_block *s)
{
if (!atomic_add_unless(&s->s_active, -1, 1)) {
down_write(&s->s_umount);
deactivate_locked_super(s);
}
}
EXPORT_SYMBOL(deactivate_super);
/**
* grab_super - acquire an active reference
* @s: reference we are trying to make active
*
* Tries to acquire an active reference. grab_super() is used when we
* had just found a superblock in super_blocks or fs_type->fs_supers
* and want to turn it into a full-blown active reference. grab_super()
* is called with sb_lock held and drops it. Returns 1 in case of
* success, 0 if we had failed (superblock contents was already dead or
livelock avoidance in sget() Eric Sandeen has found a nasty livelock in sget() - take a mount(2) about to fail. The superblock is on ->fs_supers, ->s_umount is held exclusive, ->s_active is 1. Along comes two more processes, trying to mount the same thing; sget() in each is picking that superblock, bumping ->s_count and trying to grab ->s_umount. ->s_active is 3 now. Original mount(2) finally gets to deactivate_locked_super() on failure; ->s_active is 2, superblock is still ->fs_supers because shutdown will *not* happen until ->s_active hits 0. ->s_umount is dropped and now we have two processes chasing each other: s_active = 2, A acquired ->s_umount, B blocked A sees that the damn thing is stillborn, does deactivate_locked_super() s_active = 1, A drops ->s_umount, B gets it A restarts the search and finds the same superblock. And bumps it ->s_active. s_active = 2, B holds ->s_umount, A blocked on trying to get it ... and we are in the earlier situation with A and B switched places. The root cause, of course, is that ->s_active should not grow until we'd got MS_BORN. Then failing ->mount() will have deactivate_locked_super() shut the damn thing down. Fortunately, it's easy to do - the key point is that grab_super() is called only for superblocks currently on ->fs_supers, so it can bump ->s_count and grab ->s_umount first, then check MS_BORN and bump ->s_active; we must never increment ->s_count for superblocks past ->kill_sb(), but grab_super() is never called for those. The bug is pretty old; we would've caught it by now, if not for accidental exclusion between sget() for block filesystems; the things like cgroup or e.g. mtd-based filesystems don't have anything of that sort, so they get bitten. The right way to deal with that is obviously to fix sget()... Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-07-20 07:13:55 +08:00
* dying when grab_super() had been called). Note that this is only
* called for superblocks not in rundown mode (== ones still on ->fs_supers
* of their type), so increment of ->s_count is OK here.
*/
static int grab_super(struct super_block *s) __releases(sb_lock)
{
s->s_count++;
spin_unlock(&sb_lock);
down_write(&s->s_umount);
livelock avoidance in sget() Eric Sandeen has found a nasty livelock in sget() - take a mount(2) about to fail. The superblock is on ->fs_supers, ->s_umount is held exclusive, ->s_active is 1. Along comes two more processes, trying to mount the same thing; sget() in each is picking that superblock, bumping ->s_count and trying to grab ->s_umount. ->s_active is 3 now. Original mount(2) finally gets to deactivate_locked_super() on failure; ->s_active is 2, superblock is still ->fs_supers because shutdown will *not* happen until ->s_active hits 0. ->s_umount is dropped and now we have two processes chasing each other: s_active = 2, A acquired ->s_umount, B blocked A sees that the damn thing is stillborn, does deactivate_locked_super() s_active = 1, A drops ->s_umount, B gets it A restarts the search and finds the same superblock. And bumps it ->s_active. s_active = 2, B holds ->s_umount, A blocked on trying to get it ... and we are in the earlier situation with A and B switched places. The root cause, of course, is that ->s_active should not grow until we'd got MS_BORN. Then failing ->mount() will have deactivate_locked_super() shut the damn thing down. Fortunately, it's easy to do - the key point is that grab_super() is called only for superblocks currently on ->fs_supers, so it can bump ->s_count and grab ->s_umount first, then check MS_BORN and bump ->s_active; we must never increment ->s_count for superblocks past ->kill_sb(), but grab_super() is never called for those. The bug is pretty old; we would've caught it by now, if not for accidental exclusion between sget() for block filesystems; the things like cgroup or e.g. mtd-based filesystems don't have anything of that sort, so they get bitten. The right way to deal with that is obviously to fix sget()... Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-07-20 07:13:55 +08:00
if ((s->s_flags & MS_BORN) && atomic_inc_not_zero(&s->s_active)) {
put_super(s);
return 1;
}
up_write(&s->s_umount);
put_super(s);
return 0;
}
/*
* grab_super_passive - acquire a passive reference
* @sb: reference we are trying to grab
*
* Tries to acquire a passive reference. This is used in places where we
* cannot take an active reference but we need to ensure that the
* superblock does not go away while we are working on it. It returns
* false if a reference was not gained, and returns true with the s_umount
* lock held in read mode if a reference is gained. On successful return,
* the caller must drop the s_umount lock and the passive reference when
* done.
*/
bool grab_super_passive(struct super_block *sb)
{
spin_lock(&sb_lock);
if (hlist_unhashed(&sb->s_instances)) {
spin_unlock(&sb_lock);
return false;
}
sb->s_count++;
spin_unlock(&sb_lock);
if (down_read_trylock(&sb->s_umount)) {
if (sb->s_root && (sb->s_flags & MS_BORN))
return true;
up_read(&sb->s_umount);
}
put_super(sb);
return false;
}
/**
* generic_shutdown_super - common helper for ->kill_sb()
* @sb: superblock to kill
*
* generic_shutdown_super() does all fs-independent work on superblock
* shutdown. Typical ->kill_sb() should pick all fs-specific objects
* that need destruction out of superblock, call generic_shutdown_super()
* and release aforementioned objects. Note: dentries and inodes _are_
* taken care of and do not need specific handling.
[PATCH] VFS: Destroy the dentries contributed by a superblock on unmounting The attached patch destroys all the dentries attached to a superblock in one go by: (1) Destroying the tree rooted at s_root. (2) Destroying every entry in the anon list, one at a time. (3) Each entry in the anon list has its subtree consumed from the leaves inwards. This reduces the amount of work generic_shutdown_super() does, and avoids iterating through the dentry_unused list. Note that locking is almost entirely absent in the shrink_dcache_for_umount*() functions added by this patch. This is because: (1) at the point the filesystem calls generic_shutdown_super(), it is not permitted to further touch the superblock's set of dentries, and nor may it remove aliases from inodes; (2) the dcache memory shrinker now skips dentries that are being unmounted; and (3) the superblock no longer has any external references through which the VFS can reach it. Given these points, the only locking we need to do is when we remove dentries from the unused list and the name hashes, which we do a directory's worth at a time. We also don't need to guard against reference counts going to zero unexpectedly and removing bits of the tree we're working on as nothing else can call dput(). A cut down version of dentry_iput() has been folded into shrink_dcache_for_umount_subtree() function. Apart from not needing to unlock things, it also doesn't need to check for inotify watches. In this version of the patch, the complaint about a dentry still being in use has been expanded from a single BUG_ON() and now gives much more information. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: NeilBrown <neilb@suse.de> Acked-by: Ian Kent <raven@themaw.net> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-11 16:22:19 +08:00
*
* Upon calling this function, the filesystem may no longer alter or
* rearrange the set of dentries belonging to this super_block, nor may it
* change the attachments of dentries to inodes.
*/
void generic_shutdown_super(struct super_block *sb)
{
const struct super_operations *sop = sb->s_op;
[PATCH] VFS: Destroy the dentries contributed by a superblock on unmounting The attached patch destroys all the dentries attached to a superblock in one go by: (1) Destroying the tree rooted at s_root. (2) Destroying every entry in the anon list, one at a time. (3) Each entry in the anon list has its subtree consumed from the leaves inwards. This reduces the amount of work generic_shutdown_super() does, and avoids iterating through the dentry_unused list. Note that locking is almost entirely absent in the shrink_dcache_for_umount*() functions added by this patch. This is because: (1) at the point the filesystem calls generic_shutdown_super(), it is not permitted to further touch the superblock's set of dentries, and nor may it remove aliases from inodes; (2) the dcache memory shrinker now skips dentries that are being unmounted; and (3) the superblock no longer has any external references through which the VFS can reach it. Given these points, the only locking we need to do is when we remove dentries from the unused list and the name hashes, which we do a directory's worth at a time. We also don't need to guard against reference counts going to zero unexpectedly and removing bits of the tree we're working on as nothing else can call dput(). A cut down version of dentry_iput() has been folded into shrink_dcache_for_umount_subtree() function. Apart from not needing to unlock things, it also doesn't need to check for inotify watches. In this version of the patch, the complaint about a dentry still being in use has been expanded from a single BUG_ON() and now gives much more information. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: NeilBrown <neilb@suse.de> Acked-by: Ian Kent <raven@themaw.net> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-11 16:22:19 +08:00
if (sb->s_root) {
shrink_dcache_for_umount(sb);
sync_filesystem(sb);
sb->s_flags &= ~MS_ACTIVE;
fsnotify_unmount_inodes(&sb->s_inodes);
evict_inodes(sb);
if (sb->s_dio_done_wq) {
destroy_workqueue(sb->s_dio_done_wq);
sb->s_dio_done_wq = NULL;
}
if (sop->put_super)
sop->put_super(sb);
if (!list_empty(&sb->s_inodes)) {
printk("VFS: Busy inodes after unmount of %s. "
"Self-destruct in 5 seconds. Have a nice day...\n",
sb->s_id);
}
}
spin_lock(&sb_lock);
/* should be initialized for __put_super_and_need_restart() */
hlist_del_init(&sb->s_instances);
spin_unlock(&sb_lock);
up_write(&sb->s_umount);
}
EXPORT_SYMBOL(generic_shutdown_super);
/**
* sget - find or create a superblock
* @type: filesystem type superblock should belong to
* @test: comparison callback
* @set: setup callback
* @flags: mount flags
* @data: argument to each of them
*/
struct super_block *sget(struct file_system_type *type,
int (*test)(struct super_block *,void *),
int (*set)(struct super_block *,void *),
int flags,
void *data)
{
struct super_block *s = NULL;
struct super_block *old;
int err;
retry:
spin_lock(&sb_lock);
if (test) {
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 09:06:00 +08:00
hlist_for_each_entry(old, &type->fs_supers, s_instances) {
if (!test(old, data))
continue;
if (!grab_super(old))
goto retry;
if (s) {
up_write(&s->s_umount);
destroy_super(s);
s = NULL;
}
return old;
}
}
if (!s) {
spin_unlock(&sb_lock);
s = alloc_super(type, flags);
if (!s)
return ERR_PTR(-ENOMEM);
goto retry;
}
err = set(s, data);
if (err) {
spin_unlock(&sb_lock);
up_write(&s->s_umount);
destroy_super(s);
return ERR_PTR(err);
}
s->s_type = type;
strlcpy(s->s_id, type->name, sizeof(s->s_id));
list_add_tail(&s->s_list, &super_blocks);
hlist_add_head(&s->s_instances, &type->fs_supers);
spin_unlock(&sb_lock);
get_filesystem(type);
register_shrinker(&s->s_shrink);
return s;
}
EXPORT_SYMBOL(sget);
void drop_super(struct super_block *sb)
{
up_read(&sb->s_umount);
put_super(sb);
}
EXPORT_SYMBOL(drop_super);
/**
* iterate_supers - call function for all active superblocks
* @f: function to call
* @arg: argument to pass to it
*
* Scans the superblock list and calls given function, passing it
* locked superblock and given argument.
*/
void iterate_supers(void (*f)(struct super_block *, void *), void *arg)
{
struct super_block *sb, *p = NULL;
spin_lock(&sb_lock);
list_for_each_entry(sb, &super_blocks, s_list) {
if (hlist_unhashed(&sb->s_instances))
continue;
sb->s_count++;
spin_unlock(&sb_lock);
down_read(&sb->s_umount);
if (sb->s_root && (sb->s_flags & MS_BORN))
f(sb, arg);
up_read(&sb->s_umount);
spin_lock(&sb_lock);
if (p)
__put_super(p);
p = sb;
}
if (p)
__put_super(p);
spin_unlock(&sb_lock);
}
/**
* iterate_supers_type - call function for superblocks of given type
* @type: fs type
* @f: function to call
* @arg: argument to pass to it
*
* Scans the superblock list and calls given function, passing it
* locked superblock and given argument.
*/
void iterate_supers_type(struct file_system_type *type,
void (*f)(struct super_block *, void *), void *arg)
{
struct super_block *sb, *p = NULL;
spin_lock(&sb_lock);
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 09:06:00 +08:00
hlist_for_each_entry(sb, &type->fs_supers, s_instances) {
sb->s_count++;
spin_unlock(&sb_lock);
down_read(&sb->s_umount);
if (sb->s_root && (sb->s_flags & MS_BORN))
f(sb, arg);
up_read(&sb->s_umount);
spin_lock(&sb_lock);
if (p)
__put_super(p);
p = sb;
}
if (p)
__put_super(p);
spin_unlock(&sb_lock);
}
EXPORT_SYMBOL(iterate_supers_type);
/**
* get_super - get the superblock of a device
* @bdev: device to get the superblock for
*
* Scans the superblock list and finds the superblock of the file system
* mounted on the device given. %NULL is returned if no match is found.
*/
struct super_block *get_super(struct block_device *bdev)
{
struct super_block *sb;
if (!bdev)
return NULL;
spin_lock(&sb_lock);
rescan:
list_for_each_entry(sb, &super_blocks, s_list) {
if (hlist_unhashed(&sb->s_instances))
continue;
if (sb->s_bdev == bdev) {
sb->s_count++;
spin_unlock(&sb_lock);
down_read(&sb->s_umount);
/* still alive? */
if (sb->s_root && (sb->s_flags & MS_BORN))
return sb;
up_read(&sb->s_umount);
/* nope, got unmounted */
spin_lock(&sb_lock);
__put_super(sb);
goto rescan;
}
}
spin_unlock(&sb_lock);
return NULL;
}
EXPORT_SYMBOL(get_super);
/**
* get_super_thawed - get thawed superblock of a device
* @bdev: device to get the superblock for
*
* Scans the superblock list and finds the superblock of the file system
* mounted on the device. The superblock is returned once it is thawed
* (or immediately if it was not frozen). %NULL is returned if no match
* is found.
*/
struct super_block *get_super_thawed(struct block_device *bdev)
{
while (1) {
struct super_block *s = get_super(bdev);
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 22:20:34 +08:00
if (!s || s->s_writers.frozen == SB_UNFROZEN)
return s;
up_read(&s->s_umount);
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 22:20:34 +08:00
wait_event(s->s_writers.wait_unfrozen,
s->s_writers.frozen == SB_UNFROZEN);
put_super(s);
}
}
EXPORT_SYMBOL(get_super_thawed);
/**
* get_active_super - get an active reference to the superblock of a device
* @bdev: device to get the superblock for
*
* Scans the superblock list and finds the superblock of the file system
* mounted on the device given. Returns the superblock with an active
* reference or %NULL if none was found.
*/
struct super_block *get_active_super(struct block_device *bdev)
{
struct super_block *sb;
if (!bdev)
return NULL;
restart:
spin_lock(&sb_lock);
list_for_each_entry(sb, &super_blocks, s_list) {
if (hlist_unhashed(&sb->s_instances))
continue;
if (sb->s_bdev == bdev) {
livelock avoidance in sget() Eric Sandeen has found a nasty livelock in sget() - take a mount(2) about to fail. The superblock is on ->fs_supers, ->s_umount is held exclusive, ->s_active is 1. Along comes two more processes, trying to mount the same thing; sget() in each is picking that superblock, bumping ->s_count and trying to grab ->s_umount. ->s_active is 3 now. Original mount(2) finally gets to deactivate_locked_super() on failure; ->s_active is 2, superblock is still ->fs_supers because shutdown will *not* happen until ->s_active hits 0. ->s_umount is dropped and now we have two processes chasing each other: s_active = 2, A acquired ->s_umount, B blocked A sees that the damn thing is stillborn, does deactivate_locked_super() s_active = 1, A drops ->s_umount, B gets it A restarts the search and finds the same superblock. And bumps it ->s_active. s_active = 2, B holds ->s_umount, A blocked on trying to get it ... and we are in the earlier situation with A and B switched places. The root cause, of course, is that ->s_active should not grow until we'd got MS_BORN. Then failing ->mount() will have deactivate_locked_super() shut the damn thing down. Fortunately, it's easy to do - the key point is that grab_super() is called only for superblocks currently on ->fs_supers, so it can bump ->s_count and grab ->s_umount first, then check MS_BORN and bump ->s_active; we must never increment ->s_count for superblocks past ->kill_sb(), but grab_super() is never called for those. The bug is pretty old; we would've caught it by now, if not for accidental exclusion between sget() for block filesystems; the things like cgroup or e.g. mtd-based filesystems don't have anything of that sort, so they get bitten. The right way to deal with that is obviously to fix sget()... Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-07-20 07:13:55 +08:00
if (!grab_super(sb))
goto restart;
livelock avoidance in sget() Eric Sandeen has found a nasty livelock in sget() - take a mount(2) about to fail. The superblock is on ->fs_supers, ->s_umount is held exclusive, ->s_active is 1. Along comes two more processes, trying to mount the same thing; sget() in each is picking that superblock, bumping ->s_count and trying to grab ->s_umount. ->s_active is 3 now. Original mount(2) finally gets to deactivate_locked_super() on failure; ->s_active is 2, superblock is still ->fs_supers because shutdown will *not* happen until ->s_active hits 0. ->s_umount is dropped and now we have two processes chasing each other: s_active = 2, A acquired ->s_umount, B blocked A sees that the damn thing is stillborn, does deactivate_locked_super() s_active = 1, A drops ->s_umount, B gets it A restarts the search and finds the same superblock. And bumps it ->s_active. s_active = 2, B holds ->s_umount, A blocked on trying to get it ... and we are in the earlier situation with A and B switched places. The root cause, of course, is that ->s_active should not grow until we'd got MS_BORN. Then failing ->mount() will have deactivate_locked_super() shut the damn thing down. Fortunately, it's easy to do - the key point is that grab_super() is called only for superblocks currently on ->fs_supers, so it can bump ->s_count and grab ->s_umount first, then check MS_BORN and bump ->s_active; we must never increment ->s_count for superblocks past ->kill_sb(), but grab_super() is never called for those. The bug is pretty old; we would've caught it by now, if not for accidental exclusion between sget() for block filesystems; the things like cgroup or e.g. mtd-based filesystems don't have anything of that sort, so they get bitten. The right way to deal with that is obviously to fix sget()... Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-07-20 07:13:55 +08:00
up_write(&sb->s_umount);
return sb;
}
}
spin_unlock(&sb_lock);
return NULL;
}
struct super_block *user_get_super(dev_t dev)
{
struct super_block *sb;
spin_lock(&sb_lock);
rescan:
list_for_each_entry(sb, &super_blocks, s_list) {
if (hlist_unhashed(&sb->s_instances))
continue;
if (sb->s_dev == dev) {
sb->s_count++;
spin_unlock(&sb_lock);
down_read(&sb->s_umount);
/* still alive? */
if (sb->s_root && (sb->s_flags & MS_BORN))
return sb;
up_read(&sb->s_umount);
/* nope, got unmounted */
spin_lock(&sb_lock);
__put_super(sb);
goto rescan;
}
}
spin_unlock(&sb_lock);
return NULL;
}
/**
* do_remount_sb - asks filesystem to change mount options.
* @sb: superblock in question
* @flags: numeric part of options
* @data: the rest of options
* @force: whether or not to force the change
*
* Alters the mount options of a mounted file system.
*/
int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
{
int retval;
int remount_ro;
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 22:20:34 +08:00
if (sb->s_writers.frozen != SB_UNFROZEN)
return -EBUSY;
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
#ifdef CONFIG_BLOCK
if (!(flags & MS_RDONLY) && bdev_read_only(sb->s_bdev))
return -EACCES;
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
#endif
if (flags & MS_RDONLY)
acct_auto_close(sb);
shrink_dcache_sb(sb);
sync_filesystem(sb);
2009-12-22 08:28:53 +08:00
remount_ro = (flags & MS_RDONLY) && !(sb->s_flags & MS_RDONLY);
/* If we are remounting RDONLY and current sb is read/write,
make sure there are no rw files opened */
2009-12-22 08:28:53 +08:00
if (remount_ro) {
if (force) {
mark_files_ro(sb);
} else {
retval = sb_prepare_remount_readonly(sb);
if (retval)
return retval;
}
}
if (sb->s_op->remount_fs) {
retval = sb->s_op->remount_fs(sb, &flags, data);
if (retval) {
if (!force)
goto cancel_readonly;
/* If forced remount, go ahead despite any errors */
WARN(1, "forced remount of a %s fs returned %i\n",
sb->s_type->name, retval);
}
}
sb->s_flags = (sb->s_flags & ~MS_RMT_MASK) | (flags & MS_RMT_MASK);
/* Needs to be ordered wrt mnt_is_readonly() */
smp_wmb();
sb->s_readonly_remount = 0;
2009-12-22 08:28:53 +08:00
/*
* Some filesystems modify their metadata via some other path than the
* bdev buffer cache (eg. use a private mapping, or directories in
* pagecache, etc). Also file data modifications go via their own
* mappings. So If we try to mount readonly then copy the filesystem
* from bdev, we could get stale data, so invalidate it to give a best
* effort at coherency.
*/
if (remount_ro && sb->s_bdev)
invalidate_bdev(sb->s_bdev);
return 0;
cancel_readonly:
sb->s_readonly_remount = 0;
return retval;
}
static void do_emergency_remount(struct work_struct *work)
{
struct super_block *sb, *p = NULL;
spin_lock(&sb_lock);
list_for_each_entry(sb, &super_blocks, s_list) {
if (hlist_unhashed(&sb->s_instances))
continue;
sb->s_count++;
spin_unlock(&sb_lock);
down_write(&sb->s_umount);
if (sb->s_root && sb->s_bdev && (sb->s_flags & MS_BORN) &&
!(sb->s_flags & MS_RDONLY)) {
/*
* What lock protects sb->s_flags??
*/
do_remount_sb(sb, MS_RDONLY, NULL, 1);
}
up_write(&sb->s_umount);
spin_lock(&sb_lock);
if (p)
__put_super(p);
p = sb;
}
if (p)
__put_super(p);
spin_unlock(&sb_lock);
kfree(work);
printk("Emergency Remount complete\n");
}
void emergency_remount(void)
{
struct work_struct *work;
work = kmalloc(sizeof(*work), GFP_ATOMIC);
if (work) {
INIT_WORK(work, do_emergency_remount);
schedule_work(work);
}
}
/*
* Unnamed block devices are dummy devices used by virtual
* filesystems which don't use real block-devices. -- jrs
*/
static DEFINE_IDA(unnamed_dev_ida);
static DEFINE_SPINLOCK(unnamed_dev_lock);/* protects the above */
static int unnamed_dev_start = 0; /* don't bother trying below it */
int get_anon_bdev(dev_t *p)
{
int dev;
int error;
retry:
if (ida_pre_get(&unnamed_dev_ida, GFP_ATOMIC) == 0)
return -ENOMEM;
spin_lock(&unnamed_dev_lock);
error = ida_get_new_above(&unnamed_dev_ida, unnamed_dev_start, &dev);
if (!error)
unnamed_dev_start = dev + 1;
spin_unlock(&unnamed_dev_lock);
if (error == -EAGAIN)
/* We raced and lost with another CPU. */
goto retry;
else if (error)
return -EAGAIN;
idr: remove MAX_IDR_MASK and move left MAX_IDR_* into idr.c MAX_IDR_MASK is another weirdness in the idr interface. As idr covers whole positive integer range, it's defined as 0x7fffffff or INT_MAX. Its usage in idr_find(), idr_replace() and idr_remove() is bizarre. They basically mask off the sign bit and operate on the rest, so if the caller, by accident, passes in a negative number, the sign bit will be masked off and the remaining part will be used as if that was the input, which is worse than crashing. The constant is visible in idr.h and there are several users in the kernel. * drivers/i2c/i2c-core.c:i2c_add_numbered_adapter() Basically used to test if adap->nr is a negative number which isn't -1 and returns -EINVAL if so. idr_alloc() already has negative @start checking (w/ WARN_ON_ONCE), so this can go away. * drivers/infiniband/core/cm.c:cm_alloc_id() drivers/infiniband/hw/mlx4/cm.c:id_map_alloc() Used to wrap cyclic @start. Can be replaced with max(next, 0). Note that this type of cyclic allocation using idr is buggy. These are prone to spurious -ENOSPC failure after the first wraparound. * fs/super.c:get_anon_bdev() The ID allocated from ida is masked off before being tested whether it's inside valid range. ida allocated ID can never be a negative number and the masking is unnecessary. Update idr_*() functions to fail with -EINVAL when negative @id is specified and update other MAX_IDR_MASK users as described above. This leaves MAX_IDR_MASK without any user, remove it and relocate other MAX_IDR_* constants to lib/idr.c. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Jean Delvare <khali@linux-fr.org> Cc: Roland Dreier <roland@kernel.org> Cc: Sean Hefty <sean.hefty@intel.com> Cc: Hal Rosenstock <hal.rosenstock@gmail.com> Cc: "Marciniszyn, Mike" <mike.marciniszyn@intel.com> Cc: Jack Morgenstein <jackm@dev.mellanox.co.il> Cc: Or Gerlitz <ogerlitz@mellanox.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Acked-by: Wolfram Sang <wolfram@the-dreams.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 09:05:04 +08:00
if (dev == (1 << MINORBITS)) {
spin_lock(&unnamed_dev_lock);
ida_remove(&unnamed_dev_ida, dev);
if (unnamed_dev_start > dev)
unnamed_dev_start = dev;
spin_unlock(&unnamed_dev_lock);
return -EMFILE;
}
*p = MKDEV(0, dev & MINORMASK);
return 0;
}
EXPORT_SYMBOL(get_anon_bdev);
void free_anon_bdev(dev_t dev)
{
int slot = MINOR(dev);
spin_lock(&unnamed_dev_lock);
ida_remove(&unnamed_dev_ida, slot);
if (slot < unnamed_dev_start)
unnamed_dev_start = slot;
spin_unlock(&unnamed_dev_lock);
}
EXPORT_SYMBOL(free_anon_bdev);
int set_anon_super(struct super_block *s, void *data)
{
int error = get_anon_bdev(&s->s_dev);
if (!error)
s->s_bdi = &noop_backing_dev_info;
return error;
}
EXPORT_SYMBOL(set_anon_super);
void kill_anon_super(struct super_block *sb)
{
dev_t dev = sb->s_dev;
generic_shutdown_super(sb);
free_anon_bdev(dev);
}
EXPORT_SYMBOL(kill_anon_super);
void kill_litter_super(struct super_block *sb)
{
if (sb->s_root)
d_genocide(sb->s_root);
kill_anon_super(sb);
}
EXPORT_SYMBOL(kill_litter_super);
static int ns_test_super(struct super_block *sb, void *data)
{
return sb->s_fs_info == data;
}
static int ns_set_super(struct super_block *sb, void *data)
{
sb->s_fs_info = data;
return set_anon_super(sb, NULL);
}
struct dentry *mount_ns(struct file_system_type *fs_type, int flags,
void *data, int (*fill_super)(struct super_block *, void *, int))
{
struct super_block *sb;
sb = sget(fs_type, ns_test_super, ns_set_super, flags, data);
if (IS_ERR(sb))
return ERR_CAST(sb);
if (!sb->s_root) {
int err;
err = fill_super(sb, data, flags & MS_SILENT ? 1 : 0);
if (err) {
deactivate_locked_super(sb);
return ERR_PTR(err);
}
sb->s_flags |= MS_ACTIVE;
}
return dget(sb->s_root);
}
EXPORT_SYMBOL(mount_ns);
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
#ifdef CONFIG_BLOCK
static int set_bdev_super(struct super_block *s, void *data)
{
s->s_bdev = data;
s->s_dev = s->s_bdev->bd_dev;
/*
* We set the bdi here to the queue backing, file systems can
* overwrite this in ->fill_super()
*/
s->s_bdi = &bdev_get_queue(s->s_bdev)->backing_dev_info;
return 0;
}
static int test_bdev_super(struct super_block *s, void *data)
{
return (void *)s->s_bdev == data;
}
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))
{
struct block_device *bdev;
struct super_block *s;
fmode_t mode = FMODE_READ | FMODE_EXCL;
int error = 0;
if (!(flags & MS_RDONLY))
mode |= FMODE_WRITE;
bdev = blkdev_get_by_path(dev_name, mode, fs_type);
if (IS_ERR(bdev))
return ERR_CAST(bdev);
/*
* once the super is inserted into the list by sget, s_umount
* will protect the lockfs code from trying to start a snapshot
* while we are mounting
*/
mutex_lock(&bdev->bd_fsfreeze_mutex);
if (bdev->bd_fsfreeze_count > 0) {
mutex_unlock(&bdev->bd_fsfreeze_mutex);
error = -EBUSY;
goto error_bdev;
}
s = sget(fs_type, test_bdev_super, set_bdev_super, flags | MS_NOSEC,
bdev);
mutex_unlock(&bdev->bd_fsfreeze_mutex);
if (IS_ERR(s))
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
goto error_s;
if (s->s_root) {
if ((flags ^ s->s_flags) & MS_RDONLY) {
deactivate_locked_super(s);
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
error = -EBUSY;
goto error_bdev;
}
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
/*
* s_umount nests inside bd_mutex during
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 18:55:17 +08:00
* __invalidate_device(). blkdev_put() acquires
* bd_mutex and can't be called under s_umount. Drop
* s_umount temporarily. This is safe as we're
* holding an active reference.
*/
up_write(&s->s_umount);
blkdev_put(bdev, mode);
down_write(&s->s_umount);
} else {
char b[BDEVNAME_SIZE];
s->s_mode = mode;
strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
sb_set_blocksize(s, block_size(bdev));
error = fill_super(s, data, flags & MS_SILENT ? 1 : 0);
if (error) {
deactivate_locked_super(s);
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
goto error;
}
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
s->s_flags |= MS_ACTIVE;
bdev->bd_super = s;
}
return dget(s->s_root);
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
error_s:
error = PTR_ERR(s);
error_bdev:
blkdev_put(bdev, mode);
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
error:
return ERR_PTR(error);
}
EXPORT_SYMBOL(mount_bdev);
void kill_block_super(struct super_block *sb)
{
struct block_device *bdev = sb->s_bdev;
fmode_t mode = sb->s_mode;
bdev->bd_super = NULL;
generic_shutdown_super(sb);
sync_blockdev(bdev);
WARN_ON_ONCE(!(mode & FMODE_EXCL));
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 18:55:17 +08:00
blkdev_put(bdev, mode | FMODE_EXCL);
}
EXPORT_SYMBOL(kill_block_super);
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
#endif
struct dentry *mount_nodev(struct file_system_type *fs_type,
int flags, void *data,
int (*fill_super)(struct super_block *, void *, int))
{
int error;
struct super_block *s = sget(fs_type, NULL, set_anon_super, flags, NULL);
if (IS_ERR(s))
return ERR_CAST(s);
error = fill_super(s, data, flags & MS_SILENT ? 1 : 0);
if (error) {
deactivate_locked_super(s);
return ERR_PTR(error);
}
s->s_flags |= MS_ACTIVE;
return dget(s->s_root);
}
EXPORT_SYMBOL(mount_nodev);
static int compare_single(struct super_block *s, void *p)
{
return 1;
}
struct dentry *mount_single(struct file_system_type *fs_type,
int flags, void *data,
int (*fill_super)(struct super_block *, void *, int))
{
struct super_block *s;
int error;
s = sget(fs_type, compare_single, set_anon_super, flags, NULL);
if (IS_ERR(s))
return ERR_CAST(s);
if (!s->s_root) {
error = fill_super(s, data, flags & MS_SILENT ? 1 : 0);
if (error) {
deactivate_locked_super(s);
return ERR_PTR(error);
}
s->s_flags |= MS_ACTIVE;
} else {
do_remount_sb(s, flags, data, 0);
}
return dget(s->s_root);
}
EXPORT_SYMBOL(mount_single);
struct dentry *
mount_fs(struct file_system_type *type, int flags, const char *name, void *data)
{
struct dentry *root;
struct super_block *sb;
char *secdata = NULL;
int error = -ENOMEM;
if (data && !(type->fs_flags & FS_BINARY_MOUNTDATA)) {
secdata = alloc_secdata();
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
if (!secdata)
goto out;
error = security_sb_copy_data(data, secdata);
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
if (error)
goto out_free_secdata;
}
root = type->mount(type, flags, name, data);
if (IS_ERR(root)) {
error = PTR_ERR(root);
goto out_free_secdata;
}
sb = root->d_sb;
BUG_ON(!sb);
WARN_ON(!sb->s_bdi);
WARN_ON(sb->s_bdi == &default_backing_dev_info);
sb->s_flags |= MS_BORN;
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
error = security_sb_kern_mount(sb, flags, secdata);
if (error)
goto out_sb;
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
/*
* filesystems should never set s_maxbytes larger than MAX_LFS_FILESIZE
* but s_maxbytes was an unsigned long long for many releases. Throw
* this warning for a little while to try and catch filesystems that
* violate this rule.
*/
WARN((sb->s_maxbytes < 0), "%s set sb->s_maxbytes to "
"negative value (%lld)\n", type->name, sb->s_maxbytes);
up_write(&sb->s_umount);
free_secdata(secdata);
return root;
out_sb:
dput(root);
deactivate_locked_super(sb);
out_free_secdata:
free_secdata(secdata);
out:
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
return ERR_PTR(error);
}
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 22:20:34 +08:00
/*
* This is an internal function, please use sb_end_{write,pagefault,intwrite}
* instead.
*/
void __sb_end_write(struct super_block *sb, int level)
{
percpu_counter_dec(&sb->s_writers.counter[level-1]);
/*
* Make sure s_writers are updated before we wake up waiters in
* freeze_super().
*/
smp_mb();
if (waitqueue_active(&sb->s_writers.wait))
wake_up(&sb->s_writers.wait);
rwsem_release(&sb->s_writers.lock_map[level-1], 1, _RET_IP_);
}
EXPORT_SYMBOL(__sb_end_write);
#ifdef CONFIG_LOCKDEP
/*
* We want lockdep to tell us about possible deadlocks with freezing but
* it's it bit tricky to properly instrument it. Getting a freeze protection
* works as getting a read lock but there are subtle problems. XFS for example
* gets freeze protection on internal level twice in some cases, which is OK
* only because we already hold a freeze protection also on higher level. Due
* to these cases we have to tell lockdep we are doing trylock when we
* already hold a freeze protection for a higher freeze level.
*/
static void acquire_freeze_lock(struct super_block *sb, int level, bool trylock,
unsigned long ip)
{
int i;
if (!trylock) {
for (i = 0; i < level - 1; i++)
if (lock_is_held(&sb->s_writers.lock_map[i])) {
trylock = true;
break;
}
}
rwsem_acquire_read(&sb->s_writers.lock_map[level-1], 0, trylock, ip);
}
#endif
/*
* This is an internal function, please use sb_start_{write,pagefault,intwrite}
* instead.
*/
int __sb_start_write(struct super_block *sb, int level, bool wait)
{
retry:
if (unlikely(sb->s_writers.frozen >= level)) {
if (!wait)
return 0;
wait_event(sb->s_writers.wait_unfrozen,
sb->s_writers.frozen < level);
}
#ifdef CONFIG_LOCKDEP
acquire_freeze_lock(sb, level, !wait, _RET_IP_);
#endif
percpu_counter_inc(&sb->s_writers.counter[level-1]);
/*
* Make sure counter is updated before we check for frozen.
* freeze_super() first sets frozen and then checks the counter.
*/
smp_mb();
if (unlikely(sb->s_writers.frozen >= level)) {
__sb_end_write(sb, level);
goto retry;
}
return 1;
}
EXPORT_SYMBOL(__sb_start_write);
/**
* sb_wait_write - wait until all writers to given file system finish
* @sb: the super for which we wait
* @level: type of writers we wait for (normal vs page fault)
*
* This function waits until there are no writers of given type to given file
* system. Caller of this function should make sure there can be no new writers
* of type @level before calling this function. Otherwise this function can
* livelock.
*/
static void sb_wait_write(struct super_block *sb, int level)
{
s64 writers;
/*
* We just cycle-through lockdep here so that it does not complain
* about returning with lock to userspace
*/
rwsem_acquire(&sb->s_writers.lock_map[level-1], 0, 0, _THIS_IP_);
rwsem_release(&sb->s_writers.lock_map[level-1], 1, _THIS_IP_);
do {
DEFINE_WAIT(wait);
/*
* We use a barrier in prepare_to_wait() to separate setting
* of frozen and checking of the counter
*/
prepare_to_wait(&sb->s_writers.wait, &wait,
TASK_UNINTERRUPTIBLE);
writers = percpu_counter_sum(&sb->s_writers.counter[level-1]);
if (writers)
schedule();
finish_wait(&sb->s_writers.wait, &wait);
} while (writers);
}
/**
* freeze_super - lock the filesystem and force it into a consistent state
* @sb: the super to lock
*
* Syncs the super to make sure the filesystem is consistent and calls the fs's
* freeze_fs. Subsequent calls to this without first thawing the fs will return
* -EBUSY.
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 22:20:34 +08:00
*
* During this function, sb->s_writers.frozen goes through these values:
*
* SB_UNFROZEN: File system is normal, all writes progress as usual.
*
* SB_FREEZE_WRITE: The file system is in the process of being frozen. New
* writes should be blocked, though page faults are still allowed. We wait for
* all writes to complete and then proceed to the next stage.
*
* SB_FREEZE_PAGEFAULT: Freezing continues. Now also page faults are blocked
* but internal fs threads can still modify the filesystem (although they
* should not dirty new pages or inodes), writeback can run etc. After waiting
* for all running page faults we sync the filesystem which will clean all
* dirty pages and inodes (no new dirty pages or inodes can be created when
* sync is running).
*
* SB_FREEZE_FS: The file system is frozen. Now all internal sources of fs
* modification are blocked (e.g. XFS preallocation truncation on inode
* reclaim). This is usually implemented by blocking new transactions for
* filesystems that have them and need this additional guard. After all
* internal writers are finished we call ->freeze_fs() to finish filesystem
* freezing. Then we transition to SB_FREEZE_COMPLETE state. This state is
* mostly auxiliary for filesystems to verify they do not modify frozen fs.
*
* sb->s_writers.frozen is protected by sb->s_umount.
*/
int freeze_super(struct super_block *sb)
{
int ret;
atomic_inc(&sb->s_active);
down_write(&sb->s_umount);
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 22:20:34 +08:00
if (sb->s_writers.frozen != SB_UNFROZEN) {
deactivate_locked_super(sb);
return -EBUSY;
}
if (!(sb->s_flags & MS_BORN)) {
up_write(&sb->s_umount);
return 0; /* sic - it's "nothing to do" */
}
if (sb->s_flags & MS_RDONLY) {
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 22:20:34 +08:00
/* Nothing to do really... */
sb->s_writers.frozen = SB_FREEZE_COMPLETE;
up_write(&sb->s_umount);
return 0;
}
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 22:20:34 +08:00
/* From now on, no new normal writers can start */
sb->s_writers.frozen = SB_FREEZE_WRITE;
smp_wmb();
/* Release s_umount to preserve sb_start_write -> s_umount ordering */
up_write(&sb->s_umount);
sb_wait_write(sb, SB_FREEZE_WRITE);
/* Now we go and block page faults... */
down_write(&sb->s_umount);
sb->s_writers.frozen = SB_FREEZE_PAGEFAULT;
smp_wmb();
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 22:20:34 +08:00
sb_wait_write(sb, SB_FREEZE_PAGEFAULT);
/* All writers are done so after syncing there won't be dirty data */
sync_filesystem(sb);
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 22:20:34 +08:00
/* Now wait for internal filesystem counter */
sb->s_writers.frozen = SB_FREEZE_FS;
smp_wmb();
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 22:20:34 +08:00
sb_wait_write(sb, SB_FREEZE_FS);
if (sb->s_op->freeze_fs) {
ret = sb->s_op->freeze_fs(sb);
if (ret) {
printk(KERN_ERR
"VFS:Filesystem freeze failed\n");
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 22:20:34 +08:00
sb->s_writers.frozen = SB_UNFROZEN;
smp_wmb();
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 22:20:34 +08:00
wake_up(&sb->s_writers.wait_unfrozen);
deactivate_locked_super(sb);
return ret;
}
}
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 22:20:34 +08:00
/*
* This is just for debugging purposes so that fs can warn if it
* sees write activity when frozen is set to SB_FREEZE_COMPLETE.
*/
sb->s_writers.frozen = SB_FREEZE_COMPLETE;
up_write(&sb->s_umount);
return 0;
}
EXPORT_SYMBOL(freeze_super);
/**
* thaw_super -- unlock filesystem
* @sb: the super to thaw
*
* Unlocks the filesystem and marks it writeable again after freeze_super().
*/
int thaw_super(struct super_block *sb)
{
int error;
down_write(&sb->s_umount);
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 22:20:34 +08:00
if (sb->s_writers.frozen == SB_UNFROZEN) {
up_write(&sb->s_umount);
return -EINVAL;
}
if (sb->s_flags & MS_RDONLY)
goto out;
if (sb->s_op->unfreeze_fs) {
error = sb->s_op->unfreeze_fs(sb);
if (error) {
printk(KERN_ERR
"VFS:Filesystem thaw failed\n");
up_write(&sb->s_umount);
return error;
}
}
out:
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 22:20:34 +08:00
sb->s_writers.frozen = SB_UNFROZEN;
smp_wmb();
fs: Improve filesystem freezing handling vfs_check_frozen() tests are racy since the filesystem can be frozen just after the test is performed. Thus in write paths we can end up marking some pages or inodes dirty even though the file system is already frozen. This creates problems with flusher thread hanging on frozen filesystem. Another problem is that exclusion between ->page_mkwrite() and filesystem freezing has been handled by setting page dirty and then verifying s_frozen. This guaranteed that either the freezing code sees the faulted page, writes it, and writeprotects it again or we see s_frozen set and bail out of page fault. This works to protect from page being marked writeable while filesystem freezing is running but has an unpleasant artefact of leaving dirty (although unmodified and writeprotected) pages on frozen filesystem resulting in similar problems with flusher thread as the first problem. This patch aims at providing exclusion between write paths and filesystem freezing. We implement a writer-freeze read-write semaphore in the superblock. Actually, there are three such semaphores because of lock ranking reasons - one for page fault handlers (->page_mkwrite), one for all other writers, and one of internal filesystem purposes (used e.g. to track running transactions). Write paths which should block freezing (e.g. directory operations, ->aio_write(), ->page_mkwrite) hold reader side of the semaphore. Code freezing the filesystem takes the writer side. Only that we don't really want to bounce cachelines of the semaphores between CPUs for each write happening. So we implement the reader side of the semaphore as a per-cpu counter and the writer side is implemented using s_writers.frozen superblock field. [AV: microoptimize sb_start_write(); we want it fast in normal case] BugLink: https://bugs.launchpad.net/bugs/897421 Tested-by: Kamal Mostafa <kamal@canonical.com> Tested-by: Peter M. Petrakis <peter.petrakis@canonical.com> Tested-by: Dann Frazier <dann.frazier@canonical.com> Tested-by: Massimo Morana <massimo.morana@canonical.com> Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-12 22:20:34 +08:00
wake_up(&sb->s_writers.wait_unfrozen);
deactivate_locked_super(sb);
return 0;
}
EXPORT_SYMBOL(thaw_super);