linux-sg2042/fs/dcache.c

3443 lines
88 KiB
C
Raw Normal View History

/*
* fs/dcache.c
*
* Complete reimplementation
* (C) 1997 Thomas Schoebel-Theuer,
* with heavy changes by Linus Torvalds
*/
/*
* Notes on the allocation strategy:
*
* The dcache is a master of the icache - whenever a dcache entry
* exists, the inode will always exist. "iput()" is done either when
* the dcache entry is deleted or garbage collected.
*/
#include <linux/syscalls.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/fsnotify.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/hash.h>
#include <linux/cache.h>
#include <linux/export.h>
#include <linux/mount.h>
#include <linux/file.h>
#include <asm/uaccess.h>
#include <linux/security.h>
#include <linux/seqlock.h>
#include <linux/swap.h>
#include <linux/bootmem.h>
#include <linux/fs_struct.h>
#include <linux/hardirq.h>
#include <linux/bit_spinlock.h>
#include <linux/rculist_bl.h>
#include <linux/prefetch.h>
#include <linux/ratelimit.h>
#include <linux/list_lru.h>
#include "internal.h"
#include "mount.h"
/*
* Usage:
* dcache->d_inode->i_lock protects:
* - i_dentry, d_alias, d_inode of aliases
* dcache_hash_bucket lock protects:
* - the dcache hash table
* s_anon bl list spinlock protects:
* - the s_anon list (see __d_drop)
dentry: move to per-sb LRU locks With the dentry LRUs being per-sb structures, there is no real need for a global dentry_lru_lock. The locking can be made more fine-grained by moving to a per-sb LRU lock, isolating the LRU operations of different filesytsems completely from each other. The need for this is independent of any performance consideration that may arise: in the interest of abstracting the lru operations away, it is mandatory that each lru works around its own lock instead of a global lock for all of them. [glommer@openvz.org: updated changelog ] Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> Reviewed-by: Christoph Hellwig <hch@lst.de> 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 08:17:55 +08:00
* dentry->d_sb->s_dentry_lru_lock protects:
* - the dcache lru lists and counters
* d_lock protects:
* - d_flags
* - d_name
* - d_lru
* - d_count
* - d_unhashed()
* - d_parent and d_subdirs
* - childrens' d_child and d_parent
* - d_alias, d_inode
*
* Ordering:
* dentry->d_inode->i_lock
* dentry->d_lock
dentry: move to per-sb LRU locks With the dentry LRUs being per-sb structures, there is no real need for a global dentry_lru_lock. The locking can be made more fine-grained by moving to a per-sb LRU lock, isolating the LRU operations of different filesytsems completely from each other. The need for this is independent of any performance consideration that may arise: in the interest of abstracting the lru operations away, it is mandatory that each lru works around its own lock instead of a global lock for all of them. [glommer@openvz.org: updated changelog ] Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> Reviewed-by: Christoph Hellwig <hch@lst.de> 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 08:17:55 +08:00
* dentry->d_sb->s_dentry_lru_lock
* dcache_hash_bucket lock
* s_anon lock
*
* If there is an ancestor relationship:
* dentry->d_parent->...->d_parent->d_lock
* ...
* dentry->d_parent->d_lock
* dentry->d_lock
*
* If no ancestor relationship:
* if (dentry1 < dentry2)
* dentry1->d_lock
* dentry2->d_lock
*/
int sysctl_vfs_cache_pressure __read_mostly = 100;
EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure);
__cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock);
EXPORT_SYMBOL(rename_lock);
static struct kmem_cache *dentry_cache __read_mostly;
/*
* This is the single most critical data structure when it comes
* to the dcache: the hashtable for lookups. Somebody should try
* to make this good - I've just made it work.
*
* This hash-function tries to avoid losing too many bits of hash
* information, yet avoid using a prime hash-size or similar.
*/
static unsigned int d_hash_mask __read_mostly;
static unsigned int d_hash_shift __read_mostly;
static struct hlist_bl_head *dentry_hashtable __read_mostly;
static inline struct hlist_bl_head *d_hash(const struct dentry *parent,
vfs: get rid of batshit-insane pointless dentry hash calculations For some odd historical reason, the final mixing round for the dentry cache hash table lookup had an insane "xor with big constant" logic. In two places. The big constant that is being xor'ed is GOLDEN_RATIO_PRIME, which is a fairly random-looking number that is designed to be *multiplied* with so that the bits get spread out over a whole long-word. But xor'ing with it is insane. It doesn't really even change the hash - it really only shifts the hash around in the hash table. To make matters worse, the insane big constant is different on 32-bit and 64-bit builds, even though the name hash bits we use are always 32-bit (and the bits from the pointer we mix in effectively are too). It's all total voodoo programming, in other words. Now, some testing and analysis of the hash chains shows that the rest of the hash function seems to be fairly good. It does pick the right bits of the parent dentry pointer, for example, and while it's generally a bad idea to use an xor to mix down the upper bits (because if there is a repeating pattern, the xor can cause "destructive interference"), it seems to not have been a disaster. For example, replacing the hash with the normal "hash_long()" code (that uses the GOLDEN_RATIO_PRIME constant correctly, btw) actually just makes the hash worse. The hand-picked hash knew which bits of the pointer had the highest entropy, and hash_long() ends up mixing bits less optimally at least in some trivial tests. So the hash function overall seems fine, it just has that really odd "shift result around by a constant xor". So get rid of the silly xor, and replace the down-mixing of the bits with an add instead of an xor that tends to not have the same kind of destructive interference issues. Some stats on the resulting hash chains shows that they look statistically identical before and after, but the code is simpler and no longer makes you go "WTF?". Also, the incoming hash really is just "unsigned int", not a long, and there's no real point to worry about the high 26 bits of the dentry pointer for the 64-bit case, because they are all going to be identical anyway. So also change the hashing to be done in the more natural 'unsigned int' that is the real size of the actual hashed data anyway. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-20 07:19:53 +08:00
unsigned int hash)
{
vfs: get rid of batshit-insane pointless dentry hash calculations For some odd historical reason, the final mixing round for the dentry cache hash table lookup had an insane "xor with big constant" logic. In two places. The big constant that is being xor'ed is GOLDEN_RATIO_PRIME, which is a fairly random-looking number that is designed to be *multiplied* with so that the bits get spread out over a whole long-word. But xor'ing with it is insane. It doesn't really even change the hash - it really only shifts the hash around in the hash table. To make matters worse, the insane big constant is different on 32-bit and 64-bit builds, even though the name hash bits we use are always 32-bit (and the bits from the pointer we mix in effectively are too). It's all total voodoo programming, in other words. Now, some testing and analysis of the hash chains shows that the rest of the hash function seems to be fairly good. It does pick the right bits of the parent dentry pointer, for example, and while it's generally a bad idea to use an xor to mix down the upper bits (because if there is a repeating pattern, the xor can cause "destructive interference"), it seems to not have been a disaster. For example, replacing the hash with the normal "hash_long()" code (that uses the GOLDEN_RATIO_PRIME constant correctly, btw) actually just makes the hash worse. The hand-picked hash knew which bits of the pointer had the highest entropy, and hash_long() ends up mixing bits less optimally at least in some trivial tests. So the hash function overall seems fine, it just has that really odd "shift result around by a constant xor". So get rid of the silly xor, and replace the down-mixing of the bits with an add instead of an xor that tends to not have the same kind of destructive interference issues. Some stats on the resulting hash chains shows that they look statistically identical before and after, but the code is simpler and no longer makes you go "WTF?". Also, the incoming hash really is just "unsigned int", not a long, and there's no real point to worry about the high 26 bits of the dentry pointer for the 64-bit case, because they are all going to be identical anyway. So also change the hashing to be done in the more natural 'unsigned int' that is the real size of the actual hashed data anyway. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-20 07:19:53 +08:00
hash += (unsigned long) parent / L1_CACHE_BYTES;
hash = hash + (hash >> d_hash_shift);
return dentry_hashtable + (hash & d_hash_mask);
}
/* Statistics gathering. */
struct dentry_stat_t dentry_stat = {
.age_limit = 45,
};
fs: bump inode and dentry counters to long This series reworks our current object cache shrinking infrastructure in two main ways: * Noticing that a lot of users copy and paste their own version of LRU lists for objects, we put some effort in providing a generic version. It is modeled after the filesystem users: dentries, inodes, and xfs (for various tasks), but we expect that other users could benefit in the near future with little or no modification. Let us know if you have any issues. * The underlying list_lru being proposed automatically and transparently keeps the elements in per-node lists, and is able to manipulate the node lists individually. Given this infrastructure, we are able to modify the up-to-now hammer called shrink_slab to proceed with node-reclaim instead of always searching memory from all over like it has been doing. Per-node lru lists are also expected to lead to less contention in the lru locks on multi-node scans, since we are now no longer fighting for a global lock. The locks usually disappear from the profilers with this change. Although we have no official benchmarks for this version - be our guest to independently evaluate this - earlier versions of this series were performance tested (details at http://permalink.gmane.org/gmane.linux.kernel.mm/100537) yielding no visible performance regressions while yielding a better qualitative behavior in NUMA machines. With this infrastructure in place, we can use the list_lru entry point to provide memcg isolation and per-memcg targeted reclaim. Historically, those two pieces of work have been posted together. This version presents only the infrastructure work, deferring the memcg work for a later time, so we can focus on getting this part tested. You can see more about the history of such work at http://lwn.net/Articles/552769/ Dave Chinner (18): dcache: convert dentry_stat.nr_unused to per-cpu counters dentry: move to per-sb LRU locks dcache: remove dentries from LRU before putting on dispose list mm: new shrinker API shrinker: convert superblock shrinkers to new API list: add a new LRU list type inode: convert inode lru list to generic lru list code. dcache: convert to use new lru list infrastructure list_lru: per-node list infrastructure shrinker: add node awareness fs: convert inode and dentry shrinking to be node aware xfs: convert buftarg LRU to generic code xfs: rework buffer dispose list tracking xfs: convert dquot cache lru to list_lru fs: convert fs shrinkers to new scan/count API drivers: convert shrinkers to new count/scan API shrinker: convert remaining shrinkers to count/scan API shrinker: Kill old ->shrink API. Glauber Costa (7): fs: bump inode and dentry counters to long super: fix calculation of shrinkable objects for small numbers list_lru: per-node API vmscan: per-node deferred work i915: bail out earlier when shrinker cannot acquire mutex hugepage: convert huge zero page shrinker to new shrinker API list_lru: dynamically adjust node arrays This patch: There are situations in very large machines in which we can have a large quantity of dirty inodes, unused dentries, etc. This is particularly true when umounting a filesystem, where eventually since every live object will eventually be discarded. Dave Chinner reported a problem with this while experimenting with the shrinker revamp patchset. So we believe it is time for a change. This patch just moves int to longs. Machines where it matters should have a big long anyway. Signed-off-by: Glauber Costa <glommer@openvz.org> Cc: Dave Chinner <dchinner@redhat.com> 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: Dave Chinner <dchinner@redhat.com> 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
static DEFINE_PER_CPU(long, nr_dentry);
dcache: convert dentry_stat.nr_unused to per-cpu counters Before we split up the dcache_lru_lock, the unused dentry counter needs to be made independent of the global dcache_lru_lock. Convert it to per-cpu counters to do this. Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> Reviewed-by: Christoph Hellwig <hch@lst.de> 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 08:17:54 +08:00
static DEFINE_PER_CPU(long, nr_dentry_unused);
#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
dcache: convert dentry_stat.nr_unused to per-cpu counters Before we split up the dcache_lru_lock, the unused dentry counter needs to be made independent of the global dcache_lru_lock. Convert it to per-cpu counters to do this. Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> Reviewed-by: Christoph Hellwig <hch@lst.de> 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 08:17:54 +08:00
/*
* Here we resort to our own counters instead of using generic per-cpu counters
* for consistency with what the vfs inode code does. We are expected to harvest
* better code and performance by having our own specialized counters.
*
* Please note that the loop is done over all possible CPUs, not over all online
* CPUs. The reason for this is that we don't want to play games with CPUs going
* on and off. If one of them goes off, we will just keep their counters.
*
* glommer: See cffbc8a for details, and if you ever intend to change this,
* please update all vfs counters to match.
*/
fs: bump inode and dentry counters to long This series reworks our current object cache shrinking infrastructure in two main ways: * Noticing that a lot of users copy and paste their own version of LRU lists for objects, we put some effort in providing a generic version. It is modeled after the filesystem users: dentries, inodes, and xfs (for various tasks), but we expect that other users could benefit in the near future with little or no modification. Let us know if you have any issues. * The underlying list_lru being proposed automatically and transparently keeps the elements in per-node lists, and is able to manipulate the node lists individually. Given this infrastructure, we are able to modify the up-to-now hammer called shrink_slab to proceed with node-reclaim instead of always searching memory from all over like it has been doing. Per-node lru lists are also expected to lead to less contention in the lru locks on multi-node scans, since we are now no longer fighting for a global lock. The locks usually disappear from the profilers with this change. Although we have no official benchmarks for this version - be our guest to independently evaluate this - earlier versions of this series were performance tested (details at http://permalink.gmane.org/gmane.linux.kernel.mm/100537) yielding no visible performance regressions while yielding a better qualitative behavior in NUMA machines. With this infrastructure in place, we can use the list_lru entry point to provide memcg isolation and per-memcg targeted reclaim. Historically, those two pieces of work have been posted together. This version presents only the infrastructure work, deferring the memcg work for a later time, so we can focus on getting this part tested. You can see more about the history of such work at http://lwn.net/Articles/552769/ Dave Chinner (18): dcache: convert dentry_stat.nr_unused to per-cpu counters dentry: move to per-sb LRU locks dcache: remove dentries from LRU before putting on dispose list mm: new shrinker API shrinker: convert superblock shrinkers to new API list: add a new LRU list type inode: convert inode lru list to generic lru list code. dcache: convert to use new lru list infrastructure list_lru: per-node list infrastructure shrinker: add node awareness fs: convert inode and dentry shrinking to be node aware xfs: convert buftarg LRU to generic code xfs: rework buffer dispose list tracking xfs: convert dquot cache lru to list_lru fs: convert fs shrinkers to new scan/count API drivers: convert shrinkers to new count/scan API shrinker: convert remaining shrinkers to count/scan API shrinker: Kill old ->shrink API. Glauber Costa (7): fs: bump inode and dentry counters to long super: fix calculation of shrinkable objects for small numbers list_lru: per-node API vmscan: per-node deferred work i915: bail out earlier when shrinker cannot acquire mutex hugepage: convert huge zero page shrinker to new shrinker API list_lru: dynamically adjust node arrays This patch: There are situations in very large machines in which we can have a large quantity of dirty inodes, unused dentries, etc. This is particularly true when umounting a filesystem, where eventually since every live object will eventually be discarded. Dave Chinner reported a problem with this while experimenting with the shrinker revamp patchset. So we believe it is time for a change. This patch just moves int to longs. Machines where it matters should have a big long anyway. Signed-off-by: Glauber Costa <glommer@openvz.org> Cc: Dave Chinner <dchinner@redhat.com> 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: Dave Chinner <dchinner@redhat.com> 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
static long get_nr_dentry(void)
fs: use fast counters for vfs caches percpu_counter library generates quite nasty code, so unless you need to dynamically allocate counters or take fast approximate value, a simple per cpu set of counters is much better. The percpu_counter can never be made to work as well, because it has an indirection from pointer to percpu memory, and it can't use direct this_cpu_inc interfaces because it doesn't use static PER_CPU data, so code will always be worse. In the fastpath, it is the difference between this: incl %gs:nr_dentry # nr_dentry and this: movl percpu_counter_batch(%rip), %edx # percpu_counter_batch, movl $1, %esi #, movq $nr_dentry, %rdi #, call __percpu_counter_add # (plus I clobber registers) __percpu_counter_add: pushq %rbp # movq %rsp, %rbp #, subq $32, %rsp #, movq %rbx, -24(%rbp) #, movq %r12, -16(%rbp) #, movq %r13, -8(%rbp) #, movq %rdi, %rbx # fbc, fbc #APP # 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1 movq %gs:kernel_stack,%rax #, pfo_ret__ # 0 "" 2 #NO_APP incl -8124(%rax) # <variable>.preempt_count movq 32(%rdi), %r12 # <variable>.counters, tcp_ptr__ #APP # 78 "lib/percpu_counter.c" 1 add %gs:this_cpu_off, %r12 # this_cpu_off, tcp_ptr__ # 0 "" 2 #NO_APP movslq (%r12),%r13 #* tcp_ptr__, tmp73 movslq %edx,%rax # batch, batch addq %rsi, %r13 # amount, count cmpq %rax, %r13 # batch, count jge .L27 #, negl %edx # tmp76 movslq %edx,%rdx # tmp76, tmp77 cmpq %rdx, %r13 # tmp77, count jg .L28 #, .L27: movq %rbx, %rdi # fbc, call _raw_spin_lock # addq %r13, 8(%rbx) # count, <variable>.count movq %rbx, %rdi # fbc, movl $0, (%r12) #,* tcp_ptr__ call _raw_spin_unlock # .L29: #APP # 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1 movq %gs:kernel_stack,%rax #, pfo_ret__ # 0 "" 2 #NO_APP decl -8124(%rax) # <variable>.preempt_count movq -8136(%rax), %rax #, D.14625 testb $8, %al #, D.14625 jne .L32 #, .L31: movq -24(%rbp), %rbx #, movq -16(%rbp), %r12 #, movq -8(%rbp), %r13 #, leave ret .p2align 4,,10 .p2align 3 .L28: movl %r13d, (%r12) # count,* jmp .L29 # .L32: call preempt_schedule # .p2align 4,,6 jmp .L31 # .size __percpu_counter_add, .-__percpu_counter_add .p2align 4,,15 Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:19 +08:00
{
int i;
fs: bump inode and dentry counters to long This series reworks our current object cache shrinking infrastructure in two main ways: * Noticing that a lot of users copy and paste their own version of LRU lists for objects, we put some effort in providing a generic version. It is modeled after the filesystem users: dentries, inodes, and xfs (for various tasks), but we expect that other users could benefit in the near future with little or no modification. Let us know if you have any issues. * The underlying list_lru being proposed automatically and transparently keeps the elements in per-node lists, and is able to manipulate the node lists individually. Given this infrastructure, we are able to modify the up-to-now hammer called shrink_slab to proceed with node-reclaim instead of always searching memory from all over like it has been doing. Per-node lru lists are also expected to lead to less contention in the lru locks on multi-node scans, since we are now no longer fighting for a global lock. The locks usually disappear from the profilers with this change. Although we have no official benchmarks for this version - be our guest to independently evaluate this - earlier versions of this series were performance tested (details at http://permalink.gmane.org/gmane.linux.kernel.mm/100537) yielding no visible performance regressions while yielding a better qualitative behavior in NUMA machines. With this infrastructure in place, we can use the list_lru entry point to provide memcg isolation and per-memcg targeted reclaim. Historically, those two pieces of work have been posted together. This version presents only the infrastructure work, deferring the memcg work for a later time, so we can focus on getting this part tested. You can see more about the history of such work at http://lwn.net/Articles/552769/ Dave Chinner (18): dcache: convert dentry_stat.nr_unused to per-cpu counters dentry: move to per-sb LRU locks dcache: remove dentries from LRU before putting on dispose list mm: new shrinker API shrinker: convert superblock shrinkers to new API list: add a new LRU list type inode: convert inode lru list to generic lru list code. dcache: convert to use new lru list infrastructure list_lru: per-node list infrastructure shrinker: add node awareness fs: convert inode and dentry shrinking to be node aware xfs: convert buftarg LRU to generic code xfs: rework buffer dispose list tracking xfs: convert dquot cache lru to list_lru fs: convert fs shrinkers to new scan/count API drivers: convert shrinkers to new count/scan API shrinker: convert remaining shrinkers to count/scan API shrinker: Kill old ->shrink API. Glauber Costa (7): fs: bump inode and dentry counters to long super: fix calculation of shrinkable objects for small numbers list_lru: per-node API vmscan: per-node deferred work i915: bail out earlier when shrinker cannot acquire mutex hugepage: convert huge zero page shrinker to new shrinker API list_lru: dynamically adjust node arrays This patch: There are situations in very large machines in which we can have a large quantity of dirty inodes, unused dentries, etc. This is particularly true when umounting a filesystem, where eventually since every live object will eventually be discarded. Dave Chinner reported a problem with this while experimenting with the shrinker revamp patchset. So we believe it is time for a change. This patch just moves int to longs. Machines where it matters should have a big long anyway. Signed-off-by: Glauber Costa <glommer@openvz.org> Cc: Dave Chinner <dchinner@redhat.com> 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: Dave Chinner <dchinner@redhat.com> 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
long sum = 0;
fs: use fast counters for vfs caches percpu_counter library generates quite nasty code, so unless you need to dynamically allocate counters or take fast approximate value, a simple per cpu set of counters is much better. The percpu_counter can never be made to work as well, because it has an indirection from pointer to percpu memory, and it can't use direct this_cpu_inc interfaces because it doesn't use static PER_CPU data, so code will always be worse. In the fastpath, it is the difference between this: incl %gs:nr_dentry # nr_dentry and this: movl percpu_counter_batch(%rip), %edx # percpu_counter_batch, movl $1, %esi #, movq $nr_dentry, %rdi #, call __percpu_counter_add # (plus I clobber registers) __percpu_counter_add: pushq %rbp # movq %rsp, %rbp #, subq $32, %rsp #, movq %rbx, -24(%rbp) #, movq %r12, -16(%rbp) #, movq %r13, -8(%rbp) #, movq %rdi, %rbx # fbc, fbc #APP # 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1 movq %gs:kernel_stack,%rax #, pfo_ret__ # 0 "" 2 #NO_APP incl -8124(%rax) # <variable>.preempt_count movq 32(%rdi), %r12 # <variable>.counters, tcp_ptr__ #APP # 78 "lib/percpu_counter.c" 1 add %gs:this_cpu_off, %r12 # this_cpu_off, tcp_ptr__ # 0 "" 2 #NO_APP movslq (%r12),%r13 #* tcp_ptr__, tmp73 movslq %edx,%rax # batch, batch addq %rsi, %r13 # amount, count cmpq %rax, %r13 # batch, count jge .L27 #, negl %edx # tmp76 movslq %edx,%rdx # tmp76, tmp77 cmpq %rdx, %r13 # tmp77, count jg .L28 #, .L27: movq %rbx, %rdi # fbc, call _raw_spin_lock # addq %r13, 8(%rbx) # count, <variable>.count movq %rbx, %rdi # fbc, movl $0, (%r12) #,* tcp_ptr__ call _raw_spin_unlock # .L29: #APP # 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1 movq %gs:kernel_stack,%rax #, pfo_ret__ # 0 "" 2 #NO_APP decl -8124(%rax) # <variable>.preempt_count movq -8136(%rax), %rax #, D.14625 testb $8, %al #, D.14625 jne .L32 #, .L31: movq -24(%rbp), %rbx #, movq -16(%rbp), %r12 #, movq -8(%rbp), %r13 #, leave ret .p2align 4,,10 .p2align 3 .L28: movl %r13d, (%r12) # count,* jmp .L29 # .L32: call preempt_schedule # .p2align 4,,6 jmp .L31 # .size __percpu_counter_add, .-__percpu_counter_add .p2align 4,,15 Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:19 +08:00
for_each_possible_cpu(i)
sum += per_cpu(nr_dentry, i);
return sum < 0 ? 0 : sum;
}
dcache: convert dentry_stat.nr_unused to per-cpu counters Before we split up the dcache_lru_lock, the unused dentry counter needs to be made independent of the global dcache_lru_lock. Convert it to per-cpu counters to do this. Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> Reviewed-by: Christoph Hellwig <hch@lst.de> 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 08:17:54 +08:00
static long get_nr_dentry_unused(void)
{
int i;
long sum = 0;
for_each_possible_cpu(i)
sum += per_cpu(nr_dentry_unused, i);
return sum < 0 ? 0 : sum;
}
int proc_nr_dentry(ctl_table *table, int write, void __user *buffer,
size_t *lenp, loff_t *ppos)
{
fs: use fast counters for vfs caches percpu_counter library generates quite nasty code, so unless you need to dynamically allocate counters or take fast approximate value, a simple per cpu set of counters is much better. The percpu_counter can never be made to work as well, because it has an indirection from pointer to percpu memory, and it can't use direct this_cpu_inc interfaces because it doesn't use static PER_CPU data, so code will always be worse. In the fastpath, it is the difference between this: incl %gs:nr_dentry # nr_dentry and this: movl percpu_counter_batch(%rip), %edx # percpu_counter_batch, movl $1, %esi #, movq $nr_dentry, %rdi #, call __percpu_counter_add # (plus I clobber registers) __percpu_counter_add: pushq %rbp # movq %rsp, %rbp #, subq $32, %rsp #, movq %rbx, -24(%rbp) #, movq %r12, -16(%rbp) #, movq %r13, -8(%rbp) #, movq %rdi, %rbx # fbc, fbc #APP # 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1 movq %gs:kernel_stack,%rax #, pfo_ret__ # 0 "" 2 #NO_APP incl -8124(%rax) # <variable>.preempt_count movq 32(%rdi), %r12 # <variable>.counters, tcp_ptr__ #APP # 78 "lib/percpu_counter.c" 1 add %gs:this_cpu_off, %r12 # this_cpu_off, tcp_ptr__ # 0 "" 2 #NO_APP movslq (%r12),%r13 #* tcp_ptr__, tmp73 movslq %edx,%rax # batch, batch addq %rsi, %r13 # amount, count cmpq %rax, %r13 # batch, count jge .L27 #, negl %edx # tmp76 movslq %edx,%rdx # tmp76, tmp77 cmpq %rdx, %r13 # tmp77, count jg .L28 #, .L27: movq %rbx, %rdi # fbc, call _raw_spin_lock # addq %r13, 8(%rbx) # count, <variable>.count movq %rbx, %rdi # fbc, movl $0, (%r12) #,* tcp_ptr__ call _raw_spin_unlock # .L29: #APP # 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1 movq %gs:kernel_stack,%rax #, pfo_ret__ # 0 "" 2 #NO_APP decl -8124(%rax) # <variable>.preempt_count movq -8136(%rax), %rax #, D.14625 testb $8, %al #, D.14625 jne .L32 #, .L31: movq -24(%rbp), %rbx #, movq -16(%rbp), %r12 #, movq -8(%rbp), %r13 #, leave ret .p2align 4,,10 .p2align 3 .L28: movl %r13d, (%r12) # count,* jmp .L29 # .L32: call preempt_schedule # .p2align 4,,6 jmp .L31 # .size __percpu_counter_add, .-__percpu_counter_add .p2align 4,,15 Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:19 +08:00
dentry_stat.nr_dentry = get_nr_dentry();
dcache: convert dentry_stat.nr_unused to per-cpu counters Before we split up the dcache_lru_lock, the unused dentry counter needs to be made independent of the global dcache_lru_lock. Convert it to per-cpu counters to do this. Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> Reviewed-by: Christoph Hellwig <hch@lst.de> 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 08:17:54 +08:00
dentry_stat.nr_unused = get_nr_dentry_unused();
fs: bump inode and dentry counters to long This series reworks our current object cache shrinking infrastructure in two main ways: * Noticing that a lot of users copy and paste their own version of LRU lists for objects, we put some effort in providing a generic version. It is modeled after the filesystem users: dentries, inodes, and xfs (for various tasks), but we expect that other users could benefit in the near future with little or no modification. Let us know if you have any issues. * The underlying list_lru being proposed automatically and transparently keeps the elements in per-node lists, and is able to manipulate the node lists individually. Given this infrastructure, we are able to modify the up-to-now hammer called shrink_slab to proceed with node-reclaim instead of always searching memory from all over like it has been doing. Per-node lru lists are also expected to lead to less contention in the lru locks on multi-node scans, since we are now no longer fighting for a global lock. The locks usually disappear from the profilers with this change. Although we have no official benchmarks for this version - be our guest to independently evaluate this - earlier versions of this series were performance tested (details at http://permalink.gmane.org/gmane.linux.kernel.mm/100537) yielding no visible performance regressions while yielding a better qualitative behavior in NUMA machines. With this infrastructure in place, we can use the list_lru entry point to provide memcg isolation and per-memcg targeted reclaim. Historically, those two pieces of work have been posted together. This version presents only the infrastructure work, deferring the memcg work for a later time, so we can focus on getting this part tested. You can see more about the history of such work at http://lwn.net/Articles/552769/ Dave Chinner (18): dcache: convert dentry_stat.nr_unused to per-cpu counters dentry: move to per-sb LRU locks dcache: remove dentries from LRU before putting on dispose list mm: new shrinker API shrinker: convert superblock shrinkers to new API list: add a new LRU list type inode: convert inode lru list to generic lru list code. dcache: convert to use new lru list infrastructure list_lru: per-node list infrastructure shrinker: add node awareness fs: convert inode and dentry shrinking to be node aware xfs: convert buftarg LRU to generic code xfs: rework buffer dispose list tracking xfs: convert dquot cache lru to list_lru fs: convert fs shrinkers to new scan/count API drivers: convert shrinkers to new count/scan API shrinker: convert remaining shrinkers to count/scan API shrinker: Kill old ->shrink API. Glauber Costa (7): fs: bump inode and dentry counters to long super: fix calculation of shrinkable objects for small numbers list_lru: per-node API vmscan: per-node deferred work i915: bail out earlier when shrinker cannot acquire mutex hugepage: convert huge zero page shrinker to new shrinker API list_lru: dynamically adjust node arrays This patch: There are situations in very large machines in which we can have a large quantity of dirty inodes, unused dentries, etc. This is particularly true when umounting a filesystem, where eventually since every live object will eventually be discarded. Dave Chinner reported a problem with this while experimenting with the shrinker revamp patchset. So we believe it is time for a change. This patch just moves int to longs. Machines where it matters should have a big long anyway. Signed-off-by: Glauber Costa <glommer@openvz.org> Cc: Dave Chinner <dchinner@redhat.com> 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: Dave Chinner <dchinner@redhat.com> 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
return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
}
#endif
/*
* Compare 2 name strings, return 0 if they match, otherwise non-zero.
* The strings are both count bytes long, and count is non-zero.
*/
#ifdef CONFIG_DCACHE_WORD_ACCESS
#include <asm/word-at-a-time.h>
/*
* NOTE! 'cs' and 'scount' come from a dentry, so it has a
* aligned allocation for this particular component. We don't
* strictly need the load_unaligned_zeropad() safety, but it
* doesn't hurt either.
*
* In contrast, 'ct' and 'tcount' can be from a pathname, and do
* need the careful unaligned handling.
*/
static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount)
{
unsigned long a,b,mask;
for (;;) {
vfs: clean up __d_lookup_rcu() and dentry_cmp() interfaces The calling conventions for __d_lookup_rcu() and dentry_cmp() are annoying in different ways, and there is actually one single underlying reason for both of the annoyances. The fundamental reason is that we do the returned dentry sequence number check inside __d_lookup_rcu() instead of doing it in the caller. This results in two annoyances: - __d_lookup_rcu() now not only needs to return the dentry and the sequence number that goes along with the lookup, it also needs to return the inode pointer that was validated by that sequence number check. - and because we did the sequence number check early (to validate the name pointer and length) we also couldn't just pass the dentry itself to dentry_cmp(), we had to pass the counted string that contained the name. So that sequence number decision caused two separate ugly calling conventions. Both of these problems would be solved if we just did the sequence number check in the caller instead. There's only one caller, and that caller already has to do the sequence number check for the parent anyway, so just do that. That allows us to stop returning the dentry->d_inode in that in-out argument (pointer-to-pointer-to-inode), so we can make the inode argument just a regular input inode pointer. The caller can just load the inode from dentry->d_inode, and then do the sequence number check after that to make sure that it's synchronized with the name we looked up. And it allows us to just pass in the dentry to dentry_cmp(), which is what all the callers really wanted. Sure, dentry_cmp() has to be a bit careful about the dentry (which is not stable during RCU lookup), but that's actually very simple. And now that dentry_cmp() can clearly see that the first string argument is a dentry, we can use the direct word access for that, instead of the careful unaligned zero-padding. The dentry name is always properly aligned, since it is a single path component that is either embedded into the dentry itself, or was allocated with kmalloc() (see __d_alloc). Finally, this also uninlines the nasty slow-case for dentry comparisons: that one *does* need to do a sequence number check, since it will call in to the low-level filesystems, and we want to give those a stable inode pointer and path component length/start arguments. Doing an extra sequence check for that slow case is not a problem, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-05-05 05:59:14 +08:00
a = *(unsigned long *)cs;
b = load_unaligned_zeropad(ct);
if (tcount < sizeof(unsigned long))
break;
if (unlikely(a != b))
return 1;
cs += sizeof(unsigned long);
ct += sizeof(unsigned long);
tcount -= sizeof(unsigned long);
if (!tcount)
return 0;
}
mask = bytemask_from_count(tcount);
return unlikely(!!((a ^ b) & mask));
}
#else
static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount)
{
do {
if (*cs != *ct)
return 1;
cs++;
ct++;
tcount--;
} while (tcount);
return 0;
}
#endif
static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *ct, unsigned tcount)
{
2012-05-22 07:14:04 +08:00
const unsigned char *cs;
/*
* Be careful about RCU walk racing with rename:
* use ACCESS_ONCE to fetch the name pointer.
*
* NOTE! Even if a rename will mean that the length
* was not loaded atomically, we don't care. The
* RCU walk will check the sequence count eventually,
* and catch it. And we won't overrun the buffer,
* because we're reading the name pointer atomically,
* and a dentry name is guaranteed to be properly
* terminated with a NUL byte.
*
* End result: even if 'len' is wrong, we'll exit
* early because the data cannot match (there can
* be no NUL in the ct/tcount data)
*/
2012-05-22 07:14:04 +08:00
cs = ACCESS_ONCE(dentry->d_name.name);
smp_read_barrier_depends();
return dentry_string_cmp(cs, ct, tcount);
}
static void __d_free(struct rcu_head *head)
{
struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
WARN_ON(!hlist_unhashed(&dentry->d_alias));
if (dname_external(dentry))
kfree(dentry->d_name.name);
kmem_cache_free(dentry_cache, dentry);
}
/*
* no locks, please.
*/
static void d_free(struct dentry *dentry)
{
vfs: use lockred "dead" flag to mark unrecoverably dead dentries This simplifies the RCU to refcounting code in particular. I was originally intending to leave this for later, but walking through all the dput() logic (see previous commit), I realized that the dput() "might_sleep()" check was misleadingly weak. And I removed it as misleading, both for performance profiling and for debugging. However, the might_sleep() debugging case is actually true: the final dput() can indeed sleep, if the inode of the dentry that you are releasing ends up sleeping at iput time (see dentry_iput()). So the problem with the might_sleep() in dput() wasn't that it wasn't true, it was that it wasn't actually testing and triggering on the interesting case. In particular, just about *any* dput() can indeed sleep, if you happen to race with another thread deleting the file in question, and you then lose the race to the be the last dput() for that file. But because it's a very rare race, the debugging code would never trigger it in practice. Why is this problematic? The new d_rcu_to_refcount() (see commit 15570086b590: "vfs: reimplement d_rcu_to_refcount() using lockref_get_or_lock()") does a dput() for the failure case, and it does it under the RCU lock. So potentially sleeping really is a bug. But there's no way I'm going to fix this with the previous complicated "lockref_get_or_lock()" interface. And rather than revert to the old and crufty nested dentry locking code (which did get this right by delaying the reference count updates until they were verified to be safe), let's make forward progress. Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-09 04:46:52 +08:00
BUG_ON((int)dentry->d_lockref.count > 0);
fs: use fast counters for vfs caches percpu_counter library generates quite nasty code, so unless you need to dynamically allocate counters or take fast approximate value, a simple per cpu set of counters is much better. The percpu_counter can never be made to work as well, because it has an indirection from pointer to percpu memory, and it can't use direct this_cpu_inc interfaces because it doesn't use static PER_CPU data, so code will always be worse. In the fastpath, it is the difference between this: incl %gs:nr_dentry # nr_dentry and this: movl percpu_counter_batch(%rip), %edx # percpu_counter_batch, movl $1, %esi #, movq $nr_dentry, %rdi #, call __percpu_counter_add # (plus I clobber registers) __percpu_counter_add: pushq %rbp # movq %rsp, %rbp #, subq $32, %rsp #, movq %rbx, -24(%rbp) #, movq %r12, -16(%rbp) #, movq %r13, -8(%rbp) #, movq %rdi, %rbx # fbc, fbc #APP # 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1 movq %gs:kernel_stack,%rax #, pfo_ret__ # 0 "" 2 #NO_APP incl -8124(%rax) # <variable>.preempt_count movq 32(%rdi), %r12 # <variable>.counters, tcp_ptr__ #APP # 78 "lib/percpu_counter.c" 1 add %gs:this_cpu_off, %r12 # this_cpu_off, tcp_ptr__ # 0 "" 2 #NO_APP movslq (%r12),%r13 #* tcp_ptr__, tmp73 movslq %edx,%rax # batch, batch addq %rsi, %r13 # amount, count cmpq %rax, %r13 # batch, count jge .L27 #, negl %edx # tmp76 movslq %edx,%rdx # tmp76, tmp77 cmpq %rdx, %r13 # tmp77, count jg .L28 #, .L27: movq %rbx, %rdi # fbc, call _raw_spin_lock # addq %r13, 8(%rbx) # count, <variable>.count movq %rbx, %rdi # fbc, movl $0, (%r12) #,* tcp_ptr__ call _raw_spin_unlock # .L29: #APP # 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1 movq %gs:kernel_stack,%rax #, pfo_ret__ # 0 "" 2 #NO_APP decl -8124(%rax) # <variable>.preempt_count movq -8136(%rax), %rax #, D.14625 testb $8, %al #, D.14625 jne .L32 #, .L31: movq -24(%rbp), %rbx #, movq -16(%rbp), %r12 #, movq -8(%rbp), %r13 #, leave ret .p2align 4,,10 .p2align 3 .L28: movl %r13d, (%r12) # count,* jmp .L29 # .L32: call preempt_schedule # .p2align 4,,6 jmp .L31 # .size __percpu_counter_add, .-__percpu_counter_add .p2align 4,,15 Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:19 +08:00
this_cpu_dec(nr_dentry);
if (dentry->d_op && dentry->d_op->d_release)
dentry->d_op->d_release(dentry);
vfs: get rid of insane dentry hashing rules The dentry hashing rules have been really quite complicated for a long while, in odd ways. That made functions like __d_drop() very fragile and non-obvious. In particular, whether a dentry was hashed or not was indicated with an explicit DCACHE_UNHASHED bit. That's despite the fact that the hash abstraction that the dentries use actually have a 'is this entry hashed or not' model (which is a simple test of the 'pprev' pointer). The reason that was done is because we used the normal 'is this entry unhashed' model to mark whether the dentry had _ever_ been hashed in the dentry hash tables, and that logic goes back many years (commit b3423415fbc2: "dcache: avoid RCU for never-hashed dentries"). That, in turn, meant that __d_drop had totally different unhashing logic for the dentry hash table case and for the anonymous dcache case, because in order to use the "is this dentry hashed" logic as a flag for whether it had ever been on the RCU hash table, we had to unhash such a dentry differently so that we'd never think that it wasn't 'unhashed' and wouldn't be free'd correctly. That's just insane. It made the logic really hard to follow, when there were two different kinds of "unhashed" states, and one of them (the one that used "list_bl_unhashed()") really had nothing at all to do with being unhashed per se, but with a very subtle lifetime rule instead. So turn all of it around, and make it logical. Instead of having a DENTRY_UNHASHED bit in d_flags to indicate whether the dentry is on the hash chains or not, use the hash chain unhashed logic for that. Suddenly "d_unhashed()" just uses "list_bl_unhashed()", and everything makes sense. And for the lifetime rule, just use an explicit DENTRY_RCUACCEES bit. If we ever insert the dentry into the dentry hash table so that it is visible to RCU lookup, we mark it DENTRY_RCUACCESS to show that it now needs the RCU lifetime rules. Now suddently that test at dentry free time makes sense too. And because unhashing now is sane and doesn't depend on where the dentry got unhashed from (because the dentry hash chain details doesn't have some subtle side effects), we can re-unify the __d_drop() logic and use common code for the unhashing. Also fix one more open-coded hash chain bit_spin_lock() that I missed in the previous chain locking cleanup commit. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-04-24 22:58:46 +08:00
/* if dentry was never visible to RCU, immediate free is OK */
if (!(dentry->d_flags & DCACHE_RCUACCESS))
__d_free(&dentry->d_u.d_rcu);
else
call_rcu(&dentry->d_u.d_rcu, __d_free);
}
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
/**
* dentry_rcuwalk_barrier - invalidate in-progress rcu-walk lookups
* @dentry: the target dentry
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
* After this call, in-progress rcu-walk path lookup will fail. This
* should be called after unhashing, and after changing d_inode (if
* the dentry has not already been unhashed).
*/
static inline void dentry_rcuwalk_barrier(struct dentry *dentry)
{
assert_spin_locked(&dentry->d_lock);
/* Go through a barrier */
write_seqcount_barrier(&dentry->d_seq);
}
/*
* Release the dentry's inode, using the filesystem
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
* d_iput() operation if defined. Dentry has no refcount
* and is unhashed.
*/
static void dentry_iput(struct dentry * dentry)
__releases(dentry->d_lock)
__releases(dentry->d_inode->i_lock)
{
struct inode *inode = dentry->d_inode;
if (inode) {
dentry->d_inode = NULL;
hlist_del_init(&dentry->d_alias);
spin_unlock(&dentry->d_lock);
spin_unlock(&inode->i_lock);
if (!inode->i_nlink)
fsnotify_inoderemove(inode);
if (dentry->d_op && dentry->d_op->d_iput)
dentry->d_op->d_iput(dentry, inode);
else
iput(inode);
} else {
spin_unlock(&dentry->d_lock);
}
}
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
/*
* Release the dentry's inode, using the filesystem
* d_iput() operation if defined. dentry remains in-use.
*/
static void dentry_unlink_inode(struct dentry * dentry)
__releases(dentry->d_lock)
__releases(dentry->d_inode->i_lock)
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
{
struct inode *inode = dentry->d_inode;
__d_clear_type(dentry);
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
dentry->d_inode = NULL;
hlist_del_init(&dentry->d_alias);
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
dentry_rcuwalk_barrier(dentry);
spin_unlock(&dentry->d_lock);
spin_unlock(&inode->i_lock);
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
if (!inode->i_nlink)
fsnotify_inoderemove(inode);
if (dentry->d_op && dentry->d_op->d_iput)
dentry->d_op->d_iput(dentry, inode);
else
iput(inode);
}
/*
* The DCACHE_LRU_LIST bit is set whenever the 'd_lru' entry
* is in use - which includes both the "real" per-superblock
* LRU list _and_ the DCACHE_SHRINK_LIST use.
*
* The DCACHE_SHRINK_LIST bit is set whenever the dentry is
* on the shrink list (ie not on the superblock LRU list).
*
* The per-cpu "nr_dentry_unused" counters are updated with
* the DCACHE_LRU_LIST bit.
*
* These helper functions make sure we always follow the
* rules. d_lock must be held by the caller.
*/
#define D_FLAG_VERIFY(dentry,x) WARN_ON_ONCE(((dentry)->d_flags & (DCACHE_LRU_LIST | DCACHE_SHRINK_LIST)) != (x))
static void d_lru_add(struct dentry *dentry)
{
D_FLAG_VERIFY(dentry, 0);
dentry->d_flags |= DCACHE_LRU_LIST;
this_cpu_inc(nr_dentry_unused);
WARN_ON_ONCE(!list_lru_add(&dentry->d_sb->s_dentry_lru, &dentry->d_lru));
}
static void d_lru_del(struct dentry *dentry)
{
D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST);
dentry->d_flags &= ~DCACHE_LRU_LIST;
this_cpu_dec(nr_dentry_unused);
WARN_ON_ONCE(!list_lru_del(&dentry->d_sb->s_dentry_lru, &dentry->d_lru));
}
static void d_shrink_del(struct dentry *dentry)
{
D_FLAG_VERIFY(dentry, DCACHE_SHRINK_LIST | DCACHE_LRU_LIST);
list_del_init(&dentry->d_lru);
dentry->d_flags &= ~(DCACHE_SHRINK_LIST | DCACHE_LRU_LIST);
this_cpu_dec(nr_dentry_unused);
}
static void d_shrink_add(struct dentry *dentry, struct list_head *list)
{
D_FLAG_VERIFY(dentry, 0);
list_add(&dentry->d_lru, list);
dentry->d_flags |= DCACHE_SHRINK_LIST | DCACHE_LRU_LIST;
this_cpu_inc(nr_dentry_unused);
}
/*
* These can only be called under the global LRU lock, ie during the
* callback for freeing the LRU list. "isolate" removes it from the
* LRU lists entirely, while shrink_move moves it to the indicated
* private list.
*/
static void d_lru_isolate(struct dentry *dentry)
{
D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST);
dentry->d_flags &= ~DCACHE_LRU_LIST;
this_cpu_dec(nr_dentry_unused);
list_del_init(&dentry->d_lru);
}
static void d_lru_shrink_move(struct dentry *dentry, struct list_head *list)
{
D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST);
dentry->d_flags |= DCACHE_SHRINK_LIST;
list_move_tail(&dentry->d_lru, list);
}
fix soft lock up at NFS mount via per-SB LRU-list of unused dentries [Summary] Split LRU-list of unused dentries to one per superblock to avoid soft lock up during NFS mounts and remounting of any filesystem. Previously I posted here: http://lkml.org/lkml/2008/3/5/590 [Descriptions] - background dentry_unused is a list of dentries which are not referenced. dentry_unused grows up when references on directories or files are released. This list can be very long if there is huge free memory. - the problem When shrink_dcache_sb() is called, it scans all dentry_unused linearly under spin_lock(), and if dentry->d_sb is differnt from given superblock, scan next dentry. This scan costs very much if there are many entries, and very ineffective if there are many superblocks. IOW, When we need to shrink unused dentries on one dentry, but scans unused dentries on all superblocks in the system. For example, we scan 500 dentries to unmount a filesystem, but scans 1,000,000 or more unused dentries on other superblocks. In our case , At mounting NFS*, shrink_dcache_sb() is called to shrink unused dentries on NFS, but scans 100,000,000 unused dentries on superblocks in the system such as local ext3 filesystems. I hear NFS mounting took 1 min on some system in use. * : NFS uses virtual filesystem in rpc layer, so NFS is affected by this problem. 100,000,000 is possible number on large systems. Per-superblock LRU of unused dentried can reduce the cost in reasonable manner. - How to fix I found this problem is solved by David Chinner's "Per-superblock unused dentry LRU lists V3"(1), so I rebase it and add some fix to reclaim with fairness, which is in Andrew Morton's comments(2). 1) http://lkml.org/lkml/2006/5/25/318 2) http://lkml.org/lkml/2006/5/25/320 Split LRU-list of unused dentries to each superblocks. Then, NFS mounting will check dentries under a superblock instead of all. But this spliting will break LRU of dentry-unused. So, I've attempted to make reclaim unused dentrins with fairness by calculate number of dentries to scan on this sb based on following way number of dentries to scan on this sb = count * (number of dentries on this sb / number of dentries in the machine) - ToDo - I have to measuring performance number and do stress tests. - When unmount occurs during prune_dcache(), scanning on same superblock, It is unable to reach next superblock because it is gone away. We restart scannig superblock from first one, it causes unfairness of reclaim unused dentries on first superblock. But I think this happens very rarely. - Test Results Result on 6GB boxes with excessive unused dentries. Without patch: $ cat /proc/sys/fs/dentry-state 10181835 10180203 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m1.830s user 0m0.001s sys 0m1.653s With this patch: $ cat /proc/sys/fs/dentry-state 10236610 10234751 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m0.106s user 0m0.002s sys 0m0.032s [akpm@linux-foundation.org: fix comments] Signed-off-by: Kentaro Makita <k-makita@np.css.fujitsu.com> Cc: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: David Chinner <dgc@sgi.com> Cc: "J. Bruce Fields" <bfields@fieldses.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:27:13 +08:00
/*
* dentry_lru_(add|del)_list) must be called with d_lock held.
fix soft lock up at NFS mount via per-SB LRU-list of unused dentries [Summary] Split LRU-list of unused dentries to one per superblock to avoid soft lock up during NFS mounts and remounting of any filesystem. Previously I posted here: http://lkml.org/lkml/2008/3/5/590 [Descriptions] - background dentry_unused is a list of dentries which are not referenced. dentry_unused grows up when references on directories or files are released. This list can be very long if there is huge free memory. - the problem When shrink_dcache_sb() is called, it scans all dentry_unused linearly under spin_lock(), and if dentry->d_sb is differnt from given superblock, scan next dentry. This scan costs very much if there are many entries, and very ineffective if there are many superblocks. IOW, When we need to shrink unused dentries on one dentry, but scans unused dentries on all superblocks in the system. For example, we scan 500 dentries to unmount a filesystem, but scans 1,000,000 or more unused dentries on other superblocks. In our case , At mounting NFS*, shrink_dcache_sb() is called to shrink unused dentries on NFS, but scans 100,000,000 unused dentries on superblocks in the system such as local ext3 filesystems. I hear NFS mounting took 1 min on some system in use. * : NFS uses virtual filesystem in rpc layer, so NFS is affected by this problem. 100,000,000 is possible number on large systems. Per-superblock LRU of unused dentried can reduce the cost in reasonable manner. - How to fix I found this problem is solved by David Chinner's "Per-superblock unused dentry LRU lists V3"(1), so I rebase it and add some fix to reclaim with fairness, which is in Andrew Morton's comments(2). 1) http://lkml.org/lkml/2006/5/25/318 2) http://lkml.org/lkml/2006/5/25/320 Split LRU-list of unused dentries to each superblocks. Then, NFS mounting will check dentries under a superblock instead of all. But this spliting will break LRU of dentry-unused. So, I've attempted to make reclaim unused dentrins with fairness by calculate number of dentries to scan on this sb based on following way number of dentries to scan on this sb = count * (number of dentries on this sb / number of dentries in the machine) - ToDo - I have to measuring performance number and do stress tests. - When unmount occurs during prune_dcache(), scanning on same superblock, It is unable to reach next superblock because it is gone away. We restart scannig superblock from first one, it causes unfairness of reclaim unused dentries on first superblock. But I think this happens very rarely. - Test Results Result on 6GB boxes with excessive unused dentries. Without patch: $ cat /proc/sys/fs/dentry-state 10181835 10180203 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m1.830s user 0m0.001s sys 0m1.653s With this patch: $ cat /proc/sys/fs/dentry-state 10236610 10234751 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m0.106s user 0m0.002s sys 0m0.032s [akpm@linux-foundation.org: fix comments] Signed-off-by: Kentaro Makita <k-makita@np.css.fujitsu.com> Cc: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: David Chinner <dgc@sgi.com> Cc: "J. Bruce Fields" <bfields@fieldses.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:27:13 +08:00
*/
static void dentry_lru_add(struct dentry *dentry)
{
if (unlikely(!(dentry->d_flags & DCACHE_LRU_LIST)))
d_lru_add(dentry);
fix soft lock up at NFS mount via per-SB LRU-list of unused dentries [Summary] Split LRU-list of unused dentries to one per superblock to avoid soft lock up during NFS mounts and remounting of any filesystem. Previously I posted here: http://lkml.org/lkml/2008/3/5/590 [Descriptions] - background dentry_unused is a list of dentries which are not referenced. dentry_unused grows up when references on directories or files are released. This list can be very long if there is huge free memory. - the problem When shrink_dcache_sb() is called, it scans all dentry_unused linearly under spin_lock(), and if dentry->d_sb is differnt from given superblock, scan next dentry. This scan costs very much if there are many entries, and very ineffective if there are many superblocks. IOW, When we need to shrink unused dentries on one dentry, but scans unused dentries on all superblocks in the system. For example, we scan 500 dentries to unmount a filesystem, but scans 1,000,000 or more unused dentries on other superblocks. In our case , At mounting NFS*, shrink_dcache_sb() is called to shrink unused dentries on NFS, but scans 100,000,000 unused dentries on superblocks in the system such as local ext3 filesystems. I hear NFS mounting took 1 min on some system in use. * : NFS uses virtual filesystem in rpc layer, so NFS is affected by this problem. 100,000,000 is possible number on large systems. Per-superblock LRU of unused dentried can reduce the cost in reasonable manner. - How to fix I found this problem is solved by David Chinner's "Per-superblock unused dentry LRU lists V3"(1), so I rebase it and add some fix to reclaim with fairness, which is in Andrew Morton's comments(2). 1) http://lkml.org/lkml/2006/5/25/318 2) http://lkml.org/lkml/2006/5/25/320 Split LRU-list of unused dentries to each superblocks. Then, NFS mounting will check dentries under a superblock instead of all. But this spliting will break LRU of dentry-unused. So, I've attempted to make reclaim unused dentrins with fairness by calculate number of dentries to scan on this sb based on following way number of dentries to scan on this sb = count * (number of dentries on this sb / number of dentries in the machine) - ToDo - I have to measuring performance number and do stress tests. - When unmount occurs during prune_dcache(), scanning on same superblock, It is unable to reach next superblock because it is gone away. We restart scannig superblock from first one, it causes unfairness of reclaim unused dentries on first superblock. But I think this happens very rarely. - Test Results Result on 6GB boxes with excessive unused dentries. Without patch: $ cat /proc/sys/fs/dentry-state 10181835 10180203 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m1.830s user 0m0.001s sys 0m1.653s With this patch: $ cat /proc/sys/fs/dentry-state 10236610 10234751 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m0.106s user 0m0.002s sys 0m0.032s [akpm@linux-foundation.org: fix comments] Signed-off-by: Kentaro Makita <k-makita@np.css.fujitsu.com> Cc: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: David Chinner <dgc@sgi.com> Cc: "J. Bruce Fields" <bfields@fieldses.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:27:13 +08:00
}
/*
* Remove a dentry with references from the LRU.
dcache: remove dentries from LRU before putting on dispose list One of the big problems with modifying the way the dcache shrinker and LRU implementation works is that the LRU is abused in several ways. One of these is shrink_dentry_list(). Basically, we can move a dentry off the LRU onto a different list without doing any accounting changes, and then use dentry_lru_prune() to remove it from what-ever list it is now on to do the LRU accounting at that point. This makes it -really hard- to change the LRU implementation. The use of the per-sb LRU lock serialises movement of the dentries between the different lists and the removal of them, and this is the only reason that it works. If we want to break up the dentry LRU lock and lists into, say, per-node lists, we remove the only serialisation that allows this lru list/dispose list abuse to work. To make this work effectively, the dispose list has to be isolated from the LRU list - dentries have to be removed from the LRU *before* being placed on the dispose list. This means that the LRU accounting and isolation is completed before disposal is started, and that means we can change the LRU implementation freely in future. This means that dentries *must* be marked with DCACHE_SHRINK_LIST when they are placed on the dispose list so that we don't think that parent dentries found in try_prune_one_dentry() are on the LRU when the are actually on the dispose list. This would result in accounting the dentry to the LRU a second time. Hence dentry_lru_del() has to handle the DCACHE_SHRINK_LIST case Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> 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 08:17:55 +08:00
*
* If we are on the shrink list, then we can get to try_prune_one_dentry() and
* lose our last reference through the parent walk. In this case, we need to
* remove ourselves from the shrink list, not the LRU.
*/
fix soft lock up at NFS mount via per-SB LRU-list of unused dentries [Summary] Split LRU-list of unused dentries to one per superblock to avoid soft lock up during NFS mounts and remounting of any filesystem. Previously I posted here: http://lkml.org/lkml/2008/3/5/590 [Descriptions] - background dentry_unused is a list of dentries which are not referenced. dentry_unused grows up when references on directories or files are released. This list can be very long if there is huge free memory. - the problem When shrink_dcache_sb() is called, it scans all dentry_unused linearly under spin_lock(), and if dentry->d_sb is differnt from given superblock, scan next dentry. This scan costs very much if there are many entries, and very ineffective if there are many superblocks. IOW, When we need to shrink unused dentries on one dentry, but scans unused dentries on all superblocks in the system. For example, we scan 500 dentries to unmount a filesystem, but scans 1,000,000 or more unused dentries on other superblocks. In our case , At mounting NFS*, shrink_dcache_sb() is called to shrink unused dentries on NFS, but scans 100,000,000 unused dentries on superblocks in the system such as local ext3 filesystems. I hear NFS mounting took 1 min on some system in use. * : NFS uses virtual filesystem in rpc layer, so NFS is affected by this problem. 100,000,000 is possible number on large systems. Per-superblock LRU of unused dentried can reduce the cost in reasonable manner. - How to fix I found this problem is solved by David Chinner's "Per-superblock unused dentry LRU lists V3"(1), so I rebase it and add some fix to reclaim with fairness, which is in Andrew Morton's comments(2). 1) http://lkml.org/lkml/2006/5/25/318 2) http://lkml.org/lkml/2006/5/25/320 Split LRU-list of unused dentries to each superblocks. Then, NFS mounting will check dentries under a superblock instead of all. But this spliting will break LRU of dentry-unused. So, I've attempted to make reclaim unused dentrins with fairness by calculate number of dentries to scan on this sb based on following way number of dentries to scan on this sb = count * (number of dentries on this sb / number of dentries in the machine) - ToDo - I have to measuring performance number and do stress tests. - When unmount occurs during prune_dcache(), scanning on same superblock, It is unable to reach next superblock because it is gone away. We restart scannig superblock from first one, it causes unfairness of reclaim unused dentries on first superblock. But I think this happens very rarely. - Test Results Result on 6GB boxes with excessive unused dentries. Without patch: $ cat /proc/sys/fs/dentry-state 10181835 10180203 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m1.830s user 0m0.001s sys 0m1.653s With this patch: $ cat /proc/sys/fs/dentry-state 10236610 10234751 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m0.106s user 0m0.002s sys 0m0.032s [akpm@linux-foundation.org: fix comments] Signed-off-by: Kentaro Makita <k-makita@np.css.fujitsu.com> Cc: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: David Chinner <dgc@sgi.com> Cc: "J. Bruce Fields" <bfields@fieldses.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:27:13 +08:00
static void dentry_lru_del(struct dentry *dentry)
{
if (dentry->d_flags & DCACHE_LRU_LIST) {
if (dentry->d_flags & DCACHE_SHRINK_LIST)
return d_shrink_del(dentry);
d_lru_del(dentry);
fix soft lock up at NFS mount via per-SB LRU-list of unused dentries [Summary] Split LRU-list of unused dentries to one per superblock to avoid soft lock up during NFS mounts and remounting of any filesystem. Previously I posted here: http://lkml.org/lkml/2008/3/5/590 [Descriptions] - background dentry_unused is a list of dentries which are not referenced. dentry_unused grows up when references on directories or files are released. This list can be very long if there is huge free memory. - the problem When shrink_dcache_sb() is called, it scans all dentry_unused linearly under spin_lock(), and if dentry->d_sb is differnt from given superblock, scan next dentry. This scan costs very much if there are many entries, and very ineffective if there are many superblocks. IOW, When we need to shrink unused dentries on one dentry, but scans unused dentries on all superblocks in the system. For example, we scan 500 dentries to unmount a filesystem, but scans 1,000,000 or more unused dentries on other superblocks. In our case , At mounting NFS*, shrink_dcache_sb() is called to shrink unused dentries on NFS, but scans 100,000,000 unused dentries on superblocks in the system such as local ext3 filesystems. I hear NFS mounting took 1 min on some system in use. * : NFS uses virtual filesystem in rpc layer, so NFS is affected by this problem. 100,000,000 is possible number on large systems. Per-superblock LRU of unused dentried can reduce the cost in reasonable manner. - How to fix I found this problem is solved by David Chinner's "Per-superblock unused dentry LRU lists V3"(1), so I rebase it and add some fix to reclaim with fairness, which is in Andrew Morton's comments(2). 1) http://lkml.org/lkml/2006/5/25/318 2) http://lkml.org/lkml/2006/5/25/320 Split LRU-list of unused dentries to each superblocks. Then, NFS mounting will check dentries under a superblock instead of all. But this spliting will break LRU of dentry-unused. So, I've attempted to make reclaim unused dentrins with fairness by calculate number of dentries to scan on this sb based on following way number of dentries to scan on this sb = count * (number of dentries on this sb / number of dentries in the machine) - ToDo - I have to measuring performance number and do stress tests. - When unmount occurs during prune_dcache(), scanning on same superblock, It is unable to reach next superblock because it is gone away. We restart scannig superblock from first one, it causes unfairness of reclaim unused dentries on first superblock. But I think this happens very rarely. - Test Results Result on 6GB boxes with excessive unused dentries. Without patch: $ cat /proc/sys/fs/dentry-state 10181835 10180203 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m1.830s user 0m0.001s sys 0m1.653s With this patch: $ cat /proc/sys/fs/dentry-state 10236610 10234751 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m0.106s user 0m0.002s sys 0m0.032s [akpm@linux-foundation.org: fix comments] Signed-off-by: Kentaro Makita <k-makita@np.css.fujitsu.com> Cc: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: David Chinner <dgc@sgi.com> Cc: "J. Bruce Fields" <bfields@fieldses.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:27:13 +08:00
}
}
fix quadratic behavior of shrink_dcache_parent() The time shrink_dcache_parent() takes, grows quadratically with the depth of the tree under 'parent'. This starts to get noticable at about 10,000. These kinds of depths don't occur normally, and filesystems which invoke shrink_dcache_parent() via d_invalidate() seem to have other depth dependent timings, so it's not even easy to expose this problem. However with FUSE it's easy to create a deep tree and d_invalidate() will also get called. This can make a syscall hang for a very long time. This is the original discovery of the problem by Russ Cox: http://article.gmane.org/gmane.comp.file-systems.fuse.devel/3826 The following patch fixes the quadratic behavior, by optionally allowing prune_dcache() to prune ancestors of a dentry in one go, instead of doing it one at a time. Common code in dput() and prune_one_dentry() is extracted into a new helper function d_kill(). shrink_dcache_parent() as well as shrink_dcache_sb() are converted to use the ancestry-pruner option. Only for shrink_dcache_memory() is this behavior not desirable, so it keeps using the old algorithm. Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Maneesh Soni <maneesh@in.ibm.com> Acked-by: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 15:23:46 +08:00
/**
* d_kill - kill dentry and return parent
* @dentry: dentry to kill
* @parent: parent dentry
fix quadratic behavior of shrink_dcache_parent() The time shrink_dcache_parent() takes, grows quadratically with the depth of the tree under 'parent'. This starts to get noticable at about 10,000. These kinds of depths don't occur normally, and filesystems which invoke shrink_dcache_parent() via d_invalidate() seem to have other depth dependent timings, so it's not even easy to expose this problem. However with FUSE it's easy to create a deep tree and d_invalidate() will also get called. This can make a syscall hang for a very long time. This is the original discovery of the problem by Russ Cox: http://article.gmane.org/gmane.comp.file-systems.fuse.devel/3826 The following patch fixes the quadratic behavior, by optionally allowing prune_dcache() to prune ancestors of a dentry in one go, instead of doing it one at a time. Common code in dput() and prune_one_dentry() is extracted into a new helper function d_kill(). shrink_dcache_parent() as well as shrink_dcache_sb() are converted to use the ancestry-pruner option. Only for shrink_dcache_memory() is this behavior not desirable, so it keeps using the old algorithm. Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Maneesh Soni <maneesh@in.ibm.com> Acked-by: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 15:23:46 +08:00
*
* The dentry must already be unhashed and removed from the LRU.
fix quadratic behavior of shrink_dcache_parent() The time shrink_dcache_parent() takes, grows quadratically with the depth of the tree under 'parent'. This starts to get noticable at about 10,000. These kinds of depths don't occur normally, and filesystems which invoke shrink_dcache_parent() via d_invalidate() seem to have other depth dependent timings, so it's not even easy to expose this problem. However with FUSE it's easy to create a deep tree and d_invalidate() will also get called. This can make a syscall hang for a very long time. This is the original discovery of the problem by Russ Cox: http://article.gmane.org/gmane.comp.file-systems.fuse.devel/3826 The following patch fixes the quadratic behavior, by optionally allowing prune_dcache() to prune ancestors of a dentry in one go, instead of doing it one at a time. Common code in dput() and prune_one_dentry() is extracted into a new helper function d_kill(). shrink_dcache_parent() as well as shrink_dcache_sb() are converted to use the ancestry-pruner option. Only for shrink_dcache_memory() is this behavior not desirable, so it keeps using the old algorithm. Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Maneesh Soni <maneesh@in.ibm.com> Acked-by: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 15:23:46 +08:00
*
* If this is the root of the dentry tree, return NULL.
*
* dentry->d_lock and parent->d_lock must be held by caller, and are dropped by
* d_kill.
fix quadratic behavior of shrink_dcache_parent() The time shrink_dcache_parent() takes, grows quadratically with the depth of the tree under 'parent'. This starts to get noticable at about 10,000. These kinds of depths don't occur normally, and filesystems which invoke shrink_dcache_parent() via d_invalidate() seem to have other depth dependent timings, so it's not even easy to expose this problem. However with FUSE it's easy to create a deep tree and d_invalidate() will also get called. This can make a syscall hang for a very long time. This is the original discovery of the problem by Russ Cox: http://article.gmane.org/gmane.comp.file-systems.fuse.devel/3826 The following patch fixes the quadratic behavior, by optionally allowing prune_dcache() to prune ancestors of a dentry in one go, instead of doing it one at a time. Common code in dput() and prune_one_dentry() is extracted into a new helper function d_kill(). shrink_dcache_parent() as well as shrink_dcache_sb() are converted to use the ancestry-pruner option. Only for shrink_dcache_memory() is this behavior not desirable, so it keeps using the old algorithm. Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Maneesh Soni <maneesh@in.ibm.com> Acked-by: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 15:23:46 +08:00
*/
static struct dentry *d_kill(struct dentry *dentry, struct dentry *parent)
__releases(dentry->d_lock)
__releases(parent->d_lock)
__releases(dentry->d_inode->i_lock)
fix quadratic behavior of shrink_dcache_parent() The time shrink_dcache_parent() takes, grows quadratically with the depth of the tree under 'parent'. This starts to get noticable at about 10,000. These kinds of depths don't occur normally, and filesystems which invoke shrink_dcache_parent() via d_invalidate() seem to have other depth dependent timings, so it's not even easy to expose this problem. However with FUSE it's easy to create a deep tree and d_invalidate() will also get called. This can make a syscall hang for a very long time. This is the original discovery of the problem by Russ Cox: http://article.gmane.org/gmane.comp.file-systems.fuse.devel/3826 The following patch fixes the quadratic behavior, by optionally allowing prune_dcache() to prune ancestors of a dentry in one go, instead of doing it one at a time. Common code in dput() and prune_one_dentry() is extracted into a new helper function d_kill(). shrink_dcache_parent() as well as shrink_dcache_sb() are converted to use the ancestry-pruner option. Only for shrink_dcache_memory() is this behavior not desirable, so it keeps using the old algorithm. Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Maneesh Soni <maneesh@in.ibm.com> Acked-by: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 15:23:46 +08:00
{
list_del(&dentry->d_u.d_child);
/*
* Inform d_walk() that we are no longer attached to the
* dentry tree
*/
dentry->d_flags |= DCACHE_DENTRY_KILLED;
if (parent)
spin_unlock(&parent->d_lock);
fix quadratic behavior of shrink_dcache_parent() The time shrink_dcache_parent() takes, grows quadratically with the depth of the tree under 'parent'. This starts to get noticable at about 10,000. These kinds of depths don't occur normally, and filesystems which invoke shrink_dcache_parent() via d_invalidate() seem to have other depth dependent timings, so it's not even easy to expose this problem. However with FUSE it's easy to create a deep tree and d_invalidate() will also get called. This can make a syscall hang for a very long time. This is the original discovery of the problem by Russ Cox: http://article.gmane.org/gmane.comp.file-systems.fuse.devel/3826 The following patch fixes the quadratic behavior, by optionally allowing prune_dcache() to prune ancestors of a dentry in one go, instead of doing it one at a time. Common code in dput() and prune_one_dentry() is extracted into a new helper function d_kill(). shrink_dcache_parent() as well as shrink_dcache_sb() are converted to use the ancestry-pruner option. Only for shrink_dcache_memory() is this behavior not desirable, so it keeps using the old algorithm. Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Maneesh Soni <maneesh@in.ibm.com> Acked-by: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 15:23:46 +08:00
dentry_iput(dentry);
/*
* dentry_iput drops the locks, at which point nobody (except
* transient RCU lookups) can reach this dentry.
*/
fix quadratic behavior of shrink_dcache_parent() The time shrink_dcache_parent() takes, grows quadratically with the depth of the tree under 'parent'. This starts to get noticable at about 10,000. These kinds of depths don't occur normally, and filesystems which invoke shrink_dcache_parent() via d_invalidate() seem to have other depth dependent timings, so it's not even easy to expose this problem. However with FUSE it's easy to create a deep tree and d_invalidate() will also get called. This can make a syscall hang for a very long time. This is the original discovery of the problem by Russ Cox: http://article.gmane.org/gmane.comp.file-systems.fuse.devel/3826 The following patch fixes the quadratic behavior, by optionally allowing prune_dcache() to prune ancestors of a dentry in one go, instead of doing it one at a time. Common code in dput() and prune_one_dentry() is extracted into a new helper function d_kill(). shrink_dcache_parent() as well as shrink_dcache_sb() are converted to use the ancestry-pruner option. Only for shrink_dcache_memory() is this behavior not desirable, so it keeps using the old algorithm. Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Maneesh Soni <maneesh@in.ibm.com> Acked-by: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 15:23:46 +08:00
d_free(dentry);
return parent;
fix quadratic behavior of shrink_dcache_parent() The time shrink_dcache_parent() takes, grows quadratically with the depth of the tree under 'parent'. This starts to get noticable at about 10,000. These kinds of depths don't occur normally, and filesystems which invoke shrink_dcache_parent() via d_invalidate() seem to have other depth dependent timings, so it's not even easy to expose this problem. However with FUSE it's easy to create a deep tree and d_invalidate() will also get called. This can make a syscall hang for a very long time. This is the original discovery of the problem by Russ Cox: http://article.gmane.org/gmane.comp.file-systems.fuse.devel/3826 The following patch fixes the quadratic behavior, by optionally allowing prune_dcache() to prune ancestors of a dentry in one go, instead of doing it one at a time. Common code in dput() and prune_one_dentry() is extracted into a new helper function d_kill(). shrink_dcache_parent() as well as shrink_dcache_sb() are converted to use the ancestry-pruner option. Only for shrink_dcache_memory() is this behavior not desirable, so it keeps using the old algorithm. Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Maneesh Soni <maneesh@in.ibm.com> Acked-by: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 15:23:46 +08:00
}
/**
* d_drop - drop a dentry
* @dentry: dentry to drop
*
* d_drop() unhashes the entry from the parent dentry hashes, so that it won't
* be found through a VFS lookup any more. Note that this is different from
* deleting the dentry - d_delete will try to mark the dentry negative if
* possible, giving a successful _negative_ lookup, while d_drop will
* just make the cache lookup fail.
*
* d_drop() is used mainly for stuff that wants to invalidate a dentry for some
* reason (NFS timeouts or autofs deletes).
*
* __d_drop requires dentry->d_lock.
*/
void __d_drop(struct dentry *dentry)
{
vfs: get rid of insane dentry hashing rules The dentry hashing rules have been really quite complicated for a long while, in odd ways. That made functions like __d_drop() very fragile and non-obvious. In particular, whether a dentry was hashed or not was indicated with an explicit DCACHE_UNHASHED bit. That's despite the fact that the hash abstraction that the dentries use actually have a 'is this entry hashed or not' model (which is a simple test of the 'pprev' pointer). The reason that was done is because we used the normal 'is this entry unhashed' model to mark whether the dentry had _ever_ been hashed in the dentry hash tables, and that logic goes back many years (commit b3423415fbc2: "dcache: avoid RCU for never-hashed dentries"). That, in turn, meant that __d_drop had totally different unhashing logic for the dentry hash table case and for the anonymous dcache case, because in order to use the "is this dentry hashed" logic as a flag for whether it had ever been on the RCU hash table, we had to unhash such a dentry differently so that we'd never think that it wasn't 'unhashed' and wouldn't be free'd correctly. That's just insane. It made the logic really hard to follow, when there were two different kinds of "unhashed" states, and one of them (the one that used "list_bl_unhashed()") really had nothing at all to do with being unhashed per se, but with a very subtle lifetime rule instead. So turn all of it around, and make it logical. Instead of having a DENTRY_UNHASHED bit in d_flags to indicate whether the dentry is on the hash chains or not, use the hash chain unhashed logic for that. Suddenly "d_unhashed()" just uses "list_bl_unhashed()", and everything makes sense. And for the lifetime rule, just use an explicit DENTRY_RCUACCEES bit. If we ever insert the dentry into the dentry hash table so that it is visible to RCU lookup, we mark it DENTRY_RCUACCESS to show that it now needs the RCU lifetime rules. Now suddently that test at dentry free time makes sense too. And because unhashing now is sane and doesn't depend on where the dentry got unhashed from (because the dentry hash chain details doesn't have some subtle side effects), we can re-unify the __d_drop() logic and use common code for the unhashing. Also fix one more open-coded hash chain bit_spin_lock() that I missed in the previous chain locking cleanup commit. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-04-24 22:58:46 +08:00
if (!d_unhashed(dentry)) {
struct hlist_bl_head *b;
dcache: use IS_ROOT to decide where dentry is hashed Every hashed dentry is either hashed in the dentry_hashtable, or a superblock's s_anon list. __d_drop() assumes it can determine which is the case by checking DCACHE_DISCONNECTED; this is not true. It is true that when DCACHE_DISCONNECTED is cleared, the dentry is not only hashed on dentry_hashtable, but is fully connected to its parents back to the root. But the converse is *not* true: fs/exportfs/expfs.c:reconnect_path() attempts to connect a directory (found by filehandle lookup) back to root by ascending to parents and performing lookups one at a time. It does not clear DCACHE_DISCONNECTED until it's done, and that is not at all an atomic process. In particular, it is possible for DCACHE_DISCONNECTED to be set on a dentry which is hashed on the dentry_hashtable. Instead, use IS_ROOT() to check which hash chain a dentry is on. This *does* work: Dentries are hashed only by: - d_obtain_alias, which adds an IS_ROOT() dentry to sb_anon. - __d_rehash, called by _d_rehash: hashes to the dentry's parent, and all callers of _d_rehash appear to have d_parent set to a "real" parent. - __d_rehash, called by __d_move: rehashes the moved dentry to hash chain determined by target, and assigns target's d_parent to its d_parent, before dropping the dentry's d_lock. Therefore I believe it's safe for a holder of a dentry's d_lock to assume that it is hashed on sb_anon if and only if IS_ROOT(dentry) is true. I believe the incorrect assumption about DCACHE_DISCONNECTED was originally introduced by ceb5bdc2d246 "fs: dcache per-bucket dcache hash locking". Also add a comment while we're here. Cc: Nick Piggin <npiggin@kernel.dk> Acked-by: Christoph Hellwig <hch@infradead.org> Reviewed-by: NeilBrown <neilb@suse.de> Signed-off-by: J. Bruce Fields <bfields@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2012-06-29 00:10:55 +08:00
/*
* Hashed dentries are normally on the dentry hashtable,
* with the exception of those newly allocated by
* d_obtain_alias, which are always IS_ROOT:
*/
if (unlikely(IS_ROOT(dentry)))
b = &dentry->d_sb->s_anon;
else
b = d_hash(dentry->d_parent, dentry->d_name.hash);
hlist_bl_lock(b);
__hlist_bl_del(&dentry->d_hash);
dentry->d_hash.pprev = NULL;
hlist_bl_unlock(b);
vfs: get rid of insane dentry hashing rules The dentry hashing rules have been really quite complicated for a long while, in odd ways. That made functions like __d_drop() very fragile and non-obvious. In particular, whether a dentry was hashed or not was indicated with an explicit DCACHE_UNHASHED bit. That's despite the fact that the hash abstraction that the dentries use actually have a 'is this entry hashed or not' model (which is a simple test of the 'pprev' pointer). The reason that was done is because we used the normal 'is this entry unhashed' model to mark whether the dentry had _ever_ been hashed in the dentry hash tables, and that logic goes back many years (commit b3423415fbc2: "dcache: avoid RCU for never-hashed dentries"). That, in turn, meant that __d_drop had totally different unhashing logic for the dentry hash table case and for the anonymous dcache case, because in order to use the "is this dentry hashed" logic as a flag for whether it had ever been on the RCU hash table, we had to unhash such a dentry differently so that we'd never think that it wasn't 'unhashed' and wouldn't be free'd correctly. That's just insane. It made the logic really hard to follow, when there were two different kinds of "unhashed" states, and one of them (the one that used "list_bl_unhashed()") really had nothing at all to do with being unhashed per se, but with a very subtle lifetime rule instead. So turn all of it around, and make it logical. Instead of having a DENTRY_UNHASHED bit in d_flags to indicate whether the dentry is on the hash chains or not, use the hash chain unhashed logic for that. Suddenly "d_unhashed()" just uses "list_bl_unhashed()", and everything makes sense. And for the lifetime rule, just use an explicit DENTRY_RCUACCEES bit. If we ever insert the dentry into the dentry hash table so that it is visible to RCU lookup, we mark it DENTRY_RCUACCESS to show that it now needs the RCU lifetime rules. Now suddently that test at dentry free time makes sense too. And because unhashing now is sane and doesn't depend on where the dentry got unhashed from (because the dentry hash chain details doesn't have some subtle side effects), we can re-unify the __d_drop() logic and use common code for the unhashing. Also fix one more open-coded hash chain bit_spin_lock() that I missed in the previous chain locking cleanup commit. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-04-24 22:58:46 +08:00
dentry_rcuwalk_barrier(dentry);
}
}
EXPORT_SYMBOL(__d_drop);
void d_drop(struct dentry *dentry)
{
spin_lock(&dentry->d_lock);
__d_drop(dentry);
spin_unlock(&dentry->d_lock);
}
EXPORT_SYMBOL(d_drop);
/*
* Finish off a dentry we've decided to kill.
* dentry->d_lock must be held, returns with it unlocked.
* If ref is non-zero, then decrement the refcount too.
* Returns dentry requiring refcount drop, or NULL if we're done.
*/
static struct dentry *
dcache: remove dentries from LRU before putting on dispose list One of the big problems with modifying the way the dcache shrinker and LRU implementation works is that the LRU is abused in several ways. One of these is shrink_dentry_list(). Basically, we can move a dentry off the LRU onto a different list without doing any accounting changes, and then use dentry_lru_prune() to remove it from what-ever list it is now on to do the LRU accounting at that point. This makes it -really hard- to change the LRU implementation. The use of the per-sb LRU lock serialises movement of the dentries between the different lists and the removal of them, and this is the only reason that it works. If we want to break up the dentry LRU lock and lists into, say, per-node lists, we remove the only serialisation that allows this lru list/dispose list abuse to work. To make this work effectively, the dispose list has to be isolated from the LRU list - dentries have to be removed from the LRU *before* being placed on the dispose list. This means that the LRU accounting and isolation is completed before disposal is started, and that means we can change the LRU implementation freely in future. This means that dentries *must* be marked with DCACHE_SHRINK_LIST when they are placed on the dispose list so that we don't think that parent dentries found in try_prune_one_dentry() are on the LRU when the are actually on the dispose list. This would result in accounting the dentry to the LRU a second time. Hence dentry_lru_del() has to handle the DCACHE_SHRINK_LIST case Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> 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 08:17:55 +08:00
dentry_kill(struct dentry *dentry, int unlock_on_failure)
__releases(dentry->d_lock)
{
struct inode *inode;
struct dentry *parent;
inode = dentry->d_inode;
if (inode && !spin_trylock(&inode->i_lock)) {
relock:
dcache: remove dentries from LRU before putting on dispose list One of the big problems with modifying the way the dcache shrinker and LRU implementation works is that the LRU is abused in several ways. One of these is shrink_dentry_list(). Basically, we can move a dentry off the LRU onto a different list without doing any accounting changes, and then use dentry_lru_prune() to remove it from what-ever list it is now on to do the LRU accounting at that point. This makes it -really hard- to change the LRU implementation. The use of the per-sb LRU lock serialises movement of the dentries between the different lists and the removal of them, and this is the only reason that it works. If we want to break up the dentry LRU lock and lists into, say, per-node lists, we remove the only serialisation that allows this lru list/dispose list abuse to work. To make this work effectively, the dispose list has to be isolated from the LRU list - dentries have to be removed from the LRU *before* being placed on the dispose list. This means that the LRU accounting and isolation is completed before disposal is started, and that means we can change the LRU implementation freely in future. This means that dentries *must* be marked with DCACHE_SHRINK_LIST when they are placed on the dispose list so that we don't think that parent dentries found in try_prune_one_dentry() are on the LRU when the are actually on the dispose list. This would result in accounting the dentry to the LRU a second time. Hence dentry_lru_del() has to handle the DCACHE_SHRINK_LIST case Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> 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 08:17:55 +08:00
if (unlock_on_failure) {
spin_unlock(&dentry->d_lock);
cpu_relax();
}
return dentry; /* try again with same dentry */
}
if (IS_ROOT(dentry))
parent = NULL;
else
parent = dentry->d_parent;
if (parent && !spin_trylock(&parent->d_lock)) {
if (inode)
spin_unlock(&inode->i_lock);
goto relock;
}
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
vfs: use lockred "dead" flag to mark unrecoverably dead dentries This simplifies the RCU to refcounting code in particular. I was originally intending to leave this for later, but walking through all the dput() logic (see previous commit), I realized that the dput() "might_sleep()" check was misleadingly weak. And I removed it as misleading, both for performance profiling and for debugging. However, the might_sleep() debugging case is actually true: the final dput() can indeed sleep, if the inode of the dentry that you are releasing ends up sleeping at iput time (see dentry_iput()). So the problem with the might_sleep() in dput() wasn't that it wasn't true, it was that it wasn't actually testing and triggering on the interesting case. In particular, just about *any* dput() can indeed sleep, if you happen to race with another thread deleting the file in question, and you then lose the race to the be the last dput() for that file. But because it's a very rare race, the debugging code would never trigger it in practice. Why is this problematic? The new d_rcu_to_refcount() (see commit 15570086b590: "vfs: reimplement d_rcu_to_refcount() using lockref_get_or_lock()") does a dput() for the failure case, and it does it under the RCU lock. So potentially sleeping really is a bug. But there's no way I'm going to fix this with the previous complicated "lockref_get_or_lock()" interface. And rather than revert to the old and crufty nested dentry locking code (which did get this right by delaying the reference count updates until they were verified to be safe), let's make forward progress. Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-09 04:46:52 +08:00
/*
* The dentry is now unrecoverably dead to the world.
*/
lockref_mark_dead(&dentry->d_lockref);
/*
* inform the fs via d_prune that this dentry is about to be
* unhashed and destroyed.
*/
if ((dentry->d_flags & DCACHE_OP_PRUNE) && !d_unhashed(dentry))
dentry->d_op->d_prune(dentry);
dentry_lru_del(dentry);
/* if it was on the hash then remove it */
__d_drop(dentry);
return d_kill(dentry, parent);
}
/*
* This is dput
*
* This is complicated by the fact that we do not want to put
* dentries that are no longer on any hash chain on the unused
* list: we'd much rather just get rid of them immediately.
*
* However, that implies that we have to traverse the dentry
* tree upwards to the parents which might _also_ now be
* scheduled for deletion (it may have been only waiting for
* its last child to go away).
*
* This tail recursion is done by hand as we don't want to depend
* on the compiler to always get this right (gcc generally doesn't).
* Real recursion would eat up our stack space.
*/
/*
* dput - release a dentry
* @dentry: dentry to release
*
* Release a dentry. This will drop the usage count and if appropriate
* call the dentry unlink method as well as removing it from the queues and
* releasing its resources. If the parent dentries were scheduled for release
* they too may now get deleted.
*/
void dput(struct dentry *dentry)
{
if (unlikely(!dentry))
return;
repeat:
if (lockref_put_or_lock(&dentry->d_lockref))
return;
/* Unreachable? Get rid of it */
if (unlikely(d_unhashed(dentry)))
goto kill_it;
if (unlikely(dentry->d_flags & DCACHE_OP_DELETE)) {
if (dentry->d_op->d_delete(dentry))
goto kill_it;
}
if (!(dentry->d_flags & DCACHE_REFERENCED))
dentry->d_flags |= DCACHE_REFERENCED;
dentry_lru_add(dentry);
dentry->d_lockref.count--;
spin_unlock(&dentry->d_lock);
return;
fix quadratic behavior of shrink_dcache_parent() The time shrink_dcache_parent() takes, grows quadratically with the depth of the tree under 'parent'. This starts to get noticable at about 10,000. These kinds of depths don't occur normally, and filesystems which invoke shrink_dcache_parent() via d_invalidate() seem to have other depth dependent timings, so it's not even easy to expose this problem. However with FUSE it's easy to create a deep tree and d_invalidate() will also get called. This can make a syscall hang for a very long time. This is the original discovery of the problem by Russ Cox: http://article.gmane.org/gmane.comp.file-systems.fuse.devel/3826 The following patch fixes the quadratic behavior, by optionally allowing prune_dcache() to prune ancestors of a dentry in one go, instead of doing it one at a time. Common code in dput() and prune_one_dentry() is extracted into a new helper function d_kill(). shrink_dcache_parent() as well as shrink_dcache_sb() are converted to use the ancestry-pruner option. Only for shrink_dcache_memory() is this behavior not desirable, so it keeps using the old algorithm. Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Maneesh Soni <maneesh@in.ibm.com> Acked-by: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 15:23:46 +08:00
kill_it:
dcache: remove dentries from LRU before putting on dispose list One of the big problems with modifying the way the dcache shrinker and LRU implementation works is that the LRU is abused in several ways. One of these is shrink_dentry_list(). Basically, we can move a dentry off the LRU onto a different list without doing any accounting changes, and then use dentry_lru_prune() to remove it from what-ever list it is now on to do the LRU accounting at that point. This makes it -really hard- to change the LRU implementation. The use of the per-sb LRU lock serialises movement of the dentries between the different lists and the removal of them, and this is the only reason that it works. If we want to break up the dentry LRU lock and lists into, say, per-node lists, we remove the only serialisation that allows this lru list/dispose list abuse to work. To make this work effectively, the dispose list has to be isolated from the LRU list - dentries have to be removed from the LRU *before* being placed on the dispose list. This means that the LRU accounting and isolation is completed before disposal is started, and that means we can change the LRU implementation freely in future. This means that dentries *must* be marked with DCACHE_SHRINK_LIST when they are placed on the dispose list so that we don't think that parent dentries found in try_prune_one_dentry() are on the LRU when the are actually on the dispose list. This would result in accounting the dentry to the LRU a second time. Hence dentry_lru_del() has to handle the DCACHE_SHRINK_LIST case Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> 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 08:17:55 +08:00
dentry = dentry_kill(dentry, 1);
fix quadratic behavior of shrink_dcache_parent() The time shrink_dcache_parent() takes, grows quadratically with the depth of the tree under 'parent'. This starts to get noticable at about 10,000. These kinds of depths don't occur normally, and filesystems which invoke shrink_dcache_parent() via d_invalidate() seem to have other depth dependent timings, so it's not even easy to expose this problem. However with FUSE it's easy to create a deep tree and d_invalidate() will also get called. This can make a syscall hang for a very long time. This is the original discovery of the problem by Russ Cox: http://article.gmane.org/gmane.comp.file-systems.fuse.devel/3826 The following patch fixes the quadratic behavior, by optionally allowing prune_dcache() to prune ancestors of a dentry in one go, instead of doing it one at a time. Common code in dput() and prune_one_dentry() is extracted into a new helper function d_kill(). shrink_dcache_parent() as well as shrink_dcache_sb() are converted to use the ancestry-pruner option. Only for shrink_dcache_memory() is this behavior not desirable, so it keeps using the old algorithm. Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Maneesh Soni <maneesh@in.ibm.com> Acked-by: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 15:23:46 +08:00
if (dentry)
goto repeat;
}
EXPORT_SYMBOL(dput);
/**
* d_invalidate - invalidate a dentry
* @dentry: dentry to invalidate
*
* Try to invalidate the dentry if it turns out to be
* possible. If there are other dentries that can be
* reached through this one we can't delete it and we
* return -EBUSY. On success we return 0.
*
* no dcache lock.
*/
int d_invalidate(struct dentry * dentry)
{
/*
* If it's already been dropped, return OK.
*/
spin_lock(&dentry->d_lock);
if (d_unhashed(dentry)) {
spin_unlock(&dentry->d_lock);
return 0;
}
/*
* Check whether to do a partial shrink_dcache
* to get rid of unused child entries.
*/
if (!list_empty(&dentry->d_subdirs)) {
spin_unlock(&dentry->d_lock);
shrink_dcache_parent(dentry);
spin_lock(&dentry->d_lock);
}
/*
* Somebody else still using it?
*
* If it's a directory, we can't drop it
* for fear of somebody re-populating it
* with children (even though dropping it
* would make it unreachable from the root,
* we might still populate it if it was a
* working directory or similar).
* We also need to leave mountpoints alone,
* directory or not.
*/
if (dentry->d_lockref.count > 1 && dentry->d_inode) {
if (S_ISDIR(dentry->d_inode->i_mode) || d_mountpoint(dentry)) {
spin_unlock(&dentry->d_lock);
return -EBUSY;
}
}
__d_drop(dentry);
spin_unlock(&dentry->d_lock);
return 0;
}
EXPORT_SYMBOL(d_invalidate);
/* This must be called with d_lock held */
static inline void __dget_dlock(struct dentry *dentry)
{
dentry->d_lockref.count++;
}
static inline void __dget(struct dentry *dentry)
{
lockref_get(&dentry->d_lockref);
}
struct dentry *dget_parent(struct dentry *dentry)
{
int gotref;
struct dentry *ret;
/*
* Do optimistic parent lookup without any
* locking.
*/
rcu_read_lock();
ret = ACCESS_ONCE(dentry->d_parent);
gotref = lockref_get_not_zero(&ret->d_lockref);
rcu_read_unlock();
if (likely(gotref)) {
if (likely(ret == ACCESS_ONCE(dentry->d_parent)))
return ret;
dput(ret);
}
repeat:
/*
* Don't need rcu_dereference because we re-check it was correct under
* the lock.
*/
rcu_read_lock();
ret = dentry->d_parent;
spin_lock(&ret->d_lock);
if (unlikely(ret != dentry->d_parent)) {
spin_unlock(&ret->d_lock);
rcu_read_unlock();
goto repeat;
}
rcu_read_unlock();
BUG_ON(!ret->d_lockref.count);
ret->d_lockref.count++;
spin_unlock(&ret->d_lock);
return ret;
}
EXPORT_SYMBOL(dget_parent);
/**
* d_find_alias - grab a hashed alias of inode
* @inode: inode in question
Revert "vfs: stop d_splice_alias creating directory aliases" This reverts commit 7732a557b1342c6e6966efb5f07effcf99f56167 (and commit 3f50fff4dace23d3cfeb195d5cd4ee813cee68b7, which was a follow-up cleanup). We're chasing an elusive bug that Dave Jones can apparently reproduce using his system call fuzzer tool, and that looks like some kind of locking ordering problem on the directory i_mutex chain. Our i_mutex locking is rather complex, and depends on the topological ordering of the directories, which is why we have been very wary of splicing directory entries around. Of course, we really don't want to ever see aliased unconnected directories anyway, so none of this should ever happen, but this revert aims to basically get us back to a known older state. Bruce points to some of the previous discussion at http://marc.info/?i=<20110310105821.GE22723@ZenIV.linux.org.uk> and in particular a long post from Neil: http://marc.info/?i=<20110311150749.2fa2be66@notabene.brown> It should be noted that it's possible that Dave's problems come from other changes altohgether, including possibly just the fact that Dave constantly is teachning his fuzzer new tricks. So what appears to be a new bug could in fact be an old one that just gets newly triggered, but reverting these patches as "still under heavy discussion" is the right thing regardless. Requested-by: Al Viro <viro@zeniv.linux.org.uk> Acked-by: J. Bruce Fields <bfields@fieldses.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-06-09 01:34:03 +08:00
* @want_discon: flag, used by d_splice_alias, to request
* that only a DISCONNECTED alias be returned.
*
* If inode has a hashed alias, or is a directory and has any alias,
* acquire the reference to alias and return it. Otherwise return NULL.
* Notice that if inode is a directory there can be only one alias and
* it can be unhashed only if it has no children, or if it is the root
* of a filesystem.
*
[PATCH] knfsd: close a race-opportunity in d_splice_alias There is a possible race in d_splice_alias. Though __d_find_alias(inode, 1) will only return a dentry with DCACHE_DISCONNECTED set, it is possible for it to get cleared before the BUG_ON, and it is is not possible to lock against that. There are a couple of problems here. Firstly, the code doesn't match the comment. The comment describes a 'disconnected' dentry as being IS_ROOT as well as DCACHE_DISCONNECTED, however there is not testing of IS_ROOT anythere. A dentry is marked DCACHE_DISCONNECTED when allocated with d_alloc_anon, and remains DCACHE_DISCONNECTED while a path is built up towards the root. So a dentry can have a valid name and a valid parent and even grandparent, but will still be DCACHE_DISCONNECTED until a path to the root is created. Once the path to the root is complete, everything in the path gets DCACHE_DISCONNECTED cleared. So the fact that DCACHE_DISCONNECTED isn't enough to say that a dentry is free to be spliced in with a given name. This can only be allowed if the dentry does not yet have a name, so the IS_ROOT test is needed too. However even adding that test to __d_find_alias isn't enough. As d_splice_alias drops dcache_lock before calling d_move to perform the splice, it could race with another thread calling d_splice_alias to splice the inode in with a different name in a different part of the tree (in the case where a file has hard links). So that splicing code is only really safe for directories (as we know that directories only have one link). For directories, the caller of d_splice_alias will be holding i_mutex on the (unique) parent so there is no room for a race. A consequence of this is that a non-directory will never benefit from being spliced into a pre-exisiting dentry, but that isn't a problem. It is perfectly OK for a non-directory to have multiple dentries, some anonymous, some not. And the comment for d_splice_alias says that it only happens for directories anyway. Signed-off-by: Neil Brown <neilb@suse.de> Cc: Christoph Hellwig <hch@lst.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Dipankar Sarma <dipankar@in.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-04 17:16:16 +08:00
* If the inode has an IS_ROOT, DCACHE_DISCONNECTED alias, then prefer
Revert "vfs: stop d_splice_alias creating directory aliases" This reverts commit 7732a557b1342c6e6966efb5f07effcf99f56167 (and commit 3f50fff4dace23d3cfeb195d5cd4ee813cee68b7, which was a follow-up cleanup). We're chasing an elusive bug that Dave Jones can apparently reproduce using his system call fuzzer tool, and that looks like some kind of locking ordering problem on the directory i_mutex chain. Our i_mutex locking is rather complex, and depends on the topological ordering of the directories, which is why we have been very wary of splicing directory entries around. Of course, we really don't want to ever see aliased unconnected directories anyway, so none of this should ever happen, but this revert aims to basically get us back to a known older state. Bruce points to some of the previous discussion at http://marc.info/?i=<20110310105821.GE22723@ZenIV.linux.org.uk> and in particular a long post from Neil: http://marc.info/?i=<20110311150749.2fa2be66@notabene.brown> It should be noted that it's possible that Dave's problems come from other changes altohgether, including possibly just the fact that Dave constantly is teachning his fuzzer new tricks. So what appears to be a new bug could in fact be an old one that just gets newly triggered, but reverting these patches as "still under heavy discussion" is the right thing regardless. Requested-by: Al Viro <viro@zeniv.linux.org.uk> Acked-by: J. Bruce Fields <bfields@fieldses.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-06-09 01:34:03 +08:00
* any other hashed alias over that one unless @want_discon is set,
* in which case only return an IS_ROOT, DCACHE_DISCONNECTED alias.
*/
Revert "vfs: stop d_splice_alias creating directory aliases" This reverts commit 7732a557b1342c6e6966efb5f07effcf99f56167 (and commit 3f50fff4dace23d3cfeb195d5cd4ee813cee68b7, which was a follow-up cleanup). We're chasing an elusive bug that Dave Jones can apparently reproduce using his system call fuzzer tool, and that looks like some kind of locking ordering problem on the directory i_mutex chain. Our i_mutex locking is rather complex, and depends on the topological ordering of the directories, which is why we have been very wary of splicing directory entries around. Of course, we really don't want to ever see aliased unconnected directories anyway, so none of this should ever happen, but this revert aims to basically get us back to a known older state. Bruce points to some of the previous discussion at http://marc.info/?i=<20110310105821.GE22723@ZenIV.linux.org.uk> and in particular a long post from Neil: http://marc.info/?i=<20110311150749.2fa2be66@notabene.brown> It should be noted that it's possible that Dave's problems come from other changes altohgether, including possibly just the fact that Dave constantly is teachning his fuzzer new tricks. So what appears to be a new bug could in fact be an old one that just gets newly triggered, but reverting these patches as "still under heavy discussion" is the right thing regardless. Requested-by: Al Viro <viro@zeniv.linux.org.uk> Acked-by: J. Bruce Fields <bfields@fieldses.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-06-09 01:34:03 +08:00
static struct dentry *__d_find_alias(struct inode *inode, int want_discon)
{
struct dentry *alias, *discon_alias;
again:
discon_alias = NULL;
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(alias, &inode->i_dentry, d_alias) {
spin_lock(&alias->d_lock);
if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) {
[PATCH] knfsd: close a race-opportunity in d_splice_alias There is a possible race in d_splice_alias. Though __d_find_alias(inode, 1) will only return a dentry with DCACHE_DISCONNECTED set, it is possible for it to get cleared before the BUG_ON, and it is is not possible to lock against that. There are a couple of problems here. Firstly, the code doesn't match the comment. The comment describes a 'disconnected' dentry as being IS_ROOT as well as DCACHE_DISCONNECTED, however there is not testing of IS_ROOT anythere. A dentry is marked DCACHE_DISCONNECTED when allocated with d_alloc_anon, and remains DCACHE_DISCONNECTED while a path is built up towards the root. So a dentry can have a valid name and a valid parent and even grandparent, but will still be DCACHE_DISCONNECTED until a path to the root is created. Once the path to the root is complete, everything in the path gets DCACHE_DISCONNECTED cleared. So the fact that DCACHE_DISCONNECTED isn't enough to say that a dentry is free to be spliced in with a given name. This can only be allowed if the dentry does not yet have a name, so the IS_ROOT test is needed too. However even adding that test to __d_find_alias isn't enough. As d_splice_alias drops dcache_lock before calling d_move to perform the splice, it could race with another thread calling d_splice_alias to splice the inode in with a different name in a different part of the tree (in the case where a file has hard links). So that splicing code is only really safe for directories (as we know that directories only have one link). For directories, the caller of d_splice_alias will be holding i_mutex on the (unique) parent so there is no room for a race. A consequence of this is that a non-directory will never benefit from being spliced into a pre-exisiting dentry, but that isn't a problem. It is perfectly OK for a non-directory to have multiple dentries, some anonymous, some not. And the comment for d_splice_alias says that it only happens for directories anyway. Signed-off-by: Neil Brown <neilb@suse.de> Cc: Christoph Hellwig <hch@lst.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Dipankar Sarma <dipankar@in.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-04 17:16:16 +08:00
if (IS_ROOT(alias) &&
(alias->d_flags & DCACHE_DISCONNECTED)) {
discon_alias = alias;
Revert "vfs: stop d_splice_alias creating directory aliases" This reverts commit 7732a557b1342c6e6966efb5f07effcf99f56167 (and commit 3f50fff4dace23d3cfeb195d5cd4ee813cee68b7, which was a follow-up cleanup). We're chasing an elusive bug that Dave Jones can apparently reproduce using his system call fuzzer tool, and that looks like some kind of locking ordering problem on the directory i_mutex chain. Our i_mutex locking is rather complex, and depends on the topological ordering of the directories, which is why we have been very wary of splicing directory entries around. Of course, we really don't want to ever see aliased unconnected directories anyway, so none of this should ever happen, but this revert aims to basically get us back to a known older state. Bruce points to some of the previous discussion at http://marc.info/?i=<20110310105821.GE22723@ZenIV.linux.org.uk> and in particular a long post from Neil: http://marc.info/?i=<20110311150749.2fa2be66@notabene.brown> It should be noted that it's possible that Dave's problems come from other changes altohgether, including possibly just the fact that Dave constantly is teachning his fuzzer new tricks. So what appears to be a new bug could in fact be an old one that just gets newly triggered, but reverting these patches as "still under heavy discussion" is the right thing regardless. Requested-by: Al Viro <viro@zeniv.linux.org.uk> Acked-by: J. Bruce Fields <bfields@fieldses.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-06-09 01:34:03 +08:00
} else if (!want_discon) {
__dget_dlock(alias);
spin_unlock(&alias->d_lock);
return alias;
}
}
spin_unlock(&alias->d_lock);
}
if (discon_alias) {
alias = discon_alias;
spin_lock(&alias->d_lock);
if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) {
if (IS_ROOT(alias) &&
(alias->d_flags & DCACHE_DISCONNECTED)) {
__dget_dlock(alias);
spin_unlock(&alias->d_lock);
return alias;
}
}
spin_unlock(&alias->d_lock);
goto again;
}
return NULL;
}
struct dentry *d_find_alias(struct inode *inode)
{
struct dentry *de = NULL;
if (!hlist_empty(&inode->i_dentry)) {
spin_lock(&inode->i_lock);
Revert "vfs: stop d_splice_alias creating directory aliases" This reverts commit 7732a557b1342c6e6966efb5f07effcf99f56167 (and commit 3f50fff4dace23d3cfeb195d5cd4ee813cee68b7, which was a follow-up cleanup). We're chasing an elusive bug that Dave Jones can apparently reproduce using his system call fuzzer tool, and that looks like some kind of locking ordering problem on the directory i_mutex chain. Our i_mutex locking is rather complex, and depends on the topological ordering of the directories, which is why we have been very wary of splicing directory entries around. Of course, we really don't want to ever see aliased unconnected directories anyway, so none of this should ever happen, but this revert aims to basically get us back to a known older state. Bruce points to some of the previous discussion at http://marc.info/?i=<20110310105821.GE22723@ZenIV.linux.org.uk> and in particular a long post from Neil: http://marc.info/?i=<20110311150749.2fa2be66@notabene.brown> It should be noted that it's possible that Dave's problems come from other changes altohgether, including possibly just the fact that Dave constantly is teachning his fuzzer new tricks. So what appears to be a new bug could in fact be an old one that just gets newly triggered, but reverting these patches as "still under heavy discussion" is the right thing regardless. Requested-by: Al Viro <viro@zeniv.linux.org.uk> Acked-by: J. Bruce Fields <bfields@fieldses.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-06-09 01:34:03 +08:00
de = __d_find_alias(inode, 0);
spin_unlock(&inode->i_lock);
}
return de;
}
EXPORT_SYMBOL(d_find_alias);
/*
* Try to kill dentries associated with this inode.
* WARNING: you must own a reference to inode.
*/
void d_prune_aliases(struct inode *inode)
{
struct dentry *dentry;
restart:
spin_lock(&inode->i_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(dentry, &inode->i_dentry, d_alias) {
spin_lock(&dentry->d_lock);
if (!dentry->d_lockref.count) {
/*
* inform the fs via d_prune that this dentry
* is about to be unhashed and destroyed.
*/
if ((dentry->d_flags & DCACHE_OP_PRUNE) &&
!d_unhashed(dentry))
dentry->d_op->d_prune(dentry);
__dget_dlock(dentry);
__d_drop(dentry);
spin_unlock(&dentry->d_lock);
spin_unlock(&inode->i_lock);
dput(dentry);
goto restart;
}
spin_unlock(&dentry->d_lock);
}
spin_unlock(&inode->i_lock);
}
EXPORT_SYMBOL(d_prune_aliases);
/*
* Try to throw away a dentry - free the inode, dput the parent.
* Requires dentry->d_lock is held, and dentry->d_count == 0.
* Releases dentry->d_lock.
*
* This may fail if locks cannot be acquired no problem, just try again.
*/
dcache: remove dentries from LRU before putting on dispose list One of the big problems with modifying the way the dcache shrinker and LRU implementation works is that the LRU is abused in several ways. One of these is shrink_dentry_list(). Basically, we can move a dentry off the LRU onto a different list without doing any accounting changes, and then use dentry_lru_prune() to remove it from what-ever list it is now on to do the LRU accounting at that point. This makes it -really hard- to change the LRU implementation. The use of the per-sb LRU lock serialises movement of the dentries between the different lists and the removal of them, and this is the only reason that it works. If we want to break up the dentry LRU lock and lists into, say, per-node lists, we remove the only serialisation that allows this lru list/dispose list abuse to work. To make this work effectively, the dispose list has to be isolated from the LRU list - dentries have to be removed from the LRU *before* being placed on the dispose list. This means that the LRU accounting and isolation is completed before disposal is started, and that means we can change the LRU implementation freely in future. This means that dentries *must* be marked with DCACHE_SHRINK_LIST when they are placed on the dispose list so that we don't think that parent dentries found in try_prune_one_dentry() are on the LRU when the are actually on the dispose list. This would result in accounting the dentry to the LRU a second time. Hence dentry_lru_del() has to handle the DCACHE_SHRINK_LIST case Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> 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 08:17:55 +08:00
static struct dentry * try_prune_one_dentry(struct dentry *dentry)
__releases(dentry->d_lock)
{
struct dentry *parent;
fix quadratic behavior of shrink_dcache_parent() The time shrink_dcache_parent() takes, grows quadratically with the depth of the tree under 'parent'. This starts to get noticable at about 10,000. These kinds of depths don't occur normally, and filesystems which invoke shrink_dcache_parent() via d_invalidate() seem to have other depth dependent timings, so it's not even easy to expose this problem. However with FUSE it's easy to create a deep tree and d_invalidate() will also get called. This can make a syscall hang for a very long time. This is the original discovery of the problem by Russ Cox: http://article.gmane.org/gmane.comp.file-systems.fuse.devel/3826 The following patch fixes the quadratic behavior, by optionally allowing prune_dcache() to prune ancestors of a dentry in one go, instead of doing it one at a time. Common code in dput() and prune_one_dentry() is extracted into a new helper function d_kill(). shrink_dcache_parent() as well as shrink_dcache_sb() are converted to use the ancestry-pruner option. Only for shrink_dcache_memory() is this behavior not desirable, so it keeps using the old algorithm. Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Maneesh Soni <maneesh@in.ibm.com> Acked-by: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 15:23:46 +08:00
dcache: remove dentries from LRU before putting on dispose list One of the big problems with modifying the way the dcache shrinker and LRU implementation works is that the LRU is abused in several ways. One of these is shrink_dentry_list(). Basically, we can move a dentry off the LRU onto a different list without doing any accounting changes, and then use dentry_lru_prune() to remove it from what-ever list it is now on to do the LRU accounting at that point. This makes it -really hard- to change the LRU implementation. The use of the per-sb LRU lock serialises movement of the dentries between the different lists and the removal of them, and this is the only reason that it works. If we want to break up the dentry LRU lock and lists into, say, per-node lists, we remove the only serialisation that allows this lru list/dispose list abuse to work. To make this work effectively, the dispose list has to be isolated from the LRU list - dentries have to be removed from the LRU *before* being placed on the dispose list. This means that the LRU accounting and isolation is completed before disposal is started, and that means we can change the LRU implementation freely in future. This means that dentries *must* be marked with DCACHE_SHRINK_LIST when they are placed on the dispose list so that we don't think that parent dentries found in try_prune_one_dentry() are on the LRU when the are actually on the dispose list. This would result in accounting the dentry to the LRU a second time. Hence dentry_lru_del() has to handle the DCACHE_SHRINK_LIST case Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> 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 08:17:55 +08:00
parent = dentry_kill(dentry, 0);
fix quadratic behavior of shrink_dcache_parent() The time shrink_dcache_parent() takes, grows quadratically with the depth of the tree under 'parent'. This starts to get noticable at about 10,000. These kinds of depths don't occur normally, and filesystems which invoke shrink_dcache_parent() via d_invalidate() seem to have other depth dependent timings, so it's not even easy to expose this problem. However with FUSE it's easy to create a deep tree and d_invalidate() will also get called. This can make a syscall hang for a very long time. This is the original discovery of the problem by Russ Cox: http://article.gmane.org/gmane.comp.file-systems.fuse.devel/3826 The following patch fixes the quadratic behavior, by optionally allowing prune_dcache() to prune ancestors of a dentry in one go, instead of doing it one at a time. Common code in dput() and prune_one_dentry() is extracted into a new helper function d_kill(). shrink_dcache_parent() as well as shrink_dcache_sb() are converted to use the ancestry-pruner option. Only for shrink_dcache_memory() is this behavior not desirable, so it keeps using the old algorithm. Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Maneesh Soni <maneesh@in.ibm.com> Acked-by: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 15:23:46 +08:00
/*
* If dentry_kill returns NULL, we have nothing more to do.
* if it returns the same dentry, trylocks failed. In either
* case, just loop again.
*
* Otherwise, we need to prune ancestors too. This is necessary
* to prevent quadratic behavior of shrink_dcache_parent(), but
* is also expected to be beneficial in reducing dentry cache
* fragmentation.
fix quadratic behavior of shrink_dcache_parent() The time shrink_dcache_parent() takes, grows quadratically with the depth of the tree under 'parent'. This starts to get noticable at about 10,000. These kinds of depths don't occur normally, and filesystems which invoke shrink_dcache_parent() via d_invalidate() seem to have other depth dependent timings, so it's not even easy to expose this problem. However with FUSE it's easy to create a deep tree and d_invalidate() will also get called. This can make a syscall hang for a very long time. This is the original discovery of the problem by Russ Cox: http://article.gmane.org/gmane.comp.file-systems.fuse.devel/3826 The following patch fixes the quadratic behavior, by optionally allowing prune_dcache() to prune ancestors of a dentry in one go, instead of doing it one at a time. Common code in dput() and prune_one_dentry() is extracted into a new helper function d_kill(). shrink_dcache_parent() as well as shrink_dcache_sb() are converted to use the ancestry-pruner option. Only for shrink_dcache_memory() is this behavior not desirable, so it keeps using the old algorithm. Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Maneesh Soni <maneesh@in.ibm.com> Acked-by: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 15:23:46 +08:00
*/
if (!parent)
dcache: remove dentries from LRU before putting on dispose list One of the big problems with modifying the way the dcache shrinker and LRU implementation works is that the LRU is abused in several ways. One of these is shrink_dentry_list(). Basically, we can move a dentry off the LRU onto a different list without doing any accounting changes, and then use dentry_lru_prune() to remove it from what-ever list it is now on to do the LRU accounting at that point. This makes it -really hard- to change the LRU implementation. The use of the per-sb LRU lock serialises movement of the dentries between the different lists and the removal of them, and this is the only reason that it works. If we want to break up the dentry LRU lock and lists into, say, per-node lists, we remove the only serialisation that allows this lru list/dispose list abuse to work. To make this work effectively, the dispose list has to be isolated from the LRU list - dentries have to be removed from the LRU *before* being placed on the dispose list. This means that the LRU accounting and isolation is completed before disposal is started, and that means we can change the LRU implementation freely in future. This means that dentries *must* be marked with DCACHE_SHRINK_LIST when they are placed on the dispose list so that we don't think that parent dentries found in try_prune_one_dentry() are on the LRU when the are actually on the dispose list. This would result in accounting the dentry to the LRU a second time. Hence dentry_lru_del() has to handle the DCACHE_SHRINK_LIST case Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> 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 08:17:55 +08:00
return NULL;
if (parent == dentry)
dcache: remove dentries from LRU before putting on dispose list One of the big problems with modifying the way the dcache shrinker and LRU implementation works is that the LRU is abused in several ways. One of these is shrink_dentry_list(). Basically, we can move a dentry off the LRU onto a different list without doing any accounting changes, and then use dentry_lru_prune() to remove it from what-ever list it is now on to do the LRU accounting at that point. This makes it -really hard- to change the LRU implementation. The use of the per-sb LRU lock serialises movement of the dentries between the different lists and the removal of them, and this is the only reason that it works. If we want to break up the dentry LRU lock and lists into, say, per-node lists, we remove the only serialisation that allows this lru list/dispose list abuse to work. To make this work effectively, the dispose list has to be isolated from the LRU list - dentries have to be removed from the LRU *before* being placed on the dispose list. This means that the LRU accounting and isolation is completed before disposal is started, and that means we can change the LRU implementation freely in future. This means that dentries *must* be marked with DCACHE_SHRINK_LIST when they are placed on the dispose list so that we don't think that parent dentries found in try_prune_one_dentry() are on the LRU when the are actually on the dispose list. This would result in accounting the dentry to the LRU a second time. Hence dentry_lru_del() has to handle the DCACHE_SHRINK_LIST case Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> 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 08:17:55 +08:00
return dentry;
/* Prune ancestors. */
dentry = parent;
fix quadratic behavior of shrink_dcache_parent() The time shrink_dcache_parent() takes, grows quadratically with the depth of the tree under 'parent'. This starts to get noticable at about 10,000. These kinds of depths don't occur normally, and filesystems which invoke shrink_dcache_parent() via d_invalidate() seem to have other depth dependent timings, so it's not even easy to expose this problem. However with FUSE it's easy to create a deep tree and d_invalidate() will also get called. This can make a syscall hang for a very long time. This is the original discovery of the problem by Russ Cox: http://article.gmane.org/gmane.comp.file-systems.fuse.devel/3826 The following patch fixes the quadratic behavior, by optionally allowing prune_dcache() to prune ancestors of a dentry in one go, instead of doing it one at a time. Common code in dput() and prune_one_dentry() is extracted into a new helper function d_kill(). shrink_dcache_parent() as well as shrink_dcache_sb() are converted to use the ancestry-pruner option. Only for shrink_dcache_memory() is this behavior not desirable, so it keeps using the old algorithm. Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Maneesh Soni <maneesh@in.ibm.com> Acked-by: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 15:23:46 +08:00
while (dentry) {
if (lockref_put_or_lock(&dentry->d_lockref))
dcache: remove dentries from LRU before putting on dispose list One of the big problems with modifying the way the dcache shrinker and LRU implementation works is that the LRU is abused in several ways. One of these is shrink_dentry_list(). Basically, we can move a dentry off the LRU onto a different list without doing any accounting changes, and then use dentry_lru_prune() to remove it from what-ever list it is now on to do the LRU accounting at that point. This makes it -really hard- to change the LRU implementation. The use of the per-sb LRU lock serialises movement of the dentries between the different lists and the removal of them, and this is the only reason that it works. If we want to break up the dentry LRU lock and lists into, say, per-node lists, we remove the only serialisation that allows this lru list/dispose list abuse to work. To make this work effectively, the dispose list has to be isolated from the LRU list - dentries have to be removed from the LRU *before* being placed on the dispose list. This means that the LRU accounting and isolation is completed before disposal is started, and that means we can change the LRU implementation freely in future. This means that dentries *must* be marked with DCACHE_SHRINK_LIST when they are placed on the dispose list so that we don't think that parent dentries found in try_prune_one_dentry() are on the LRU when the are actually on the dispose list. This would result in accounting the dentry to the LRU a second time. Hence dentry_lru_del() has to handle the DCACHE_SHRINK_LIST case Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> 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 08:17:55 +08:00
return NULL;
dentry = dentry_kill(dentry, 1);
fix quadratic behavior of shrink_dcache_parent() The time shrink_dcache_parent() takes, grows quadratically with the depth of the tree under 'parent'. This starts to get noticable at about 10,000. These kinds of depths don't occur normally, and filesystems which invoke shrink_dcache_parent() via d_invalidate() seem to have other depth dependent timings, so it's not even easy to expose this problem. However with FUSE it's easy to create a deep tree and d_invalidate() will also get called. This can make a syscall hang for a very long time. This is the original discovery of the problem by Russ Cox: http://article.gmane.org/gmane.comp.file-systems.fuse.devel/3826 The following patch fixes the quadratic behavior, by optionally allowing prune_dcache() to prune ancestors of a dentry in one go, instead of doing it one at a time. Common code in dput() and prune_one_dentry() is extracted into a new helper function d_kill(). shrink_dcache_parent() as well as shrink_dcache_sb() are converted to use the ancestry-pruner option. Only for shrink_dcache_memory() is this behavior not desirable, so it keeps using the old algorithm. Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Maneesh Soni <maneesh@in.ibm.com> Acked-by: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 15:23:46 +08:00
}
dcache: remove dentries from LRU before putting on dispose list One of the big problems with modifying the way the dcache shrinker and LRU implementation works is that the LRU is abused in several ways. One of these is shrink_dentry_list(). Basically, we can move a dentry off the LRU onto a different list without doing any accounting changes, and then use dentry_lru_prune() to remove it from what-ever list it is now on to do the LRU accounting at that point. This makes it -really hard- to change the LRU implementation. The use of the per-sb LRU lock serialises movement of the dentries between the different lists and the removal of them, and this is the only reason that it works. If we want to break up the dentry LRU lock and lists into, say, per-node lists, we remove the only serialisation that allows this lru list/dispose list abuse to work. To make this work effectively, the dispose list has to be isolated from the LRU list - dentries have to be removed from the LRU *before* being placed on the dispose list. This means that the LRU accounting and isolation is completed before disposal is started, and that means we can change the LRU implementation freely in future. This means that dentries *must* be marked with DCACHE_SHRINK_LIST when they are placed on the dispose list so that we don't think that parent dentries found in try_prune_one_dentry() are on the LRU when the are actually on the dispose list. This would result in accounting the dentry to the LRU a second time. Hence dentry_lru_del() has to handle the DCACHE_SHRINK_LIST case Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> 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 08:17:55 +08:00
return NULL;
}
static void shrink_dentry_list(struct list_head *list)
{
fix soft lock up at NFS mount via per-SB LRU-list of unused dentries [Summary] Split LRU-list of unused dentries to one per superblock to avoid soft lock up during NFS mounts and remounting of any filesystem. Previously I posted here: http://lkml.org/lkml/2008/3/5/590 [Descriptions] - background dentry_unused is a list of dentries which are not referenced. dentry_unused grows up when references on directories or files are released. This list can be very long if there is huge free memory. - the problem When shrink_dcache_sb() is called, it scans all dentry_unused linearly under spin_lock(), and if dentry->d_sb is differnt from given superblock, scan next dentry. This scan costs very much if there are many entries, and very ineffective if there are many superblocks. IOW, When we need to shrink unused dentries on one dentry, but scans unused dentries on all superblocks in the system. For example, we scan 500 dentries to unmount a filesystem, but scans 1,000,000 or more unused dentries on other superblocks. In our case , At mounting NFS*, shrink_dcache_sb() is called to shrink unused dentries on NFS, but scans 100,000,000 unused dentries on superblocks in the system such as local ext3 filesystems. I hear NFS mounting took 1 min on some system in use. * : NFS uses virtual filesystem in rpc layer, so NFS is affected by this problem. 100,000,000 is possible number on large systems. Per-superblock LRU of unused dentried can reduce the cost in reasonable manner. - How to fix I found this problem is solved by David Chinner's "Per-superblock unused dentry LRU lists V3"(1), so I rebase it and add some fix to reclaim with fairness, which is in Andrew Morton's comments(2). 1) http://lkml.org/lkml/2006/5/25/318 2) http://lkml.org/lkml/2006/5/25/320 Split LRU-list of unused dentries to each superblocks. Then, NFS mounting will check dentries under a superblock instead of all. But this spliting will break LRU of dentry-unused. So, I've attempted to make reclaim unused dentrins with fairness by calculate number of dentries to scan on this sb based on following way number of dentries to scan on this sb = count * (number of dentries on this sb / number of dentries in the machine) - ToDo - I have to measuring performance number and do stress tests. - When unmount occurs during prune_dcache(), scanning on same superblock, It is unable to reach next superblock because it is gone away. We restart scannig superblock from first one, it causes unfairness of reclaim unused dentries on first superblock. But I think this happens very rarely. - Test Results Result on 6GB boxes with excessive unused dentries. Without patch: $ cat /proc/sys/fs/dentry-state 10181835 10180203 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m1.830s user 0m0.001s sys 0m1.653s With this patch: $ cat /proc/sys/fs/dentry-state 10236610 10234751 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m0.106s user 0m0.002s sys 0m0.032s [akpm@linux-foundation.org: fix comments] Signed-off-by: Kentaro Makita <k-makita@np.css.fujitsu.com> Cc: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: David Chinner <dgc@sgi.com> Cc: "J. Bruce Fields" <bfields@fieldses.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:27:13 +08:00
struct dentry *dentry;
rcu_read_lock();
for (;;) {
dentry = list_entry_rcu(list->prev, struct dentry, d_lru);
if (&dentry->d_lru == list)
break; /* empty */
/*
* Get the dentry lock, and re-verify that the dentry is
* this on the shrinking list. If it is, we know that
* DCACHE_SHRINK_LIST and DCACHE_LRU_LIST are set.
*/
spin_lock(&dentry->d_lock);
if (dentry != list_entry(list->prev, struct dentry, d_lru)) {
spin_unlock(&dentry->d_lock);
continue;
}
dcache: remove dentries from LRU before putting on dispose list One of the big problems with modifying the way the dcache shrinker and LRU implementation works is that the LRU is abused in several ways. One of these is shrink_dentry_list(). Basically, we can move a dentry off the LRU onto a different list without doing any accounting changes, and then use dentry_lru_prune() to remove it from what-ever list it is now on to do the LRU accounting at that point. This makes it -really hard- to change the LRU implementation. The use of the per-sb LRU lock serialises movement of the dentries between the different lists and the removal of them, and this is the only reason that it works. If we want to break up the dentry LRU lock and lists into, say, per-node lists, we remove the only serialisation that allows this lru list/dispose list abuse to work. To make this work effectively, the dispose list has to be isolated from the LRU list - dentries have to be removed from the LRU *before* being placed on the dispose list. This means that the LRU accounting and isolation is completed before disposal is started, and that means we can change the LRU implementation freely in future. This means that dentries *must* be marked with DCACHE_SHRINK_LIST when they are placed on the dispose list so that we don't think that parent dentries found in try_prune_one_dentry() are on the LRU when the are actually on the dispose list. This would result in accounting the dentry to the LRU a second time. Hence dentry_lru_del() has to handle the DCACHE_SHRINK_LIST case Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> 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 08:17:55 +08:00
/*
* The dispose list is isolated and dentries are not accounted
* to the LRU here, so we can simply remove it from the list
* here regardless of whether it is referenced or not.
*/
d_shrink_del(dentry);
dcache: remove dentries from LRU before putting on dispose list One of the big problems with modifying the way the dcache shrinker and LRU implementation works is that the LRU is abused in several ways. One of these is shrink_dentry_list(). Basically, we can move a dentry off the LRU onto a different list without doing any accounting changes, and then use dentry_lru_prune() to remove it from what-ever list it is now on to do the LRU accounting at that point. This makes it -really hard- to change the LRU implementation. The use of the per-sb LRU lock serialises movement of the dentries between the different lists and the removal of them, and this is the only reason that it works. If we want to break up the dentry LRU lock and lists into, say, per-node lists, we remove the only serialisation that allows this lru list/dispose list abuse to work. To make this work effectively, the dispose list has to be isolated from the LRU list - dentries have to be removed from the LRU *before* being placed on the dispose list. This means that the LRU accounting and isolation is completed before disposal is started, and that means we can change the LRU implementation freely in future. This means that dentries *must* be marked with DCACHE_SHRINK_LIST when they are placed on the dispose list so that we don't think that parent dentries found in try_prune_one_dentry() are on the LRU when the are actually on the dispose list. This would result in accounting the dentry to the LRU a second time. Hence dentry_lru_del() has to handle the DCACHE_SHRINK_LIST case Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> 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 08:17:55 +08:00
/*
* We found an inuse dentry which was not removed from
dcache: remove dentries from LRU before putting on dispose list One of the big problems with modifying the way the dcache shrinker and LRU implementation works is that the LRU is abused in several ways. One of these is shrink_dentry_list(). Basically, we can move a dentry off the LRU onto a different list without doing any accounting changes, and then use dentry_lru_prune() to remove it from what-ever list it is now on to do the LRU accounting at that point. This makes it -really hard- to change the LRU implementation. The use of the per-sb LRU lock serialises movement of the dentries between the different lists and the removal of them, and this is the only reason that it works. If we want to break up the dentry LRU lock and lists into, say, per-node lists, we remove the only serialisation that allows this lru list/dispose list abuse to work. To make this work effectively, the dispose list has to be isolated from the LRU list - dentries have to be removed from the LRU *before* being placed on the dispose list. This means that the LRU accounting and isolation is completed before disposal is started, and that means we can change the LRU implementation freely in future. This means that dentries *must* be marked with DCACHE_SHRINK_LIST when they are placed on the dispose list so that we don't think that parent dentries found in try_prune_one_dentry() are on the LRU when the are actually on the dispose list. This would result in accounting the dentry to the LRU a second time. Hence dentry_lru_del() has to handle the DCACHE_SHRINK_LIST case Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> 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 08:17:55 +08:00
* the LRU because of laziness during lookup. Do not free it.
*/
if (dentry->d_lockref.count) {
fix soft lock up at NFS mount via per-SB LRU-list of unused dentries [Summary] Split LRU-list of unused dentries to one per superblock to avoid soft lock up during NFS mounts and remounting of any filesystem. Previously I posted here: http://lkml.org/lkml/2008/3/5/590 [Descriptions] - background dentry_unused is a list of dentries which are not referenced. dentry_unused grows up when references on directories or files are released. This list can be very long if there is huge free memory. - the problem When shrink_dcache_sb() is called, it scans all dentry_unused linearly under spin_lock(), and if dentry->d_sb is differnt from given superblock, scan next dentry. This scan costs very much if there are many entries, and very ineffective if there are many superblocks. IOW, When we need to shrink unused dentries on one dentry, but scans unused dentries on all superblocks in the system. For example, we scan 500 dentries to unmount a filesystem, but scans 1,000,000 or more unused dentries on other superblocks. In our case , At mounting NFS*, shrink_dcache_sb() is called to shrink unused dentries on NFS, but scans 100,000,000 unused dentries on superblocks in the system such as local ext3 filesystems. I hear NFS mounting took 1 min on some system in use. * : NFS uses virtual filesystem in rpc layer, so NFS is affected by this problem. 100,000,000 is possible number on large systems. Per-superblock LRU of unused dentried can reduce the cost in reasonable manner. - How to fix I found this problem is solved by David Chinner's "Per-superblock unused dentry LRU lists V3"(1), so I rebase it and add some fix to reclaim with fairness, which is in Andrew Morton's comments(2). 1) http://lkml.org/lkml/2006/5/25/318 2) http://lkml.org/lkml/2006/5/25/320 Split LRU-list of unused dentries to each superblocks. Then, NFS mounting will check dentries under a superblock instead of all. But this spliting will break LRU of dentry-unused. So, I've attempted to make reclaim unused dentrins with fairness by calculate number of dentries to scan on this sb based on following way number of dentries to scan on this sb = count * (number of dentries on this sb / number of dentries in the machine) - ToDo - I have to measuring performance number and do stress tests. - When unmount occurs during prune_dcache(), scanning on same superblock, It is unable to reach next superblock because it is gone away. We restart scannig superblock from first one, it causes unfairness of reclaim unused dentries on first superblock. But I think this happens very rarely. - Test Results Result on 6GB boxes with excessive unused dentries. Without patch: $ cat /proc/sys/fs/dentry-state 10181835 10180203 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m1.830s user 0m0.001s sys 0m1.653s With this patch: $ cat /proc/sys/fs/dentry-state 10236610 10234751 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m0.106s user 0m0.002s sys 0m0.032s [akpm@linux-foundation.org: fix comments] Signed-off-by: Kentaro Makita <k-makita@np.css.fujitsu.com> Cc: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: David Chinner <dgc@sgi.com> Cc: "J. Bruce Fields" <bfields@fieldses.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:27:13 +08:00
spin_unlock(&dentry->d_lock);
continue;
}
rcu_read_unlock();
/*
* If 'try_to_prune()' returns a dentry, it will
* be the same one we passed in, and d_lock will
* have been held the whole time, so it will not
* have been added to any other lists. We failed
* to get the inode lock.
*
* We just add it back to the shrink list.
*/
dcache: remove dentries from LRU before putting on dispose list One of the big problems with modifying the way the dcache shrinker and LRU implementation works is that the LRU is abused in several ways. One of these is shrink_dentry_list(). Basically, we can move a dentry off the LRU onto a different list without doing any accounting changes, and then use dentry_lru_prune() to remove it from what-ever list it is now on to do the LRU accounting at that point. This makes it -really hard- to change the LRU implementation. The use of the per-sb LRU lock serialises movement of the dentries between the different lists and the removal of them, and this is the only reason that it works. If we want to break up the dentry LRU lock and lists into, say, per-node lists, we remove the only serialisation that allows this lru list/dispose list abuse to work. To make this work effectively, the dispose list has to be isolated from the LRU list - dentries have to be removed from the LRU *before* being placed on the dispose list. This means that the LRU accounting and isolation is completed before disposal is started, and that means we can change the LRU implementation freely in future. This means that dentries *must* be marked with DCACHE_SHRINK_LIST when they are placed on the dispose list so that we don't think that parent dentries found in try_prune_one_dentry() are on the LRU when the are actually on the dispose list. This would result in accounting the dentry to the LRU a second time. Hence dentry_lru_del() has to handle the DCACHE_SHRINK_LIST case Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> 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 08:17:55 +08:00
dentry = try_prune_one_dentry(dentry);
rcu_read_lock();
dcache: remove dentries from LRU before putting on dispose list One of the big problems with modifying the way the dcache shrinker and LRU implementation works is that the LRU is abused in several ways. One of these is shrink_dentry_list(). Basically, we can move a dentry off the LRU onto a different list without doing any accounting changes, and then use dentry_lru_prune() to remove it from what-ever list it is now on to do the LRU accounting at that point. This makes it -really hard- to change the LRU implementation. The use of the per-sb LRU lock serialises movement of the dentries between the different lists and the removal of them, and this is the only reason that it works. If we want to break up the dentry LRU lock and lists into, say, per-node lists, we remove the only serialisation that allows this lru list/dispose list abuse to work. To make this work effectively, the dispose list has to be isolated from the LRU list - dentries have to be removed from the LRU *before* being placed on the dispose list. This means that the LRU accounting and isolation is completed before disposal is started, and that means we can change the LRU implementation freely in future. This means that dentries *must* be marked with DCACHE_SHRINK_LIST when they are placed on the dispose list so that we don't think that parent dentries found in try_prune_one_dentry() are on the LRU when the are actually on the dispose list. This would result in accounting the dentry to the LRU a second time. Hence dentry_lru_del() has to handle the DCACHE_SHRINK_LIST case Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> 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 08:17:55 +08:00
if (dentry) {
d_shrink_add(dentry, list);
dcache: remove dentries from LRU before putting on dispose list One of the big problems with modifying the way the dcache shrinker and LRU implementation works is that the LRU is abused in several ways. One of these is shrink_dentry_list(). Basically, we can move a dentry off the LRU onto a different list without doing any accounting changes, and then use dentry_lru_prune() to remove it from what-ever list it is now on to do the LRU accounting at that point. This makes it -really hard- to change the LRU implementation. The use of the per-sb LRU lock serialises movement of the dentries between the different lists and the removal of them, and this is the only reason that it works. If we want to break up the dentry LRU lock and lists into, say, per-node lists, we remove the only serialisation that allows this lru list/dispose list abuse to work. To make this work effectively, the dispose list has to be isolated from the LRU list - dentries have to be removed from the LRU *before* being placed on the dispose list. This means that the LRU accounting and isolation is completed before disposal is started, and that means we can change the LRU implementation freely in future. This means that dentries *must* be marked with DCACHE_SHRINK_LIST when they are placed on the dispose list so that we don't think that parent dentries found in try_prune_one_dentry() are on the LRU when the are actually on the dispose list. This would result in accounting the dentry to the LRU a second time. Hence dentry_lru_del() has to handle the DCACHE_SHRINK_LIST case Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> 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 08:17:55 +08:00
spin_unlock(&dentry->d_lock);
}
fix soft lock up at NFS mount via per-SB LRU-list of unused dentries [Summary] Split LRU-list of unused dentries to one per superblock to avoid soft lock up during NFS mounts and remounting of any filesystem. Previously I posted here: http://lkml.org/lkml/2008/3/5/590 [Descriptions] - background dentry_unused is a list of dentries which are not referenced. dentry_unused grows up when references on directories or files are released. This list can be very long if there is huge free memory. - the problem When shrink_dcache_sb() is called, it scans all dentry_unused linearly under spin_lock(), and if dentry->d_sb is differnt from given superblock, scan next dentry. This scan costs very much if there are many entries, and very ineffective if there are many superblocks. IOW, When we need to shrink unused dentries on one dentry, but scans unused dentries on all superblocks in the system. For example, we scan 500 dentries to unmount a filesystem, but scans 1,000,000 or more unused dentries on other superblocks. In our case , At mounting NFS*, shrink_dcache_sb() is called to shrink unused dentries on NFS, but scans 100,000,000 unused dentries on superblocks in the system such as local ext3 filesystems. I hear NFS mounting took 1 min on some system in use. * : NFS uses virtual filesystem in rpc layer, so NFS is affected by this problem. 100,000,000 is possible number on large systems. Per-superblock LRU of unused dentried can reduce the cost in reasonable manner. - How to fix I found this problem is solved by David Chinner's "Per-superblock unused dentry LRU lists V3"(1), so I rebase it and add some fix to reclaim with fairness, which is in Andrew Morton's comments(2). 1) http://lkml.org/lkml/2006/5/25/318 2) http://lkml.org/lkml/2006/5/25/320 Split LRU-list of unused dentries to each superblocks. Then, NFS mounting will check dentries under a superblock instead of all. But this spliting will break LRU of dentry-unused. So, I've attempted to make reclaim unused dentrins with fairness by calculate number of dentries to scan on this sb based on following way number of dentries to scan on this sb = count * (number of dentries on this sb / number of dentries in the machine) - ToDo - I have to measuring performance number and do stress tests. - When unmount occurs during prune_dcache(), scanning on same superblock, It is unable to reach next superblock because it is gone away. We restart scannig superblock from first one, it causes unfairness of reclaim unused dentries on first superblock. But I think this happens very rarely. - Test Results Result on 6GB boxes with excessive unused dentries. Without patch: $ cat /proc/sys/fs/dentry-state 10181835 10180203 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m1.830s user 0m0.001s sys 0m1.653s With this patch: $ cat /proc/sys/fs/dentry-state 10236610 10234751 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m0.106s user 0m0.002s sys 0m0.032s [akpm@linux-foundation.org: fix comments] Signed-off-by: Kentaro Makita <k-makita@np.css.fujitsu.com> Cc: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: David Chinner <dgc@sgi.com> Cc: "J. Bruce Fields" <bfields@fieldses.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:27:13 +08:00
}
rcu_read_unlock();
}
static enum lru_status
dentry_lru_isolate(struct list_head *item, spinlock_t *lru_lock, void *arg)
{
struct list_head *freeable = arg;
struct dentry *dentry = container_of(item, struct dentry, d_lru);
/*
* we are inverting the lru lock/dentry->d_lock here,
* so use a trylock. If we fail to get the lock, just skip
* it
*/
if (!spin_trylock(&dentry->d_lock))
return LRU_SKIP;
/*
* Referenced dentries are still in use. If they have active
* counts, just remove them from the LRU. Otherwise give them
* another pass through the LRU.
*/
if (dentry->d_lockref.count) {
d_lru_isolate(dentry);
spin_unlock(&dentry->d_lock);
return LRU_REMOVED;
}
if (dentry->d_flags & DCACHE_REFERENCED) {
dentry->d_flags &= ~DCACHE_REFERENCED;
spin_unlock(&dentry->d_lock);
/*
* The list move itself will be made by the common LRU code. At
* this point, we've dropped the dentry->d_lock but keep the
* lru lock. This is safe to do, since every list movement is
* protected by the lru lock even if both locks are held.
*
* This is guaranteed by the fact that all LRU management
* functions are intermediated by the LRU API calls like
* list_lru_add and list_lru_del. List movement in this file
* only ever occur through this functions or through callbacks
* like this one, that are called from the LRU API.
*
* The only exceptions to this are functions like
* shrink_dentry_list, and code that first checks for the
* DCACHE_SHRINK_LIST flag. Those are guaranteed to be
* operating only with stack provided lists after they are
* properly isolated from the main list. It is thus, always a
* local access.
*/
return LRU_ROTATE;
}
d_lru_shrink_move(dentry, freeable);
spin_unlock(&dentry->d_lock);
return LRU_REMOVED;
}
/**
dcache: use a dispose list in select_parent select_parent currently abuses the dentry cache LRU to provide cleanup features for child dentries that need to be freed. It moves them to the tail of the LRU, then tells shrink_dcache_parent() to calls __shrink_dcache_sb to unconditionally move them to a dispose list (as DCACHE_REFERENCED is ignored). __shrink_dcache_sb() has to relock the dentries to move them off the LRU onto the dispose list, but otherwise does not touch the dentries that select_parent() moved to the tail of the LRU. It then passses the dispose list to shrink_dentry_list() which tries to free the dentries. IOWs, the use of __shrink_dcache_sb() is superfluous - we can build exactly the same list of dentries for disposal directly in select_parent() and call shrink_dentry_list() instead of calling __shrink_dcache_sb() to do that. This means that we avoid long holds on the lru lock walking the LRU moving dentries to the dispose list We also avoid the need to relock each dentry just to move it off the LRU, reducing the numebr of times we lock each dentry to dispose of them in shrink_dcache_parent() from 3 to 2 times. Further, we remove one of the two callers of __shrink_dcache_sb(). This also means that __shrink_dcache_sb can be moved into back into prune_dcache_sb() and we no longer have to handle referenced dentries conditionally, simplifying the code. Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2011-08-23 16:56:24 +08:00
* prune_dcache_sb - shrink the dcache
* @sb: superblock
* @nr_to_scan : number of entries to try to free
2013-08-28 08:18:05 +08:00
* @nid: which node to scan for freeable entities
dcache: use a dispose list in select_parent select_parent currently abuses the dentry cache LRU to provide cleanup features for child dentries that need to be freed. It moves them to the tail of the LRU, then tells shrink_dcache_parent() to calls __shrink_dcache_sb to unconditionally move them to a dispose list (as DCACHE_REFERENCED is ignored). __shrink_dcache_sb() has to relock the dentries to move them off the LRU onto the dispose list, but otherwise does not touch the dentries that select_parent() moved to the tail of the LRU. It then passses the dispose list to shrink_dentry_list() which tries to free the dentries. IOWs, the use of __shrink_dcache_sb() is superfluous - we can build exactly the same list of dentries for disposal directly in select_parent() and call shrink_dentry_list() instead of calling __shrink_dcache_sb() to do that. This means that we avoid long holds on the lru lock walking the LRU moving dentries to the dispose list We also avoid the need to relock each dentry just to move it off the LRU, reducing the numebr of times we lock each dentry to dispose of them in shrink_dcache_parent() from 3 to 2 times. Further, we remove one of the two callers of __shrink_dcache_sb(). This also means that __shrink_dcache_sb can be moved into back into prune_dcache_sb() and we no longer have to handle referenced dentries conditionally, simplifying the code. Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2011-08-23 16:56:24 +08:00
*
* Attempt to shrink the superblock dcache LRU by @nr_to_scan entries. This is
dcache: use a dispose list in select_parent select_parent currently abuses the dentry cache LRU to provide cleanup features for child dentries that need to be freed. It moves them to the tail of the LRU, then tells shrink_dcache_parent() to calls __shrink_dcache_sb to unconditionally move them to a dispose list (as DCACHE_REFERENCED is ignored). __shrink_dcache_sb() has to relock the dentries to move them off the LRU onto the dispose list, but otherwise does not touch the dentries that select_parent() moved to the tail of the LRU. It then passses the dispose list to shrink_dentry_list() which tries to free the dentries. IOWs, the use of __shrink_dcache_sb() is superfluous - we can build exactly the same list of dentries for disposal directly in select_parent() and call shrink_dentry_list() instead of calling __shrink_dcache_sb() to do that. This means that we avoid long holds on the lru lock walking the LRU moving dentries to the dispose list We also avoid the need to relock each dentry just to move it off the LRU, reducing the numebr of times we lock each dentry to dispose of them in shrink_dcache_parent() from 3 to 2 times. Further, we remove one of the two callers of __shrink_dcache_sb(). This also means that __shrink_dcache_sb can be moved into back into prune_dcache_sb() and we no longer have to handle referenced dentries conditionally, simplifying the code. Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2011-08-23 16:56:24 +08:00
* done when we need more memory an called from the superblock shrinker
* function.
*
dcache: use a dispose list in select_parent select_parent currently abuses the dentry cache LRU to provide cleanup features for child dentries that need to be freed. It moves them to the tail of the LRU, then tells shrink_dcache_parent() to calls __shrink_dcache_sb to unconditionally move them to a dispose list (as DCACHE_REFERENCED is ignored). __shrink_dcache_sb() has to relock the dentries to move them off the LRU onto the dispose list, but otherwise does not touch the dentries that select_parent() moved to the tail of the LRU. It then passses the dispose list to shrink_dentry_list() which tries to free the dentries. IOWs, the use of __shrink_dcache_sb() is superfluous - we can build exactly the same list of dentries for disposal directly in select_parent() and call shrink_dentry_list() instead of calling __shrink_dcache_sb() to do that. This means that we avoid long holds on the lru lock walking the LRU moving dentries to the dispose list We also avoid the need to relock each dentry just to move it off the LRU, reducing the numebr of times we lock each dentry to dispose of them in shrink_dcache_parent() from 3 to 2 times. Further, we remove one of the two callers of __shrink_dcache_sb(). This also means that __shrink_dcache_sb can be moved into back into prune_dcache_sb() and we no longer have to handle referenced dentries conditionally, simplifying the code. Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2011-08-23 16:56:24 +08:00
* This function may fail to free any resources if all the dentries are in
* use.
*/
2013-08-28 08:18:05 +08:00
long prune_dcache_sb(struct super_block *sb, unsigned long nr_to_scan,
int nid)
{
LIST_HEAD(dispose);
long freed;
2013-08-28 08:18:05 +08:00
freed = list_lru_walk_node(&sb->s_dentry_lru, nid, dentry_lru_isolate,
&dispose, &nr_to_scan);
shrink_dentry_list(&dispose);
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 freed;
fix soft lock up at NFS mount via per-SB LRU-list of unused dentries [Summary] Split LRU-list of unused dentries to one per superblock to avoid soft lock up during NFS mounts and remounting of any filesystem. Previously I posted here: http://lkml.org/lkml/2008/3/5/590 [Descriptions] - background dentry_unused is a list of dentries which are not referenced. dentry_unused grows up when references on directories or files are released. This list can be very long if there is huge free memory. - the problem When shrink_dcache_sb() is called, it scans all dentry_unused linearly under spin_lock(), and if dentry->d_sb is differnt from given superblock, scan next dentry. This scan costs very much if there are many entries, and very ineffective if there are many superblocks. IOW, When we need to shrink unused dentries on one dentry, but scans unused dentries on all superblocks in the system. For example, we scan 500 dentries to unmount a filesystem, but scans 1,000,000 or more unused dentries on other superblocks. In our case , At mounting NFS*, shrink_dcache_sb() is called to shrink unused dentries on NFS, but scans 100,000,000 unused dentries on superblocks in the system such as local ext3 filesystems. I hear NFS mounting took 1 min on some system in use. * : NFS uses virtual filesystem in rpc layer, so NFS is affected by this problem. 100,000,000 is possible number on large systems. Per-superblock LRU of unused dentried can reduce the cost in reasonable manner. - How to fix I found this problem is solved by David Chinner's "Per-superblock unused dentry LRU lists V3"(1), so I rebase it and add some fix to reclaim with fairness, which is in Andrew Morton's comments(2). 1) http://lkml.org/lkml/2006/5/25/318 2) http://lkml.org/lkml/2006/5/25/320 Split LRU-list of unused dentries to each superblocks. Then, NFS mounting will check dentries under a superblock instead of all. But this spliting will break LRU of dentry-unused. So, I've attempted to make reclaim unused dentrins with fairness by calculate number of dentries to scan on this sb based on following way number of dentries to scan on this sb = count * (number of dentries on this sb / number of dentries in the machine) - ToDo - I have to measuring performance number and do stress tests. - When unmount occurs during prune_dcache(), scanning on same superblock, It is unable to reach next superblock because it is gone away. We restart scannig superblock from first one, it causes unfairness of reclaim unused dentries on first superblock. But I think this happens very rarely. - Test Results Result on 6GB boxes with excessive unused dentries. Without patch: $ cat /proc/sys/fs/dentry-state 10181835 10180203 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m1.830s user 0m0.001s sys 0m1.653s With this patch: $ cat /proc/sys/fs/dentry-state 10236610 10234751 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m0.106s user 0m0.002s sys 0m0.032s [akpm@linux-foundation.org: fix comments] Signed-off-by: Kentaro Makita <k-makita@np.css.fujitsu.com> Cc: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: David Chinner <dgc@sgi.com> Cc: "J. Bruce Fields" <bfields@fieldses.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:27:13 +08:00
}
list_lru: remove special case function list_lru_dispose_all. The list_lru implementation has one function, list_lru_dispose_all, with only one user (the dentry code). At first, such function appears to make sense because we are really not interested in the result of isolating each dentry separately - all of them are going away anyway. However, it's implementation is buggy in the following way: When we call list_lru_dispose_all in fs/dcache.c, we scan all dentries marking them with DCACHE_SHRINK_LIST. However, this is done without the nlru->lock taken. The imediate result of that is that someone else may add or remove the dentry from the LRU at the same time. When list_lru_del happens in that scenario we will see an element that is not yet marked with DCACHE_SHRINK_LIST (even though it will be in the future) and obviously remove it from an lru where the element no longer is. Since list_lru_dispose_all will in effect count down nlru's nr_items and list_lru_del will do the same, this will lead to an imbalance. The solution for this would not be so simple: we can obviously just keep the lru_lock taken, but then we have no guarantees that we will be able to acquire the dentry lock (dentry->d_lock). To properly solve this, we need a communication mechanism between the lru and dentry code, so they can coordinate this with each other. Such mechanism already exists in the form of the list_lru_walk_cb callback. So it is possible to construct a dcache-side prune function that does the right thing only by calling list_lru_walk in a loop until no more dentries are available. With only one user, plus the fact that a sane solution for the problem would involve boucing between dcache and list_lru anyway, I see little justification to keep the special case list_lru_dispose_all in tree. Signed-off-by: Glauber Costa <glommer@openvz.org> Cc: Michal Hocko <mhocko@suse.cz> Acked-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 08:18:03 +08:00
static enum lru_status dentry_lru_isolate_shrink(struct list_head *item,
spinlock_t *lru_lock, void *arg)
dcache: remove dentries from LRU before putting on dispose list One of the big problems with modifying the way the dcache shrinker and LRU implementation works is that the LRU is abused in several ways. One of these is shrink_dentry_list(). Basically, we can move a dentry off the LRU onto a different list without doing any accounting changes, and then use dentry_lru_prune() to remove it from what-ever list it is now on to do the LRU accounting at that point. This makes it -really hard- to change the LRU implementation. The use of the per-sb LRU lock serialises movement of the dentries between the different lists and the removal of them, and this is the only reason that it works. If we want to break up the dentry LRU lock and lists into, say, per-node lists, we remove the only serialisation that allows this lru list/dispose list abuse to work. To make this work effectively, the dispose list has to be isolated from the LRU list - dentries have to be removed from the LRU *before* being placed on the dispose list. This means that the LRU accounting and isolation is completed before disposal is started, and that means we can change the LRU implementation freely in future. This means that dentries *must* be marked with DCACHE_SHRINK_LIST when they are placed on the dispose list so that we don't think that parent dentries found in try_prune_one_dentry() are on the LRU when the are actually on the dispose list. This would result in accounting the dentry to the LRU a second time. Hence dentry_lru_del() has to handle the DCACHE_SHRINK_LIST case Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> 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 08:17:55 +08:00
{
list_lru: remove special case function list_lru_dispose_all. The list_lru implementation has one function, list_lru_dispose_all, with only one user (the dentry code). At first, such function appears to make sense because we are really not interested in the result of isolating each dentry separately - all of them are going away anyway. However, it's implementation is buggy in the following way: When we call list_lru_dispose_all in fs/dcache.c, we scan all dentries marking them with DCACHE_SHRINK_LIST. However, this is done without the nlru->lock taken. The imediate result of that is that someone else may add or remove the dentry from the LRU at the same time. When list_lru_del happens in that scenario we will see an element that is not yet marked with DCACHE_SHRINK_LIST (even though it will be in the future) and obviously remove it from an lru where the element no longer is. Since list_lru_dispose_all will in effect count down nlru's nr_items and list_lru_del will do the same, this will lead to an imbalance. The solution for this would not be so simple: we can obviously just keep the lru_lock taken, but then we have no guarantees that we will be able to acquire the dentry lock (dentry->d_lock). To properly solve this, we need a communication mechanism between the lru and dentry code, so they can coordinate this with each other. Such mechanism already exists in the form of the list_lru_walk_cb callback. So it is possible to construct a dcache-side prune function that does the right thing only by calling list_lru_walk in a loop until no more dentries are available. With only one user, plus the fact that a sane solution for the problem would involve boucing between dcache and list_lru anyway, I see little justification to keep the special case list_lru_dispose_all in tree. Signed-off-by: Glauber Costa <glommer@openvz.org> Cc: Michal Hocko <mhocko@suse.cz> Acked-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 08:18:03 +08:00
struct list_head *freeable = arg;
struct dentry *dentry = container_of(item, struct dentry, d_lru);
dcache: remove dentries from LRU before putting on dispose list One of the big problems with modifying the way the dcache shrinker and LRU implementation works is that the LRU is abused in several ways. One of these is shrink_dentry_list(). Basically, we can move a dentry off the LRU onto a different list without doing any accounting changes, and then use dentry_lru_prune() to remove it from what-ever list it is now on to do the LRU accounting at that point. This makes it -really hard- to change the LRU implementation. The use of the per-sb LRU lock serialises movement of the dentries between the different lists and the removal of them, and this is the only reason that it works. If we want to break up the dentry LRU lock and lists into, say, per-node lists, we remove the only serialisation that allows this lru list/dispose list abuse to work. To make this work effectively, the dispose list has to be isolated from the LRU list - dentries have to be removed from the LRU *before* being placed on the dispose list. This means that the LRU accounting and isolation is completed before disposal is started, and that means we can change the LRU implementation freely in future. This means that dentries *must* be marked with DCACHE_SHRINK_LIST when they are placed on the dispose list so that we don't think that parent dentries found in try_prune_one_dentry() are on the LRU when the are actually on the dispose list. This would result in accounting the dentry to the LRU a second time. Hence dentry_lru_del() has to handle the DCACHE_SHRINK_LIST case Signed-off-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Glauber Costa <glommer@openvz.org> 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 08:17:55 +08:00
list_lru: remove special case function list_lru_dispose_all. The list_lru implementation has one function, list_lru_dispose_all, with only one user (the dentry code). At first, such function appears to make sense because we are really not interested in the result of isolating each dentry separately - all of them are going away anyway. However, it's implementation is buggy in the following way: When we call list_lru_dispose_all in fs/dcache.c, we scan all dentries marking them with DCACHE_SHRINK_LIST. However, this is done without the nlru->lock taken. The imediate result of that is that someone else may add or remove the dentry from the LRU at the same time. When list_lru_del happens in that scenario we will see an element that is not yet marked with DCACHE_SHRINK_LIST (even though it will be in the future) and obviously remove it from an lru where the element no longer is. Since list_lru_dispose_all will in effect count down nlru's nr_items and list_lru_del will do the same, this will lead to an imbalance. The solution for this would not be so simple: we can obviously just keep the lru_lock taken, but then we have no guarantees that we will be able to acquire the dentry lock (dentry->d_lock). To properly solve this, we need a communication mechanism between the lru and dentry code, so they can coordinate this with each other. Such mechanism already exists in the form of the list_lru_walk_cb callback. So it is possible to construct a dcache-side prune function that does the right thing only by calling list_lru_walk in a loop until no more dentries are available. With only one user, plus the fact that a sane solution for the problem would involve boucing between dcache and list_lru anyway, I see little justification to keep the special case list_lru_dispose_all in tree. Signed-off-by: Glauber Costa <glommer@openvz.org> Cc: Michal Hocko <mhocko@suse.cz> Acked-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 08:18:03 +08:00
/*
* we are inverting the lru lock/dentry->d_lock here,
* so use a trylock. If we fail to get the lock, just skip
* it
*/
if (!spin_trylock(&dentry->d_lock))
return LRU_SKIP;
d_lru_shrink_move(dentry, freeable);
list_lru: remove special case function list_lru_dispose_all. The list_lru implementation has one function, list_lru_dispose_all, with only one user (the dentry code). At first, such function appears to make sense because we are really not interested in the result of isolating each dentry separately - all of them are going away anyway. However, it's implementation is buggy in the following way: When we call list_lru_dispose_all in fs/dcache.c, we scan all dentries marking them with DCACHE_SHRINK_LIST. However, this is done without the nlru->lock taken. The imediate result of that is that someone else may add or remove the dentry from the LRU at the same time. When list_lru_del happens in that scenario we will see an element that is not yet marked with DCACHE_SHRINK_LIST (even though it will be in the future) and obviously remove it from an lru where the element no longer is. Since list_lru_dispose_all will in effect count down nlru's nr_items and list_lru_del will do the same, this will lead to an imbalance. The solution for this would not be so simple: we can obviously just keep the lru_lock taken, but then we have no guarantees that we will be able to acquire the dentry lock (dentry->d_lock). To properly solve this, we need a communication mechanism between the lru and dentry code, so they can coordinate this with each other. Such mechanism already exists in the form of the list_lru_walk_cb callback. So it is possible to construct a dcache-side prune function that does the right thing only by calling list_lru_walk in a loop until no more dentries are available. With only one user, plus the fact that a sane solution for the problem would involve boucing between dcache and list_lru anyway, I see little justification to keep the special case list_lru_dispose_all in tree. Signed-off-by: Glauber Costa <glommer@openvz.org> Cc: Michal Hocko <mhocko@suse.cz> Acked-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 08:18:03 +08:00
spin_unlock(&dentry->d_lock);
list_lru: remove special case function list_lru_dispose_all. The list_lru implementation has one function, list_lru_dispose_all, with only one user (the dentry code). At first, such function appears to make sense because we are really not interested in the result of isolating each dentry separately - all of them are going away anyway. However, it's implementation is buggy in the following way: When we call list_lru_dispose_all in fs/dcache.c, we scan all dentries marking them with DCACHE_SHRINK_LIST. However, this is done without the nlru->lock taken. The imediate result of that is that someone else may add or remove the dentry from the LRU at the same time. When list_lru_del happens in that scenario we will see an element that is not yet marked with DCACHE_SHRINK_LIST (even though it will be in the future) and obviously remove it from an lru where the element no longer is. Since list_lru_dispose_all will in effect count down nlru's nr_items and list_lru_del will do the same, this will lead to an imbalance. The solution for this would not be so simple: we can obviously just keep the lru_lock taken, but then we have no guarantees that we will be able to acquire the dentry lock (dentry->d_lock). To properly solve this, we need a communication mechanism between the lru and dentry code, so they can coordinate this with each other. Such mechanism already exists in the form of the list_lru_walk_cb callback. So it is possible to construct a dcache-side prune function that does the right thing only by calling list_lru_walk in a loop until no more dentries are available. With only one user, plus the fact that a sane solution for the problem would involve boucing between dcache and list_lru anyway, I see little justification to keep the special case list_lru_dispose_all in tree. Signed-off-by: Glauber Costa <glommer@openvz.org> Cc: Michal Hocko <mhocko@suse.cz> Acked-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 08:18:03 +08:00
return LRU_REMOVED;
fix soft lock up at NFS mount via per-SB LRU-list of unused dentries [Summary] Split LRU-list of unused dentries to one per superblock to avoid soft lock up during NFS mounts and remounting of any filesystem. Previously I posted here: http://lkml.org/lkml/2008/3/5/590 [Descriptions] - background dentry_unused is a list of dentries which are not referenced. dentry_unused grows up when references on directories or files are released. This list can be very long if there is huge free memory. - the problem When shrink_dcache_sb() is called, it scans all dentry_unused linearly under spin_lock(), and if dentry->d_sb is differnt from given superblock, scan next dentry. This scan costs very much if there are many entries, and very ineffective if there are many superblocks. IOW, When we need to shrink unused dentries on one dentry, but scans unused dentries on all superblocks in the system. For example, we scan 500 dentries to unmount a filesystem, but scans 1,000,000 or more unused dentries on other superblocks. In our case , At mounting NFS*, shrink_dcache_sb() is called to shrink unused dentries on NFS, but scans 100,000,000 unused dentries on superblocks in the system such as local ext3 filesystems. I hear NFS mounting took 1 min on some system in use. * : NFS uses virtual filesystem in rpc layer, so NFS is affected by this problem. 100,000,000 is possible number on large systems. Per-superblock LRU of unused dentried can reduce the cost in reasonable manner. - How to fix I found this problem is solved by David Chinner's "Per-superblock unused dentry LRU lists V3"(1), so I rebase it and add some fix to reclaim with fairness, which is in Andrew Morton's comments(2). 1) http://lkml.org/lkml/2006/5/25/318 2) http://lkml.org/lkml/2006/5/25/320 Split LRU-list of unused dentries to each superblocks. Then, NFS mounting will check dentries under a superblock instead of all. But this spliting will break LRU of dentry-unused. So, I've attempted to make reclaim unused dentrins with fairness by calculate number of dentries to scan on this sb based on following way number of dentries to scan on this sb = count * (number of dentries on this sb / number of dentries in the machine) - ToDo - I have to measuring performance number and do stress tests. - When unmount occurs during prune_dcache(), scanning on same superblock, It is unable to reach next superblock because it is gone away. We restart scannig superblock from first one, it causes unfairness of reclaim unused dentries on first superblock. But I think this happens very rarely. - Test Results Result on 6GB boxes with excessive unused dentries. Without patch: $ cat /proc/sys/fs/dentry-state 10181835 10180203 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m1.830s user 0m0.001s sys 0m1.653s With this patch: $ cat /proc/sys/fs/dentry-state 10236610 10234751 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m0.106s user 0m0.002s sys 0m0.032s [akpm@linux-foundation.org: fix comments] Signed-off-by: Kentaro Makita <k-makita@np.css.fujitsu.com> Cc: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: David Chinner <dgc@sgi.com> Cc: "J. Bruce Fields" <bfields@fieldses.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:27:13 +08:00
}
list_lru: remove special case function list_lru_dispose_all. The list_lru implementation has one function, list_lru_dispose_all, with only one user (the dentry code). At first, such function appears to make sense because we are really not interested in the result of isolating each dentry separately - all of them are going away anyway. However, it's implementation is buggy in the following way: When we call list_lru_dispose_all in fs/dcache.c, we scan all dentries marking them with DCACHE_SHRINK_LIST. However, this is done without the nlru->lock taken. The imediate result of that is that someone else may add or remove the dentry from the LRU at the same time. When list_lru_del happens in that scenario we will see an element that is not yet marked with DCACHE_SHRINK_LIST (even though it will be in the future) and obviously remove it from an lru where the element no longer is. Since list_lru_dispose_all will in effect count down nlru's nr_items and list_lru_del will do the same, this will lead to an imbalance. The solution for this would not be so simple: we can obviously just keep the lru_lock taken, but then we have no guarantees that we will be able to acquire the dentry lock (dentry->d_lock). To properly solve this, we need a communication mechanism between the lru and dentry code, so they can coordinate this with each other. Such mechanism already exists in the form of the list_lru_walk_cb callback. So it is possible to construct a dcache-side prune function that does the right thing only by calling list_lru_walk in a loop until no more dentries are available. With only one user, plus the fact that a sane solution for the problem would involve boucing between dcache and list_lru anyway, I see little justification to keep the special case list_lru_dispose_all in tree. Signed-off-by: Glauber Costa <glommer@openvz.org> Cc: Michal Hocko <mhocko@suse.cz> Acked-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 08:18:03 +08:00
/**
* shrink_dcache_sb - shrink dcache for a superblock
* @sb: superblock
*
* Shrink the dcache for the specified super block. This is used to free
* the dcache before unmounting a file system.
*/
void shrink_dcache_sb(struct super_block *sb)
{
list_lru: remove special case function list_lru_dispose_all. The list_lru implementation has one function, list_lru_dispose_all, with only one user (the dentry code). At first, such function appears to make sense because we are really not interested in the result of isolating each dentry separately - all of them are going away anyway. However, it's implementation is buggy in the following way: When we call list_lru_dispose_all in fs/dcache.c, we scan all dentries marking them with DCACHE_SHRINK_LIST. However, this is done without the nlru->lock taken. The imediate result of that is that someone else may add or remove the dentry from the LRU at the same time. When list_lru_del happens in that scenario we will see an element that is not yet marked with DCACHE_SHRINK_LIST (even though it will be in the future) and obviously remove it from an lru where the element no longer is. Since list_lru_dispose_all will in effect count down nlru's nr_items and list_lru_del will do the same, this will lead to an imbalance. The solution for this would not be so simple: we can obviously just keep the lru_lock taken, but then we have no guarantees that we will be able to acquire the dentry lock (dentry->d_lock). To properly solve this, we need a communication mechanism between the lru and dentry code, so they can coordinate this with each other. Such mechanism already exists in the form of the list_lru_walk_cb callback. So it is possible to construct a dcache-side prune function that does the right thing only by calling list_lru_walk in a loop until no more dentries are available. With only one user, plus the fact that a sane solution for the problem would involve boucing between dcache and list_lru anyway, I see little justification to keep the special case list_lru_dispose_all in tree. Signed-off-by: Glauber Costa <glommer@openvz.org> Cc: Michal Hocko <mhocko@suse.cz> Acked-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 08:18:03 +08:00
long freed;
do {
LIST_HEAD(dispose);
freed = list_lru_walk(&sb->s_dentry_lru,
dentry_lru_isolate_shrink, &dispose, UINT_MAX);
list_lru: remove special case function list_lru_dispose_all. The list_lru implementation has one function, list_lru_dispose_all, with only one user (the dentry code). At first, such function appears to make sense because we are really not interested in the result of isolating each dentry separately - all of them are going away anyway. However, it's implementation is buggy in the following way: When we call list_lru_dispose_all in fs/dcache.c, we scan all dentries marking them with DCACHE_SHRINK_LIST. However, this is done without the nlru->lock taken. The imediate result of that is that someone else may add or remove the dentry from the LRU at the same time. When list_lru_del happens in that scenario we will see an element that is not yet marked with DCACHE_SHRINK_LIST (even though it will be in the future) and obviously remove it from an lru where the element no longer is. Since list_lru_dispose_all will in effect count down nlru's nr_items and list_lru_del will do the same, this will lead to an imbalance. The solution for this would not be so simple: we can obviously just keep the lru_lock taken, but then we have no guarantees that we will be able to acquire the dentry lock (dentry->d_lock). To properly solve this, we need a communication mechanism between the lru and dentry code, so they can coordinate this with each other. Such mechanism already exists in the form of the list_lru_walk_cb callback. So it is possible to construct a dcache-side prune function that does the right thing only by calling list_lru_walk in a loop until no more dentries are available. With only one user, plus the fact that a sane solution for the problem would involve boucing between dcache and list_lru anyway, I see little justification to keep the special case list_lru_dispose_all in tree. Signed-off-by: Glauber Costa <glommer@openvz.org> Cc: Michal Hocko <mhocko@suse.cz> Acked-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-08-28 08:18:03 +08:00
this_cpu_sub(nr_dentry_unused, freed);
shrink_dentry_list(&dispose);
} while (freed > 0);
}
EXPORT_SYMBOL(shrink_dcache_sb);
/**
* enum d_walk_ret - action to talke during tree walk
* @D_WALK_CONTINUE: contrinue walk
* @D_WALK_QUIT: quit walk
* @D_WALK_NORETRY: quit when retry is needed
* @D_WALK_SKIP: skip this dentry and its children
*/
enum d_walk_ret {
D_WALK_CONTINUE,
D_WALK_QUIT,
D_WALK_NORETRY,
D_WALK_SKIP,
};
/**
* d_walk - walk the dentry tree
* @parent: start of walk
* @data: data passed to @enter() and @finish()
* @enter: callback when first entering the dentry
* @finish: callback when successfully finished the walk
*
* The @enter() and @finish() callbacks are called with d_lock held.
*/
static void d_walk(struct dentry *parent, void *data,
enum d_walk_ret (*enter)(void *, struct dentry *),
void (*finish)(void *))
{
struct dentry *this_parent;
struct list_head *next;
unsigned seq = 0;
enum d_walk_ret ret;
bool retry = true;
again:
read_seqbegin_or_lock(&rename_lock, &seq);
this_parent = parent;
spin_lock(&this_parent->d_lock);
ret = enter(data, this_parent);
switch (ret) {
case D_WALK_CONTINUE:
break;
case D_WALK_QUIT:
case D_WALK_SKIP:
goto out_unlock;
case D_WALK_NORETRY:
retry = false;
break;
}
repeat:
next = this_parent->d_subdirs.next;
resume:
while (next != &this_parent->d_subdirs) {
struct list_head *tmp = next;
[PATCH] shrink dentry struct Some long time ago, dentry struct was carefully tuned so that on 32 bits UP, sizeof(struct dentry) was exactly 128, ie a power of 2, and a multiple of memory cache lines. Then RCU was added and dentry struct enlarged by two pointers, with nice results for SMP, but not so good on UP, because breaking the above tuning (128 + 8 = 136 bytes) This patch reverts this unwanted side effect, by using an union (d_u), where d_rcu and d_child are placed so that these two fields can share their memory needs. At the time d_free() is called (and d_rcu is really used), d_child is known to be empty and not touched by the dentry freeing. Lockless lookups only access d_name, d_parent, d_lock, d_op, d_flags (so the previous content of d_child is not needed if said dentry was unhashed but still accessed by a CPU because of RCU constraints) As dentry cache easily contains millions of entries, a size reduction is worth the extra complexity of the ugly C union. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Maneesh Soni <maneesh@in.ibm.com> Cc: Miklos Szeredi <miklos@szeredi.hu> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Ian Kent <raven@themaw.net> Cc: Paul Jackson <pj@sgi.com> Cc: Al Viro <viro@ftp.linux.org.uk> Cc: Christoph Hellwig <hch@lst.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Neil Brown <neilb@cse.unsw.edu.au> Cc: James Morris <jmorris@namei.org> Cc: Stephen Smalley <sds@epoch.ncsc.mil> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:03:32 +08:00
struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child);
next = tmp->next;
spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
ret = enter(data, dentry);
switch (ret) {
case D_WALK_CONTINUE:
break;
case D_WALK_QUIT:
spin_unlock(&dentry->d_lock);
goto out_unlock;
case D_WALK_NORETRY:
retry = false;
break;
case D_WALK_SKIP:
spin_unlock(&dentry->d_lock);
continue;
}
if (!list_empty(&dentry->d_subdirs)) {
spin_unlock(&this_parent->d_lock);
spin_release(&dentry->d_lock.dep_map, 1, _RET_IP_);
this_parent = dentry;
spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_);
goto repeat;
}
spin_unlock(&dentry->d_lock);
}
/*
* All done at this level ... ascend and resume the search.
*/
if (this_parent != parent) {
struct dentry *child = this_parent;
this_parent = child->d_parent;
rcu_read_lock();
spin_unlock(&child->d_lock);
spin_lock(&this_parent->d_lock);
/*
* might go back up the wrong parent if we have had a rename
* or deletion
*/
if (this_parent != child->d_parent ||
(child->d_flags & DCACHE_DENTRY_KILLED) ||
need_seqretry(&rename_lock, seq)) {
spin_unlock(&this_parent->d_lock);
rcu_read_unlock();
goto rename_retry;
}
rcu_read_unlock();
next = child->d_u.d_child.next;
goto resume;
}
if (need_seqretry(&rename_lock, seq)) {
spin_unlock(&this_parent->d_lock);
goto rename_retry;
}
if (finish)
finish(data);
out_unlock:
spin_unlock(&this_parent->d_lock);
done_seqretry(&rename_lock, seq);
return;
rename_retry:
if (!retry)
return;
seq = 1;
goto again;
}
/*
* Search for at least 1 mount point in the dentry's subdirs.
* We descend to the next level whenever the d_subdirs
* list is non-empty and continue searching.
*/
static enum d_walk_ret check_mount(void *data, struct dentry *dentry)
{
int *ret = data;
if (d_mountpoint(dentry)) {
*ret = 1;
return D_WALK_QUIT;
}
return D_WALK_CONTINUE;
}
/**
* have_submounts - check for mounts over a dentry
* @parent: dentry to check.
*
* Return true if the parent or its subdirectories contain
* a mount point
*/
int have_submounts(struct dentry *parent)
{
int ret = 0;
d_walk(parent, &ret, check_mount, NULL);
return ret;
}
EXPORT_SYMBOL(have_submounts);
/*
* Called by mount code to set a mountpoint and check if the mountpoint is
* reachable (e.g. NFS can unhash a directory dentry and then the complete
* subtree can become unreachable).
*
* Only one of check_submounts_and_drop() and d_set_mounted() must succeed. For
* this reason take rename_lock and d_lock on dentry and ancestors.
*/
int d_set_mounted(struct dentry *dentry)
{
struct dentry *p;
int ret = -ENOENT;
write_seqlock(&rename_lock);
for (p = dentry->d_parent; !IS_ROOT(p); p = p->d_parent) {
/* Need exclusion wrt. check_submounts_and_drop() */
spin_lock(&p->d_lock);
if (unlikely(d_unhashed(p))) {
spin_unlock(&p->d_lock);
goto out;
}
spin_unlock(&p->d_lock);
}
spin_lock(&dentry->d_lock);
if (!d_unlinked(dentry)) {
dentry->d_flags |= DCACHE_MOUNTED;
ret = 0;
}
spin_unlock(&dentry->d_lock);
out:
write_sequnlock(&rename_lock);
return ret;
}
/*
* Search the dentry child list of the specified parent,
* and move any unused dentries to the end of the unused
* list for prune_dcache(). We descend to the next level
* whenever the d_subdirs list is non-empty and continue
* searching.
*
* It returns zero iff there are no unused children,
* otherwise it returns the number of children moved to
* the end of the unused list. This may not be the total
* number of unused children, because select_parent can
* drop the lock and return early due to latency
* constraints.
*/
struct select_data {
struct dentry *start;
struct list_head dispose;
int found;
};
static enum d_walk_ret select_collect(void *_data, struct dentry *dentry)
{
struct select_data *data = _data;
enum d_walk_ret ret = D_WALK_CONTINUE;
if (data->start == dentry)
goto out;
/*
* move only zero ref count dentries to the dispose list.
*
* Those which are presently on the shrink list, being processed
* by shrink_dentry_list(), shouldn't be moved. Otherwise the
* loop in shrink_dcache_parent() might not make any progress
* and loop forever.
*/
if (dentry->d_lockref.count) {
dentry_lru_del(dentry);
} else if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) {
/*
* We can't use d_lru_shrink_move() because we
* need to get the global LRU lock and do the
* LRU accounting.
*/
d_lru_del(dentry);
d_shrink_add(dentry, &data->dispose);
data->found++;
ret = D_WALK_NORETRY;
}
/*
* We can return to the caller if we have found some (this
* ensures forward progress). We'll be coming back to find
* the rest.
*/
if (data->found && need_resched())
ret = D_WALK_QUIT;
out:
return ret;
}
/**
* shrink_dcache_parent - prune dcache
* @parent: parent of entries to prune
*
* Prune the dcache to remove unused children of the parent dentry.
*/
void shrink_dcache_parent(struct dentry *parent)
{
for (;;) {
struct select_data data;
INIT_LIST_HEAD(&data.dispose);
data.start = parent;
data.found = 0;
d_walk(parent, &data, select_collect, NULL);
if (!data.found)
break;
shrink_dentry_list(&data.dispose);
fs/dcache.c: add cond_resched() to shrink_dcache_parent() Call cond_resched() in shrink_dcache_parent() to maintain interactivity. Before this patch: void shrink_dcache_parent(struct dentry * parent) { while ((found = select_parent(parent, &dispose)) != 0) shrink_dentry_list(&dispose); } select_parent() populates the dispose list with dentries which shrink_dentry_list() then deletes. select_parent() carefully uses need_resched() to avoid doing too much work at once. But neither shrink_dcache_parent() nor its called functions call cond_resched(). So once need_resched() is set select_parent() will return single dentry dispose list which is then deleted by shrink_dentry_list(). This is inefficient when there are a lot of dentry to process. This can cause softlockup and hurts interactivity on non preemptable kernels. This change adds cond_resched() in shrink_dcache_parent(). The benefit of this is that need_resched() is quickly cleared so that future calls to select_parent() are able to efficiently return a big batch of dentry. These additional cond_resched() do not seem to impact performance, at least for the workload below. Here is a program which can cause soft lockup if other system activity sets need_resched(). int main() { struct rlimit rlim; int i; int f[100000]; char buf[20]; struct timeval t1, t2; double diff; /* cleanup past run */ system("rm -rf x"); /* boost nfile rlimit */ rlim.rlim_cur = 200000; rlim.rlim_max = 200000; if (setrlimit(RLIMIT_NOFILE, &rlim)) err(1, "setrlimit"); /* make directory for files */ if (mkdir("x", 0700)) err(1, "mkdir"); if (gettimeofday(&t1, NULL)) err(1, "gettimeofday"); /* populate directory with open files */ for (i = 0; i < 100000; i++) { snprintf(buf, sizeof(buf), "x/%d", i); f[i] = open(buf, O_CREAT); if (f[i] == -1) err(1, "open"); } /* close some of the files */ for (i = 0; i < 85000; i++) close(f[i]); /* unlink all files, even open ones */ system("rm -rf x"); if (gettimeofday(&t2, NULL)) err(1, "gettimeofday"); diff = (((double)t2.tv_sec * 1000000 + t2.tv_usec) - ((double)t1.tv_sec * 1000000 + t1.tv_usec)); printf("done: %g elapsed\n", diff/1e6); return 0; } Signed-off-by: Greg Thelen <gthelen@google.com> Signed-off-by: Dave Chinner <david@fromorbit.com> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-05-01 06:26:48 +08:00
cond_resched();
}
}
EXPORT_SYMBOL(shrink_dcache_parent);
static enum d_walk_ret umount_collect(void *_data, struct dentry *dentry)
{
struct select_data *data = _data;
enum d_walk_ret ret = D_WALK_CONTINUE;
if (dentry->d_lockref.count) {
dentry_lru_del(dentry);
if (likely(!list_empty(&dentry->d_subdirs)))
goto out;
if (dentry == data->start && dentry->d_lockref.count == 1)
goto out;
printk(KERN_ERR
"BUG: Dentry %p{i=%lx,n=%s}"
" still in use (%d)"
" [unmount of %s %s]\n",
dentry,
dentry->d_inode ?
dentry->d_inode->i_ino : 0UL,
dentry->d_name.name,
dentry->d_lockref.count,
dentry->d_sb->s_type->name,
dentry->d_sb->s_id);
BUG();
} else if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) {
/*
* We can't use d_lru_shrink_move() because we
* need to get the global LRU lock and do the
* LRU accounting.
*/
if (dentry->d_flags & DCACHE_LRU_LIST)
d_lru_del(dentry);
d_shrink_add(dentry, &data->dispose);
data->found++;
ret = D_WALK_NORETRY;
}
out:
if (data->found && need_resched())
ret = D_WALK_QUIT;
return ret;
}
/*
* destroy the dentries attached to a superblock on unmounting
*/
void shrink_dcache_for_umount(struct super_block *sb)
{
struct dentry *dentry;
if (down_read_trylock(&sb->s_umount))
BUG();
dentry = sb->s_root;
sb->s_root = NULL;
for (;;) {
struct select_data data;
INIT_LIST_HEAD(&data.dispose);
data.start = dentry;
data.found = 0;
d_walk(dentry, &data, umount_collect, NULL);
if (!data.found)
break;
shrink_dentry_list(&data.dispose);
cond_resched();
}
d_drop(dentry);
dput(dentry);
while (!hlist_bl_empty(&sb->s_anon)) {
struct select_data data;
dentry = hlist_bl_entry(hlist_bl_first(&sb->s_anon), struct dentry, d_hash);
INIT_LIST_HEAD(&data.dispose);
data.start = NULL;
data.found = 0;
d_walk(dentry, &data, umount_collect, NULL);
if (data.found)
shrink_dentry_list(&data.dispose);
cond_resched();
}
}
static enum d_walk_ret check_and_collect(void *_data, struct dentry *dentry)
{
struct select_data *data = _data;
if (d_mountpoint(dentry)) {
data->found = -EBUSY;
return D_WALK_QUIT;
}
return select_collect(_data, dentry);
}
static void check_and_drop(void *_data)
{
struct select_data *data = _data;
if (d_mountpoint(data->start))
data->found = -EBUSY;
if (!data->found)
__d_drop(data->start);
}
/**
* check_submounts_and_drop - prune dcache, check for submounts and drop
*
* All done as a single atomic operation relative to has_unlinked_ancestor().
* Returns 0 if successfully unhashed @parent. If there were submounts then
* return -EBUSY.
*
* @dentry: dentry to prune and drop
*/
int check_submounts_and_drop(struct dentry *dentry)
{
int ret = 0;
/* Negative dentries can be dropped without further checks */
if (!dentry->d_inode) {
d_drop(dentry);
goto out;
}
for (;;) {
struct select_data data;
INIT_LIST_HEAD(&data.dispose);
data.start = dentry;
data.found = 0;
d_walk(dentry, &data, check_and_collect, check_and_drop);
ret = data.found;
if (!list_empty(&data.dispose))
shrink_dentry_list(&data.dispose);
if (ret <= 0)
break;
cond_resched();
}
out:
return ret;
}
EXPORT_SYMBOL(check_submounts_and_drop);
/**
* __d_alloc - allocate a dcache entry
* @sb: filesystem it will belong to
* @name: qstr of the name
*
* Allocates a dentry. It returns %NULL if there is insufficient memory
* available. On a success the dentry is returned. The name passed in is
* copied and the copy passed in may be reused after this call.
*/
struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
{
struct dentry *dentry;
char *dname;
dentry = kmem_cache_alloc(dentry_cache, GFP_KERNEL);
if (!dentry)
return NULL;
2012-05-22 07:14:04 +08:00
/*
* We guarantee that the inline name is always NUL-terminated.
* This way the memcpy() done by the name switching in rename
* will still always have a NUL at the end, even if we might
* be overwriting an internal NUL character
*/
dentry->d_iname[DNAME_INLINE_LEN-1] = 0;
if (name->len > DNAME_INLINE_LEN-1) {
dname = kmalloc(name->len + 1, GFP_KERNEL);
if (!dname) {
kmem_cache_free(dentry_cache, dentry);
return NULL;
}
} else {
dname = dentry->d_iname;
}
dentry->d_name.len = name->len;
dentry->d_name.hash = name->hash;
memcpy(dname, name->name, name->len);
dname[name->len] = 0;
2012-05-22 07:14:04 +08:00
/* Make sure we always see the terminating NUL character */
smp_wmb();
dentry->d_name.name = dname;
dentry->d_lockref.count = 1;
vfs: get rid of insane dentry hashing rules The dentry hashing rules have been really quite complicated for a long while, in odd ways. That made functions like __d_drop() very fragile and non-obvious. In particular, whether a dentry was hashed or not was indicated with an explicit DCACHE_UNHASHED bit. That's despite the fact that the hash abstraction that the dentries use actually have a 'is this entry hashed or not' model (which is a simple test of the 'pprev' pointer). The reason that was done is because we used the normal 'is this entry unhashed' model to mark whether the dentry had _ever_ been hashed in the dentry hash tables, and that logic goes back many years (commit b3423415fbc2: "dcache: avoid RCU for never-hashed dentries"). That, in turn, meant that __d_drop had totally different unhashing logic for the dentry hash table case and for the anonymous dcache case, because in order to use the "is this dentry hashed" logic as a flag for whether it had ever been on the RCU hash table, we had to unhash such a dentry differently so that we'd never think that it wasn't 'unhashed' and wouldn't be free'd correctly. That's just insane. It made the logic really hard to follow, when there were two different kinds of "unhashed" states, and one of them (the one that used "list_bl_unhashed()") really had nothing at all to do with being unhashed per se, but with a very subtle lifetime rule instead. So turn all of it around, and make it logical. Instead of having a DENTRY_UNHASHED bit in d_flags to indicate whether the dentry is on the hash chains or not, use the hash chain unhashed logic for that. Suddenly "d_unhashed()" just uses "list_bl_unhashed()", and everything makes sense. And for the lifetime rule, just use an explicit DENTRY_RCUACCEES bit. If we ever insert the dentry into the dentry hash table so that it is visible to RCU lookup, we mark it DENTRY_RCUACCESS to show that it now needs the RCU lifetime rules. Now suddently that test at dentry free time makes sense too. And because unhashing now is sane and doesn't depend on where the dentry got unhashed from (because the dentry hash chain details doesn't have some subtle side effects), we can re-unify the __d_drop() logic and use common code for the unhashing. Also fix one more open-coded hash chain bit_spin_lock() that I missed in the previous chain locking cleanup commit. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-04-24 22:58:46 +08:00
dentry->d_flags = 0;
spin_lock_init(&dentry->d_lock);
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
seqcount_init(&dentry->d_seq);
dentry->d_inode = NULL;
dentry->d_parent = dentry;
dentry->d_sb = sb;
dentry->d_op = NULL;
dentry->d_fsdata = NULL;
INIT_HLIST_BL_NODE(&dentry->d_hash);
INIT_LIST_HEAD(&dentry->d_lru);
INIT_LIST_HEAD(&dentry->d_subdirs);
INIT_HLIST_NODE(&dentry->d_alias);
INIT_LIST_HEAD(&dentry->d_u.d_child);
d_set_d_op(dentry, dentry->d_sb->s_d_op);
fs: use fast counters for vfs caches percpu_counter library generates quite nasty code, so unless you need to dynamically allocate counters or take fast approximate value, a simple per cpu set of counters is much better. The percpu_counter can never be made to work as well, because it has an indirection from pointer to percpu memory, and it can't use direct this_cpu_inc interfaces because it doesn't use static PER_CPU data, so code will always be worse. In the fastpath, it is the difference between this: incl %gs:nr_dentry # nr_dentry and this: movl percpu_counter_batch(%rip), %edx # percpu_counter_batch, movl $1, %esi #, movq $nr_dentry, %rdi #, call __percpu_counter_add # (plus I clobber registers) __percpu_counter_add: pushq %rbp # movq %rsp, %rbp #, subq $32, %rsp #, movq %rbx, -24(%rbp) #, movq %r12, -16(%rbp) #, movq %r13, -8(%rbp) #, movq %rdi, %rbx # fbc, fbc #APP # 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1 movq %gs:kernel_stack,%rax #, pfo_ret__ # 0 "" 2 #NO_APP incl -8124(%rax) # <variable>.preempt_count movq 32(%rdi), %r12 # <variable>.counters, tcp_ptr__ #APP # 78 "lib/percpu_counter.c" 1 add %gs:this_cpu_off, %r12 # this_cpu_off, tcp_ptr__ # 0 "" 2 #NO_APP movslq (%r12),%r13 #* tcp_ptr__, tmp73 movslq %edx,%rax # batch, batch addq %rsi, %r13 # amount, count cmpq %rax, %r13 # batch, count jge .L27 #, negl %edx # tmp76 movslq %edx,%rdx # tmp76, tmp77 cmpq %rdx, %r13 # tmp77, count jg .L28 #, .L27: movq %rbx, %rdi # fbc, call _raw_spin_lock # addq %r13, 8(%rbx) # count, <variable>.count movq %rbx, %rdi # fbc, movl $0, (%r12) #,* tcp_ptr__ call _raw_spin_unlock # .L29: #APP # 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1 movq %gs:kernel_stack,%rax #, pfo_ret__ # 0 "" 2 #NO_APP decl -8124(%rax) # <variable>.preempt_count movq -8136(%rax), %rax #, D.14625 testb $8, %al #, D.14625 jne .L32 #, .L31: movq -24(%rbp), %rbx #, movq -16(%rbp), %r12 #, movq -8(%rbp), %r13 #, leave ret .p2align 4,,10 .p2align 3 .L28: movl %r13d, (%r12) # count,* jmp .L29 # .L32: call preempt_schedule # .p2align 4,,6 jmp .L31 # .size __percpu_counter_add, .-__percpu_counter_add .p2align 4,,15 Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:19 +08:00
this_cpu_inc(nr_dentry);
return dentry;
}
/**
* d_alloc - allocate a dcache entry
* @parent: parent of entry to allocate
* @name: qstr of the name
*
* Allocates a dentry. It returns %NULL if there is insufficient memory
* available. On a success the dentry is returned. The name passed in is
* copied and the copy passed in may be reused after this call.
*/
struct dentry *d_alloc(struct dentry * parent, const struct qstr *name)
{
struct dentry *dentry = __d_alloc(parent->d_sb, name);
if (!dentry)
return NULL;
spin_lock(&parent->d_lock);
/*
* don't need child lock because it is not subject
* to concurrency here
*/
__dget_dlock(parent);
dentry->d_parent = parent;
list_add(&dentry->d_u.d_child, &parent->d_subdirs);
spin_unlock(&parent->d_lock);
return dentry;
}
EXPORT_SYMBOL(d_alloc);
/**
* d_alloc_pseudo - allocate a dentry (for lookup-less filesystems)
* @sb: the superblock
* @name: qstr of the name
*
* For a filesystem that just pins its dentries in memory and never
* performs lookups at all, return an unhashed IS_ROOT dentry.
*/
struct dentry *d_alloc_pseudo(struct super_block *sb, const struct qstr *name)
{
return __d_alloc(sb, name);
}
EXPORT_SYMBOL(d_alloc_pseudo);
struct dentry *d_alloc_name(struct dentry *parent, const char *name)
{
struct qstr q;
q.name = name;
q.len = strlen(name);
q.hash = full_name_hash(q.name, q.len);
return d_alloc(parent, &q);
}
EXPORT_SYMBOL(d_alloc_name);
void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op)
{
WARN_ON_ONCE(dentry->d_op);
WARN_ON_ONCE(dentry->d_flags & (DCACHE_OP_HASH |
DCACHE_OP_COMPARE |
DCACHE_OP_REVALIDATE |
vfs: kill FS_REVAL_DOT by adding a d_weak_revalidate dentry op The following set of operations on a NFS client and server will cause server# mkdir a client# cd a server# mv a a.bak client# sleep 30 # (or whatever the dir attrcache timeout is) client# stat . stat: cannot stat `.': Stale NFS file handle Obviously, we should not be getting an ESTALE error back there since the inode still exists on the server. The problem is that the lookup code will call d_revalidate on the dentry that "." refers to, because NFS has FS_REVAL_DOT set. nfs_lookup_revalidate will see that the parent directory has changed and will try to reverify the dentry by redoing a LOOKUP. That of course fails, so the lookup code returns ESTALE. The problem here is that d_revalidate is really a bad fit for this case. What we really want to know at this point is whether the inode is still good or not, but we don't really care what name it goes by or whether the dcache is still valid. Add a new d_op->d_weak_revalidate operation and have complete_walk call that instead of d_revalidate. The intent there is to allow for a "weaker" d_revalidate that just checks to see whether the inode is still good. This is also gives us an opportunity to kill off the FS_REVAL_DOT special casing. [AV: changed method name, added note in porting, fixed confusion re having it possibly called from RCU mode (it won't be)] Cc: NeilBrown <neilb@suse.de> Signed-off-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-02-21 00:19:05 +08:00
DCACHE_OP_WEAK_REVALIDATE |
DCACHE_OP_DELETE ));
dentry->d_op = op;
if (!op)
return;
if (op->d_hash)
dentry->d_flags |= DCACHE_OP_HASH;
if (op->d_compare)
dentry->d_flags |= DCACHE_OP_COMPARE;
if (op->d_revalidate)
dentry->d_flags |= DCACHE_OP_REVALIDATE;
vfs: kill FS_REVAL_DOT by adding a d_weak_revalidate dentry op The following set of operations on a NFS client and server will cause server# mkdir a client# cd a server# mv a a.bak client# sleep 30 # (or whatever the dir attrcache timeout is) client# stat . stat: cannot stat `.': Stale NFS file handle Obviously, we should not be getting an ESTALE error back there since the inode still exists on the server. The problem is that the lookup code will call d_revalidate on the dentry that "." refers to, because NFS has FS_REVAL_DOT set. nfs_lookup_revalidate will see that the parent directory has changed and will try to reverify the dentry by redoing a LOOKUP. That of course fails, so the lookup code returns ESTALE. The problem here is that d_revalidate is really a bad fit for this case. What we really want to know at this point is whether the inode is still good or not, but we don't really care what name it goes by or whether the dcache is still valid. Add a new d_op->d_weak_revalidate operation and have complete_walk call that instead of d_revalidate. The intent there is to allow for a "weaker" d_revalidate that just checks to see whether the inode is still good. This is also gives us an opportunity to kill off the FS_REVAL_DOT special casing. [AV: changed method name, added note in porting, fixed confusion re having it possibly called from RCU mode (it won't be)] Cc: NeilBrown <neilb@suse.de> Signed-off-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-02-21 00:19:05 +08:00
if (op->d_weak_revalidate)
dentry->d_flags |= DCACHE_OP_WEAK_REVALIDATE;
if (op->d_delete)
dentry->d_flags |= DCACHE_OP_DELETE;
if (op->d_prune)
dentry->d_flags |= DCACHE_OP_PRUNE;
}
EXPORT_SYMBOL(d_set_d_op);
static unsigned d_flags_for_inode(struct inode *inode)
{
unsigned add_flags = DCACHE_FILE_TYPE;
if (!inode)
return DCACHE_MISS_TYPE;
if (S_ISDIR(inode->i_mode)) {
add_flags = DCACHE_DIRECTORY_TYPE;
if (unlikely(!(inode->i_opflags & IOP_LOOKUP))) {
if (unlikely(!inode->i_op->lookup))
add_flags = DCACHE_AUTODIR_TYPE;
else
inode->i_opflags |= IOP_LOOKUP;
}
} else if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) {
if (unlikely(inode->i_op->follow_link))
add_flags = DCACHE_SYMLINK_TYPE;
else
inode->i_opflags |= IOP_NOFOLLOW;
}
if (unlikely(IS_AUTOMOUNT(inode)))
add_flags |= DCACHE_NEED_AUTOMOUNT;
return add_flags;
}
static void __d_instantiate(struct dentry *dentry, struct inode *inode)
{
unsigned add_flags = d_flags_for_inode(inode);
spin_lock(&dentry->d_lock);
dentry->d_flags &= ~DCACHE_ENTRY_TYPE;
dentry->d_flags |= add_flags;
if (inode)
hlist_add_head(&dentry->d_alias, &inode->i_dentry);
dentry->d_inode = inode;
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
dentry_rcuwalk_barrier(dentry);
spin_unlock(&dentry->d_lock);
fsnotify_d_instantiate(dentry, inode);
}
/**
* d_instantiate - fill in inode information for a dentry
* @entry: dentry to complete
* @inode: inode to attach to this dentry
*
* Fill in inode information in the entry.
*
* This turns negative dentries into productive full members
* of society.
*
* NOTE! This assumes that the inode count has been incremented
* (or otherwise set) by the caller to indicate that it is now
* in use by the dcache.
*/
void d_instantiate(struct dentry *entry, struct inode * inode)
{
BUG_ON(!hlist_unhashed(&entry->d_alias));
if (inode)
spin_lock(&inode->i_lock);
__d_instantiate(entry, inode);
if (inode)
spin_unlock(&inode->i_lock);
security_d_instantiate(entry, inode);
}
EXPORT_SYMBOL(d_instantiate);
/**
* d_instantiate_unique - instantiate a non-aliased dentry
* @entry: dentry to instantiate
* @inode: inode to attach to this dentry
*
* Fill in inode information in the entry. On success, it returns NULL.
* If an unhashed alias of "entry" already exists, then we return the
* aliased dentry instead and drop one reference to inode.
*
* Note that in order to avoid conflicts with rename() etc, the caller
* had better be holding the parent directory semaphore.
*
* This also assumes that the inode count has been incremented
* (or otherwise set) by the caller to indicate that it is now
* in use by the dcache.
*/
static struct dentry *__d_instantiate_unique(struct dentry *entry,
struct inode *inode)
{
struct dentry *alias;
int len = entry->d_name.len;
const char *name = entry->d_name.name;
unsigned int hash = entry->d_name.hash;
if (!inode) {
__d_instantiate(entry, NULL);
return NULL;
}
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(alias, &inode->i_dentry, d_alias) {
/*
* Don't need alias->d_lock here, because aliases with
* d_parent == entry->d_parent are not subject to name or
* parent changes, because the parent inode i_mutex is held.
*/
vfs: clean up __d_lookup_rcu() and dentry_cmp() interfaces The calling conventions for __d_lookup_rcu() and dentry_cmp() are annoying in different ways, and there is actually one single underlying reason for both of the annoyances. The fundamental reason is that we do the returned dentry sequence number check inside __d_lookup_rcu() instead of doing it in the caller. This results in two annoyances: - __d_lookup_rcu() now not only needs to return the dentry and the sequence number that goes along with the lookup, it also needs to return the inode pointer that was validated by that sequence number check. - and because we did the sequence number check early (to validate the name pointer and length) we also couldn't just pass the dentry itself to dentry_cmp(), we had to pass the counted string that contained the name. So that sequence number decision caused two separate ugly calling conventions. Both of these problems would be solved if we just did the sequence number check in the caller instead. There's only one caller, and that caller already has to do the sequence number check for the parent anyway, so just do that. That allows us to stop returning the dentry->d_inode in that in-out argument (pointer-to-pointer-to-inode), so we can make the inode argument just a regular input inode pointer. The caller can just load the inode from dentry->d_inode, and then do the sequence number check after that to make sure that it's synchronized with the name we looked up. And it allows us to just pass in the dentry to dentry_cmp(), which is what all the callers really wanted. Sure, dentry_cmp() has to be a bit careful about the dentry (which is not stable during RCU lookup), but that's actually very simple. And now that dentry_cmp() can clearly see that the first string argument is a dentry, we can use the direct word access for that, instead of the careful unaligned zero-padding. The dentry name is always properly aligned, since it is a single path component that is either embedded into the dentry itself, or was allocated with kmalloc() (see __d_alloc). Finally, this also uninlines the nasty slow-case for dentry comparisons: that one *does* need to do a sequence number check, since it will call in to the low-level filesystems, and we want to give those a stable inode pointer and path component length/start arguments. Doing an extra sequence check for that slow case is not a problem, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-05-05 05:59:14 +08:00
if (alias->d_name.hash != hash)
continue;
if (alias->d_parent != entry->d_parent)
continue;
if (alias->d_name.len != len)
continue;
vfs: clean up __d_lookup_rcu() and dentry_cmp() interfaces The calling conventions for __d_lookup_rcu() and dentry_cmp() are annoying in different ways, and there is actually one single underlying reason for both of the annoyances. The fundamental reason is that we do the returned dentry sequence number check inside __d_lookup_rcu() instead of doing it in the caller. This results in two annoyances: - __d_lookup_rcu() now not only needs to return the dentry and the sequence number that goes along with the lookup, it also needs to return the inode pointer that was validated by that sequence number check. - and because we did the sequence number check early (to validate the name pointer and length) we also couldn't just pass the dentry itself to dentry_cmp(), we had to pass the counted string that contained the name. So that sequence number decision caused two separate ugly calling conventions. Both of these problems would be solved if we just did the sequence number check in the caller instead. There's only one caller, and that caller already has to do the sequence number check for the parent anyway, so just do that. That allows us to stop returning the dentry->d_inode in that in-out argument (pointer-to-pointer-to-inode), so we can make the inode argument just a regular input inode pointer. The caller can just load the inode from dentry->d_inode, and then do the sequence number check after that to make sure that it's synchronized with the name we looked up. And it allows us to just pass in the dentry to dentry_cmp(), which is what all the callers really wanted. Sure, dentry_cmp() has to be a bit careful about the dentry (which is not stable during RCU lookup), but that's actually very simple. And now that dentry_cmp() can clearly see that the first string argument is a dentry, we can use the direct word access for that, instead of the careful unaligned zero-padding. The dentry name is always properly aligned, since it is a single path component that is either embedded into the dentry itself, or was allocated with kmalloc() (see __d_alloc). Finally, this also uninlines the nasty slow-case for dentry comparisons: that one *does* need to do a sequence number check, since it will call in to the low-level filesystems, and we want to give those a stable inode pointer and path component length/start arguments. Doing an extra sequence check for that slow case is not a problem, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-05-05 05:59:14 +08:00
if (dentry_cmp(alias, name, len))
continue;
__dget(alias);
return alias;
}
__d_instantiate(entry, inode);
return NULL;
}
struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode)
{
struct dentry *result;
BUG_ON(!hlist_unhashed(&entry->d_alias));
if (inode)
spin_lock(&inode->i_lock);
result = __d_instantiate_unique(entry, inode);
if (inode)
spin_unlock(&inode->i_lock);
if (!result) {
security_d_instantiate(entry, inode);
return NULL;
}
BUG_ON(!d_unhashed(result));
iput(inode);
return result;
}
EXPORT_SYMBOL(d_instantiate_unique);
/**
* d_instantiate_no_diralias - instantiate a non-aliased dentry
* @entry: dentry to complete
* @inode: inode to attach to this dentry
*
* Fill in inode information in the entry. If a directory alias is found, then
* return an error (and drop inode). Together with d_materialise_unique() this
* guarantees that a directory inode may never have more than one alias.
*/
int d_instantiate_no_diralias(struct dentry *entry, struct inode *inode)
{
BUG_ON(!hlist_unhashed(&entry->d_alias));
spin_lock(&inode->i_lock);
if (S_ISDIR(inode->i_mode) && !hlist_empty(&inode->i_dentry)) {
spin_unlock(&inode->i_lock);
iput(inode);
return -EBUSY;
}
__d_instantiate(entry, inode);
spin_unlock(&inode->i_lock);
security_d_instantiate(entry, inode);
return 0;
}
EXPORT_SYMBOL(d_instantiate_no_diralias);
struct dentry *d_make_root(struct inode *root_inode)
{
struct dentry *res = NULL;
if (root_inode) {
static const struct qstr name = QSTR_INIT("/", 1);
res = __d_alloc(root_inode->i_sb, &name);
if (res)
d_instantiate(res, root_inode);
else
iput(root_inode);
}
return res;
}
EXPORT_SYMBOL(d_make_root);
fs/dcache: allow d_obtain_alias() to return unhashed dentries Without this patch, inodes are not promptly freed on last close of an unlinked file by an nfs client: client$ mount -tnfs4 server:/export/ /mnt/ client$ tail -f /mnt/FOO ... server$ df -i /export server$ rm /export/FOO (^C the tail -f) server$ df -i /export server$ echo 2 >/proc/sys/vm/drop_caches server$ df -i /export the df's will show that the inode is not freed on the filesystem until the last step, when it could have been freed after killing the client's tail -f. On-disk data won't be deallocated either, leading to possible spurious ENOSPC. This occurs because when the client does the close, it arrives in a compound with a putfh and a close, processed like: - putfh: look up the filehandle.  The only alias found for the inode will be DCACHE_UNHASHED alias referenced by the filp this, so it creates a new DCACHE_DISCONECTED dentry and returns that instead. - close: closes the existing filp, which is destroyed immediately by dput() since it's DCACHE_UNHASHED. - end of the compound: release the reference to the current filehandle, and dput() the new DCACHE_DISCONECTED dentry, which gets put on the unused list instead of being destroyed immediately. Nick Piggin suggested fixing this by allowing d_obtain_alias to return the unhashed dentry that is referenced by the filp, instead of making it create a new dentry. Leave __d_find_alias() alone to avoid changing behavior of other callers. Also nfsd doesn't need all the checks of __d_find_alias(); any dentry, hashed or unhashed, disconnected or not, should work. Signed-off-by: J. Bruce Fields <bfields@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2011-01-19 04:45:09 +08:00
static struct dentry * __d_find_any_alias(struct inode *inode)
{
struct dentry *alias;
if (hlist_empty(&inode->i_dentry))
fs/dcache: allow d_obtain_alias() to return unhashed dentries Without this patch, inodes are not promptly freed on last close of an unlinked file by an nfs client: client$ mount -tnfs4 server:/export/ /mnt/ client$ tail -f /mnt/FOO ... server$ df -i /export server$ rm /export/FOO (^C the tail -f) server$ df -i /export server$ echo 2 >/proc/sys/vm/drop_caches server$ df -i /export the df's will show that the inode is not freed on the filesystem until the last step, when it could have been freed after killing the client's tail -f. On-disk data won't be deallocated either, leading to possible spurious ENOSPC. This occurs because when the client does the close, it arrives in a compound with a putfh and a close, processed like: - putfh: look up the filehandle.  The only alias found for the inode will be DCACHE_UNHASHED alias referenced by the filp this, so it creates a new DCACHE_DISCONECTED dentry and returns that instead. - close: closes the existing filp, which is destroyed immediately by dput() since it's DCACHE_UNHASHED. - end of the compound: release the reference to the current filehandle, and dput() the new DCACHE_DISCONECTED dentry, which gets put on the unused list instead of being destroyed immediately. Nick Piggin suggested fixing this by allowing d_obtain_alias to return the unhashed dentry that is referenced by the filp, instead of making it create a new dentry. Leave __d_find_alias() alone to avoid changing behavior of other callers. Also nfsd doesn't need all the checks of __d_find_alias(); any dentry, hashed or unhashed, disconnected or not, should work. Signed-off-by: J. Bruce Fields <bfields@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2011-01-19 04:45:09 +08:00
return NULL;
alias = hlist_entry(inode->i_dentry.first, struct dentry, d_alias);
fs/dcache: allow d_obtain_alias() to return unhashed dentries Without this patch, inodes are not promptly freed on last close of an unlinked file by an nfs client: client$ mount -tnfs4 server:/export/ /mnt/ client$ tail -f /mnt/FOO ... server$ df -i /export server$ rm /export/FOO (^C the tail -f) server$ df -i /export server$ echo 2 >/proc/sys/vm/drop_caches server$ df -i /export the df's will show that the inode is not freed on the filesystem until the last step, when it could have been freed after killing the client's tail -f. On-disk data won't be deallocated either, leading to possible spurious ENOSPC. This occurs because when the client does the close, it arrives in a compound with a putfh and a close, processed like: - putfh: look up the filehandle.  The only alias found for the inode will be DCACHE_UNHASHED alias referenced by the filp this, so it creates a new DCACHE_DISCONECTED dentry and returns that instead. - close: closes the existing filp, which is destroyed immediately by dput() since it's DCACHE_UNHASHED. - end of the compound: release the reference to the current filehandle, and dput() the new DCACHE_DISCONECTED dentry, which gets put on the unused list instead of being destroyed immediately. Nick Piggin suggested fixing this by allowing d_obtain_alias to return the unhashed dentry that is referenced by the filp, instead of making it create a new dentry. Leave __d_find_alias() alone to avoid changing behavior of other callers. Also nfsd doesn't need all the checks of __d_find_alias(); any dentry, hashed or unhashed, disconnected or not, should work. Signed-off-by: J. Bruce Fields <bfields@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2011-01-19 04:45:09 +08:00
__dget(alias);
return alias;
}
/**
* d_find_any_alias - find any alias for a given inode
* @inode: inode to find an alias for
*
* If any aliases exist for the given inode, take and return a
* reference for one of them. If no aliases exist, return %NULL.
*/
struct dentry *d_find_any_alias(struct inode *inode)
fs/dcache: allow d_obtain_alias() to return unhashed dentries Without this patch, inodes are not promptly freed on last close of an unlinked file by an nfs client: client$ mount -tnfs4 server:/export/ /mnt/ client$ tail -f /mnt/FOO ... server$ df -i /export server$ rm /export/FOO (^C the tail -f) server$ df -i /export server$ echo 2 >/proc/sys/vm/drop_caches server$ df -i /export the df's will show that the inode is not freed on the filesystem until the last step, when it could have been freed after killing the client's tail -f. On-disk data won't be deallocated either, leading to possible spurious ENOSPC. This occurs because when the client does the close, it arrives in a compound with a putfh and a close, processed like: - putfh: look up the filehandle.  The only alias found for the inode will be DCACHE_UNHASHED alias referenced by the filp this, so it creates a new DCACHE_DISCONECTED dentry and returns that instead. - close: closes the existing filp, which is destroyed immediately by dput() since it's DCACHE_UNHASHED. - end of the compound: release the reference to the current filehandle, and dput() the new DCACHE_DISCONECTED dentry, which gets put on the unused list instead of being destroyed immediately. Nick Piggin suggested fixing this by allowing d_obtain_alias to return the unhashed dentry that is referenced by the filp, instead of making it create a new dentry. Leave __d_find_alias() alone to avoid changing behavior of other callers. Also nfsd doesn't need all the checks of __d_find_alias(); any dentry, hashed or unhashed, disconnected or not, should work. Signed-off-by: J. Bruce Fields <bfields@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2011-01-19 04:45:09 +08:00
{
struct dentry *de;
spin_lock(&inode->i_lock);
de = __d_find_any_alias(inode);
spin_unlock(&inode->i_lock);
return de;
}
EXPORT_SYMBOL(d_find_any_alias);
fs/dcache: allow d_obtain_alias() to return unhashed dentries Without this patch, inodes are not promptly freed on last close of an unlinked file by an nfs client: client$ mount -tnfs4 server:/export/ /mnt/ client$ tail -f /mnt/FOO ... server$ df -i /export server$ rm /export/FOO (^C the tail -f) server$ df -i /export server$ echo 2 >/proc/sys/vm/drop_caches server$ df -i /export the df's will show that the inode is not freed on the filesystem until the last step, when it could have been freed after killing the client's tail -f. On-disk data won't be deallocated either, leading to possible spurious ENOSPC. This occurs because when the client does the close, it arrives in a compound with a putfh and a close, processed like: - putfh: look up the filehandle.  The only alias found for the inode will be DCACHE_UNHASHED alias referenced by the filp this, so it creates a new DCACHE_DISCONECTED dentry and returns that instead. - close: closes the existing filp, which is destroyed immediately by dput() since it's DCACHE_UNHASHED. - end of the compound: release the reference to the current filehandle, and dput() the new DCACHE_DISCONECTED dentry, which gets put on the unused list instead of being destroyed immediately. Nick Piggin suggested fixing this by allowing d_obtain_alias to return the unhashed dentry that is referenced by the filp, instead of making it create a new dentry. Leave __d_find_alias() alone to avoid changing behavior of other callers. Also nfsd doesn't need all the checks of __d_find_alias(); any dentry, hashed or unhashed, disconnected or not, should work. Signed-off-by: J. Bruce Fields <bfields@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2011-01-19 04:45:09 +08:00
/**
* d_obtain_alias - find or allocate a dentry for a given inode
* @inode: inode to allocate the dentry for
*
* Obtain a dentry for an inode resulting from NFS filehandle conversion or
* similar open by handle operations. The returned dentry may be anonymous,
* or may have a full name (if the inode was already in the cache).
*
* When called on a directory inode, we must ensure that the inode only ever
* has one dentry. If a dentry is found, that is returned instead of
* allocating a new one.
*
* On successful return, the reference to the inode has been transferred
* to the dentry. In case of an error the reference on the inode is released.
* To make it easier to use in export operations a %NULL or IS_ERR inode may
* be passed in and will be the error will be propagate to the return value,
* with a %NULL @inode replaced by ERR_PTR(-ESTALE).
*/
struct dentry *d_obtain_alias(struct inode *inode)
{
static const struct qstr anonstring = QSTR_INIT("/", 1);
struct dentry *tmp;
struct dentry *res;
unsigned add_flags;
if (!inode)
return ERR_PTR(-ESTALE);
if (IS_ERR(inode))
return ERR_CAST(inode);
fs/dcache: allow d_obtain_alias() to return unhashed dentries Without this patch, inodes are not promptly freed on last close of an unlinked file by an nfs client: client$ mount -tnfs4 server:/export/ /mnt/ client$ tail -f /mnt/FOO ... server$ df -i /export server$ rm /export/FOO (^C the tail -f) server$ df -i /export server$ echo 2 >/proc/sys/vm/drop_caches server$ df -i /export the df's will show that the inode is not freed on the filesystem until the last step, when it could have been freed after killing the client's tail -f. On-disk data won't be deallocated either, leading to possible spurious ENOSPC. This occurs because when the client does the close, it arrives in a compound with a putfh and a close, processed like: - putfh: look up the filehandle.  The only alias found for the inode will be DCACHE_UNHASHED alias referenced by the filp this, so it creates a new DCACHE_DISCONECTED dentry and returns that instead. - close: closes the existing filp, which is destroyed immediately by dput() since it's DCACHE_UNHASHED. - end of the compound: release the reference to the current filehandle, and dput() the new DCACHE_DISCONECTED dentry, which gets put on the unused list instead of being destroyed immediately. Nick Piggin suggested fixing this by allowing d_obtain_alias to return the unhashed dentry that is referenced by the filp, instead of making it create a new dentry. Leave __d_find_alias() alone to avoid changing behavior of other callers. Also nfsd doesn't need all the checks of __d_find_alias(); any dentry, hashed or unhashed, disconnected or not, should work. Signed-off-by: J. Bruce Fields <bfields@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2011-01-19 04:45:09 +08:00
res = d_find_any_alias(inode);
if (res)
goto out_iput;
tmp = __d_alloc(inode->i_sb, &anonstring);
if (!tmp) {
res = ERR_PTR(-ENOMEM);
goto out_iput;
}
spin_lock(&inode->i_lock);
fs/dcache: allow d_obtain_alias() to return unhashed dentries Without this patch, inodes are not promptly freed on last close of an unlinked file by an nfs client: client$ mount -tnfs4 server:/export/ /mnt/ client$ tail -f /mnt/FOO ... server$ df -i /export server$ rm /export/FOO (^C the tail -f) server$ df -i /export server$ echo 2 >/proc/sys/vm/drop_caches server$ df -i /export the df's will show that the inode is not freed on the filesystem until the last step, when it could have been freed after killing the client's tail -f. On-disk data won't be deallocated either, leading to possible spurious ENOSPC. This occurs because when the client does the close, it arrives in a compound with a putfh and a close, processed like: - putfh: look up the filehandle.  The only alias found for the inode will be DCACHE_UNHASHED alias referenced by the filp this, so it creates a new DCACHE_DISCONECTED dentry and returns that instead. - close: closes the existing filp, which is destroyed immediately by dput() since it's DCACHE_UNHASHED. - end of the compound: release the reference to the current filehandle, and dput() the new DCACHE_DISCONECTED dentry, which gets put on the unused list instead of being destroyed immediately. Nick Piggin suggested fixing this by allowing d_obtain_alias to return the unhashed dentry that is referenced by the filp, instead of making it create a new dentry. Leave __d_find_alias() alone to avoid changing behavior of other callers. Also nfsd doesn't need all the checks of __d_find_alias(); any dentry, hashed or unhashed, disconnected or not, should work. Signed-off-by: J. Bruce Fields <bfields@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2011-01-19 04:45:09 +08:00
res = __d_find_any_alias(inode);
if (res) {
spin_unlock(&inode->i_lock);
dput(tmp);
goto out_iput;
}
/* attach a disconnected dentry */
add_flags = d_flags_for_inode(inode) | DCACHE_DISCONNECTED;
spin_lock(&tmp->d_lock);
tmp->d_inode = inode;
tmp->d_flags |= add_flags;
hlist_add_head(&tmp->d_alias, &inode->i_dentry);
hlist_bl_lock(&tmp->d_sb->s_anon);
hlist_bl_add_head(&tmp->d_hash, &tmp->d_sb->s_anon);
hlist_bl_unlock(&tmp->d_sb->s_anon);
spin_unlock(&tmp->d_lock);
spin_unlock(&inode->i_lock);
security_d_instantiate(tmp, inode);
return tmp;
out_iput:
if (res && !IS_ERR(res))
security_d_instantiate(res, inode);
iput(inode);
return res;
}
EXPORT_SYMBOL(d_obtain_alias);
/**
* d_splice_alias - splice a disconnected dentry into the tree if one exists
* @inode: the inode which may have a disconnected dentry
* @dentry: a negative dentry which we want to point to the inode.
*
* If inode is a directory and has a 'disconnected' dentry (i.e. IS_ROOT and
* DCACHE_DISCONNECTED), then d_move that in place of the given dentry
* and return it, else simply d_add the inode to the dentry and return NULL.
*
* This is needed in the lookup routine of any filesystem that is exportable
* (via knfsd) so that we can build dcache paths to directories effectively.
*
* If a dentry was found and moved, then it is returned. Otherwise NULL
* is returned. This matches the expected return value of ->lookup.
*
* Cluster filesystems may call this function with a negative, hashed dentry.
* In that case, we know that the inode will be a regular file, and also this
* will only occur during atomic_open. So we need to check for the dentry
* being already hashed only in the final case.
*/
struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
{
struct dentry *new = NULL;
if (IS_ERR(inode))
return ERR_CAST(inode);
[PATCH] knfsd: close a race-opportunity in d_splice_alias There is a possible race in d_splice_alias. Though __d_find_alias(inode, 1) will only return a dentry with DCACHE_DISCONNECTED set, it is possible for it to get cleared before the BUG_ON, and it is is not possible to lock against that. There are a couple of problems here. Firstly, the code doesn't match the comment. The comment describes a 'disconnected' dentry as being IS_ROOT as well as DCACHE_DISCONNECTED, however there is not testing of IS_ROOT anythere. A dentry is marked DCACHE_DISCONNECTED when allocated with d_alloc_anon, and remains DCACHE_DISCONNECTED while a path is built up towards the root. So a dentry can have a valid name and a valid parent and even grandparent, but will still be DCACHE_DISCONNECTED until a path to the root is created. Once the path to the root is complete, everything in the path gets DCACHE_DISCONNECTED cleared. So the fact that DCACHE_DISCONNECTED isn't enough to say that a dentry is free to be spliced in with a given name. This can only be allowed if the dentry does not yet have a name, so the IS_ROOT test is needed too. However even adding that test to __d_find_alias isn't enough. As d_splice_alias drops dcache_lock before calling d_move to perform the splice, it could race with another thread calling d_splice_alias to splice the inode in with a different name in a different part of the tree (in the case where a file has hard links). So that splicing code is only really safe for directories (as we know that directories only have one link). For directories, the caller of d_splice_alias will be holding i_mutex on the (unique) parent so there is no room for a race. A consequence of this is that a non-directory will never benefit from being spliced into a pre-exisiting dentry, but that isn't a problem. It is perfectly OK for a non-directory to have multiple dentries, some anonymous, some not. And the comment for d_splice_alias says that it only happens for directories anyway. Signed-off-by: Neil Brown <neilb@suse.de> Cc: Christoph Hellwig <hch@lst.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Dipankar Sarma <dipankar@in.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-04 17:16:16 +08:00
if (inode && S_ISDIR(inode->i_mode)) {
spin_lock(&inode->i_lock);
Revert "vfs: stop d_splice_alias creating directory aliases" This reverts commit 7732a557b1342c6e6966efb5f07effcf99f56167 (and commit 3f50fff4dace23d3cfeb195d5cd4ee813cee68b7, which was a follow-up cleanup). We're chasing an elusive bug that Dave Jones can apparently reproduce using his system call fuzzer tool, and that looks like some kind of locking ordering problem on the directory i_mutex chain. Our i_mutex locking is rather complex, and depends on the topological ordering of the directories, which is why we have been very wary of splicing directory entries around. Of course, we really don't want to ever see aliased unconnected directories anyway, so none of this should ever happen, but this revert aims to basically get us back to a known older state. Bruce points to some of the previous discussion at http://marc.info/?i=<20110310105821.GE22723@ZenIV.linux.org.uk> and in particular a long post from Neil: http://marc.info/?i=<20110311150749.2fa2be66@notabene.brown> It should be noted that it's possible that Dave's problems come from other changes altohgether, including possibly just the fact that Dave constantly is teachning his fuzzer new tricks. So what appears to be a new bug could in fact be an old one that just gets newly triggered, but reverting these patches as "still under heavy discussion" is the right thing regardless. Requested-by: Al Viro <viro@zeniv.linux.org.uk> Acked-by: J. Bruce Fields <bfields@fieldses.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-06-09 01:34:03 +08:00
new = __d_find_alias(inode, 1);
if (new) {
Revert "vfs: stop d_splice_alias creating directory aliases" This reverts commit 7732a557b1342c6e6966efb5f07effcf99f56167 (and commit 3f50fff4dace23d3cfeb195d5cd4ee813cee68b7, which was a follow-up cleanup). We're chasing an elusive bug that Dave Jones can apparently reproduce using his system call fuzzer tool, and that looks like some kind of locking ordering problem on the directory i_mutex chain. Our i_mutex locking is rather complex, and depends on the topological ordering of the directories, which is why we have been very wary of splicing directory entries around. Of course, we really don't want to ever see aliased unconnected directories anyway, so none of this should ever happen, but this revert aims to basically get us back to a known older state. Bruce points to some of the previous discussion at http://marc.info/?i=<20110310105821.GE22723@ZenIV.linux.org.uk> and in particular a long post from Neil: http://marc.info/?i=<20110311150749.2fa2be66@notabene.brown> It should be noted that it's possible that Dave's problems come from other changes altohgether, including possibly just the fact that Dave constantly is teachning his fuzzer new tricks. So what appears to be a new bug could in fact be an old one that just gets newly triggered, but reverting these patches as "still under heavy discussion" is the right thing regardless. Requested-by: Al Viro <viro@zeniv.linux.org.uk> Acked-by: J. Bruce Fields <bfields@fieldses.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-06-09 01:34:03 +08:00
BUG_ON(!(new->d_flags & DCACHE_DISCONNECTED));
spin_unlock(&inode->i_lock);
security_d_instantiate(new, inode);
d_move(new, dentry);
iput(inode);
} else {
/* already taking inode->i_lock, so d_add() by hand */
__d_instantiate(dentry, inode);
spin_unlock(&inode->i_lock);
security_d_instantiate(dentry, inode);
d_rehash(dentry);
}
} else {
d_instantiate(dentry, inode);
if (d_unhashed(dentry))
d_rehash(dentry);
}
return new;
}
EXPORT_SYMBOL(d_splice_alias);
/**
* d_add_ci - lookup or allocate new dentry with case-exact name
* @inode: the inode case-insensitive lookup has found
* @dentry: the negative dentry that was passed to the parent's lookup func
* @name: the case-exact name to be associated with the returned dentry
*
* This is to avoid filling the dcache with case-insensitive names to the
* same inode, only the actual correct case is stored in the dcache for
* case-insensitive filesystems.
*
* For a case-insensitive lookup match and if the the case-exact dentry
* already exists in in the dcache, use it and return it.
*
* If no entry exists with the exact case name, allocate new dentry with
* the exact case, and return the spliced entry.
*/
struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode,
struct qstr *name)
{
struct dentry *found;
struct dentry *new;
/*
* First check if a dentry matching the name already exists,
* if not go ahead and create it now.
*/
found = d_hash_and_lookup(dentry->d_parent, name);
if (unlikely(IS_ERR(found)))
goto err_out;
if (!found) {
new = d_alloc(dentry->d_parent, name);
if (!new) {
found = ERR_PTR(-ENOMEM);
goto err_out;
}
found = d_splice_alias(inode, new);
if (found) {
dput(new);
return found;
}
return new;
}
/*
* If a matching dentry exists, and it's not negative use it.
*
* Decrement the reference count to balance the iget() done
* earlier on.
*/
if (found->d_inode) {
if (unlikely(found->d_inode != inode)) {
/* This can't happen because bad inodes are unhashed. */
BUG_ON(!is_bad_inode(inode));
BUG_ON(!is_bad_inode(found->d_inode));
}
iput(inode);
return found;
}
/*
* Negative dentry: instantiate it unless the inode is a directory and
* already has a dentry.
*/
new = d_splice_alias(inode, found);
if (new) {
dput(found);
found = new;
}
return found;
err_out:
iput(inode);
return found;
}
EXPORT_SYMBOL(d_add_ci);
vfs: clean up __d_lookup_rcu() and dentry_cmp() interfaces The calling conventions for __d_lookup_rcu() and dentry_cmp() are annoying in different ways, and there is actually one single underlying reason for both of the annoyances. The fundamental reason is that we do the returned dentry sequence number check inside __d_lookup_rcu() instead of doing it in the caller. This results in two annoyances: - __d_lookup_rcu() now not only needs to return the dentry and the sequence number that goes along with the lookup, it also needs to return the inode pointer that was validated by that sequence number check. - and because we did the sequence number check early (to validate the name pointer and length) we also couldn't just pass the dentry itself to dentry_cmp(), we had to pass the counted string that contained the name. So that sequence number decision caused two separate ugly calling conventions. Both of these problems would be solved if we just did the sequence number check in the caller instead. There's only one caller, and that caller already has to do the sequence number check for the parent anyway, so just do that. That allows us to stop returning the dentry->d_inode in that in-out argument (pointer-to-pointer-to-inode), so we can make the inode argument just a regular input inode pointer. The caller can just load the inode from dentry->d_inode, and then do the sequence number check after that to make sure that it's synchronized with the name we looked up. And it allows us to just pass in the dentry to dentry_cmp(), which is what all the callers really wanted. Sure, dentry_cmp() has to be a bit careful about the dentry (which is not stable during RCU lookup), but that's actually very simple. And now that dentry_cmp() can clearly see that the first string argument is a dentry, we can use the direct word access for that, instead of the careful unaligned zero-padding. The dentry name is always properly aligned, since it is a single path component that is either embedded into the dentry itself, or was allocated with kmalloc() (see __d_alloc). Finally, this also uninlines the nasty slow-case for dentry comparisons: that one *does* need to do a sequence number check, since it will call in to the low-level filesystems, and we want to give those a stable inode pointer and path component length/start arguments. Doing an extra sequence check for that slow case is not a problem, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-05-05 05:59:14 +08:00
/*
* Do the slow-case of the dentry name compare.
*
* Unlike the dentry_cmp() function, we need to atomically
* load the name and length information, so that the
vfs: clean up __d_lookup_rcu() and dentry_cmp() interfaces The calling conventions for __d_lookup_rcu() and dentry_cmp() are annoying in different ways, and there is actually one single underlying reason for both of the annoyances. The fundamental reason is that we do the returned dentry sequence number check inside __d_lookup_rcu() instead of doing it in the caller. This results in two annoyances: - __d_lookup_rcu() now not only needs to return the dentry and the sequence number that goes along with the lookup, it also needs to return the inode pointer that was validated by that sequence number check. - and because we did the sequence number check early (to validate the name pointer and length) we also couldn't just pass the dentry itself to dentry_cmp(), we had to pass the counted string that contained the name. So that sequence number decision caused two separate ugly calling conventions. Both of these problems would be solved if we just did the sequence number check in the caller instead. There's only one caller, and that caller already has to do the sequence number check for the parent anyway, so just do that. That allows us to stop returning the dentry->d_inode in that in-out argument (pointer-to-pointer-to-inode), so we can make the inode argument just a regular input inode pointer. The caller can just load the inode from dentry->d_inode, and then do the sequence number check after that to make sure that it's synchronized with the name we looked up. And it allows us to just pass in the dentry to dentry_cmp(), which is what all the callers really wanted. Sure, dentry_cmp() has to be a bit careful about the dentry (which is not stable during RCU lookup), but that's actually very simple. And now that dentry_cmp() can clearly see that the first string argument is a dentry, we can use the direct word access for that, instead of the careful unaligned zero-padding. The dentry name is always properly aligned, since it is a single path component that is either embedded into the dentry itself, or was allocated with kmalloc() (see __d_alloc). Finally, this also uninlines the nasty slow-case for dentry comparisons: that one *does* need to do a sequence number check, since it will call in to the low-level filesystems, and we want to give those a stable inode pointer and path component length/start arguments. Doing an extra sequence check for that slow case is not a problem, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-05-05 05:59:14 +08:00
* filesystem can rely on them, and can use the 'name' and
* 'len' information without worrying about walking off the
* end of memory etc.
*
* Thus the read_seqcount_retry() and the "duplicate" info
* in arguments (the low-level filesystem should not look
* at the dentry inode or name contents directly, since
* rename can change them while we're in RCU mode).
*/
enum slow_d_compare {
D_COMP_OK,
D_COMP_NOMATCH,
D_COMP_SEQRETRY,
};
static noinline enum slow_d_compare slow_dentry_cmp(
const struct dentry *parent,
struct dentry *dentry,
unsigned int seq,
const struct qstr *name)
{
int tlen = dentry->d_name.len;
const char *tname = dentry->d_name.name;
if (read_seqcount_retry(&dentry->d_seq, seq)) {
cpu_relax();
return D_COMP_SEQRETRY;
}
if (parent->d_op->d_compare(parent, dentry, tlen, tname, name))
vfs: clean up __d_lookup_rcu() and dentry_cmp() interfaces The calling conventions for __d_lookup_rcu() and dentry_cmp() are annoying in different ways, and there is actually one single underlying reason for both of the annoyances. The fundamental reason is that we do the returned dentry sequence number check inside __d_lookup_rcu() instead of doing it in the caller. This results in two annoyances: - __d_lookup_rcu() now not only needs to return the dentry and the sequence number that goes along with the lookup, it also needs to return the inode pointer that was validated by that sequence number check. - and because we did the sequence number check early (to validate the name pointer and length) we also couldn't just pass the dentry itself to dentry_cmp(), we had to pass the counted string that contained the name. So that sequence number decision caused two separate ugly calling conventions. Both of these problems would be solved if we just did the sequence number check in the caller instead. There's only one caller, and that caller already has to do the sequence number check for the parent anyway, so just do that. That allows us to stop returning the dentry->d_inode in that in-out argument (pointer-to-pointer-to-inode), so we can make the inode argument just a regular input inode pointer. The caller can just load the inode from dentry->d_inode, and then do the sequence number check after that to make sure that it's synchronized with the name we looked up. And it allows us to just pass in the dentry to dentry_cmp(), which is what all the callers really wanted. Sure, dentry_cmp() has to be a bit careful about the dentry (which is not stable during RCU lookup), but that's actually very simple. And now that dentry_cmp() can clearly see that the first string argument is a dentry, we can use the direct word access for that, instead of the careful unaligned zero-padding. The dentry name is always properly aligned, since it is a single path component that is either embedded into the dentry itself, or was allocated with kmalloc() (see __d_alloc). Finally, this also uninlines the nasty slow-case for dentry comparisons: that one *does* need to do a sequence number check, since it will call in to the low-level filesystems, and we want to give those a stable inode pointer and path component length/start arguments. Doing an extra sequence check for that slow case is not a problem, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-05-05 05:59:14 +08:00
return D_COMP_NOMATCH;
return D_COMP_OK;
}
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
/**
* __d_lookup_rcu - search for a dentry (racy, store-free)
* @parent: parent dentry
* @name: qstr of name we wish to find
* @seqp: returns d_seq value at the point where the dentry was found
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
* Returns: dentry, or NULL
*
* __d_lookup_rcu is the dcache lookup function for rcu-walk name
* resolution (store-free path walking) design described in
* Documentation/filesystems/path-lookup.txt.
*
* This is not to be used outside core vfs.
*
* __d_lookup_rcu must only be used in rcu-walk mode, ie. with vfsmount lock
* held, and rcu_read_lock held. The returned dentry must not be stored into
* without taking d_lock and checking d_seq sequence count against @seq
* returned here.
*
* A refcount may be taken on the found dentry with the d_rcu_to_refcount
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
* function.
*
* Alternatively, __d_lookup_rcu may be called again to look up the child of
* the returned dentry, so long as its parent's seqlock is checked after the
* child is looked up. Thus, an interlocking stepping of sequence lock checks
* is formed, giving integrity down the path walk.
vfs: clean up __d_lookup_rcu() and dentry_cmp() interfaces The calling conventions for __d_lookup_rcu() and dentry_cmp() are annoying in different ways, and there is actually one single underlying reason for both of the annoyances. The fundamental reason is that we do the returned dentry sequence number check inside __d_lookup_rcu() instead of doing it in the caller. This results in two annoyances: - __d_lookup_rcu() now not only needs to return the dentry and the sequence number that goes along with the lookup, it also needs to return the inode pointer that was validated by that sequence number check. - and because we did the sequence number check early (to validate the name pointer and length) we also couldn't just pass the dentry itself to dentry_cmp(), we had to pass the counted string that contained the name. So that sequence number decision caused two separate ugly calling conventions. Both of these problems would be solved if we just did the sequence number check in the caller instead. There's only one caller, and that caller already has to do the sequence number check for the parent anyway, so just do that. That allows us to stop returning the dentry->d_inode in that in-out argument (pointer-to-pointer-to-inode), so we can make the inode argument just a regular input inode pointer. The caller can just load the inode from dentry->d_inode, and then do the sequence number check after that to make sure that it's synchronized with the name we looked up. And it allows us to just pass in the dentry to dentry_cmp(), which is what all the callers really wanted. Sure, dentry_cmp() has to be a bit careful about the dentry (which is not stable during RCU lookup), but that's actually very simple. And now that dentry_cmp() can clearly see that the first string argument is a dentry, we can use the direct word access for that, instead of the careful unaligned zero-padding. The dentry name is always properly aligned, since it is a single path component that is either embedded into the dentry itself, or was allocated with kmalloc() (see __d_alloc). Finally, this also uninlines the nasty slow-case for dentry comparisons: that one *does* need to do a sequence number check, since it will call in to the low-level filesystems, and we want to give those a stable inode pointer and path component length/start arguments. Doing an extra sequence check for that slow case is not a problem, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-05-05 05:59:14 +08:00
*
* NOTE! The caller *has* to check the resulting dentry against the sequence
* number we've returned before using any of the resulting dentry state!
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
*/
struct dentry *__d_lookup_rcu(const struct dentry *parent,
const struct qstr *name,
unsigned *seqp)
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
{
u64 hashlen = name->hash_len;
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
const unsigned char *str = name->name;
struct hlist_bl_head *b = d_hash(parent, hashlen_hash(hashlen));
struct hlist_bl_node *node;
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
struct dentry *dentry;
/*
* Note: There is significant duplication with __d_lookup_rcu which is
* required to prevent single threaded performance regressions
* especially on architectures where smp_rmb (in seqcounts) are costly.
* Keep the two functions in sync.
*/
/*
* The hash list is protected using RCU.
*
* Carefully use d_seq when comparing a candidate dentry, to avoid
* races with d_move().
*
* It is possible that concurrent renames can mess up our list
* walk here and result in missing our dentry, resulting in the
* false-negative result. d_lookup() protects against concurrent
* renames using rename_lock seqlock.
*
* See Documentation/filesystems/path-lookup.txt for more details.
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
*/
hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) {
unsigned seq;
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
seqretry:
vfs: clean up __d_lookup_rcu() and dentry_cmp() interfaces The calling conventions for __d_lookup_rcu() and dentry_cmp() are annoying in different ways, and there is actually one single underlying reason for both of the annoyances. The fundamental reason is that we do the returned dentry sequence number check inside __d_lookup_rcu() instead of doing it in the caller. This results in two annoyances: - __d_lookup_rcu() now not only needs to return the dentry and the sequence number that goes along with the lookup, it also needs to return the inode pointer that was validated by that sequence number check. - and because we did the sequence number check early (to validate the name pointer and length) we also couldn't just pass the dentry itself to dentry_cmp(), we had to pass the counted string that contained the name. So that sequence number decision caused two separate ugly calling conventions. Both of these problems would be solved if we just did the sequence number check in the caller instead. There's only one caller, and that caller already has to do the sequence number check for the parent anyway, so just do that. That allows us to stop returning the dentry->d_inode in that in-out argument (pointer-to-pointer-to-inode), so we can make the inode argument just a regular input inode pointer. The caller can just load the inode from dentry->d_inode, and then do the sequence number check after that to make sure that it's synchronized with the name we looked up. And it allows us to just pass in the dentry to dentry_cmp(), which is what all the callers really wanted. Sure, dentry_cmp() has to be a bit careful about the dentry (which is not stable during RCU lookup), but that's actually very simple. And now that dentry_cmp() can clearly see that the first string argument is a dentry, we can use the direct word access for that, instead of the careful unaligned zero-padding. The dentry name is always properly aligned, since it is a single path component that is either embedded into the dentry itself, or was allocated with kmalloc() (see __d_alloc). Finally, this also uninlines the nasty slow-case for dentry comparisons: that one *does* need to do a sequence number check, since it will call in to the low-level filesystems, and we want to give those a stable inode pointer and path component length/start arguments. Doing an extra sequence check for that slow case is not a problem, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-05-05 05:59:14 +08:00
/*
* The dentry sequence count protects us from concurrent
* renames, and thus protects parent and name fields.
vfs: clean up __d_lookup_rcu() and dentry_cmp() interfaces The calling conventions for __d_lookup_rcu() and dentry_cmp() are annoying in different ways, and there is actually one single underlying reason for both of the annoyances. The fundamental reason is that we do the returned dentry sequence number check inside __d_lookup_rcu() instead of doing it in the caller. This results in two annoyances: - __d_lookup_rcu() now not only needs to return the dentry and the sequence number that goes along with the lookup, it also needs to return the inode pointer that was validated by that sequence number check. - and because we did the sequence number check early (to validate the name pointer and length) we also couldn't just pass the dentry itself to dentry_cmp(), we had to pass the counted string that contained the name. So that sequence number decision caused two separate ugly calling conventions. Both of these problems would be solved if we just did the sequence number check in the caller instead. There's only one caller, and that caller already has to do the sequence number check for the parent anyway, so just do that. That allows us to stop returning the dentry->d_inode in that in-out argument (pointer-to-pointer-to-inode), so we can make the inode argument just a regular input inode pointer. The caller can just load the inode from dentry->d_inode, and then do the sequence number check after that to make sure that it's synchronized with the name we looked up. And it allows us to just pass in the dentry to dentry_cmp(), which is what all the callers really wanted. Sure, dentry_cmp() has to be a bit careful about the dentry (which is not stable during RCU lookup), but that's actually very simple. And now that dentry_cmp() can clearly see that the first string argument is a dentry, we can use the direct word access for that, instead of the careful unaligned zero-padding. The dentry name is always properly aligned, since it is a single path component that is either embedded into the dentry itself, or was allocated with kmalloc() (see __d_alloc). Finally, this also uninlines the nasty slow-case for dentry comparisons: that one *does* need to do a sequence number check, since it will call in to the low-level filesystems, and we want to give those a stable inode pointer and path component length/start arguments. Doing an extra sequence check for that slow case is not a problem, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-05-05 05:59:14 +08:00
*
* The caller must perform a seqcount check in order
* to do anything useful with the returned dentry.
vfs: clean up __d_lookup_rcu() and dentry_cmp() interfaces The calling conventions for __d_lookup_rcu() and dentry_cmp() are annoying in different ways, and there is actually one single underlying reason for both of the annoyances. The fundamental reason is that we do the returned dentry sequence number check inside __d_lookup_rcu() instead of doing it in the caller. This results in two annoyances: - __d_lookup_rcu() now not only needs to return the dentry and the sequence number that goes along with the lookup, it also needs to return the inode pointer that was validated by that sequence number check. - and because we did the sequence number check early (to validate the name pointer and length) we also couldn't just pass the dentry itself to dentry_cmp(), we had to pass the counted string that contained the name. So that sequence number decision caused two separate ugly calling conventions. Both of these problems would be solved if we just did the sequence number check in the caller instead. There's only one caller, and that caller already has to do the sequence number check for the parent anyway, so just do that. That allows us to stop returning the dentry->d_inode in that in-out argument (pointer-to-pointer-to-inode), so we can make the inode argument just a regular input inode pointer. The caller can just load the inode from dentry->d_inode, and then do the sequence number check after that to make sure that it's synchronized with the name we looked up. And it allows us to just pass in the dentry to dentry_cmp(), which is what all the callers really wanted. Sure, dentry_cmp() has to be a bit careful about the dentry (which is not stable during RCU lookup), but that's actually very simple. And now that dentry_cmp() can clearly see that the first string argument is a dentry, we can use the direct word access for that, instead of the careful unaligned zero-padding. The dentry name is always properly aligned, since it is a single path component that is either embedded into the dentry itself, or was allocated with kmalloc() (see __d_alloc). Finally, this also uninlines the nasty slow-case for dentry comparisons: that one *does* need to do a sequence number check, since it will call in to the low-level filesystems, and we want to give those a stable inode pointer and path component length/start arguments. Doing an extra sequence check for that slow case is not a problem, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-05-05 05:59:14 +08:00
*
* NOTE! We do a "raw" seqcount_begin here. That means that
* we don't wait for the sequence count to stabilize if it
* is in the middle of a sequence change. If we do the slow
* dentry compare, we will do seqretries until it is stable,
* and if we end up with a successful lookup, we actually
* want to exit RCU lookup anyway.
*/
seq = raw_seqcount_begin(&dentry->d_seq);
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
if (dentry->d_parent != parent)
continue;
if (d_unhashed(dentry))
continue;
vfs: clean up __d_lookup_rcu() and dentry_cmp() interfaces The calling conventions for __d_lookup_rcu() and dentry_cmp() are annoying in different ways, and there is actually one single underlying reason for both of the annoyances. The fundamental reason is that we do the returned dentry sequence number check inside __d_lookup_rcu() instead of doing it in the caller. This results in two annoyances: - __d_lookup_rcu() now not only needs to return the dentry and the sequence number that goes along with the lookup, it also needs to return the inode pointer that was validated by that sequence number check. - and because we did the sequence number check early (to validate the name pointer and length) we also couldn't just pass the dentry itself to dentry_cmp(), we had to pass the counted string that contained the name. So that sequence number decision caused two separate ugly calling conventions. Both of these problems would be solved if we just did the sequence number check in the caller instead. There's only one caller, and that caller already has to do the sequence number check for the parent anyway, so just do that. That allows us to stop returning the dentry->d_inode in that in-out argument (pointer-to-pointer-to-inode), so we can make the inode argument just a regular input inode pointer. The caller can just load the inode from dentry->d_inode, and then do the sequence number check after that to make sure that it's synchronized with the name we looked up. And it allows us to just pass in the dentry to dentry_cmp(), which is what all the callers really wanted. Sure, dentry_cmp() has to be a bit careful about the dentry (which is not stable during RCU lookup), but that's actually very simple. And now that dentry_cmp() can clearly see that the first string argument is a dentry, we can use the direct word access for that, instead of the careful unaligned zero-padding. The dentry name is always properly aligned, since it is a single path component that is either embedded into the dentry itself, or was allocated with kmalloc() (see __d_alloc). Finally, this also uninlines the nasty slow-case for dentry comparisons: that one *does* need to do a sequence number check, since it will call in to the low-level filesystems, and we want to give those a stable inode pointer and path component length/start arguments. Doing an extra sequence check for that slow case is not a problem, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-05-05 05:59:14 +08:00
if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) {
if (dentry->d_name.hash != hashlen_hash(hashlen))
continue;
*seqp = seq;
switch (slow_dentry_cmp(parent, dentry, seq, name)) {
vfs: clean up __d_lookup_rcu() and dentry_cmp() interfaces The calling conventions for __d_lookup_rcu() and dentry_cmp() are annoying in different ways, and there is actually one single underlying reason for both of the annoyances. The fundamental reason is that we do the returned dentry sequence number check inside __d_lookup_rcu() instead of doing it in the caller. This results in two annoyances: - __d_lookup_rcu() now not only needs to return the dentry and the sequence number that goes along with the lookup, it also needs to return the inode pointer that was validated by that sequence number check. - and because we did the sequence number check early (to validate the name pointer and length) we also couldn't just pass the dentry itself to dentry_cmp(), we had to pass the counted string that contained the name. So that sequence number decision caused two separate ugly calling conventions. Both of these problems would be solved if we just did the sequence number check in the caller instead. There's only one caller, and that caller already has to do the sequence number check for the parent anyway, so just do that. That allows us to stop returning the dentry->d_inode in that in-out argument (pointer-to-pointer-to-inode), so we can make the inode argument just a regular input inode pointer. The caller can just load the inode from dentry->d_inode, and then do the sequence number check after that to make sure that it's synchronized with the name we looked up. And it allows us to just pass in the dentry to dentry_cmp(), which is what all the callers really wanted. Sure, dentry_cmp() has to be a bit careful about the dentry (which is not stable during RCU lookup), but that's actually very simple. And now that dentry_cmp() can clearly see that the first string argument is a dentry, we can use the direct word access for that, instead of the careful unaligned zero-padding. The dentry name is always properly aligned, since it is a single path component that is either embedded into the dentry itself, or was allocated with kmalloc() (see __d_alloc). Finally, this also uninlines the nasty slow-case for dentry comparisons: that one *does* need to do a sequence number check, since it will call in to the low-level filesystems, and we want to give those a stable inode pointer and path component length/start arguments. Doing an extra sequence check for that slow case is not a problem, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-05-05 05:59:14 +08:00
case D_COMP_OK:
return dentry;
case D_COMP_NOMATCH:
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
continue;
vfs: clean up __d_lookup_rcu() and dentry_cmp() interfaces The calling conventions for __d_lookup_rcu() and dentry_cmp() are annoying in different ways, and there is actually one single underlying reason for both of the annoyances. The fundamental reason is that we do the returned dentry sequence number check inside __d_lookup_rcu() instead of doing it in the caller. This results in two annoyances: - __d_lookup_rcu() now not only needs to return the dentry and the sequence number that goes along with the lookup, it also needs to return the inode pointer that was validated by that sequence number check. - and because we did the sequence number check early (to validate the name pointer and length) we also couldn't just pass the dentry itself to dentry_cmp(), we had to pass the counted string that contained the name. So that sequence number decision caused two separate ugly calling conventions. Both of these problems would be solved if we just did the sequence number check in the caller instead. There's only one caller, and that caller already has to do the sequence number check for the parent anyway, so just do that. That allows us to stop returning the dentry->d_inode in that in-out argument (pointer-to-pointer-to-inode), so we can make the inode argument just a regular input inode pointer. The caller can just load the inode from dentry->d_inode, and then do the sequence number check after that to make sure that it's synchronized with the name we looked up. And it allows us to just pass in the dentry to dentry_cmp(), which is what all the callers really wanted. Sure, dentry_cmp() has to be a bit careful about the dentry (which is not stable during RCU lookup), but that's actually very simple. And now that dentry_cmp() can clearly see that the first string argument is a dentry, we can use the direct word access for that, instead of the careful unaligned zero-padding. The dentry name is always properly aligned, since it is a single path component that is either embedded into the dentry itself, or was allocated with kmalloc() (see __d_alloc). Finally, this also uninlines the nasty slow-case for dentry comparisons: that one *does* need to do a sequence number check, since it will call in to the low-level filesystems, and we want to give those a stable inode pointer and path component length/start arguments. Doing an extra sequence check for that slow case is not a problem, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-05-05 05:59:14 +08:00
default:
goto seqretry;
}
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
}
vfs: clean up __d_lookup_rcu() and dentry_cmp() interfaces The calling conventions for __d_lookup_rcu() and dentry_cmp() are annoying in different ways, and there is actually one single underlying reason for both of the annoyances. The fundamental reason is that we do the returned dentry sequence number check inside __d_lookup_rcu() instead of doing it in the caller. This results in two annoyances: - __d_lookup_rcu() now not only needs to return the dentry and the sequence number that goes along with the lookup, it also needs to return the inode pointer that was validated by that sequence number check. - and because we did the sequence number check early (to validate the name pointer and length) we also couldn't just pass the dentry itself to dentry_cmp(), we had to pass the counted string that contained the name. So that sequence number decision caused two separate ugly calling conventions. Both of these problems would be solved if we just did the sequence number check in the caller instead. There's only one caller, and that caller already has to do the sequence number check for the parent anyway, so just do that. That allows us to stop returning the dentry->d_inode in that in-out argument (pointer-to-pointer-to-inode), so we can make the inode argument just a regular input inode pointer. The caller can just load the inode from dentry->d_inode, and then do the sequence number check after that to make sure that it's synchronized with the name we looked up. And it allows us to just pass in the dentry to dentry_cmp(), which is what all the callers really wanted. Sure, dentry_cmp() has to be a bit careful about the dentry (which is not stable during RCU lookup), but that's actually very simple. And now that dentry_cmp() can clearly see that the first string argument is a dentry, we can use the direct word access for that, instead of the careful unaligned zero-padding. The dentry name is always properly aligned, since it is a single path component that is either embedded into the dentry itself, or was allocated with kmalloc() (see __d_alloc). Finally, this also uninlines the nasty slow-case for dentry comparisons: that one *does* need to do a sequence number check, since it will call in to the low-level filesystems, and we want to give those a stable inode pointer and path component length/start arguments. Doing an extra sequence check for that slow case is not a problem, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-05-05 05:59:14 +08:00
if (dentry->d_name.hash_len != hashlen)
continue;
*seqp = seq;
if (!dentry_cmp(dentry, str, hashlen_len(hashlen)))
vfs: clean up __d_lookup_rcu() and dentry_cmp() interfaces The calling conventions for __d_lookup_rcu() and dentry_cmp() are annoying in different ways, and there is actually one single underlying reason for both of the annoyances. The fundamental reason is that we do the returned dentry sequence number check inside __d_lookup_rcu() instead of doing it in the caller. This results in two annoyances: - __d_lookup_rcu() now not only needs to return the dentry and the sequence number that goes along with the lookup, it also needs to return the inode pointer that was validated by that sequence number check. - and because we did the sequence number check early (to validate the name pointer and length) we also couldn't just pass the dentry itself to dentry_cmp(), we had to pass the counted string that contained the name. So that sequence number decision caused two separate ugly calling conventions. Both of these problems would be solved if we just did the sequence number check in the caller instead. There's only one caller, and that caller already has to do the sequence number check for the parent anyway, so just do that. That allows us to stop returning the dentry->d_inode in that in-out argument (pointer-to-pointer-to-inode), so we can make the inode argument just a regular input inode pointer. The caller can just load the inode from dentry->d_inode, and then do the sequence number check after that to make sure that it's synchronized with the name we looked up. And it allows us to just pass in the dentry to dentry_cmp(), which is what all the callers really wanted. Sure, dentry_cmp() has to be a bit careful about the dentry (which is not stable during RCU lookup), but that's actually very simple. And now that dentry_cmp() can clearly see that the first string argument is a dentry, we can use the direct word access for that, instead of the careful unaligned zero-padding. The dentry name is always properly aligned, since it is a single path component that is either embedded into the dentry itself, or was allocated with kmalloc() (see __d_alloc). Finally, this also uninlines the nasty slow-case for dentry comparisons: that one *does* need to do a sequence number check, since it will call in to the low-level filesystems, and we want to give those a stable inode pointer and path component length/start arguments. Doing an extra sequence check for that slow case is not a problem, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-05-05 05:59:14 +08:00
return dentry;
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
}
return NULL;
}
/**
* d_lookup - search for a dentry
* @parent: parent dentry
* @name: qstr of name we wish to find
* Returns: dentry, or NULL
*
* d_lookup searches the children of the parent dentry for the name in
* question. If the dentry is found its reference count is incremented and the
* dentry is returned. The caller must use dput to free the entry when it has
* finished using it. %NULL is returned if the dentry does not exist.
*/
struct dentry *d_lookup(const struct dentry *parent, const struct qstr *name)
{
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
struct dentry *dentry;
unsigned seq;
do {
seq = read_seqbegin(&rename_lock);
dentry = __d_lookup(parent, name);
if (dentry)
break;
} while (read_seqretry(&rename_lock, seq));
return dentry;
}
EXPORT_SYMBOL(d_lookup);
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
/**
* __d_lookup - search for a dentry (racy)
* @parent: parent dentry
* @name: qstr of name we wish to find
* Returns: dentry, or NULL
*
* __d_lookup is like d_lookup, however it may (rarely) return a
* false-negative result due to unrelated rename activity.
*
* __d_lookup is slightly faster by avoiding rename_lock read seqlock,
* however it must be used carefully, eg. with a following d_lookup in
* the case of failure.
*
* __d_lookup callers must be commented.
*/
struct dentry *__d_lookup(const struct dentry *parent, const struct qstr *name)
{
unsigned int len = name->len;
unsigned int hash = name->hash;
const unsigned char *str = name->name;
struct hlist_bl_head *b = d_hash(parent, hash);
struct hlist_bl_node *node;
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
struct dentry *found = NULL;
struct dentry *dentry;
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
/*
* Note: There is significant duplication with __d_lookup_rcu which is
* required to prevent single threaded performance regressions
* especially on architectures where smp_rmb (in seqcounts) are costly.
* Keep the two functions in sync.
*/
/*
* The hash list is protected using RCU.
*
* Take d_lock when comparing a candidate dentry, to avoid races
* with d_move().
*
* It is possible that concurrent renames can mess up our list
* walk here and result in missing our dentry, resulting in the
* false-negative result. d_lookup() protects against concurrent
* renames using rename_lock seqlock.
*
* See Documentation/filesystems/path-lookup.txt for more details.
*/
rcu_read_lock();
hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) {
if (dentry->d_name.hash != hash)
continue;
spin_lock(&dentry->d_lock);
if (dentry->d_parent != parent)
goto next;
Fix NULL pointer dereference in proc_sys_compare The VFS interface for the 'd_compare()' is a bit special (read: 'odd'), because it really just essentially replaces a memcmp(). The filesystem is supposed to just compare the two names with whatever case-independent or other function. And when I say 'is supposed to', I obviously mean that 'procfs does odd things, and actually looks at the dentry that we don't even pass down, rather than just the name'. Which results in problems, because we actually call d_compare before we have even verified that the dentry is still hashed at all. And that causes a problm since the inode that procfs looks at may have been free'd and the d_inode pointer is NULL. procfs just assumes that all dentries are positive, since procfs itself never generates a negative one. But memory pressure will still result in the dentry getting torn down, and as it is removed by RCU, it still remains visible on some lists - and to d_compare. If the filesystem just did a name comparison, we wouldn't care. And we could just fix procfs to know about negative dentries too. But rather than have the low-level filesystems know about internal VFS details, just move the check for a unhashed dentry up a bit, so that we will only call d_compare on dentries that are still active. The actual oops this caused didn't look like a NULL pointer dereference because procfs did a 'container_of(inode, struct proc_inode, vfs_inode)' to get at its internal proc_inode information from the inode pointer, and accessed a field below the inode. So the oops would look something like BUG: unable to handle kernel paging request at fffffffffffffff0 IP: [<ffffffff802bc6c6>] proc_sys_compare+0x36/0x50 and was seen on both x86-64 (Alexey Dobriyan and Hugh Dickins) and ppc64 (Hugh Dickins). Reported-by: Alexey Dobriyan <adobriyan@gmail.com> Acked-by: Hugh Dickins <hugh@veritas.com> Cc: Al Viro <viro@ZenIV.linux.org.uk> Reviewed-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-of-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-09-29 22:42:57 +08:00
if (d_unhashed(dentry))
goto next;
/*
* It is safe to compare names since d_move() cannot
* change the qstr (protected by d_lock).
*/
if (parent->d_flags & DCACHE_OP_COMPARE) {
vfs: clean up __d_lookup_rcu() and dentry_cmp() interfaces The calling conventions for __d_lookup_rcu() and dentry_cmp() are annoying in different ways, and there is actually one single underlying reason for both of the annoyances. The fundamental reason is that we do the returned dentry sequence number check inside __d_lookup_rcu() instead of doing it in the caller. This results in two annoyances: - __d_lookup_rcu() now not only needs to return the dentry and the sequence number that goes along with the lookup, it also needs to return the inode pointer that was validated by that sequence number check. - and because we did the sequence number check early (to validate the name pointer and length) we also couldn't just pass the dentry itself to dentry_cmp(), we had to pass the counted string that contained the name. So that sequence number decision caused two separate ugly calling conventions. Both of these problems would be solved if we just did the sequence number check in the caller instead. There's only one caller, and that caller already has to do the sequence number check for the parent anyway, so just do that. That allows us to stop returning the dentry->d_inode in that in-out argument (pointer-to-pointer-to-inode), so we can make the inode argument just a regular input inode pointer. The caller can just load the inode from dentry->d_inode, and then do the sequence number check after that to make sure that it's synchronized with the name we looked up. And it allows us to just pass in the dentry to dentry_cmp(), which is what all the callers really wanted. Sure, dentry_cmp() has to be a bit careful about the dentry (which is not stable during RCU lookup), but that's actually very simple. And now that dentry_cmp() can clearly see that the first string argument is a dentry, we can use the direct word access for that, instead of the careful unaligned zero-padding. The dentry name is always properly aligned, since it is a single path component that is either embedded into the dentry itself, or was allocated with kmalloc() (see __d_alloc). Finally, this also uninlines the nasty slow-case for dentry comparisons: that one *does* need to do a sequence number check, since it will call in to the low-level filesystems, and we want to give those a stable inode pointer and path component length/start arguments. Doing an extra sequence check for that slow case is not a problem, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-05-05 05:59:14 +08:00
int tlen = dentry->d_name.len;
const char *tname = dentry->d_name.name;
if (parent->d_op->d_compare(parent, dentry, tlen, tname, name))
goto next;
} else {
if (dentry->d_name.len != len)
goto next;
vfs: clean up __d_lookup_rcu() and dentry_cmp() interfaces The calling conventions for __d_lookup_rcu() and dentry_cmp() are annoying in different ways, and there is actually one single underlying reason for both of the annoyances. The fundamental reason is that we do the returned dentry sequence number check inside __d_lookup_rcu() instead of doing it in the caller. This results in two annoyances: - __d_lookup_rcu() now not only needs to return the dentry and the sequence number that goes along with the lookup, it also needs to return the inode pointer that was validated by that sequence number check. - and because we did the sequence number check early (to validate the name pointer and length) we also couldn't just pass the dentry itself to dentry_cmp(), we had to pass the counted string that contained the name. So that sequence number decision caused two separate ugly calling conventions. Both of these problems would be solved if we just did the sequence number check in the caller instead. There's only one caller, and that caller already has to do the sequence number check for the parent anyway, so just do that. That allows us to stop returning the dentry->d_inode in that in-out argument (pointer-to-pointer-to-inode), so we can make the inode argument just a regular input inode pointer. The caller can just load the inode from dentry->d_inode, and then do the sequence number check after that to make sure that it's synchronized with the name we looked up. And it allows us to just pass in the dentry to dentry_cmp(), which is what all the callers really wanted. Sure, dentry_cmp() has to be a bit careful about the dentry (which is not stable during RCU lookup), but that's actually very simple. And now that dentry_cmp() can clearly see that the first string argument is a dentry, we can use the direct word access for that, instead of the careful unaligned zero-padding. The dentry name is always properly aligned, since it is a single path component that is either embedded into the dentry itself, or was allocated with kmalloc() (see __d_alloc). Finally, this also uninlines the nasty slow-case for dentry comparisons: that one *does* need to do a sequence number check, since it will call in to the low-level filesystems, and we want to give those a stable inode pointer and path component length/start arguments. Doing an extra sequence check for that slow case is not a problem, though. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-05-05 05:59:14 +08:00
if (dentry_cmp(dentry, str, len))
goto next;
}
dentry->d_lockref.count++;
Fix NULL pointer dereference in proc_sys_compare The VFS interface for the 'd_compare()' is a bit special (read: 'odd'), because it really just essentially replaces a memcmp(). The filesystem is supposed to just compare the two names with whatever case-independent or other function. And when I say 'is supposed to', I obviously mean that 'procfs does odd things, and actually looks at the dentry that we don't even pass down, rather than just the name'. Which results in problems, because we actually call d_compare before we have even verified that the dentry is still hashed at all. And that causes a problm since the inode that procfs looks at may have been free'd and the d_inode pointer is NULL. procfs just assumes that all dentries are positive, since procfs itself never generates a negative one. But memory pressure will still result in the dentry getting torn down, and as it is removed by RCU, it still remains visible on some lists - and to d_compare. If the filesystem just did a name comparison, we wouldn't care. And we could just fix procfs to know about negative dentries too. But rather than have the low-level filesystems know about internal VFS details, just move the check for a unhashed dentry up a bit, so that we will only call d_compare on dentries that are still active. The actual oops this caused didn't look like a NULL pointer dereference because procfs did a 'container_of(inode, struct proc_inode, vfs_inode)' to get at its internal proc_inode information from the inode pointer, and accessed a field below the inode. So the oops would look something like BUG: unable to handle kernel paging request at fffffffffffffff0 IP: [<ffffffff802bc6c6>] proc_sys_compare+0x36/0x50 and was seen on both x86-64 (Alexey Dobriyan and Hugh Dickins) and ppc64 (Hugh Dickins). Reported-by: Alexey Dobriyan <adobriyan@gmail.com> Acked-by: Hugh Dickins <hugh@veritas.com> Cc: Al Viro <viro@ZenIV.linux.org.uk> Reviewed-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-of-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-09-29 22:42:57 +08:00
found = dentry;
spin_unlock(&dentry->d_lock);
break;
next:
spin_unlock(&dentry->d_lock);
}
rcu_read_unlock();
return found;
}
/**
* d_hash_and_lookup - hash the qstr then search for a dentry
* @dir: Directory to search in
* @name: qstr of name we wish to find
*
* On lookup failure NULL is returned; on bad name - ERR_PTR(-error)
*/
struct dentry *d_hash_and_lookup(struct dentry *dir, struct qstr *name)
{
/*
* Check for a fs-specific hash function. Note that we must
* calculate the standard hash first, as the d_op->d_hash()
* routine may choose to leave the hash value unchanged.
*/
name->hash = full_name_hash(name->name, name->len);
if (dir->d_flags & DCACHE_OP_HASH) {
int err = dir->d_op->d_hash(dir, name);
if (unlikely(err < 0))
return ERR_PTR(err);
}
return d_lookup(dir, name);
}
EXPORT_SYMBOL(d_hash_and_lookup);
/**
* d_validate - verify dentry provided from insecure source (deprecated)
* @dentry: The dentry alleged to be valid child of @dparent
* @dparent: The parent dentry (known to be valid)
*
* An insecure source has sent us a dentry, here we verify it and dget() it.
* This is used by ncpfs in its readdir implementation.
* Zero is returned in the dentry is invalid.
*
* This function is slow for big directories, and deprecated, do not use it.
*/
int d_validate(struct dentry *dentry, struct dentry *dparent)
{
struct dentry *child;
spin_lock(&dparent->d_lock);
list_for_each_entry(child, &dparent->d_subdirs, d_u.d_child) {
if (dentry == child) {
spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
__dget_dlock(dentry);
spin_unlock(&dentry->d_lock);
spin_unlock(&dparent->d_lock);
return 1;
}
}
spin_unlock(&dparent->d_lock);
return 0;
}
EXPORT_SYMBOL(d_validate);
/*
* When a file is deleted, we have two options:
* - turn this dentry into a negative dentry
* - unhash this dentry and free it.
*
* Usually, we want to just turn this into
* a negative dentry, but if anybody else is
* currently using the dentry or the inode
* we can't do that and we fall back on removing
* it from the hash queues and waiting for
* it to be deleted later when it has no users
*/
/**
* d_delete - delete a dentry
* @dentry: The dentry to delete
*
* Turn the dentry into a negative dentry if possible, otherwise
* remove it from the hash queues so it can be deleted later
*/
void d_delete(struct dentry * dentry)
{
struct inode *inode;
int isdir = 0;
/*
* Are we the only user?
*/
again:
spin_lock(&dentry->d_lock);
inode = dentry->d_inode;
isdir = S_ISDIR(inode->i_mode);
if (dentry->d_lockref.count == 1) {
if (!spin_trylock(&inode->i_lock)) {
spin_unlock(&dentry->d_lock);
cpu_relax();
goto again;
}
dentry->d_flags &= ~DCACHE_CANT_MOUNT;
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
dentry_unlink_inode(dentry);
fsnotify_nameremove(dentry, isdir);
return;
}
if (!d_unhashed(dentry))
__d_drop(dentry);
spin_unlock(&dentry->d_lock);
fsnotify_nameremove(dentry, isdir);
}
EXPORT_SYMBOL(d_delete);
static void __d_rehash(struct dentry * entry, struct hlist_bl_head *b)
{
BUG_ON(!d_unhashed(entry));
hlist_bl_lock(b);
vfs: get rid of insane dentry hashing rules The dentry hashing rules have been really quite complicated for a long while, in odd ways. That made functions like __d_drop() very fragile and non-obvious. In particular, whether a dentry was hashed or not was indicated with an explicit DCACHE_UNHASHED bit. That's despite the fact that the hash abstraction that the dentries use actually have a 'is this entry hashed or not' model (which is a simple test of the 'pprev' pointer). The reason that was done is because we used the normal 'is this entry unhashed' model to mark whether the dentry had _ever_ been hashed in the dentry hash tables, and that logic goes back many years (commit b3423415fbc2: "dcache: avoid RCU for never-hashed dentries"). That, in turn, meant that __d_drop had totally different unhashing logic for the dentry hash table case and for the anonymous dcache case, because in order to use the "is this dentry hashed" logic as a flag for whether it had ever been on the RCU hash table, we had to unhash such a dentry differently so that we'd never think that it wasn't 'unhashed' and wouldn't be free'd correctly. That's just insane. It made the logic really hard to follow, when there were two different kinds of "unhashed" states, and one of them (the one that used "list_bl_unhashed()") really had nothing at all to do with being unhashed per se, but with a very subtle lifetime rule instead. So turn all of it around, and make it logical. Instead of having a DENTRY_UNHASHED bit in d_flags to indicate whether the dentry is on the hash chains or not, use the hash chain unhashed logic for that. Suddenly "d_unhashed()" just uses "list_bl_unhashed()", and everything makes sense. And for the lifetime rule, just use an explicit DENTRY_RCUACCEES bit. If we ever insert the dentry into the dentry hash table so that it is visible to RCU lookup, we mark it DENTRY_RCUACCESS to show that it now needs the RCU lifetime rules. Now suddently that test at dentry free time makes sense too. And because unhashing now is sane and doesn't depend on where the dentry got unhashed from (because the dentry hash chain details doesn't have some subtle side effects), we can re-unify the __d_drop() logic and use common code for the unhashing. Also fix one more open-coded hash chain bit_spin_lock() that I missed in the previous chain locking cleanup commit. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-04-24 22:58:46 +08:00
entry->d_flags |= DCACHE_RCUACCESS;
hlist_bl_add_head_rcu(&entry->d_hash, b);
hlist_bl_unlock(b);
}
static void _d_rehash(struct dentry * entry)
{
__d_rehash(entry, d_hash(entry->d_parent, entry->d_name.hash));
}
/**
* d_rehash - add an entry back to the hash
* @entry: dentry to add to the hash
*
* Adds a dentry to the hash according to its name.
*/
void d_rehash(struct dentry * entry)
{
spin_lock(&entry->d_lock);
_d_rehash(entry);
spin_unlock(&entry->d_lock);
}
EXPORT_SYMBOL(d_rehash);
/**
* dentry_update_name_case - update case insensitive dentry with a new name
* @dentry: dentry to be updated
* @name: new name
*
* Update a case insensitive dentry with new case of name.
*
* dentry must have been returned by d_lookup with name @name. Old and new
* name lengths must match (ie. no d_compare which allows mismatched name
* lengths).
*
* Parent inode i_mutex must be held over d_lookup and into this call (to
* keep renames and concurrent inserts, and readdir(2) away).
*/
void dentry_update_name_case(struct dentry *dentry, struct qstr *name)
{
BUG_ON(!mutex_is_locked(&dentry->d_parent->d_inode->i_mutex));
BUG_ON(dentry->d_name.len != name->len); /* d_lookup gives this */
spin_lock(&dentry->d_lock);
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
write_seqcount_begin(&dentry->d_seq);
memcpy((unsigned char *)dentry->d_name.name, name->name, name->len);
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
write_seqcount_end(&dentry->d_seq);
spin_unlock(&dentry->d_lock);
}
EXPORT_SYMBOL(dentry_update_name_case);
static void switch_names(struct dentry *dentry, struct dentry *target)
{
if (dname_external(target)) {
if (dname_external(dentry)) {
/*
* Both external: swap the pointers
*/
swap(target->d_name.name, dentry->d_name.name);
} else {
/*
* dentry:internal, target:external. Steal target's
* storage and make target internal.
*/
memcpy(target->d_iname, dentry->d_name.name,
dentry->d_name.len + 1);
dentry->d_name.name = target->d_name.name;
target->d_name.name = target->d_iname;
}
} else {
if (dname_external(dentry)) {
/*
* dentry:external, target:internal. Give dentry's
* storage to target and make dentry internal
*/
memcpy(dentry->d_iname, target->d_name.name,
target->d_name.len + 1);
target->d_name.name = dentry->d_name.name;
dentry->d_name.name = dentry->d_iname;
} else {
/*
* Both are internal. Just copy target to dentry
*/
memcpy(dentry->d_iname, target->d_name.name,
target->d_name.len + 1);
dentry->d_name.len = target->d_name.len;
return;
}
}
swap(dentry->d_name.len, target->d_name.len);
}
static void dentry_lock_for_move(struct dentry *dentry, struct dentry *target)
{
/*
* XXXX: do we really need to take target->d_lock?
*/
if (IS_ROOT(dentry) || dentry->d_parent == target->d_parent)
spin_lock(&target->d_parent->d_lock);
else {
if (d_ancestor(dentry->d_parent, target->d_parent)) {
spin_lock(&dentry->d_parent->d_lock);
spin_lock_nested(&target->d_parent->d_lock,
DENTRY_D_LOCK_NESTED);
} else {
spin_lock(&target->d_parent->d_lock);
spin_lock_nested(&dentry->d_parent->d_lock,
DENTRY_D_LOCK_NESTED);
}
}
if (target < dentry) {
spin_lock_nested(&target->d_lock, 2);
spin_lock_nested(&dentry->d_lock, 3);
} else {
spin_lock_nested(&dentry->d_lock, 2);
spin_lock_nested(&target->d_lock, 3);
}
}
static void dentry_unlock_parents_for_move(struct dentry *dentry,
struct dentry *target)
{
if (target->d_parent != dentry->d_parent)
spin_unlock(&dentry->d_parent->d_lock);
if (target->d_parent != target)
spin_unlock(&target->d_parent->d_lock);
}
/*
* When switching names, the actual string doesn't strictly have to
* be preserved in the target - because we're dropping the target
* anyway. As such, we can just do a simple memcpy() to copy over
* the new name before we switch.
*
* Note that we have to be a lot more careful about getting the hash
* switched - we have to switch the hash value properly even if it
* then no longer matches the actual (corrupted) string of the target.
* The hash value has to match the hash queue that the dentry is on..
*/
/*
* __d_move - move a dentry
* @dentry: entry to move
* @target: new dentry
*
* Update the dcache to reflect the move of a file name. Negative
* dcache entries should not be moved in this way. Caller must hold
* rename_lock, the i_mutex of the source and target directories,
* and the sb->s_vfs_rename_mutex if they differ. See lock_rename().
*/
static void __d_move(struct dentry * dentry, struct dentry * target)
{
if (!dentry->d_inode)
printk(KERN_WARNING "VFS: moving negative dcache entry\n");
BUG_ON(d_ancestor(dentry, target));
BUG_ON(d_ancestor(target, dentry));
dentry_lock_for_move(dentry, target);
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
write_seqcount_begin(&dentry->d_seq);
write_seqcount_begin_nested(&target->d_seq, DENTRY_D_LOCK_NESTED);
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
/* __d_drop does write_seqcount_barrier, but they're OK to nest. */
/*
* Move the dentry to the target hash queue. Don't bother checking
* for the same hash queue because of how unlikely it is.
*/
__d_drop(dentry);
__d_rehash(dentry, d_hash(target->d_parent, target->d_name.hash));
/* Unhash the target: dput() will then get rid of it */
__d_drop(target);
[PATCH] shrink dentry struct Some long time ago, dentry struct was carefully tuned so that on 32 bits UP, sizeof(struct dentry) was exactly 128, ie a power of 2, and a multiple of memory cache lines. Then RCU was added and dentry struct enlarged by two pointers, with nice results for SMP, but not so good on UP, because breaking the above tuning (128 + 8 = 136 bytes) This patch reverts this unwanted side effect, by using an union (d_u), where d_rcu and d_child are placed so that these two fields can share their memory needs. At the time d_free() is called (and d_rcu is really used), d_child is known to be empty and not touched by the dentry freeing. Lockless lookups only access d_name, d_parent, d_lock, d_op, d_flags (so the previous content of d_child is not needed if said dentry was unhashed but still accessed by a CPU because of RCU constraints) As dentry cache easily contains millions of entries, a size reduction is worth the extra complexity of the ugly C union. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Maneesh Soni <maneesh@in.ibm.com> Cc: Miklos Szeredi <miklos@szeredi.hu> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Ian Kent <raven@themaw.net> Cc: Paul Jackson <pj@sgi.com> Cc: Al Viro <viro@ftp.linux.org.uk> Cc: Christoph Hellwig <hch@lst.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Neil Brown <neilb@cse.unsw.edu.au> Cc: James Morris <jmorris@namei.org> Cc: Stephen Smalley <sds@epoch.ncsc.mil> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:03:32 +08:00
list_del(&dentry->d_u.d_child);
list_del(&target->d_u.d_child);
/* Switch the names.. */
switch_names(dentry, target);
swap(dentry->d_name.hash, target->d_name.hash);
/* ... and switch the parents */
if (IS_ROOT(dentry)) {
dentry->d_parent = target->d_parent;
target->d_parent = target;
[PATCH] shrink dentry struct Some long time ago, dentry struct was carefully tuned so that on 32 bits UP, sizeof(struct dentry) was exactly 128, ie a power of 2, and a multiple of memory cache lines. Then RCU was added and dentry struct enlarged by two pointers, with nice results for SMP, but not so good on UP, because breaking the above tuning (128 + 8 = 136 bytes) This patch reverts this unwanted side effect, by using an union (d_u), where d_rcu and d_child are placed so that these two fields can share their memory needs. At the time d_free() is called (and d_rcu is really used), d_child is known to be empty and not touched by the dentry freeing. Lockless lookups only access d_name, d_parent, d_lock, d_op, d_flags (so the previous content of d_child is not needed if said dentry was unhashed but still accessed by a CPU because of RCU constraints) As dentry cache easily contains millions of entries, a size reduction is worth the extra complexity of the ugly C union. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Maneesh Soni <maneesh@in.ibm.com> Cc: Miklos Szeredi <miklos@szeredi.hu> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Ian Kent <raven@themaw.net> Cc: Paul Jackson <pj@sgi.com> Cc: Al Viro <viro@ftp.linux.org.uk> Cc: Christoph Hellwig <hch@lst.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Neil Brown <neilb@cse.unsw.edu.au> Cc: James Morris <jmorris@namei.org> Cc: Stephen Smalley <sds@epoch.ncsc.mil> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:03:32 +08:00
INIT_LIST_HEAD(&target->d_u.d_child);
} else {
swap(dentry->d_parent, target->d_parent);
/* And add them back to the (new) parent lists */
[PATCH] shrink dentry struct Some long time ago, dentry struct was carefully tuned so that on 32 bits UP, sizeof(struct dentry) was exactly 128, ie a power of 2, and a multiple of memory cache lines. Then RCU was added and dentry struct enlarged by two pointers, with nice results for SMP, but not so good on UP, because breaking the above tuning (128 + 8 = 136 bytes) This patch reverts this unwanted side effect, by using an union (d_u), where d_rcu and d_child are placed so that these two fields can share their memory needs. At the time d_free() is called (and d_rcu is really used), d_child is known to be empty and not touched by the dentry freeing. Lockless lookups only access d_name, d_parent, d_lock, d_op, d_flags (so the previous content of d_child is not needed if said dentry was unhashed but still accessed by a CPU because of RCU constraints) As dentry cache easily contains millions of entries, a size reduction is worth the extra complexity of the ugly C union. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Maneesh Soni <maneesh@in.ibm.com> Cc: Miklos Szeredi <miklos@szeredi.hu> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Ian Kent <raven@themaw.net> Cc: Paul Jackson <pj@sgi.com> Cc: Al Viro <viro@ftp.linux.org.uk> Cc: Christoph Hellwig <hch@lst.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Neil Brown <neilb@cse.unsw.edu.au> Cc: James Morris <jmorris@namei.org> Cc: Stephen Smalley <sds@epoch.ncsc.mil> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:03:32 +08:00
list_add(&target->d_u.d_child, &target->d_parent->d_subdirs);
}
[PATCH] shrink dentry struct Some long time ago, dentry struct was carefully tuned so that on 32 bits UP, sizeof(struct dentry) was exactly 128, ie a power of 2, and a multiple of memory cache lines. Then RCU was added and dentry struct enlarged by two pointers, with nice results for SMP, but not so good on UP, because breaking the above tuning (128 + 8 = 136 bytes) This patch reverts this unwanted side effect, by using an union (d_u), where d_rcu and d_child are placed so that these two fields can share their memory needs. At the time d_free() is called (and d_rcu is really used), d_child is known to be empty and not touched by the dentry freeing. Lockless lookups only access d_name, d_parent, d_lock, d_op, d_flags (so the previous content of d_child is not needed if said dentry was unhashed but still accessed by a CPU because of RCU constraints) As dentry cache easily contains millions of entries, a size reduction is worth the extra complexity of the ugly C union. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Cc: Dipankar Sarma <dipankar@in.ibm.com> Cc: Maneesh Soni <maneesh@in.ibm.com> Cc: Miklos Szeredi <miklos@szeredi.hu> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Cc: Ian Kent <raven@themaw.net> Cc: Paul Jackson <pj@sgi.com> Cc: Al Viro <viro@ftp.linux.org.uk> Cc: Christoph Hellwig <hch@lst.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: Neil Brown <neilb@cse.unsw.edu.au> Cc: James Morris <jmorris@namei.org> Cc: Stephen Smalley <sds@epoch.ncsc.mil> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 17:03:32 +08:00
list_add(&dentry->d_u.d_child, &dentry->d_parent->d_subdirs);
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
write_seqcount_end(&target->d_seq);
write_seqcount_end(&dentry->d_seq);
dentry_unlock_parents_for_move(dentry, target);
spin_unlock(&target->d_lock);
fsnotify_d_move(dentry);
spin_unlock(&dentry->d_lock);
}
/*
* d_move - move a dentry
* @dentry: entry to move
* @target: new dentry
*
* Update the dcache to reflect the move of a file name. Negative
* dcache entries should not be moved in this way. See the locking
* requirements for __d_move.
*/
void d_move(struct dentry *dentry, struct dentry *target)
{
write_seqlock(&rename_lock);
__d_move(dentry, target);
write_sequnlock(&rename_lock);
}
EXPORT_SYMBOL(d_move);
/**
* d_ancestor - search for an ancestor
* @p1: ancestor dentry
* @p2: child dentry
*
* Returns the ancestor dentry of p2 which is a child of p1, if p1 is
* an ancestor of p2, else NULL.
*/
struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2)
{
struct dentry *p;
for (p = p2; !IS_ROOT(p); p = p->d_parent) {
if (p->d_parent == p1)
return p;
}
return NULL;
}
/*
* This helper attempts to cope with remotely renamed directories
*
* It assumes that the caller is already holding
* dentry->d_parent->d_inode->i_mutex, inode->i_lock and rename_lock
*
* Note: If ever the locking in lock_rename() changes, then please
* remember to update this too...
*/
static struct dentry *__d_unalias(struct inode *inode,
struct dentry *dentry, struct dentry *alias)
{
struct mutex *m1 = NULL, *m2 = NULL;
struct dentry *ret = ERR_PTR(-EBUSY);
/* If alias and dentry share a parent, then no extra locks required */
if (alias->d_parent == dentry->d_parent)
goto out_unalias;
/* See lock_rename() */
if (!mutex_trylock(&dentry->d_sb->s_vfs_rename_mutex))
goto out_err;
m1 = &dentry->d_sb->s_vfs_rename_mutex;
if (!mutex_trylock(&alias->d_parent->d_inode->i_mutex))
goto out_err;
m2 = &alias->d_parent->d_inode->i_mutex;
out_unalias:
if (likely(!d_mountpoint(alias))) {
__d_move(alias, dentry);
ret = alias;
}
out_err:
spin_unlock(&inode->i_lock);
if (m2)
mutex_unlock(m2);
if (m1)
mutex_unlock(m1);
return ret;
}
/*
* Prepare an anonymous dentry for life in the superblock's dentry tree as a
* named dentry in place of the dentry to be replaced.
* returns with anon->d_lock held!
*/
static void __d_materialise_dentry(struct dentry *dentry, struct dentry *anon)
{
struct dentry *dparent;
dentry_lock_for_move(anon, dentry);
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
write_seqcount_begin(&dentry->d_seq);
write_seqcount_begin_nested(&anon->d_seq, DENTRY_D_LOCK_NESTED);
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
dparent = dentry->d_parent;
switch_names(dentry, anon);
swap(dentry->d_name.hash, anon->d_name.hash);
dentry->d_parent = dentry;
list_del_init(&dentry->d_u.d_child);
anon->d_parent = dparent;
list_move(&anon->d_u.d_child, &dparent->d_subdirs);
fs: rcu-walk for path lookup Perform common cases of path lookups without any stores or locking in the ancestor dentry elements. This is called rcu-walk, as opposed to the current algorithm which is a refcount based walk, or ref-walk. This results in far fewer atomic operations on every path element, significantly improving path lookup performance. It also avoids cacheline bouncing on common dentries, significantly improving scalability. The overall design is like this: * LOOKUP_RCU is set in nd->flags, which distinguishes rcu-walk from ref-walk. * Take the RCU lock for the entire path walk, starting with the acquiring of the starting path (eg. root/cwd/fd-path). So now dentry refcounts are not required for dentry persistence. * synchronize_rcu is called when unregistering a filesystem, so we can access d_ops and i_ops during rcu-walk. * Similarly take the vfsmount lock for the entire path walk. So now mnt refcounts are not required for persistence. Also we are free to perform mount lookups, and to assume dentry mount points and mount roots are stable up and down the path. * Have a per-dentry seqlock to protect the dentry name, parent, and inode, so we can load this tuple atomically, and also check whether any of its members have changed. * Dentry lookups (based on parent, candidate string tuple) recheck the parent sequence after the child is found in case anything changed in the parent during the path walk. * inode is also RCU protected so we can load d_inode and use the inode for limited things. * i_mode, i_uid, i_gid can be tested for exec permissions during path walk. * i_op can be loaded. When we reach the destination dentry, we lock it, recheck lookup sequence, and increment its refcount and mountpoint refcount. RCU and vfsmount locks are dropped. This is termed "dropping rcu-walk". If the dentry refcount does not match, we can not drop rcu-walk gracefully at the current point in the lokup, so instead return -ECHILD (for want of a better errno). This signals the path walking code to re-do the entire lookup with a ref-walk. Aside from the final dentry, there are other situations that may be encounted where we cannot continue rcu-walk. In that case, we drop rcu-walk (ie. take a reference on the last good dentry) and continue with a ref-walk. Again, if we can drop rcu-walk gracefully, we return -ECHILD and do the whole lookup using ref-walk. But it is very important that we can continue with ref-walk for most cases, particularly to avoid the overhead of double lookups, and to gain the scalability advantages on common path elements (like cwd and root). The cases where rcu-walk cannot continue are: * NULL dentry (ie. any uncached path element) * parent with d_inode->i_op->permission or ACLs * dentries with d_revalidate * Following links In future patches, permission checks and d_revalidate become rcu-walk aware. It may be possible eventually to make following links rcu-walk aware. Uncached path elements will always require dropping to ref-walk mode, at the very least because i_mutex needs to be grabbed, and objects allocated. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
2011-01-07 14:49:52 +08:00
write_seqcount_end(&dentry->d_seq);
write_seqcount_end(&anon->d_seq);
dentry_unlock_parents_for_move(anon, dentry);
spin_unlock(&dentry->d_lock);
/* anon->d_lock still locked, returns locked */
}
/**
* d_materialise_unique - introduce an inode into the tree
* @dentry: candidate dentry
* @inode: inode to bind to the dentry, to which aliases may be attached
*
* Introduces an dentry into the tree, substituting an extant disconnected
* root directory alias in its place if there is one. Caller must hold the
* i_mutex of the parent directory.
*/
struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
{
struct dentry *actual;
BUG_ON(!d_unhashed(dentry));
if (!inode) {
actual = dentry;
__d_instantiate(dentry, NULL);
d_rehash(actual);
goto out_nolock;
}
spin_lock(&inode->i_lock);
if (S_ISDIR(inode->i_mode)) {
struct dentry *alias;
/* Does an aliased dentry already exist? */
Revert "vfs: stop d_splice_alias creating directory aliases" This reverts commit 7732a557b1342c6e6966efb5f07effcf99f56167 (and commit 3f50fff4dace23d3cfeb195d5cd4ee813cee68b7, which was a follow-up cleanup). We're chasing an elusive bug that Dave Jones can apparently reproduce using his system call fuzzer tool, and that looks like some kind of locking ordering problem on the directory i_mutex chain. Our i_mutex locking is rather complex, and depends on the topological ordering of the directories, which is why we have been very wary of splicing directory entries around. Of course, we really don't want to ever see aliased unconnected directories anyway, so none of this should ever happen, but this revert aims to basically get us back to a known older state. Bruce points to some of the previous discussion at http://marc.info/?i=<20110310105821.GE22723@ZenIV.linux.org.uk> and in particular a long post from Neil: http://marc.info/?i=<20110311150749.2fa2be66@notabene.brown> It should be noted that it's possible that Dave's problems come from other changes altohgether, including possibly just the fact that Dave constantly is teachning his fuzzer new tricks. So what appears to be a new bug could in fact be an old one that just gets newly triggered, but reverting these patches as "still under heavy discussion" is the right thing regardless. Requested-by: Al Viro <viro@zeniv.linux.org.uk> Acked-by: J. Bruce Fields <bfields@fieldses.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-06-09 01:34:03 +08:00
alias = __d_find_alias(inode, 0);
if (alias) {
actual = alias;
write_seqlock(&rename_lock);
if (d_ancestor(alias, dentry)) {
/* Check for loops */
actual = ERR_PTR(-ELOOP);
spin_unlock(&inode->i_lock);
} else if (IS_ROOT(alias)) {
/* Is this an anonymous mountpoint that we
* could splice into our tree? */
__d_materialise_dentry(dentry, alias);
write_sequnlock(&rename_lock);
__d_drop(alias);
goto found;
} else {
/* Nope, but we must(!) avoid directory
* aliasing. This drops inode->i_lock */
actual = __d_unalias(inode, dentry, alias);
}
write_sequnlock(&rename_lock);
if (IS_ERR(actual)) {
if (PTR_ERR(actual) == -ELOOP)
pr_warn_ratelimited(
"VFS: Lookup of '%s' in %s %s"
" would have caused loop\n",
dentry->d_name.name,
inode->i_sb->s_type->name,
inode->i_sb->s_id);
dput(alias);
}
goto out_nolock;
}
}
/* Add a unique reference */
actual = __d_instantiate_unique(dentry, inode);
if (!actual)
actual = dentry;
else
BUG_ON(!d_unhashed(actual));
spin_lock(&actual->d_lock);
found:
_d_rehash(actual);
spin_unlock(&actual->d_lock);
spin_unlock(&inode->i_lock);
out_nolock:
if (actual == dentry) {
security_d_instantiate(dentry, inode);
return NULL;
}
iput(inode);
return actual;
}
EXPORT_SYMBOL_GPL(d_materialise_unique);
static int prepend(char **buffer, int *buflen, const char *str, int namelen)
{
*buflen -= namelen;
if (*buflen < 0)
return -ENAMETOOLONG;
*buffer -= namelen;
memcpy(*buffer, str, namelen);
return 0;
}
dcache: Translating dentry into pathname without taking rename_lock When running the AIM7's short workload, Linus' lockref patch eliminated most of the spinlock contention. However, there were still some left: 8.46% reaim [kernel.kallsyms] [k] _raw_spin_lock |--42.21%-- d_path | proc_pid_readlink | SyS_readlinkat | SyS_readlink | system_call | __GI___readlink | |--40.97%-- sys_getcwd | system_call | __getcwd The big one here is the rename_lock (seqlock) contention in d_path() and the getcwd system call. This patch will eliminate the need to take the rename_lock while translating dentries into the full pathnames. The need to take the rename_lock is to make sure that no rename operation can be ongoing while the translation is in progress. However, only one thread can take the rename_lock thus blocking all the other threads that need it even though the translation process won't make any change to the dentries. This patch will replace the writer's write_seqlock/write_sequnlock sequence of the rename_lock of the callers of the prepend_path() and __dentry_path() functions with the reader's read_seqbegin/read_seqretry sequence within these 2 functions. As a result, the code will have to retry if one or more rename operations had been performed. In addition, RCU read lock will be taken during the translation process to make sure that no dentries will go away. To prevent live-lock from happening, the code will switch back to take the rename_lock if read_seqretry() fails for three times. To further reduce spinlock contention, this patch does not take the dentry's d_lock when copying the filename from the dentries. Instead, it treats the name pointer and length as unreliable and just copy the string byte-by-byte over until it hits a null byte or the end of string as specified by the length. This should avoid stepping into invalid memory address. The error cases are left to be handled by the sequence number check. The following code re-factoring are also made: 1. Move prepend('/') into prepend_name() to remove one conditional check. 2. Move the global root check in prepend_path() back to the top of the while loop. With this patch, the _raw_spin_lock will now account for only 1.2% of the total CPU cycles for the short workload. This patch also has the effect of reducing the effect of running perf on its profile since the perf command itself can be a heavy user of the d_path() function depending on the complexity of the workload. When taking the perf profile of the high-systime workload, the amount of spinlock contention contributed by running perf without this patch was about 16%. With this patch, the spinlock contention caused by the running of perf will go away and we will have a more accurate perf profile. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-10 00:18:13 +08:00
/**
* prepend_name - prepend a pathname in front of current buffer pointer
* @buffer: buffer pointer
* @buflen: allocated length of the buffer
* @name: name string and length qstr structure
dcache: Translating dentry into pathname without taking rename_lock When running the AIM7's short workload, Linus' lockref patch eliminated most of the spinlock contention. However, there were still some left: 8.46% reaim [kernel.kallsyms] [k] _raw_spin_lock |--42.21%-- d_path | proc_pid_readlink | SyS_readlinkat | SyS_readlink | system_call | __GI___readlink | |--40.97%-- sys_getcwd | system_call | __getcwd The big one here is the rename_lock (seqlock) contention in d_path() and the getcwd system call. This patch will eliminate the need to take the rename_lock while translating dentries into the full pathnames. The need to take the rename_lock is to make sure that no rename operation can be ongoing while the translation is in progress. However, only one thread can take the rename_lock thus blocking all the other threads that need it even though the translation process won't make any change to the dentries. This patch will replace the writer's write_seqlock/write_sequnlock sequence of the rename_lock of the callers of the prepend_path() and __dentry_path() functions with the reader's read_seqbegin/read_seqretry sequence within these 2 functions. As a result, the code will have to retry if one or more rename operations had been performed. In addition, RCU read lock will be taken during the translation process to make sure that no dentries will go away. To prevent live-lock from happening, the code will switch back to take the rename_lock if read_seqretry() fails for three times. To further reduce spinlock contention, this patch does not take the dentry's d_lock when copying the filename from the dentries. Instead, it treats the name pointer and length as unreliable and just copy the string byte-by-byte over until it hits a null byte or the end of string as specified by the length. This should avoid stepping into invalid memory address. The error cases are left to be handled by the sequence number check. The following code re-factoring are also made: 1. Move prepend('/') into prepend_name() to remove one conditional check. 2. Move the global root check in prepend_path() back to the top of the while loop. With this patch, the _raw_spin_lock will now account for only 1.2% of the total CPU cycles for the short workload. This patch also has the effect of reducing the effect of running perf on its profile since the perf command itself can be a heavy user of the d_path() function depending on the complexity of the workload. When taking the perf profile of the high-systime workload, the amount of spinlock contention contributed by running perf without this patch was about 16%. With this patch, the spinlock contention caused by the running of perf will go away and we will have a more accurate perf profile. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-10 00:18:13 +08:00
*
* With RCU path tracing, it may race with d_move(). Use ACCESS_ONCE() to
* make sure that either the old or the new name pointer and length are
* fetched. However, there may be mismatch between length and pointer.
* The length cannot be trusted, we need to copy it byte-by-byte until
* the length is reached or a null byte is found. It also prepends "/" at
* the beginning of the name. The sequence number check at the caller will
* retry it again when a d_move() does happen. So any garbage in the buffer
* due to mismatched pointer and length will be discarded.
*/
static int prepend_name(char **buffer, int *buflen, struct qstr *name)
{
dcache: Translating dentry into pathname without taking rename_lock When running the AIM7's short workload, Linus' lockref patch eliminated most of the spinlock contention. However, there were still some left: 8.46% reaim [kernel.kallsyms] [k] _raw_spin_lock |--42.21%-- d_path | proc_pid_readlink | SyS_readlinkat | SyS_readlink | system_call | __GI___readlink | |--40.97%-- sys_getcwd | system_call | __getcwd The big one here is the rename_lock (seqlock) contention in d_path() and the getcwd system call. This patch will eliminate the need to take the rename_lock while translating dentries into the full pathnames. The need to take the rename_lock is to make sure that no rename operation can be ongoing while the translation is in progress. However, only one thread can take the rename_lock thus blocking all the other threads that need it even though the translation process won't make any change to the dentries. This patch will replace the writer's write_seqlock/write_sequnlock sequence of the rename_lock of the callers of the prepend_path() and __dentry_path() functions with the reader's read_seqbegin/read_seqretry sequence within these 2 functions. As a result, the code will have to retry if one or more rename operations had been performed. In addition, RCU read lock will be taken during the translation process to make sure that no dentries will go away. To prevent live-lock from happening, the code will switch back to take the rename_lock if read_seqretry() fails for three times. To further reduce spinlock contention, this patch does not take the dentry's d_lock when copying the filename from the dentries. Instead, it treats the name pointer and length as unreliable and just copy the string byte-by-byte over until it hits a null byte or the end of string as specified by the length. This should avoid stepping into invalid memory address. The error cases are left to be handled by the sequence number check. The following code re-factoring are also made: 1. Move prepend('/') into prepend_name() to remove one conditional check. 2. Move the global root check in prepend_path() back to the top of the while loop. With this patch, the _raw_spin_lock will now account for only 1.2% of the total CPU cycles for the short workload. This patch also has the effect of reducing the effect of running perf on its profile since the perf command itself can be a heavy user of the d_path() function depending on the complexity of the workload. When taking the perf profile of the high-systime workload, the amount of spinlock contention contributed by running perf without this patch was about 16%. With this patch, the spinlock contention caused by the running of perf will go away and we will have a more accurate perf profile. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-10 00:18:13 +08:00
const char *dname = ACCESS_ONCE(name->name);
u32 dlen = ACCESS_ONCE(name->len);
char *p;
*buflen -= dlen + 1;
if (*buflen < 0)
return -ENAMETOOLONG;
dcache: Translating dentry into pathname without taking rename_lock When running the AIM7's short workload, Linus' lockref patch eliminated most of the spinlock contention. However, there were still some left: 8.46% reaim [kernel.kallsyms] [k] _raw_spin_lock |--42.21%-- d_path | proc_pid_readlink | SyS_readlinkat | SyS_readlink | system_call | __GI___readlink | |--40.97%-- sys_getcwd | system_call | __getcwd The big one here is the rename_lock (seqlock) contention in d_path() and the getcwd system call. This patch will eliminate the need to take the rename_lock while translating dentries into the full pathnames. The need to take the rename_lock is to make sure that no rename operation can be ongoing while the translation is in progress. However, only one thread can take the rename_lock thus blocking all the other threads that need it even though the translation process won't make any change to the dentries. This patch will replace the writer's write_seqlock/write_sequnlock sequence of the rename_lock of the callers of the prepend_path() and __dentry_path() functions with the reader's read_seqbegin/read_seqretry sequence within these 2 functions. As a result, the code will have to retry if one or more rename operations had been performed. In addition, RCU read lock will be taken during the translation process to make sure that no dentries will go away. To prevent live-lock from happening, the code will switch back to take the rename_lock if read_seqretry() fails for three times. To further reduce spinlock contention, this patch does not take the dentry's d_lock when copying the filename from the dentries. Instead, it treats the name pointer and length as unreliable and just copy the string byte-by-byte over until it hits a null byte or the end of string as specified by the length. This should avoid stepping into invalid memory address. The error cases are left to be handled by the sequence number check. The following code re-factoring are also made: 1. Move prepend('/') into prepend_name() to remove one conditional check. 2. Move the global root check in prepend_path() back to the top of the while loop. With this patch, the _raw_spin_lock will now account for only 1.2% of the total CPU cycles for the short workload. This patch also has the effect of reducing the effect of running perf on its profile since the perf command itself can be a heavy user of the d_path() function depending on the complexity of the workload. When taking the perf profile of the high-systime workload, the amount of spinlock contention contributed by running perf without this patch was about 16%. With this patch, the spinlock contention caused by the running of perf will go away and we will have a more accurate perf profile. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-10 00:18:13 +08:00
p = *buffer -= dlen + 1;
*p++ = '/';
while (dlen--) {
char c = *dname++;
if (!c)
break;
*p++ = c;
}
return 0;
}
/**
* prepend_path - Prepend path string to a buffer
* @path: the dentry/vfsmount to report
fix apparmor dereferencing potentially freed dentry, sanitize __d_path() API __d_path() API is asking for trouble and in case of apparmor d_namespace_path() getting just that. The root cause is that when __d_path() misses the root it had been told to look for, it stores the location of the most remote ancestor in *root. Without grabbing references. Sure, at the moment of call it had been pinned down by what we have in *path. And if we raced with umount -l, we could have very well stopped at vfsmount/dentry that got freed as soon as prepend_path() dropped vfsmount_lock. It is safe to compare these pointers with pre-existing (and known to be still alive) vfsmount and dentry, as long as all we are asking is "is it the same address?". Dereferencing is not safe and apparmor ended up stepping into that. d_namespace_path() really wants to examine the place where we stopped, even if it's not connected to our namespace. As the result, it looked at ->d_sb->s_magic of a dentry that might've been already freed by that point. All other callers had been careful enough to avoid that, but it's really a bad interface - it invites that kind of trouble. The fix is fairly straightforward, even though it's bigger than I'd like: * prepend_path() root argument becomes const. * __d_path() is never called with NULL/NULL root. It was a kludge to start with. Instead, we have an explicit function - d_absolute_root(). Same as __d_path(), except that it doesn't get root passed and stops where it stops. apparmor and tomoyo are using it. * __d_path() returns NULL on path outside of root. The main caller is show_mountinfo() and that's precisely what we pass root for - to skip those outside chroot jail. Those who don't want that can (and do) use d_path(). * __d_path() root argument becomes const. Everyone agrees, I hope. * apparmor does *NOT* try to use __d_path() or any of its variants when it sees that path->mnt is an internal vfsmount. In that case it's definitely not mounted anywhere and dentry_path() is exactly what we want there. Handling of sysctl()-triggered weirdness is moved to that place. * if apparmor is asked to do pathname relative to chroot jail and __d_path() tells it we it's not in that jail, the sucker just calls d_absolute_path() instead. That's the other remaining caller of __d_path(), BTW. * seq_path_root() does _NOT_ return -ENAMETOOLONG (it's stupid anyway - the normal seq_file logics will take care of growing the buffer and redoing the call of ->show() just fine). However, if it gets path not reachable from root, it returns SEQ_SKIP. The only caller adjusted (i.e. stopped ignoring the return value as it used to do). Reviewed-by: John Johansen <john.johansen@canonical.com> ACKed-by: John Johansen <john.johansen@canonical.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Cc: stable@vger.kernel.org
2011-12-05 21:43:34 +08:00
* @root: root vfsmnt/dentry
* @buffer: pointer to the end of the buffer
* @buflen: pointer to buffer length
*
* The function will first try to write out the pathname without taking any
* lock other than the RCU read lock to make sure that dentries won't go away.
* It only checks the sequence number of the global rename_lock as any change
* in the dentry's d_seq will be preceded by changes in the rename_lock
* sequence number. If the sequence number had been changed, it will restart
* the whole pathname back-tracing sequence again by taking the rename_lock.
* In this case, there is no need to take the RCU read lock as the recursive
* parent pointer references will keep the dentry chain alive as long as no
* rename operation is performed.
*/
fix apparmor dereferencing potentially freed dentry, sanitize __d_path() API __d_path() API is asking for trouble and in case of apparmor d_namespace_path() getting just that. The root cause is that when __d_path() misses the root it had been told to look for, it stores the location of the most remote ancestor in *root. Without grabbing references. Sure, at the moment of call it had been pinned down by what we have in *path. And if we raced with umount -l, we could have very well stopped at vfsmount/dentry that got freed as soon as prepend_path() dropped vfsmount_lock. It is safe to compare these pointers with pre-existing (and known to be still alive) vfsmount and dentry, as long as all we are asking is "is it the same address?". Dereferencing is not safe and apparmor ended up stepping into that. d_namespace_path() really wants to examine the place where we stopped, even if it's not connected to our namespace. As the result, it looked at ->d_sb->s_magic of a dentry that might've been already freed by that point. All other callers had been careful enough to avoid that, but it's really a bad interface - it invites that kind of trouble. The fix is fairly straightforward, even though it's bigger than I'd like: * prepend_path() root argument becomes const. * __d_path() is never called with NULL/NULL root. It was a kludge to start with. Instead, we have an explicit function - d_absolute_root(). Same as __d_path(), except that it doesn't get root passed and stops where it stops. apparmor and tomoyo are using it. * __d_path() returns NULL on path outside of root. The main caller is show_mountinfo() and that's precisely what we pass root for - to skip those outside chroot jail. Those who don't want that can (and do) use d_path(). * __d_path() root argument becomes const. Everyone agrees, I hope. * apparmor does *NOT* try to use __d_path() or any of its variants when it sees that path->mnt is an internal vfsmount. In that case it's definitely not mounted anywhere and dentry_path() is exactly what we want there. Handling of sysctl()-triggered weirdness is moved to that place. * if apparmor is asked to do pathname relative to chroot jail and __d_path() tells it we it's not in that jail, the sucker just calls d_absolute_path() instead. That's the other remaining caller of __d_path(), BTW. * seq_path_root() does _NOT_ return -ENAMETOOLONG (it's stupid anyway - the normal seq_file logics will take care of growing the buffer and redoing the call of ->show() just fine). However, if it gets path not reachable from root, it returns SEQ_SKIP. The only caller adjusted (i.e. stopped ignoring the return value as it used to do). Reviewed-by: John Johansen <john.johansen@canonical.com> ACKed-by: John Johansen <john.johansen@canonical.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Cc: stable@vger.kernel.org
2011-12-05 21:43:34 +08:00
static int prepend_path(const struct path *path,
const struct path *root,
char **buffer, int *buflen)
{
struct dentry *dentry;
struct vfsmount *vfsmnt;
struct mount *mnt;
int error = 0;
RCU'd vfsmounts * RCU-delayed freeing of vfsmounts * vfsmount_lock replaced with a seqlock (mount_lock) * sequence number from mount_lock is stored in nameidata->m_seq and used when we exit RCU mode * new vfsmount flag - MNT_SYNC_UMOUNT. Set by umount_tree() when its caller knows that vfsmount will have no surviving references. * synchronize_rcu() done between unlocking namespace_sem in namespace_unlock() and doing pending mntput(). * new helper: legitimize_mnt(mnt, seq). Checks the mount_lock sequence number against seq, then grabs reference to mnt. Then it rechecks mount_lock again to close the race and either returns success or drops the reference it has acquired. The subtle point is that in case of MNT_SYNC_UMOUNT we can simply decrement the refcount and sod off - aforementioned synchronize_rcu() makes sure that final mntput() won't come until we leave RCU mode. We need that, since we don't want to end up with some lazy pathwalk racing with umount() and stealing the final mntput() from it - caller of umount() may expect it to return only once the fs is shut down and we don't want to break that. In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do full-blown mntput() in case of mount_lock sequence number mismatch happening just as we'd grabbed the reference, but in those cases we won't be stealing the final mntput() from anything that would care. * mntput_no_expire() doesn't lock anything on the fast path now. Incidentally, SMP and UP cases are handled the same way - no ifdefs there. * normal pathname resolution does *not* do any writes to mount_lock. It does, of course, bump the refcounts of vfsmount and dentry in the very end, but that's it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-30 10:06:07 +08:00
unsigned seq, m_seq = 0;
dcache: Translating dentry into pathname without taking rename_lock When running the AIM7's short workload, Linus' lockref patch eliminated most of the spinlock contention. However, there were still some left: 8.46% reaim [kernel.kallsyms] [k] _raw_spin_lock |--42.21%-- d_path | proc_pid_readlink | SyS_readlinkat | SyS_readlink | system_call | __GI___readlink | |--40.97%-- sys_getcwd | system_call | __getcwd The big one here is the rename_lock (seqlock) contention in d_path() and the getcwd system call. This patch will eliminate the need to take the rename_lock while translating dentries into the full pathnames. The need to take the rename_lock is to make sure that no rename operation can be ongoing while the translation is in progress. However, only one thread can take the rename_lock thus blocking all the other threads that need it even though the translation process won't make any change to the dentries. This patch will replace the writer's write_seqlock/write_sequnlock sequence of the rename_lock of the callers of the prepend_path() and __dentry_path() functions with the reader's read_seqbegin/read_seqretry sequence within these 2 functions. As a result, the code will have to retry if one or more rename operations had been performed. In addition, RCU read lock will be taken during the translation process to make sure that no dentries will go away. To prevent live-lock from happening, the code will switch back to take the rename_lock if read_seqretry() fails for three times. To further reduce spinlock contention, this patch does not take the dentry's d_lock when copying the filename from the dentries. Instead, it treats the name pointer and length as unreliable and just copy the string byte-by-byte over until it hits a null byte or the end of string as specified by the length. This should avoid stepping into invalid memory address. The error cases are left to be handled by the sequence number check. The following code re-factoring are also made: 1. Move prepend('/') into prepend_name() to remove one conditional check. 2. Move the global root check in prepend_path() back to the top of the while loop. With this patch, the _raw_spin_lock will now account for only 1.2% of the total CPU cycles for the short workload. This patch also has the effect of reducing the effect of running perf on its profile since the perf command itself can be a heavy user of the d_path() function depending on the complexity of the workload. When taking the perf profile of the high-systime workload, the amount of spinlock contention contributed by running perf without this patch was about 16%. With this patch, the spinlock contention caused by the running of perf will go away and we will have a more accurate perf profile. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-10 00:18:13 +08:00
char *bptr;
int blen;
rcu_read_lock();
RCU'd vfsmounts * RCU-delayed freeing of vfsmounts * vfsmount_lock replaced with a seqlock (mount_lock) * sequence number from mount_lock is stored in nameidata->m_seq and used when we exit RCU mode * new vfsmount flag - MNT_SYNC_UMOUNT. Set by umount_tree() when its caller knows that vfsmount will have no surviving references. * synchronize_rcu() done between unlocking namespace_sem in namespace_unlock() and doing pending mntput(). * new helper: legitimize_mnt(mnt, seq). Checks the mount_lock sequence number against seq, then grabs reference to mnt. Then it rechecks mount_lock again to close the race and either returns success or drops the reference it has acquired. The subtle point is that in case of MNT_SYNC_UMOUNT we can simply decrement the refcount and sod off - aforementioned synchronize_rcu() makes sure that final mntput() won't come until we leave RCU mode. We need that, since we don't want to end up with some lazy pathwalk racing with umount() and stealing the final mntput() from it - caller of umount() may expect it to return only once the fs is shut down and we don't want to break that. In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do full-blown mntput() in case of mount_lock sequence number mismatch happening just as we'd grabbed the reference, but in those cases we won't be stealing the final mntput() from anything that would care. * mntput_no_expire() doesn't lock anything on the fast path now. Incidentally, SMP and UP cases are handled the same way - no ifdefs there. * normal pathname resolution does *not* do any writes to mount_lock. It does, of course, bump the refcounts of vfsmount and dentry in the very end, but that's it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-30 10:06:07 +08:00
restart_mnt:
read_seqbegin_or_lock(&mount_lock, &m_seq);
seq = 0;
rcu_read_lock();
dcache: Translating dentry into pathname without taking rename_lock When running the AIM7's short workload, Linus' lockref patch eliminated most of the spinlock contention. However, there were still some left: 8.46% reaim [kernel.kallsyms] [k] _raw_spin_lock |--42.21%-- d_path | proc_pid_readlink | SyS_readlinkat | SyS_readlink | system_call | __GI___readlink | |--40.97%-- sys_getcwd | system_call | __getcwd The big one here is the rename_lock (seqlock) contention in d_path() and the getcwd system call. This patch will eliminate the need to take the rename_lock while translating dentries into the full pathnames. The need to take the rename_lock is to make sure that no rename operation can be ongoing while the translation is in progress. However, only one thread can take the rename_lock thus blocking all the other threads that need it even though the translation process won't make any change to the dentries. This patch will replace the writer's write_seqlock/write_sequnlock sequence of the rename_lock of the callers of the prepend_path() and __dentry_path() functions with the reader's read_seqbegin/read_seqretry sequence within these 2 functions. As a result, the code will have to retry if one or more rename operations had been performed. In addition, RCU read lock will be taken during the translation process to make sure that no dentries will go away. To prevent live-lock from happening, the code will switch back to take the rename_lock if read_seqretry() fails for three times. To further reduce spinlock contention, this patch does not take the dentry's d_lock when copying the filename from the dentries. Instead, it treats the name pointer and length as unreliable and just copy the string byte-by-byte over until it hits a null byte or the end of string as specified by the length. This should avoid stepping into invalid memory address. The error cases are left to be handled by the sequence number check. The following code re-factoring are also made: 1. Move prepend('/') into prepend_name() to remove one conditional check. 2. Move the global root check in prepend_path() back to the top of the while loop. With this patch, the _raw_spin_lock will now account for only 1.2% of the total CPU cycles for the short workload. This patch also has the effect of reducing the effect of running perf on its profile since the perf command itself can be a heavy user of the d_path() function depending on the complexity of the workload. When taking the perf profile of the high-systime workload, the amount of spinlock contention contributed by running perf without this patch was about 16%. With this patch, the spinlock contention caused by the running of perf will go away and we will have a more accurate perf profile. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-10 00:18:13 +08:00
restart:
bptr = *buffer;
blen = *buflen;
RCU'd vfsmounts * RCU-delayed freeing of vfsmounts * vfsmount_lock replaced with a seqlock (mount_lock) * sequence number from mount_lock is stored in nameidata->m_seq and used when we exit RCU mode * new vfsmount flag - MNT_SYNC_UMOUNT. Set by umount_tree() when its caller knows that vfsmount will have no surviving references. * synchronize_rcu() done between unlocking namespace_sem in namespace_unlock() and doing pending mntput(). * new helper: legitimize_mnt(mnt, seq). Checks the mount_lock sequence number against seq, then grabs reference to mnt. Then it rechecks mount_lock again to close the race and either returns success or drops the reference it has acquired. The subtle point is that in case of MNT_SYNC_UMOUNT we can simply decrement the refcount and sod off - aforementioned synchronize_rcu() makes sure that final mntput() won't come until we leave RCU mode. We need that, since we don't want to end up with some lazy pathwalk racing with umount() and stealing the final mntput() from it - caller of umount() may expect it to return only once the fs is shut down and we don't want to break that. In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do full-blown mntput() in case of mount_lock sequence number mismatch happening just as we'd grabbed the reference, but in those cases we won't be stealing the final mntput() from anything that would care. * mntput_no_expire() doesn't lock anything on the fast path now. Incidentally, SMP and UP cases are handled the same way - no ifdefs there. * normal pathname resolution does *not* do any writes to mount_lock. It does, of course, bump the refcounts of vfsmount and dentry in the very end, but that's it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-30 10:06:07 +08:00
error = 0;
dentry = path->dentry;
vfsmnt = path->mnt;
mnt = real_mount(vfsmnt);
dcache: Translating dentry into pathname without taking rename_lock When running the AIM7's short workload, Linus' lockref patch eliminated most of the spinlock contention. However, there were still some left: 8.46% reaim [kernel.kallsyms] [k] _raw_spin_lock |--42.21%-- d_path | proc_pid_readlink | SyS_readlinkat | SyS_readlink | system_call | __GI___readlink | |--40.97%-- sys_getcwd | system_call | __getcwd The big one here is the rename_lock (seqlock) contention in d_path() and the getcwd system call. This patch will eliminate the need to take the rename_lock while translating dentries into the full pathnames. The need to take the rename_lock is to make sure that no rename operation can be ongoing while the translation is in progress. However, only one thread can take the rename_lock thus blocking all the other threads that need it even though the translation process won't make any change to the dentries. This patch will replace the writer's write_seqlock/write_sequnlock sequence of the rename_lock of the callers of the prepend_path() and __dentry_path() functions with the reader's read_seqbegin/read_seqretry sequence within these 2 functions. As a result, the code will have to retry if one or more rename operations had been performed. In addition, RCU read lock will be taken during the translation process to make sure that no dentries will go away. To prevent live-lock from happening, the code will switch back to take the rename_lock if read_seqretry() fails for three times. To further reduce spinlock contention, this patch does not take the dentry's d_lock when copying the filename from the dentries. Instead, it treats the name pointer and length as unreliable and just copy the string byte-by-byte over until it hits a null byte or the end of string as specified by the length. This should avoid stepping into invalid memory address. The error cases are left to be handled by the sequence number check. The following code re-factoring are also made: 1. Move prepend('/') into prepend_name() to remove one conditional check. 2. Move the global root check in prepend_path() back to the top of the while loop. With this patch, the _raw_spin_lock will now account for only 1.2% of the total CPU cycles for the short workload. This patch also has the effect of reducing the effect of running perf on its profile since the perf command itself can be a heavy user of the d_path() function depending on the complexity of the workload. When taking the perf profile of the high-systime workload, the amount of spinlock contention contributed by running perf without this patch was about 16%. With this patch, the spinlock contention caused by the running of perf will go away and we will have a more accurate perf profile. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-10 00:18:13 +08:00
read_seqbegin_or_lock(&rename_lock, &seq);
while (dentry != root->dentry || vfsmnt != root->mnt) {
struct dentry * parent;
if (dentry == vfsmnt->mnt_root || IS_ROOT(dentry)) {
RCU'd vfsmounts * RCU-delayed freeing of vfsmounts * vfsmount_lock replaced with a seqlock (mount_lock) * sequence number from mount_lock is stored in nameidata->m_seq and used when we exit RCU mode * new vfsmount flag - MNT_SYNC_UMOUNT. Set by umount_tree() when its caller knows that vfsmount will have no surviving references. * synchronize_rcu() done between unlocking namespace_sem in namespace_unlock() and doing pending mntput(). * new helper: legitimize_mnt(mnt, seq). Checks the mount_lock sequence number against seq, then grabs reference to mnt. Then it rechecks mount_lock again to close the race and either returns success or drops the reference it has acquired. The subtle point is that in case of MNT_SYNC_UMOUNT we can simply decrement the refcount and sod off - aforementioned synchronize_rcu() makes sure that final mntput() won't come until we leave RCU mode. We need that, since we don't want to end up with some lazy pathwalk racing with umount() and stealing the final mntput() from it - caller of umount() may expect it to return only once the fs is shut down and we don't want to break that. In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do full-blown mntput() in case of mount_lock sequence number mismatch happening just as we'd grabbed the reference, but in those cases we won't be stealing the final mntput() from anything that would care. * mntput_no_expire() doesn't lock anything on the fast path now. Incidentally, SMP and UP cases are handled the same way - no ifdefs there. * normal pathname resolution does *not* do any writes to mount_lock. It does, of course, bump the refcounts of vfsmount and dentry in the very end, but that's it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-30 10:06:07 +08:00
struct mount *parent = ACCESS_ONCE(mnt->mnt_parent);
/* Global root? */
RCU'd vfsmounts * RCU-delayed freeing of vfsmounts * vfsmount_lock replaced with a seqlock (mount_lock) * sequence number from mount_lock is stored in nameidata->m_seq and used when we exit RCU mode * new vfsmount flag - MNT_SYNC_UMOUNT. Set by umount_tree() when its caller knows that vfsmount will have no surviving references. * synchronize_rcu() done between unlocking namespace_sem in namespace_unlock() and doing pending mntput(). * new helper: legitimize_mnt(mnt, seq). Checks the mount_lock sequence number against seq, then grabs reference to mnt. Then it rechecks mount_lock again to close the race and either returns success or drops the reference it has acquired. The subtle point is that in case of MNT_SYNC_UMOUNT we can simply decrement the refcount and sod off - aforementioned synchronize_rcu() makes sure that final mntput() won't come until we leave RCU mode. We need that, since we don't want to end up with some lazy pathwalk racing with umount() and stealing the final mntput() from it - caller of umount() may expect it to return only once the fs is shut down and we don't want to break that. In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do full-blown mntput() in case of mount_lock sequence number mismatch happening just as we'd grabbed the reference, but in those cases we won't be stealing the final mntput() from anything that would care. * mntput_no_expire() doesn't lock anything on the fast path now. Incidentally, SMP and UP cases are handled the same way - no ifdefs there. * normal pathname resolution does *not* do any writes to mount_lock. It does, of course, bump the refcounts of vfsmount and dentry in the very end, but that's it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-30 10:06:07 +08:00
if (mnt != parent) {
dentry = ACCESS_ONCE(mnt->mnt_mountpoint);
mnt = parent;
dcache: Translating dentry into pathname without taking rename_lock When running the AIM7's short workload, Linus' lockref patch eliminated most of the spinlock contention. However, there were still some left: 8.46% reaim [kernel.kallsyms] [k] _raw_spin_lock |--42.21%-- d_path | proc_pid_readlink | SyS_readlinkat | SyS_readlink | system_call | __GI___readlink | |--40.97%-- sys_getcwd | system_call | __getcwd The big one here is the rename_lock (seqlock) contention in d_path() and the getcwd system call. This patch will eliminate the need to take the rename_lock while translating dentries into the full pathnames. The need to take the rename_lock is to make sure that no rename operation can be ongoing while the translation is in progress. However, only one thread can take the rename_lock thus blocking all the other threads that need it even though the translation process won't make any change to the dentries. This patch will replace the writer's write_seqlock/write_sequnlock sequence of the rename_lock of the callers of the prepend_path() and __dentry_path() functions with the reader's read_seqbegin/read_seqretry sequence within these 2 functions. As a result, the code will have to retry if one or more rename operations had been performed. In addition, RCU read lock will be taken during the translation process to make sure that no dentries will go away. To prevent live-lock from happening, the code will switch back to take the rename_lock if read_seqretry() fails for three times. To further reduce spinlock contention, this patch does not take the dentry's d_lock when copying the filename from the dentries. Instead, it treats the name pointer and length as unreliable and just copy the string byte-by-byte over until it hits a null byte or the end of string as specified by the length. This should avoid stepping into invalid memory address. The error cases are left to be handled by the sequence number check. The following code re-factoring are also made: 1. Move prepend('/') into prepend_name() to remove one conditional check. 2. Move the global root check in prepend_path() back to the top of the while loop. With this patch, the _raw_spin_lock will now account for only 1.2% of the total CPU cycles for the short workload. This patch also has the effect of reducing the effect of running perf on its profile since the perf command itself can be a heavy user of the d_path() function depending on the complexity of the workload. When taking the perf profile of the high-systime workload, the amount of spinlock contention contributed by running perf without this patch was about 16%. With this patch, the spinlock contention caused by the running of perf will go away and we will have a more accurate perf profile. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-10 00:18:13 +08:00
vfsmnt = &mnt->mnt;
continue;
}
/*
* Filesystems needing to implement special "root names"
* should do so with ->d_dname()
*/
if (IS_ROOT(dentry) &&
(dentry->d_name.len != 1 ||
dentry->d_name.name[0] != '/')) {
WARN(1, "Root dentry has weird name <%.*s>\n",
(int) dentry->d_name.len,
dentry->d_name.name);
}
if (!error)
error = is_mounted(vfsmnt) ? 1 : 2;
break;
}
parent = dentry->d_parent;
prefetch(parent);
dcache: Translating dentry into pathname without taking rename_lock When running the AIM7's short workload, Linus' lockref patch eliminated most of the spinlock contention. However, there were still some left: 8.46% reaim [kernel.kallsyms] [k] _raw_spin_lock |--42.21%-- d_path | proc_pid_readlink | SyS_readlinkat | SyS_readlink | system_call | __GI___readlink | |--40.97%-- sys_getcwd | system_call | __getcwd The big one here is the rename_lock (seqlock) contention in d_path() and the getcwd system call. This patch will eliminate the need to take the rename_lock while translating dentries into the full pathnames. The need to take the rename_lock is to make sure that no rename operation can be ongoing while the translation is in progress. However, only one thread can take the rename_lock thus blocking all the other threads that need it even though the translation process won't make any change to the dentries. This patch will replace the writer's write_seqlock/write_sequnlock sequence of the rename_lock of the callers of the prepend_path() and __dentry_path() functions with the reader's read_seqbegin/read_seqretry sequence within these 2 functions. As a result, the code will have to retry if one or more rename operations had been performed. In addition, RCU read lock will be taken during the translation process to make sure that no dentries will go away. To prevent live-lock from happening, the code will switch back to take the rename_lock if read_seqretry() fails for three times. To further reduce spinlock contention, this patch does not take the dentry's d_lock when copying the filename from the dentries. Instead, it treats the name pointer and length as unreliable and just copy the string byte-by-byte over until it hits a null byte or the end of string as specified by the length. This should avoid stepping into invalid memory address. The error cases are left to be handled by the sequence number check. The following code re-factoring are also made: 1. Move prepend('/') into prepend_name() to remove one conditional check. 2. Move the global root check in prepend_path() back to the top of the while loop. With this patch, the _raw_spin_lock will now account for only 1.2% of the total CPU cycles for the short workload. This patch also has the effect of reducing the effect of running perf on its profile since the perf command itself can be a heavy user of the d_path() function depending on the complexity of the workload. When taking the perf profile of the high-systime workload, the amount of spinlock contention contributed by running perf without this patch was about 16%. With this patch, the spinlock contention caused by the running of perf will go away and we will have a more accurate perf profile. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-10 00:18:13 +08:00
error = prepend_name(&bptr, &blen, &dentry->d_name);
if (error)
break;
dentry = parent;
}
if (!(seq & 1))
rcu_read_unlock();
if (need_seqretry(&rename_lock, seq)) {
seq = 1;
dcache: Translating dentry into pathname without taking rename_lock When running the AIM7's short workload, Linus' lockref patch eliminated most of the spinlock contention. However, there were still some left: 8.46% reaim [kernel.kallsyms] [k] _raw_spin_lock |--42.21%-- d_path | proc_pid_readlink | SyS_readlinkat | SyS_readlink | system_call | __GI___readlink | |--40.97%-- sys_getcwd | system_call | __getcwd The big one here is the rename_lock (seqlock) contention in d_path() and the getcwd system call. This patch will eliminate the need to take the rename_lock while translating dentries into the full pathnames. The need to take the rename_lock is to make sure that no rename operation can be ongoing while the translation is in progress. However, only one thread can take the rename_lock thus blocking all the other threads that need it even though the translation process won't make any change to the dentries. This patch will replace the writer's write_seqlock/write_sequnlock sequence of the rename_lock of the callers of the prepend_path() and __dentry_path() functions with the reader's read_seqbegin/read_seqretry sequence within these 2 functions. As a result, the code will have to retry if one or more rename operations had been performed. In addition, RCU read lock will be taken during the translation process to make sure that no dentries will go away. To prevent live-lock from happening, the code will switch back to take the rename_lock if read_seqretry() fails for three times. To further reduce spinlock contention, this patch does not take the dentry's d_lock when copying the filename from the dentries. Instead, it treats the name pointer and length as unreliable and just copy the string byte-by-byte over until it hits a null byte or the end of string as specified by the length. This should avoid stepping into invalid memory address. The error cases are left to be handled by the sequence number check. The following code re-factoring are also made: 1. Move prepend('/') into prepend_name() to remove one conditional check. 2. Move the global root check in prepend_path() back to the top of the while loop. With this patch, the _raw_spin_lock will now account for only 1.2% of the total CPU cycles for the short workload. This patch also has the effect of reducing the effect of running perf on its profile since the perf command itself can be a heavy user of the d_path() function depending on the complexity of the workload. When taking the perf profile of the high-systime workload, the amount of spinlock contention contributed by running perf without this patch was about 16%. With this patch, the spinlock contention caused by the running of perf will go away and we will have a more accurate perf profile. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-10 00:18:13 +08:00
goto restart;
}
done_seqretry(&rename_lock, seq);
if (!(m_seq & 1))
rcu_read_unlock();
RCU'd vfsmounts * RCU-delayed freeing of vfsmounts * vfsmount_lock replaced with a seqlock (mount_lock) * sequence number from mount_lock is stored in nameidata->m_seq and used when we exit RCU mode * new vfsmount flag - MNT_SYNC_UMOUNT. Set by umount_tree() when its caller knows that vfsmount will have no surviving references. * synchronize_rcu() done between unlocking namespace_sem in namespace_unlock() and doing pending mntput(). * new helper: legitimize_mnt(mnt, seq). Checks the mount_lock sequence number against seq, then grabs reference to mnt. Then it rechecks mount_lock again to close the race and either returns success or drops the reference it has acquired. The subtle point is that in case of MNT_SYNC_UMOUNT we can simply decrement the refcount and sod off - aforementioned synchronize_rcu() makes sure that final mntput() won't come until we leave RCU mode. We need that, since we don't want to end up with some lazy pathwalk racing with umount() and stealing the final mntput() from it - caller of umount() may expect it to return only once the fs is shut down and we don't want to break that. In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do full-blown mntput() in case of mount_lock sequence number mismatch happening just as we'd grabbed the reference, but in those cases we won't be stealing the final mntput() from anything that would care. * mntput_no_expire() doesn't lock anything on the fast path now. Incidentally, SMP and UP cases are handled the same way - no ifdefs there. * normal pathname resolution does *not* do any writes to mount_lock. It does, of course, bump the refcounts of vfsmount and dentry in the very end, but that's it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-30 10:06:07 +08:00
if (need_seqretry(&mount_lock, m_seq)) {
m_seq = 1;
goto restart_mnt;
}
done_seqretry(&mount_lock, m_seq);
dcache: Translating dentry into pathname without taking rename_lock When running the AIM7's short workload, Linus' lockref patch eliminated most of the spinlock contention. However, there were still some left: 8.46% reaim [kernel.kallsyms] [k] _raw_spin_lock |--42.21%-- d_path | proc_pid_readlink | SyS_readlinkat | SyS_readlink | system_call | __GI___readlink | |--40.97%-- sys_getcwd | system_call | __getcwd The big one here is the rename_lock (seqlock) contention in d_path() and the getcwd system call. This patch will eliminate the need to take the rename_lock while translating dentries into the full pathnames. The need to take the rename_lock is to make sure that no rename operation can be ongoing while the translation is in progress. However, only one thread can take the rename_lock thus blocking all the other threads that need it even though the translation process won't make any change to the dentries. This patch will replace the writer's write_seqlock/write_sequnlock sequence of the rename_lock of the callers of the prepend_path() and __dentry_path() functions with the reader's read_seqbegin/read_seqretry sequence within these 2 functions. As a result, the code will have to retry if one or more rename operations had been performed. In addition, RCU read lock will be taken during the translation process to make sure that no dentries will go away. To prevent live-lock from happening, the code will switch back to take the rename_lock if read_seqretry() fails for three times. To further reduce spinlock contention, this patch does not take the dentry's d_lock when copying the filename from the dentries. Instead, it treats the name pointer and length as unreliable and just copy the string byte-by-byte over until it hits a null byte or the end of string as specified by the length. This should avoid stepping into invalid memory address. The error cases are left to be handled by the sequence number check. The following code re-factoring are also made: 1. Move prepend('/') into prepend_name() to remove one conditional check. 2. Move the global root check in prepend_path() back to the top of the while loop. With this patch, the _raw_spin_lock will now account for only 1.2% of the total CPU cycles for the short workload. This patch also has the effect of reducing the effect of running perf on its profile since the perf command itself can be a heavy user of the d_path() function depending on the complexity of the workload. When taking the perf profile of the high-systime workload, the amount of spinlock contention contributed by running perf without this patch was about 16%. With this patch, the spinlock contention caused by the running of perf will go away and we will have a more accurate perf profile. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-10 00:18:13 +08:00
if (error >= 0 && bptr == *buffer) {
if (--blen < 0)
error = -ENAMETOOLONG;
else
*--bptr = '/';
}
*buffer = bptr;
*buflen = blen;
return error;
}
/**
* __d_path - return the path of a dentry
* @path: the dentry/vfsmount to report
fix apparmor dereferencing potentially freed dentry, sanitize __d_path() API __d_path() API is asking for trouble and in case of apparmor d_namespace_path() getting just that. The root cause is that when __d_path() misses the root it had been told to look for, it stores the location of the most remote ancestor in *root. Without grabbing references. Sure, at the moment of call it had been pinned down by what we have in *path. And if we raced with umount -l, we could have very well stopped at vfsmount/dentry that got freed as soon as prepend_path() dropped vfsmount_lock. It is safe to compare these pointers with pre-existing (and known to be still alive) vfsmount and dentry, as long as all we are asking is "is it the same address?". Dereferencing is not safe and apparmor ended up stepping into that. d_namespace_path() really wants to examine the place where we stopped, even if it's not connected to our namespace. As the result, it looked at ->d_sb->s_magic of a dentry that might've been already freed by that point. All other callers had been careful enough to avoid that, but it's really a bad interface - it invites that kind of trouble. The fix is fairly straightforward, even though it's bigger than I'd like: * prepend_path() root argument becomes const. * __d_path() is never called with NULL/NULL root. It was a kludge to start with. Instead, we have an explicit function - d_absolute_root(). Same as __d_path(), except that it doesn't get root passed and stops where it stops. apparmor and tomoyo are using it. * __d_path() returns NULL on path outside of root. The main caller is show_mountinfo() and that's precisely what we pass root for - to skip those outside chroot jail. Those who don't want that can (and do) use d_path(). * __d_path() root argument becomes const. Everyone agrees, I hope. * apparmor does *NOT* try to use __d_path() or any of its variants when it sees that path->mnt is an internal vfsmount. In that case it's definitely not mounted anywhere and dentry_path() is exactly what we want there. Handling of sysctl()-triggered weirdness is moved to that place. * if apparmor is asked to do pathname relative to chroot jail and __d_path() tells it we it's not in that jail, the sucker just calls d_absolute_path() instead. That's the other remaining caller of __d_path(), BTW. * seq_path_root() does _NOT_ return -ENAMETOOLONG (it's stupid anyway - the normal seq_file logics will take care of growing the buffer and redoing the call of ->show() just fine). However, if it gets path not reachable from root, it returns SEQ_SKIP. The only caller adjusted (i.e. stopped ignoring the return value as it used to do). Reviewed-by: John Johansen <john.johansen@canonical.com> ACKed-by: John Johansen <john.johansen@canonical.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Cc: stable@vger.kernel.org
2011-12-05 21:43:34 +08:00
* @root: root vfsmnt/dentry
* @buf: buffer to return value in
* @buflen: buffer length
*
* Convert a dentry into an ASCII path name.
*
* Returns a pointer into the buffer or an error code if the
* path was too long.
*
* "buflen" should be positive.
*
fix apparmor dereferencing potentially freed dentry, sanitize __d_path() API __d_path() API is asking for trouble and in case of apparmor d_namespace_path() getting just that. The root cause is that when __d_path() misses the root it had been told to look for, it stores the location of the most remote ancestor in *root. Without grabbing references. Sure, at the moment of call it had been pinned down by what we have in *path. And if we raced with umount -l, we could have very well stopped at vfsmount/dentry that got freed as soon as prepend_path() dropped vfsmount_lock. It is safe to compare these pointers with pre-existing (and known to be still alive) vfsmount and dentry, as long as all we are asking is "is it the same address?". Dereferencing is not safe and apparmor ended up stepping into that. d_namespace_path() really wants to examine the place where we stopped, even if it's not connected to our namespace. As the result, it looked at ->d_sb->s_magic of a dentry that might've been already freed by that point. All other callers had been careful enough to avoid that, but it's really a bad interface - it invites that kind of trouble. The fix is fairly straightforward, even though it's bigger than I'd like: * prepend_path() root argument becomes const. * __d_path() is never called with NULL/NULL root. It was a kludge to start with. Instead, we have an explicit function - d_absolute_root(). Same as __d_path(), except that it doesn't get root passed and stops where it stops. apparmor and tomoyo are using it. * __d_path() returns NULL on path outside of root. The main caller is show_mountinfo() and that's precisely what we pass root for - to skip those outside chroot jail. Those who don't want that can (and do) use d_path(). * __d_path() root argument becomes const. Everyone agrees, I hope. * apparmor does *NOT* try to use __d_path() or any of its variants when it sees that path->mnt is an internal vfsmount. In that case it's definitely not mounted anywhere and dentry_path() is exactly what we want there. Handling of sysctl()-triggered weirdness is moved to that place. * if apparmor is asked to do pathname relative to chroot jail and __d_path() tells it we it's not in that jail, the sucker just calls d_absolute_path() instead. That's the other remaining caller of __d_path(), BTW. * seq_path_root() does _NOT_ return -ENAMETOOLONG (it's stupid anyway - the normal seq_file logics will take care of growing the buffer and redoing the call of ->show() just fine). However, if it gets path not reachable from root, it returns SEQ_SKIP. The only caller adjusted (i.e. stopped ignoring the return value as it used to do). Reviewed-by: John Johansen <john.johansen@canonical.com> ACKed-by: John Johansen <john.johansen@canonical.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Cc: stable@vger.kernel.org
2011-12-05 21:43:34 +08:00
* If the path is not reachable from the supplied root, return %NULL.
*/
fix apparmor dereferencing potentially freed dentry, sanitize __d_path() API __d_path() API is asking for trouble and in case of apparmor d_namespace_path() getting just that. The root cause is that when __d_path() misses the root it had been told to look for, it stores the location of the most remote ancestor in *root. Without grabbing references. Sure, at the moment of call it had been pinned down by what we have in *path. And if we raced with umount -l, we could have very well stopped at vfsmount/dentry that got freed as soon as prepend_path() dropped vfsmount_lock. It is safe to compare these pointers with pre-existing (and known to be still alive) vfsmount and dentry, as long as all we are asking is "is it the same address?". Dereferencing is not safe and apparmor ended up stepping into that. d_namespace_path() really wants to examine the place where we stopped, even if it's not connected to our namespace. As the result, it looked at ->d_sb->s_magic of a dentry that might've been already freed by that point. All other callers had been careful enough to avoid that, but it's really a bad interface - it invites that kind of trouble. The fix is fairly straightforward, even though it's bigger than I'd like: * prepend_path() root argument becomes const. * __d_path() is never called with NULL/NULL root. It was a kludge to start with. Instead, we have an explicit function - d_absolute_root(). Same as __d_path(), except that it doesn't get root passed and stops where it stops. apparmor and tomoyo are using it. * __d_path() returns NULL on path outside of root. The main caller is show_mountinfo() and that's precisely what we pass root for - to skip those outside chroot jail. Those who don't want that can (and do) use d_path(). * __d_path() root argument becomes const. Everyone agrees, I hope. * apparmor does *NOT* try to use __d_path() or any of its variants when it sees that path->mnt is an internal vfsmount. In that case it's definitely not mounted anywhere and dentry_path() is exactly what we want there. Handling of sysctl()-triggered weirdness is moved to that place. * if apparmor is asked to do pathname relative to chroot jail and __d_path() tells it we it's not in that jail, the sucker just calls d_absolute_path() instead. That's the other remaining caller of __d_path(), BTW. * seq_path_root() does _NOT_ return -ENAMETOOLONG (it's stupid anyway - the normal seq_file logics will take care of growing the buffer and redoing the call of ->show() just fine). However, if it gets path not reachable from root, it returns SEQ_SKIP. The only caller adjusted (i.e. stopped ignoring the return value as it used to do). Reviewed-by: John Johansen <john.johansen@canonical.com> ACKed-by: John Johansen <john.johansen@canonical.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Cc: stable@vger.kernel.org
2011-12-05 21:43:34 +08:00
char *__d_path(const struct path *path,
const struct path *root,
char *buf, int buflen)
{
char *res = buf + buflen;
int error;
prepend(&res, &buflen, "\0", 1);
error = prepend_path(path, root, &res, &buflen);
fix apparmor dereferencing potentially freed dentry, sanitize __d_path() API __d_path() API is asking for trouble and in case of apparmor d_namespace_path() getting just that. The root cause is that when __d_path() misses the root it had been told to look for, it stores the location of the most remote ancestor in *root. Without grabbing references. Sure, at the moment of call it had been pinned down by what we have in *path. And if we raced with umount -l, we could have very well stopped at vfsmount/dentry that got freed as soon as prepend_path() dropped vfsmount_lock. It is safe to compare these pointers with pre-existing (and known to be still alive) vfsmount and dentry, as long as all we are asking is "is it the same address?". Dereferencing is not safe and apparmor ended up stepping into that. d_namespace_path() really wants to examine the place where we stopped, even if it's not connected to our namespace. As the result, it looked at ->d_sb->s_magic of a dentry that might've been already freed by that point. All other callers had been careful enough to avoid that, but it's really a bad interface - it invites that kind of trouble. The fix is fairly straightforward, even though it's bigger than I'd like: * prepend_path() root argument becomes const. * __d_path() is never called with NULL/NULL root. It was a kludge to start with. Instead, we have an explicit function - d_absolute_root(). Same as __d_path(), except that it doesn't get root passed and stops where it stops. apparmor and tomoyo are using it. * __d_path() returns NULL on path outside of root. The main caller is show_mountinfo() and that's precisely what we pass root for - to skip those outside chroot jail. Those who don't want that can (and do) use d_path(). * __d_path() root argument becomes const. Everyone agrees, I hope. * apparmor does *NOT* try to use __d_path() or any of its variants when it sees that path->mnt is an internal vfsmount. In that case it's definitely not mounted anywhere and dentry_path() is exactly what we want there. Handling of sysctl()-triggered weirdness is moved to that place. * if apparmor is asked to do pathname relative to chroot jail and __d_path() tells it we it's not in that jail, the sucker just calls d_absolute_path() instead. That's the other remaining caller of __d_path(), BTW. * seq_path_root() does _NOT_ return -ENAMETOOLONG (it's stupid anyway - the normal seq_file logics will take care of growing the buffer and redoing the call of ->show() just fine). However, if it gets path not reachable from root, it returns SEQ_SKIP. The only caller adjusted (i.e. stopped ignoring the return value as it used to do). Reviewed-by: John Johansen <john.johansen@canonical.com> ACKed-by: John Johansen <john.johansen@canonical.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Cc: stable@vger.kernel.org
2011-12-05 21:43:34 +08:00
if (error < 0)
return ERR_PTR(error);
if (error > 0)
return NULL;
return res;
}
char *d_absolute_path(const struct path *path,
char *buf, int buflen)
{
struct path root = {};
char *res = buf + buflen;
int error;
prepend(&res, &buflen, "\0", 1);
error = prepend_path(path, &root, &res, &buflen);
if (error > 1)
error = -EINVAL;
if (error < 0)
return ERR_PTR(error);
return res;
}
/*
* same as __d_path but appends "(deleted)" for unlinked files.
*/
fix apparmor dereferencing potentially freed dentry, sanitize __d_path() API __d_path() API is asking for trouble and in case of apparmor d_namespace_path() getting just that. The root cause is that when __d_path() misses the root it had been told to look for, it stores the location of the most remote ancestor in *root. Without grabbing references. Sure, at the moment of call it had been pinned down by what we have in *path. And if we raced with umount -l, we could have very well stopped at vfsmount/dentry that got freed as soon as prepend_path() dropped vfsmount_lock. It is safe to compare these pointers with pre-existing (and known to be still alive) vfsmount and dentry, as long as all we are asking is "is it the same address?". Dereferencing is not safe and apparmor ended up stepping into that. d_namespace_path() really wants to examine the place where we stopped, even if it's not connected to our namespace. As the result, it looked at ->d_sb->s_magic of a dentry that might've been already freed by that point. All other callers had been careful enough to avoid that, but it's really a bad interface - it invites that kind of trouble. The fix is fairly straightforward, even though it's bigger than I'd like: * prepend_path() root argument becomes const. * __d_path() is never called with NULL/NULL root. It was a kludge to start with. Instead, we have an explicit function - d_absolute_root(). Same as __d_path(), except that it doesn't get root passed and stops where it stops. apparmor and tomoyo are using it. * __d_path() returns NULL on path outside of root. The main caller is show_mountinfo() and that's precisely what we pass root for - to skip those outside chroot jail. Those who don't want that can (and do) use d_path(). * __d_path() root argument becomes const. Everyone agrees, I hope. * apparmor does *NOT* try to use __d_path() or any of its variants when it sees that path->mnt is an internal vfsmount. In that case it's definitely not mounted anywhere and dentry_path() is exactly what we want there. Handling of sysctl()-triggered weirdness is moved to that place. * if apparmor is asked to do pathname relative to chroot jail and __d_path() tells it we it's not in that jail, the sucker just calls d_absolute_path() instead. That's the other remaining caller of __d_path(), BTW. * seq_path_root() does _NOT_ return -ENAMETOOLONG (it's stupid anyway - the normal seq_file logics will take care of growing the buffer and redoing the call of ->show() just fine). However, if it gets path not reachable from root, it returns SEQ_SKIP. The only caller adjusted (i.e. stopped ignoring the return value as it used to do). Reviewed-by: John Johansen <john.johansen@canonical.com> ACKed-by: John Johansen <john.johansen@canonical.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Cc: stable@vger.kernel.org
2011-12-05 21:43:34 +08:00
static int path_with_deleted(const struct path *path,
const struct path *root,
char **buf, int *buflen)
{
prepend(buf, buflen, "\0", 1);
if (d_unlinked(path->dentry)) {
int error = prepend(buf, buflen, " (deleted)", 10);
if (error)
return error;
}
return prepend_path(path, root, buf, buflen);
}
static int prepend_unreachable(char **buffer, int *buflen)
{
return prepend(buffer, buflen, "(unreachable)", 13);
}
static void get_fs_root_rcu(struct fs_struct *fs, struct path *root)
{
unsigned seq;
do {
seq = read_seqcount_begin(&fs->seq);
*root = fs->root;
} while (read_seqcount_retry(&fs->seq, seq));
}
/**
* d_path - return the path of a dentry
* @path: path to report
* @buf: buffer to return value in
* @buflen: buffer length
*
* Convert a dentry into an ASCII path name. If the entry has been deleted
* the string " (deleted)" is appended. Note that this is ambiguous.
*
* Returns a pointer into the buffer or an error code if the path was
* too long. Note: Callers should use the returned pointer, not the passed
* in buffer, to use the name! The implementation often starts at an offset
* into the buffer, and may leave 0 bytes at the start.
*
* "buflen" should be positive.
*/
char *d_path(const struct path *path, char *buf, int buflen)
{
char *res = buf + buflen;
struct path root;
int error;
/*
* We have various synthetic filesystems that never get mounted. On
* these filesystems dentries are never used for lookup purposes, and
* thus don't need to be hashed. They also don't need a name until a
* user wants to identify the object in /proc/pid/fd/. The little hack
* below allows us to generate a name for these objects on demand:
2013-11-09 08:31:29 +08:00
*
* Some pseudo inodes are mountable. When they are mounted
* path->dentry == path->mnt->mnt_root. In that case don't call d_dname
* and instead have d_path return the mounted path.
*/
2013-11-09 08:31:29 +08:00
if (path->dentry->d_op && path->dentry->d_op->d_dname &&
(!IS_ROOT(path->dentry) || path->dentry != path->mnt->mnt_root))
return path->dentry->d_op->d_dname(path->dentry, buf, buflen);
rcu_read_lock();
get_fs_root_rcu(current->fs, &root);
fix apparmor dereferencing potentially freed dentry, sanitize __d_path() API __d_path() API is asking for trouble and in case of apparmor d_namespace_path() getting just that. The root cause is that when __d_path() misses the root it had been told to look for, it stores the location of the most remote ancestor in *root. Without grabbing references. Sure, at the moment of call it had been pinned down by what we have in *path. And if we raced with umount -l, we could have very well stopped at vfsmount/dentry that got freed as soon as prepend_path() dropped vfsmount_lock. It is safe to compare these pointers with pre-existing (and known to be still alive) vfsmount and dentry, as long as all we are asking is "is it the same address?". Dereferencing is not safe and apparmor ended up stepping into that. d_namespace_path() really wants to examine the place where we stopped, even if it's not connected to our namespace. As the result, it looked at ->d_sb->s_magic of a dentry that might've been already freed by that point. All other callers had been careful enough to avoid that, but it's really a bad interface - it invites that kind of trouble. The fix is fairly straightforward, even though it's bigger than I'd like: * prepend_path() root argument becomes const. * __d_path() is never called with NULL/NULL root. It was a kludge to start with. Instead, we have an explicit function - d_absolute_root(). Same as __d_path(), except that it doesn't get root passed and stops where it stops. apparmor and tomoyo are using it. * __d_path() returns NULL on path outside of root. The main caller is show_mountinfo() and that's precisely what we pass root for - to skip those outside chroot jail. Those who don't want that can (and do) use d_path(). * __d_path() root argument becomes const. Everyone agrees, I hope. * apparmor does *NOT* try to use __d_path() or any of its variants when it sees that path->mnt is an internal vfsmount. In that case it's definitely not mounted anywhere and dentry_path() is exactly what we want there. Handling of sysctl()-triggered weirdness is moved to that place. * if apparmor is asked to do pathname relative to chroot jail and __d_path() tells it we it's not in that jail, the sucker just calls d_absolute_path() instead. That's the other remaining caller of __d_path(), BTW. * seq_path_root() does _NOT_ return -ENAMETOOLONG (it's stupid anyway - the normal seq_file logics will take care of growing the buffer and redoing the call of ->show() just fine). However, if it gets path not reachable from root, it returns SEQ_SKIP. The only caller adjusted (i.e. stopped ignoring the return value as it used to do). Reviewed-by: John Johansen <john.johansen@canonical.com> ACKed-by: John Johansen <john.johansen@canonical.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Cc: stable@vger.kernel.org
2011-12-05 21:43:34 +08:00
error = path_with_deleted(path, &root, &res, &buflen);
rcu_read_unlock();
fix apparmor dereferencing potentially freed dentry, sanitize __d_path() API __d_path() API is asking for trouble and in case of apparmor d_namespace_path() getting just that. The root cause is that when __d_path() misses the root it had been told to look for, it stores the location of the most remote ancestor in *root. Without grabbing references. Sure, at the moment of call it had been pinned down by what we have in *path. And if we raced with umount -l, we could have very well stopped at vfsmount/dentry that got freed as soon as prepend_path() dropped vfsmount_lock. It is safe to compare these pointers with pre-existing (and known to be still alive) vfsmount and dentry, as long as all we are asking is "is it the same address?". Dereferencing is not safe and apparmor ended up stepping into that. d_namespace_path() really wants to examine the place where we stopped, even if it's not connected to our namespace. As the result, it looked at ->d_sb->s_magic of a dentry that might've been already freed by that point. All other callers had been careful enough to avoid that, but it's really a bad interface - it invites that kind of trouble. The fix is fairly straightforward, even though it's bigger than I'd like: * prepend_path() root argument becomes const. * __d_path() is never called with NULL/NULL root. It was a kludge to start with. Instead, we have an explicit function - d_absolute_root(). Same as __d_path(), except that it doesn't get root passed and stops where it stops. apparmor and tomoyo are using it. * __d_path() returns NULL on path outside of root. The main caller is show_mountinfo() and that's precisely what we pass root for - to skip those outside chroot jail. Those who don't want that can (and do) use d_path(). * __d_path() root argument becomes const. Everyone agrees, I hope. * apparmor does *NOT* try to use __d_path() or any of its variants when it sees that path->mnt is an internal vfsmount. In that case it's definitely not mounted anywhere and dentry_path() is exactly what we want there. Handling of sysctl()-triggered weirdness is moved to that place. * if apparmor is asked to do pathname relative to chroot jail and __d_path() tells it we it's not in that jail, the sucker just calls d_absolute_path() instead. That's the other remaining caller of __d_path(), BTW. * seq_path_root() does _NOT_ return -ENAMETOOLONG (it's stupid anyway - the normal seq_file logics will take care of growing the buffer and redoing the call of ->show() just fine). However, if it gets path not reachable from root, it returns SEQ_SKIP. The only caller adjusted (i.e. stopped ignoring the return value as it used to do). Reviewed-by: John Johansen <john.johansen@canonical.com> ACKed-by: John Johansen <john.johansen@canonical.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Cc: stable@vger.kernel.org
2011-12-05 21:43:34 +08:00
if (error < 0)
res = ERR_PTR(error);
return res;
}
EXPORT_SYMBOL(d_path);
/*
* Helper function for dentry_operations.d_dname() members
*/
char *dynamic_dname(struct dentry *dentry, char *buffer, int buflen,
const char *fmt, ...)
{
va_list args;
char temp[64];
int sz;
va_start(args, fmt);
sz = vsnprintf(temp, sizeof(temp), fmt, args) + 1;
va_end(args);
if (sz > sizeof(temp) || sz > buflen)
return ERR_PTR(-ENAMETOOLONG);
buffer += buflen - sz;
return memcpy(buffer, temp, sz);
}
char *simple_dname(struct dentry *dentry, char *buffer, int buflen)
{
char *end = buffer + buflen;
/* these dentries are never renamed, so d_lock is not needed */
if (prepend(&end, &buflen, " (deleted)", 11) ||
dcache: Translating dentry into pathname without taking rename_lock When running the AIM7's short workload, Linus' lockref patch eliminated most of the spinlock contention. However, there were still some left: 8.46% reaim [kernel.kallsyms] [k] _raw_spin_lock |--42.21%-- d_path | proc_pid_readlink | SyS_readlinkat | SyS_readlink | system_call | __GI___readlink | |--40.97%-- sys_getcwd | system_call | __getcwd The big one here is the rename_lock (seqlock) contention in d_path() and the getcwd system call. This patch will eliminate the need to take the rename_lock while translating dentries into the full pathnames. The need to take the rename_lock is to make sure that no rename operation can be ongoing while the translation is in progress. However, only one thread can take the rename_lock thus blocking all the other threads that need it even though the translation process won't make any change to the dentries. This patch will replace the writer's write_seqlock/write_sequnlock sequence of the rename_lock of the callers of the prepend_path() and __dentry_path() functions with the reader's read_seqbegin/read_seqretry sequence within these 2 functions. As a result, the code will have to retry if one or more rename operations had been performed. In addition, RCU read lock will be taken during the translation process to make sure that no dentries will go away. To prevent live-lock from happening, the code will switch back to take the rename_lock if read_seqretry() fails for three times. To further reduce spinlock contention, this patch does not take the dentry's d_lock when copying the filename from the dentries. Instead, it treats the name pointer and length as unreliable and just copy the string byte-by-byte over until it hits a null byte or the end of string as specified by the length. This should avoid stepping into invalid memory address. The error cases are left to be handled by the sequence number check. The following code re-factoring are also made: 1. Move prepend('/') into prepend_name() to remove one conditional check. 2. Move the global root check in prepend_path() back to the top of the while loop. With this patch, the _raw_spin_lock will now account for only 1.2% of the total CPU cycles for the short workload. This patch also has the effect of reducing the effect of running perf on its profile since the perf command itself can be a heavy user of the d_path() function depending on the complexity of the workload. When taking the perf profile of the high-systime workload, the amount of spinlock contention contributed by running perf without this patch was about 16%. With this patch, the spinlock contention caused by the running of perf will go away and we will have a more accurate perf profile. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-10 00:18:13 +08:00
prepend(&end, &buflen, dentry->d_name.name, dentry->d_name.len) ||
prepend(&end, &buflen, "/", 1))
end = ERR_PTR(-ENAMETOOLONG);
dcache: Translating dentry into pathname without taking rename_lock When running the AIM7's short workload, Linus' lockref patch eliminated most of the spinlock contention. However, there were still some left: 8.46% reaim [kernel.kallsyms] [k] _raw_spin_lock |--42.21%-- d_path | proc_pid_readlink | SyS_readlinkat | SyS_readlink | system_call | __GI___readlink | |--40.97%-- sys_getcwd | system_call | __getcwd The big one here is the rename_lock (seqlock) contention in d_path() and the getcwd system call. This patch will eliminate the need to take the rename_lock while translating dentries into the full pathnames. The need to take the rename_lock is to make sure that no rename operation can be ongoing while the translation is in progress. However, only one thread can take the rename_lock thus blocking all the other threads that need it even though the translation process won't make any change to the dentries. This patch will replace the writer's write_seqlock/write_sequnlock sequence of the rename_lock of the callers of the prepend_path() and __dentry_path() functions with the reader's read_seqbegin/read_seqretry sequence within these 2 functions. As a result, the code will have to retry if one or more rename operations had been performed. In addition, RCU read lock will be taken during the translation process to make sure that no dentries will go away. To prevent live-lock from happening, the code will switch back to take the rename_lock if read_seqretry() fails for three times. To further reduce spinlock contention, this patch does not take the dentry's d_lock when copying the filename from the dentries. Instead, it treats the name pointer and length as unreliable and just copy the string byte-by-byte over until it hits a null byte or the end of string as specified by the length. This should avoid stepping into invalid memory address. The error cases are left to be handled by the sequence number check. The following code re-factoring are also made: 1. Move prepend('/') into prepend_name() to remove one conditional check. 2. Move the global root check in prepend_path() back to the top of the while loop. With this patch, the _raw_spin_lock will now account for only 1.2% of the total CPU cycles for the short workload. This patch also has the effect of reducing the effect of running perf on its profile since the perf command itself can be a heavy user of the d_path() function depending on the complexity of the workload. When taking the perf profile of the high-systime workload, the amount of spinlock contention contributed by running perf without this patch was about 16%. With this patch, the spinlock contention caused by the running of perf will go away and we will have a more accurate perf profile. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-10 00:18:13 +08:00
return end;
}
/*
* Write full pathname from the root of the filesystem into the buffer.
*/
static char *__dentry_path(struct dentry *d, char *buf, int buflen)
{
struct dentry *dentry;
dcache: Translating dentry into pathname without taking rename_lock When running the AIM7's short workload, Linus' lockref patch eliminated most of the spinlock contention. However, there were still some left: 8.46% reaim [kernel.kallsyms] [k] _raw_spin_lock |--42.21%-- d_path | proc_pid_readlink | SyS_readlinkat | SyS_readlink | system_call | __GI___readlink | |--40.97%-- sys_getcwd | system_call | __getcwd The big one here is the rename_lock (seqlock) contention in d_path() and the getcwd system call. This patch will eliminate the need to take the rename_lock while translating dentries into the full pathnames. The need to take the rename_lock is to make sure that no rename operation can be ongoing while the translation is in progress. However, only one thread can take the rename_lock thus blocking all the other threads that need it even though the translation process won't make any change to the dentries. This patch will replace the writer's write_seqlock/write_sequnlock sequence of the rename_lock of the callers of the prepend_path() and __dentry_path() functions with the reader's read_seqbegin/read_seqretry sequence within these 2 functions. As a result, the code will have to retry if one or more rename operations had been performed. In addition, RCU read lock will be taken during the translation process to make sure that no dentries will go away. To prevent live-lock from happening, the code will switch back to take the rename_lock if read_seqretry() fails for three times. To further reduce spinlock contention, this patch does not take the dentry's d_lock when copying the filename from the dentries. Instead, it treats the name pointer and length as unreliable and just copy the string byte-by-byte over until it hits a null byte or the end of string as specified by the length. This should avoid stepping into invalid memory address. The error cases are left to be handled by the sequence number check. The following code re-factoring are also made: 1. Move prepend('/') into prepend_name() to remove one conditional check. 2. Move the global root check in prepend_path() back to the top of the while loop. With this patch, the _raw_spin_lock will now account for only 1.2% of the total CPU cycles for the short workload. This patch also has the effect of reducing the effect of running perf on its profile since the perf command itself can be a heavy user of the d_path() function depending on the complexity of the workload. When taking the perf profile of the high-systime workload, the amount of spinlock contention contributed by running perf without this patch was about 16%. With this patch, the spinlock contention caused by the running of perf will go away and we will have a more accurate perf profile. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-10 00:18:13 +08:00
char *end, *retval;
int len, seq = 0;
int error = 0;
if (buflen < 2)
goto Elong;
rcu_read_lock();
dcache: Translating dentry into pathname without taking rename_lock When running the AIM7's short workload, Linus' lockref patch eliminated most of the spinlock contention. However, there were still some left: 8.46% reaim [kernel.kallsyms] [k] _raw_spin_lock |--42.21%-- d_path | proc_pid_readlink | SyS_readlinkat | SyS_readlink | system_call | __GI___readlink | |--40.97%-- sys_getcwd | system_call | __getcwd The big one here is the rename_lock (seqlock) contention in d_path() and the getcwd system call. This patch will eliminate the need to take the rename_lock while translating dentries into the full pathnames. The need to take the rename_lock is to make sure that no rename operation can be ongoing while the translation is in progress. However, only one thread can take the rename_lock thus blocking all the other threads that need it even though the translation process won't make any change to the dentries. This patch will replace the writer's write_seqlock/write_sequnlock sequence of the rename_lock of the callers of the prepend_path() and __dentry_path() functions with the reader's read_seqbegin/read_seqretry sequence within these 2 functions. As a result, the code will have to retry if one or more rename operations had been performed. In addition, RCU read lock will be taken during the translation process to make sure that no dentries will go away. To prevent live-lock from happening, the code will switch back to take the rename_lock if read_seqretry() fails for three times. To further reduce spinlock contention, this patch does not take the dentry's d_lock when copying the filename from the dentries. Instead, it treats the name pointer and length as unreliable and just copy the string byte-by-byte over until it hits a null byte or the end of string as specified by the length. This should avoid stepping into invalid memory address. The error cases are left to be handled by the sequence number check. The following code re-factoring are also made: 1. Move prepend('/') into prepend_name() to remove one conditional check. 2. Move the global root check in prepend_path() back to the top of the while loop. With this patch, the _raw_spin_lock will now account for only 1.2% of the total CPU cycles for the short workload. This patch also has the effect of reducing the effect of running perf on its profile since the perf command itself can be a heavy user of the d_path() function depending on the complexity of the workload. When taking the perf profile of the high-systime workload, the amount of spinlock contention contributed by running perf without this patch was about 16%. With this patch, the spinlock contention caused by the running of perf will go away and we will have a more accurate perf profile. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-10 00:18:13 +08:00
restart:
dentry = d;
dcache: Translating dentry into pathname without taking rename_lock When running the AIM7's short workload, Linus' lockref patch eliminated most of the spinlock contention. However, there were still some left: 8.46% reaim [kernel.kallsyms] [k] _raw_spin_lock |--42.21%-- d_path | proc_pid_readlink | SyS_readlinkat | SyS_readlink | system_call | __GI___readlink | |--40.97%-- sys_getcwd | system_call | __getcwd The big one here is the rename_lock (seqlock) contention in d_path() and the getcwd system call. This patch will eliminate the need to take the rename_lock while translating dentries into the full pathnames. The need to take the rename_lock is to make sure that no rename operation can be ongoing while the translation is in progress. However, only one thread can take the rename_lock thus blocking all the other threads that need it even though the translation process won't make any change to the dentries. This patch will replace the writer's write_seqlock/write_sequnlock sequence of the rename_lock of the callers of the prepend_path() and __dentry_path() functions with the reader's read_seqbegin/read_seqretry sequence within these 2 functions. As a result, the code will have to retry if one or more rename operations had been performed. In addition, RCU read lock will be taken during the translation process to make sure that no dentries will go away. To prevent live-lock from happening, the code will switch back to take the rename_lock if read_seqretry() fails for three times. To further reduce spinlock contention, this patch does not take the dentry's d_lock when copying the filename from the dentries. Instead, it treats the name pointer and length as unreliable and just copy the string byte-by-byte over until it hits a null byte or the end of string as specified by the length. This should avoid stepping into invalid memory address. The error cases are left to be handled by the sequence number check. The following code re-factoring are also made: 1. Move prepend('/') into prepend_name() to remove one conditional check. 2. Move the global root check in prepend_path() back to the top of the while loop. With this patch, the _raw_spin_lock will now account for only 1.2% of the total CPU cycles for the short workload. This patch also has the effect of reducing the effect of running perf on its profile since the perf command itself can be a heavy user of the d_path() function depending on the complexity of the workload. When taking the perf profile of the high-systime workload, the amount of spinlock contention contributed by running perf without this patch was about 16%. With this patch, the spinlock contention caused by the running of perf will go away and we will have a more accurate perf profile. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-10 00:18:13 +08:00
end = buf + buflen;
len = buflen;
prepend(&end, &len, "\0", 1);
/* Get '/' right */
retval = end-1;
*retval = '/';
dcache: Translating dentry into pathname without taking rename_lock When running the AIM7's short workload, Linus' lockref patch eliminated most of the spinlock contention. However, there were still some left: 8.46% reaim [kernel.kallsyms] [k] _raw_spin_lock |--42.21%-- d_path | proc_pid_readlink | SyS_readlinkat | SyS_readlink | system_call | __GI___readlink | |--40.97%-- sys_getcwd | system_call | __getcwd The big one here is the rename_lock (seqlock) contention in d_path() and the getcwd system call. This patch will eliminate the need to take the rename_lock while translating dentries into the full pathnames. The need to take the rename_lock is to make sure that no rename operation can be ongoing while the translation is in progress. However, only one thread can take the rename_lock thus blocking all the other threads that need it even though the translation process won't make any change to the dentries. This patch will replace the writer's write_seqlock/write_sequnlock sequence of the rename_lock of the callers of the prepend_path() and __dentry_path() functions with the reader's read_seqbegin/read_seqretry sequence within these 2 functions. As a result, the code will have to retry if one or more rename operations had been performed. In addition, RCU read lock will be taken during the translation process to make sure that no dentries will go away. To prevent live-lock from happening, the code will switch back to take the rename_lock if read_seqretry() fails for three times. To further reduce spinlock contention, this patch does not take the dentry's d_lock when copying the filename from the dentries. Instead, it treats the name pointer and length as unreliable and just copy the string byte-by-byte over until it hits a null byte or the end of string as specified by the length. This should avoid stepping into invalid memory address. The error cases are left to be handled by the sequence number check. The following code re-factoring are also made: 1. Move prepend('/') into prepend_name() to remove one conditional check. 2. Move the global root check in prepend_path() back to the top of the while loop. With this patch, the _raw_spin_lock will now account for only 1.2% of the total CPU cycles for the short workload. This patch also has the effect of reducing the effect of running perf on its profile since the perf command itself can be a heavy user of the d_path() function depending on the complexity of the workload. When taking the perf profile of the high-systime workload, the amount of spinlock contention contributed by running perf without this patch was about 16%. With this patch, the spinlock contention caused by the running of perf will go away and we will have a more accurate perf profile. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-10 00:18:13 +08:00
read_seqbegin_or_lock(&rename_lock, &seq);
while (!IS_ROOT(dentry)) {
struct dentry *parent = dentry->d_parent;
prefetch(parent);
dcache: Translating dentry into pathname without taking rename_lock When running the AIM7's short workload, Linus' lockref patch eliminated most of the spinlock contention. However, there were still some left: 8.46% reaim [kernel.kallsyms] [k] _raw_spin_lock |--42.21%-- d_path | proc_pid_readlink | SyS_readlinkat | SyS_readlink | system_call | __GI___readlink | |--40.97%-- sys_getcwd | system_call | __getcwd The big one here is the rename_lock (seqlock) contention in d_path() and the getcwd system call. This patch will eliminate the need to take the rename_lock while translating dentries into the full pathnames. The need to take the rename_lock is to make sure that no rename operation can be ongoing while the translation is in progress. However, only one thread can take the rename_lock thus blocking all the other threads that need it even though the translation process won't make any change to the dentries. This patch will replace the writer's write_seqlock/write_sequnlock sequence of the rename_lock of the callers of the prepend_path() and __dentry_path() functions with the reader's read_seqbegin/read_seqretry sequence within these 2 functions. As a result, the code will have to retry if one or more rename operations had been performed. In addition, RCU read lock will be taken during the translation process to make sure that no dentries will go away. To prevent live-lock from happening, the code will switch back to take the rename_lock if read_seqretry() fails for three times. To further reduce spinlock contention, this patch does not take the dentry's d_lock when copying the filename from the dentries. Instead, it treats the name pointer and length as unreliable and just copy the string byte-by-byte over until it hits a null byte or the end of string as specified by the length. This should avoid stepping into invalid memory address. The error cases are left to be handled by the sequence number check. The following code re-factoring are also made: 1. Move prepend('/') into prepend_name() to remove one conditional check. 2. Move the global root check in prepend_path() back to the top of the while loop. With this patch, the _raw_spin_lock will now account for only 1.2% of the total CPU cycles for the short workload. This patch also has the effect of reducing the effect of running perf on its profile since the perf command itself can be a heavy user of the d_path() function depending on the complexity of the workload. When taking the perf profile of the high-systime workload, the amount of spinlock contention contributed by running perf without this patch was about 16%. With this patch, the spinlock contention caused by the running of perf will go away and we will have a more accurate perf profile. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-10 00:18:13 +08:00
error = prepend_name(&end, &len, &dentry->d_name);
if (error)
break;
retval = end;
dentry = parent;
}
if (!(seq & 1))
rcu_read_unlock();
if (need_seqretry(&rename_lock, seq)) {
seq = 1;
dcache: Translating dentry into pathname without taking rename_lock When running the AIM7's short workload, Linus' lockref patch eliminated most of the spinlock contention. However, there were still some left: 8.46% reaim [kernel.kallsyms] [k] _raw_spin_lock |--42.21%-- d_path | proc_pid_readlink | SyS_readlinkat | SyS_readlink | system_call | __GI___readlink | |--40.97%-- sys_getcwd | system_call | __getcwd The big one here is the rename_lock (seqlock) contention in d_path() and the getcwd system call. This patch will eliminate the need to take the rename_lock while translating dentries into the full pathnames. The need to take the rename_lock is to make sure that no rename operation can be ongoing while the translation is in progress. However, only one thread can take the rename_lock thus blocking all the other threads that need it even though the translation process won't make any change to the dentries. This patch will replace the writer's write_seqlock/write_sequnlock sequence of the rename_lock of the callers of the prepend_path() and __dentry_path() functions with the reader's read_seqbegin/read_seqretry sequence within these 2 functions. As a result, the code will have to retry if one or more rename operations had been performed. In addition, RCU read lock will be taken during the translation process to make sure that no dentries will go away. To prevent live-lock from happening, the code will switch back to take the rename_lock if read_seqretry() fails for three times. To further reduce spinlock contention, this patch does not take the dentry's d_lock when copying the filename from the dentries. Instead, it treats the name pointer and length as unreliable and just copy the string byte-by-byte over until it hits a null byte or the end of string as specified by the length. This should avoid stepping into invalid memory address. The error cases are left to be handled by the sequence number check. The following code re-factoring are also made: 1. Move prepend('/') into prepend_name() to remove one conditional check. 2. Move the global root check in prepend_path() back to the top of the while loop. With this patch, the _raw_spin_lock will now account for only 1.2% of the total CPU cycles for the short workload. This patch also has the effect of reducing the effect of running perf on its profile since the perf command itself can be a heavy user of the d_path() function depending on the complexity of the workload. When taking the perf profile of the high-systime workload, the amount of spinlock contention contributed by running perf without this patch was about 16%. With this patch, the spinlock contention caused by the running of perf will go away and we will have a more accurate perf profile. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-10 00:18:13 +08:00
goto restart;
}
done_seqretry(&rename_lock, seq);
dcache: Translating dentry into pathname without taking rename_lock When running the AIM7's short workload, Linus' lockref patch eliminated most of the spinlock contention. However, there were still some left: 8.46% reaim [kernel.kallsyms] [k] _raw_spin_lock |--42.21%-- d_path | proc_pid_readlink | SyS_readlinkat | SyS_readlink | system_call | __GI___readlink | |--40.97%-- sys_getcwd | system_call | __getcwd The big one here is the rename_lock (seqlock) contention in d_path() and the getcwd system call. This patch will eliminate the need to take the rename_lock while translating dentries into the full pathnames. The need to take the rename_lock is to make sure that no rename operation can be ongoing while the translation is in progress. However, only one thread can take the rename_lock thus blocking all the other threads that need it even though the translation process won't make any change to the dentries. This patch will replace the writer's write_seqlock/write_sequnlock sequence of the rename_lock of the callers of the prepend_path() and __dentry_path() functions with the reader's read_seqbegin/read_seqretry sequence within these 2 functions. As a result, the code will have to retry if one or more rename operations had been performed. In addition, RCU read lock will be taken during the translation process to make sure that no dentries will go away. To prevent live-lock from happening, the code will switch back to take the rename_lock if read_seqretry() fails for three times. To further reduce spinlock contention, this patch does not take the dentry's d_lock when copying the filename from the dentries. Instead, it treats the name pointer and length as unreliable and just copy the string byte-by-byte over until it hits a null byte or the end of string as specified by the length. This should avoid stepping into invalid memory address. The error cases are left to be handled by the sequence number check. The following code re-factoring are also made: 1. Move prepend('/') into prepend_name() to remove one conditional check. 2. Move the global root check in prepend_path() back to the top of the while loop. With this patch, the _raw_spin_lock will now account for only 1.2% of the total CPU cycles for the short workload. This patch also has the effect of reducing the effect of running perf on its profile since the perf command itself can be a heavy user of the d_path() function depending on the complexity of the workload. When taking the perf profile of the high-systime workload, the amount of spinlock contention contributed by running perf without this patch was about 16%. With this patch, the spinlock contention caused by the running of perf will go away and we will have a more accurate perf profile. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-10 00:18:13 +08:00
if (error)
goto Elong;
return retval;
Elong:
return ERR_PTR(-ENAMETOOLONG);
}
char *dentry_path_raw(struct dentry *dentry, char *buf, int buflen)
{
dcache: Translating dentry into pathname without taking rename_lock When running the AIM7's short workload, Linus' lockref patch eliminated most of the spinlock contention. However, there were still some left: 8.46% reaim [kernel.kallsyms] [k] _raw_spin_lock |--42.21%-- d_path | proc_pid_readlink | SyS_readlinkat | SyS_readlink | system_call | __GI___readlink | |--40.97%-- sys_getcwd | system_call | __getcwd The big one here is the rename_lock (seqlock) contention in d_path() and the getcwd system call. This patch will eliminate the need to take the rename_lock while translating dentries into the full pathnames. The need to take the rename_lock is to make sure that no rename operation can be ongoing while the translation is in progress. However, only one thread can take the rename_lock thus blocking all the other threads that need it even though the translation process won't make any change to the dentries. This patch will replace the writer's write_seqlock/write_sequnlock sequence of the rename_lock of the callers of the prepend_path() and __dentry_path() functions with the reader's read_seqbegin/read_seqretry sequence within these 2 functions. As a result, the code will have to retry if one or more rename operations had been performed. In addition, RCU read lock will be taken during the translation process to make sure that no dentries will go away. To prevent live-lock from happening, the code will switch back to take the rename_lock if read_seqretry() fails for three times. To further reduce spinlock contention, this patch does not take the dentry's d_lock when copying the filename from the dentries. Instead, it treats the name pointer and length as unreliable and just copy the string byte-by-byte over until it hits a null byte or the end of string as specified by the length. This should avoid stepping into invalid memory address. The error cases are left to be handled by the sequence number check. The following code re-factoring are also made: 1. Move prepend('/') into prepend_name() to remove one conditional check. 2. Move the global root check in prepend_path() back to the top of the while loop. With this patch, the _raw_spin_lock will now account for only 1.2% of the total CPU cycles for the short workload. This patch also has the effect of reducing the effect of running perf on its profile since the perf command itself can be a heavy user of the d_path() function depending on the complexity of the workload. When taking the perf profile of the high-systime workload, the amount of spinlock contention contributed by running perf without this patch was about 16%. With this patch, the spinlock contention caused by the running of perf will go away and we will have a more accurate perf profile. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-10 00:18:13 +08:00
return __dentry_path(dentry, buf, buflen);
}
EXPORT_SYMBOL(dentry_path_raw);
char *dentry_path(struct dentry *dentry, char *buf, int buflen)
{
char *p = NULL;
char *retval;
if (d_unlinked(dentry)) {
p = buf + buflen;
if (prepend(&p, &buflen, "//deleted", 10) != 0)
goto Elong;
buflen++;
}
retval = __dentry_path(dentry, buf, buflen);
if (!IS_ERR(retval) && p)
*p = '/'; /* restore '/' overriden with '\0' */
return retval;
Elong:
return ERR_PTR(-ENAMETOOLONG);
}
static void get_fs_root_and_pwd_rcu(struct fs_struct *fs, struct path *root,
struct path *pwd)
{
unsigned seq;
do {
seq = read_seqcount_begin(&fs->seq);
*root = fs->root;
*pwd = fs->pwd;
} while (read_seqcount_retry(&fs->seq, seq));
}
/*
* NOTE! The user-level library version returns a
* character pointer. The kernel system call just
* returns the length of the buffer filled (which
* includes the ending '\0' character), or a negative
* error value. So libc would do something like
*
* char *getcwd(char * buf, size_t size)
* {
* int retval;
*
* retval = sys_getcwd(buf, size);
* if (retval >= 0)
* return buf;
* errno = -retval;
* return NULL;
* }
*/
SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size)
{
int error;
struct path pwd, root;
char *page = __getname();
if (!page)
return -ENOMEM;
rcu_read_lock();
get_fs_root_and_pwd_rcu(current->fs, &root, &pwd);
error = -ENOENT;
if (!d_unlinked(pwd.dentry)) {
unsigned long len;
char *cwd = page + PATH_MAX;
int buflen = PATH_MAX;
prepend(&cwd, &buflen, "\0", 1);
fix apparmor dereferencing potentially freed dentry, sanitize __d_path() API __d_path() API is asking for trouble and in case of apparmor d_namespace_path() getting just that. The root cause is that when __d_path() misses the root it had been told to look for, it stores the location of the most remote ancestor in *root. Without grabbing references. Sure, at the moment of call it had been pinned down by what we have in *path. And if we raced with umount -l, we could have very well stopped at vfsmount/dentry that got freed as soon as prepend_path() dropped vfsmount_lock. It is safe to compare these pointers with pre-existing (and known to be still alive) vfsmount and dentry, as long as all we are asking is "is it the same address?". Dereferencing is not safe and apparmor ended up stepping into that. d_namespace_path() really wants to examine the place where we stopped, even if it's not connected to our namespace. As the result, it looked at ->d_sb->s_magic of a dentry that might've been already freed by that point. All other callers had been careful enough to avoid that, but it's really a bad interface - it invites that kind of trouble. The fix is fairly straightforward, even though it's bigger than I'd like: * prepend_path() root argument becomes const. * __d_path() is never called with NULL/NULL root. It was a kludge to start with. Instead, we have an explicit function - d_absolute_root(). Same as __d_path(), except that it doesn't get root passed and stops where it stops. apparmor and tomoyo are using it. * __d_path() returns NULL on path outside of root. The main caller is show_mountinfo() and that's precisely what we pass root for - to skip those outside chroot jail. Those who don't want that can (and do) use d_path(). * __d_path() root argument becomes const. Everyone agrees, I hope. * apparmor does *NOT* try to use __d_path() or any of its variants when it sees that path->mnt is an internal vfsmount. In that case it's definitely not mounted anywhere and dentry_path() is exactly what we want there. Handling of sysctl()-triggered weirdness is moved to that place. * if apparmor is asked to do pathname relative to chroot jail and __d_path() tells it we it's not in that jail, the sucker just calls d_absolute_path() instead. That's the other remaining caller of __d_path(), BTW. * seq_path_root() does _NOT_ return -ENAMETOOLONG (it's stupid anyway - the normal seq_file logics will take care of growing the buffer and redoing the call of ->show() just fine). However, if it gets path not reachable from root, it returns SEQ_SKIP. The only caller adjusted (i.e. stopped ignoring the return value as it used to do). Reviewed-by: John Johansen <john.johansen@canonical.com> ACKed-by: John Johansen <john.johansen@canonical.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Cc: stable@vger.kernel.org
2011-12-05 21:43:34 +08:00
error = prepend_path(&pwd, &root, &cwd, &buflen);
rcu_read_unlock();
fix apparmor dereferencing potentially freed dentry, sanitize __d_path() API __d_path() API is asking for trouble and in case of apparmor d_namespace_path() getting just that. The root cause is that when __d_path() misses the root it had been told to look for, it stores the location of the most remote ancestor in *root. Without grabbing references. Sure, at the moment of call it had been pinned down by what we have in *path. And if we raced with umount -l, we could have very well stopped at vfsmount/dentry that got freed as soon as prepend_path() dropped vfsmount_lock. It is safe to compare these pointers with pre-existing (and known to be still alive) vfsmount and dentry, as long as all we are asking is "is it the same address?". Dereferencing is not safe and apparmor ended up stepping into that. d_namespace_path() really wants to examine the place where we stopped, even if it's not connected to our namespace. As the result, it looked at ->d_sb->s_magic of a dentry that might've been already freed by that point. All other callers had been careful enough to avoid that, but it's really a bad interface - it invites that kind of trouble. The fix is fairly straightforward, even though it's bigger than I'd like: * prepend_path() root argument becomes const. * __d_path() is never called with NULL/NULL root. It was a kludge to start with. Instead, we have an explicit function - d_absolute_root(). Same as __d_path(), except that it doesn't get root passed and stops where it stops. apparmor and tomoyo are using it. * __d_path() returns NULL on path outside of root. The main caller is show_mountinfo() and that's precisely what we pass root for - to skip those outside chroot jail. Those who don't want that can (and do) use d_path(). * __d_path() root argument becomes const. Everyone agrees, I hope. * apparmor does *NOT* try to use __d_path() or any of its variants when it sees that path->mnt is an internal vfsmount. In that case it's definitely not mounted anywhere and dentry_path() is exactly what we want there. Handling of sysctl()-triggered weirdness is moved to that place. * if apparmor is asked to do pathname relative to chroot jail and __d_path() tells it we it's not in that jail, the sucker just calls d_absolute_path() instead. That's the other remaining caller of __d_path(), BTW. * seq_path_root() does _NOT_ return -ENAMETOOLONG (it's stupid anyway - the normal seq_file logics will take care of growing the buffer and redoing the call of ->show() just fine). However, if it gets path not reachable from root, it returns SEQ_SKIP. The only caller adjusted (i.e. stopped ignoring the return value as it used to do). Reviewed-by: John Johansen <john.johansen@canonical.com> ACKed-by: John Johansen <john.johansen@canonical.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Cc: stable@vger.kernel.org
2011-12-05 21:43:34 +08:00
if (error < 0)
goto out;
/* Unreachable from current root */
fix apparmor dereferencing potentially freed dentry, sanitize __d_path() API __d_path() API is asking for trouble and in case of apparmor d_namespace_path() getting just that. The root cause is that when __d_path() misses the root it had been told to look for, it stores the location of the most remote ancestor in *root. Without grabbing references. Sure, at the moment of call it had been pinned down by what we have in *path. And if we raced with umount -l, we could have very well stopped at vfsmount/dentry that got freed as soon as prepend_path() dropped vfsmount_lock. It is safe to compare these pointers with pre-existing (and known to be still alive) vfsmount and dentry, as long as all we are asking is "is it the same address?". Dereferencing is not safe and apparmor ended up stepping into that. d_namespace_path() really wants to examine the place where we stopped, even if it's not connected to our namespace. As the result, it looked at ->d_sb->s_magic of a dentry that might've been already freed by that point. All other callers had been careful enough to avoid that, but it's really a bad interface - it invites that kind of trouble. The fix is fairly straightforward, even though it's bigger than I'd like: * prepend_path() root argument becomes const. * __d_path() is never called with NULL/NULL root. It was a kludge to start with. Instead, we have an explicit function - d_absolute_root(). Same as __d_path(), except that it doesn't get root passed and stops where it stops. apparmor and tomoyo are using it. * __d_path() returns NULL on path outside of root. The main caller is show_mountinfo() and that's precisely what we pass root for - to skip those outside chroot jail. Those who don't want that can (and do) use d_path(). * __d_path() root argument becomes const. Everyone agrees, I hope. * apparmor does *NOT* try to use __d_path() or any of its variants when it sees that path->mnt is an internal vfsmount. In that case it's definitely not mounted anywhere and dentry_path() is exactly what we want there. Handling of sysctl()-triggered weirdness is moved to that place. * if apparmor is asked to do pathname relative to chroot jail and __d_path() tells it we it's not in that jail, the sucker just calls d_absolute_path() instead. That's the other remaining caller of __d_path(), BTW. * seq_path_root() does _NOT_ return -ENAMETOOLONG (it's stupid anyway - the normal seq_file logics will take care of growing the buffer and redoing the call of ->show() just fine). However, if it gets path not reachable from root, it returns SEQ_SKIP. The only caller adjusted (i.e. stopped ignoring the return value as it used to do). Reviewed-by: John Johansen <john.johansen@canonical.com> ACKed-by: John Johansen <john.johansen@canonical.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Cc: stable@vger.kernel.org
2011-12-05 21:43:34 +08:00
if (error > 0) {
error = prepend_unreachable(&cwd, &buflen);
if (error)
goto out;
}
error = -ERANGE;
len = PATH_MAX + page - cwd;
if (len <= size) {
error = len;
if (copy_to_user(buf, cwd, len))
error = -EFAULT;
}
} else {
rcu_read_unlock();
}
out:
__putname(page);
return error;
}
/*
* Test whether new_dentry is a subdirectory of old_dentry.
*
* Trivially implemented using the dcache structure
*/
/**
* is_subdir - is new dentry a subdirectory of old_dentry
* @new_dentry: new dentry
* @old_dentry: old dentry
*
* Returns 1 if new_dentry is a subdirectory of the parent (at any depth).
* Returns 0 otherwise.
* Caller must ensure that "new_dentry" is pinned before calling is_subdir()
*/
int is_subdir(struct dentry *new_dentry, struct dentry *old_dentry)
{
int result;
unsigned seq;
if (new_dentry == old_dentry)
return 1;
do {
/* for restarting inner loop in case of seq retry */
seq = read_seqbegin(&rename_lock);
/*
* Need rcu_readlock to protect against the d_parent trashing
* due to d_move
*/
rcu_read_lock();
if (d_ancestor(old_dentry, new_dentry))
result = 1;
else
result = 0;
rcu_read_unlock();
} while (read_seqretry(&rename_lock, seq));
return result;
}
static enum d_walk_ret d_genocide_kill(void *data, struct dentry *dentry)
{
struct dentry *root = data;
if (dentry != root) {
if (d_unhashed(dentry) || !dentry->d_inode)
return D_WALK_SKIP;
if (!(dentry->d_flags & DCACHE_GENOCIDE)) {
dentry->d_flags |= DCACHE_GENOCIDE;
dentry->d_lockref.count--;
}
}
return D_WALK_CONTINUE;
}
void d_genocide(struct dentry *parent)
{
d_walk(parent, parent, d_genocide_kill, NULL);
}
void d_tmpfile(struct dentry *dentry, struct inode *inode)
{
inode_dec_link_count(inode);
BUG_ON(dentry->d_name.name != dentry->d_iname ||
!hlist_unhashed(&dentry->d_alias) ||
!d_unlinked(dentry));
spin_lock(&dentry->d_parent->d_lock);
spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
dentry->d_name.len = sprintf(dentry->d_iname, "#%llu",
(unsigned long long)inode->i_ino);
spin_unlock(&dentry->d_lock);
spin_unlock(&dentry->d_parent->d_lock);
d_instantiate(dentry, inode);
}
EXPORT_SYMBOL(d_tmpfile);
static __initdata unsigned long dhash_entries;
static int __init set_dhash_entries(char *str)
{
if (!str)
return 0;
dhash_entries = simple_strtoul(str, &str, 0);
return 1;
}
__setup("dhash_entries=", set_dhash_entries);
static void __init dcache_init_early(void)
{
unsigned int loop;
/* If hashes are distributed across NUMA nodes, defer
* hash allocation until vmalloc space is available.
*/
if (hashdist)
return;
dentry_hashtable =
alloc_large_system_hash("Dentry cache",
sizeof(struct hlist_bl_head),
dhash_entries,
13,
HASH_EARLY,
&d_hash_shift,
&d_hash_mask,
0,
0);
for (loop = 0; loop < (1U << d_hash_shift); loop++)
INIT_HLIST_BL_HEAD(dentry_hashtable + loop);
}
static void __init dcache_init(void)
{
unsigned int loop;
/*
* A constructor could be added for stable state like the lists,
* but it is probably not worth it because of the cache nature
* of the dcache.
*/
dentry_cache = KMEM_CACHE(dentry,
SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD);
/* Hash may have been set up in dcache_init_early */
if (!hashdist)
return;
dentry_hashtable =
alloc_large_system_hash("Dentry cache",
sizeof(struct hlist_bl_head),
dhash_entries,
13,
0,
&d_hash_shift,
&d_hash_mask,
0,
0);
for (loop = 0; loop < (1U << d_hash_shift); loop++)
INIT_HLIST_BL_HEAD(dentry_hashtable + loop);
}
/* SLAB cache for __getname() consumers */
struct kmem_cache *names_cachep __read_mostly;
EXPORT_SYMBOL(names_cachep);
EXPORT_SYMBOL(d_genocide);
void __init vfs_caches_init_early(void)
{
dcache_init_early();
inode_init_early();
}
void __init vfs_caches_init(unsigned long mempages)
{
unsigned long reserve;
/* Base hash sizes on available memory, with a reserve equal to
150% of current kernel size */
reserve = min((mempages - nr_free_pages()) * 3/2, mempages - 1);
mempages -= reserve;
names_cachep = kmem_cache_create("names_cache", PATH_MAX, 0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
dcache_init();
inode_init();
files_init(mempages);
mnt_init();
bdev_cache_init();
chrdev_init();
}