Add a new lock, dcache_lru_lock, to protect the dcache LRU list from concurrent
modification. d_lru is also protected by d_lock, which allows LRU lists to be
accessed without the lru lock, using RCU in future patches.
Signed-off-by: NNick Piggin <npiggin@kernel.dk>

Add a new lock, dcache_hash_lock, to protect the dcache hash table from
concurrent modification. d_hash is also protected by d_lock.
Signed-off-by: NNick Piggin <npiggin@kernel.dk>

Remove dcache_lock locking from hostfs filesystem, and move it into dcache
helpers. All that is required is a coherent path name. Protection from
concurrent modification of the namespace after path name generation is not
provided in current code, because dcache_lock is dropped before the path is
used.
Signed-off-by: NNick Piggin <npiggin@kernel.dk>

Change d_hash so it may be called from lock-free RCU lookups. See similar
patch for d_compare for details.

For in-tree filesystems, this is just a mechanical change.
Signed-off-by: NNick Piggin <npiggin@kernel.dk>

Change d_compare so it may be called from lock-free RCU lookups. This
does put significant restrictions on what may be done from the callback,
however there don't seem to have been any problems with in-tree fses.
If some strange use case pops up that _really_ cannot cope with the
rcu-walk rules, we can just add new rcu-unaware callbacks, which would
cause name lookup to drop out of rcu-walk mode.

For in-tree filesystems, this is just a mechanical change.
Signed-off-by: NNick Piggin <npiggin@kernel.dk>

smpfs and ncpfs want to update a live dentry name in-place. Rather than
have them open code the locking, provide a documented dcache API.
Signed-off-by: NNick Piggin <npiggin@kernel.dk>

Change d_delete from a dentry deletion notification to a dentry caching
advise, more like ->drop_inode. Require it to be constant and idempotent,
and not take d_lock. This is how all existing filesystems use the callback
anyway.

This makes fine grained dentry locking of dput and dentry lru scanning
much simpler.
Signed-off-by: NNick Piggin <npiggin@kernel.dk>

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: NNick Piggin <npiggin@kernel.dk>

The nr_unused counters count the number of objects on an LRU, and as such they
are synchronized with LRU object insertion and removal and scanning, and
protected under the LRU lock.

Making it per-cpu does not actually get any concurrency improvements because of
this lock, and summing the counter is much slower, and
incrementing/decrementing it costs more code size and is slower too.

These counters should stay per-LRU, which currently means global.
Signed-off-by: NNick Piggin <npiggin@kernel.dk>

d_validate has been broken for a long time.

kmem_ptr_validate does not guarantee that a pointer can be dereferenced
if it can go away at any time. Even rcu_read_lock doesn't help, because
the pointer might be queued in RCU callbacks but not executed yet.

So the parent cannot be checked, nor the name hashed. The dentry pointer
can not be touched until it can be verified under lock. Hashing simply
cannot be used.

Instead, verify the parent/child relationship by traversing parent's
d_child list. It's slow, but only ncpfs and the destaged smbfs care
about it, at this point.
Signed-off-by: NNick Piggin <npiggin@kernel.dk>

This reverts commit 3825bdb7.

You cannot dget() a dentry without having a reference, or holding
a lock that guarantees it remains valid.
Signed-off-by: NNick Piggin <npiggin@kernel.dk>

d_validate does a purely read lookup in the dentry hash, so use RCU read side
locking instead of dcache_lock.  Split out from a larget patch by
Nick Piggin <npiggin@suse.de>.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Always do a list_del_init on the LRU to make sure the list_empty invariant for
not beeing on the LRU always holds true, and fold dentry_lru_del_init into
dentry_lru_del.  Replace the dentry_lru_add_tail primitive with a
dentry_lru_move_tail operations that simpler when the dentry already is one
the list, which is always is.  Move the list_empty into dentry_lru_add to
fit the scheme of the other lru helpers, and simplify locking once we
move to a separate LRU lock.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Currently __shrink_dcache_sb has an extremly awkward calling convention
because it tries to please very different callers.  Split out the
main loop into a shrink_dentry_list helper, which gets called directly
from shrink_dcache_sb for the cases where all dentries need to be pruned,
or from __shrink_dcache_sb for pruning only a certain number of dentries.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

dentry referenced bit is only set when installing the dentry back
onto the LRU. However with lazy LRU, the dentry can already be on
the LRU list at dput time, thus missing out on setting the referenced
bit. Fix this.
Signed-off-by: NNick Piggin <npiggin@suse.de>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

The nr_dentry stat is a globally touched cacheline and atomic operation
twice over the lifetime of a dentry. It is used for the benfit of userspace
only. Turn it into a per-cpu counter and always decrement it in d_free instead
of doing various batching operations to reduce lock hold times in the callers.

Based on an earlier patch from Nick Piggin <npiggin@suse.de>.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Remove d_callback and always call __d_free with a RCU head.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

All callers take dcache_lock just around the call to __d_path, so
take the lock into it in preparation of getting rid of dcache_lock.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

fs: brlock vfsmount_lock

Use a brlock for the vfsmount lock. It must be taken for write whenever
modifying the mount hash or associated fields, and may be taken for read when
performing mount hash lookups.

A new lock is added for the mnt-id allocator, so it doesn't need to take
the heavy vfsmount write-lock.

The number of atomics should remain the same for fastpath rlock cases, though
code would be slightly slower due to per-cpu access. Scalability is not not be
much improved in common cases yet, due to other locks (ie. dcache_lock) getting
in the way. However path lookups crossing mountpoints should be one case where
scalability is improved (currently requiring the global lock).

The slowpath is slower due to use of brlock. On a 64 core, 64 socket, 32 node
Altix system (high latency to remote nodes), a simple umount microbenchmark
(mount --bind mnt mnt2 ; umount mnt2 loop 1000 times), before this patch it
took 6.8s, afterwards took 7.1s, about 5% slower.

Cc: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: NNick Piggin <npiggin@kernel.dk>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

fs: remove extra lookup in __lookup_hash

Optimize lookup for create operations, where no dentry should often be
common-case. In cases where it is not, such as unlink, the added overhead
is much smaller than the removed.

Also, move comments about __d_lookup racyness to the __d_lookup call site.
d_lookup is intuitive; __d_lookup is what needs commenting. So in that same
vein, add kerneldoc comments to __d_lookup and clean up some of the comments:

- We are interested in how the RCU lookup works here, particularly with
  renames. Make that explicit, and point to the document where it is explained
  in more detail.
- RCU is pretty standard now, and macros make implementations pretty mindless.
  If we want to know about RCU barrier details, we look in RCU code.
- Delete some boring legacy comments because we don't care much about how the
  code used to work, more about the interesting parts of how it works now. So
  comments about lazy LRU may be interesting, but would better be done in the
  LRU or refcount management code.
Signed-off-by: NNick Piggin <npiggin@kernel.dk>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Fix parameter name in kernel-doc notation (causes a warning).
Signed-off-by: NRandy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Prepend "(unreachable)" to path strings if the path is not reachable
from the current root.

Two places updated are
 - the return string from getcwd()
 - and symlinks under /proc/$PID.

Other uses of d_path() are left unchanged (we know that some old
software crashes if /proc/mounts is changed).
Signed-off-by: NMiklos Szeredi <mszeredi@suse.cz>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

__d_path() has 4 callers:

  d_path()
  sys_getcwd()
  seq_path_root()
  tomoyo_realpath_from_path2()

Of these the only one which needs the " (deleted)" ending is d_path().

sys_getcwd() checks for existence before calling __d_path().

seq_path_root() is used to show the mountpoint path in
/proc/PID/mountinfo, which is always a positive.

And tomoyo doesn't want the deleted ending.

Create a helper "path_with_deleted()" as subsequent patches will need
this in multiple places.
Signed-off-by: NMiklos Szeredi <mszeredi@suse.cz>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Split off prepend_path() from __d_path().  This new helper takes an
end-of-buffer pointer and buffer-length pointer just like the other
prepend_* functions.  Move the " (deleted)" postfix out to __d_path().

This patch doesn't change any functionality but paves the way for the
following patches.
Signed-off-by: NMiklos Szeredi <mszeredi@suse.cz>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

In the old times pseudo-filesystems set the name of theroot dentry to
some prefix like "pipe:" and the name of the child dentry to "[123]"
and relied on a hack in __d_path() to replace the preceding slash with
the root's name to get "pipe:[123]".

Then the d_dname() dentry operation was introduced which solved the
same problem without having to pre-fill the name in each dentry.

Currently the following pseudo filesystems exist in the kernel:

perfmon
mtd
anon_inode
bdev
pipe
socket

Of these only perfmon, anon_inode, pipe and socket create
sub-dentries, all of which have now been switched to using d_dname().

bdev and mtd only create inodes.

This means that now the hack to overwrite the slash can be removed, so
for unreachable paths (e.g. within a detached mount) the path string
won't be polluted with garbage.  For these cases a subsequent patch
will add a prefix, indicating that the path is unreachable.
Signed-off-by: NMiklos Szeredi <mszeredi@suse.cz>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Add three helpers that retrieve a refcounted copy of the root and cwd
from the supplied fs_struct.

 get_fs_root()
 get_fs_pwd()
 get_fs_root_and_pwd()
Signed-off-by: NMiklos Szeredi <mszeredi@suse.cz>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

just delay __put_super() a bit
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

builds path relative to fs root, called under dcache_lock,
doesn't append any nonsense to unlinked ones.
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

The current shrinker implementation requires the registered callback
to have global state to work from. This makes it difficult to shrink
caches that are not global (e.g. per-filesystem caches). Pass the shrinker
structure to the callback so that users can embed the shrinker structure
in the context the shrinker needs to operate on and get back to it in the
callback via container_of().
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>

list_for_each_entry_safe is not suitable to protect against concurrent
modification of the list. 6754af64 introduced a race in sb walking.

list_for_each_entry can use the trick of pinning the current entry in
the list before we drop and retake the lock because it subsequently
follows cur->next. However list_for_each_entry_safe saves n=cur->next
for following before entering the loop body, so when the lock is
dropped, n may be deleted.
Signed-off-by: NNick Piggin <npiggin@suse.de>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: John Stultz <johnstul@us.ibm.com>
Cc: Frank Mayhar <fmayhar@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

... and get rid of the last __put_super_and_need_restart() caller
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

We used to remove from s_list and s_instances at the same
time.  So let's *not* do the former and skip superblocks
that have empty s_instances in the loops over s_list.

The next step, of course, will be to get rid of rescan logics
in those loops.
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

We set the "it's dead, don't mount on it" flag _and_ do not remove it if
we turn the damn thing negative and leave it around.  And if it goes
positive afterwards, well...

Fortunately, there's only one place where that needs to be caught:
only d_delete() can turn the sucker negative without immediately freeing
it; all other places that can lead to ->d_iput() call are followed by
unconditionally freeing struct dentry in question.  So the fix is obvious:

Addresses https://bugzilla.kernel.org/show_bug.cgi?id=16014Reported-by: NAdam Tkac <vonsch@gmail.com>
Tested-by: NAdam Tkac <vonsch@gmail.com>
Cc: <stable@kernel.org>         [2.6.34.x]
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

rehashing the negative placeholder opens a race with d_lookup();
we unhash it almost immediately (by d_move()), but the race
window is there.  Since d_move() doesn't rely on target being
hashed, we don't need that d_rehash() at all.
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Analog of is_subdir for vfsmount,dentry pairs, moved from audit_tree.c
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Cleanup EXPORT* macros according to Documantation/CodingStyle.

Move EXPORT* macros to the line immediately after the closing
function brace.
Signed-off-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

The EXPORT_SYMBOL for d_alloc_name is in fs/libfs.c but the function
is in fs/dcache.c.  Move the EXPORT_SYMBOL to the line immediately
after the closing function brace line in fs/dcache.c as mentioned
in Documentation/CodingStyle.
Signed-off-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

might_sleep() is called late-ish in cond_resched(), after the
need_resched()/preempt enabled/system running tests are
checked.

It's better to check the sleeps while atomic earlier and not
depend on some environment datas that reduce the chances to
detect a problem.

Also define cond_resched_*() helpers as macros, so that the
FILE/LINE reported in the sleeping while atomic warning
displays the real origin and not sched.h

Changes in v2:

 - Call __might_sleep() directly instead of might_sleep() which
   may call cond_resched()

 - Turn cond_resched() into a macro so that the file:line
   couple reported refers to the caller of cond_resched() and
   not __cond_resched() itself.

Changes in v3:

 - Also propagate this __might_sleep() pull up to
   cond_resched_lock() and cond_resched_softirq()
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1247725694-6082-6-git-send-email-fweisbec@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

d_unlinked() will be used in middle-term to ban checkpointing when opened
but unlinked file is detected, and in long term, to detect such situation
and special case on it.
Signed-off-by: NAlexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Fix ordering of LRU when moving referenced dentries to the head of the list
(they should go to the head of the list in the same order as they were found
from the tail, rather than reverse order).
Signed-off-by: NNick Piggin <npiggin@suse.de>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>