inotify: use GFP_NOFS in kernel_event() to work around a lockdep false-positive

There is what we believe to be a false positive reported by lockdep.

inotify_inode_queue_event() => take inotify_mutex => kernel_event() =>
kmalloc() => SLOB => alloc_pages_node() => page reclaim => slab reclaim =>
dcache reclaim => inotify_inode_is_dead => take inotify_mutex => deadlock

The plan is to fix this via lockdep annotation, but that is proving to be
quite involved.

The patch flips the allocation over to GFP_NFS to shut the warning up, for
the 2.6.30 release.

Hopefully we will fix this for real in 2.6.31.  I'll queue a patch in -mm
to switch it back to GFP_KERNEL so we don't forget.

  =================================
  [ INFO: inconsistent lock state ]
  2.6.30-rc2-next-20090417 #203
  ---------------------------------
  inconsistent {RECLAIM_FS-ON-W} -> {IN-RECLAIM_FS-W} usage.
  kswapd0/380 [HC0[0]:SC0[0]:HE1:SE1] takes:
   (&inode->inotify_mutex){+.+.?.}, at: [<ffffffff8112f1b5>] inotify_inode_is_dead+0x35/0xb0
  {RECLAIM_FS-ON-W} state was registered at:
    [<ffffffff81079188>] mark_held_locks+0x68/0x90
    [<ffffffff810792a5>] lockdep_trace_alloc+0xf5/0x100
    [<ffffffff810f5261>] __kmalloc_node+0x31/0x1e0
    [<ffffffff81130652>] kernel_event+0xe2/0x190
    [<ffffffff81130826>] inotify_dev_queue_event+0x126/0x230
    [<ffffffff8112f096>] inotify_inode_queue_event+0xc6/0x110
    [<ffffffff8110444d>] vfs_create+0xcd/0x140
    [<ffffffff8110825d>] do_filp_open+0x88d/0xa20
    [<ffffffff810f6b68>] do_sys_open+0x98/0x140
    [<ffffffff810f6c50>] sys_open+0x20/0x30
    [<ffffffff8100c272>] system_call_fastpath+0x16/0x1b
    [<ffffffffffffffff>] 0xffffffffffffffff
  irq event stamp: 690455
  hardirqs last  enabled at (690455): [<ffffffff81564fe4>] _spin_unlock_irqrestore+0x44/0x80
  hardirqs last disabled at (690454): [<ffffffff81565372>] _spin_lock_irqsave+0x32/0xa0
  softirqs last  enabled at (690178): [<ffffffff81052282>] __do_softirq+0x202/0x220
  softirqs last disabled at (690157): [<ffffffff8100d50c>] call_softirq+0x1c/0x50

  other info that might help us debug this:
  2 locks held by kswapd0/380:
   #0:  (shrinker_rwsem){++++..}, at: [<ffffffff810d0bd7>] shrink_slab+0x37/0x180
   #1:  (&type->s_umount_key#17){++++..}, at: [<ffffffff8110cfbf>] shrink_dcache_memory+0x11f/0x1e0

  stack backtrace:
  Pid: 380, comm: kswapd0 Not tainted 2.6.30-rc2-next-20090417 #203
  Call Trace:
   [<ffffffff810789ef>] print_usage_bug+0x19f/0x200
   [<ffffffff81018bff>] ? save_stack_trace+0x2f/0x50
   [<ffffffff81078f0b>] mark_lock+0x4bb/0x6d0
   [<ffffffff810799e0>] ? check_usage_forwards+0x0/0xc0
   [<ffffffff8107b142>] __lock_acquire+0xc62/0x1ae0
   [<ffffffff810f478c>] ? slob_free+0x10c/0x370
   [<ffffffff8107c0a1>] lock_acquire+0xe1/0x120
   [<ffffffff8112f1b5>] ? inotify_inode_is_dead+0x35/0xb0
   [<ffffffff81562d43>] mutex_lock_nested+0x63/0x420
   [<ffffffff8112f1b5>] ? inotify_inode_is_dead+0x35/0xb0
   [<ffffffff8112f1b5>] ? inotify_inode_is_dead+0x35/0xb0
   [<ffffffff81012fe9>] ? sched_clock+0x9/0x10
   [<ffffffff81077165>] ? lock_release_holdtime+0x35/0x1c0
   [<ffffffff8112f1b5>] inotify_inode_is_dead+0x35/0xb0
   [<ffffffff8110c9dc>] dentry_iput+0xbc/0xe0
   [<ffffffff8110cb23>] d_kill+0x33/0x60
   [<ffffffff8110ce23>] __shrink_dcache_sb+0x2d3/0x350
   [<ffffffff8110cffa>] shrink_dcache_memory+0x15a/0x1e0
   [<ffffffff810d0cc5>] shrink_slab+0x125/0x180
   [<ffffffff810d1540>] kswapd+0x560/0x7a0
   [<ffffffff810ce160>] ? isolate_pages_global+0x0/0x2c0
   [<ffffffff81065a30>] ? autoremove_wake_function+0x0/0x40
   [<ffffffff8107953d>] ? trace_hardirqs_on+0xd/0x10
   [<ffffffff810d0fe0>] ? kswapd+0x0/0x7a0
   [<ffffffff8106555b>] kthread+0x5b/0xa0
   [<ffffffff8100d40a>] child_rip+0xa/0x20
   [<ffffffff8100cdd0>] ? restore_args+0x0/0x30
   [<ffffffff81065500>] ? kthread+0x0/0xa0
   [<ffffffff8100d400>] ? child_rip+0x0/0x20

[eparis@redhat.com: fix audit too]
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index bed766e..1634319 100644 (file)
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -220,7 +220,7 @@ static struct inotify_kernel_event * kernel_event(s32 wd, u32 mask, u32 cookie,
                                rem = 0;
                }
 
-               kevent->name = kmalloc(len + rem, GFP_KERNEL);
+               kevent->name = kmalloc(len + rem, GFP_NOFS);
                if (unlikely(!kevent->name)) {
                        kmem_cache_free(event_cachep, kevent);
                        return NULL;

diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index a6fe71f..713098e 100644 (file)
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -1028,7 +1028,7 @@ static void audit_update_watch(struct audit_parent *parent,
 
                if (audit_enabled) {
                        struct audit_buffer *ab;
-                       ab = audit_log_start(NULL, GFP_KERNEL,
+                       ab = audit_log_start(NULL, GFP_NOFS,
                                AUDIT_CONFIG_CHANGE);
                        audit_log_format(ab, "auid=%u ses=%u",
                                audit_get_loginuid(current),
@@ -1067,7 +1067,7 @@ static void audit_remove_parent_watches(struct audit_parent *parent)
                        e = container_of(r, struct audit_entry, rule);
                        if (audit_enabled) {
                                struct audit_buffer *ab;
-                               ab = audit_log_start(NULL, GFP_KERNEL,
+                               ab = audit_log_start(NULL, GFP_NOFS,
                                        AUDIT_CONFIG_CHANGE);
                                audit_log_format(ab, "auid=%u ses=%u",
                                        audit_get_loginuid(current),