lockdep: fix fs_reclaim annotation

While revisiting my Btrfs swapfile series [1], I introduced a situation
in which reclaim would lock i_rwsem, and even though the swapon() path
clearly made GFP_KERNEL allocations while holding i_rwsem, I got no
complaints from lockdep.  It turns out that the rework of the fs_reclaim
annotation was broken: if the current task has PF_MEMALLOC set, we don't
acquire the dummy fs_reclaim lock, but when reclaiming we always check
this _after_ we've just set the PF_MEMALLOC flag.  In most cases, we can
fix this by moving the fs_reclaim_{acquire,release}() outside of the
memalloc_noreclaim_{save,restore}(), althought kswapd is slightly
different.  After applying this, I got the expected lockdep splats.

1: https://lwn.net/Articles/625412/

Link: http://lkml.kernel.org/r/9f8aa70652a98e98d7c4de0fc96a4addcee13efe.1523778026.git.osandov@fb.com
Fixes: d92a8cfcb37e ("locking/lockdep: Rework FS_RECLAIM annotation")
Signed-off-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 15 insertions, 5 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 4fbe211340e0..b93cc79a8db4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3701,7 +3701,7 @@ should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_fla
 #endif /* CONFIG_COMPACTION */
 
 #ifdef CONFIG_LOCKDEP
-struct lockdep_map __fs_reclaim_map =
+static struct lockdep_map __fs_reclaim_map =
         STATIC_LOCKDEP_MAP_INIT("fs_reclaim", &__fs_reclaim_map);
 
 static bool __need_fs_reclaim(gfp_t gfp_mask)
@@ -3726,17 +3726,27 @@ static bool __need_fs_reclaim(gfp_t gfp_mask)
         return true;
 }
 
+void __fs_reclaim_acquire(void)
+{
+        lock_map_acquire(&__fs_reclaim_map);
+}
+
+void __fs_reclaim_release(void)
+{
+        lock_map_release(&__fs_reclaim_map);
+}
+
 void fs_reclaim_acquire(gfp_t gfp_mask)
 {
         if (__need_fs_reclaim(gfp_mask))
-                lock_map_acquire(&__fs_reclaim_map);
+                __fs_reclaim_acquire();
 }
 EXPORT_SYMBOL_GPL(fs_reclaim_acquire);
 
 void fs_reclaim_release(gfp_t gfp_mask)
 {
         if (__need_fs_reclaim(gfp_mask))
-                lock_map_release(&__fs_reclaim_map);
+                __fs_reclaim_release();
 }
 EXPORT_SYMBOL_GPL(fs_reclaim_release);
 #endif
@@ -3754,8 +3764,8 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order,
 
         /* We now go into synchronous reclaim */
         cpuset_memory_pressure_bump();
-        noreclaim_flag = memalloc_noreclaim_save();
         fs_reclaim_acquire(gfp_mask);
+        noreclaim_flag = memalloc_noreclaim_save();
         reclaim_state.reclaimed_slab = 0;
         current->reclaim_state = &reclaim_state;
 
@@ -3763,8 +3773,8 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order,
                                                                 ac->nodemask);
 
         current->reclaim_state = NULL;
-        fs_reclaim_release(gfp_mask);
         memalloc_noreclaim_restore(noreclaim_flag);
+        fs_reclaim_release(gfp_mask);
 
         cond_resched();