mm: emit the "free" trace report before freeing memory in kmem_cache_free()

After the memory is freed, it can be immediately allocated by other
CPUs, before the "free" trace report has been emitted.  This causes
inaccurate traces.

For example, if the following sequence of events occurs:

    CPU 0                 CPU 1

  (1) alloc xxxxxx
  (2) free  xxxxxx
                         (3) alloc xxxxxx
                         (4) free  xxxxxx

Then they will be inaccurately reported via tracing, so that they appear
to have happened in this order:

    CPU 0                 CPU 1

  (1) alloc xxxxxx
                         (2) alloc xxxxxx
  (3) free  xxxxxx
                         (4) free  xxxxxx

This makes it look like CPU 1 somehow managed to allocate memory that
CPU 0 still had allocated for itself.

In order to avoid this, emit the "free xxxxxx" tracing report just
before the actual call to free the memory, instead of just after it.

Link: https://lkml.kernel.org/r/374eb75d-7404-8721-4e1e-65b0e5b17279@huawei.com
Signed-off-by: Yunfeng Ye <yeyunfeng@huawei.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 3 insertions, 5 deletions

diff --git a/mm/slab.c b/mm/slab.c
index da132a9ae6f8..ca4822f6b2b6 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3733,14 +3733,13 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp)
 	if (!cachep)
 		return;
 
+	trace_kmem_cache_free(_RET_IP_, objp, cachep->name);
 	local_irq_save(flags);
 	debug_check_no_locks_freed(objp, cachep->object_size);
 	if (!(cachep->flags & SLAB_DEBUG_OBJECTS))
 		debug_check_no_obj_freed(objp, cachep->object_size);
 	__cache_free(cachep, objp, _RET_IP_);
 	local_irq_restore(flags);
-
-	trace_kmem_cache_free(_RET_IP_, objp, cachep->name);
 }
 EXPORT_SYMBOL(kmem_cache_free);
 
diff --git a/mm/slob.c b/mm/slob.c
index 74d3f6e60666..03deee1e6a94 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -666,6 +666,7 @@ static void kmem_rcu_free(struct rcu_head *head)
 void kmem_cache_free(struct kmem_cache *c, void *b)
 {
 	kmemleak_free_recursive(b, c->flags);
+	trace_kmem_cache_free(_RET_IP_, b, c->name);
 	if (unlikely(c->flags & SLAB_TYPESAFE_BY_RCU)) {
 		struct slob_rcu *slob_rcu;
 		slob_rcu = b + (c->size - sizeof(struct slob_rcu));
@@ -674,8 +675,6 @@ void kmem_cache_free(struct kmem_cache *c, void *b)
 	} else {
 		__kmem_cache_free(b, c->size);
 	}
-
-	trace_kmem_cache_free(_RET_IP_, b, c->name);
 }
 EXPORT_SYMBOL(kmem_cache_free);
 
diff --git a/mm/slub.c b/mm/slub.c
index f7368bfffb7a..a8626825a829 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3526,8 +3526,8 @@ void kmem_cache_free(struct kmem_cache *s, void *x)
 	s = cache_from_obj(s, x);
 	if (!s)
 		return;
-	slab_free(s, virt_to_head_page(x), x, NULL, 1, _RET_IP_);
 	trace_kmem_cache_free(_RET_IP_, x, s->name);
+	slab_free(s, virt_to_head_page(x), x, NULL, 1, _RET_IP_);
 }
 EXPORT_SYMBOL(kmem_cache_free);