summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJoonsoo Kim <js1304@gmail.com>2012-09-17 14:09:09 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2012-09-17 15:00:38 -0700
commit8ba00bb68a067c221cc3ea3a0293e8fcbdcb7ba1 (patch)
tree6642f9819b79c51891d7f829c5cf1f384ffc6cc5
parentd014dc2ed4fae84cb92509416c8bfc9078d4f0d9 (diff)
slub: consider pfmemalloc_match() in get_partial_node()
get_partial() is currently not checking pfmemalloc_match() meaning that it is possible for pfmemalloc pages to leak to non-pfmemalloc users. This is a problem in the following situation. Assume that there is a request from normal allocation and there are no objects in the per-cpu cache and no node-partial slab. In this case, slab_alloc enters the slow path and new_slab_objects() is called which may return a PFMEMALLOC page. As the current user is not allowed to access PFMEMALLOC page, deactivate_slab() is called ([5091b74a: mm: slub: optimise the SLUB fast path to avoid pfmemalloc checks]) and returns an object from PFMEMALLOC page. Next time, when we get another request from normal allocation, slab_alloc() enters the slow-path and calls new_slab_objects(). In new_slab_objects(), we call get_partial() and get a partial slab which was just deactivated but is a pfmemalloc page. We extract one object from it and re-deactivate. "deactivate -> re-get in get_partial -> re-deactivate" occures repeatedly. As a result, access to PFMEMALLOC page is not properly restricted and it can cause a performance degradation due to frequent deactivation. deactivation frequently. This patch changes get_partial_node() to take pfmemalloc_match() into account and prevents the "deactivate -> re-get in get_partial() scenario. Instead, new_slab() is called. Signed-off-by: Joonsoo Kim <js1304@gmail.com> Acked-by: David Rientjes <rientjes@google.com> Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: David Miller <davem@davemloft.net> Cc: Chuck Lever <chuck.lever@oracle.com> Cc: Pekka Enberg <penberg@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--mm/slub.c15
1 files changed, 10 insertions, 5 deletions
diff --git a/mm/slub.c b/mm/slub.c
index 8f78e2577031..2fdd96f9e998 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1524,12 +1524,13 @@ static inline void *acquire_slab(struct kmem_cache *s,
}
static int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain);
+static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags);
/*
* Try to allocate a partial slab from a specific node.
*/
-static void *get_partial_node(struct kmem_cache *s,
- struct kmem_cache_node *n, struct kmem_cache_cpu *c)
+static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
+ struct kmem_cache_cpu *c, gfp_t flags)
{
struct page *page, *page2;
void *object = NULL;
@@ -1545,9 +1546,13 @@ static void *get_partial_node(struct kmem_cache *s,
spin_lock(&n->list_lock);
list_for_each_entry_safe(page, page2, &n->partial, lru) {
- void *t = acquire_slab(s, n, page, object == NULL);
+ void *t;
int available;
+ if (!pfmemalloc_match(page, flags))
+ continue;
+
+ t = acquire_slab(s, n, page, object == NULL);
if (!t)
break;
@@ -1614,7 +1619,7 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
n->nr_partial > s->min_partial) {
- object = get_partial_node(s, n, c);
+ object = get_partial_node(s, n, c, flags);
if (object) {
/*
* Return the object even if
@@ -1643,7 +1648,7 @@ static void *get_partial(struct kmem_cache *s, gfp_t flags, int node,
void *object;
int searchnode = (node == NUMA_NO_NODE) ? numa_node_id() : node;
- object = get_partial_node(s, get_node(s, searchnode), c);
+ object = get_partial_node(s, get_node(s, searchnode), c, flags);
if (object || node != NUMA_NO_NODE)
return object;