mm: allocate kernel pages to the right memcg
When a process tries to allocate a page with the __GFP_KMEMCG flag, the
page allocator will call the corresponding memcg functions to validate
the allocation. Tasks in the root memcg can always proceed.
To avoid adding markers to the page - and a kmem flag that would
necessarily follow, as much as doing page_cgroup lookups for no reason,
whoever is marking its allocations with __GFP_KMEMCG flag is responsible
for telling the page allocator that this is such an allocation at
free_pages() time. This is done by the invocation of
__free_accounted_pages() and free_accounted_pages().
Signed-off-by: Glauber Costa <glommer@parallels.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Mel Gorman <mgorman@suse.de>
Acked-by: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Suleiman Souhlal <suleiman@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Frederic Weisbecker <fweisbec@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: JoonSoo Kim <js1304@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 62496ed..2ad2ad1 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2612,6 +2612,7 @@
int migratetype = allocflags_to_migratetype(gfp_mask);
unsigned int cpuset_mems_cookie;
int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET;
+ struct mem_cgroup *memcg = NULL;
gfp_mask &= gfp_allowed_mask;
@@ -2630,6 +2631,13 @@
if (unlikely(!zonelist->_zonerefs->zone))
return NULL;
+ /*
+ * Will only have any effect when __GFP_KMEMCG is set. This is
+ * verified in the (always inline) callee
+ */
+ if (!memcg_kmem_newpage_charge(gfp_mask, &memcg, order))
+ return NULL;
+
retry_cpuset:
cpuset_mems_cookie = get_mems_allowed();
@@ -2665,6 +2673,8 @@
if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
goto retry_cpuset;
+ memcg_kmem_commit_charge(page, memcg, order);
+
return page;
}
EXPORT_SYMBOL(__alloc_pages_nodemask);
@@ -2717,6 +2727,31 @@
EXPORT_SYMBOL(free_pages);
+/*
+ * __free_memcg_kmem_pages and free_memcg_kmem_pages will free
+ * pages allocated with __GFP_KMEMCG.
+ *
+ * Those pages are accounted to a particular memcg, embedded in the
+ * corresponding page_cgroup. To avoid adding a hit in the allocator to search
+ * for that information only to find out that it is NULL for users who have no
+ * interest in that whatsoever, we provide these functions.
+ *
+ * The caller knows better which flags it relies on.
+ */
+void __free_memcg_kmem_pages(struct page *page, unsigned int order)
+{
+ memcg_kmem_uncharge_pages(page, order);
+ __free_pages(page, order);
+}
+
+void free_memcg_kmem_pages(unsigned long addr, unsigned int order)
+{
+ if (addr != 0) {
+ VM_BUG_ON(!virt_addr_valid((void *)addr));
+ __free_memcg_kmem_pages(virt_to_page((void *)addr), order);
+ }
+}
+
static void *make_alloc_exact(unsigned long addr, unsigned order, size_t size)
{
if (addr) {