mm: charge/uncharge kmemcg from generic page allocator paths

Currently, to charge a non-slab allocation to kmemcg one has to use
alloc_kmem_pages helper with __GFP_ACCOUNT flag.  A page allocated with
this helper should finally be freed using free_kmem_pages, otherwise it
won't be uncharged.

This API suits its current users fine, but it turns out to be impossible
to use along with page reference counting, i.e.  when an allocation is
supposed to be freed with put_page, as it is the case with pipe or unix
socket buffers.

To overcome this limitation, this patch moves charging/uncharging to
generic page allocator paths, i.e.  to __alloc_pages_nodemask and
free_pages_prepare, and zaps alloc/free_kmem_pages helpers.  This way,
one can use any of the available page allocation functions to get the
allocated page charged to kmemcg - it's enough to pass __GFP_ACCOUNT,
just like in case of kmalloc and friends.  A charged page will be
automatically uncharged on free.

To make it possible, we need to mark pages charged to kmemcg somehow.
To avoid introducing a new page flag, we make use of page->_mapcount for
marking such pages.  Since pages charged to kmemcg are not supposed to
be mapped to userspace, it should work just fine.  There are other
(ab)users of page->_mapcount - buddy and balloon pages - but we don't
conflict with them.

In case kmemcg is compiled out or not used at runtime, this patch
introduces no overhead to generic page allocator paths.  If kmemcg is
used, it will be plus one gfp flags check on alloc and plus one
page->_mapcount check on free, which shouldn't hurt performance, because
the data accessed are hot.

Link: http://lkml.kernel.org/r/a9736d856f895bcb465d9f257b54efe32eda6f99.1464079538.git.vdavydov@virtuozzo.com
Signed-off-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 8 insertions, 9 deletions

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 570383a41853..c29e9d347bc6 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -78,8 +78,7 @@ struct vm_area_struct;
  * __GFP_THISNODE forces the allocation to be satisified from the requested
  *   node with no fallbacks or placement policy enforcements.
  *
- * __GFP_ACCOUNT causes the allocation to be accounted to kmemcg (only relevant
- *   to kmem allocations).
+ * __GFP_ACCOUNT causes the allocation to be accounted to kmemcg.
  */
 #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE)
 #define __GFP_WRITE	((__force gfp_t)___GFP_WRITE)
@@ -486,10 +485,6 @@ extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order,
 #define alloc_page_vma_node(gfp_mask, vma, addr, node)		\
 	alloc_pages_vma(gfp_mask, 0, vma, addr, node, false)
 
-extern struct page *alloc_kmem_pages(gfp_t gfp_mask, unsigned int order);
-extern struct page *alloc_kmem_pages_node(int nid, gfp_t gfp_mask,
-					  unsigned int order);
-
 extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order);
 extern unsigned long get_zeroed_page(gfp_t gfp_mask);
 
@@ -513,9 +508,6 @@ extern void *__alloc_page_frag(struct page_frag_cache *nc,
 			       unsigned int fragsz, gfp_t gfp_mask);
 extern void __free_page_frag(void *addr);
 
-extern void __free_kmem_pages(struct page *page, unsigned int order);
-extern void free_kmem_pages(unsigned long addr, unsigned int order);
-
 #define __free_page(page) __free_pages((page), 0)
 #define free_page(addr) free_pages((addr), 0)
 
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 96084ee74ee8..7c8e82ac2eb7 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -641,6 +641,13 @@ PAGE_MAPCOUNT_OPS(Buddy, BUDDY)
 #define PAGE_BALLOON_MAPCOUNT_VALUE		(-256)
 PAGE_MAPCOUNT_OPS(Balloon, BALLOON)
 
+/*
+ * If kmemcg is enabled, the buddy allocator will set PageKmemcg() on
+ * pages allocated with __GFP_ACCOUNT. It gets cleared on page free.
+ */
+#define PAGE_KMEMCG_MAPCOUNT_VALUE		(-512)
+PAGE_MAPCOUNT_OPS(Kmemcg, KMEMCG)
+
 extern bool is_free_buddy_page(struct page *page);
 
 __PAGEFLAG(Isolated, isolated, PF_ANY);